Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage VLLMUploader
Starting job with name chaiml-muster-v2-q235b-77862-v1-uploader
Waiting for job on chaiml-muster-v2-q235b-77862-v1-uploader to finish
chaiml-muster-v2-q235b-77862-v1-uploader: Using quantization_mode: w4a16
chaiml-muster-v2-q235b-77862-v1-uploader: Checking if ChaiML/muster-v2-q235b-lr1e4ep2r64g4-W4A16 already exists in ChaiML
chaiml-muster-v2-q235b-77862-v1-uploader: Downloading snapshot of ChaiML/muster-v2-q235b-lr1e4ep2r64g4...
HTTP Request: %s %s "%s %d %s"
chaiml-muster-v2-q235b-77862-v1-uploader: 
Fetching 107 files:   0%|          | 0/107 [00:00<?, ?it/s]
Fetching 107 files:   1%|          | 1/107 [00:00<00:34,  3.07it/s]
Fetching 107 files:   7%|▋         | 8/107 [00:13<02:52,  1.74s/it]
Fetching 107 files:   8%|▊         | 9/107 [00:14<02:41,  1.65s/it]
Fetching 107 files:  11%|█         | 12/107 [00:15<01:43,  1.08s/it]
Fetching 107 files:  15%|█▍        | 16/107 [00:26<02:44,  1.80s/it]
Fetching 107 files:  16%|█▌        | 17/107 [00:27<02:36,  1.74s/it]
Fetching 107 files:  21%|██        | 22/107 [00:28<01:18,  1.09it/s]
Fetching 107 files:  22%|██▏       | 24/107 [00:37<02:24,  1.74s/it]
Fetching 107 files:  23%|██▎       | 25/107 [00:38<02:13,  1.63s/it]
Fetching 107 files:  24%|██▍       | 26/107 [00:39<02:01,  1.49s/it]
Fetching 107 files:  25%|██▌       | 27/107 [00:39<01:41,  1.26s/it]
Fetching 107 files:  26%|██▌       | 28/107 [00:40<01:36,  1.22s/it]
Fetching 107 files:  28%|██▊       | 30/107 [00:41<01:07,  1.14it/s]
Fetching 107 files:  29%|██▉       | 31/107 [00:41<00:56,  1.34it/s]
Fetching 107 files:  30%|██▉       | 32/107 [00:49<03:01,  2.42s/it]
Fetching 107 files:  31%|███       | 33/107 [00:50<02:28,  2.01s/it]
Fetching 107 files:  32%|███▏      | 34/107 [00:51<02:25,  2.00s/it]
Fetching 107 files:  34%|███▎      | 36/107 [00:53<01:42,  1.44s/it]
Fetching 107 files:  35%|███▍      | 37/107 [00:54<01:30,  1.29s/it]
Fetching 107 files:  36%|███▌      | 38/107 [00:54<01:09,  1.01s/it]
Fetching 107 files:  37%|███▋      | 40/107 [01:00<02:09,  1.94s/it]
Fetching 107 files:  38%|███▊      | 41/107 [01:02<01:58,  1.80s/it]
Fetching 107 files:  39%|███▉      | 42/107 [01:05<02:19,  2.15s/it]
Fetching 107 files:  41%|████      | 44/107 [01:06<01:34,  1.51s/it]
Fetching 107 files:  42%|████▏     | 45/107 [01:07<01:28,  1.43s/it]
Fetching 107 files:  44%|████▍     | 47/107 [01:08<01:00,  1.01s/it]
Fetching 107 files:  45%|████▍     | 48/107 [01:13<01:46,  1.81s/it]
Fetching 107 files:  46%|████▌     | 49/107 [01:14<01:45,  1.82s/it]
Fetching 107 files:  47%|████▋     | 50/107 [01:17<02:00,  2.11s/it]
Fetching 107 files:  48%|████▊     | 51/107 [01:18<01:29,  1.61s/it]
Fetching 107 files:  49%|████▊     | 52/107 [01:18<01:11,  1.29s/it]
Fetching 107 files:  50%|████▉     | 53/107 [01:20<01:13,  1.35s/it]
Fetching 107 files:  50%|█████     | 54/107 [01:20<00:58,  1.11s/it]
Fetching 107 files:  51%|█████▏    | 55/107 [01:21<00:54,  1.05s/it]
Fetching 107 files:  52%|█████▏    | 56/107 [01:25<01:43,  2.03s/it]
Fetching 107 files:  53%|█████▎    | 57/107 [01:27<01:28,  1.76s/it]
Fetching 107 files:  54%|█████▍    | 58/107 [01:31<02:09,  2.64s/it]
Fetching 107 files:  56%|█████▌    | 60/107 [01:31<01:09,  1.47s/it]
Fetching 107 files:  57%|█████▋    | 61/107 [01:32<00:58,  1.27s/it]
Fetching 107 files:  58%|█████▊    | 62/107 [01:33<00:49,  1.10s/it]
Fetching 107 files:  59%|█████▉    | 63/107 [01:34<00:46,  1.05s/it]
Fetching 107 files:  60%|█████▉    | 64/107 [01:48<03:23,  4.74s/it]
Fetching 107 files:  63%|██████▎   | 67/107 [01:48<01:28,  2.21s/it]
Fetching 107 files:  67%|██████▋   | 72/107 [01:50<00:40,  1.16s/it]
Fetching 107 files:  68%|██████▊   | 73/107 [01:54<00:55,  1.63s/it]
Fetching 107 files:  69%|██████▉   | 74/107 [01:56<00:55,  1.69s/it]
Fetching 107 files:  70%|███████   | 75/107 [01:57<00:48,  1.52s/it]
Fetching 107 files:  71%|███████   | 76/107 [02:00<00:55,  1.79s/it]
Fetching 107 files:  73%|███████▎  | 78/107 [02:00<00:34,  1.19s/it]
Fetching 107 files:  74%|███████▍  | 79/107 [02:02<00:36,  1.31s/it]
Fetching 107 files:  75%|███████▍  | 80/107 [02:03<00:33,  1.25s/it]
Fetching 107 files:  76%|███████▌  | 81/107 [02:06<00:40,  1.56s/it]
Fetching 107 files:  77%|███████▋  | 82/107 [02:08<00:43,  1.73s/it]
Fetching 107 files:  78%|███████▊  | 83/107 [02:09<00:38,  1.60s/it]
Fetching 107 files:  79%|███████▊  | 84/107 [02:11<00:38,  1.66s/it]
Fetching 107 files:  79%|███████▉  | 85/107 [02:12<00:32,  1.49s/it]
Fetching 107 files:  80%|████████  | 86/107 [02:21<01:19,  3.78s/it]
Fetching 107 files:  85%|████████▌ | 91/107 [02:22<00:20,  1.28s/it]
Fetching 107 files:  86%|████████▌ | 92/107 [02:24<00:20,  1.39s/it]
Fetching 107 files:  87%|████████▋ | 93/107 [02:25<00:19,  1.39s/it]
Fetching 107 files:  88%|████████▊ | 94/107 [02:29<00:24,  1.85s/it]
Fetching 107 files:  89%|████████▉ | 95/107 [02:31<00:23,  1.99s/it]
Fetching 107 files:  90%|████████▉ | 96/107 [02:33<00:22,  2.01s/it]
Fetching 107 files:  91%|█████████ | 97/107 [02:34<00:16,  1.61s/it]
Fetching 107 files:  92%|█████████▏| 98/107 [02:34<00:12,  1.37s/it]
Fetching 107 files:  93%|█████████▎| 100/107 [02:35<00:06,  1.05it/s]
Fetching 107 files:  94%|█████████▍| 101/107 [02:37<00:06,  1.09s/it]
Fetching 107 files: 100%|██████████| 107/107 [02:37<00:00,  1.47s/it]
chaiml-muster-v2-q235b-77862-v1-uploader: Downloaded in 157.391s
chaiml-muster-v2-q235b-77862-v1-uploader: Applying quantization...
chaiml-muster-v2-q235b-77862-v1-uploader: 2026-02-09 19:37:47 WARNING modeling_utils.py L4670: `torch_dtype` is deprecated! Use `dtype` instead!
chaiml-muster-v2-q235b-77862-v1-uploader: 
Loading checkpoint shards:   0%|          | 0/95 [00:00<?, ?it/s]
Loading checkpoint shards:   6%|▋         | 6/95 [00:00<00:01, 50.23it/s]
Loading checkpoint shards:  13%|█▎        | 12/95 [00:00<00:01, 49.14it/s]
Loading checkpoint shards:  18%|█▊        | 17/95 [00:00<00:01, 49.09it/s]
Loading checkpoint shards:  23%|██▎       | 22/95 [00:00<00:01, 48.97it/s]
Loading checkpoint shards:  28%|██▊       | 27/95 [00:00<00:01, 48.92it/s]
Loading checkpoint shards:  34%|███▎      | 32/95 [00:00<00:01, 48.96it/s]
Loading checkpoint shards:  39%|███▉      | 37/95 [00:00<00:01, 48.79it/s]
Loading checkpoint shards:  44%|████▍     | 42/95 [00:00<00:01, 48.59it/s]
Loading checkpoint shards:  49%|████▉     | 47/95 [00:00<00:00, 48.50it/s]
Loading checkpoint shards:  55%|█████▍    | 52/95 [00:01<00:00, 48.55it/s]
Loading checkpoint shards:  60%|██████    | 57/95 [00:01<00:00, 47.68it/s]
Loading checkpoint shards:  65%|██████▌   | 62/95 [00:01<00:00, 48.13it/s]
Loading checkpoint shards:  71%|███████   | 67/95 [00:01<00:00, 48.04it/s]
Loading checkpoint shards:  76%|███████▌  | 72/95 [00:01<00:00, 48.32it/s]
Loading checkpoint shards:  81%|████████  | 77/95 [00:01<00:00, 48.40it/s]
Loading checkpoint shards:  86%|████████▋ | 82/95 [00:01<00:00, 48.49it/s]
Loading checkpoint shards:  92%|█████████▏| 87/95 [00:01<00:00, 48.51it/s]
Loading checkpoint shards:  97%|█████████▋| 92/95 [00:01<00:00, 48.54it/s]
Loading checkpoint shards: 100%|██████████| 95/95 [00:01<00:00, 49.07it/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 2026-02-09 19:37:57 INFO base.py L366: using torch.bfloat16 for quantization tuning
chaiml-muster-v2-q235b-77862-v1-uploader: 
Generating train split:   0%|          | 0/10000 [00:00<?, ? examples/s]
Generating train split: 100%|██████████| 10000/10000 [00:00<00:00, 58186.34 examples/s]
Generating train split: 100%|██████████| 10000/10000 [00:00<00:00, 57594.29 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
Map:   0%|          | 0/10000 [00:00<?, ? examples/s]
Map:  10%|█         | 1000/10000 [00:00<00:04, 2120.98 examples/s]
Map:  20%|██        | 2000/10000 [00:01<00:04, 1790.27 examples/s]
Map:  30%|███       | 3000/10000 [00:05<00:16, 431.94 examples/s] 
Map:  40%|████      | 4000/10000 [00:05<00:09, 633.29 examples/s]
Map:  50%|█████     | 5000/10000 [00:06<00:05, 837.72 examples/s]
Map:  60%|██████    | 6000/10000 [00:06<00:03, 1061.34 examples/s]
Map:  70%|███████   | 7000/10000 [00:07<00:02, 1047.70 examples/s]
Map:  80%|████████  | 8000/10000 [00:08<00:01, 1168.36 examples/s]
Map:  90%|█████████ | 9000/10000 [00:09<00:00, 1317.30 examples/s]
Map: 100%|██████████| 10000/10000 [00:09<00:00, 1271.25 examples/s]
Map: 100%|██████████| 10000/10000 [00:09<00:00, 1005.98 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
Filter:   0%|          | 0/10000 [00:00<?, ? examples/s]
Filter:  10%|█         | 1000/10000 [00:00<00:03, 2794.22 examples/s]
Filter:  20%|██        | 2000/10000 [00:00<00:02, 2837.71 examples/s]
Filter:  30%|███       | 3000/10000 [00:01<00:02, 2820.70 examples/s]
Filter:  40%|████      | 4000/10000 [00:01<00:02, 2882.94 examples/s]
Filter:  50%|█████     | 5000/10000 [00:01<00:01, 2887.56 examples/s]
Filter:  60%|██████    | 6000/10000 [00:02<00:01, 2907.92 examples/s]
Filter:  70%|███████   | 7000/10000 [00:02<00:01, 2898.31 examples/s]
Filter:  80%|████████  | 8000/10000 [00:02<00:00, 2892.46 examples/s]
Filter:  90%|█████████ | 9000/10000 [00:03<00:00, 2923.69 examples/s]
Filter: 100%|██████████| 10000/10000 [00:03<00:00, 2975.13 examples/s]
Filter: 100%|██████████| 10000/10000 [00:03<00:00, 2910.44 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
Casting the dataset:   0%|          | 0/1216 [00:00<?, ? examples/s]
Casting the dataset:  82%|████████▏ | 1000/1216 [00:01<00:00, 523.83 examples/s]
Casting the dataset: 100%|██████████| 1216/1216 [00:02<00:00, 526.10 examples/s]
Casting the dataset: 100%|██████████| 1216/1216 [00:02<00:00, 524.95 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
Map:   0%|          | 0/10000 [00:00<?, ? examples/s]
Map:  10%|█         | 1000/10000 [00:00<00:05, 1535.91 examples/s]
Map:  20%|██        | 2000/10000 [00:01<00:04, 1642.54 examples/s]
Map:  30%|███       | 3000/10000 [00:03<00:11, 635.62 examples/s] 
Map:  40%|████      | 4000/10000 [00:04<00:06, 885.54 examples/s]
Map:  50%|█████     | 5000/10000 [00:04<00:04, 1110.68 examples/s]
Map:  60%|██████    | 6000/10000 [00:05<00:03, 1320.69 examples/s]
Map:  70%|███████   | 7000/10000 [00:06<00:02, 1205.44 examples/s]
Map:  80%|████████  | 8000/10000 [00:06<00:01, 1305.45 examples/s]
Map:  90%|█████████ | 9000/10000 [00:07<00:00, 1406.85 examples/s]
Map: 100%|██████████| 10000/10000 [00:08<00:00, 1388.50 examples/s]
Map: 100%|██████████| 10000/10000 [00:08<00:00, 1201.51 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
Filter:   0%|          | 0/10000 [00:00<?, ? examples/s]
Filter:  10%|█         | 1000/10000 [00:00<00:03, 2925.28 examples/s]
Filter:  20%|██        | 2000/10000 [00:00<00:02, 3005.99 examples/s]
Filter:  30%|███       | 3000/10000 [00:01<00:02, 2931.03 examples/s]
Filter:  40%|████      | 4000/10000 [00:01<00:02, 2953.63 examples/s]
Filter:  50%|█████     | 5000/10000 [00:01<00:01, 2929.56 examples/s]
Filter:  60%|██████    | 6000/10000 [00:02<00:01, 2925.28 examples/s]
Filter:  70%|███████   | 7000/10000 [00:02<00:01, 2913.38 examples/s]
Filter:  80%|████████  | 8000/10000 [00:02<00:00, 2914.97 examples/s]
Filter:  90%|█████████ | 9000/10000 [00:03<00:00, 2939.29 examples/s]
Filter: 100%|██████████| 10000/10000 [00:03<00:00, 2983.12 examples/s]
Filter: 100%|██████████| 10000/10000 [00:03<00:00, 2948.84 examples/s]
HTTP Request: %s %s "%s %d %s"
chaiml-muster-v2-q235b-77862-v1-uploader: 
Casting the dataset:   0%|          | 0/1216 [00:00<?, ? examples/s]
Casting the dataset:  82%|████████▏ | 1000/1216 [00:01<00:00, 526.20 examples/s]
Casting the dataset: 100%|██████████| 1216/1216 [00:02<00:00, 529.93 examples/s]
Casting the dataset: 100%|██████████| 1216/1216 [00:02<00:00, 528.47 examples/s]
chaiml-muster-v2-q235b-77862-v1-uploader: 
  0%|          | 0/94 [00:00<?, ?it/s]
Quantizing model.layers.0:   0%|          | 0/94 [00:00<?, ?it/s]/usr/local/lib/python3.12/dist-packages/torch/backends/cuda/__init__.py:131: UserWarning: Please use the new API settings to control TF32 behavior, such as torch.backends.cudnn.conv.fp32_precision = 'tf32' or torch.backends.cuda.matmul.fp32_precision = 'ieee'. Old settings, e.g, torch.backends.cuda.matmul.allow_tf32 = True, torch.backends.cudnn.allow_tf32 = True, allowTF32CuDNN() and allowTF32CuBLAS() will be deprecated after Pytorch 2.9. Please see https://pytorch.org/docs/main/notes/cuda.html#tensorfloat-32-tf32-on-ampere-and-later-devices (Triggered internally at /pytorch/aten/src/ATen/Context.cpp:80.)
chaiml-muster-v2-q235b-77862-v1-uploader:   return torch._C._get_cublas_allow_tf32()
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:38:58.830000 7 torch/_dynamo/convert_frame.py:1358] [6/8] torch._dynamo hit config.recompile_limit (8)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:38:58.830000 7 torch/_dynamo/convert_frame.py:1358] [6/8]    function: 'forward' (/usr/local/lib/python3.12/dist-packages/transformers/models/qwen3_moe/modeling_qwen3_moe.py:208)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:38:58.830000 7 torch/_dynamo/convert_frame.py:1358] [6/8]    last reason: 6/7: self._modules['up_proj'].imatrix_cnt == 1351             # module.imatrix_cnt += input.shape[0]  # auto_round/compressors/base.py:1179 in get_imatrix_hook (HINT: torch.compile considers integer attributes of the nn.Module to be static. If you are observing recompilation, you might want to make this integer dynamic using torch._dynamo.config.allow_unspec_int_on_nn_module = True, or convert this integer into a tensor.)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:38:58.830000 7 torch/_dynamo/convert_frame.py:1358] [6/8] To log all recompilation reasons, use TORCH_LOGS="recompiles".
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:38:58.830000 7 torch/_dynamo/convert_frame.py:1358] [6/8] To diagnose recompilation issues, see https://pytorch.org/docs/main/torch.compiler_troubleshooting.html
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:39:01.694000 7 torch/_dynamo/convert_frame.py:1358] [3/8] torch._dynamo hit config.recompile_limit (8)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:39:01.694000 7 torch/_dynamo/convert_frame.py:1358] [3/8]    function: 'forward' (/usr/local/lib/python3.12/dist-packages/transformers/models/qwen3_moe/modeling_qwen3_moe.py:305)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:39:01.694000 7 torch/_dynamo/convert_frame.py:1358] [3/8]    last reason: 3/7: self._modules['self_attn']._modules['k_proj'].imatrix_cnt == 56  # module.imatrix_cnt += input.shape[0]  # auto_round/compressors/base.py:1179 in get_imatrix_hook (HINT: torch.compile considers integer attributes of the nn.Module to be static. If you are observing recompilation, you might want to make this integer dynamic using torch._dynamo.config.allow_unspec_int_on_nn_module = True, or convert this integer into a tensor.)
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:39:01.694000 7 torch/_dynamo/convert_frame.py:1358] [3/8] To log all recompilation reasons, use TORCH_LOGS="recompiles".
chaiml-muster-v2-q235b-77862-v1-uploader: W0209 19:39:01.694000 7 torch/_dynamo/convert_frame.py:1358] [3/8] To diagnose recompilation issues, see https://pytorch.org/docs/main/torch.compiler_troubleshooting.html
chaiml-muster-v2-q235b-77862-v1-uploader: 2026-02-09 19:39:19 WARNING gguf.py L297: please use more data via setting `nsamples` to improve accuracy as calibration activations contain 0
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Failed to get response for submission blend_beren_2026-01-30: ('http://chaiml-2a6f-69d4-linear-w01-v4-predictor.tenant-chaiml-guanaco.kchai-coreweave-us-east-04a.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:52026->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
HTTP Request: %s %s "%s %d %s"
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
chaiml-muster-v2-q235b-77862-v1-uploader: 
Quantizing model.layers.0:   1%|          | 1/94 [01:29<2:18:28, 89.34s/it]
Quantizing model.layers.1:   1%|          | 1/94 [01:29<2:18:28, 89.34s/it]
Quantizing model.layers.1:   2%|▏         | 2/94 [02:13<1:35:47, 62.48s/it]
Quantizing model.layers.2:   2%|▏         | 2/94 [02:13<1:35:47, 62.48s/it]
Quantizing model.layers.2:   3%|▎         | 3/94 [02:56<1:21:42, 53.88s/it]
Quantizing model.layers.3:   3%|▎         | 3/94 [02:56<1:21:42, 53.88s/it]
Quantizing model.layers.3:   4%|▍         | 4/94 [03:40<1:14:38, 49.76s/it]
Quantizing model.layers.4:   4%|▍         | 4/94 [03:40<1:14:38, 49.76s/it]
Quantizing model.layers.4:   5%|▌         | 5/94 [04:23<1:10:36, 47.60s/it]
Quantizing model.layers.5:   5%|▌         | 5/94 [04:23<1:10:36, 47.60s/it]
Quantizing model.layers.5:   6%|▋         | 6/94 [05:07<1:07:51, 46.27s/it]
Quantizing model.layers.6:   6%|▋         | 6/94 [05:07<1:07:51, 46.27s/it]
Quantizing model.layers.6:   7%|▋         | 7/94 [05:52<1:06:31, 45.88s/it]
Quantizing model.layers.7:   7%|▋         | 7/94 [05:52<1:06:31, 45.88s/it]
Quantizing model.layers.7:   9%|▊         | 8/94 [06:37<1:05:14, 45.52s/it]
Quantizing model.layers.8:   9%|▊         | 8/94 [06:37<1:05:14, 45.52s/it]
Quantizing model.layers.8:  10%|▉         | 9/94 [07:21<1:03:54, 45.11s/it]
Quantizing model.layers.9:  10%|▉         | 9/94 [07:21<1:03:54, 45.11s/it]
Quantizing model.layers.9:  11%|█         | 10/94 [08:05<1:02:40, 44.77s/it]
Quantizing model.layers.10:  11%|█         | 10/94 [08:05<1:02:40, 44.77s/it]
Quantizing model.layers.10:  12%|█▏        | 11/94 [08:49<1:01:41, 44.60s/it]
Quantizing model.layers.11:  12%|█▏        | 11/94 [08:49<1:01:41, 44.60s/it]
Quantizing model.layers.11:  13%|█▎        | 12/94 [09:33<1:00:44, 44.44s/it]
Quantizing model.layers.12:  13%|█▎        | 12/94 [09:33<1:00:44, 44.44s/it]
Quantizing model.layers.12:  14%|█▍        | 13/94 [10:18<59:52, 44.36s/it]  
Quantizing model.layers.13:  14%|█▍        | 13/94 [10:18<59:52, 44.36s/it]
Quantizing model.layers.13:  15%|█▍        | 14/94 [11:02<59:00, 44.26s/it]
Quantizing model.layers.14:  15%|█▍        | 14/94 [11:02<59:00, 44.26s/it]
Quantizing model.layers.14:  16%|█▌        | 15/94 [11:46<58:27, 44.40s/it]
Quantizing model.layers.15:  16%|█▌        | 15/94 [11:46<58:27, 44.40s/it]
Quantizing model.layers.15:  17%|█▋        | 16/94 [12:31<57:38, 44.33s/it]
Quantizing model.layers.16:  17%|█▋        | 16/94 [12:31<57:38, 44.33s/it]
Quantizing model.layers.16:  18%|█▊        | 17/94 [13:15<56:47, 44.25s/it]
Quantizing model.layers.17:  18%|█▊        | 17/94 [13:15<56:47, 44.25s/it]
Quantizing model.layers.17:  19%|█▉        | 18/94 [13:59<55:59, 44.20s/it]
Quantizing model.layers.18:  19%|█▉        | 18/94 [13:59<55:59, 44.20s/it]
Quantizing model.layers.18:  20%|██        | 19/94 [14:43<55:11, 44.15s/it]
Quantizing model.layers.19:  20%|██        | 19/94 [14:43<55:11, 44.15s/it]
Quantizing model.layers.19:  21%|██▏       | 20/94 [15:27<54:23, 44.10s/it]
Quantizing model.layers.20:  21%|██▏       | 20/94 [15:27<54:23, 44.10s/it]
Quantizing model.layers.20:  22%|██▏       | 21/94 [16:11<53:35, 44.05s/it]
Quantizing model.layers.21:  22%|██▏       | 21/94 [16:11<53:35, 44.05s/it]
Quantizing model.layers.21:  23%|██▎       | 22/94 [16:55<52:49, 44.03s/it]
Quantizing model.layers.22:  23%|██▎       | 22/94 [16:55<52:49, 44.03s/it]
Quantizing model.layers.22:  24%|██▍       | 23/94 [17:39<52:06, 44.03s/it]
Quantizing model.layers.23:  24%|██▍       | 23/94 [17:39<52:06, 44.03s/it]
Quantizing model.layers.23:  26%|██▌       | 24/94 [18:23<51:20, 44.00s/it]
Quantizing model.layers.24:  26%|██▌       | 24/94 [18:23<51:20, 44.00s/it]
Quantizing model.layers.24:  27%|██▋       | 25/94 [19:06<50:34, 43.98s/it]
Quantizing model.layers.25:  27%|██▋       | 25/94 [19:06<50:34, 43.98s/it]
Quantizing model.layers.25:  28%|██▊       | 26/94 [19:50<49:50, 43.97s/it]
Quantizing model.layers.26:  28%|██▊       | 26/94 [19:50<49:50, 43.97s/it]
Quantizing model.layers.26:  29%|██▊       | 27/94 [20:35<49:09, 44.02s/it]
Quantizing model.layers.27:  29%|██▊       | 27/94 [20:35<49:09, 44.02s/it]
Quantizing model.layers.27:  30%|██▉       | 28/94 [21:19<48:26, 44.03s/it]
Quantizing model.layers.28:  30%|██▉       | 28/94 [21:19<48:26, 44.03s/it]
Quantizing model.layers.28:  31%|███       | 29/94 [22:03<47:43, 44.06s/it]
Quantizing model.layers.29:  31%|███       | 29/94 [22:03<47:43, 44.06s/it]
Quantizing model.layers.29:  32%|███▏      | 30/94 [22:47<47:05, 44.14s/it]
Quantizing model.layers.30:  32%|███▏      | 30/94 [22:47<47:05, 44.14s/it]
Quantizing model.layers.30:  33%|███▎      | 31/94 [23:31<46:23, 44.17s/it]
Quantizing model.layers.31:  33%|███▎      | 31/94 [23:31<46:23, 44.17s/it]
Quantizing model.layers.31:  34%|███▍      | 32/94 [24:16<45:41, 44.21s/it]
Quantizing model.layers.32:  34%|███▍      | 32/94 [24:16<45:41, 44.21s/it]
Quantizing model.layers.32:  35%|███▌      | 33/94 [25:00<44:55, 44.18s/it]
Quantizing model.layers.33:  35%|███▌      | 33/94 [25:00<44:55, 44.18s/it]
Quantizing model.layers.33:  36%|███▌      | 34/94 [25:44<44:10, 44.17s/it]
Quantizing model.layers.34:  36%|███▌      | 34/94 [25:44<44:10, 44.17s/it]
Quantizing model.layers.34:  37%|███▋      | 35/94 [26:28<43:25, 44.16s/it]
Quantizing model.layers.35:  37%|███▋      | 35/94 [26:28<43:25, 44.16s/it]
Quantizing model.layers.35:  38%|███▊      | 36/94 [27:12<42:44, 44.22s/it]
Quantizing model.layers.36:  38%|███▊      | 36/94 [27:12<42:44, 44.22s/it]
Quantizing model.layers.36:  39%|███▉      | 37/94 [27:58<42:28, 44.72s/it]
Quantizing model.layers.37:  39%|███▉      | 37/94 [27:58<42:28, 44.72s/it]
Quantizing model.layers.37:  40%|████      | 38/94 [28:42<41:33, 44.53s/it]
Quantizing model.layers.38:  40%|████      | 38/94 [28:42<41:33, 44.53s/it]
Quantizing model.layers.38:  41%|████▏     | 39/94 [29:27<40:42, 44.41s/it]
Quantizing model.layers.39:  41%|████▏     | 39/94 [29:27<40:42, 44.41s/it]
Quantizing model.layers.39:  43%|████▎     | 40/94 [30:11<39:52, 44.31s/it]
Quantizing model.layers.40:  43%|████▎     | 40/94 [30:11<39:52, 44.31s/it]
Quantizing model.layers.40:  44%|████▎     | 41/94 [30:55<39:03, 44.22s/it]
Quantizing model.layers.41:  44%|████▎     | 41/94 [30:55<39:03, 44.22s/it]
Quantizing model.layers.41:  45%|████▍     | 42/94 [31:39<38:18, 44.21s/it]
Quantizing model.layers.42:  45%|████▍     | 42/94 [31:39<38:18, 44.21s/it]
Quantizing model.layers.42:  46%|████▌     | 43/94 [32:23<37:36, 44.24s/it]
Quantizing model.layers.43:  46%|████▌     | 43/94 [32:23<37:36, 44.24s/it]
Quantizing model.layers.43:  47%|████▋     | 44/94 [33:07<36:49, 44.18s/it]
Quantizing model.layers.44:  47%|████▋     | 44/94 [33:07<36:49, 44.18s/it]
Quantizing model.layers.44:  48%|████▊     | 45/94 [33:51<36:05, 44.19s/it]
Quantizing model.layers.45:  48%|████▊     | 45/94 [33:51<36:05, 44.19s/it]
Quantizing model.layers.45:  49%|████▉     | 46/94 [34:35<35:19, 44.15s/it]
Quantizing model.layers.46:  49%|████▉     | 46/94 [34:35<35:19, 44.15s/it]
Quantizing model.layers.46:  50%|█████     | 47/94 [35:19<34:34, 44.13s/it]
Quantizing model.layers.47:  50%|█████     | 47/94 [35:19<34:34, 44.13s/it]
Quantizing model.layers.47:  51%|█████     | 48/94 [36:04<33:50, 44.15s/it]
Quantizing model.layers.48:  51%|█████     | 48/94 [36:04<33:50, 44.15s/it]
Quantizing model.layers.48:  52%|█████▏    | 49/94 [36:48<33:08, 44.18s/it]
Quantizing model.layers.49:  52%|█████▏    | 49/94 [36:48<33:08, 44.18s/it]
Quantizing model.layers.49:  53%|█████▎    | 50/94 [37:32<32:26, 44.24s/it]
Quantizing model.layers.50:  53%|█████▎    | 50/94 [37:32<32:26, 44.24s/it]
Quantizing model.layers.50:  54%|█████▍    | 51/94 [38:17<31:44, 44.30s/it]
Quantizing model.layers.51:  54%|█████▍    | 51/94 [38:17<31:44, 44.30s/it]
Quantizing model.layers.51:  55%|█████▌    | 52/94 [39:01<31:02, 44.34s/it]
Quantizing model.layers.52:  55%|█████▌    | 52/94 [39:01<31:02, 44.34s/it]
Quantizing model.layers.52:  56%|█████▋    | 53/94 [39:46<30:18, 44.36s/it]
Quantizing model.layers.53:  56%|█████▋    | 53/94 [39:46<30:18, 44.36s/it]
Quantizing model.layers.53:  57%|█████▋    | 54/94 [40:30<29:30, 44.27s/it]
Quantizing model.layers.54:  57%|█████▋    | 54/94 [40:30<29:30, 44.27s/it]
Quantizing model.layers.54:  59%|█████▊    | 55/94 [41:14<28:45, 44.24s/it]
Quantizing model.layers.55:  59%|█████▊    | 55/94 [41:14<28:45, 44.24s/it]
Quantizing model.layers.55:  60%|█████▉    | 56/94 [41:59<28:10, 44.47s/it]
Quantizing model.layers.56:  60%|█████▉    | 56/94 [41:59<28:10, 44.47s/it]
Quantizing model.layers.56:  61%|██████    | 57/94 [42:43<27:24, 44.44s/it]
Quantizing model.layers.57:  61%|██████    | 57/94 [42:43<27:24, 44.44s/it]
Quantizing model.layers.57:  62%|██████▏   | 58/94 [43:27<26:38, 44.39s/it]
Quantizing model.layers.58:  62%|██████▏   | 58/94 [43:27<26:38, 44.39s/it]
Quantizing model.layers.58:  63%|██████▎   | 59/94 [44:12<25:51, 44.33s/it]
Quantizing model.layers.59:  63%|██████▎   | 59/94 [44:12<25:51, 44.33s/it]
Quantizing model.layers.59:  64%|██████▍   | 60/94 [44:56<25:06, 44.30s/it]
Quantizing model.layers.60:  64%|██████▍   | 60/94 [44:56<25:06, 44.30s/it]
Quantizing model.layers.60:  65%|██████▍   | 61/94 [45:40<24:19, 44.24s/it]
Quantizing model.layers.61:  65%|██████▍   | 61/94 [45:40<24:19, 44.24s/it]
Quantizing model.layers.61:  66%|██████▌   | 62/94 [46:24<23:37, 44.29s/it]
Quantizing model.layers.62:  66%|██████▌   | 62/94 [46:24<23:37, 44.29s/it]
Quantizing model.layers.62:  67%|██████▋   | 63/94 [47:09<22:54, 44.34s/it]
Quantizing model.layers.63:  67%|██████▋   | 63/94 [47:09<22:54, 44.34s/it]
Quantizing model.layers.63:  68%|██████▊   | 64/94 [47:53<22:09, 44.30s/it]
Quantizing model.layers.64:  68%|██████▊   | 64/94 [47:53<22:09, 44.30s/it]
Quantizing model.layers.64:  69%|██████▉   | 65/94 [48:37<21:23, 44.25s/it]
Quantizing model.layers.65:  69%|██████▉   | 65/94 [48:37<21:23, 44.25s/it]
Quantizing model.layers.65:  70%|███████   | 66/94 [49:21<20:36, 44.18s/it]
Quantizing model.layers.66:  70%|███████   | 66/94 [49:21<20:36, 44.18s/it]
Quantizing model.layers.66:  71%|███████▏  | 67/94 [50:05<19:52, 44.16s/it]
Quantizing model.layers.67:  71%|███████▏  | 67/94 [50:05<19:52, 44.16s/it]
Quantizing model.layers.67:  72%|███████▏  | 68/94 [50:49<19:07, 44.15s/it]
Quantizing model.layers.68:  72%|███████▏  | 68/94 [50:49<19:07, 44.15s/it]
Quantizing model.layers.68:  73%|███████▎  | 69/94 [51:34<18:23, 44.13s/it]
Quantizing model.layers.69:  73%|███████▎  | 69/94 [51:34<18:23, 44.13s/it]
Quantizing model.layers.69:  74%|███████▍  | 70/94 [52:18<17:40, 44.19s/it]
Quantizing model.layers.70:  74%|███████▍  | 70/94 [52:18<17:40, 44.19s/it]
Quantizing model.layers.70:  76%|███████▌  | 71/94 [53:02<16:57, 44.23s/it]
Quantizing model.layers.71:  76%|███████▌  | 71/94 [53:02<16:57, 44.23s/it]
Quantizing model.layers.71:  77%|███████▋  | 72/94 [53:46<16:12, 44.22s/it]
Quantizing model.layers.72:  77%|███████▋  | 72/94 [53:46<16:12, 44.22s/it]
Quantizing model.layers.72:  78%|███████▊  | 73/94 [54:31<15:28, 44.22s/it]
Quantizing model.layers.73:  78%|███████▊  | 73/94 [54:31<15:28, 44.22s/it]
Quantizing model.layers.73:  79%|███████▊  | 74/94 [55:15<14:43, 44.15s/it]
Quantizing model.layers.74:  79%|███████▊  | 74/94 [55:15<14:43, 44.15s/it]
Quantizing model.layers.74:  80%|███████▉  | 75/94 [55:59<13:58, 44.14s/it]
Quantizing model.layers.75:  80%|███████▉  | 75/94 [55:59<13:58, 44.14s/it]
Quantizing model.layers.75:  81%|████████  | 76/94 [56:43<13:14, 44.15s/it]
Quantizing model.layers.76:  81%|████████  | 76/94 [56:43<13:14, 44.15s/it]
Quantizing model.layers.76:  82%|████████▏ | 77/94 [57:27<12:29, 44.11s/it]
Quantizing model.layers.77:  82%|████████▏ | 77/94 [57:27<12:29, 44.11s/it]
Quantizing model.layers.77:  83%|████████▎ | 78/94 [58:11<11:45, 44.12s/it]
Quantizing model.layers.78:  83%|████████▎ | 78/94 [58:11<11:45, 44.12s/it]
Quantizing model.layers.78:  84%|████████▍ | 79/94 [58:56<11:03, 44.22s/it]
Quantizing model.layers.79:  84%|████████▍ | 79/94 [58:56<11:03, 44.22s/it]
Quantizing model.layers.79:  85%|████████▌ | 80/94 [59:40<10:19, 44.26s/it]
Quantizing model.layers.80:  85%|████████▌ | 80/94 [59:40<10:19, 44.26s/it]
Quantizing model.layers.80:  86%|████████▌ | 81/94 [1:00:24<09:35, 44.27s/it]
Quantizing model.layers.81:  86%|████████▌ | 81/94 [1:00:24<09:35, 44.27s/it]
Quantizing model.layers.81:  87%|████████▋ | 82/94 [1:01:08<08:51, 44.26s/it]
Quantizing model.layers.82:  87%|████████▋ | 82/94 [1:01:08<08:51, 44.26s/it]
Quantizing model.layers.82:  88%|████████▊ | 83/94 [1:01:53<08:07, 44.28s/it]
Quantizing model.layers.83:  88%|████████▊ | 83/94 [1:01:53<08:07, 44.28s/it]
Quantizing model.layers.83:  89%|████████▉ | 84/94 [1:02:37<07:22, 44.30s/it]
Quantizing model.layers.84:  89%|████████▉ | 84/94 [1:02:37<07:22, 44.30s/it]
Quantizing model.layers.84:  90%|█████████ | 85/94 [1:03:21<06:38, 44.31s/it]
Quantizing model.layers.85:  90%|█████████ | 85/94 [1:03:21<06:38, 44.31s/it]
Quantizing model.layers.85:  91%|█████████▏| 86/94 [1:04:06<05:54, 44.31s/it]
Quantizing model.layers.86:  91%|█████████▏| 86/94 [1:04:06<05:54, 44.31s/it]
Quantizing model.layers.86:  93%|█████████▎| 87/94 [1:04:50<05:10, 44.35s/it]
Quantizing model.layers.87:  93%|█████████▎| 87/94 [1:04:50<05:10, 44.35s/it]
Quantizing model.layers.87:  94%|█████████▎| 88/94 [1:05:35<04:26, 44.36s/it]
Quantizing model.layers.88:  94%|█████████▎| 88/94 [1:05:35<04:26, 44.36s/it]
Quantizing model.layers.88:  95%|█████████▍| 89/94 [1:06:19<03:41, 44.39s/it]
Quantizing model.layers.89:  95%|█████████▍| 89/94 [1:06:19<03:41, 44.39s/it]
Quantizing model.layers.89:  96%|█████████▌| 90/94 [1:07:03<02:57, 44.30s/it]
Quantizing model.layers.90:  96%|█████████▌| 90/94 [1:07:03<02:57, 44.30s/it]
Quantizing model.layers.90:  97%|█████████▋| 91/94 [1:07:47<02:12, 44.28s/it]
Quantizing model.layers.91:  97%|█████████▋| 91/94 [1:07:47<02:12, 44.28s/it]
Quantizing model.layers.91:  98%|█████████▊| 92/94 [1:08:32<01:28, 44.32s/it]
Quantizing model.layers.92:  98%|█████████▊| 92/94 [1:08:32<01:28, 44.32s/it]
Quantizing model.layers.92:  99%|█████████▉| 93/94 [1:09:16<00:44, 44.32s/it]
Quantizing model.layers.93:  99%|█████████▉| 93/94 [1:09:16<00:44, 44.32s/it]
Quantizing model.layers.93: 100%|██████████| 94/94 [1:10:00<00:00, 44.30s/it]
Quantizing model.layers.93: 100%|██████████| 94/94 [1:10:00<00:00, 44.69s/it]
chaiml-muster-v2-q235b-77862-v1-uploader: 
  0%|          | 0/36566 [00:00<?, ?it/s]
packing model.layers.0.mlp.gate:   0%|          | 0/36566 [00:00<?, ?it/s]
packing model.layers.0.mlp.gate:   0%|          | 1/36566 [00:01<10:59:26,  1.08s/it]
packing model.layers.1.mlp.gate:   0%|          | 1/36566 [00:01<10:59:26,  1.08s/it]
packing model.layers.2.mlp.gate:   0%|          | 2/36566 [00:01<10:59:24,  1.08s/it]
packing model.layers.3.mlp.gate:   0%|          | 3/36566 [00:01<10:59:23,  1.08s/it]
packing model.layers.4.mlp.gate:   0%|          | 4/36566 [00:01<10:59:22,  1.08s/it]
packing model.layers.5.mlp.gate:   0%|          | 5/36566 [00:01<10:59:21,  1.08s/it]
packing model.layers.6.mlp.gate:   0%|          | 6/36566 [00:01<10:59:20,  1.08s/it]
packing model.layers.7.mlp.gate:   0%|          | 7/36566 [00:01<10:59:19,  1.08s/it]
packing model.layers.8.mlp.gate:   0%|          | 8/36566 [00:01<10:59:18,  1.08s/it]
packing model.layers.9.mlp.gate:   0%|          | 9/36566 [00:01<10:59:17,  1.08s/it]
packing model.layers.10.mlp.gate:   0%|          | 10/36566 [00:01<10:59:16,  1.08s/it]
packing model.layers.11.mlp.gate:   0%|          | 11/36566 [00:01<10:59:15,  1.08s/it]
packing model.layers.12.mlp.gate:   0%|          | 12/36566 [00:01<10:59:14,  1.08s/it]
packing model.layers.13.mlp.gate:   0%|          | 13/36566 [00:01<10:59:13,  1.08s/it]
packing model.layers.14.mlp.gate:   0%|          | 14/36566 [00:01<10:59:12,  1.08s/it]
packing model.layers.15.mlp.gate:   0%|          | 15/36566 [00:01<10:59:10,  1.08s/it]
packing model.layers.16.mlp.gate:   0%|          | 16/36566 [00:01<10:59:09,  1.08s/it]
packing model.layers.17.mlp.gate:   0%|          | 17/36566 [00:01<10:59:08,  1.08s/it]
packing model.layers.18.mlp.gate:   0%|          | 18/36566 [00:01<10:59:07,  1.08s/it]
packing model.layers.19.mlp.gate:   0%|          | 19/36566 [00:01<10:59:06,  1.08s/it]
packing model.layers.20.mlp.gate:   0%|          | 20/36566 [00:01<10:59:05,  1.08s/it]
packing model.layers.21.mlp.gate:   0%|          | 21/36566 [00:01<10:59:04,  1.08s/it]
packing model.layers.22.mlp.gate:   0%|          | 22/36566 [00:01<10:59:03,  1.08s/it]
packing model.layers.23.mlp.gate:   0%|          | 23/36566 [00:01<10:59:02,  1.08s/it]
packing model.layers.24.mlp.gate:   0%|          | 24/36566 [00:01<10:59:01,  1.08s/it]
packing model.layers.25.mlp.gate:   0%|          | 25/36566 [00:01<10:59:00,  1.08s/it]
packing model.layers.26.mlp.gate:   0%|          | 26/36566 [00:01<10:58:59,  1.08s/it]
packing model.layers.27.mlp.gate:   0%|          | 27/36566 [00:01<10:58:57,  1.08s/it]
packing model.layers.28.mlp.gate:   0%|          | 28/36566 [00:01<10:58:56,  1.08s/it]
packing model.layers.29.mlp.gate:   0%|          | 29/36566 [00:01<10:58:55,  1.08s/it]
packing model.layers.30.mlp.gate:   0%|          | 30/36566 [00:01<10:58:54,  1.08s/it]
packing model.layers.31.mlp.gate:   0%|          | 31/36566 [00:01<10:58:53,  1.08s/it]
packing model.layers.32.mlp.gate:   0%|          | 32/36566 [00:01<10:58:52,  1.08s/it]
packing model.layers.33.mlp.gate:   0%|          | 33/36566 [00:01<10:58:51,  1.08s/it]
packing model.layers.34.mlp.gate:   0%|          | 34/36566 [00:01<10:58:50,  1.08s/it]
packing model.layers.35.mlp.gate:   0%|          | 35/36566 [00:01<10:58:49,  1.08s/it]
packing model.layers.36.mlp.gate:   0%|          | 36/36566 [00:01<10:58:48,  1.08s/it]
packing model.layers.37.mlp.gate:   0%|          | 37/36566 [00:01<10:58:47,  1.08s/it]
packing model.layers.38.mlp.gate:   0%|          | 38/36566 [00:01<10:58:46,  1.08s/it]
packing model.layers.39.mlp.gate:   0%|          | 39/36566 [00:01<10:58:44,  1.08s/it]
packing model.layers.40.mlp.gate:   0%|          | 40/36566 [00:01<10:58:43,  1.08s/it]
packing model.layers.41.mlp.gate:   0%|          | 41/36566 [00:01<10:58:42,  1.08s/it]
packing model.layers.42.mlp.gate:   0%|          | 42/36566 [00:01<10:58:41,  1.08s/it]
packing model.layers.43.mlp.gate:   0%|          | 43/36566 [00:01<10:58:40,  1.08s/it]
packing model.layers.44.mlp.gate:   0%|          | 44/36566 [00:01<10:58:39,  1.08s/it]
packing model.layers.45.mlp.gate:   0%|          | 45/36566 [00:01<10:58:38,  1.08s/it]
packing model.layers.46.mlp.gate:   0%|          | 46/36566 [00:01<10:58:37,  1.08s/it]
packing model.layers.47.mlp.gate:   0%|          | 47/36566 [00:01<10:58:36,  1.08s/it]
packing model.layers.48.mlp.gate:   0%|          | 48/36566 [00:01<10:58:35,  1.08s/it]
packing model.layers.49.mlp.gate:   0%|          | 49/36566 [00:01<10:58:34,  1.08s/it]
packing model.layers.50.mlp.gate:   0%|          | 50/36566 [00:01<10:58:33,  1.08s/it]
packing model.layers.51.mlp.gate:   0%|          | 51/36566 [00:01<10:58:31,  1.08s/it]
packing model.layers.52.mlp.gate:   0%|          | 52/36566 [00:01<10:58:30,  1.08s/it]
packing model.layers.53.mlp.gate:   0%|          | 53/36566 [00:01<10:58:29,  1.08s/it]
packing model.layers.54.mlp.gate:   0%|          | 54/36566 [00:01<10:58:28,  1.08s/it]
packing model.layers.55.mlp.gate:   0%|          | 55/36566 [00:01<10:58:27,  1.08s/it]
packing model.layers.56.mlp.gate:   0%|          | 56/36566 [00:01<10:58:26,  1.08s/it]
packing model.layers.57.mlp.gate:   0%|          | 57/36566 [00:01<10:58:25,  1.08s/it]
packing model.layers.58.mlp.gate:   0%|          | 58/36566 [00:01<10:58:24,  1.08s/it]
packing model.layers.59.mlp.gate:   0%|          | 59/36566 [00:01<10:58:23,  1.08s/it]
packing model.layers.60.mlp.gate:   0%|          | 60/36566 [00:01<10:58:22,  1.08s/it]
packing model.layers.61.mlp.gate:   0%|          | 61/36566 [00:01<10:58:21,  1.08s/it]
packing model.layers.62.mlp.gate:   0%|          | 62/36566 [00:01<10:58:20,  1.08s/it]
packing model.layers.63.mlp.gate:   0%|          | 63/36566 [00:01<10:58:18,  1.08s/it]
packing model.layers.64.mlp.gate:   0%|          | 64/36566 [00:01<10:58:17,  1.08s/it]
packing model.layers.65.mlp.gate:   0%|          | 65/36566 [00:01<10:58:16,  1.08s/it]
packing model.layers.66.mlp.gate:   0%|          | 66/36566 [00:01<10:58:15,  1.08s/it]
packing model.layers.67.mlp.gate:   0%|          | 67/36566 [00:01<10:58:14,  1.08s/it]
packing model.layers.68.mlp.gate:   0%|          | 68/36566 [00:01<10:58:13,  1.08s/it]
packing model.layers.69.mlp.gate:   0%|          | 69/36566 [00:01<10:58:12,  1.08s/it]
packing model.layers.70.mlp.gate:   0%|          | 70/36566 [00:01<10:58:11,  1.08s/it]
packing model.layers.71.mlp.gate:   0%|          | 71/36566 [00:01<10:58:10,  1.08s/it]
packing model.layers.72.mlp.gate:   0%|          | 72/36566 [00:01<10:58:09,  1.08s/it]
packing model.layers.73.mlp.gate:   0%|          | 73/36566 [00:01<10:58:08,  1.08s/it]
packing model.layers.74.mlp.gate:   0%|          | 74/36566 [00:01<10:58:07,  1.08s/it]
packing model.layers.75.mlp.gate:   0%|          | 75/36566 [00:01<10:58:06,  1.08s/it]
packing model.layers.76.mlp.gate:   0%|          | 76/36566 [00:01<10:58:04,  1.08s/it]
packing model.layers.77.mlp.gate:   0%|          | 77/36566 [00:01<10:58:03,  1.08s/it]
packing model.layers.78.mlp.gate:   0%|          | 78/36566 [00:01<10:58:02,  1.08s/it]
packing model.layers.79.mlp.gate:   0%|          | 79/36566 [00:01<10:58:01,  1.08s/it]
packing model.layers.80.mlp.gate:   0%|          | 80/36566 [00:01<10:58:00,  1.08s/it]
packing model.layers.81.mlp.gate:   0%|          | 81/36566 [00:01<10:57:59,  1.08s/it]
packing model.layers.82.mlp.gate:   0%|          | 82/36566 [00:01<10:57:58,  1.08s/it]
packing model.layers.83.mlp.gate:   0%|          | 83/36566 [00:01<10:57:57,  1.08s/it]
packing model.layers.84.mlp.gate:   0%|          | 84/36566 [00:01<10:57:56,  1.08s/it]
packing model.layers.85.mlp.gate:   0%|          | 85/36566 [00:01<10:57:55,  1.08s/it]
packing model.layers.86.mlp.gate:   0%|          | 86/36566 [00:01<10:57:54,  1.08s/it]
packing model.layers.87.mlp.gate:   0%|          | 87/36566 [00:01<10:57:53,  1.08s/it]
packing model.layers.88.mlp.gate:   0%|          | 88/36566 [00:01<10:57:51,  1.08s/it]
packing model.layers.89.mlp.gate:   0%|          | 89/36566 [00:01<10:57:50,  1.08s/it]
packing model.layers.90.mlp.gate:   0%|          | 90/36566 [00:01<10:57:49,  1.08s/it]
packing model.layers.91.mlp.gate:   0%|          | 91/36566 [00:01<10:57:48,  1.08s/it]
packing model.layers.92.mlp.gate:   0%|          | 92/36566 [00:01<10:57:47,  1.08s/it]
packing model.layers.93.mlp.gate:   0%|          | 93/36566 [00:01<10:57:46,  1.08s/it]
packing model.layers.0.self_attn.k_proj:   0%|          | 94/36566 [00:01<10:57:45,  1.08s/it]
packing model.layers.1.self_attn.k_proj:   0%|          | 95/36566 [00:01<10:57:44,  1.08s/it]
packing model.layers.2.self_attn.k_proj:   0%|          | 96/36566 [00:01<10:57:43,  1.08s/it]
packing model.layers.3.self_attn.k_proj:   0%|          | 97/36566 [00:01<10:57:42,  1.08s/it]
packing model.layers.4.self_attn.k_proj:   0%|          | 98/36566 [00:01<10:57:41,  1.08s/it]
packing model.layers.5.self_attn.k_proj:   0%|          | 99/36566 [00:01<10:57:40,  1.08s/it]
packing model.layers.6.self_attn.k_proj:   0%|          | 100/36566 [00:01<10:57:38,  1.08s/it]
packing model.layers.7.self_attn.k_proj:   0%|          | 101/36566 [00:01<10:57:37,  1.08s/it]
packing model.layers.8.self_attn.k_proj:   0%|          | 102/36566 [00:01<10:57:36,  1.08s/it]
packing model.layers.9.self_attn.k_proj:   0%|          | 103/36566 [00:01<10:57:35,  1.08s/it]
packing model.layers.10.self_attn.k_proj:   0%|          | 104/36566 [00:01<10:57:34,  1.08s/it]
packing model.layers.11.self_attn.k_proj:   0%|          | 105/36566 [00:01<10:57:33,  1.08s/it]
packing model.layers.12.self_attn.k_proj:   0%|          | 106/36566 [00:01<10:57:32,  1.08s/it]
packing model.layers.13.self_attn.k_proj:   0%|          | 107/36566 [00:01<10:57:31,  1.08s/it]
packing model.layers.14.self_attn.k_proj:   0%|          | 108/36566 [00:01<10:57:30,  1.08s/it]
packing model.layers.15.self_attn.k_proj:   0%|          | 109/36566 [00:01<10:57:29,  1.08s/it]
packing model.layers.16.self_attn.k_proj:   0%|          | 110/36566 [00:01<10:57:28,  1.08s/it]
packing model.layers.17.self_attn.k_proj:   0%|          | 111/36566 [00:01<10:57:27,  1.08s/it]
packing model.layers.18.self_attn.k_proj:   0%|          | 112/36566 [00:01<10:57:25,  1.08s/it]
packing model.layers.19.self_attn.k_proj:   0%|          | 113/36566 [00:01<10:57:24,  1.08s/it]
packing model.layers.19.self_attn.k_proj:   0%|          | 114/36566 [00:01<04:35, 132.53it/s]  
packing model.layers.20.self_attn.k_proj:   0%|          | 114/36566 [00:01<04:35, 132.53it/s]
packing model.layers.21.self_attn.k_proj:   0%|          | 115/36566 [00:01<04:35, 132.53it/s]
packing model.layers.22.self_attn.k_proj:   0%|          | 116/36566 [00:01<04:35, 132.53it/s]
packing model.layers.23.self_attn.k_proj:   0%|          | 117/36566 [00:01<04:35, 132.53it/s]
packing model.layers.24.self_attn.k_proj:   0%|          | 118/36566 [00:01<04:35, 132.53it/s]
packing model.layers.25.self_attn.k_proj:   0%|          | 119/36566 [00:01<04:35, 132.53it/s]
packing model.layers.26.self_attn.k_proj:   0%|          | 120/36566 [00:01<04:35, 132.53it/s]
packing model.layers.27.self_attn.k_proj:   0%|          | 121/36566 [00:01<04:34, 132.53it/s]
packing model.layers.28.self_attn.k_proj:   0%|          | 122/36566 [00:01<04:34, 132.53it/s]
packing model.layers.29.self_attn.k_proj:   0%|          | 123/36566 [00:01<04:34, 132.53it/s]
packing model.layers.30.self_attn.k_proj:   0%|          | 124/36566 [00:01<04:34, 132.53it/s]
packing model.layers.31.self_attn.k_proj:   0%|          | 125/36566 [00:01<04:34, 132.53it/s]
packing model.layers.32.self_attn.k_proj:   0%|          | 126/36566 [00:01<04:34, 132.53it/s]
packing model.layers.33.self_attn.k_proj:   0%|          | 127/36566 [00:01<04:34, 132.53it/s]
packing model.layers.34.self_attn.k_proj:   0%|          | 128/36566 [00:01<04:34, 132.53it/s]
packing model.layers.35.self_attn.k_proj:   0%|          | 129/36566 [00:01<04:34, 132.53it/s]
packing model.layers.36.self_attn.k_proj:   0%|          | 130/36566 [00:01<04:34, 132.53it/s]
packing model.layers.37.self_attn.k_proj:   0%|          | 131/36566 [00:01<04:34, 132.53it/s]
packing model.layers.38.self_attn.k_proj:   0%|          | 132/36566 [00:01<04:34, 132.53it/s]
packing model.layers.39.self_attn.k_proj:   0%|          | 133/36566 [00:01<04:34, 132.53it/s]
packing model.layers.40.self_attn.k_proj:   0%|          | 134/36566 [00:01<04:34, 132.53it/s]
packing model.layers.41.self_attn.k_proj:   0%|          | 135/36566 [00:01<04:34, 132.53it/s]
packing model.layers.42.self_attn.k_proj:   0%|          | 136/36566 [00:01<04:34, 132.53it/s]
packing model.layers.43.self_attn.k_proj:   0%|          | 137/36566 [00:01<04:34, 132.53it/s]
packing model.layers.44.self_attn.k_proj:   0%|          | 138/36566 [00:01<04:34, 132.53it/s]
packing model.layers.45.self_attn.k_proj:   0%|          | 139/36566 [00:01<04:34, 132.53it/s]
packing model.layers.46.self_attn.k_proj:   0%|          | 140/36566 [00:01<04:34, 132.53it/s]
packing model.layers.47.self_attn.k_proj:   0%|          | 141/36566 [00:01<04:34, 132.53it/s]
packing model.layers.48.self_attn.k_proj:   0%|          | 142/36566 [00:01<04:34, 132.53it/s]
packing model.layers.49.self_attn.k_proj:   0%|          | 143/36566 [00:01<04:34, 132.53it/s]
packing model.layers.50.self_attn.k_proj:   0%|          | 144/36566 [00:01<04:34, 132.53it/s]
packing model.layers.51.self_attn.k_proj:   0%|          | 145/36566 [00:01<04:34, 132.53it/s]
packing model.layers.52.self_attn.k_proj:   0%|          | 146/36566 [00:01<04:34, 132.53it/s]
packing model.layers.53.self_attn.k_proj:   0%|          | 147/36566 [00:01<04:34, 132.53it/s]
packing model.layers.54.self_attn.k_proj:   0%|          | 148/36566 [00:01<04:34, 132.53it/s]
packing model.layers.55.self_attn.k_proj:   0%|          | 149/36566 [00:01<04:34, 132.53it/s]
packing model.layers.56.self_attn.k_proj:   0%|          | 150/36566 [00:01<04:34, 132.53it/s]
packing model.layers.57.self_attn.k_proj:   0%|          | 151/36566 [00:01<04:34, 132.53it/s]
packing model.layers.58.self_attn.k_proj:   0%|          | 152/36566 [00:01<04:34, 132.53it/s]
packing model.layers.59.self_attn.k_proj:   0%|          | 153/36566 [00:01<04:34, 132.53it/s]
packing model.layers.60.self_attn.k_proj:   0%|          | 154/36566 [00:01<04:34, 132.53it/s]
packing model.layers.61.self_attn.k_proj:   0%|          | 155/36566 [00:01<04:34, 132.53it/s]
packing model.layers.62.self_attn.k_proj:   0%|          | 156/36566 [00:01<04:34, 132.53it/s]
packing model.layers.63.self_attn.k_proj:   0%|          | 157/36566 [00:01<04:34, 132.53it/s]
packing model.layers.64.self_attn.k_proj:   0%|          | 158/36566 [00:01<04:34, 132.53it/s]
packing model.layers.65.self_attn.k_proj:   0%|          | 159/36566 [00:01<04:34, 132.53it/s]
packing model.layers.66.self_attn.k_proj:   0%|          | 160/36566 [00:01<04:34, 132.53it/s]
packing model.layers.67.self_attn.k_proj:   0%|          | 161/36566 [00:01<04:34, 132.53it/s]
packing model.layers.68.self_attn.k_proj:   0%|          | 162/36566 [00:01<04:34, 132.53it/s]
packing model.layers.69.self_attn.k_proj:   0%|          | 163/36566 [00:01<04:34, 132.53it/s]
packing model.layers.70.self_attn.k_proj:   0%|          | 164/36566 [00:01<04:34, 132.53it/s]
packing model.layers.71.self_attn.k_proj:   0%|          | 165/36566 [00:01<04:34, 132.53it/s]
packing model.layers.72.self_attn.k_proj:   0%|          | 166/36566 [00:01<04:34, 132.53it/s]
packing model.layers.73.self_attn.k_proj:   0%|          | 167/36566 [00:01<04:34, 132.53it/s]
packing model.layers.74.self_attn.k_proj:   0%|          | 168/36566 [00:01<04:34, 132.53it/s]
packing model.layers.75.self_attn.k_proj:   0%|          | 169/36566 [00:01<04:34, 132.53it/s]
packing model.layers.76.self_attn.k_proj:   0%|          | 170/36566 [00:01<04:34, 132.53it/s]
packing model.layers.77.self_attn.k_proj:   0%|          | 171/36566 [00:01<04:34, 132.53it/s]
packing model.layers.78.self_attn.k_proj:   0%|          | 172/36566 [00:01<04:34, 132.53it/s]
packing model.layers.79.self_attn.k_proj:   0%|          | 173/36566 [00:01<04:34, 132.53it/s]
packing model.layers.80.self_attn.k_proj:   0%|          | 174/36566 [00:01<04:34, 132.53it/s]
packing model.layers.81.self_attn.k_proj:   0%|          | 175/36566 [00:01<04:34, 132.53it/s]
packing model.layers.82.self_attn.k_proj:   0%|          | 176/36566 [00:01<04:34, 132.53it/s]
packing model.layers.83.self_attn.k_proj:   0%|          | 177/36566 [00:01<04:34, 132.53it/s]
packing model.layers.84.self_attn.k_proj:   0%|          | 178/36566 [00:01<04:34, 132.53it/s]
packing model.layers.85.self_attn.k_proj:   0%|          | 179/36566 [00:01<04:34, 132.53it/s]
packing model.layers.86.self_attn.k_proj:   0%|          | 180/36566 [00:01<04:34, 132.53it/s]
packing model.layers.87.self_attn.k_proj:   0%|          | 181/36566 [00:01<04:34, 132.53it/s]
packing model.layers.88.self_attn.k_proj:   0%|          | 182/36566 [00:01<04:34, 132.53it/s]
packing model.layers.89.self_attn.k_proj:   1%|          | 183/36566 [00:01<04:34, 132.53it/s]
packing model.layers.90.self_attn.k_proj:   1%|          | 184/36566 [00:01<04:34, 132.53it/s]
packing model.layers.91.self_attn.k_proj:   1%|          | 185/36566 [00:01<04:34, 132.53it/s]
packing model.layers.92.self_attn.k_proj:   1%|          | 186/36566 [00:01<04:34, 132.53it/s]
packing model.layers.93.self_attn.k_proj:   1%|          | 187/36566 [00:01<04:34, 132.53it/s]
packing model.layers.0.self_attn.o_proj:   1%|          | 188/36566 [00:01<04:34, 132.53it/s] 
packing model.layers.1.self_attn.o_proj:   1%|          | 189/36566 [00:01<04:34, 132.53it/s]
packing model.layers.2.self_attn.o_proj:   1%|          | 190/36566 [00:01<04:34, 132.53it/s]
packing model.layers.3.self_attn.o_proj:   1%|          | 191/36566 [00:01<04:34, 132.53it/s]
packing model.layers.4.self_attn.o_proj:   1%|          | 192/36566 [00:01<04:34, 132.53it/s]
packing model.layers.5.self_attn.o_proj:   1%|          | 193/36566 [00:01<04:34, 132.53it/s]
packing model.layers.6.self_attn.o_proj:   1%|          | 194/36566 [00:01<04:34, 132.53it/s]
packing model.layers.7.self_attn.o_proj:   1%|          | 195/36566 [00:01<04:34, 132.53it/s]
packing model.layers.8.self_attn.o_proj:   1%|          | 196/36566 [00:01<04:34, 132.53it/s]
packing model.layers.9.self_attn.o_proj:   1%|          | 197/36566 [00:01<04:34, 132.53it/s]
packing model.layers.10.self_attn.o_proj:   1%|          | 198/36566 [00:01<04:34, 132.53it/s]
packing model.layers.11.self_attn.o_proj:   1%|          | 199/36566 [00:01<04:34, 132.53it/s]
packing model.layers.12.self_attn.o_proj:   1%|          | 200/36566 [00:01<04:34, 132.53it/s]
packing model.layers.13.self_attn.o_proj:   1%|          | 201/36566 [00:01<04:34, 132.53it/s]
packing model.layers.14.self_attn.o_proj:   1%|          | 202/36566 [00:01<04:34, 132.53it/s]
packing model.layers.15.self_attn.o_proj:   1%|          | 203/36566 [00:01<04:34, 132.53it/s]
packing model.layers.16.self_attn.o_proj:   1%|          | 204/36566 [00:01<04:34, 132.53it/s]
packing model.layers.17.self_attn.o_proj:   1%|          | 205/36566 [00:01<04:34, 132.53it/s]
packing model.layers.18.self_attn.o_proj:   1%|          | 206/36566 [00:01<04:34, 132.53it/s]
packing model.layers.19.self_attn.o_proj:   1%|          | 207/36566 [00:01<04:34, 132.53it/s]
packing model.layers.20.self_attn.o_proj:   1%|          | 208/36566 [00:01<04:34, 132.53it/s]
packing model.layers.21.self_attn.o_proj:   1%|          | 209/36566 [00:01<04:34, 132.53it/s]
packing model.layers.22.self_attn.o_proj:   1%|          | 210/36566 [00:01<04:34, 132.53it/s]
packing model.layers.23.self_attn.o_proj:   1%|          | 211/36566 [00:01<04:34, 132.53it/s]
packing model.layers.24.self_attn.o_proj:   1%|          | 212/36566 [00:01<04:34, 132.53it/s]
packing model.layers.25.self_attn.o_proj:   1%|          | 213/36566 [00:01<04:34, 132.53it/s]
packing model.layers.26.self_attn.o_proj:   1%|          | 214/36566 [00:01<04:34, 132.53it/s]
packing model.layers.27.self_attn.o_proj:   1%|          | 215/36566 [00:01<04:34, 132.53it/s]
packing model.layers.28.self_attn.o_proj:   1%|          | 216/36566 [00:01<04:34, 132.53it/s]
packing model.layers.29.self_attn.o_proj:   1%|          | 217/36566 [00:01<04:34, 132.53it/s]
packing model.layers.30.self_attn.o_proj:   1%|          | 218/36566 [00:01<04:34, 132.53it/s]
packing model.layers.31.self_attn.o_proj:   1%|          | 219/36566 [00:01<04:34, 132.53it/s]
packing model.layers.32.self_attn.o_proj:   1%|          | 220/36566 [00:01<04:34, 132.53it/s]
packing model.layers.33.self_attn.o_proj:   1%|          | 221/36566 [00:01<04:34, 132.53it/s]
packing model.layers.34.self_attn.o_proj:   1%|          | 222/36566 [00:01<04:34, 132.53it/s]
packing model.layers.35.self_attn.o_proj:   1%|          | 223/36566 [00:01<04:34, 132.53it/s]
packing model.layers.36.self_attn.o_proj:   1%|          | 224/36566 [00:01<04:34, 132.53it/s]
packing model.layers.37.self_attn.o_proj:   1%|          | 225/36566 [00:01<04:34, 132.53it/s]
packing model.layers.38.self_attn.o_proj:   1%|          | 226/36566 [00:01<04:34, 132.53it/s]
packing model.layers.39.self_attn.o_proj:   1%|          | 227/36566 [00:01<04:34, 132.53it/s]
packing model.layers.40.self_attn.o_proj:   1%|          | 228/36566 [00:01<04:34, 132.53it/s]
packing model.layers.41.self_attn.o_proj:   1%|          | 229/36566 [00:01<04:34, 132.53it/s]
packing model.layers.41.self_attn.o_proj:   1%|          | 230/36566 [00:01<02:10, 278.94it/s]
packing model.layers.42.self_attn.o_proj:   1%|          | 230/36566 [00:01<02:10, 278.94it/s]
packing model.layers.43.self_attn.o_proj:   1%|          | 231/36566 [00:01<02:10, 278.94it/s]
packing model.layers.44.self_attn.o_proj:   1%|          | 232/36566 [00:01<02:10, 278.94it/s]
packing model.layers.45.self_attn.o_proj:   1%|          | 233/36566 [00:01<02:10, 278.94it/s]
packing model.layers.46.self_attn.o_proj:   1%|          | 234/36566 [00:01<02:10, 278.94it/s]
packing model.layers.47.self_attn.o_proj:   1%|          | 235/36566 [00:01<02:10, 278.94it/s]
packing model.layers.48.self_attn.o_proj:   1%|          | 236/36566 [00:01<02:10, 278.94it/s]
packing model.layers.49.self_attn.o_proj:   1%|          | 237/36566 [00:01<02:10, 278.94it/s]
packing model.layers.50.self_attn.o_proj:   1%|          | 238/36566 [00:01<02:10, 278.94it/s]
packing model.layers.51.self_attn.o_proj:   1%|          | 239/36566 [00:01<02:10, 278.94it/s]
packing model.layers.52.self_attn.o_proj:   1%|          | 240/36566 [00:01<02:10, 278.94it/s]
packing model.layers.53.self_attn.o_proj:   1%|          | 241/36566 [00:01<02:10, 278.94it/s]
packing model.layers.54.self_attn.o_proj:   1%|          | 242/36566 [00:01<02:10, 278.94it/s]
packing model.layers.55.self_attn.o_proj:   1%|          | 243/36566 [00:01<02:10, 278.94it/s]
packing model.layers.56.self_attn.o_proj:   1%|          | 244/36566 [00:01<02:10, 278.94it/s]
packing model.layers.57.self_attn.o_proj:   1%|          | 245/36566 [00:01<02:10, 278.94it/s]
packing model.layers.58.self_attn.o_proj:   1%|          | 246/36566 [00:01<02:10, 278.94it/s]
packing model.layers.59.self_attn.o_proj:   1%|          | 247/36566 [00:01<02:10, 278.94it/s]
packing model.layers.60.self_attn.o_proj:   1%|          | 248/36566 [00:01<02:10, 278.94it/s]
packing model.layers.61.self_attn.o_proj:   1%|          | 249/36566 [00:01<02:10, 278.94it/s]
packing model.layers.62.self_attn.o_proj:   1%|          | 250/36566 [00:01<02:10, 278.94it/s]
packing model.layers.63.self_attn.o_proj:   1%|          | 251/36566 [00:01<02:10, 278.94it/s]
packing model.layers.64.self_attn.o_proj:   1%|          | 252/36566 [00:01<02:10, 278.94it/s]
packing model.layers.65.self_attn.o_proj:   1%|          | 253/36566 [00:01<02:10, 278.94it/s]
packing model.layers.66.self_attn.o_proj:   1%|          | 254/36566 [00:01<02:10, 278.94it/s]
packing model.layers.67.self_attn.o_proj:   1%|          | 255/36566 [00:01<02:10, 278.94it/s]
packing model.layers.68.self_attn.o_proj:   1%|          | 256/36566 [00:01<02:10, 278.94it/s]
packing model.layers.69.self_attn.o_proj:   1%|          | 257/36566 [00:01<02:10, 278.94it/s]
packing model.layers.70.self_attn.o_proj:   1%|          | 258/36566 [00:01<02:10, 278.94it/s]
packing model.layers.71.self_attn.o_proj:   1%|          | 259/36566 [00:01<02:10, 278.94it/s]
packing model.layers.72.self_attn.o_proj:   1%|          | 260/36566 [00:01<02:10, 278.94it/s]
packing model.layers.73.self_attn.o_proj:   1%|          | 261/36566 [00:01<02:10, 278.94it/s]
packing model.layers.74.self_attn.o_proj:   1%|          | 262/36566 [00:01<02:10, 278.94it/s]
packing model.layers.75.self_attn.o_proj:   1%|          | 263/36566 [00:01<02:10, 278.94it/s]
packing model.layers.76.self_attn.o_proj:   1%|          | 264/36566 [00:01<02:10, 278.94it/s]
packing model.layers.77.self_attn.o_proj:   1%|          | 265/36566 [00:01<02:10, 278.94it/s]
packing model.layers.78.self_attn.o_proj:   1%|          | 266/36566 [00:01<02:10, 278.94it/s]
packing model.layers.79.self_attn.o_proj:   1%|          | 267/36566 [00:01<02:10, 278.94it/s]
packing model.layers.80.self_attn.o_proj:   1%|          | 268/36566 [00:01<02:10, 278.94it/s]
packing model.layers.81.self_attn.o_proj:   1%|          | 269/36566 [00:01<02:10, 278.94it/s]
packing model.layers.82.self_attn.o_proj:   1%|          | 270/36566 [00:01<02:10, 278.94it/s]
packing model.layers.83.self_attn.o_proj:   1%|          | 271/36566 [00:01<02:10, 278.94it/s]
packing model.layers.84.self_attn.o_proj:   1%|          | 272/36566 [00:01<02:10, 278.94it/s]
packing model.layers.85.self_attn.o_proj:   1%|          | 273/36566 [00:01<02:10, 278.94it/s]
packing model.layers.86.self_attn.o_proj:   1%|          | 274/36566 [00:01<02:10, 278.94it/s]
packing model.layers.87.self_attn.o_proj:   1%|          | 275/36566 [00:01<02:10, 278.94it/s]
packing model.layers.88.self_attn.o_proj:   1%|          | 276/36566 [00:01<02:10, 278.94it/s]
packing model.layers.89.self_attn.o_proj:   1%|          | 277/36566 [00:01<02:10, 278.94it/s]
packing model.layers.90.self_attn.o_proj:   1%|          | 278/36566 [00:01<02:10, 278.94it/s]
packing model.layers.91.self_attn.o_proj:   1%|          | 279/36566 [00:01<02:10, 278.94it/s]
packing model.layers.92.self_attn.o_proj:   1%|          | 280/36566 [00:01<02:10, 278.94it/s]
packing model.layers.93.self_attn.o_proj:   1%|          | 281/36566 [00:01<02:10, 278.94it/s]
packing model.layers.0.self_attn.q_proj:   1%|          | 282/36566 [00:01<02:10, 278.94it/s] 
packing model.layers.1.self_attn.q_proj:   1%|          | 283/36566 [00:01<02:10, 278.94it/s]
packing model.layers.2.self_attn.q_proj:   1%|          | 284/36566 [00:01<02:10, 278.94it/s]
packing model.layers.3.self_attn.q_proj:   1%|          | 285/36566 [00:01<02:10, 278.94it/s]
packing model.layers.4.self_attn.q_proj:   1%|          | 286/36566 [00:01<02:10, 278.94it/s]
packing model.layers.5.self_attn.q_proj:   1%|          | 287/36566 [00:01<02:10, 278.94it/s]
packing model.layers.6.self_attn.q_proj:   1%|          | 288/36566 [00:01<02:10, 278.94it/s]
packing model.layers.7.self_attn.q_proj:   1%|          | 289/36566 [00:01<02:10, 278.94it/s]
packing model.layers.8.self_attn.q_proj:   1%|          | 290/36566 [00:01<02:10, 278.94it/s]
packing model.layers.9.self_attn.q_proj:   1%|          | 291/36566 [00:01<02:10, 278.94it/s]
packing model.layers.10.self_attn.q_proj:   1%|          | 292/36566 [00:01<02:10, 278.94it/s]
packing model.layers.11.self_attn.q_proj:   1%|          | 293/36566 [00:01<02:10, 278.94it/s]
packing model.layers.12.self_attn.q_proj:   1%|          | 294/36566 [00:01<02:10, 278.94it/s]
packing model.layers.13.self_attn.q_proj:   1%|          | 295/36566 [00:01<02:10, 278.94it/s]
packing model.layers.14.self_attn.q_proj:   1%|          | 296/36566 [00:01<02:10, 278.94it/s]
packing model.layers.15.self_attn.q_proj:   1%|          | 297/36566 [00:01<02:10, 278.94it/s]
packing model.layers.16.self_attn.q_proj:   1%|          | 298/36566 [00:01<02:10, 278.94it/s]
packing model.layers.17.self_attn.q_proj:   1%|          | 299/36566 [00:01<02:10, 278.94it/s]
packing model.layers.18.self_attn.q_proj:   1%|          | 300/36566 [00:01<02:10, 278.94it/s]
packing model.layers.19.self_attn.q_proj:   1%|          | 301/36566 [00:01<02:10, 278.94it/s]
packing model.layers.20.self_attn.q_proj:   1%|          | 302/36566 [00:01<02:10, 278.94it/s]
packing model.layers.21.self_attn.q_proj:   1%|          | 303/36566 [00:01<02:10, 278.94it/s]
packing model.layers.22.self_attn.q_proj:   1%|          | 304/36566 [00:01<02:10, 278.94it/s]
packing model.layers.23.self_attn.q_proj:   1%|          | 305/36566 [00:01<02:09, 278.94it/s]
packing model.layers.24.self_attn.q_proj:   1%|          | 306/36566 [00:01<02:09, 278.94it/s]
packing model.layers.25.self_attn.q_proj:   1%|          | 307/36566 [00:01<02:09, 278.94it/s]
packing model.layers.26.self_attn.q_proj:   1%|          | 308/36566 [00:01<02:09, 278.94it/s]
packing model.layers.27.self_attn.q_proj:   1%|          | 309/36566 [00:01<02:09, 278.94it/s]
packing model.layers.28.self_attn.q_proj:   1%|          | 310/36566 [00:01<02:09, 278.94it/s]
packing model.layers.29.self_attn.q_proj:   1%|          | 311/36566 [00:01<02:09, 278.94it/s]
packing model.layers.30.self_attn.q_proj:   1%|          | 312/36566 [00:01<02:09, 278.94it/s]
packing model.layers.31.self_attn.q_proj:   1%|          | 313/36566 [00:01<02:09, 278.94it/s]
packing model.layers.32.self_attn.q_proj:   1%|          | 314/36566 [00:01<02:09, 278.94it/s]
packing model.layers.33.self_attn.q_proj:   1%|          | 315/36566 [00:01<02:09, 278.94it/s]
packing model.layers.34.self_attn.q_proj:   1%|          | 316/36566 [00:01<02:09, 278.94it/s]
packing model.layers.35.self_attn.q_proj:   1%|          | 317/36566 [00:01<02:09, 278.94it/s]
packing model.layers.36.self_attn.q_proj:   1%|          | 318/36566 [00:01<02:09, 278.94it/s]
packing model.layers.37.self_attn.q_proj:   1%|          | 319/36566 [00:01<02:09, 278.94it/s]
packing model.layers.38.self_attn.q_proj:   1%|          | 320/36566 [00:01<02:09, 278.94it/s]
packing model.layers.39.self_attn.q_proj:   1%|          | 321/36566 [00:01<02:09, 278.94it/s]
packing model.layers.40.self_attn.q_proj:   1%|          | 322/36566 [00:01<02:09, 278.94it/s]
packing model.layers.41.self_attn.q_proj:   1%|          | 323/36566 [00:01<02:09, 278.94it/s]
packing model.layers.42.self_attn.q_proj:   1%|          | 324/36566 [00:01<02:09, 278.94it/s]
packing model.layers.43.self_attn.q_proj:   1%|          | 325/36566 [00:01<02:09, 278.94it/s]
packing model.layers.44.self_attn.q_proj:   1%|          | 326/36566 [00:01<02:09, 278.94it/s]
packing model.layers.45.self_attn.q_proj:   1%|          | 327/36566 [00:01<02:09, 278.94it/s]
packing model.layers.46.self_attn.q_proj:   1%|          | 328/36566 [00:01<02:09, 278.94it/s]
packing model.layers.47.self_attn.q_proj:   1%|          | 329/36566 [00:01<02:09, 278.94it/s]
packing model.layers.48.self_attn.q_proj:   1%|          | 330/36566 [00:01<02:09, 278.94it/s]
packing model.layers.49.self_attn.q_proj:   1%|          | 331/36566 [00:01<02:09, 278.94it/s]
packing model.layers.50.self_attn.q_proj:   1%|          | 332/36566 [00:01<02:09, 278.94it/s]
packing model.layers.51.self_attn.q_proj:   1%|          | 333/36566 [00:01<02:09, 278.94it/s]
packing model.layers.52.self_attn.q_proj:   1%|          | 334/36566 [00:01<02:09, 278.94it/s]
packing model.layers.53.self_attn.q_proj:   1%|          | 335/36566 [00:01<02:09, 278.94it/s]
packing model.layers.54.self_attn.q_proj:   1%|          | 336/36566 [00:01<02:09, 278.94it/s]
packing model.layers.55.self_attn.q_proj:   1%|          | 337/36566 [00:01<02:09, 278.94it/s]
packing model.layers.56.self_attn.q_proj:   1%|          | 338/36566 [00:01<02:09, 278.94it/s]
packing model.layers.57.self_attn.q_proj:   1%|          | 339/36566 [00:01<02:09, 278.94it/s]
packing model.layers.58.self_attn.q_proj:   1%|          | 340/36566 [00:01<02:09, 278.94it/s]
packing model.layers.59.self_attn.q_proj:   1%|          | 341/36566 [00:01<02:09, 278.94it/s]
packing model.layers.60.self_attn.q_proj:   1%|          | 342/36566 [00:01<02:09, 278.94it/s]
packing model.layers.61.self_attn.q_proj:   1%|          | 343/36566 [00:01<02:09, 278.94it/s]
packing model.layers.62.self_attn.q_proj:   1%|          | 344/36566 [00:01<02:09, 278.94it/s]
packing model.layers.63.self_attn.q_proj:   1%|          | 345/36566 [00:01<02:09, 278.94it/s]
packing model.layers.63.self_attn.q_proj:   1%|          | 346/36566 [00:01<01:24, 427.95it/s]
packing model.layers.64.self_attn.q_proj:   1%|          | 346/36566 [00:01<01:24, 427.95it/s]
packing model.layers.65.self_attn.q_proj:   1%|          | 347/36566 [00:01<01:24, 427.95it/s]
packing model.layers.66.self_attn.q_proj:   1%|          | 348/36566 [00:01<01:24, 427.95it/s]
packing model.layers.67.self_attn.q_proj:   1%|          | 349/36566 [00:01<01:24, 427.95it/s]
packing model.layers.68.self_attn.q_proj:   1%|          | 350/36566 [00:01<01:24, 427.95it/s]
packing model.layers.69.self_attn.q_proj:   1%|          | 351/36566 [00:01<01:24, 427.95it/s]
packing model.layers.70.self_attn.q_proj:   1%|          | 352/36566 [00:01<01:24, 427.95it/s]
packing model.layers.71.self_attn.q_proj:   1%|          | 353/36566 [00:01<01:24, 427.95it/s]
packing model.layers.72.self_attn.q_proj:   1%|          | 354/36566 [00:01<01:24, 427.95it/s]
packing model.layers.73.self_attn.q_proj:   1%|          | 355/36566 [00:01<01:24, 427.95it/s]
packing model.layers.74.self_attn.q_proj:   1%|          | 356/36566 [00:01<01:24, 427.95it/s]
packing model.layers.75.self_attn.q_proj:   1%|          | 357/36566 [00:01<01:24, 427.95it/s]
packing model.layers.76.self_attn.q_proj:   1%|          | 358/36566 [00:01<01:24, 427.95it/s]
packing model.layers.77.self_attn.q_proj:   1%|          | 359/36566 [00:01<01:24, 427.95it/s]
packing model.layers.78.self_attn.q_proj:   1%|          | 360/36566 [00:01<01:24, 427.95it/s]
packing model.layers.79.self_attn.q_proj:   1%|          | 361/36566 [00:01<01:24, 427.95it/s]
packing model.layers.80.self_attn.q_proj:   1%|          | 362/36566 [00:01<01:24, 427.95it/s]
packing model.layers.81.self_attn.q_proj:   1%|          | 363/36566 [00:01<01:24, 427.95it/s]
packing model.layers.82.self_attn.q_proj:   1%|          | 364/36566 [00:01<01:24, 427.95it/s]
packing model.layers.83.self_attn.q_proj:   1%|          | 365/36566 [00:01<01:24, 427.95it/s]
packing model.layers.84.self_attn.q_proj:   1%|          | 366/36566 [00:01<01:24, 427.95it/s]
packing model.layers.85.self_attn.q_proj:   1%|          | 367/36566 [00:01<01:24, 427.95it/s]
packing model.layers.86.self_attn.q_proj:   1%|          | 368/36566 [00:01<01:24, 427.95it/s]
packing model.layers.87.self_attn.q_proj:   1%|          | 369/36566 [00:01<01:24, 427.95it/s]
packing model.layers.88.self_attn.q_proj:   1%|          | 370/36566 [00:01<01:24, 427.95it/s]
packing model.layers.89.self_attn.q_proj:   1%|          | 371/36566 [00:01<01:24, 427.95it/s]
packing model.layers.90.self_attn.q_proj:   1%|          | 372/36566 [00:01<01:24, 427.95it/s]
packing model.layers.91.self_attn.q_proj:   1%|          | 373/36566 [00:01<01:24, 427.95it/s]
packing model.layers.92.self_attn.q_proj:   1%|          | 374/36566 [00:01<01:24, 427.95it/s]
packing model.layers.93.self_attn.q_proj:   1%|          | 375/36566 [00:01<01:24, 427.95it/s]
packing model.layers.0.self_attn.v_proj:   1%|          | 376/36566 [00:01<01:24, 427.95it/s] 
packing model.layers.1.self_attn.v_proj:   1%|          | 377/36566 [00:01<01:24, 427.95it/s]
packing model.layers.2.self_attn.v_proj:   1%|          | 378/36566 [00:01<01:24, 427.95it/s]
packing model.layers.3.self_attn.v_proj:   1%|          | 379/36566 [00:01<01:24, 427.95it/s]
packing model.layers.4.self_attn.v_proj:   1%|          | 380/36566 [00:01<01:24, 427.95it/s]
packing model.layers.5.self_attn.v_proj:   1%|          | 381/36566 [00:01<01:24, 427.95it/s]
packing model.layers.6.self_attn.v_proj:   1%|          | 382/36566 [00:01<01:24, 427.95it/s]
packing model.layers.7.self_attn.v_proj:   1%|          | 383/36566 [00:01<01:24, 427.95it/s]
packing model.layers.8.self_attn.v_proj:   1%|          | 384/36566 [00:01<01:24, 427.95it/s]
packing model.layers.9.self_attn.v_proj:   1%|          | 385/36566 [00:01<01:24, 427.95it/s]
packing model.layers.10.self_attn.v_proj:   1%|          | 386/36566 [00:01<01:24, 427.95it/s]
packing model.layers.11.self_attn.v_proj:   1%|          | 387/36566 [00:01<01:24, 427.95it/s]
packing model.layers.12.self_attn.v_proj:   1%|          | 388/36566 [00:01<01:24, 427.95it/s]
packing model.layers.13.self_attn.v_proj:   1%|          | 389/36566 [00:01<01:24, 427.95it/s]
packing model.layers.14.self_attn.v_proj:   1%|          | 390/36566 [00:01<01:24, 427.95it/s]
packing model.layers.15.self_attn.v_proj:   1%|          | 391/36566 [00:01<01:24, 427.95it/s]
packing model.layers.16.self_attn.v_proj:   1%|          | 392/36566 [00:01<01:24, 427.95it/s]
packing model.layers.17.self_attn.v_proj:   1%|          | 393/36566 [00:01<01:24, 427.95it/s]
packing model.layers.18.self_attn.v_proj:   1%|          | 394/36566 [00:01<01:24, 427.95it/s]
packing model.layers.19.self_attn.v_proj:   1%|          | 395/36566 [00:01<01:24, 427.95it/s]
packing model.layers.20.self_attn.v_proj:   1%|          | 396/36566 [00:01<01:24, 427.95it/s]
packing model.layers.21.self_attn.v_proj:   1%|          | 397/36566 [00:01<01:24, 427.95it/s]
packing model.layers.22.self_attn.v_proj:   1%|          | 398/36566 [00:01<01:24, 427.95it/s]
packing model.layers.23.self_attn.v_proj:   1%|          | 399/36566 [00:01<01:24, 427.95it/s]
packing model.layers.24.self_attn.v_proj:   1%|          | 400/36566 [00:01<01:24, 427.95it/s]
packing model.layers.25.self_attn.v_proj:   1%|          | 401/36566 [00:01<01:24, 427.95it/s]
packing model.layers.26.self_attn.v_proj:   1%|          | 402/36566 [00:01<01:24, 427.95it/s]
packing model.layers.27.self_attn.v_proj:   1%|          | 403/36566 [00:01<01:24, 427.95it/s]
packing model.layers.28.self_attn.v_proj:   1%|          | 404/36566 [00:01<01:24, 427.95it/s]
packing model.layers.29.self_attn.v_proj:   1%|          | 405/36566 [00:01<01:24, 427.95it/s]
packing model.layers.30.self_attn.v_proj:   1%|          | 406/36566 [00:01<01:24, 427.95it/s]
packing model.layers.31.self_attn.v_proj:   1%|          | 407/36566 [00:01<01:24, 427.95it/s]
packing model.layers.32.self_attn.v_proj:   1%|          | 408/36566 [00:01<01:24, 427.95it/s]
packing model.layers.33.self_attn.v_proj:   1%|          | 409/36566 [00:01<01:24, 427.95it/s]
packing model.layers.34.self_attn.v_proj:   1%|          | 410/36566 [00:01<01:24, 427.95it/s]
packing model.layers.35.self_attn.v_proj:   1%|          | 411/36566 [00:01<01:24, 427.95it/s]
packing model.layers.36.self_attn.v_proj:   1%|          | 412/36566 [00:01<01:24, 427.95it/s]
packing model.layers.37.self_attn.v_proj:   1%|          | 413/36566 [00:01<01:24, 427.95it/s]
packing model.layers.38.self_attn.v_proj:   1%|          | 414/36566 [00:01<01:24, 427.95it/s]
packing model.layers.39.self_attn.v_proj:   1%|          | 415/36566 [00:01<01:24, 427.95it/s]
packing model.layers.40.self_attn.v_proj:   1%|          | 416/36566 [00:01<01:24, 427.95it/s]
packing model.layers.41.self_attn.v_proj:   1%|          | 417/36566 [00:01<01:24, 427.95it/s]
packing model.layers.42.self_attn.v_proj:   1%|          | 418/36566 [00:01<01:24, 427.95it/s]
packing model.layers.43.self_attn.v_proj:   1%|          | 419/36566 [00:01<01:24, 427.95it/s]
packing model.layers.44.self_attn.v_proj:   1%|          | 420/36566 [00:01<01:24, 427.95it/s]
packing model.layers.45.self_attn.v_proj:   1%|          | 421/36566 [00:01<01:24, 427.95it/s]
packing model.layers.46.self_attn.v_proj:   1%|          | 422/36566 [00:01<01:24, 427.95it/s]
packing model.layers.47.self_attn.v_proj:   1%|          | 423/36566 [00:01<01:24, 427.95it/s]
packing model.layers.48.self_attn.v_proj:   1%|          | 424/36566 [00:01<01:24, 427.95it/s]
packing model.layers.49.self_attn.v_proj:   1%|          | 425/36566 [00:01<01:24, 427.95it/s]
packing model.layers.50.self_attn.v_proj:   1%|          | 426/36566 [00:01<01:24, 427.95it/s]
packing model.layers.51.self_attn.v_proj:   1%|          | 427/36566 [00:01<01:24, 427.95it/s]
packing model.layers.52.self_attn.v_proj:   1%|          | 428/36566 [00:01<01:24, 427.95it/s]
packing model.layers.53.self_attn.v_proj:   1%|          | 429/36566 [00:01<01:24, 427.95it/s]
packing model.layers.54.self_attn.v_proj:   1%|          | 430/36566 [00:01<01:24, 427.95it/s]
packing model.layers.55.self_attn.v_proj:   1%|          | 431/36566 [00:01<01:24, 427.95it/s]
packing model.layers.56.self_attn.v_proj:   1%|          | 432/36566 [00:01<01:24, 427.95it/s]
packing model.layers.57.self_attn.v_proj:   1%|          | 433/36566 [00:01<01:24, 427.95it/s]
packing model.layers.58.self_attn.v_proj:   1%|          | 434/36566 [00:01<01:24, 427.95it/s]
packing model.layers.59.self_attn.v_proj:   1%|          | 435/36566 [00:01<01:24, 427.95it/s]
packing model.layers.60.self_attn.v_proj:   1%|          | 436/36566 [00:01<01:24, 427.95it/s]
packing model.layers.61.self_attn.v_proj:   1%|          | 437/36566 [00:01<01:24, 427.95it/s]
packing model.layers.62.self_attn.v_proj:   1%|          | 438/36566 [00:01<01:24, 427.95it/s]
packing model.layers.63.self_attn.v_proj:   1%|          | 439/36566 [00:01<01:24, 427.95it/s]
packing model.layers.64.self_attn.v_proj:   1%|          | 440/36566 [00:01<01:24, 427.95it/s]
packing model.layers.65.self_attn.v_proj:   1%|          | 441/36566 [00:01<01:24, 427.95it/s]
packing model.layers.66.self_attn.v_proj:   1%|          | 442/36566 [00:01<01:24, 427.95it/s]
packing model.layers.67.self_attn.v_proj:   1%|          | 443/36566 [00:01<01:24, 427.95it/s]
packing model.layers.68.self_attn.v_proj:   1%|          | 444/36566 [00:01<01:24, 427.95it/s]
packing model.layers.69.self_attn.v_proj:   1%|          | 445/36566 [00:01<01:24, 427.95it/s]
packing model.layers.70.self_attn.v_proj:   1%|          | 446/36566 [00:01<01:24, 427.95it/s]
packing model.layers.71.self_attn.v_proj:   1%|          | 447/36566 [00:01<01:24, 427.95it/s]
packing model.layers.72.self_attn.v_proj:   1%|          | 448/36566 [00:01<01:24, 427.95it/s]
packing model.layers.73.self_attn.v_proj:   1%|          | 449/36566 [00:01<01:24, 427.95it/s]
packing model.layers.74.self_attn.v_proj:   1%|          | 450/36566 [00:01<01:24, 427.95it/s]
packing model.layers.75.self_attn.v_proj:   1%|          | 451/36566 [00:01<01:24, 427.95it/s]
packing model.layers.76.self_attn.v_proj:   1%|          | 452/36566 [00:01<01:24, 427.95it/s]
packing model.layers.77.self_attn.v_proj:   1%|          | 453/36566 [00:01<01:24, 427.95it/s]
packing model.layers.78.self_attn.v_proj:   1%|          | 454/36566 [00:01<01:24, 427.95it/s]
packing model.layers.79.self_attn.v_proj:   1%|          | 455/36566 [00:01<01:24, 427.95it/s]
packing model.layers.80.self_attn.v_proj:   1%|          | 456/36566 [00:01<01:24, 427.95it/s]
packing model.layers.81.self_attn.v_proj:   1%|          | 457/36566 [00:01<01:24, 427.95it/s]
packing model.layers.82.self_attn.v_proj:   1%|▏         | 458/36566 [00:01<01:24, 427.95it/s]
packing model.layers.83.self_attn.v_proj:   1%|▏         | 459/36566 [00:01<01:24, 427.95it/s]
packing model.layers.84.self_attn.v_proj:   1%|▏         | 460/36566 [00:01<01:24, 427.95it/s]
packing model.layers.85.self_attn.v_proj:   1%|▏         | 461/36566 [00:01<01:24, 427.95it/s]
packing model.layers.85.self_attn.v_proj:   1%|▏         | 462/36566 [00:01<01:03, 569.90it/s]
packing model.layers.86.self_attn.v_proj:   1%|▏         | 462/36566 [00:01<01:03, 569.90it/s]
packing model.layers.87.self_attn.v_proj:   1%|▏         | 463/36566 [00:01<01:03, 569.90it/s]
packing model.layers.88.self_attn.v_proj:   1%|▏         | 464/36566 [00:01<01:03, 569.90it/s]
packing model.layers.89.self_attn.v_proj:   1%|▏         | 465/36566 [00:01<01:03, 569.90it/s]
packing model.layers.90.self_attn.v_proj:   1%|▏         | 466/36566 [00:01<01:03, 569.90it/s]
packing model.layers.91.self_attn.v_proj:   1%|▏         | 467/36566 [00:01<01:03, 569.90it/s]
packing model.layers.92.self_attn.v_proj:   1%|▏         | 468/36566 [00:01<01:03, 569.90it/s]
packing model.layers.93.self_attn.v_proj:   1%|▏         | 469/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.0.gate_proj:   1%|▏         | 470/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.0.up_proj:   1%|▏         | 471/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.0.down_proj:   1%|▏         | 472/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.1.gate_proj:   1%|▏         | 473/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.1.up_proj:   1%|▏         | 474/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.1.down_proj:   1%|▏         | 475/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.2.gate_proj:   1%|▏         | 476/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.2.up_proj:   1%|▏         | 477/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.2.down_proj:   1%|▏         | 478/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.3.gate_proj:   1%|▏         | 479/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.3.up_proj:   1%|▏         | 480/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.3.down_proj:   1%|▏         | 481/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.4.gate_proj:   1%|▏         | 482/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.4.up_proj:   1%|▏         | 483/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.4.down_proj:   1%|▏         | 484/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.5.gate_proj:   1%|▏         | 485/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.5.up_proj:   1%|▏         | 486/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.5.down_proj:   1%|▏         | 487/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.6.gate_proj:   1%|▏         | 488/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.6.up_proj:   1%|▏         | 489/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.6.down_proj:   1%|▏         | 490/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.7.gate_proj:   1%|▏         | 491/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.7.up_proj:   1%|▏         | 492/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.7.down_proj:   1%|▏         | 493/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.8.gate_proj:   1%|▏         | 494/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.8.up_proj:   1%|▏         | 495/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.8.down_proj:   1%|▏         | 496/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.9.gate_proj:   1%|▏         | 497/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.9.up_proj:   1%|▏         | 498/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.9.down_proj:   1%|▏         | 499/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.10.gate_proj:   1%|▏         | 500/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.10.up_proj:   1%|▏         | 501/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.10.down_proj:   1%|▏         | 502/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.11.gate_proj:   1%|▏         | 503/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.11.up_proj:   1%|▏         | 504/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.11.down_proj:   1%|▏         | 505/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.12.gate_proj:   1%|▏         | 506/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.12.up_proj:   1%|▏         | 507/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.12.down_proj:   1%|▏         | 508/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.13.gate_proj:   1%|▏         | 509/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.13.up_proj:   1%|▏         | 510/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.13.down_proj:   1%|▏         | 511/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.14.gate_proj:   1%|▏         | 512/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.14.up_proj:   1%|▏         | 513/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.14.down_proj:   1%|▏         | 514/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.15.gate_proj:   1%|▏         | 515/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.15.up_proj:   1%|▏         | 516/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.15.down_proj:   1%|▏         | 517/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.16.gate_proj:   1%|▏         | 518/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.16.up_proj:   1%|▏         | 519/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.16.down_proj:   1%|▏         | 520/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.17.gate_proj:   1%|▏         | 521/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.17.up_proj:   1%|▏         | 522/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.17.down_proj:   1%|▏         | 523/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.18.gate_proj:   1%|▏         | 524/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.18.up_proj:   1%|▏         | 525/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.18.down_proj:   1%|▏         | 526/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.19.gate_proj:   1%|▏         | 527/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.19.up_proj:   1%|▏         | 528/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.19.down_proj:   1%|▏         | 529/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.20.gate_proj:   1%|▏         | 530/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.20.up_proj:   1%|▏         | 531/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.20.down_proj:   1%|▏         | 532/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.21.gate_proj:   1%|▏         | 533/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.21.up_proj:   1%|▏         | 534/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.21.down_proj:   1%|▏         | 535/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.22.gate_proj:   1%|▏         | 536/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.22.up_proj:   1%|▏         | 537/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.22.down_proj:   1%|▏         | 538/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.23.gate_proj:   1%|▏         | 539/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.23.up_proj:   1%|▏         | 540/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.23.down_proj:   1%|▏         | 541/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.24.gate_proj:   1%|▏         | 542/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.24.up_proj:   1%|▏         | 543/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.24.down_proj:   1%|▏         | 544/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.25.gate_proj:   1%|▏         | 545/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.25.up_proj:   1%|▏         | 546/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.25.down_proj:   1%|▏         | 547/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.26.gate_proj:   1%|▏         | 548/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.26.up_proj:   2%|▏         | 549/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.26.down_proj:   2%|▏         | 550/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.27.gate_proj:   2%|▏         | 551/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.27.up_proj:   2%|▏         | 552/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.27.down_proj:   2%|▏         | 553/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.28.gate_proj:   2%|▏         | 554/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.28.up_proj:   2%|▏         | 555/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.28.down_proj:   2%|▏         | 556/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.29.gate_proj:   2%|▏         | 557/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.29.up_proj:   2%|▏         | 558/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.29.down_proj:   2%|▏         | 559/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.30.gate_proj:   2%|▏         | 560/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.30.up_proj:   2%|▏         | 561/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.30.down_proj:   2%|▏         | 562/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.31.gate_proj:   2%|▏         | 563/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.31.up_proj:   2%|▏         | 564/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.31.down_proj:   2%|▏         | 565/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.32.gate_proj:   2%|▏         | 566/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.32.up_proj:   2%|▏         | 567/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.32.down_proj:   2%|▏         | 568/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.33.gate_proj:   2%|▏         | 569/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.33.up_proj:   2%|▏         | 570/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.33.down_proj:   2%|▏         | 571/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.34.gate_proj:   2%|▏         | 572/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.34.up_proj:   2%|▏         | 573/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.34.down_proj:   2%|▏         | 574/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.35.gate_proj:   2%|▏         | 575/36566 [00:01<01:03, 569.90it/s]
packing model.layers.0.mlp.experts.35.up_proj:   2%|▏         | 576/36566 [00:01<01:03, 569.90it/s]  
packing model.layers.0.mlp.experts.35.up_proj:   2%|▏         | 577/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.35.down_proj:   2%|▏         | 577/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.36.gate_proj:   2%|▏         | 578/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.36.up_proj:   2%|▏         | 579/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.36.down_proj:   2%|▏         | 580/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.37.gate_proj:   2%|▏         | 581/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.37.up_proj:   2%|▏         | 582/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.37.down_proj:   2%|▏         | 583/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.38.gate_proj:   2%|▏         | 584/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.38.up_proj:   2%|▏         | 585/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.38.down_proj:   2%|▏         | 586/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.39.gate_proj:   2%|▏         | 587/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.39.up_proj:   2%|▏         | 588/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.39.down_proj:   2%|▏         | 589/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.40.gate_proj:   2%|▏         | 590/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.40.up_proj:   2%|▏         | 591/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.40.down_proj:   2%|▏         | 592/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.41.gate_proj:   2%|▏         | 593/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.41.up_proj:   2%|▏         | 594/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.41.down_proj:   2%|▏         | 595/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.42.gate_proj:   2%|▏         | 596/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.42.up_proj:   2%|▏         | 597/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.42.down_proj:   2%|▏         | 598/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.43.gate_proj:   2%|▏         | 599/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.43.up_proj:   2%|▏         | 600/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.43.down_proj:   2%|▏         | 601/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.44.gate_proj:   2%|▏         | 602/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.44.up_proj:   2%|▏         | 603/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.44.down_proj:   2%|▏         | 604/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.45.gate_proj:   2%|▏         | 605/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.45.up_proj:   2%|▏         | 606/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.45.down_proj:   2%|▏         | 607/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.46.gate_proj:   2%|▏         | 608/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.46.up_proj:   2%|▏         | 609/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.46.down_proj:   2%|▏         | 610/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.47.gate_proj:   2%|▏         | 611/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.47.up_proj:   2%|▏         | 612/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.47.down_proj:   2%|▏         | 613/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.48.gate_proj:   2%|▏         | 614/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.48.up_proj:   2%|▏         | 615/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.48.down_proj:   2%|▏         | 616/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.49.gate_proj:   2%|▏         | 617/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.49.up_proj:   2%|▏         | 618/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.49.down_proj:   2%|▏         | 619/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.50.gate_proj:   2%|▏         | 620/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.50.up_proj:   2%|▏         | 621/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.50.down_proj:   2%|▏         | 622/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.51.gate_proj:   2%|▏         | 623/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.51.up_proj:   2%|▏         | 624/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.51.down_proj:   2%|▏         | 625/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.52.gate_proj:   2%|▏         | 626/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.52.up_proj:   2%|▏         | 627/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.52.down_proj:   2%|▏         | 628/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.53.gate_proj:   2%|▏         | 629/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.53.up_proj:   2%|▏         | 630/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.53.down_proj:   2%|▏         | 631/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.54.gate_proj:   2%|▏         | 632/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.54.up_proj:   2%|▏         | 633/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.54.down_proj:   2%|▏         | 634/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.55.gate_proj:   2%|▏         | 635/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.55.up_proj:   2%|▏         | 636/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.55.down_proj:   2%|▏         | 637/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.56.gate_proj:   2%|▏         | 638/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.56.up_proj:   2%|▏         | 639/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.56.down_proj:   2%|▏         | 640/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.57.gate_proj:   2%|▏         | 641/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.57.up_proj:   2%|▏         | 642/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.57.down_proj:   2%|▏         | 643/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.58.gate_proj:   2%|▏         | 644/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.58.up_proj:   2%|▏         | 645/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.58.down_proj:   2%|▏         | 646/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.59.gate_proj:   2%|▏         | 647/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.59.up_proj:   2%|▏         | 648/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.59.down_proj:   2%|▏         | 649/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.60.gate_proj:   2%|▏         | 650/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.60.up_proj:   2%|▏         | 651/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.60.down_proj:   2%|▏         | 652/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.61.gate_proj:   2%|▏         | 653/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.61.up_proj:   2%|▏         | 654/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.61.down_proj:   2%|▏         | 655/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.62.gate_proj:   2%|▏         | 656/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.62.up_proj:   2%|▏         | 657/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.62.down_proj:   2%|▏         | 658/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.63.gate_proj:   2%|▏         | 659/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.63.up_proj:   2%|▏         | 660/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.63.down_proj:   2%|▏         | 661/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.64.gate_proj:   2%|▏         | 662/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.64.up_proj:   2%|▏         | 663/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.64.down_proj:   2%|▏         | 664/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.65.gate_proj:   2%|▏         | 665/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.65.up_proj:   2%|▏         | 666/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.65.down_proj:   2%|▏         | 667/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.66.gate_proj:   2%|▏         | 668/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.66.up_proj:   2%|▏         | 669/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.66.down_proj:   2%|▏         | 670/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.67.gate_proj:   2%|▏         | 671/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.67.up_proj:   2%|▏         | 672/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.67.down_proj:   2%|▏         | 673/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.68.gate_proj:   2%|▏         | 674/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.68.up_proj:   2%|▏         | 675/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.68.down_proj:   2%|▏         | 676/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.69.gate_proj:   2%|▏         | 677/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.69.up_proj:   2%|▏         | 678/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.69.down_proj:   2%|▏         | 679/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.70.gate_proj:   2%|▏         | 680/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.70.up_proj:   2%|▏         | 681/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.70.down_proj:   2%|▏         | 682/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.71.gate_proj:   2%|▏         | 683/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.71.up_proj:   2%|▏         | 684/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.71.down_proj:   2%|▏         | 685/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.72.gate_proj:   2%|▏         | 686/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.72.up_proj:   2%|▏         | 687/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.72.down_proj:   2%|▏         | 688/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.73.gate_proj:   2%|▏         | 689/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.73.up_proj:   2%|▏         | 690/36566 [00:01<00:51, 694.88it/s]  
packing model.layers.0.mlp.experts.73.down_proj:   2%|▏         | 691/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.74.gate_proj:   2%|▏         | 692/36566 [00:01<00:51, 694.88it/s]
packing model.layers.0.mlp.experts.74.gate_proj:   2%|▏         | 693/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.74.up_proj:   2%|▏         | 693/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.74.down_proj:   2%|▏         | 694/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.75.gate_proj:   2%|▏         | 695/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.75.up_proj:   2%|▏         | 696/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.75.down_proj:   2%|▏         | 697/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.76.gate_proj:   2%|▏         | 698/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.76.up_proj:   2%|▏         | 699/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.76.down_proj:   2%|▏         | 700/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.77.gate_proj:   2%|▏         | 701/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.77.up_proj:   2%|▏         | 702/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.77.down_proj:   2%|▏         | 703/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.78.gate_proj:   2%|▏         | 704/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.78.up_proj:   2%|▏         | 705/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.78.down_proj:   2%|▏         | 706/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.79.gate_proj:   2%|▏         | 707/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.79.up_proj:   2%|▏         | 708/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.79.down_proj:   2%|▏         | 709/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.80.gate_proj:   2%|▏         | 710/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.80.up_proj:   2%|▏         | 711/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.80.down_proj:   2%|▏         | 712/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.81.gate_proj:   2%|▏         | 713/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.81.up_proj:   2%|▏         | 714/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.81.down_proj:   2%|▏         | 715/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.82.gate_proj:   2%|▏         | 716/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.82.up_proj:   2%|▏         | 717/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.82.down_proj:   2%|▏         | 718/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.83.gate_proj:   2%|▏         | 719/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.83.up_proj:   2%|▏         | 720/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.83.down_proj:   2%|▏         | 721/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.84.gate_proj:   2%|▏         | 722/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.84.up_proj:   2%|▏         | 723/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.84.down_proj:   2%|▏         | 724/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.85.gate_proj:   2%|▏         | 725/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.85.up_proj:   2%|▏         | 726/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.85.down_proj:   2%|▏         | 727/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.86.gate_proj:   2%|▏         | 728/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.86.up_proj:   2%|▏         | 729/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.86.down_proj:   2%|▏         | 730/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.87.gate_proj:   2%|▏         | 731/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.87.up_proj:   2%|▏         | 732/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.87.down_proj:   2%|▏         | 733/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.88.gate_proj:   2%|▏         | 734/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.88.up_proj:   2%|▏         | 735/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.88.down_proj:   2%|▏         | 736/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.89.gate_proj:   2%|▏         | 737/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.89.up_proj:   2%|▏         | 738/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.89.down_proj:   2%|▏         | 739/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.90.gate_proj:   2%|▏         | 740/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.90.up_proj:   2%|▏         | 741/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.90.down_proj:   2%|▏         | 742/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.91.gate_proj:   2%|▏         | 743/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.91.up_proj:   2%|▏         | 744/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.91.down_proj:   2%|▏         | 745/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.92.gate_proj:   2%|▏         | 746/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.92.up_proj:   2%|▏         | 747/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.92.down_proj:   2%|▏         | 748/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.93.gate_proj:   2%|▏         | 749/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.93.up_proj:   2%|▏         | 750/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.93.down_proj:   2%|▏         | 751/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.94.gate_proj:   2%|▏         | 752/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.94.up_proj:   2%|▏         | 753/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.94.down_proj:   2%|▏         | 754/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.95.gate_proj:   2%|▏         | 755/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.95.up_proj:   2%|▏         | 756/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.95.down_proj:   2%|▏         | 757/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.96.gate_proj:   2%|▏         | 758/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.96.up_proj:   2%|▏         | 759/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.96.down_proj:   2%|▏         | 760/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.97.gate_proj:   2%|▏         | 761/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.97.up_proj:   2%|▏         | 762/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.97.down_proj:   2%|▏         | 763/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.98.gate_proj:   2%|▏         | 764/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.98.up_proj:   2%|▏         | 765/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.98.down_proj:   2%|▏         | 766/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.99.gate_proj:   2%|▏         | 767/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.99.up_proj:   2%|▏         | 768/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.99.down_proj:   2%|▏         | 769/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.100.gate_proj:   2%|▏         | 770/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.100.up_proj:   2%|▏         | 771/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.100.down_proj:   2%|▏         | 772/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.101.gate_proj:   2%|▏         | 773/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.101.up_proj:   2%|▏         | 774/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.101.down_proj:   2%|▏         | 775/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.102.gate_proj:   2%|▏         | 776/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.102.up_proj:   2%|▏         | 777/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.102.down_proj:   2%|▏         | 778/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.103.gate_proj:   2%|▏         | 779/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.103.up_proj:   2%|▏         | 780/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.103.down_proj:   2%|▏         | 781/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.104.gate_proj:   2%|▏         | 782/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.104.up_proj:   2%|▏         | 783/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.104.down_proj:   2%|▏         | 784/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.105.gate_proj:   2%|▏         | 785/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.105.up_proj:   2%|▏         | 786/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.105.down_proj:   2%|▏         | 787/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.106.gate_proj:   2%|▏         | 788/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.106.up_proj:   2%|▏         | 789/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.106.down_proj:   2%|▏         | 790/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.107.gate_proj:   2%|▏         | 791/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.107.up_proj:   2%|▏         | 792/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.107.down_proj:   2%|▏         | 793/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.108.gate_proj:   2%|▏         | 794/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.108.up_proj:   2%|▏         | 795/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.108.down_proj:   2%|▏         | 796/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.109.gate_proj:   2%|▏         | 797/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.109.up_proj:   2%|▏         | 798/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.109.down_proj:   2%|▏         | 799/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.110.gate_proj:   2%|▏         | 800/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.110.up_proj:   2%|▏         | 801/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.110.down_proj:   2%|▏         | 802/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.111.gate_proj:   2%|▏         | 803/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.111.up_proj:   2%|▏         | 804/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.111.down_proj:   2%|▏         | 805/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.112.gate_proj:   2%|▏         | 806/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.112.up_proj:   2%|▏         | 807/36566 [00:01<00:44, 804.38it/s]  
packing model.layers.0.mlp.experts.112.down_proj:   2%|▏         | 808/36566 [00:01<00:44, 804.38it/s]
packing model.layers.0.mlp.experts.112.down_proj:   2%|▏         | 809/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.113.gate_proj:   2%|▏         | 809/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.113.up_proj:   2%|▏         | 810/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.113.down_proj:   2%|▏         | 811/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.114.gate_proj:   2%|▏         | 812/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.114.up_proj:   2%|▏         | 813/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.114.down_proj:   2%|▏         | 814/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.115.gate_proj:   2%|▏         | 815/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.115.up_proj:   2%|▏         | 816/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.115.down_proj:   2%|▏         | 817/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.116.gate_proj:   2%|▏         | 818/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.116.up_proj:   2%|▏         | 819/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.116.down_proj:   2%|▏         | 820/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.117.gate_proj:   2%|▏         | 821/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.117.up_proj:   2%|▏         | 822/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.117.down_proj:   2%|▏         | 823/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.118.gate_proj:   2%|▏         | 824/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.118.up_proj:   2%|▏         | 825/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.118.down_proj:   2%|▏         | 826/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.119.gate_proj:   2%|▏         | 827/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.119.up_proj:   2%|▏         | 828/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.119.down_proj:   2%|▏         | 829/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.120.gate_proj:   2%|▏         | 830/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.120.up_proj:   2%|▏         | 831/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.120.down_proj:   2%|▏         | 832/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.121.gate_proj:   2%|▏         | 833/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.121.up_proj:   2%|▏         | 834/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.121.down_proj:   2%|▏         | 835/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.122.gate_proj:   2%|▏         | 836/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.122.up_proj:   2%|▏         | 837/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.122.down_proj:   2%|▏         | 838/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.123.gate_proj:   2%|▏         | 839/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.123.up_proj:   2%|▏         | 840/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.123.down_proj:   2%|▏         | 841/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.124.gate_proj:   2%|▏         | 842/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.124.up_proj:   2%|▏         | 843/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.124.down_proj:   2%|▏         | 844/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.125.gate_proj:   2%|▏         | 845/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.125.up_proj:   2%|▏         | 846/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.125.down_proj:   2%|▏         | 847/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.126.gate_proj:   2%|▏         | 848/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.126.up_proj:   2%|▏         | 849/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.126.down_proj:   2%|▏         | 850/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.127.gate_proj:   2%|▏         | 851/36566 [00:01<00:40, 892.41it/s]
packing model.layers.0.mlp.experts.127.up_proj:   2%|▏         | 852/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.0.mlp.experts.127.down_proj:   2%|▏         | 853/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.0.gate_proj:   2%|▏         | 854/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.0.up_proj:   2%|▏         | 855/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.0.down_proj:   2%|▏         | 856/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.1.gate_proj:   2%|▏         | 857/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.1.up_proj:   2%|▏         | 858/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.1.down_proj:   2%|▏         | 859/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.2.gate_proj:   2%|▏         | 860/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.2.up_proj:   2%|▏         | 861/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.2.down_proj:   2%|▏         | 862/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.3.gate_proj:   2%|▏         | 863/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.3.up_proj:   2%|▏         | 864/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.3.down_proj:   2%|▏         | 865/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.4.gate_proj:   2%|▏         | 866/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.4.up_proj:   2%|▏         | 867/36566 [00:01<00:40, 892.41it/s]  
packing model.layers.1.mlp.experts.4.down_proj:   2%|▏         | 868/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.5.gate_proj:   2%|▏         | 869/36566 [00:01<00:40, 892.41it/s]
packing model.layers.1.mlp.experts.5.up_proj:   2%|▏         | 870/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.5.down_proj:   2%|▏         | 871/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.6.gate_proj:   2%|▏         | 872/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.6.up_proj:   2%|▏         | 873/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.6.down_proj:   2%|▏         | 874/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.7.gate_proj:   2%|▏         | 875/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.7.up_proj:   2%|▏         | 876/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.7.down_proj:   2%|▏         | 877/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.8.gate_proj:   2%|▏         | 878/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.8.up_proj:   2%|▏         | 879/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.8.down_proj:   2%|▏         | 880/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.9.gate_proj:   2%|▏         | 881/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.9.up_proj:   2%|▏         | 882/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.9.down_proj:   2%|▏         | 883/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.10.gate_proj:   2%|▏         | 884/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.10.up_proj:   2%|▏         | 885/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.10.down_proj:   2%|▏         | 886/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.11.gate_proj:   2%|▏         | 887/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.11.up_proj:   2%|▏         | 888/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.11.down_proj:   2%|▏         | 889/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.12.gate_proj:   2%|▏         | 890/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.12.up_proj:   2%|▏         | 891/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.12.down_proj:   2%|▏         | 892/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.13.gate_proj:   2%|▏         | 893/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.13.up_proj:   2%|▏         | 894/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.13.down_proj:   2%|▏         | 895/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.14.gate_proj:   2%|▏         | 896/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.14.up_proj:   2%|▏         | 897/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.14.down_proj:   2%|▏         | 898/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.15.gate_proj:   2%|▏         | 899/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.15.up_proj:   2%|▏         | 900/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.15.down_proj:   2%|▏         | 901/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.16.gate_proj:   2%|▏         | 902/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.16.up_proj:   2%|▏         | 903/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.16.down_proj:   2%|▏         | 904/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.17.gate_proj:   2%|▏         | 905/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.17.up_proj:   2%|▏         | 906/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.17.down_proj:   2%|▏         | 907/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.18.gate_proj:   2%|▏         | 908/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.18.up_proj:   2%|▏         | 909/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.18.down_proj:   2%|▏         | 910/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.19.gate_proj:   2%|▏         | 911/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.19.up_proj:   2%|▏         | 912/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.19.down_proj:   2%|▏         | 913/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.20.gate_proj:   2%|▏         | 914/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.20.up_proj:   3%|▎         | 915/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.20.down_proj:   3%|▎         | 916/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.21.gate_proj:   3%|▎         | 917/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.21.up_proj:   3%|▎         | 918/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.21.down_proj:   3%|▎         | 919/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.22.gate_proj:   3%|▎         | 920/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.22.up_proj:   3%|▎         | 921/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.22.down_proj:   3%|▎         | 922/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.23.gate_proj:   3%|▎         | 923/36566 [00:01<00:39, 892.41it/s]
packing model.layers.1.mlp.experts.23.up_proj:   3%|▎         | 924/36566 [00:01<00:39, 892.41it/s]  
packing model.layers.1.mlp.experts.23.up_proj:   3%|▎         | 925/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.23.down_proj:   3%|▎         | 925/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.24.gate_proj:   3%|▎         | 926/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.24.up_proj:   3%|▎         | 927/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.24.down_proj:   3%|▎         | 928/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.25.gate_proj:   3%|▎         | 929/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.25.up_proj:   3%|▎         | 930/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.25.down_proj:   3%|▎         | 931/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.26.gate_proj:   3%|▎         | 932/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.26.up_proj:   3%|▎         | 933/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.26.down_proj:   3%|▎         | 934/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.27.gate_proj:   3%|▎         | 935/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.27.up_proj:   3%|▎         | 936/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.27.down_proj:   3%|▎         | 937/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.28.gate_proj:   3%|▎         | 938/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.28.up_proj:   3%|▎         | 939/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.28.down_proj:   3%|▎         | 940/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.29.gate_proj:   3%|▎         | 941/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.29.up_proj:   3%|▎         | 942/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.29.down_proj:   3%|▎         | 943/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.30.gate_proj:   3%|▎         | 944/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.30.up_proj:   3%|▎         | 945/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.30.down_proj:   3%|▎         | 946/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.31.gate_proj:   3%|▎         | 947/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.31.up_proj:   3%|▎         | 948/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.31.down_proj:   3%|▎         | 949/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.32.gate_proj:   3%|▎         | 950/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.32.up_proj:   3%|▎         | 951/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.32.down_proj:   3%|▎         | 952/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.33.gate_proj:   3%|▎         | 953/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.33.up_proj:   3%|▎         | 954/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.33.down_proj:   3%|▎         | 955/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.34.gate_proj:   3%|▎         | 956/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.34.up_proj:   3%|▎         | 957/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.34.down_proj:   3%|▎         | 958/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.35.gate_proj:   3%|▎         | 959/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.35.up_proj:   3%|▎         | 960/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.35.down_proj:   3%|▎         | 961/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.36.gate_proj:   3%|▎         | 962/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.36.up_proj:   3%|▎         | 963/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.36.down_proj:   3%|▎         | 964/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.37.gate_proj:   3%|▎         | 965/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.37.up_proj:   3%|▎         | 966/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.37.down_proj:   3%|▎         | 967/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.38.gate_proj:   3%|▎         | 968/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.38.up_proj:   3%|▎         | 969/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.38.down_proj:   3%|▎         | 970/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.39.gate_proj:   3%|▎         | 971/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.39.up_proj:   3%|▎         | 972/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.39.down_proj:   3%|▎         | 973/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.40.gate_proj:   3%|▎         | 974/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.40.up_proj:   3%|▎         | 975/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.40.down_proj:   3%|▎         | 976/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.41.gate_proj:   3%|▎         | 977/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.41.up_proj:   3%|▎         | 978/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.41.down_proj:   3%|▎         | 979/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.42.gate_proj:   3%|▎         | 980/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.42.up_proj:   3%|▎         | 981/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.42.down_proj:   3%|▎         | 982/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.43.gate_proj:   3%|▎         | 983/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.43.up_proj:   3%|▎         | 984/36566 [00:01<00:37, 961.62it/s]  
packing model.layers.1.mlp.experts.43.down_proj:   3%|▎         | 985/36566 [00:01<00:37, 961.62it/s]
packing model.layers.1.mlp.experts.44.gate_proj:   3%|▎         | 986/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.44.up_proj:   3%|▎         | 987/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.44.down_proj:   3%|▎         | 988/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.45.gate_proj:   3%|▎         | 989/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.45.up_proj:   3%|▎         | 990/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.45.down_proj:   3%|▎         | 991/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.46.gate_proj:   3%|▎         | 992/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.46.up_proj:   3%|▎         | 993/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.46.down_proj:   3%|▎         | 994/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.47.gate_proj:   3%|▎         | 995/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.47.up_proj:   3%|▎         | 996/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.47.down_proj:   3%|▎         | 997/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.48.gate_proj:   3%|▎         | 998/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.48.up_proj:   3%|▎         | 999/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.48.down_proj:   3%|▎         | 1000/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.49.gate_proj:   3%|▎         | 1001/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.49.up_proj:   3%|▎         | 1002/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.49.down_proj:   3%|▎         | 1003/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.50.gate_proj:   3%|▎         | 1004/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.50.up_proj:   3%|▎         | 1005/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.50.down_proj:   3%|▎         | 1006/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.51.gate_proj:   3%|▎         | 1007/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.51.up_proj:   3%|▎         | 1008/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.51.down_proj:   3%|▎         | 1009/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.52.gate_proj:   3%|▎         | 1010/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.52.up_proj:   3%|▎         | 1011/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.52.down_proj:   3%|▎         | 1012/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.53.gate_proj:   3%|▎         | 1013/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.53.up_proj:   3%|▎         | 1014/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.53.down_proj:   3%|▎         | 1015/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.54.gate_proj:   3%|▎         | 1016/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.54.up_proj:   3%|▎         | 1017/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.54.down_proj:   3%|▎         | 1018/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.55.gate_proj:   3%|▎         | 1019/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.55.up_proj:   3%|▎         | 1020/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.55.down_proj:   3%|▎         | 1021/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.56.gate_proj:   3%|▎         | 1022/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.56.up_proj:   3%|▎         | 1023/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.56.down_proj:   3%|▎         | 1024/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.57.gate_proj:   3%|▎         | 1025/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.57.up_proj:   3%|▎         | 1026/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.57.down_proj:   3%|▎         | 1027/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.58.gate_proj:   3%|▎         | 1028/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.58.up_proj:   3%|▎         | 1029/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.58.down_proj:   3%|▎         | 1030/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.59.gate_proj:   3%|▎         | 1031/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.59.up_proj:   3%|▎         | 1032/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.59.down_proj:   3%|▎         | 1033/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.60.gate_proj:   3%|▎         | 1034/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.60.up_proj:   3%|▎         | 1035/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.60.down_proj:   3%|▎         | 1036/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.61.gate_proj:   3%|▎         | 1037/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.61.up_proj:   3%|▎         | 1038/36566 [00:01<00:36, 961.62it/s]  
packing model.layers.1.mlp.experts.61.down_proj:   3%|▎         | 1039/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.62.gate_proj:   3%|▎         | 1040/36566 [00:01<00:36, 961.62it/s]
packing model.layers.1.mlp.experts.62.gate_proj:   3%|▎         | 1041/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.62.up_proj:   3%|▎         | 1041/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.62.down_proj:   3%|▎         | 1042/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.63.gate_proj:   3%|▎         | 1043/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.63.up_proj:   3%|▎         | 1044/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.63.down_proj:   3%|▎         | 1045/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.64.gate_proj:   3%|▎         | 1046/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.64.up_proj:   3%|▎         | 1047/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.64.down_proj:   3%|▎         | 1048/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.65.gate_proj:   3%|▎         | 1049/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.65.up_proj:   3%|▎         | 1050/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.65.down_proj:   3%|▎         | 1051/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.66.gate_proj:   3%|▎         | 1052/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.66.up_proj:   3%|▎         | 1053/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.66.down_proj:   3%|▎         | 1054/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.67.gate_proj:   3%|▎         | 1055/36566 [00:01<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.67.up_proj:   3%|▎         | 1056/36566 [00:01<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.67.down_proj:   3%|▎         | 1057/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.68.gate_proj:   3%|▎         | 1058/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.68.up_proj:   3%|▎         | 1059/36566 [00:02<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.68.down_proj:   3%|▎         | 1060/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.69.gate_proj:   3%|▎         | 1061/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.69.up_proj:   3%|▎         | 1062/36566 [00:02<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.69.down_proj:   3%|▎         | 1063/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.70.gate_proj:   3%|▎         | 1064/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.70.up_proj:   3%|▎         | 1065/36566 [00:02<00:35, 1014.25it/s]  
packing model.layers.1.mlp.experts.70.down_proj:   3%|▎         | 1066/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.71.gate_proj:   3%|▎         | 1067/36566 [00:02<00:35, 1014.25it/s]
packing model.layers.1.mlp.experts.71.up_proj:   3%|▎         | 1068/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.71.down_proj:   3%|▎         | 1069/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.72.gate_proj:   3%|▎         | 1070/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.72.up_proj:   3%|▎         | 1071/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.72.down_proj:   3%|▎         | 1072/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.73.gate_proj:   3%|▎         | 1073/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.73.up_proj:   3%|▎         | 1074/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.73.down_proj:   3%|▎         | 1075/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.74.gate_proj:   3%|▎         | 1076/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.74.up_proj:   3%|▎         | 1077/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.74.down_proj:   3%|▎         | 1078/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.75.gate_proj:   3%|▎         | 1079/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.75.up_proj:   3%|▎         | 1080/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.75.down_proj:   3%|▎         | 1081/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.76.gate_proj:   3%|▎         | 1082/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.76.up_proj:   3%|▎         | 1083/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.76.down_proj:   3%|▎         | 1084/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.77.gate_proj:   3%|▎         | 1085/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.77.up_proj:   3%|▎         | 1086/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.77.down_proj:   3%|▎         | 1087/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.78.gate_proj:   3%|▎         | 1088/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.78.up_proj:   3%|▎         | 1089/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.78.down_proj:   3%|▎         | 1090/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.79.gate_proj:   3%|▎         | 1091/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.79.up_proj:   3%|▎         | 1092/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.79.down_proj:   3%|▎         | 1093/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.80.gate_proj:   3%|▎         | 1094/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.80.up_proj:   3%|▎         | 1095/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.80.down_proj:   3%|▎         | 1096/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.81.gate_proj:   3%|▎         | 1097/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.81.up_proj:   3%|▎         | 1098/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.81.down_proj:   3%|▎         | 1099/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.82.gate_proj:   3%|▎         | 1100/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.82.up_proj:   3%|▎         | 1101/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.82.down_proj:   3%|▎         | 1102/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.83.gate_proj:   3%|▎         | 1103/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.83.up_proj:   3%|▎         | 1104/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.83.down_proj:   3%|▎         | 1105/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.84.gate_proj:   3%|▎         | 1106/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.84.up_proj:   3%|▎         | 1107/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.84.down_proj:   3%|▎         | 1108/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.85.gate_proj:   3%|▎         | 1109/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.85.up_proj:   3%|▎         | 1110/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.85.down_proj:   3%|▎         | 1111/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.86.gate_proj:   3%|▎         | 1112/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.86.up_proj:   3%|▎         | 1113/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.86.down_proj:   3%|▎         | 1114/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.87.gate_proj:   3%|▎         | 1115/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.87.up_proj:   3%|▎         | 1116/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.87.down_proj:   3%|▎         | 1117/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.88.gate_proj:   3%|▎         | 1118/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.88.up_proj:   3%|▎         | 1119/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.88.down_proj:   3%|▎         | 1120/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.89.gate_proj:   3%|▎         | 1121/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.89.up_proj:   3%|▎         | 1122/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.89.down_proj:   3%|▎         | 1123/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.90.gate_proj:   3%|▎         | 1124/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.90.up_proj:   3%|▎         | 1125/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.90.down_proj:   3%|▎         | 1126/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.91.gate_proj:   3%|▎         | 1127/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.91.up_proj:   3%|▎         | 1128/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.91.down_proj:   3%|▎         | 1129/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.92.gate_proj:   3%|▎         | 1130/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.92.up_proj:   3%|▎         | 1131/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.92.down_proj:   3%|▎         | 1132/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.93.gate_proj:   3%|▎         | 1133/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.93.up_proj:   3%|▎         | 1134/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.93.down_proj:   3%|▎         | 1135/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.94.gate_proj:   3%|▎         | 1136/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.94.up_proj:   3%|▎         | 1137/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.94.down_proj:   3%|▎         | 1138/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.95.gate_proj:   3%|▎         | 1139/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.95.up_proj:   3%|▎         | 1140/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.95.down_proj:   3%|▎         | 1141/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.96.gate_proj:   3%|▎         | 1142/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.96.up_proj:   3%|▎         | 1143/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.96.down_proj:   3%|▎         | 1144/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.97.gate_proj:   3%|▎         | 1145/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.97.up_proj:   3%|▎         | 1146/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.97.down_proj:   3%|▎         | 1147/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.98.gate_proj:   3%|▎         | 1148/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.98.up_proj:   3%|▎         | 1149/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.98.down_proj:   3%|▎         | 1150/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.99.gate_proj:   3%|▎         | 1151/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.99.up_proj:   3%|▎         | 1152/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.99.down_proj:   3%|▎         | 1153/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.100.gate_proj:   3%|▎         | 1154/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.100.up_proj:   3%|▎         | 1155/36566 [00:02<00:34, 1014.25it/s]  
packing model.layers.1.mlp.experts.100.down_proj:   3%|▎         | 1156/36566 [00:02<00:34, 1014.25it/s]
packing model.layers.1.mlp.experts.100.down_proj:   3%|▎         | 1157/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.101.gate_proj:   3%|▎         | 1157/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.101.up_proj:   3%|▎         | 1158/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.101.down_proj:   3%|▎         | 1159/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.102.gate_proj:   3%|▎         | 1160/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.102.up_proj:   3%|▎         | 1161/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.102.down_proj:   3%|▎         | 1162/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.103.gate_proj:   3%|▎         | 1163/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.103.up_proj:   3%|▎         | 1164/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.103.down_proj:   3%|▎         | 1165/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.104.gate_proj:   3%|▎         | 1166/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.104.up_proj:   3%|▎         | 1167/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.104.down_proj:   3%|▎         | 1168/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.105.gate_proj:   3%|▎         | 1169/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.105.up_proj:   3%|▎         | 1170/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.105.down_proj:   3%|▎         | 1171/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.106.gate_proj:   3%|▎         | 1172/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.106.up_proj:   3%|▎         | 1173/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.106.down_proj:   3%|▎         | 1174/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.107.gate_proj:   3%|▎         | 1175/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.107.up_proj:   3%|▎         | 1176/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.107.down_proj:   3%|▎         | 1177/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.108.gate_proj:   3%|▎         | 1178/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.108.up_proj:   3%|▎         | 1179/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.108.down_proj:   3%|▎         | 1180/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.109.gate_proj:   3%|▎         | 1181/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.109.up_proj:   3%|▎         | 1182/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.109.down_proj:   3%|▎         | 1183/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.110.gate_proj:   3%|▎         | 1184/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.110.up_proj:   3%|▎         | 1185/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.110.down_proj:   3%|▎         | 1186/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.111.gate_proj:   3%|▎         | 1187/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.111.up_proj:   3%|▎         | 1188/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.111.down_proj:   3%|▎         | 1189/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.112.gate_proj:   3%|▎         | 1190/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.112.up_proj:   3%|▎         | 1191/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.112.down_proj:   3%|▎         | 1192/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.113.gate_proj:   3%|▎         | 1193/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.113.up_proj:   3%|▎         | 1194/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.113.down_proj:   3%|▎         | 1195/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.114.gate_proj:   3%|▎         | 1196/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.114.up_proj:   3%|▎         | 1197/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.114.down_proj:   3%|▎         | 1198/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.115.gate_proj:   3%|▎         | 1199/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.115.up_proj:   3%|▎         | 1200/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.115.down_proj:   3%|▎         | 1201/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.116.gate_proj:   3%|▎         | 1202/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.116.up_proj:   3%|▎         | 1203/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.116.down_proj:   3%|▎         | 1204/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.117.gate_proj:   3%|▎         | 1205/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.117.up_proj:   3%|▎         | 1206/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.117.down_proj:   3%|▎         | 1207/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.118.gate_proj:   3%|▎         | 1208/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.118.up_proj:   3%|▎         | 1209/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.118.down_proj:   3%|▎         | 1210/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.119.gate_proj:   3%|▎         | 1211/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.119.up_proj:   3%|▎         | 1212/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.119.down_proj:   3%|▎         | 1213/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.120.gate_proj:   3%|▎         | 1214/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.120.up_proj:   3%|▎         | 1215/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.120.down_proj:   3%|▎         | 1216/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.121.gate_proj:   3%|▎         | 1217/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.121.up_proj:   3%|▎         | 1218/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.121.down_proj:   3%|▎         | 1219/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.122.gate_proj:   3%|▎         | 1220/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.122.up_proj:   3%|▎         | 1221/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.122.down_proj:   3%|▎         | 1222/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.123.gate_proj:   3%|▎         | 1223/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.123.up_proj:   3%|▎         | 1224/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.123.down_proj:   3%|▎         | 1225/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.124.gate_proj:   3%|▎         | 1226/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.124.up_proj:   3%|▎         | 1227/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.124.down_proj:   3%|▎         | 1228/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.125.gate_proj:   3%|▎         | 1229/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.125.up_proj:   3%|▎         | 1230/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.125.down_proj:   3%|▎         | 1231/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.126.gate_proj:   3%|▎         | 1232/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.126.up_proj:   3%|▎         | 1233/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.126.down_proj:   3%|▎         | 1234/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.127.gate_proj:   3%|▎         | 1235/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.1.mlp.experts.127.up_proj:   3%|▎         | 1236/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.1.mlp.experts.127.down_proj:   3%|▎         | 1237/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.0.gate_proj:   3%|▎         | 1238/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.0.up_proj:   3%|▎         | 1239/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.0.down_proj:   3%|▎         | 1240/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.1.gate_proj:   3%|▎         | 1241/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.1.up_proj:   3%|▎         | 1242/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.1.down_proj:   3%|▎         | 1243/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.2.gate_proj:   3%|▎         | 1244/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.2.up_proj:   3%|▎         | 1245/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.2.down_proj:   3%|▎         | 1246/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.3.gate_proj:   3%|▎         | 1247/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.3.up_proj:   3%|▎         | 1248/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.3.down_proj:   3%|▎         | 1249/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.4.gate_proj:   3%|▎         | 1250/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.4.up_proj:   3%|▎         | 1251/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.4.down_proj:   3%|▎         | 1252/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.5.gate_proj:   3%|▎         | 1253/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.5.up_proj:   3%|▎         | 1254/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.5.down_proj:   3%|▎         | 1255/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.6.gate_proj:   3%|▎         | 1256/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.6.up_proj:   3%|▎         | 1257/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.6.down_proj:   3%|▎         | 1258/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.7.gate_proj:   3%|▎         | 1259/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.7.up_proj:   3%|▎         | 1260/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.7.down_proj:   3%|▎         | 1261/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.8.gate_proj:   3%|▎         | 1262/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.8.up_proj:   3%|▎         | 1263/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.8.down_proj:   3%|▎         | 1264/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.9.gate_proj:   3%|▎         | 1265/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.9.up_proj:   3%|▎         | 1266/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.9.down_proj:   3%|▎         | 1267/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.10.gate_proj:   3%|▎         | 1268/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.10.up_proj:   3%|▎         | 1269/36566 [00:02<00:33, 1054.24it/s]  
packing model.layers.2.mlp.experts.10.down_proj:   3%|▎         | 1270/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.11.gate_proj:   3%|▎         | 1271/36566 [00:02<00:33, 1054.24it/s]
packing model.layers.2.mlp.experts.11.gate_proj:   3%|▎         | 1272/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.11.up_proj:   3%|▎         | 1272/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.11.down_proj:   3%|▎         | 1273/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.12.gate_proj:   3%|▎         | 1274/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.12.up_proj:   3%|▎         | 1275/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.12.down_proj:   3%|▎         | 1276/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.13.gate_proj:   3%|▎         | 1277/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.13.up_proj:   3%|▎         | 1278/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.13.down_proj:   3%|▎         | 1279/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.14.gate_proj:   4%|▎         | 1280/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.14.up_proj:   4%|▎         | 1281/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.14.down_proj:   4%|▎         | 1282/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.15.gate_proj:   4%|▎         | 1283/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.15.up_proj:   4%|▎         | 1284/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.15.down_proj:   4%|▎         | 1285/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.16.gate_proj:   4%|▎         | 1286/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.16.up_proj:   4%|▎         | 1287/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.16.down_proj:   4%|▎         | 1288/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.17.gate_proj:   4%|▎         | 1289/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.17.up_proj:   4%|▎         | 1290/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.17.down_proj:   4%|▎         | 1291/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.18.gate_proj:   4%|▎         | 1292/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.18.up_proj:   4%|▎         | 1293/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.18.down_proj:   4%|▎         | 1294/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.19.gate_proj:   4%|▎         | 1295/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.19.up_proj:   4%|▎         | 1296/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.19.down_proj:   4%|▎         | 1297/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.20.gate_proj:   4%|▎         | 1298/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.20.up_proj:   4%|▎         | 1299/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.20.down_proj:   4%|▎         | 1300/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.21.gate_proj:   4%|▎         | 1301/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.21.up_proj:   4%|▎         | 1302/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.21.down_proj:   4%|▎         | 1303/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.22.gate_proj:   4%|▎         | 1304/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.22.up_proj:   4%|▎         | 1305/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.22.down_proj:   4%|▎         | 1306/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.23.gate_proj:   4%|▎         | 1307/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.23.up_proj:   4%|▎         | 1308/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.23.down_proj:   4%|▎         | 1309/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.24.gate_proj:   4%|▎         | 1310/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.24.up_proj:   4%|▎         | 1311/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.24.down_proj:   4%|▎         | 1312/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.25.gate_proj:   4%|▎         | 1313/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.25.up_proj:   4%|▎         | 1314/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.25.down_proj:   4%|▎         | 1315/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.26.gate_proj:   4%|▎         | 1316/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.26.up_proj:   4%|▎         | 1317/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.26.down_proj:   4%|▎         | 1318/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.27.gate_proj:   4%|▎         | 1319/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.27.up_proj:   4%|▎         | 1320/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.27.down_proj:   4%|▎         | 1321/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.28.gate_proj:   4%|▎         | 1322/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.28.up_proj:   4%|▎         | 1323/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.28.down_proj:   4%|▎         | 1324/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.29.gate_proj:   4%|▎         | 1325/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.29.up_proj:   4%|▎         | 1326/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.29.down_proj:   4%|▎         | 1327/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.30.gate_proj:   4%|▎         | 1328/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.30.up_proj:   4%|▎         | 1329/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.30.down_proj:   4%|▎         | 1330/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.31.gate_proj:   4%|▎         | 1331/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.31.up_proj:   4%|▎         | 1332/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.31.down_proj:   4%|▎         | 1333/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.32.gate_proj:   4%|▎         | 1334/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.32.up_proj:   4%|▎         | 1335/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.32.down_proj:   4%|▎         | 1336/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.33.gate_proj:   4%|▎         | 1337/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.33.up_proj:   4%|▎         | 1338/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.33.down_proj:   4%|▎         | 1339/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.34.gate_proj:   4%|▎         | 1340/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.34.up_proj:   4%|▎         | 1341/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.34.down_proj:   4%|▎         | 1342/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.35.gate_proj:   4%|▎         | 1343/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.35.up_proj:   4%|▎         | 1344/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.35.down_proj:   4%|▎         | 1345/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.36.gate_proj:   4%|▎         | 1346/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.36.up_proj:   4%|▎         | 1347/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.36.down_proj:   4%|▎         | 1348/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.37.gate_proj:   4%|▎         | 1349/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.37.up_proj:   4%|▎         | 1350/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.37.down_proj:   4%|▎         | 1351/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.38.gate_proj:   4%|▎         | 1352/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.38.up_proj:   4%|▎         | 1353/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.38.down_proj:   4%|▎         | 1354/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.39.gate_proj:   4%|▎         | 1355/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.39.up_proj:   4%|▎         | 1356/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.39.down_proj:   4%|▎         | 1357/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.40.gate_proj:   4%|▎         | 1358/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.40.up_proj:   4%|▎         | 1359/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.40.down_proj:   4%|▎         | 1360/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.41.gate_proj:   4%|▎         | 1361/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.41.up_proj:   4%|▎         | 1362/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.41.down_proj:   4%|▎         | 1363/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.42.gate_proj:   4%|▎         | 1364/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.42.up_proj:   4%|▎         | 1365/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.42.down_proj:   4%|▎         | 1366/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.43.gate_proj:   4%|▎         | 1367/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.43.up_proj:   4%|▎         | 1368/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.43.down_proj:   4%|▎         | 1369/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.44.gate_proj:   4%|▎         | 1370/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.44.up_proj:   4%|▎         | 1371/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.44.down_proj:   4%|▍         | 1372/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.45.gate_proj:   4%|▍         | 1373/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.45.up_proj:   4%|▍         | 1374/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.45.down_proj:   4%|▍         | 1375/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.46.gate_proj:   4%|▍         | 1376/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.46.up_proj:   4%|▍         | 1377/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.46.down_proj:   4%|▍         | 1378/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.47.gate_proj:   4%|▍         | 1379/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.47.up_proj:   4%|▍         | 1380/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.47.down_proj:   4%|▍         | 1381/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.48.gate_proj:   4%|▍         | 1382/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.48.up_proj:   4%|▍         | 1383/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.48.down_proj:   4%|▍         | 1384/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.49.gate_proj:   4%|▍         | 1385/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.49.up_proj:   4%|▍         | 1386/36566 [00:02<00:32, 1081.34it/s]  
packing model.layers.2.mlp.experts.49.down_proj:   4%|▍         | 1387/36566 [00:02<00:32, 1081.34it/s]
packing model.layers.2.mlp.experts.49.down_proj:   4%|▍         | 1388/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.50.gate_proj:   4%|▍         | 1388/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.50.up_proj:   4%|▍         | 1389/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.50.down_proj:   4%|▍         | 1390/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.51.gate_proj:   4%|▍         | 1391/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.51.up_proj:   4%|▍         | 1392/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.51.down_proj:   4%|▍         | 1393/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.52.gate_proj:   4%|▍         | 1394/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.52.up_proj:   4%|▍         | 1395/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.52.down_proj:   4%|▍         | 1396/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.53.gate_proj:   4%|▍         | 1397/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.53.up_proj:   4%|▍         | 1398/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.53.down_proj:   4%|▍         | 1399/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.54.gate_proj:   4%|▍         | 1400/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.54.up_proj:   4%|▍         | 1401/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.54.down_proj:   4%|▍         | 1402/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.55.gate_proj:   4%|▍         | 1403/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.55.up_proj:   4%|▍         | 1404/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.55.down_proj:   4%|▍         | 1405/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.56.gate_proj:   4%|▍         | 1406/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.56.up_proj:   4%|▍         | 1407/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.56.down_proj:   4%|▍         | 1408/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.57.gate_proj:   4%|▍         | 1409/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.57.up_proj:   4%|▍         | 1410/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.57.down_proj:   4%|▍         | 1411/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.58.gate_proj:   4%|▍         | 1412/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.58.up_proj:   4%|▍         | 1413/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.58.down_proj:   4%|▍         | 1414/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.59.gate_proj:   4%|▍         | 1415/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.59.up_proj:   4%|▍         | 1416/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.59.down_proj:   4%|▍         | 1417/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.60.gate_proj:   4%|▍         | 1418/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.60.up_proj:   4%|▍         | 1419/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.60.down_proj:   4%|▍         | 1420/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.61.gate_proj:   4%|▍         | 1421/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.61.up_proj:   4%|▍         | 1422/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.61.down_proj:   4%|▍         | 1423/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.62.gate_proj:   4%|▍         | 1424/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.62.up_proj:   4%|▍         | 1425/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.62.down_proj:   4%|▍         | 1426/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.63.gate_proj:   4%|▍         | 1427/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.63.up_proj:   4%|▍         | 1428/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.63.down_proj:   4%|▍         | 1429/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.64.gate_proj:   4%|▍         | 1430/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.64.up_proj:   4%|▍         | 1431/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.64.down_proj:   4%|▍         | 1432/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.65.gate_proj:   4%|▍         | 1433/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.65.up_proj:   4%|▍         | 1434/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.65.down_proj:   4%|▍         | 1435/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.66.gate_proj:   4%|▍         | 1436/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.66.up_proj:   4%|▍         | 1437/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.66.down_proj:   4%|▍         | 1438/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.67.gate_proj:   4%|▍         | 1439/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.67.up_proj:   4%|▍         | 1440/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.67.down_proj:   4%|▍         | 1441/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.68.gate_proj:   4%|▍         | 1442/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.68.up_proj:   4%|▍         | 1443/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.68.down_proj:   4%|▍         | 1444/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.69.gate_proj:   4%|▍         | 1445/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.69.up_proj:   4%|▍         | 1446/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.69.down_proj:   4%|▍         | 1447/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.70.gate_proj:   4%|▍         | 1448/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.70.up_proj:   4%|▍         | 1449/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.70.down_proj:   4%|▍         | 1450/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.71.gate_proj:   4%|▍         | 1451/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.71.up_proj:   4%|▍         | 1452/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.71.down_proj:   4%|▍         | 1453/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.72.gate_proj:   4%|▍         | 1454/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.72.up_proj:   4%|▍         | 1455/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.72.down_proj:   4%|▍         | 1456/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.73.gate_proj:   4%|▍         | 1457/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.73.up_proj:   4%|▍         | 1458/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.73.down_proj:   4%|▍         | 1459/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.74.gate_proj:   4%|▍         | 1460/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.74.up_proj:   4%|▍         | 1461/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.74.down_proj:   4%|▍         | 1462/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.75.gate_proj:   4%|▍         | 1463/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.75.up_proj:   4%|▍         | 1464/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.75.down_proj:   4%|▍         | 1465/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.76.gate_proj:   4%|▍         | 1466/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.76.up_proj:   4%|▍         | 1467/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.76.down_proj:   4%|▍         | 1468/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.77.gate_proj:   4%|▍         | 1469/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.77.up_proj:   4%|▍         | 1470/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.77.down_proj:   4%|▍         | 1471/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.78.gate_proj:   4%|▍         | 1472/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.78.up_proj:   4%|▍         | 1473/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.78.down_proj:   4%|▍         | 1474/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.79.gate_proj:   4%|▍         | 1475/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.79.up_proj:   4%|▍         | 1476/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.79.down_proj:   4%|▍         | 1477/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.80.gate_proj:   4%|▍         | 1478/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.80.up_proj:   4%|▍         | 1479/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.80.down_proj:   4%|▍         | 1480/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.81.gate_proj:   4%|▍         | 1481/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.81.up_proj:   4%|▍         | 1482/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.81.down_proj:   4%|▍         | 1483/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.82.gate_proj:   4%|▍         | 1484/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.82.up_proj:   4%|▍         | 1485/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.82.down_proj:   4%|▍         | 1486/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.83.gate_proj:   4%|▍         | 1487/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.83.up_proj:   4%|▍         | 1488/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.83.down_proj:   4%|▍         | 1489/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.84.gate_proj:   4%|▍         | 1490/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.84.up_proj:   4%|▍         | 1491/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.84.down_proj:   4%|▍         | 1492/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.85.gate_proj:   4%|▍         | 1493/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.85.up_proj:   4%|▍         | 1494/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.85.down_proj:   4%|▍         | 1495/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.86.gate_proj:   4%|▍         | 1496/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.86.up_proj:   4%|▍         | 1497/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.86.down_proj:   4%|▍         | 1498/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.87.gate_proj:   4%|▍         | 1499/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.87.up_proj:   4%|▍         | 1500/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.87.down_proj:   4%|▍         | 1501/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.88.gate_proj:   4%|▍         | 1502/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.88.up_proj:   4%|▍         | 1503/36566 [00:02<00:31, 1102.74it/s]  
packing model.layers.2.mlp.experts.88.down_proj:   4%|▍         | 1504/36566 [00:02<00:31, 1102.74it/s]
packing model.layers.2.mlp.experts.88.down_proj:   4%|▍         | 1505/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.89.gate_proj:   4%|▍         | 1505/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.89.up_proj:   4%|▍         | 1506/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.89.down_proj:   4%|▍         | 1507/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.90.gate_proj:   4%|▍         | 1508/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.90.up_proj:   4%|▍         | 1509/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.90.down_proj:   4%|▍         | 1510/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.91.gate_proj:   4%|▍         | 1511/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.91.up_proj:   4%|▍         | 1512/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.91.down_proj:   4%|▍         | 1513/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.92.gate_proj:   4%|▍         | 1514/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.92.up_proj:   4%|▍         | 1515/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.92.down_proj:   4%|▍         | 1516/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.93.gate_proj:   4%|▍         | 1517/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.93.up_proj:   4%|▍         | 1518/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.93.down_proj:   4%|▍         | 1519/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.94.gate_proj:   4%|▍         | 1520/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.94.up_proj:   4%|▍         | 1521/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.94.down_proj:   4%|▍         | 1522/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.95.gate_proj:   4%|▍         | 1523/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.95.up_proj:   4%|▍         | 1524/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.95.down_proj:   4%|▍         | 1525/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.96.gate_proj:   4%|▍         | 1526/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.96.up_proj:   4%|▍         | 1527/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.96.down_proj:   4%|▍         | 1528/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.97.gate_proj:   4%|▍         | 1529/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.97.up_proj:   4%|▍         | 1530/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.97.down_proj:   4%|▍         | 1531/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.98.gate_proj:   4%|▍         | 1532/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.98.up_proj:   4%|▍         | 1533/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.98.down_proj:   4%|▍         | 1534/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.99.gate_proj:   4%|▍         | 1535/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.99.up_proj:   4%|▍         | 1536/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.99.down_proj:   4%|▍         | 1537/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.100.gate_proj:   4%|▍         | 1538/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.100.up_proj:   4%|▍         | 1539/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.100.down_proj:   4%|▍         | 1540/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.101.gate_proj:   4%|▍         | 1541/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.101.up_proj:   4%|▍         | 1542/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.101.down_proj:   4%|▍         | 1543/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.102.gate_proj:   4%|▍         | 1544/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.102.up_proj:   4%|▍         | 1545/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.102.down_proj:   4%|▍         | 1546/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.103.gate_proj:   4%|▍         | 1547/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.103.up_proj:   4%|▍         | 1548/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.103.down_proj:   4%|▍         | 1549/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.104.gate_proj:   4%|▍         | 1550/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.104.up_proj:   4%|▍         | 1551/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.104.down_proj:   4%|▍         | 1552/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.105.gate_proj:   4%|▍         | 1553/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.105.up_proj:   4%|▍         | 1554/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.105.down_proj:   4%|▍         | 1555/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.106.gate_proj:   4%|▍         | 1556/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.106.up_proj:   4%|▍         | 1557/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.106.down_proj:   4%|▍         | 1558/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.107.gate_proj:   4%|▍         | 1559/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.107.up_proj:   4%|▍         | 1560/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.107.down_proj:   4%|▍         | 1561/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.108.gate_proj:   4%|▍         | 1562/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.108.up_proj:   4%|▍         | 1563/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.108.down_proj:   4%|▍         | 1564/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.109.gate_proj:   4%|▍         | 1565/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.109.up_proj:   4%|▍         | 1566/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.109.down_proj:   4%|▍         | 1567/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.110.gate_proj:   4%|▍         | 1568/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.110.up_proj:   4%|▍         | 1569/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.110.down_proj:   4%|▍         | 1570/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.111.gate_proj:   4%|▍         | 1571/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.111.up_proj:   4%|▍         | 1572/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.111.down_proj:   4%|▍         | 1573/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.112.gate_proj:   4%|▍         | 1574/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.112.up_proj:   4%|▍         | 1575/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.112.down_proj:   4%|▍         | 1576/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.113.gate_proj:   4%|▍         | 1577/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.113.up_proj:   4%|▍         | 1578/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.113.down_proj:   4%|▍         | 1579/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.114.gate_proj:   4%|▍         | 1580/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.114.up_proj:   4%|▍         | 1581/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.114.down_proj:   4%|▍         | 1582/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.115.gate_proj:   4%|▍         | 1583/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.115.up_proj:   4%|▍         | 1584/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.115.down_proj:   4%|▍         | 1585/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.116.gate_proj:   4%|▍         | 1586/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.116.up_proj:   4%|▍         | 1587/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.116.down_proj:   4%|▍         | 1588/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.117.gate_proj:   4%|▍         | 1589/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.117.up_proj:   4%|▍         | 1590/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.117.down_proj:   4%|▍         | 1591/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.118.gate_proj:   4%|▍         | 1592/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.118.up_proj:   4%|▍         | 1593/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.118.down_proj:   4%|▍         | 1594/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.119.gate_proj:   4%|▍         | 1595/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.119.up_proj:   4%|▍         | 1596/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.119.down_proj:   4%|▍         | 1597/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.120.gate_proj:   4%|▍         | 1598/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.120.up_proj:   4%|▍         | 1599/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.120.down_proj:   4%|▍         | 1600/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.121.gate_proj:   4%|▍         | 1601/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.121.up_proj:   4%|▍         | 1602/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.121.down_proj:   4%|▍         | 1603/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.122.gate_proj:   4%|▍         | 1604/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.122.up_proj:   4%|▍         | 1605/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.122.down_proj:   4%|▍         | 1606/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.123.gate_proj:   4%|▍         | 1607/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.123.up_proj:   4%|▍         | 1608/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.123.down_proj:   4%|▍         | 1609/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.124.gate_proj:   4%|▍         | 1610/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.124.up_proj:   4%|▍         | 1611/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.124.down_proj:   4%|▍         | 1612/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.125.gate_proj:   4%|▍         | 1613/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.125.up_proj:   4%|▍         | 1614/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.125.down_proj:   4%|▍         | 1615/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.126.gate_proj:   4%|▍         | 1616/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.126.up_proj:   4%|▍         | 1617/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.126.down_proj:   4%|▍         | 1618/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.127.gate_proj:   4%|▍         | 1619/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.127.up_proj:   4%|▍         | 1620/36566 [00:02<00:31, 1119.62it/s]  
packing model.layers.2.mlp.experts.127.down_proj:   4%|▍         | 1621/36566 [00:02<00:31, 1119.62it/s]
packing model.layers.2.mlp.experts.127.down_proj:   4%|▍         | 1622/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.0.gate_proj:   4%|▍         | 1622/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.0.up_proj:   4%|▍         | 1623/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.0.down_proj:   4%|▍         | 1624/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.1.gate_proj:   4%|▍         | 1625/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.1.up_proj:   4%|▍         | 1626/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.1.down_proj:   4%|▍         | 1627/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.2.gate_proj:   4%|▍         | 1628/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.2.up_proj:   4%|▍         | 1629/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.2.down_proj:   4%|▍         | 1630/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.3.gate_proj:   4%|▍         | 1631/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.3.up_proj:   4%|▍         | 1632/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.3.down_proj:   4%|▍         | 1633/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.4.gate_proj:   4%|▍         | 1634/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.4.up_proj:   4%|▍         | 1635/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.4.down_proj:   4%|▍         | 1636/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.5.gate_proj:   4%|▍         | 1637/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.5.up_proj:   4%|▍         | 1638/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.5.down_proj:   4%|▍         | 1639/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.6.gate_proj:   4%|▍         | 1640/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.6.up_proj:   4%|▍         | 1641/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.6.down_proj:   4%|▍         | 1642/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.7.gate_proj:   4%|▍         | 1643/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.7.up_proj:   4%|▍         | 1644/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.7.down_proj:   4%|▍         | 1645/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.8.gate_proj:   5%|▍         | 1646/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.8.up_proj:   5%|▍         | 1647/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.8.down_proj:   5%|▍         | 1648/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.9.gate_proj:   5%|▍         | 1649/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.9.up_proj:   5%|▍         | 1650/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.9.down_proj:   5%|▍         | 1651/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.10.gate_proj:   5%|▍         | 1652/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.10.up_proj:   5%|▍         | 1653/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.10.down_proj:   5%|▍         | 1654/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.11.gate_proj:   5%|▍         | 1655/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.11.up_proj:   5%|▍         | 1656/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.11.down_proj:   5%|▍         | 1657/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.12.gate_proj:   5%|▍         | 1658/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.12.up_proj:   5%|▍         | 1659/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.12.down_proj:   5%|▍         | 1660/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.13.gate_proj:   5%|▍         | 1661/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.13.up_proj:   5%|▍         | 1662/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.13.down_proj:   5%|▍         | 1663/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.14.gate_proj:   5%|▍         | 1664/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.14.up_proj:   5%|▍         | 1665/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.14.down_proj:   5%|▍         | 1666/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.15.gate_proj:   5%|▍         | 1667/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.15.up_proj:   5%|▍         | 1668/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.15.down_proj:   5%|▍         | 1669/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.16.gate_proj:   5%|▍         | 1670/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.16.up_proj:   5%|▍         | 1671/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.16.down_proj:   5%|▍         | 1672/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.17.gate_proj:   5%|▍         | 1673/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.17.up_proj:   5%|▍         | 1674/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.17.down_proj:   5%|▍         | 1675/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.18.gate_proj:   5%|▍         | 1676/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.18.up_proj:   5%|▍         | 1677/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.18.down_proj:   5%|▍         | 1678/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.19.gate_proj:   5%|▍         | 1679/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.19.up_proj:   5%|▍         | 1680/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.19.down_proj:   5%|▍         | 1681/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.20.gate_proj:   5%|▍         | 1682/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.20.up_proj:   5%|▍         | 1683/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.20.down_proj:   5%|▍         | 1684/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.21.gate_proj:   5%|▍         | 1685/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.21.up_proj:   5%|▍         | 1686/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.21.down_proj:   5%|▍         | 1687/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.22.gate_proj:   5%|▍         | 1688/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.22.up_proj:   5%|▍         | 1689/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.22.down_proj:   5%|▍         | 1690/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.23.gate_proj:   5%|▍         | 1691/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.23.up_proj:   5%|▍         | 1692/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.23.down_proj:   5%|▍         | 1693/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.24.gate_proj:   5%|▍         | 1694/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.24.up_proj:   5%|▍         | 1695/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.24.down_proj:   5%|▍         | 1696/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.25.gate_proj:   5%|▍         | 1697/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.25.up_proj:   5%|▍         | 1698/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.25.down_proj:   5%|▍         | 1699/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.26.gate_proj:   5%|▍         | 1700/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.26.up_proj:   5%|▍         | 1701/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.26.down_proj:   5%|▍         | 1702/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.27.gate_proj:   5%|▍         | 1703/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.27.up_proj:   5%|▍         | 1704/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.27.down_proj:   5%|▍         | 1705/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.28.gate_proj:   5%|▍         | 1706/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.28.up_proj:   5%|▍         | 1707/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.28.down_proj:   5%|▍         | 1708/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.29.gate_proj:   5%|▍         | 1709/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.29.up_proj:   5%|▍         | 1710/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.29.down_proj:   5%|▍         | 1711/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.30.gate_proj:   5%|▍         | 1712/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.30.up_proj:   5%|▍         | 1713/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.30.down_proj:   5%|▍         | 1714/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.31.gate_proj:   5%|▍         | 1715/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.31.up_proj:   5%|▍         | 1716/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.31.down_proj:   5%|▍         | 1717/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.32.gate_proj:   5%|▍         | 1718/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.32.up_proj:   5%|▍         | 1719/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.32.down_proj:   5%|▍         | 1720/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.33.gate_proj:   5%|▍         | 1721/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.33.up_proj:   5%|▍         | 1722/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.33.down_proj:   5%|▍         | 1723/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.34.gate_proj:   5%|▍         | 1724/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.34.up_proj:   5%|▍         | 1725/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.34.down_proj:   5%|▍         | 1726/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.35.gate_proj:   5%|▍         | 1727/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.35.up_proj:   5%|▍         | 1728/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.35.down_proj:   5%|▍         | 1729/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.36.gate_proj:   5%|▍         | 1730/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.36.up_proj:   5%|▍         | 1731/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.36.down_proj:   5%|▍         | 1732/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.37.gate_proj:   5%|▍         | 1733/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.37.up_proj:   5%|▍         | 1734/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.37.down_proj:   5%|▍         | 1735/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.38.gate_proj:   5%|▍         | 1736/36566 [00:02<00:30, 1132.32it/s]
packing model.layers.3.mlp.experts.38.up_proj:   5%|▍         | 1737/36566 [00:02<00:30, 1132.32it/s]  
packing model.layers.3.mlp.experts.38.up_proj:   5%|▍         | 1738/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.38.down_proj:   5%|▍         | 1738/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.39.gate_proj:   5%|▍         | 1739/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.39.up_proj:   5%|▍         | 1740/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.39.down_proj:   5%|▍         | 1741/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.40.gate_proj:   5%|▍         | 1742/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.40.up_proj:   5%|▍         | 1743/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.40.down_proj:   5%|▍         | 1744/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.41.gate_proj:   5%|▍         | 1745/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.41.up_proj:   5%|▍         | 1746/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.41.down_proj:   5%|▍         | 1747/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.42.gate_proj:   5%|▍         | 1748/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.42.up_proj:   5%|▍         | 1749/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.42.down_proj:   5%|▍         | 1750/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.43.gate_proj:   5%|▍         | 1751/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.43.up_proj:   5%|▍         | 1752/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.43.down_proj:   5%|▍         | 1753/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.44.gate_proj:   5%|▍         | 1754/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.44.up_proj:   5%|▍         | 1755/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.44.down_proj:   5%|▍         | 1756/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.45.gate_proj:   5%|▍         | 1757/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.45.up_proj:   5%|▍         | 1758/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.45.down_proj:   5%|▍         | 1759/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.46.gate_proj:   5%|▍         | 1760/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.46.up_proj:   5%|▍         | 1761/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.46.down_proj:   5%|▍         | 1762/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.47.gate_proj:   5%|▍         | 1763/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.47.up_proj:   5%|▍         | 1764/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.47.down_proj:   5%|▍         | 1765/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.48.gate_proj:   5%|▍         | 1766/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.48.up_proj:   5%|▍         | 1767/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.48.down_proj:   5%|▍         | 1768/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.49.gate_proj:   5%|▍         | 1769/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.49.up_proj:   5%|▍         | 1770/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.49.down_proj:   5%|▍         | 1771/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.50.gate_proj:   5%|▍         | 1772/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.50.up_proj:   5%|▍         | 1773/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.50.down_proj:   5%|▍         | 1774/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.51.gate_proj:   5%|▍         | 1775/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.51.up_proj:   5%|▍         | 1776/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.51.down_proj:   5%|▍         | 1777/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.52.gate_proj:   5%|▍         | 1778/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.52.up_proj:   5%|▍         | 1779/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.52.down_proj:   5%|▍         | 1780/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.53.gate_proj:   5%|▍         | 1781/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.53.up_proj:   5%|▍         | 1782/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.53.down_proj:   5%|▍         | 1783/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.54.gate_proj:   5%|▍         | 1784/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.54.up_proj:   5%|▍         | 1785/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.54.down_proj:   5%|▍         | 1786/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.55.gate_proj:   5%|▍         | 1787/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.55.up_proj:   5%|▍         | 1788/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.55.down_proj:   5%|▍         | 1789/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.56.gate_proj:   5%|▍         | 1790/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.56.up_proj:   5%|▍         | 1791/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.56.down_proj:   5%|▍         | 1792/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.57.gate_proj:   5%|▍         | 1793/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.57.up_proj:   5%|▍         | 1794/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.57.down_proj:   5%|▍         | 1795/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.58.gate_proj:   5%|▍         | 1796/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.58.up_proj:   5%|▍         | 1797/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.58.down_proj:   5%|▍         | 1798/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.59.gate_proj:   5%|▍         | 1799/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.59.up_proj:   5%|▍         | 1800/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.59.down_proj:   5%|▍         | 1801/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.60.gate_proj:   5%|▍         | 1802/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.60.up_proj:   5%|▍         | 1803/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.60.down_proj:   5%|▍         | 1804/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.61.gate_proj:   5%|▍         | 1805/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.61.up_proj:   5%|▍         | 1806/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.61.down_proj:   5%|▍         | 1807/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.62.gate_proj:   5%|▍         | 1808/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.62.up_proj:   5%|▍         | 1809/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.62.down_proj:   5%|▍         | 1810/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.63.gate_proj:   5%|▍         | 1811/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.63.up_proj:   5%|▍         | 1812/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.63.down_proj:   5%|▍         | 1813/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.64.gate_proj:   5%|▍         | 1814/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.64.up_proj:   5%|▍         | 1815/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.64.down_proj:   5%|▍         | 1816/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.65.gate_proj:   5%|▍         | 1817/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.65.up_proj:   5%|▍         | 1818/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.65.down_proj:   5%|▍         | 1819/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.66.gate_proj:   5%|▍         | 1820/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.66.up_proj:   5%|▍         | 1821/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.66.down_proj:   5%|▍         | 1822/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.67.gate_proj:   5%|▍         | 1823/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.67.up_proj:   5%|▍         | 1824/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.67.down_proj:   5%|▍         | 1825/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.68.gate_proj:   5%|▍         | 1826/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.68.up_proj:   5%|▍         | 1827/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.68.down_proj:   5%|▍         | 1828/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.69.gate_proj:   5%|▌         | 1829/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.69.up_proj:   5%|▌         | 1830/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.69.down_proj:   5%|▌         | 1831/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.70.gate_proj:   5%|▌         | 1832/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.70.up_proj:   5%|▌         | 1833/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.70.down_proj:   5%|▌         | 1834/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.71.gate_proj:   5%|▌         | 1835/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.71.up_proj:   5%|▌         | 1836/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.71.down_proj:   5%|▌         | 1837/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.72.gate_proj:   5%|▌         | 1838/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.72.up_proj:   5%|▌         | 1839/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.72.down_proj:   5%|▌         | 1840/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.73.gate_proj:   5%|▌         | 1841/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.73.up_proj:   5%|▌         | 1842/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.73.down_proj:   5%|▌         | 1843/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.74.gate_proj:   5%|▌         | 1844/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.74.up_proj:   5%|▌         | 1845/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.74.down_proj:   5%|▌         | 1846/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.75.gate_proj:   5%|▌         | 1847/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.75.up_proj:   5%|▌         | 1848/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.75.down_proj:   5%|▌         | 1849/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.76.gate_proj:   5%|▌         | 1850/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.76.up_proj:   5%|▌         | 1851/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.76.down_proj:   5%|▌         | 1852/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.77.gate_proj:   5%|▌         | 1853/36566 [00:02<00:30, 1139.21it/s]
packing model.layers.3.mlp.experts.77.up_proj:   5%|▌         | 1854/36566 [00:02<00:30, 1139.21it/s]  
packing model.layers.3.mlp.experts.77.up_proj:   5%|▌         | 1855/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.77.down_proj:   5%|▌         | 1855/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.78.gate_proj:   5%|▌         | 1856/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.78.up_proj:   5%|▌         | 1857/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.78.down_proj:   5%|▌         | 1858/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.79.gate_proj:   5%|▌         | 1859/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.79.up_proj:   5%|▌         | 1860/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.79.down_proj:   5%|▌         | 1861/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.80.gate_proj:   5%|▌         | 1862/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.80.up_proj:   5%|▌         | 1863/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.80.down_proj:   5%|▌         | 1864/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.81.gate_proj:   5%|▌         | 1865/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.81.up_proj:   5%|▌         | 1866/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.81.down_proj:   5%|▌         | 1867/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.82.gate_proj:   5%|▌         | 1868/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.82.up_proj:   5%|▌         | 1869/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.82.down_proj:   5%|▌         | 1870/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.83.gate_proj:   5%|▌         | 1871/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.83.up_proj:   5%|▌         | 1872/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.83.down_proj:   5%|▌         | 1873/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.84.gate_proj:   5%|▌         | 1874/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.84.up_proj:   5%|▌         | 1875/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.84.down_proj:   5%|▌         | 1876/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.85.gate_proj:   5%|▌         | 1877/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.85.up_proj:   5%|▌         | 1878/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.85.down_proj:   5%|▌         | 1879/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.86.gate_proj:   5%|▌         | 1880/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.86.up_proj:   5%|▌         | 1881/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.86.down_proj:   5%|▌         | 1882/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.87.gate_proj:   5%|▌         | 1883/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.87.up_proj:   5%|▌         | 1884/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.87.down_proj:   5%|▌         | 1885/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.88.gate_proj:   5%|▌         | 1886/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.88.up_proj:   5%|▌         | 1887/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.88.down_proj:   5%|▌         | 1888/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.89.gate_proj:   5%|▌         | 1889/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.89.up_proj:   5%|▌         | 1890/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.89.down_proj:   5%|▌         | 1891/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.90.gate_proj:   5%|▌         | 1892/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.90.up_proj:   5%|▌         | 1893/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.90.down_proj:   5%|▌         | 1894/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.91.gate_proj:   5%|▌         | 1895/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.91.up_proj:   5%|▌         | 1896/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.91.down_proj:   5%|▌         | 1897/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.92.gate_proj:   5%|▌         | 1898/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.92.up_proj:   5%|▌         | 1899/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.92.down_proj:   5%|▌         | 1900/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.93.gate_proj:   5%|▌         | 1901/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.93.up_proj:   5%|▌         | 1902/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.93.down_proj:   5%|▌         | 1903/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.94.gate_proj:   5%|▌         | 1904/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.94.up_proj:   5%|▌         | 1905/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.94.down_proj:   5%|▌         | 1906/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.95.gate_proj:   5%|▌         | 1907/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.95.up_proj:   5%|▌         | 1908/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.95.down_proj:   5%|▌         | 1909/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.96.gate_proj:   5%|▌         | 1910/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.96.up_proj:   5%|▌         | 1911/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.96.down_proj:   5%|▌         | 1912/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.97.gate_proj:   5%|▌         | 1913/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.97.up_proj:   5%|▌         | 1914/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.97.down_proj:   5%|▌         | 1915/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.98.gate_proj:   5%|▌         | 1916/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.98.up_proj:   5%|▌         | 1917/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.98.down_proj:   5%|▌         | 1918/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.99.gate_proj:   5%|▌         | 1919/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.99.up_proj:   5%|▌         | 1920/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.99.down_proj:   5%|▌         | 1921/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.100.gate_proj:   5%|▌         | 1922/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.100.up_proj:   5%|▌         | 1923/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.100.down_proj:   5%|▌         | 1924/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.101.gate_proj:   5%|▌         | 1925/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.101.up_proj:   5%|▌         | 1926/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.101.down_proj:   5%|▌         | 1927/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.102.gate_proj:   5%|▌         | 1928/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.102.up_proj:   5%|▌         | 1929/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.102.down_proj:   5%|▌         | 1930/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.103.gate_proj:   5%|▌         | 1931/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.103.up_proj:   5%|▌         | 1932/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.103.down_proj:   5%|▌         | 1933/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.104.gate_proj:   5%|▌         | 1934/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.104.up_proj:   5%|▌         | 1935/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.104.down_proj:   5%|▌         | 1936/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.105.gate_proj:   5%|▌         | 1937/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.105.up_proj:   5%|▌         | 1938/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.105.down_proj:   5%|▌         | 1939/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.106.gate_proj:   5%|▌         | 1940/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.106.up_proj:   5%|▌         | 1941/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.106.down_proj:   5%|▌         | 1942/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.107.gate_proj:   5%|▌         | 1943/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.107.up_proj:   5%|▌         | 1944/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.107.down_proj:   5%|▌         | 1945/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.108.gate_proj:   5%|▌         | 1946/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.108.up_proj:   5%|▌         | 1947/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.108.down_proj:   5%|▌         | 1948/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.109.gate_proj:   5%|▌         | 1949/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.109.up_proj:   5%|▌         | 1950/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.109.down_proj:   5%|▌         | 1951/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.110.gate_proj:   5%|▌         | 1952/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.110.up_proj:   5%|▌         | 1953/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.110.down_proj:   5%|▌         | 1954/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.111.gate_proj:   5%|▌         | 1955/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.111.up_proj:   5%|▌         | 1956/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.111.down_proj:   5%|▌         | 1957/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.112.gate_proj:   5%|▌         | 1958/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.112.up_proj:   5%|▌         | 1959/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.112.down_proj:   5%|▌         | 1960/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.113.gate_proj:   5%|▌         | 1961/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.113.up_proj:   5%|▌         | 1962/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.113.down_proj:   5%|▌         | 1963/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.114.gate_proj:   5%|▌         | 1964/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.114.up_proj:   5%|▌         | 1965/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.114.down_proj:   5%|▌         | 1966/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.115.gate_proj:   5%|▌         | 1967/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.115.up_proj:   5%|▌         | 1968/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.115.down_proj:   5%|▌         | 1969/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.116.gate_proj:   5%|▌         | 1970/36566 [00:02<00:30, 1146.68it/s]
packing model.layers.3.mlp.experts.116.up_proj:   5%|▌         | 1971/36566 [00:02<00:30, 1146.68it/s]  
packing model.layers.3.mlp.experts.116.up_proj:   5%|▌         | 1972/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.116.down_proj:   5%|▌         | 1972/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.117.gate_proj:   5%|▌         | 1973/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.117.up_proj:   5%|▌         | 1974/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.117.down_proj:   5%|▌         | 1975/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.118.gate_proj:   5%|▌         | 1976/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.118.up_proj:   5%|▌         | 1977/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.118.down_proj:   5%|▌         | 1978/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.119.gate_proj:   5%|▌         | 1979/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.119.up_proj:   5%|▌         | 1980/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.119.down_proj:   5%|▌         | 1981/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.120.gate_proj:   5%|▌         | 1982/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.120.up_proj:   5%|▌         | 1983/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.120.down_proj:   5%|▌         | 1984/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.121.gate_proj:   5%|▌         | 1985/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.121.up_proj:   5%|▌         | 1986/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.121.down_proj:   5%|▌         | 1987/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.122.gate_proj:   5%|▌         | 1988/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.122.up_proj:   5%|▌         | 1989/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.122.down_proj:   5%|▌         | 1990/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.123.gate_proj:   5%|▌         | 1991/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.123.up_proj:   5%|▌         | 1992/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.123.down_proj:   5%|▌         | 1993/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.124.gate_proj:   5%|▌         | 1994/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.124.up_proj:   5%|▌         | 1995/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.124.down_proj:   5%|▌         | 1996/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.125.gate_proj:   5%|▌         | 1997/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.125.up_proj:   5%|▌         | 1998/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.125.down_proj:   5%|▌         | 1999/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.126.gate_proj:   5%|▌         | 2000/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.126.up_proj:   5%|▌         | 2001/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.126.down_proj:   5%|▌         | 2002/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.127.gate_proj:   5%|▌         | 2003/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.3.mlp.experts.127.up_proj:   5%|▌         | 2004/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.3.mlp.experts.127.down_proj:   5%|▌         | 2005/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.0.gate_proj:   5%|▌         | 2006/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.0.up_proj:   5%|▌         | 2007/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.0.down_proj:   5%|▌         | 2008/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.1.gate_proj:   5%|▌         | 2009/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.1.up_proj:   5%|▌         | 2010/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.1.down_proj:   5%|▌         | 2011/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.2.gate_proj:   6%|▌         | 2012/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.2.up_proj:   6%|▌         | 2013/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.2.down_proj:   6%|▌         | 2014/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.3.gate_proj:   6%|▌         | 2015/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.3.up_proj:   6%|▌         | 2016/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.3.down_proj:   6%|▌         | 2017/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.4.gate_proj:   6%|▌         | 2018/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.4.up_proj:   6%|▌         | 2019/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.4.down_proj:   6%|▌         | 2020/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.5.gate_proj:   6%|▌         | 2021/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.5.up_proj:   6%|▌         | 2022/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.5.down_proj:   6%|▌         | 2023/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.6.gate_proj:   6%|▌         | 2024/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.6.up_proj:   6%|▌         | 2025/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.6.down_proj:   6%|▌         | 2026/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.7.gate_proj:   6%|▌         | 2027/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.7.up_proj:   6%|▌         | 2028/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.7.down_proj:   6%|▌         | 2029/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.8.gate_proj:   6%|▌         | 2030/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.8.up_proj:   6%|▌         | 2031/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.8.down_proj:   6%|▌         | 2032/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.9.gate_proj:   6%|▌         | 2033/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.9.up_proj:   6%|▌         | 2034/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.9.down_proj:   6%|▌         | 2035/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.10.gate_proj:   6%|▌         | 2036/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.10.up_proj:   6%|▌         | 2037/36566 [00:02<00:30, 1150.91it/s]  
packing model.layers.4.mlp.experts.10.down_proj:   6%|▌         | 2038/36566 [00:02<00:30, 1150.91it/s]
packing model.layers.4.mlp.experts.11.gate_proj:   6%|▌         | 2039/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.11.up_proj:   6%|▌         | 2040/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.11.down_proj:   6%|▌         | 2041/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.12.gate_proj:   6%|▌         | 2042/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.12.up_proj:   6%|▌         | 2043/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.12.down_proj:   6%|▌         | 2044/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.13.gate_proj:   6%|▌         | 2045/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.13.up_proj:   6%|▌         | 2046/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.13.down_proj:   6%|▌         | 2047/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.14.gate_proj:   6%|▌         | 2048/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.14.up_proj:   6%|▌         | 2049/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.14.down_proj:   6%|▌         | 2050/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.15.gate_proj:   6%|▌         | 2051/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.15.up_proj:   6%|▌         | 2052/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.15.down_proj:   6%|▌         | 2053/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.16.gate_proj:   6%|▌         | 2054/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.16.up_proj:   6%|▌         | 2055/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.16.down_proj:   6%|▌         | 2056/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.17.gate_proj:   6%|▌         | 2057/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.17.up_proj:   6%|▌         | 2058/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.17.down_proj:   6%|▌         | 2059/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.18.gate_proj:   6%|▌         | 2060/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.18.up_proj:   6%|▌         | 2061/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.18.down_proj:   6%|▌         | 2062/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.19.gate_proj:   6%|▌         | 2063/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.19.up_proj:   6%|▌         | 2064/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.19.down_proj:   6%|▌         | 2065/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.20.gate_proj:   6%|▌         | 2066/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.20.up_proj:   6%|▌         | 2067/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.20.down_proj:   6%|▌         | 2068/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.21.gate_proj:   6%|▌         | 2069/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.21.up_proj:   6%|▌         | 2070/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.21.down_proj:   6%|▌         | 2071/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.22.gate_proj:   6%|▌         | 2072/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.22.up_proj:   6%|▌         | 2073/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.22.down_proj:   6%|▌         | 2074/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.23.gate_proj:   6%|▌         | 2075/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.23.up_proj:   6%|▌         | 2076/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.23.down_proj:   6%|▌         | 2077/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.24.gate_proj:   6%|▌         | 2078/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.24.up_proj:   6%|▌         | 2079/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.24.down_proj:   6%|▌         | 2080/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.25.gate_proj:   6%|▌         | 2081/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.25.up_proj:   6%|▌         | 2082/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.25.down_proj:   6%|▌         | 2083/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.26.gate_proj:   6%|▌         | 2084/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.26.up_proj:   6%|▌         | 2085/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.26.down_proj:   6%|▌         | 2086/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.27.gate_proj:   6%|▌         | 2087/36566 [00:02<00:29, 1150.91it/s]
packing model.layers.4.mlp.experts.27.up_proj:   6%|▌         | 2088/36566 [00:02<00:29, 1150.91it/s]  
packing model.layers.4.mlp.experts.27.up_proj:   6%|▌         | 2089/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.27.down_proj:   6%|▌         | 2089/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.28.gate_proj:   6%|▌         | 2090/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.28.up_proj:   6%|▌         | 2091/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.28.down_proj:   6%|▌         | 2092/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.29.gate_proj:   6%|▌         | 2093/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.29.up_proj:   6%|▌         | 2094/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.29.down_proj:   6%|▌         | 2095/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.30.gate_proj:   6%|▌         | 2096/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.30.up_proj:   6%|▌         | 2097/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.30.down_proj:   6%|▌         | 2098/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.31.gate_proj:   6%|▌         | 2099/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.31.up_proj:   6%|▌         | 2100/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.31.down_proj:   6%|▌         | 2101/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.32.gate_proj:   6%|▌         | 2102/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.32.up_proj:   6%|▌         | 2103/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.32.down_proj:   6%|▌         | 2104/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.33.gate_proj:   6%|▌         | 2105/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.33.up_proj:   6%|▌         | 2106/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.33.down_proj:   6%|▌         | 2107/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.34.gate_proj:   6%|▌         | 2108/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.34.up_proj:   6%|▌         | 2109/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.34.down_proj:   6%|▌         | 2110/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.35.gate_proj:   6%|▌         | 2111/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.35.up_proj:   6%|▌         | 2112/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.35.down_proj:   6%|▌         | 2113/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.36.gate_proj:   6%|▌         | 2114/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.36.up_proj:   6%|▌         | 2115/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.36.down_proj:   6%|▌         | 2116/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.37.gate_proj:   6%|▌         | 2117/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.37.up_proj:   6%|▌         | 2118/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.37.down_proj:   6%|▌         | 2119/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.38.gate_proj:   6%|▌         | 2120/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.38.up_proj:   6%|▌         | 2121/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.38.down_proj:   6%|▌         | 2122/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.39.gate_proj:   6%|▌         | 2123/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.39.up_proj:   6%|▌         | 2124/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.39.down_proj:   6%|▌         | 2125/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.40.gate_proj:   6%|▌         | 2126/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.40.up_proj:   6%|▌         | 2127/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.40.down_proj:   6%|▌         | 2128/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.41.gate_proj:   6%|▌         | 2129/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.41.up_proj:   6%|▌         | 2130/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.41.down_proj:   6%|▌         | 2131/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.42.gate_proj:   6%|▌         | 2132/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.42.up_proj:   6%|▌         | 2133/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.42.down_proj:   6%|▌         | 2134/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.43.gate_proj:   6%|▌         | 2135/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.43.up_proj:   6%|▌         | 2136/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.43.down_proj:   6%|▌         | 2137/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.44.gate_proj:   6%|▌         | 2138/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.44.up_proj:   6%|▌         | 2139/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.44.down_proj:   6%|▌         | 2140/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.45.gate_proj:   6%|▌         | 2141/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.45.up_proj:   6%|▌         | 2142/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.45.down_proj:   6%|▌         | 2143/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.46.gate_proj:   6%|▌         | 2144/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.46.up_proj:   6%|▌         | 2145/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.46.down_proj:   6%|▌         | 2146/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.47.gate_proj:   6%|▌         | 2147/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.47.up_proj:   6%|▌         | 2148/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.47.down_proj:   6%|▌         | 2149/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.48.gate_proj:   6%|▌         | 2150/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.48.up_proj:   6%|▌         | 2151/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.48.down_proj:   6%|▌         | 2152/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.49.gate_proj:   6%|▌         | 2153/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.49.up_proj:   6%|▌         | 2154/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.49.down_proj:   6%|▌         | 2155/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.50.gate_proj:   6%|▌         | 2156/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.50.up_proj:   6%|▌         | 2157/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.50.down_proj:   6%|▌         | 2158/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.51.gate_proj:   6%|▌         | 2159/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.51.up_proj:   6%|▌         | 2160/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.51.down_proj:   6%|▌         | 2161/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.52.gate_proj:   6%|▌         | 2162/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.52.up_proj:   6%|▌         | 2163/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.52.down_proj:   6%|▌         | 2164/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.53.gate_proj:   6%|▌         | 2165/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.53.up_proj:   6%|▌         | 2166/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.53.down_proj:   6%|▌         | 2167/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.54.gate_proj:   6%|▌         | 2168/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.54.up_proj:   6%|▌         | 2169/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.54.down_proj:   6%|▌         | 2170/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.55.gate_proj:   6%|▌         | 2171/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.55.up_proj:   6%|▌         | 2172/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.55.down_proj:   6%|▌         | 2173/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.56.gate_proj:   6%|▌         | 2174/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.56.up_proj:   6%|▌         | 2175/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.56.down_proj:   6%|▌         | 2176/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.57.gate_proj:   6%|▌         | 2177/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.57.up_proj:   6%|▌         | 2178/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.57.down_proj:   6%|▌         | 2179/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.58.gate_proj:   6%|▌         | 2180/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.58.up_proj:   6%|▌         | 2181/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.58.down_proj:   6%|▌         | 2182/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.59.gate_proj:   6%|▌         | 2183/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.59.up_proj:   6%|▌         | 2184/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.59.down_proj:   6%|▌         | 2185/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.60.gate_proj:   6%|▌         | 2186/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.60.up_proj:   6%|▌         | 2187/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.60.down_proj:   6%|▌         | 2188/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.61.gate_proj:   6%|▌         | 2189/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.61.up_proj:   6%|▌         | 2190/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.61.down_proj:   6%|▌         | 2191/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.62.gate_proj:   6%|▌         | 2192/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.62.up_proj:   6%|▌         | 2193/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.62.down_proj:   6%|▌         | 2194/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.63.gate_proj:   6%|▌         | 2195/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.63.up_proj:   6%|▌         | 2196/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.63.down_proj:   6%|▌         | 2197/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.64.gate_proj:   6%|▌         | 2198/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.64.up_proj:   6%|▌         | 2199/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.64.down_proj:   6%|▌         | 2200/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.65.gate_proj:   6%|▌         | 2201/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.65.up_proj:   6%|▌         | 2202/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.65.down_proj:   6%|▌         | 2203/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.66.gate_proj:   6%|▌         | 2204/36566 [00:02<00:29, 1155.00it/s]
packing model.layers.4.mlp.experts.66.up_proj:   6%|▌         | 2205/36566 [00:02<00:29, 1155.00it/s]  
packing model.layers.4.mlp.experts.66.up_proj:   6%|▌         | 2206/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.66.down_proj:   6%|▌         | 2206/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.67.gate_proj:   6%|▌         | 2207/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.67.up_proj:   6%|▌         | 2208/36566 [00:02<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.67.down_proj:   6%|▌         | 2209/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.68.gate_proj:   6%|▌         | 2210/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.68.up_proj:   6%|▌         | 2211/36566 [00:02<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.68.down_proj:   6%|▌         | 2212/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.69.gate_proj:   6%|▌         | 2213/36566 [00:02<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.69.up_proj:   6%|▌         | 2214/36566 [00:02<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.69.down_proj:   6%|▌         | 2215/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.70.gate_proj:   6%|▌         | 2216/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.70.up_proj:   6%|▌         | 2217/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.70.down_proj:   6%|▌         | 2218/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.71.gate_proj:   6%|▌         | 2219/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.71.up_proj:   6%|▌         | 2220/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.71.down_proj:   6%|▌         | 2221/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.72.gate_proj:   6%|▌         | 2222/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.72.up_proj:   6%|▌         | 2223/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.72.down_proj:   6%|▌         | 2224/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.73.gate_proj:   6%|▌         | 2225/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.73.up_proj:   6%|▌         | 2226/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.73.down_proj:   6%|▌         | 2227/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.74.gate_proj:   6%|▌         | 2228/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.74.up_proj:   6%|▌         | 2229/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.74.down_proj:   6%|▌         | 2230/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.75.gate_proj:   6%|▌         | 2231/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.75.up_proj:   6%|▌         | 2232/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.75.down_proj:   6%|▌         | 2233/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.76.gate_proj:   6%|▌         | 2234/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.76.up_proj:   6%|▌         | 2235/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.76.down_proj:   6%|▌         | 2236/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.77.gate_proj:   6%|▌         | 2237/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.77.up_proj:   6%|▌         | 2238/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.77.down_proj:   6%|▌         | 2239/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.78.gate_proj:   6%|▌         | 2240/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.78.up_proj:   6%|▌         | 2241/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.78.down_proj:   6%|▌         | 2242/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.79.gate_proj:   6%|▌         | 2243/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.79.up_proj:   6%|▌         | 2244/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.79.down_proj:   6%|▌         | 2245/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.80.gate_proj:   6%|▌         | 2246/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.80.up_proj:   6%|▌         | 2247/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.80.down_proj:   6%|▌         | 2248/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.81.gate_proj:   6%|▌         | 2249/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.81.up_proj:   6%|▌         | 2250/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.81.down_proj:   6%|▌         | 2251/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.82.gate_proj:   6%|▌         | 2252/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.82.up_proj:   6%|▌         | 2253/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.82.down_proj:   6%|▌         | 2254/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.83.gate_proj:   6%|▌         | 2255/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.83.up_proj:   6%|▌         | 2256/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.83.down_proj:   6%|▌         | 2257/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.84.gate_proj:   6%|▌         | 2258/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.84.up_proj:   6%|▌         | 2259/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.84.down_proj:   6%|▌         | 2260/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.85.gate_proj:   6%|▌         | 2261/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.85.up_proj:   6%|▌         | 2262/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.85.down_proj:   6%|▌         | 2263/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.86.gate_proj:   6%|▌         | 2264/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.86.up_proj:   6%|▌         | 2265/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.86.down_proj:   6%|▌         | 2266/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.87.gate_proj:   6%|▌         | 2267/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.87.up_proj:   6%|▌         | 2268/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.87.down_proj:   6%|▌         | 2269/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.88.gate_proj:   6%|▌         | 2270/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.88.up_proj:   6%|▌         | 2271/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.88.down_proj:   6%|▌         | 2272/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.89.gate_proj:   6%|▌         | 2273/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.89.up_proj:   6%|▌         | 2274/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.89.down_proj:   6%|▌         | 2275/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.90.gate_proj:   6%|▌         | 2276/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.90.up_proj:   6%|▌         | 2277/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.90.down_proj:   6%|▌         | 2278/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.91.gate_proj:   6%|▌         | 2279/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.91.up_proj:   6%|▌         | 2280/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.91.down_proj:   6%|▌         | 2281/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.92.gate_proj:   6%|▌         | 2282/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.92.up_proj:   6%|▌         | 2283/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.92.down_proj:   6%|▌         | 2284/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.93.gate_proj:   6%|▌         | 2285/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.93.up_proj:   6%|▋         | 2286/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.93.down_proj:   6%|▋         | 2287/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.94.gate_proj:   6%|▋         | 2288/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.94.up_proj:   6%|▋         | 2289/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.94.down_proj:   6%|▋         | 2290/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.95.gate_proj:   6%|▋         | 2291/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.95.up_proj:   6%|▋         | 2292/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.95.down_proj:   6%|▋         | 2293/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.96.gate_proj:   6%|▋         | 2294/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.96.up_proj:   6%|▋         | 2295/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.96.down_proj:   6%|▋         | 2296/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.97.gate_proj:   6%|▋         | 2297/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.97.up_proj:   6%|▋         | 2298/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.97.down_proj:   6%|▋         | 2299/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.98.gate_proj:   6%|▋         | 2300/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.98.up_proj:   6%|▋         | 2301/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.98.down_proj:   6%|▋         | 2302/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.99.gate_proj:   6%|▋         | 2303/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.99.up_proj:   6%|▋         | 2304/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.99.down_proj:   6%|▋         | 2305/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.100.gate_proj:   6%|▋         | 2306/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.100.up_proj:   6%|▋         | 2307/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.100.down_proj:   6%|▋         | 2308/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.101.gate_proj:   6%|▋         | 2309/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.101.up_proj:   6%|▋         | 2310/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.101.down_proj:   6%|▋         | 2311/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.102.gate_proj:   6%|▋         | 2312/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.102.up_proj:   6%|▋         | 2313/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.102.down_proj:   6%|▋         | 2314/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.103.gate_proj:   6%|▋         | 2315/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.103.up_proj:   6%|▋         | 2316/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.103.down_proj:   6%|▋         | 2317/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.104.gate_proj:   6%|▋         | 2318/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.104.up_proj:   6%|▋         | 2319/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.104.down_proj:   6%|▋         | 2320/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.105.gate_proj:   6%|▋         | 2321/36566 [00:03<00:29, 1156.33it/s]
packing model.layers.4.mlp.experts.105.up_proj:   6%|▋         | 2322/36566 [00:03<00:29, 1156.33it/s]  
packing model.layers.4.mlp.experts.105.up_proj:   6%|▋         | 2323/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.105.down_proj:   6%|▋         | 2323/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.106.gate_proj:   6%|▋         | 2324/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.106.up_proj:   6%|▋         | 2325/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.106.down_proj:   6%|▋         | 2326/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.107.gate_proj:   6%|▋         | 2327/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.107.up_proj:   6%|▋         | 2328/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.107.down_proj:   6%|▋         | 2329/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.108.gate_proj:   6%|▋         | 2330/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.108.up_proj:   6%|▋         | 2331/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.108.down_proj:   6%|▋         | 2332/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.109.gate_proj:   6%|▋         | 2333/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.109.up_proj:   6%|▋         | 2334/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.109.down_proj:   6%|▋         | 2335/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.110.gate_proj:   6%|▋         | 2336/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.110.up_proj:   6%|▋         | 2337/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.110.down_proj:   6%|▋         | 2338/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.111.gate_proj:   6%|▋         | 2339/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.111.up_proj:   6%|▋         | 2340/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.111.down_proj:   6%|▋         | 2341/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.112.gate_proj:   6%|▋         | 2342/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.112.up_proj:   6%|▋         | 2343/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.112.down_proj:   6%|▋         | 2344/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.113.gate_proj:   6%|▋         | 2345/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.113.up_proj:   6%|▋         | 2346/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.113.down_proj:   6%|▋         | 2347/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.114.gate_proj:   6%|▋         | 2348/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.114.up_proj:   6%|▋         | 2349/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.114.down_proj:   6%|▋         | 2350/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.115.gate_proj:   6%|▋         | 2351/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.115.up_proj:   6%|▋         | 2352/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.115.down_proj:   6%|▋         | 2353/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.116.gate_proj:   6%|▋         | 2354/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.116.up_proj:   6%|▋         | 2355/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.116.down_proj:   6%|▋         | 2356/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.117.gate_proj:   6%|▋         | 2357/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.117.up_proj:   6%|▋         | 2358/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.117.down_proj:   6%|▋         | 2359/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.118.gate_proj:   6%|▋         | 2360/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.118.up_proj:   6%|▋         | 2361/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.118.down_proj:   6%|▋         | 2362/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.119.gate_proj:   6%|▋         | 2363/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.119.up_proj:   6%|▋         | 2364/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.119.down_proj:   6%|▋         | 2365/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.120.gate_proj:   6%|▋         | 2366/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.120.up_proj:   6%|▋         | 2367/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.120.down_proj:   6%|▋         | 2368/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.121.gate_proj:   6%|▋         | 2369/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.121.up_proj:   6%|▋         | 2370/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.121.down_proj:   6%|▋         | 2371/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.122.gate_proj:   6%|▋         | 2372/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.122.up_proj:   6%|▋         | 2373/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.122.down_proj:   6%|▋         | 2374/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.123.gate_proj:   6%|▋         | 2375/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.123.up_proj:   6%|▋         | 2376/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.123.down_proj:   7%|▋         | 2377/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.124.gate_proj:   7%|▋         | 2378/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.124.up_proj:   7%|▋         | 2379/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.124.down_proj:   7%|▋         | 2380/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.125.gate_proj:   7%|▋         | 2381/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.125.up_proj:   7%|▋         | 2382/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.125.down_proj:   7%|▋         | 2383/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.126.gate_proj:   7%|▋         | 2384/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.126.up_proj:   7%|▋         | 2385/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.126.down_proj:   7%|▋         | 2386/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.127.gate_proj:   7%|▋         | 2387/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.4.mlp.experts.127.up_proj:   7%|▋         | 2388/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.4.mlp.experts.127.down_proj:   7%|▋         | 2389/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.0.gate_proj:   7%|▋         | 2390/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.0.up_proj:   7%|▋         | 2391/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.0.down_proj:   7%|▋         | 2392/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.1.gate_proj:   7%|▋         | 2393/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.1.up_proj:   7%|▋         | 2394/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.1.down_proj:   7%|▋         | 2395/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.2.gate_proj:   7%|▋         | 2396/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.2.up_proj:   7%|▋         | 2397/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.2.down_proj:   7%|▋         | 2398/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.3.gate_proj:   7%|▋         | 2399/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.3.up_proj:   7%|▋         | 2400/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.3.down_proj:   7%|▋         | 2401/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.4.gate_proj:   7%|▋         | 2402/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.4.up_proj:   7%|▋         | 2403/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.4.down_proj:   7%|▋         | 2404/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.5.gate_proj:   7%|▋         | 2405/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.5.up_proj:   7%|▋         | 2406/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.5.down_proj:   7%|▋         | 2407/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.6.gate_proj:   7%|▋         | 2408/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.6.up_proj:   7%|▋         | 2409/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.6.down_proj:   7%|▋         | 2410/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.7.gate_proj:   7%|▋         | 2411/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.7.up_proj:   7%|▋         | 2412/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.7.down_proj:   7%|▋         | 2413/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.8.gate_proj:   7%|▋         | 2414/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.8.up_proj:   7%|▋         | 2415/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.8.down_proj:   7%|▋         | 2416/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.9.gate_proj:   7%|▋         | 2417/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.9.up_proj:   7%|▋         | 2418/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.9.down_proj:   7%|▋         | 2419/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.10.gate_proj:   7%|▋         | 2420/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.10.up_proj:   7%|▋         | 2421/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.10.down_proj:   7%|▋         | 2422/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.11.gate_proj:   7%|▋         | 2423/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.11.up_proj:   7%|▋         | 2424/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.11.down_proj:   7%|▋         | 2425/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.12.gate_proj:   7%|▋         | 2426/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.12.up_proj:   7%|▋         | 2427/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.12.down_proj:   7%|▋         | 2428/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.13.gate_proj:   7%|▋         | 2429/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.13.up_proj:   7%|▋         | 2430/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.13.down_proj:   7%|▋         | 2431/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.14.gate_proj:   7%|▋         | 2432/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.14.up_proj:   7%|▋         | 2433/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.14.down_proj:   7%|▋         | 2434/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.15.gate_proj:   7%|▋         | 2435/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.15.up_proj:   7%|▋         | 2436/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.15.down_proj:   7%|▋         | 2437/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.16.gate_proj:   7%|▋         | 2438/36566 [00:03<00:29, 1157.31it/s]
packing model.layers.5.mlp.experts.16.up_proj:   7%|▋         | 2439/36566 [00:03<00:29, 1157.31it/s]  
packing model.layers.5.mlp.experts.16.up_proj:   7%|▋         | 2440/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.16.down_proj:   7%|▋         | 2440/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.17.gate_proj:   7%|▋         | 2441/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.17.up_proj:   7%|▋         | 2442/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.17.down_proj:   7%|▋         | 2443/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.18.gate_proj:   7%|▋         | 2444/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.18.up_proj:   7%|▋         | 2445/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.18.down_proj:   7%|▋         | 2446/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.19.gate_proj:   7%|▋         | 2447/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.19.up_proj:   7%|▋         | 2448/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.19.down_proj:   7%|▋         | 2449/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.20.gate_proj:   7%|▋         | 2450/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.20.up_proj:   7%|▋         | 2451/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.20.down_proj:   7%|▋         | 2452/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.21.gate_proj:   7%|▋         | 2453/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.21.up_proj:   7%|▋         | 2454/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.21.down_proj:   7%|▋         | 2455/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.22.gate_proj:   7%|▋         | 2456/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.22.up_proj:   7%|▋         | 2457/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.22.down_proj:   7%|▋         | 2458/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.23.gate_proj:   7%|▋         | 2459/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.23.up_proj:   7%|▋         | 2460/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.23.down_proj:   7%|▋         | 2461/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.24.gate_proj:   7%|▋         | 2462/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.24.up_proj:   7%|▋         | 2463/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.24.down_proj:   7%|▋         | 2464/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.25.gate_proj:   7%|▋         | 2465/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.25.up_proj:   7%|▋         | 2466/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.25.down_proj:   7%|▋         | 2467/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.26.gate_proj:   7%|▋         | 2468/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.26.up_proj:   7%|▋         | 2469/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.26.down_proj:   7%|▋         | 2470/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.27.gate_proj:   7%|▋         | 2471/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.27.up_proj:   7%|▋         | 2472/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.27.down_proj:   7%|▋         | 2473/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.28.gate_proj:   7%|▋         | 2474/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.28.up_proj:   7%|▋         | 2475/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.28.down_proj:   7%|▋         | 2476/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.29.gate_proj:   7%|▋         | 2477/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.29.up_proj:   7%|▋         | 2478/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.29.down_proj:   7%|▋         | 2479/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.30.gate_proj:   7%|▋         | 2480/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.30.up_proj:   7%|▋         | 2481/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.30.down_proj:   7%|▋         | 2482/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.31.gate_proj:   7%|▋         | 2483/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.31.up_proj:   7%|▋         | 2484/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.31.down_proj:   7%|▋         | 2485/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.32.gate_proj:   7%|▋         | 2486/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.32.up_proj:   7%|▋         | 2487/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.32.down_proj:   7%|▋         | 2488/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.33.gate_proj:   7%|▋         | 2489/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.33.up_proj:   7%|▋         | 2490/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.33.down_proj:   7%|▋         | 2491/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.34.gate_proj:   7%|▋         | 2492/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.34.up_proj:   7%|▋         | 2493/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.34.down_proj:   7%|▋         | 2494/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.35.gate_proj:   7%|▋         | 2495/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.35.up_proj:   7%|▋         | 2496/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.35.down_proj:   7%|▋         | 2497/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.36.gate_proj:   7%|▋         | 2498/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.36.up_proj:   7%|▋         | 2499/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.36.down_proj:   7%|▋         | 2500/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.37.gate_proj:   7%|▋         | 2501/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.37.up_proj:   7%|▋         | 2502/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.37.down_proj:   7%|▋         | 2503/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.38.gate_proj:   7%|▋         | 2504/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.38.up_proj:   7%|▋         | 2505/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.38.down_proj:   7%|▋         | 2506/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.39.gate_proj:   7%|▋         | 2507/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.39.up_proj:   7%|▋         | 2508/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.39.down_proj:   7%|▋         | 2509/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.40.gate_proj:   7%|▋         | 2510/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.40.up_proj:   7%|▋         | 2511/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.40.down_proj:   7%|▋         | 2512/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.41.gate_proj:   7%|▋         | 2513/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.41.up_proj:   7%|▋         | 2514/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.41.down_proj:   7%|▋         | 2515/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.42.gate_proj:   7%|▋         | 2516/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.42.up_proj:   7%|▋         | 2517/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.42.down_proj:   7%|▋         | 2518/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.43.gate_proj:   7%|▋         | 2519/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.43.up_proj:   7%|▋         | 2520/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.43.down_proj:   7%|▋         | 2521/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.44.gate_proj:   7%|▋         | 2522/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.44.up_proj:   7%|▋         | 2523/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.44.down_proj:   7%|▋         | 2524/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.45.gate_proj:   7%|▋         | 2525/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.45.up_proj:   7%|▋         | 2526/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.45.down_proj:   7%|▋         | 2527/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.46.gate_proj:   7%|▋         | 2528/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.46.up_proj:   7%|▋         | 2529/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.46.down_proj:   7%|▋         | 2530/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.47.gate_proj:   7%|▋         | 2531/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.47.up_proj:   7%|▋         | 2532/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.47.down_proj:   7%|▋         | 2533/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.48.gate_proj:   7%|▋         | 2534/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.48.up_proj:   7%|▋         | 2535/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.48.down_proj:   7%|▋         | 2536/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.49.gate_proj:   7%|▋         | 2537/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.49.up_proj:   7%|▋         | 2538/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.49.down_proj:   7%|▋         | 2539/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.50.gate_proj:   7%|▋         | 2540/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.50.up_proj:   7%|▋         | 2541/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.50.down_proj:   7%|▋         | 2542/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.51.gate_proj:   7%|▋         | 2543/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.51.up_proj:   7%|▋         | 2544/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.51.down_proj:   7%|▋         | 2545/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.52.gate_proj:   7%|▋         | 2546/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.52.up_proj:   7%|▋         | 2547/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.52.down_proj:   7%|▋         | 2548/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.53.gate_proj:   7%|▋         | 2549/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.53.up_proj:   7%|▋         | 2550/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.53.down_proj:   7%|▋         | 2551/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.54.gate_proj:   7%|▋         | 2552/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.54.up_proj:   7%|▋         | 2553/36566 [00:03<00:29, 1156.76it/s]  
packing model.layers.5.mlp.experts.54.down_proj:   7%|▋         | 2554/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.55.gate_proj:   7%|▋         | 2555/36566 [00:03<00:29, 1156.76it/s]
packing model.layers.5.mlp.experts.55.gate_proj:   7%|▋         | 2556/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.55.up_proj:   7%|▋         | 2556/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.55.down_proj:   7%|▋         | 2557/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.56.gate_proj:   7%|▋         | 2558/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.56.up_proj:   7%|▋         | 2559/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.56.down_proj:   7%|▋         | 2560/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.57.gate_proj:   7%|▋         | 2561/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.57.up_proj:   7%|▋         | 2562/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.57.down_proj:   7%|▋         | 2563/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.58.gate_proj:   7%|▋         | 2564/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.58.up_proj:   7%|▋         | 2565/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.58.down_proj:   7%|▋         | 2566/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.59.gate_proj:   7%|▋         | 2567/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.59.up_proj:   7%|▋         | 2568/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.59.down_proj:   7%|▋         | 2569/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.60.gate_proj:   7%|▋         | 2570/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.60.up_proj:   7%|▋         | 2571/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.60.down_proj:   7%|▋         | 2572/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.61.gate_proj:   7%|▋         | 2573/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.61.up_proj:   7%|▋         | 2574/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.61.down_proj:   7%|▋         | 2575/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.62.gate_proj:   7%|▋         | 2576/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.62.up_proj:   7%|▋         | 2577/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.62.down_proj:   7%|▋         | 2578/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.63.gate_proj:   7%|▋         | 2579/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.63.up_proj:   7%|▋         | 2580/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.63.down_proj:   7%|▋         | 2581/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.64.gate_proj:   7%|▋         | 2582/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.64.up_proj:   7%|▋         | 2583/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.64.down_proj:   7%|▋         | 2584/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.65.gate_proj:   7%|▋         | 2585/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.65.up_proj:   7%|▋         | 2586/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.65.down_proj:   7%|▋         | 2587/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.66.gate_proj:   7%|▋         | 2588/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.66.up_proj:   7%|▋         | 2589/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.66.down_proj:   7%|▋         | 2590/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.67.gate_proj:   7%|▋         | 2591/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.67.up_proj:   7%|▋         | 2592/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.67.down_proj:   7%|▋         | 2593/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.68.gate_proj:   7%|▋         | 2594/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.68.up_proj:   7%|▋         | 2595/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.68.down_proj:   7%|▋         | 2596/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.69.gate_proj:   7%|▋         | 2597/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.69.up_proj:   7%|▋         | 2598/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.69.down_proj:   7%|▋         | 2599/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.70.gate_proj:   7%|▋         | 2600/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.70.up_proj:   7%|▋         | 2601/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.70.down_proj:   7%|▋         | 2602/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.71.gate_proj:   7%|▋         | 2603/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.71.up_proj:   7%|▋         | 2604/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.71.down_proj:   7%|▋         | 2605/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.72.gate_proj:   7%|▋         | 2606/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.72.up_proj:   7%|▋         | 2607/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.72.down_proj:   7%|▋         | 2608/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.73.gate_proj:   7%|▋         | 2609/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.73.up_proj:   7%|▋         | 2610/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.73.down_proj:   7%|▋         | 2611/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.74.gate_proj:   7%|▋         | 2612/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.74.up_proj:   7%|▋         | 2613/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.74.down_proj:   7%|▋         | 2614/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.75.gate_proj:   7%|▋         | 2615/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.75.up_proj:   7%|▋         | 2616/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.75.down_proj:   7%|▋         | 2617/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.76.gate_proj:   7%|▋         | 2618/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.76.up_proj:   7%|▋         | 2619/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.76.down_proj:   7%|▋         | 2620/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.77.gate_proj:   7%|▋         | 2621/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.77.up_proj:   7%|▋         | 2622/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.77.down_proj:   7%|▋         | 2623/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.78.gate_proj:   7%|▋         | 2624/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.78.up_proj:   7%|▋         | 2625/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.78.down_proj:   7%|▋         | 2626/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.79.gate_proj:   7%|▋         | 2627/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.79.up_proj:   7%|▋         | 2628/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.79.down_proj:   7%|▋         | 2629/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.80.gate_proj:   7%|▋         | 2630/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.80.up_proj:   7%|▋         | 2631/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.80.down_proj:   7%|▋         | 2632/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.81.gate_proj:   7%|▋         | 2633/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.81.up_proj:   7%|▋         | 2634/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.81.down_proj:   7%|▋         | 2635/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.82.gate_proj:   7%|▋         | 2636/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.82.up_proj:   7%|▋         | 2637/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.82.down_proj:   7%|▋         | 2638/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.83.gate_proj:   7%|▋         | 2639/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.83.up_proj:   7%|▋         | 2640/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.83.down_proj:   7%|▋         | 2641/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.84.gate_proj:   7%|▋         | 2642/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.84.up_proj:   7%|▋         | 2643/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.84.down_proj:   7%|▋         | 2644/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.85.gate_proj:   7%|▋         | 2645/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.85.up_proj:   7%|▋         | 2646/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.85.down_proj:   7%|▋         | 2647/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.86.gate_proj:   7%|▋         | 2648/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.86.up_proj:   7%|▋         | 2649/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.86.down_proj:   7%|▋         | 2650/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.87.gate_proj:   7%|▋         | 2651/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.87.up_proj:   7%|▋         | 2652/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.87.down_proj:   7%|▋         | 2653/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.88.gate_proj:   7%|▋         | 2654/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.88.up_proj:   7%|▋         | 2655/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.88.down_proj:   7%|▋         | 2656/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.89.gate_proj:   7%|▋         | 2657/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.89.up_proj:   7%|▋         | 2658/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.89.down_proj:   7%|▋         | 2659/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.90.gate_proj:   7%|▋         | 2660/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.90.up_proj:   7%|▋         | 2661/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.90.down_proj:   7%|▋         | 2662/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.91.gate_proj:   7%|▋         | 2663/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.91.up_proj:   7%|▋         | 2664/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.91.down_proj:   7%|▋         | 2665/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.92.gate_proj:   7%|▋         | 2666/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.92.up_proj:   7%|▋         | 2667/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.92.down_proj:   7%|▋         | 2668/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.93.gate_proj:   7%|▋         | 2669/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.93.up_proj:   7%|▋         | 2670/36566 [00:03<00:29, 1156.25it/s]  
packing model.layers.5.mlp.experts.93.down_proj:   7%|▋         | 2671/36566 [00:03<00:29, 1156.25it/s]
packing model.layers.5.mlp.experts.93.down_proj:   7%|▋         | 2672/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.94.gate_proj:   7%|▋         | 2672/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.94.up_proj:   7%|▋         | 2673/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.94.down_proj:   7%|▋         | 2674/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.95.gate_proj:   7%|▋         | 2675/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.95.up_proj:   7%|▋         | 2676/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.95.down_proj:   7%|▋         | 2677/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.96.gate_proj:   7%|▋         | 2678/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.96.up_proj:   7%|▋         | 2679/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.96.down_proj:   7%|▋         | 2680/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.97.gate_proj:   7%|▋         | 2681/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.97.up_proj:   7%|▋         | 2682/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.97.down_proj:   7%|▋         | 2683/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.98.gate_proj:   7%|▋         | 2684/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.98.up_proj:   7%|▋         | 2685/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.98.down_proj:   7%|▋         | 2686/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.99.gate_proj:   7%|▋         | 2687/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.99.up_proj:   7%|▋         | 2688/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.99.down_proj:   7%|▋         | 2689/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.100.gate_proj:   7%|▋         | 2690/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.100.up_proj:   7%|▋         | 2691/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.100.down_proj:   7%|▋         | 2692/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.101.gate_proj:   7%|▋         | 2693/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.101.up_proj:   7%|▋         | 2694/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.101.down_proj:   7%|▋         | 2695/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.102.gate_proj:   7%|▋         | 2696/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.102.up_proj:   7%|▋         | 2697/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.102.down_proj:   7%|▋         | 2698/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.103.gate_proj:   7%|▋         | 2699/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.103.up_proj:   7%|▋         | 2700/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.103.down_proj:   7%|▋         | 2701/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.104.gate_proj:   7%|▋         | 2702/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.104.up_proj:   7%|▋         | 2703/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.104.down_proj:   7%|▋         | 2704/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.105.gate_proj:   7%|▋         | 2705/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.105.up_proj:   7%|▋         | 2706/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.105.down_proj:   7%|▋         | 2707/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.106.gate_proj:   7%|▋         | 2708/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.106.up_proj:   7%|▋         | 2709/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.106.down_proj:   7%|▋         | 2710/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.107.gate_proj:   7%|▋         | 2711/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.107.up_proj:   7%|▋         | 2712/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.107.down_proj:   7%|▋         | 2713/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.108.gate_proj:   7%|▋         | 2714/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.108.up_proj:   7%|▋         | 2715/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.108.down_proj:   7%|▋         | 2716/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.109.gate_proj:   7%|▋         | 2717/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.109.up_proj:   7%|▋         | 2718/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.109.down_proj:   7%|▋         | 2719/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.110.gate_proj:   7%|▋         | 2720/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.110.up_proj:   7%|▋         | 2721/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.110.down_proj:   7%|▋         | 2722/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.111.gate_proj:   7%|▋         | 2723/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.111.up_proj:   7%|▋         | 2724/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.111.down_proj:   7%|▋         | 2725/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.112.gate_proj:   7%|▋         | 2726/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.112.up_proj:   7%|▋         | 2727/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.112.down_proj:   7%|▋         | 2728/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.113.gate_proj:   7%|▋         | 2729/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.113.up_proj:   7%|▋         | 2730/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.113.down_proj:   7%|▋         | 2731/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.114.gate_proj:   7%|▋         | 2732/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.114.up_proj:   7%|▋         | 2733/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.114.down_proj:   7%|▋         | 2734/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.115.gate_proj:   7%|▋         | 2735/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.115.up_proj:   7%|▋         | 2736/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.115.down_proj:   7%|▋         | 2737/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.116.gate_proj:   7%|▋         | 2738/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.116.up_proj:   7%|▋         | 2739/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.116.down_proj:   7%|▋         | 2740/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.117.gate_proj:   7%|▋         | 2741/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.117.up_proj:   7%|▋         | 2742/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.117.down_proj:   8%|▊         | 2743/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.118.gate_proj:   8%|▊         | 2744/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.118.up_proj:   8%|▊         | 2745/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.118.down_proj:   8%|▊         | 2746/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.119.gate_proj:   8%|▊         | 2747/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.119.up_proj:   8%|▊         | 2748/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.119.down_proj:   8%|▊         | 2749/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.120.gate_proj:   8%|▊         | 2750/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.120.up_proj:   8%|▊         | 2751/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.120.down_proj:   8%|▊         | 2752/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.121.gate_proj:   8%|▊         | 2753/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.121.up_proj:   8%|▊         | 2754/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.121.down_proj:   8%|▊         | 2755/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.122.gate_proj:   8%|▊         | 2756/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.122.up_proj:   8%|▊         | 2757/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.122.down_proj:   8%|▊         | 2758/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.123.gate_proj:   8%|▊         | 2759/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.123.up_proj:   8%|▊         | 2760/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.123.down_proj:   8%|▊         | 2761/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.124.gate_proj:   8%|▊         | 2762/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.124.up_proj:   8%|▊         | 2763/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.124.down_proj:   8%|▊         | 2764/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.125.gate_proj:   8%|▊         | 2765/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.125.up_proj:   8%|▊         | 2766/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.125.down_proj:   8%|▊         | 2767/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.126.gate_proj:   8%|▊         | 2768/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.126.up_proj:   8%|▊         | 2769/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.126.down_proj:   8%|▊         | 2770/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.127.gate_proj:   8%|▊         | 2771/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.5.mlp.experts.127.up_proj:   8%|▊         | 2772/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.5.mlp.experts.127.down_proj:   8%|▊         | 2773/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.0.gate_proj:   8%|▊         | 2774/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.0.up_proj:   8%|▊         | 2775/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.0.down_proj:   8%|▊         | 2776/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.1.gate_proj:   8%|▊         | 2777/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.1.up_proj:   8%|▊         | 2778/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.1.down_proj:   8%|▊         | 2779/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.2.gate_proj:   8%|▊         | 2780/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.2.up_proj:   8%|▊         | 2781/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.2.down_proj:   8%|▊         | 2782/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.3.gate_proj:   8%|▊         | 2783/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.3.up_proj:   8%|▊         | 2784/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.3.down_proj:   8%|▊         | 2785/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.4.gate_proj:   8%|▊         | 2786/36566 [00:03<00:29, 1156.68it/s]
packing model.layers.6.mlp.experts.4.up_proj:   8%|▊         | 2787/36566 [00:03<00:29, 1156.68it/s]  
packing model.layers.6.mlp.experts.4.up_proj:   8%|▊         | 2788/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.4.down_proj:   8%|▊         | 2788/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.5.gate_proj:   8%|▊         | 2789/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.5.up_proj:   8%|▊         | 2790/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.5.down_proj:   8%|▊         | 2791/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.6.gate_proj:   8%|▊         | 2792/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.6.up_proj:   8%|▊         | 2793/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.6.down_proj:   8%|▊         | 2794/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.7.gate_proj:   8%|▊         | 2795/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.7.up_proj:   8%|▊         | 2796/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.7.down_proj:   8%|▊         | 2797/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.8.gate_proj:   8%|▊         | 2798/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.8.up_proj:   8%|▊         | 2799/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.8.down_proj:   8%|▊         | 2800/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.9.gate_proj:   8%|▊         | 2801/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.9.up_proj:   8%|▊         | 2802/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.9.down_proj:   8%|▊         | 2803/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.10.gate_proj:   8%|▊         | 2804/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.10.up_proj:   8%|▊         | 2805/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.10.down_proj:   8%|▊         | 2806/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.11.gate_proj:   8%|▊         | 2807/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.11.up_proj:   8%|▊         | 2808/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.11.down_proj:   8%|▊         | 2809/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.12.gate_proj:   8%|▊         | 2810/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.12.up_proj:   8%|▊         | 2811/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.12.down_proj:   8%|▊         | 2812/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.13.gate_proj:   8%|▊         | 2813/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.13.up_proj:   8%|▊         | 2814/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.13.down_proj:   8%|▊         | 2815/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.14.gate_proj:   8%|▊         | 2816/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.14.up_proj:   8%|▊         | 2817/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.14.down_proj:   8%|▊         | 2818/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.15.gate_proj:   8%|▊         | 2819/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.15.up_proj:   8%|▊         | 2820/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.15.down_proj:   8%|▊         | 2821/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.16.gate_proj:   8%|▊         | 2822/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.16.up_proj:   8%|▊         | 2823/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.16.down_proj:   8%|▊         | 2824/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.17.gate_proj:   8%|▊         | 2825/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.17.up_proj:   8%|▊         | 2826/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.17.down_proj:   8%|▊         | 2827/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.18.gate_proj:   8%|▊         | 2828/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.18.up_proj:   8%|▊         | 2829/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.18.down_proj:   8%|▊         | 2830/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.19.gate_proj:   8%|▊         | 2831/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.19.up_proj:   8%|▊         | 2832/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.19.down_proj:   8%|▊         | 2833/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.20.gate_proj:   8%|▊         | 2834/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.20.up_proj:   8%|▊         | 2835/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.20.down_proj:   8%|▊         | 2836/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.21.gate_proj:   8%|▊         | 2837/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.21.up_proj:   8%|▊         | 2838/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.21.down_proj:   8%|▊         | 2839/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.22.gate_proj:   8%|▊         | 2840/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.22.up_proj:   8%|▊         | 2841/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.22.down_proj:   8%|▊         | 2842/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.23.gate_proj:   8%|▊         | 2843/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.23.up_proj:   8%|▊         | 2844/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.23.down_proj:   8%|▊         | 2845/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.24.gate_proj:   8%|▊         | 2846/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.24.up_proj:   8%|▊         | 2847/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.24.down_proj:   8%|▊         | 2848/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.25.gate_proj:   8%|▊         | 2849/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.25.up_proj:   8%|▊         | 2850/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.25.down_proj:   8%|▊         | 2851/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.26.gate_proj:   8%|▊         | 2852/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.26.up_proj:   8%|▊         | 2853/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.26.down_proj:   8%|▊         | 2854/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.27.gate_proj:   8%|▊         | 2855/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.27.up_proj:   8%|▊         | 2856/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.27.down_proj:   8%|▊         | 2857/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.28.gate_proj:   8%|▊         | 2858/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.28.up_proj:   8%|▊         | 2859/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.28.down_proj:   8%|▊         | 2860/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.29.gate_proj:   8%|▊         | 2861/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.29.up_proj:   8%|▊         | 2862/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.29.down_proj:   8%|▊         | 2863/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.30.gate_proj:   8%|▊         | 2864/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.30.up_proj:   8%|▊         | 2865/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.30.down_proj:   8%|▊         | 2866/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.31.gate_proj:   8%|▊         | 2867/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.31.up_proj:   8%|▊         | 2868/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.31.down_proj:   8%|▊         | 2869/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.32.gate_proj:   8%|▊         | 2870/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.32.up_proj:   8%|▊         | 2871/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.32.down_proj:   8%|▊         | 2872/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.33.gate_proj:   8%|▊         | 2873/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.33.up_proj:   8%|▊         | 2874/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.33.down_proj:   8%|▊         | 2875/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.34.gate_proj:   8%|▊         | 2876/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.34.up_proj:   8%|▊         | 2877/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.34.down_proj:   8%|▊         | 2878/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.35.gate_proj:   8%|▊         | 2879/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.35.up_proj:   8%|▊         | 2880/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.35.down_proj:   8%|▊         | 2881/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.36.gate_proj:   8%|▊         | 2882/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.36.up_proj:   8%|▊         | 2883/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.36.down_proj:   8%|▊         | 2884/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.37.gate_proj:   8%|▊         | 2885/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.37.up_proj:   8%|▊         | 2886/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.37.down_proj:   8%|▊         | 2887/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.38.gate_proj:   8%|▊         | 2888/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.38.up_proj:   8%|▊         | 2889/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.38.down_proj:   8%|▊         | 2890/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.39.gate_proj:   8%|▊         | 2891/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.39.up_proj:   8%|▊         | 2892/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.39.down_proj:   8%|▊         | 2893/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.40.gate_proj:   8%|▊         | 2894/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.40.up_proj:   8%|▊         | 2895/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.40.down_proj:   8%|▊         | 2896/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.41.gate_proj:   8%|▊         | 2897/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.41.up_proj:   8%|▊         | 2898/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.41.down_proj:   8%|▊         | 2899/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.42.gate_proj:   8%|▊         | 2900/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.42.up_proj:   8%|▊         | 2901/36566 [00:03<00:29, 1157.50it/s]  
packing model.layers.6.mlp.experts.42.down_proj:   8%|▊         | 2902/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.43.gate_proj:   8%|▊         | 2903/36566 [00:03<00:29, 1157.50it/s]
packing model.layers.6.mlp.experts.43.gate_proj:   8%|▊         | 2904/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.43.up_proj:   8%|▊         | 2904/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.43.down_proj:   8%|▊         | 2905/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.44.gate_proj:   8%|▊         | 2906/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.44.up_proj:   8%|▊         | 2907/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.44.down_proj:   8%|▊         | 2908/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.45.gate_proj:   8%|▊         | 2909/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.45.up_proj:   8%|▊         | 2910/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.45.down_proj:   8%|▊         | 2911/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.46.gate_proj:   8%|▊         | 2912/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.46.up_proj:   8%|▊         | 2913/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.46.down_proj:   8%|▊         | 2914/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.47.gate_proj:   8%|▊         | 2915/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.47.up_proj:   8%|▊         | 2916/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.47.down_proj:   8%|▊         | 2917/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.48.gate_proj:   8%|▊         | 2918/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.48.up_proj:   8%|▊         | 2919/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.48.down_proj:   8%|▊         | 2920/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.49.gate_proj:   8%|▊         | 2921/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.49.up_proj:   8%|▊         | 2922/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.49.down_proj:   8%|▊         | 2923/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.50.gate_proj:   8%|▊         | 2924/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.50.up_proj:   8%|▊         | 2925/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.50.down_proj:   8%|▊         | 2926/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.51.gate_proj:   8%|▊         | 2927/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.51.up_proj:   8%|▊         | 2928/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.51.down_proj:   8%|▊         | 2929/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.52.gate_proj:   8%|▊         | 2930/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.52.up_proj:   8%|▊         | 2931/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.52.down_proj:   8%|▊         | 2932/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.53.gate_proj:   8%|▊         | 2933/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.53.up_proj:   8%|▊         | 2934/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.53.down_proj:   8%|▊         | 2935/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.54.gate_proj:   8%|▊         | 2936/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.54.up_proj:   8%|▊         | 2937/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.54.down_proj:   8%|▊         | 2938/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.55.gate_proj:   8%|▊         | 2939/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.55.up_proj:   8%|▊         | 2940/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.55.down_proj:   8%|▊         | 2941/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.56.gate_proj:   8%|▊         | 2942/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.56.up_proj:   8%|▊         | 2943/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.56.down_proj:   8%|▊         | 2944/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.57.gate_proj:   8%|▊         | 2945/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.57.up_proj:   8%|▊         | 2946/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.57.down_proj:   8%|▊         | 2947/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.58.gate_proj:   8%|▊         | 2948/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.58.up_proj:   8%|▊         | 2949/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.58.down_proj:   8%|▊         | 2950/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.59.gate_proj:   8%|▊         | 2951/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.59.up_proj:   8%|▊         | 2952/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.59.down_proj:   8%|▊         | 2953/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.60.gate_proj:   8%|▊         | 2954/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.60.up_proj:   8%|▊         | 2955/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.60.down_proj:   8%|▊         | 2956/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.61.gate_proj:   8%|▊         | 2957/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.61.up_proj:   8%|▊         | 2958/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.61.down_proj:   8%|▊         | 2959/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.62.gate_proj:   8%|▊         | 2960/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.62.up_proj:   8%|▊         | 2961/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.62.down_proj:   8%|▊         | 2962/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.63.gate_proj:   8%|▊         | 2963/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.63.up_proj:   8%|▊         | 2964/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.63.down_proj:   8%|▊         | 2965/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.64.gate_proj:   8%|▊         | 2966/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.64.up_proj:   8%|▊         | 2967/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.64.down_proj:   8%|▊         | 2968/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.65.gate_proj:   8%|▊         | 2969/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.65.up_proj:   8%|▊         | 2970/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.65.down_proj:   8%|▊         | 2971/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.66.gate_proj:   8%|▊         | 2972/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.66.up_proj:   8%|▊         | 2973/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.66.down_proj:   8%|▊         | 2974/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.67.gate_proj:   8%|▊         | 2975/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.67.up_proj:   8%|▊         | 2976/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.67.down_proj:   8%|▊         | 2977/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.68.gate_proj:   8%|▊         | 2978/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.68.up_proj:   8%|▊         | 2979/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.68.down_proj:   8%|▊         | 2980/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.69.gate_proj:   8%|▊         | 2981/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.69.up_proj:   8%|▊         | 2982/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.69.down_proj:   8%|▊         | 2983/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.70.gate_proj:   8%|▊         | 2984/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.70.up_proj:   8%|▊         | 2985/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.70.down_proj:   8%|▊         | 2986/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.71.gate_proj:   8%|▊         | 2987/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.71.up_proj:   8%|▊         | 2988/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.71.down_proj:   8%|▊         | 2989/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.72.gate_proj:   8%|▊         | 2990/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.72.up_proj:   8%|▊         | 2991/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.72.down_proj:   8%|▊         | 2992/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.73.gate_proj:   8%|▊         | 2993/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.73.up_proj:   8%|▊         | 2994/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.73.down_proj:   8%|▊         | 2995/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.74.gate_proj:   8%|▊         | 2996/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.74.up_proj:   8%|▊         | 2997/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.74.down_proj:   8%|▊         | 2998/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.75.gate_proj:   8%|▊         | 2999/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.75.up_proj:   8%|▊         | 3000/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.75.down_proj:   8%|▊         | 3001/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.76.gate_proj:   8%|▊         | 3002/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.76.up_proj:   8%|▊         | 3003/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.76.down_proj:   8%|▊         | 3004/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.77.gate_proj:   8%|▊         | 3005/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.77.up_proj:   8%|▊         | 3006/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.77.down_proj:   8%|▊         | 3007/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.78.gate_proj:   8%|▊         | 3008/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.78.up_proj:   8%|▊         | 3009/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.78.down_proj:   8%|▊         | 3010/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.79.gate_proj:   8%|▊         | 3011/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.79.up_proj:   8%|▊         | 3012/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.79.down_proj:   8%|▊         | 3013/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.80.gate_proj:   8%|▊         | 3014/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.80.up_proj:   8%|▊         | 3015/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.80.down_proj:   8%|▊         | 3016/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.81.gate_proj:   8%|▊         | 3017/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.81.up_proj:   8%|▊         | 3018/36566 [00:03<00:29, 1156.10it/s]  
packing model.layers.6.mlp.experts.81.down_proj:   8%|▊         | 3019/36566 [00:03<00:29, 1156.10it/s]
packing model.layers.6.mlp.experts.81.down_proj:   8%|▊         | 3020/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.82.gate_proj:   8%|▊         | 3020/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.82.up_proj:   8%|▊         | 3021/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.82.down_proj:   8%|▊         | 3022/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.83.gate_proj:   8%|▊         | 3023/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.83.up_proj:   8%|▊         | 3024/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.83.down_proj:   8%|▊         | 3025/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.84.gate_proj:   8%|▊         | 3026/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.84.up_proj:   8%|▊         | 3027/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.84.down_proj:   8%|▊         | 3028/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.85.gate_proj:   8%|▊         | 3029/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.85.up_proj:   8%|▊         | 3030/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.85.down_proj:   8%|▊         | 3031/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.86.gate_proj:   8%|▊         | 3032/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.86.up_proj:   8%|▊         | 3033/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.86.down_proj:   8%|▊         | 3034/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.87.gate_proj:   8%|▊         | 3035/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.87.up_proj:   8%|▊         | 3036/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.87.down_proj:   8%|▊         | 3037/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.88.gate_proj:   8%|▊         | 3038/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.88.up_proj:   8%|▊         | 3039/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.88.down_proj:   8%|▊         | 3040/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.89.gate_proj:   8%|▊         | 3041/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.89.up_proj:   8%|▊         | 3042/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.89.down_proj:   8%|▊         | 3043/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.90.gate_proj:   8%|▊         | 3044/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.90.up_proj:   8%|▊         | 3045/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.90.down_proj:   8%|▊         | 3046/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.91.gate_proj:   8%|▊         | 3047/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.91.up_proj:   8%|▊         | 3048/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.91.down_proj:   8%|▊         | 3049/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.92.gate_proj:   8%|▊         | 3050/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.92.up_proj:   8%|▊         | 3051/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.92.down_proj:   8%|▊         | 3052/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.93.gate_proj:   8%|▊         | 3053/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.93.up_proj:   8%|▊         | 3054/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.93.down_proj:   8%|▊         | 3055/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.94.gate_proj:   8%|▊         | 3056/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.94.up_proj:   8%|▊         | 3057/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.94.down_proj:   8%|▊         | 3058/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.95.gate_proj:   8%|▊         | 3059/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.95.up_proj:   8%|▊         | 3060/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.95.down_proj:   8%|▊         | 3061/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.96.gate_proj:   8%|▊         | 3062/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.96.up_proj:   8%|▊         | 3063/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.96.down_proj:   8%|▊         | 3064/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.97.gate_proj:   8%|▊         | 3065/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.97.up_proj:   8%|▊         | 3066/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.97.down_proj:   8%|▊         | 3067/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.98.gate_proj:   8%|▊         | 3068/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.98.up_proj:   8%|▊         | 3069/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.98.down_proj:   8%|▊         | 3070/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.99.gate_proj:   8%|▊         | 3071/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.99.up_proj:   8%|▊         | 3072/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.99.down_proj:   8%|▊         | 3073/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.100.gate_proj:   8%|▊         | 3074/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.100.up_proj:   8%|▊         | 3075/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.100.down_proj:   8%|▊         | 3076/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.101.gate_proj:   8%|▊         | 3077/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.101.up_proj:   8%|▊         | 3078/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.101.down_proj:   8%|▊         | 3079/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.102.gate_proj:   8%|▊         | 3080/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.102.up_proj:   8%|▊         | 3081/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.102.down_proj:   8%|▊         | 3082/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.103.gate_proj:   8%|▊         | 3083/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.103.up_proj:   8%|▊         | 3084/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.103.down_proj:   8%|▊         | 3085/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.104.gate_proj:   8%|▊         | 3086/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.104.up_proj:   8%|▊         | 3087/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.104.down_proj:   8%|▊         | 3088/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.105.gate_proj:   8%|▊         | 3089/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.105.up_proj:   8%|▊         | 3090/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.105.down_proj:   8%|▊         | 3091/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.106.gate_proj:   8%|▊         | 3092/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.106.up_proj:   8%|▊         | 3093/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.106.down_proj:   8%|▊         | 3094/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.107.gate_proj:   8%|▊         | 3095/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.107.up_proj:   8%|▊         | 3096/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.107.down_proj:   8%|▊         | 3097/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.108.gate_proj:   8%|▊         | 3098/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.108.up_proj:   8%|▊         | 3099/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.108.down_proj:   8%|▊         | 3100/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.109.gate_proj:   8%|▊         | 3101/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.109.up_proj:   8%|▊         | 3102/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.109.down_proj:   8%|▊         | 3103/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.110.gate_proj:   8%|▊         | 3104/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.110.up_proj:   8%|▊         | 3105/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.110.down_proj:   8%|▊         | 3106/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.111.gate_proj:   8%|▊         | 3107/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.111.up_proj:   8%|▊         | 3108/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.111.down_proj:   9%|▊         | 3109/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.112.gate_proj:   9%|▊         | 3110/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.112.up_proj:   9%|▊         | 3111/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.112.down_proj:   9%|▊         | 3112/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.113.gate_proj:   9%|▊         | 3113/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.113.up_proj:   9%|▊         | 3114/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.113.down_proj:   9%|▊         | 3115/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.114.gate_proj:   9%|▊         | 3116/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.114.up_proj:   9%|▊         | 3117/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.114.down_proj:   9%|▊         | 3118/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.115.gate_proj:   9%|▊         | 3119/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.115.up_proj:   9%|▊         | 3120/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.115.down_proj:   9%|▊         | 3121/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.116.gate_proj:   9%|▊         | 3122/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.116.up_proj:   9%|▊         | 3123/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.116.down_proj:   9%|▊         | 3124/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.117.gate_proj:   9%|▊         | 3125/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.117.up_proj:   9%|▊         | 3126/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.117.down_proj:   9%|▊         | 3127/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.118.gate_proj:   9%|▊         | 3128/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.118.up_proj:   9%|▊         | 3129/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.118.down_proj:   9%|▊         | 3130/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.119.gate_proj:   9%|▊         | 3131/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.119.up_proj:   9%|▊         | 3132/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.119.down_proj:   9%|▊         | 3133/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.120.gate_proj:   9%|▊         | 3134/36566 [00:03<00:28, 1156.97it/s]
packing model.layers.6.mlp.experts.120.up_proj:   9%|▊         | 3135/36566 [00:03<00:28, 1156.97it/s]  
packing model.layers.6.mlp.experts.120.up_proj:   9%|▊         | 3136/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.120.down_proj:   9%|▊         | 3136/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.121.gate_proj:   9%|▊         | 3137/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.121.up_proj:   9%|▊         | 3138/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.121.down_proj:   9%|▊         | 3139/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.122.gate_proj:   9%|▊         | 3140/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.122.up_proj:   9%|▊         | 3141/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.122.down_proj:   9%|▊         | 3142/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.123.gate_proj:   9%|▊         | 3143/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.123.up_proj:   9%|▊         | 3144/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.123.down_proj:   9%|▊         | 3145/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.124.gate_proj:   9%|▊         | 3146/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.124.up_proj:   9%|▊         | 3147/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.124.down_proj:   9%|▊         | 3148/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.125.gate_proj:   9%|▊         | 3149/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.125.up_proj:   9%|▊         | 3150/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.125.down_proj:   9%|▊         | 3151/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.126.gate_proj:   9%|▊         | 3152/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.126.up_proj:   9%|▊         | 3153/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.126.down_proj:   9%|▊         | 3154/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.127.gate_proj:   9%|▊         | 3155/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.6.mlp.experts.127.up_proj:   9%|▊         | 3156/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.6.mlp.experts.127.down_proj:   9%|▊         | 3157/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.0.gate_proj:   9%|▊         | 3158/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.0.up_proj:   9%|▊         | 3159/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.0.down_proj:   9%|▊         | 3160/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.1.gate_proj:   9%|▊         | 3161/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.1.up_proj:   9%|▊         | 3162/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.1.down_proj:   9%|▊         | 3163/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.2.gate_proj:   9%|▊         | 3164/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.2.up_proj:   9%|▊         | 3165/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.2.down_proj:   9%|▊         | 3166/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.3.gate_proj:   9%|▊         | 3167/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.3.up_proj:   9%|▊         | 3168/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.3.down_proj:   9%|▊         | 3169/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.4.gate_proj:   9%|▊         | 3170/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.4.up_proj:   9%|▊         | 3171/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.4.down_proj:   9%|▊         | 3172/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.5.gate_proj:   9%|▊         | 3173/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.5.up_proj:   9%|▊         | 3174/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.5.down_proj:   9%|▊         | 3175/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.6.gate_proj:   9%|▊         | 3176/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.6.up_proj:   9%|▊         | 3177/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.6.down_proj:   9%|▊         | 3178/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.7.gate_proj:   9%|▊         | 3179/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.7.up_proj:   9%|▊         | 3180/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.7.down_proj:   9%|▊         | 3181/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.8.gate_proj:   9%|▊         | 3182/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.8.up_proj:   9%|▊         | 3183/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.8.down_proj:   9%|▊         | 3184/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.9.gate_proj:   9%|▊         | 3185/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.9.up_proj:   9%|▊         | 3186/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.9.down_proj:   9%|▊         | 3187/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.10.gate_proj:   9%|▊         | 3188/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.10.up_proj:   9%|▊         | 3189/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.10.down_proj:   9%|▊         | 3190/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.11.gate_proj:   9%|▊         | 3191/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.11.up_proj:   9%|▊         | 3192/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.11.down_proj:   9%|▊         | 3193/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.12.gate_proj:   9%|▊         | 3194/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.12.up_proj:   9%|▊         | 3195/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.12.down_proj:   9%|▊         | 3196/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.13.gate_proj:   9%|▊         | 3197/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.13.up_proj:   9%|▊         | 3198/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.13.down_proj:   9%|▊         | 3199/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.14.gate_proj:   9%|▉         | 3200/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.14.up_proj:   9%|▉         | 3201/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.14.down_proj:   9%|▉         | 3202/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.15.gate_proj:   9%|▉         | 3203/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.15.up_proj:   9%|▉         | 3204/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.15.down_proj:   9%|▉         | 3205/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.16.gate_proj:   9%|▉         | 3206/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.16.up_proj:   9%|▉         | 3207/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.16.down_proj:   9%|▉         | 3208/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.17.gate_proj:   9%|▉         | 3209/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.17.up_proj:   9%|▉         | 3210/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.17.down_proj:   9%|▉         | 3211/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.18.gate_proj:   9%|▉         | 3212/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.18.up_proj:   9%|▉         | 3213/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.18.down_proj:   9%|▉         | 3214/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.19.gate_proj:   9%|▉         | 3215/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.19.up_proj:   9%|▉         | 3216/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.19.down_proj:   9%|▉         | 3217/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.20.gate_proj:   9%|▉         | 3218/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.20.up_proj:   9%|▉         | 3219/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.20.down_proj:   9%|▉         | 3220/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.21.gate_proj:   9%|▉         | 3221/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.21.up_proj:   9%|▉         | 3222/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.21.down_proj:   9%|▉         | 3223/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.22.gate_proj:   9%|▉         | 3224/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.22.up_proj:   9%|▉         | 3225/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.22.down_proj:   9%|▉         | 3226/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.23.gate_proj:   9%|▉         | 3227/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.23.up_proj:   9%|▉         | 3228/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.23.down_proj:   9%|▉         | 3229/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.24.gate_proj:   9%|▉         | 3230/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.24.up_proj:   9%|▉         | 3231/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.24.down_proj:   9%|▉         | 3232/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.25.gate_proj:   9%|▉         | 3233/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.25.up_proj:   9%|▉         | 3234/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.25.down_proj:   9%|▉         | 3235/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.26.gate_proj:   9%|▉         | 3236/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.26.up_proj:   9%|▉         | 3237/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.26.down_proj:   9%|▉         | 3238/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.27.gate_proj:   9%|▉         | 3239/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.27.up_proj:   9%|▉         | 3240/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.27.down_proj:   9%|▉         | 3241/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.28.gate_proj:   9%|▉         | 3242/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.28.up_proj:   9%|▉         | 3243/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.28.down_proj:   9%|▉         | 3244/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.29.gate_proj:   9%|▉         | 3245/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.29.up_proj:   9%|▉         | 3246/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.29.down_proj:   9%|▉         | 3247/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.30.gate_proj:   9%|▉         | 3248/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.30.up_proj:   9%|▉         | 3249/36566 [00:03<00:28, 1157.47it/s]  
packing model.layers.7.mlp.experts.30.down_proj:   9%|▉         | 3250/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.31.gate_proj:   9%|▉         | 3251/36566 [00:03<00:28, 1157.47it/s]
packing model.layers.7.mlp.experts.31.gate_proj:   9%|▉         | 3252/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.31.up_proj:   9%|▉         | 3252/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.31.down_proj:   9%|▉         | 3253/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.32.gate_proj:   9%|▉         | 3254/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.32.up_proj:   9%|▉         | 3255/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.32.down_proj:   9%|▉         | 3256/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.33.gate_proj:   9%|▉         | 3257/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.33.up_proj:   9%|▉         | 3258/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.33.down_proj:   9%|▉         | 3259/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.34.gate_proj:   9%|▉         | 3260/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.34.up_proj:   9%|▉         | 3261/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.34.down_proj:   9%|▉         | 3262/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.35.gate_proj:   9%|▉         | 3263/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.35.up_proj:   9%|▉         | 3264/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.35.down_proj:   9%|▉         | 3265/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.36.gate_proj:   9%|▉         | 3266/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.36.up_proj:   9%|▉         | 3267/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.36.down_proj:   9%|▉         | 3268/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.37.gate_proj:   9%|▉         | 3269/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.37.up_proj:   9%|▉         | 3270/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.37.down_proj:   9%|▉         | 3271/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.38.gate_proj:   9%|▉         | 3272/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.38.up_proj:   9%|▉         | 3273/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.38.down_proj:   9%|▉         | 3274/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.39.gate_proj:   9%|▉         | 3275/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.39.up_proj:   9%|▉         | 3276/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.39.down_proj:   9%|▉         | 3277/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.40.gate_proj:   9%|▉         | 3278/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.40.up_proj:   9%|▉         | 3279/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.40.down_proj:   9%|▉         | 3280/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.41.gate_proj:   9%|▉         | 3281/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.41.up_proj:   9%|▉         | 3282/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.41.down_proj:   9%|▉         | 3283/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.42.gate_proj:   9%|▉         | 3284/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.42.up_proj:   9%|▉         | 3285/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.42.down_proj:   9%|▉         | 3286/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.43.gate_proj:   9%|▉         | 3287/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.43.up_proj:   9%|▉         | 3288/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.43.down_proj:   9%|▉         | 3289/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.44.gate_proj:   9%|▉         | 3290/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.44.up_proj:   9%|▉         | 3291/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.44.down_proj:   9%|▉         | 3292/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.45.gate_proj:   9%|▉         | 3293/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.45.up_proj:   9%|▉         | 3294/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.45.down_proj:   9%|▉         | 3295/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.46.gate_proj:   9%|▉         | 3296/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.46.up_proj:   9%|▉         | 3297/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.46.down_proj:   9%|▉         | 3298/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.47.gate_proj:   9%|▉         | 3299/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.47.up_proj:   9%|▉         | 3300/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.47.down_proj:   9%|▉         | 3301/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.48.gate_proj:   9%|▉         | 3302/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.48.up_proj:   9%|▉         | 3303/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.48.down_proj:   9%|▉         | 3304/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.49.gate_proj:   9%|▉         | 3305/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.49.up_proj:   9%|▉         | 3306/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.49.down_proj:   9%|▉         | 3307/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.50.gate_proj:   9%|▉         | 3308/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.50.up_proj:   9%|▉         | 3309/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.50.down_proj:   9%|▉         | 3310/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.51.gate_proj:   9%|▉         | 3311/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.51.up_proj:   9%|▉         | 3312/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.51.down_proj:   9%|▉         | 3313/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.52.gate_proj:   9%|▉         | 3314/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.52.up_proj:   9%|▉         | 3315/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.52.down_proj:   9%|▉         | 3316/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.53.gate_proj:   9%|▉         | 3317/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.53.up_proj:   9%|▉         | 3318/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.53.down_proj:   9%|▉         | 3319/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.54.gate_proj:   9%|▉         | 3320/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.54.up_proj:   9%|▉         | 3321/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.54.down_proj:   9%|▉         | 3322/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.55.gate_proj:   9%|▉         | 3323/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.55.up_proj:   9%|▉         | 3324/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.55.down_proj:   9%|▉         | 3325/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.56.gate_proj:   9%|▉         | 3326/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.56.up_proj:   9%|▉         | 3327/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.56.down_proj:   9%|▉         | 3328/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.57.gate_proj:   9%|▉         | 3329/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.57.up_proj:   9%|▉         | 3330/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.57.down_proj:   9%|▉         | 3331/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.58.gate_proj:   9%|▉         | 3332/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.58.up_proj:   9%|▉         | 3333/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.58.down_proj:   9%|▉         | 3334/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.59.gate_proj:   9%|▉         | 3335/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.59.up_proj:   9%|▉         | 3336/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.59.down_proj:   9%|▉         | 3337/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.60.gate_proj:   9%|▉         | 3338/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.60.up_proj:   9%|▉         | 3339/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.60.down_proj:   9%|▉         | 3340/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.61.gate_proj:   9%|▉         | 3341/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.61.up_proj:   9%|▉         | 3342/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.61.down_proj:   9%|▉         | 3343/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.62.gate_proj:   9%|▉         | 3344/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.62.up_proj:   9%|▉         | 3345/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.62.down_proj:   9%|▉         | 3346/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.63.gate_proj:   9%|▉         | 3347/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.63.up_proj:   9%|▉         | 3348/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.63.down_proj:   9%|▉         | 3349/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.64.gate_proj:   9%|▉         | 3350/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.64.up_proj:   9%|▉         | 3351/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.64.down_proj:   9%|▉         | 3352/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.65.gate_proj:   9%|▉         | 3353/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.65.up_proj:   9%|▉         | 3354/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.65.down_proj:   9%|▉         | 3355/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.66.gate_proj:   9%|▉         | 3356/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.66.up_proj:   9%|▉         | 3357/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.66.down_proj:   9%|▉         | 3358/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.67.gate_proj:   9%|▉         | 3359/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.67.up_proj:   9%|▉         | 3360/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.67.down_proj:   9%|▉         | 3361/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.68.gate_proj:   9%|▉         | 3362/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.68.up_proj:   9%|▉         | 3363/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.68.down_proj:   9%|▉         | 3364/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.69.gate_proj:   9%|▉         | 3365/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.69.up_proj:   9%|▉         | 3366/36566 [00:03<00:28, 1155.23it/s]  
packing model.layers.7.mlp.experts.69.down_proj:   9%|▉         | 3367/36566 [00:03<00:28, 1155.23it/s]
packing model.layers.7.mlp.experts.69.down_proj:   9%|▉         | 3368/36566 [00:03<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.70.gate_proj:   9%|▉         | 3368/36566 [00:03<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.70.up_proj:   9%|▉         | 3369/36566 [00:03<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.70.down_proj:   9%|▉         | 3370/36566 [00:03<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.71.gate_proj:   9%|▉         | 3371/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.71.up_proj:   9%|▉         | 3372/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.71.down_proj:   9%|▉         | 3373/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.72.gate_proj:   9%|▉         | 3374/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.72.up_proj:   9%|▉         | 3375/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.72.down_proj:   9%|▉         | 3376/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.73.gate_proj:   9%|▉         | 3377/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.73.up_proj:   9%|▉         | 3378/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.73.down_proj:   9%|▉         | 3379/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.74.gate_proj:   9%|▉         | 3380/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.74.up_proj:   9%|▉         | 3381/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.74.down_proj:   9%|▉         | 3382/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.75.gate_proj:   9%|▉         | 3383/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.75.up_proj:   9%|▉         | 3384/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.75.down_proj:   9%|▉         | 3385/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.76.gate_proj:   9%|▉         | 3386/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.76.up_proj:   9%|▉         | 3387/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.76.down_proj:   9%|▉         | 3388/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.77.gate_proj:   9%|▉         | 3389/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.77.up_proj:   9%|▉         | 3390/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.77.down_proj:   9%|▉         | 3391/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.78.gate_proj:   9%|▉         | 3392/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.78.up_proj:   9%|▉         | 3393/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.78.down_proj:   9%|▉         | 3394/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.79.gate_proj:   9%|▉         | 3395/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.79.up_proj:   9%|▉         | 3396/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.79.down_proj:   9%|▉         | 3397/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.80.gate_proj:   9%|▉         | 3398/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.80.up_proj:   9%|▉         | 3399/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.80.down_proj:   9%|▉         | 3400/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.81.gate_proj:   9%|▉         | 3401/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.81.up_proj:   9%|▉         | 3402/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.81.down_proj:   9%|▉         | 3403/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.82.gate_proj:   9%|▉         | 3404/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.82.up_proj:   9%|▉         | 3405/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.82.down_proj:   9%|▉         | 3406/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.83.gate_proj:   9%|▉         | 3407/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.83.up_proj:   9%|▉         | 3408/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.83.down_proj:   9%|▉         | 3409/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.84.gate_proj:   9%|▉         | 3410/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.84.up_proj:   9%|▉         | 3411/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.84.down_proj:   9%|▉         | 3412/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.85.gate_proj:   9%|▉         | 3413/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.85.up_proj:   9%|▉         | 3414/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.85.down_proj:   9%|▉         | 3415/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.86.gate_proj:   9%|▉         | 3416/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.86.up_proj:   9%|▉         | 3417/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.86.down_proj:   9%|▉         | 3418/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.87.gate_proj:   9%|▉         | 3419/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.87.up_proj:   9%|▉         | 3420/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.87.down_proj:   9%|▉         | 3421/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.88.gate_proj:   9%|▉         | 3422/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.88.up_proj:   9%|▉         | 3423/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.88.down_proj:   9%|▉         | 3424/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.89.gate_proj:   9%|▉         | 3425/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.89.up_proj:   9%|▉         | 3426/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.89.down_proj:   9%|▉         | 3427/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.90.gate_proj:   9%|▉         | 3428/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.90.up_proj:   9%|▉         | 3429/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.90.down_proj:   9%|▉         | 3430/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.91.gate_proj:   9%|▉         | 3431/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.91.up_proj:   9%|▉         | 3432/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.91.down_proj:   9%|▉         | 3433/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.92.gate_proj:   9%|▉         | 3434/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.92.up_proj:   9%|▉         | 3435/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.92.down_proj:   9%|▉         | 3436/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.93.gate_proj:   9%|▉         | 3437/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.93.up_proj:   9%|▉         | 3438/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.93.down_proj:   9%|▉         | 3439/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.94.gate_proj:   9%|▉         | 3440/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.94.up_proj:   9%|▉         | 3441/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.94.down_proj:   9%|▉         | 3442/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.95.gate_proj:   9%|▉         | 3443/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.95.up_proj:   9%|▉         | 3444/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.95.down_proj:   9%|▉         | 3445/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.96.gate_proj:   9%|▉         | 3446/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.96.up_proj:   9%|▉         | 3447/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.96.down_proj:   9%|▉         | 3448/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.97.gate_proj:   9%|▉         | 3449/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.97.up_proj:   9%|▉         | 3450/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.97.down_proj:   9%|▉         | 3451/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.98.gate_proj:   9%|▉         | 3452/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.98.up_proj:   9%|▉         | 3453/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.98.down_proj:   9%|▉         | 3454/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.99.gate_proj:   9%|▉         | 3455/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.99.up_proj:   9%|▉         | 3456/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.99.down_proj:   9%|▉         | 3457/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.100.gate_proj:   9%|▉         | 3458/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.100.up_proj:   9%|▉         | 3459/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.100.down_proj:   9%|▉         | 3460/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.101.gate_proj:   9%|▉         | 3461/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.101.up_proj:   9%|▉         | 3462/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.101.down_proj:   9%|▉         | 3463/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.102.gate_proj:   9%|▉         | 3464/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.102.up_proj:   9%|▉         | 3465/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.102.down_proj:   9%|▉         | 3466/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.103.gate_proj:   9%|▉         | 3467/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.103.up_proj:   9%|▉         | 3468/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.103.down_proj:   9%|▉         | 3469/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.104.gate_proj:   9%|▉         | 3470/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.104.up_proj:   9%|▉         | 3471/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.104.down_proj:   9%|▉         | 3472/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.105.gate_proj:   9%|▉         | 3473/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.105.up_proj:  10%|▉         | 3474/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.105.down_proj:  10%|▉         | 3475/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.106.gate_proj:  10%|▉         | 3476/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.106.up_proj:  10%|▉         | 3477/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.106.down_proj:  10%|▉         | 3478/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.107.gate_proj:  10%|▉         | 3479/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.107.up_proj:  10%|▉         | 3480/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.107.down_proj:  10%|▉         | 3481/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.108.gate_proj:  10%|▉         | 3482/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.108.up_proj:  10%|▉         | 3483/36566 [00:04<00:28, 1154.70it/s]  
packing model.layers.7.mlp.experts.108.down_proj:  10%|▉         | 3484/36566 [00:04<00:28, 1154.70it/s]
packing model.layers.7.mlp.experts.108.down_proj:  10%|▉         | 3485/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.109.gate_proj:  10%|▉         | 3485/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.109.up_proj:  10%|▉         | 3486/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.109.down_proj:  10%|▉         | 3487/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.110.gate_proj:  10%|▉         | 3488/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.110.up_proj:  10%|▉         | 3489/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.110.down_proj:  10%|▉         | 3490/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.111.gate_proj:  10%|▉         | 3491/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.111.up_proj:  10%|▉         | 3492/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.111.down_proj:  10%|▉         | 3493/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.112.gate_proj:  10%|▉         | 3494/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.112.up_proj:  10%|▉         | 3495/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.112.down_proj:  10%|▉         | 3496/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.113.gate_proj:  10%|▉         | 3497/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.113.up_proj:  10%|▉         | 3498/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.113.down_proj:  10%|▉         | 3499/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.114.gate_proj:  10%|▉         | 3500/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.114.up_proj:  10%|▉         | 3501/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.114.down_proj:  10%|▉         | 3502/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.115.gate_proj:  10%|▉         | 3503/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.115.up_proj:  10%|▉         | 3504/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.115.down_proj:  10%|▉         | 3505/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.116.gate_proj:  10%|▉         | 3506/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.116.up_proj:  10%|▉         | 3507/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.116.down_proj:  10%|▉         | 3508/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.117.gate_proj:  10%|▉         | 3509/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.117.up_proj:  10%|▉         | 3510/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.117.down_proj:  10%|▉         | 3511/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.118.gate_proj:  10%|▉         | 3512/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.118.up_proj:  10%|▉         | 3513/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.118.down_proj:  10%|▉         | 3514/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.119.gate_proj:  10%|▉         | 3515/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.119.up_proj:  10%|▉         | 3516/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.119.down_proj:  10%|▉         | 3517/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.120.gate_proj:  10%|▉         | 3518/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.120.up_proj:  10%|▉         | 3519/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.120.down_proj:  10%|▉         | 3520/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.121.gate_proj:  10%|▉         | 3521/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.121.up_proj:  10%|▉         | 3522/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.121.down_proj:  10%|▉         | 3523/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.122.gate_proj:  10%|▉         | 3524/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.122.up_proj:  10%|▉         | 3525/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.122.down_proj:  10%|▉         | 3526/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.123.gate_proj:  10%|▉         | 3527/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.123.up_proj:  10%|▉         | 3528/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.123.down_proj:  10%|▉         | 3529/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.124.gate_proj:  10%|▉         | 3530/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.124.up_proj:  10%|▉         | 3531/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.124.down_proj:  10%|▉         | 3532/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.125.gate_proj:  10%|▉         | 3533/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.125.up_proj:  10%|▉         | 3534/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.125.down_proj:  10%|▉         | 3535/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.126.gate_proj:  10%|▉         | 3536/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.126.up_proj:  10%|▉         | 3537/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.126.down_proj:  10%|▉         | 3538/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.127.gate_proj:  10%|▉         | 3539/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.7.mlp.experts.127.up_proj:  10%|▉         | 3540/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.7.mlp.experts.127.down_proj:  10%|▉         | 3541/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.0.gate_proj:  10%|▉         | 3542/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.0.up_proj:  10%|▉         | 3543/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.0.down_proj:  10%|▉         | 3544/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.1.gate_proj:  10%|▉         | 3545/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.1.up_proj:  10%|▉         | 3546/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.1.down_proj:  10%|▉         | 3547/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.2.gate_proj:  10%|▉         | 3548/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.2.up_proj:  10%|▉         | 3549/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.2.down_proj:  10%|▉         | 3550/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.3.gate_proj:  10%|▉         | 3551/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.3.up_proj:  10%|▉         | 3552/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.3.down_proj:  10%|▉         | 3553/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.4.gate_proj:  10%|▉         | 3554/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.4.up_proj:  10%|▉         | 3555/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.4.down_proj:  10%|▉         | 3556/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.5.gate_proj:  10%|▉         | 3557/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.5.up_proj:  10%|▉         | 3558/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.5.down_proj:  10%|▉         | 3559/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.6.gate_proj:  10%|▉         | 3560/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.6.up_proj:  10%|▉         | 3561/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.6.down_proj:  10%|▉         | 3562/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.7.gate_proj:  10%|▉         | 3563/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.7.up_proj:  10%|▉         | 3564/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.7.down_proj:  10%|▉         | 3565/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.8.gate_proj:  10%|▉         | 3566/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.8.up_proj:  10%|▉         | 3567/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.8.down_proj:  10%|▉         | 3568/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.9.gate_proj:  10%|▉         | 3569/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.9.up_proj:  10%|▉         | 3570/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.9.down_proj:  10%|▉         | 3571/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.10.gate_proj:  10%|▉         | 3572/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.10.up_proj:  10%|▉         | 3573/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.10.down_proj:  10%|▉         | 3574/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.11.gate_proj:  10%|▉         | 3575/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.11.up_proj:  10%|▉         | 3576/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.11.down_proj:  10%|▉         | 3577/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.12.gate_proj:  10%|▉         | 3578/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.12.up_proj:  10%|▉         | 3579/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.12.down_proj:  10%|▉         | 3580/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.13.gate_proj:  10%|▉         | 3581/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.13.up_proj:  10%|▉         | 3582/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.13.down_proj:  10%|▉         | 3583/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.14.gate_proj:  10%|▉         | 3584/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.14.up_proj:  10%|▉         | 3585/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.14.down_proj:  10%|▉         | 3586/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.15.gate_proj:  10%|▉         | 3587/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.15.up_proj:  10%|▉         | 3588/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.15.down_proj:  10%|▉         | 3589/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.16.gate_proj:  10%|▉         | 3590/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.16.up_proj:  10%|▉         | 3591/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.16.down_proj:  10%|▉         | 3592/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.17.gate_proj:  10%|▉         | 3593/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.17.up_proj:  10%|▉         | 3594/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.17.down_proj:  10%|▉         | 3595/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.18.gate_proj:  10%|▉         | 3596/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.18.up_proj:  10%|▉         | 3597/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.18.down_proj:  10%|▉         | 3598/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.19.gate_proj:  10%|▉         | 3599/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.19.up_proj:  10%|▉         | 3600/36566 [00:04<00:28, 1156.77it/s]  
packing model.layers.8.mlp.experts.19.down_proj:  10%|▉         | 3601/36566 [00:04<00:28, 1156.77it/s]
packing model.layers.8.mlp.experts.19.down_proj:  10%|▉         | 3602/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.20.gate_proj:  10%|▉         | 3602/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.20.up_proj:  10%|▉         | 3603/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.20.down_proj:  10%|▉         | 3604/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.21.gate_proj:  10%|▉         | 3605/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.21.up_proj:  10%|▉         | 3606/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.21.down_proj:  10%|▉         | 3607/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.22.gate_proj:  10%|▉         | 3608/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.22.up_proj:  10%|▉         | 3609/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.22.down_proj:  10%|▉         | 3610/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.23.gate_proj:  10%|▉         | 3611/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.23.up_proj:  10%|▉         | 3612/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.23.down_proj:  10%|▉         | 3613/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.24.gate_proj:  10%|▉         | 3614/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.24.up_proj:  10%|▉         | 3615/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.24.down_proj:  10%|▉         | 3616/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.25.gate_proj:  10%|▉         | 3617/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.25.up_proj:  10%|▉         | 3618/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.25.down_proj:  10%|▉         | 3619/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.26.gate_proj:  10%|▉         | 3620/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.26.up_proj:  10%|▉         | 3621/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.26.down_proj:  10%|▉         | 3622/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.27.gate_proj:  10%|▉         | 3623/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.27.up_proj:  10%|▉         | 3624/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.27.down_proj:  10%|▉         | 3625/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.28.gate_proj:  10%|▉         | 3626/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.28.up_proj:  10%|▉         | 3627/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.28.down_proj:  10%|▉         | 3628/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.29.gate_proj:  10%|▉         | 3629/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.29.up_proj:  10%|▉         | 3630/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.29.down_proj:  10%|▉         | 3631/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.30.gate_proj:  10%|▉         | 3632/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.30.up_proj:  10%|▉         | 3633/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.30.down_proj:  10%|▉         | 3634/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.31.gate_proj:  10%|▉         | 3635/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.31.up_proj:  10%|▉         | 3636/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.31.down_proj:  10%|▉         | 3637/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.32.gate_proj:  10%|▉         | 3638/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.32.up_proj:  10%|▉         | 3639/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.32.down_proj:  10%|▉         | 3640/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.33.gate_proj:  10%|▉         | 3641/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.33.up_proj:  10%|▉         | 3642/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.33.down_proj:  10%|▉         | 3643/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.34.gate_proj:  10%|▉         | 3644/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.34.up_proj:  10%|▉         | 3645/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.34.down_proj:  10%|▉         | 3646/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.35.gate_proj:  10%|▉         | 3647/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.35.up_proj:  10%|▉         | 3648/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.35.down_proj:  10%|▉         | 3649/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.36.gate_proj:  10%|▉         | 3650/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.36.up_proj:  10%|▉         | 3651/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.36.down_proj:  10%|▉         | 3652/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.37.gate_proj:  10%|▉         | 3653/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.37.up_proj:  10%|▉         | 3654/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.37.down_proj:  10%|▉         | 3655/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.38.gate_proj:  10%|▉         | 3656/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.38.up_proj:  10%|█         | 3657/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.38.down_proj:  10%|█         | 3658/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.39.gate_proj:  10%|█         | 3659/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.39.up_proj:  10%|█         | 3660/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.39.down_proj:  10%|█         | 3661/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.40.gate_proj:  10%|█         | 3662/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.40.up_proj:  10%|█         | 3663/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.40.down_proj:  10%|█         | 3664/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.41.gate_proj:  10%|█         | 3665/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.41.up_proj:  10%|█         | 3666/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.41.down_proj:  10%|█         | 3667/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.42.gate_proj:  10%|█         | 3668/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.42.up_proj:  10%|█         | 3669/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.42.down_proj:  10%|█         | 3670/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.43.gate_proj:  10%|█         | 3671/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.43.up_proj:  10%|█         | 3672/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.43.down_proj:  10%|█         | 3673/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.44.gate_proj:  10%|█         | 3674/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.44.up_proj:  10%|█         | 3675/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.44.down_proj:  10%|█         | 3676/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.45.gate_proj:  10%|█         | 3677/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.45.up_proj:  10%|█         | 3678/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.45.down_proj:  10%|█         | 3679/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.46.gate_proj:  10%|█         | 3680/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.46.up_proj:  10%|█         | 3681/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.46.down_proj:  10%|█         | 3682/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.47.gate_proj:  10%|█         | 3683/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.47.up_proj:  10%|█         | 3684/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.47.down_proj:  10%|█         | 3685/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.48.gate_proj:  10%|█         | 3686/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.48.up_proj:  10%|█         | 3687/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.48.down_proj:  10%|█         | 3688/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.49.gate_proj:  10%|█         | 3689/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.49.up_proj:  10%|█         | 3690/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.49.down_proj:  10%|█         | 3691/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.50.gate_proj:  10%|█         | 3692/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.50.up_proj:  10%|█         | 3693/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.50.down_proj:  10%|█         | 3694/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.51.gate_proj:  10%|█         | 3695/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.51.up_proj:  10%|█         | 3696/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.51.down_proj:  10%|█         | 3697/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.52.gate_proj:  10%|█         | 3698/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.52.up_proj:  10%|█         | 3699/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.52.down_proj:  10%|█         | 3700/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.53.gate_proj:  10%|█         | 3701/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.53.up_proj:  10%|█         | 3702/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.53.down_proj:  10%|█         | 3703/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.54.gate_proj:  10%|█         | 3704/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.54.up_proj:  10%|█         | 3705/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.54.down_proj:  10%|█         | 3706/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.55.gate_proj:  10%|█         | 3707/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.55.up_proj:  10%|█         | 3708/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.55.down_proj:  10%|█         | 3709/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.56.gate_proj:  10%|█         | 3710/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.56.up_proj:  10%|█         | 3711/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.56.down_proj:  10%|█         | 3712/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.57.gate_proj:  10%|█         | 3713/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.57.up_proj:  10%|█         | 3714/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.57.down_proj:  10%|█         | 3715/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.58.gate_proj:  10%|█         | 3716/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.58.up_proj:  10%|█         | 3717/36566 [00:04<00:28, 1158.59it/s]  
packing model.layers.8.mlp.experts.58.down_proj:  10%|█         | 3718/36566 [00:04<00:28, 1158.59it/s]
packing model.layers.8.mlp.experts.58.down_proj:  10%|█         | 3719/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.59.gate_proj:  10%|█         | 3719/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.59.up_proj:  10%|█         | 3720/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.59.down_proj:  10%|█         | 3721/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.60.gate_proj:  10%|█         | 3722/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.60.up_proj:  10%|█         | 3723/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.60.down_proj:  10%|█         | 3724/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.61.gate_proj:  10%|█         | 3725/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.61.up_proj:  10%|█         | 3726/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.61.down_proj:  10%|█         | 3727/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.62.gate_proj:  10%|█         | 3728/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.62.up_proj:  10%|█         | 3729/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.62.down_proj:  10%|█         | 3730/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.63.gate_proj:  10%|█         | 3731/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.63.up_proj:  10%|█         | 3732/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.63.down_proj:  10%|█         | 3733/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.64.gate_proj:  10%|█         | 3734/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.64.up_proj:  10%|█         | 3735/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.64.down_proj:  10%|█         | 3736/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.65.gate_proj:  10%|█         | 3737/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.65.up_proj:  10%|█         | 3738/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.65.down_proj:  10%|█         | 3739/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.66.gate_proj:  10%|█         | 3740/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.66.up_proj:  10%|█         | 3741/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.66.down_proj:  10%|█         | 3742/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.67.gate_proj:  10%|█         | 3743/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.67.up_proj:  10%|█         | 3744/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.67.down_proj:  10%|█         | 3745/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.68.gate_proj:  10%|█         | 3746/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.68.up_proj:  10%|█         | 3747/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.68.down_proj:  10%|█         | 3748/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.69.gate_proj:  10%|█         | 3749/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.69.up_proj:  10%|█         | 3750/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.69.down_proj:  10%|█         | 3751/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.70.gate_proj:  10%|█         | 3752/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.70.up_proj:  10%|█         | 3753/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.70.down_proj:  10%|█         | 3754/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.71.gate_proj:  10%|█         | 3755/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.71.up_proj:  10%|█         | 3756/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.71.down_proj:  10%|█         | 3757/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.72.gate_proj:  10%|█         | 3758/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.72.up_proj:  10%|█         | 3759/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.72.down_proj:  10%|█         | 3760/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.73.gate_proj:  10%|█         | 3761/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.73.up_proj:  10%|█         | 3762/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.73.down_proj:  10%|█         | 3763/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.74.gate_proj:  10%|█         | 3764/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.74.up_proj:  10%|█         | 3765/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.74.down_proj:  10%|█         | 3766/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.75.gate_proj:  10%|█         | 3767/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.75.up_proj:  10%|█         | 3768/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.75.down_proj:  10%|█         | 3769/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.76.gate_proj:  10%|█         | 3770/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.76.up_proj:  10%|█         | 3771/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.76.down_proj:  10%|█         | 3772/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.77.gate_proj:  10%|█         | 3773/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.77.up_proj:  10%|█         | 3774/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.77.down_proj:  10%|█         | 3775/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.78.gate_proj:  10%|█         | 3776/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.78.up_proj:  10%|█         | 3777/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.78.down_proj:  10%|█         | 3778/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.79.gate_proj:  10%|█         | 3779/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.79.up_proj:  10%|█         | 3780/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.79.down_proj:  10%|█         | 3781/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.80.gate_proj:  10%|█         | 3782/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.80.up_proj:  10%|█         | 3783/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.80.down_proj:  10%|█         | 3784/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.81.gate_proj:  10%|█         | 3785/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.81.up_proj:  10%|█         | 3786/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.81.down_proj:  10%|█         | 3787/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.82.gate_proj:  10%|█         | 3788/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.82.up_proj:  10%|█         | 3789/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.82.down_proj:  10%|█         | 3790/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.83.gate_proj:  10%|█         | 3791/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.83.up_proj:  10%|█         | 3792/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.83.down_proj:  10%|█         | 3793/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.84.gate_proj:  10%|█         | 3794/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.84.up_proj:  10%|█         | 3795/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.84.down_proj:  10%|█         | 3796/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.85.gate_proj:  10%|█         | 3797/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.85.up_proj:  10%|█         | 3798/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.85.down_proj:  10%|█         | 3799/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.86.gate_proj:  10%|█         | 3800/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.86.up_proj:  10%|█         | 3801/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.86.down_proj:  10%|█         | 3802/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.87.gate_proj:  10%|█         | 3803/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.87.up_proj:  10%|█         | 3804/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.87.down_proj:  10%|█         | 3805/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.88.gate_proj:  10%|█         | 3806/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.88.up_proj:  10%|█         | 3807/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.88.down_proj:  10%|█         | 3808/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.89.gate_proj:  10%|█         | 3809/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.89.up_proj:  10%|█         | 3810/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.89.down_proj:  10%|█         | 3811/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.90.gate_proj:  10%|█         | 3812/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.90.up_proj:  10%|█         | 3813/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.90.down_proj:  10%|█         | 3814/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.91.gate_proj:  10%|█         | 3815/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.91.up_proj:  10%|█         | 3816/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.91.down_proj:  10%|█         | 3817/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.92.gate_proj:  10%|█         | 3818/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.92.up_proj:  10%|█         | 3819/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.92.down_proj:  10%|█         | 3820/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.93.gate_proj:  10%|█         | 3821/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.93.up_proj:  10%|█         | 3822/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.93.down_proj:  10%|█         | 3823/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.94.gate_proj:  10%|█         | 3824/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.94.up_proj:  10%|█         | 3825/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.94.down_proj:  10%|█         | 3826/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.95.gate_proj:  10%|█         | 3827/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.95.up_proj:  10%|█         | 3828/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.95.down_proj:  10%|█         | 3829/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.96.gate_proj:  10%|█         | 3830/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.96.up_proj:  10%|█         | 3831/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.96.down_proj:  10%|█         | 3832/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.97.gate_proj:  10%|█         | 3833/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.97.up_proj:  10%|█         | 3834/36566 [00:04<00:28, 1160.96it/s]  
packing model.layers.8.mlp.experts.97.down_proj:  10%|█         | 3835/36566 [00:04<00:28, 1160.96it/s]
packing model.layers.8.mlp.experts.97.down_proj:  10%|█         | 3836/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.98.gate_proj:  10%|█         | 3836/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.98.up_proj:  10%|█         | 3837/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.98.down_proj:  10%|█         | 3838/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.99.gate_proj:  10%|█         | 3839/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.99.up_proj:  11%|█         | 3840/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.99.down_proj:  11%|█         | 3841/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.100.gate_proj:  11%|█         | 3842/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.100.up_proj:  11%|█         | 3843/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.100.down_proj:  11%|█         | 3844/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.101.gate_proj:  11%|█         | 3845/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.101.up_proj:  11%|█         | 3846/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.101.down_proj:  11%|█         | 3847/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.102.gate_proj:  11%|█         | 3848/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.102.up_proj:  11%|█         | 3849/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.102.down_proj:  11%|█         | 3850/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.103.gate_proj:  11%|█         | 3851/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.103.up_proj:  11%|█         | 3852/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.103.down_proj:  11%|█         | 3853/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.104.gate_proj:  11%|█         | 3854/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.104.up_proj:  11%|█         | 3855/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.104.down_proj:  11%|█         | 3856/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.105.gate_proj:  11%|█         | 3857/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.105.up_proj:  11%|█         | 3858/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.105.down_proj:  11%|█         | 3859/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.106.gate_proj:  11%|█         | 3860/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.106.up_proj:  11%|█         | 3861/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.106.down_proj:  11%|█         | 3862/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.107.gate_proj:  11%|█         | 3863/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.107.up_proj:  11%|█         | 3864/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.107.down_proj:  11%|█         | 3865/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.108.gate_proj:  11%|█         | 3866/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.108.up_proj:  11%|█         | 3867/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.108.down_proj:  11%|█         | 3868/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.109.gate_proj:  11%|█         | 3869/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.109.up_proj:  11%|█         | 3870/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.109.down_proj:  11%|█         | 3871/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.110.gate_proj:  11%|█         | 3872/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.110.up_proj:  11%|█         | 3873/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.110.down_proj:  11%|█         | 3874/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.111.gate_proj:  11%|█         | 3875/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.111.up_proj:  11%|█         | 3876/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.111.down_proj:  11%|█         | 3877/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.112.gate_proj:  11%|█         | 3878/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.112.up_proj:  11%|█         | 3879/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.112.down_proj:  11%|█         | 3880/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.113.gate_proj:  11%|█         | 3881/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.113.up_proj:  11%|█         | 3882/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.113.down_proj:  11%|█         | 3883/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.114.gate_proj:  11%|█         | 3884/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.114.up_proj:  11%|█         | 3885/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.114.down_proj:  11%|█         | 3886/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.115.gate_proj:  11%|█         | 3887/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.115.up_proj:  11%|█         | 3888/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.115.down_proj:  11%|█         | 3889/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.116.gate_proj:  11%|█         | 3890/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.116.up_proj:  11%|█         | 3891/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.116.down_proj:  11%|█         | 3892/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.117.gate_proj:  11%|█         | 3893/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.117.up_proj:  11%|█         | 3894/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.117.down_proj:  11%|█         | 3895/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.118.gate_proj:  11%|█         | 3896/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.118.up_proj:  11%|█         | 3897/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.118.down_proj:  11%|█         | 3898/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.119.gate_proj:  11%|█         | 3899/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.119.up_proj:  11%|█         | 3900/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.119.down_proj:  11%|█         | 3901/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.120.gate_proj:  11%|█         | 3902/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.120.up_proj:  11%|█         | 3903/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.120.down_proj:  11%|█         | 3904/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.121.gate_proj:  11%|█         | 3905/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.121.up_proj:  11%|█         | 3906/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.121.down_proj:  11%|█         | 3907/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.122.gate_proj:  11%|█         | 3908/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.122.up_proj:  11%|█         | 3909/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.122.down_proj:  11%|█         | 3910/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.123.gate_proj:  11%|█         | 3911/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.123.up_proj:  11%|█         | 3912/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.123.down_proj:  11%|█         | 3913/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.124.gate_proj:  11%|█         | 3914/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.124.up_proj:  11%|█         | 3915/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.124.down_proj:  11%|█         | 3916/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.125.gate_proj:  11%|█         | 3917/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.125.up_proj:  11%|█         | 3918/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.125.down_proj:  11%|█         | 3919/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.126.gate_proj:  11%|█         | 3920/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.126.up_proj:  11%|█         | 3921/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.126.down_proj:  11%|█         | 3922/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.127.gate_proj:  11%|█         | 3923/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.8.mlp.experts.127.up_proj:  11%|█         | 3924/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.8.mlp.experts.127.down_proj:  11%|█         | 3925/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.0.gate_proj:  11%|█         | 3926/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.0.up_proj:  11%|█         | 3927/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.0.down_proj:  11%|█         | 3928/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.1.gate_proj:  11%|█         | 3929/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.1.up_proj:  11%|█         | 3930/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.1.down_proj:  11%|█         | 3931/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.2.gate_proj:  11%|█         | 3932/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.2.up_proj:  11%|█         | 3933/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.2.down_proj:  11%|█         | 3934/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.3.gate_proj:  11%|█         | 3935/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.3.up_proj:  11%|█         | 3936/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.3.down_proj:  11%|█         | 3937/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.4.gate_proj:  11%|█         | 3938/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.4.up_proj:  11%|█         | 3939/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.4.down_proj:  11%|█         | 3940/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.5.gate_proj:  11%|█         | 3941/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.5.up_proj:  11%|█         | 3942/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.5.down_proj:  11%|█         | 3943/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.6.gate_proj:  11%|█         | 3944/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.6.up_proj:  11%|█         | 3945/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.6.down_proj:  11%|█         | 3946/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.7.gate_proj:  11%|█         | 3947/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.7.up_proj:  11%|█         | 3948/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.7.down_proj:  11%|█         | 3949/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.8.gate_proj:  11%|█         | 3950/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.8.up_proj:  11%|█         | 3951/36566 [00:04<00:28, 1161.17it/s]  
packing model.layers.9.mlp.experts.8.down_proj:  11%|█         | 3952/36566 [00:04<00:28, 1161.17it/s]
packing model.layers.9.mlp.experts.8.down_proj:  11%|█         | 3953/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.9.gate_proj:  11%|█         | 3953/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.9.up_proj:  11%|█         | 3954/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.9.down_proj:  11%|█         | 3955/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.10.gate_proj:  11%|█         | 3956/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.10.up_proj:  11%|█         | 3957/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.10.down_proj:  11%|█         | 3958/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.11.gate_proj:  11%|█         | 3959/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.11.up_proj:  11%|█         | 3960/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.11.down_proj:  11%|█         | 3961/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.12.gate_proj:  11%|█         | 3962/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.12.up_proj:  11%|█         | 3963/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.12.down_proj:  11%|█         | 3964/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.13.gate_proj:  11%|█         | 3965/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.13.up_proj:  11%|█         | 3966/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.13.down_proj:  11%|█         | 3967/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.14.gate_proj:  11%|█         | 3968/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.14.up_proj:  11%|█         | 3969/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.14.down_proj:  11%|█         | 3970/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.15.gate_proj:  11%|█         | 3971/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.15.up_proj:  11%|█         | 3972/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.15.down_proj:  11%|█         | 3973/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.16.gate_proj:  11%|█         | 3974/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.16.up_proj:  11%|█         | 3975/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.16.down_proj:  11%|█         | 3976/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.17.gate_proj:  11%|█         | 3977/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.17.up_proj:  11%|█         | 3978/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.17.down_proj:  11%|█         | 3979/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.18.gate_proj:  11%|█         | 3980/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.18.up_proj:  11%|█         | 3981/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.18.down_proj:  11%|█         | 3982/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.19.gate_proj:  11%|█         | 3983/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.19.up_proj:  11%|█         | 3984/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.19.down_proj:  11%|█         | 3985/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.20.gate_proj:  11%|█         | 3986/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.20.up_proj:  11%|█         | 3987/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.20.down_proj:  11%|█         | 3988/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.21.gate_proj:  11%|█         | 3989/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.21.up_proj:  11%|█         | 3990/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.21.down_proj:  11%|█         | 3991/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.22.gate_proj:  11%|█         | 3992/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.22.up_proj:  11%|█         | 3993/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.22.down_proj:  11%|█         | 3994/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.23.gate_proj:  11%|█         | 3995/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.23.up_proj:  11%|█         | 3996/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.23.down_proj:  11%|█         | 3997/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.24.gate_proj:  11%|█         | 3998/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.24.up_proj:  11%|█         | 3999/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.24.down_proj:  11%|█         | 4000/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.25.gate_proj:  11%|█         | 4001/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.25.up_proj:  11%|█         | 4002/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.25.down_proj:  11%|█         | 4003/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.26.gate_proj:  11%|█         | 4004/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.26.up_proj:  11%|█         | 4005/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.26.down_proj:  11%|█         | 4006/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.27.gate_proj:  11%|█         | 4007/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.27.up_proj:  11%|█         | 4008/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.27.down_proj:  11%|█         | 4009/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.28.gate_proj:  11%|█         | 4010/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.28.up_proj:  11%|█         | 4011/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.28.down_proj:  11%|█         | 4012/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.29.gate_proj:  11%|█         | 4013/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.29.up_proj:  11%|█         | 4014/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.29.down_proj:  11%|█         | 4015/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.30.gate_proj:  11%|█         | 4016/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.30.up_proj:  11%|█         | 4017/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.30.down_proj:  11%|█         | 4018/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.31.gate_proj:  11%|█         | 4019/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.31.up_proj:  11%|█         | 4020/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.31.down_proj:  11%|█         | 4021/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.32.gate_proj:  11%|█         | 4022/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.32.up_proj:  11%|█         | 4023/36566 [00:04<00:28, 1162.21it/s]  
packing model.layers.9.mlp.experts.32.down_proj:  11%|█         | 4024/36566 [00:04<00:28, 1162.21it/s]
packing model.layers.9.mlp.experts.33.gate_proj:  11%|█         | 4025/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.33.up_proj:  11%|█         | 4026/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.33.down_proj:  11%|█         | 4027/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.34.gate_proj:  11%|█         | 4028/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.34.up_proj:  11%|█         | 4029/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.34.down_proj:  11%|█         | 4030/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.35.gate_proj:  11%|█         | 4031/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.35.up_proj:  11%|█         | 4032/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.35.down_proj:  11%|█         | 4033/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.36.gate_proj:  11%|█         | 4034/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.36.up_proj:  11%|█         | 4035/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.36.down_proj:  11%|█         | 4036/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.37.gate_proj:  11%|█         | 4037/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.37.up_proj:  11%|█         | 4038/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.37.down_proj:  11%|█         | 4039/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.38.gate_proj:  11%|█         | 4040/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.38.up_proj:  11%|█         | 4041/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.38.down_proj:  11%|█         | 4042/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.39.gate_proj:  11%|█         | 4043/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.39.up_proj:  11%|█         | 4044/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.39.down_proj:  11%|█         | 4045/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.40.gate_proj:  11%|█         | 4046/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.40.up_proj:  11%|█         | 4047/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.40.down_proj:  11%|█         | 4048/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.41.gate_proj:  11%|█         | 4049/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.41.up_proj:  11%|█         | 4050/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.41.down_proj:  11%|█         | 4051/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.42.gate_proj:  11%|█         | 4052/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.42.up_proj:  11%|█         | 4053/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.42.down_proj:  11%|█         | 4054/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.43.gate_proj:  11%|█         | 4055/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.43.up_proj:  11%|█         | 4056/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.43.down_proj:  11%|█         | 4057/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.44.gate_proj:  11%|█         | 4058/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.44.up_proj:  11%|█         | 4059/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.44.down_proj:  11%|█         | 4060/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.45.gate_proj:  11%|█         | 4061/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.45.up_proj:  11%|█         | 4062/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.45.down_proj:  11%|█         | 4063/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.46.gate_proj:  11%|█         | 4064/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.46.up_proj:  11%|█         | 4065/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.46.down_proj:  11%|█         | 4066/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.47.gate_proj:  11%|█         | 4067/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.47.up_proj:  11%|█         | 4068/36566 [00:04<00:27, 1162.21it/s]  
packing model.layers.9.mlp.experts.47.down_proj:  11%|█         | 4069/36566 [00:04<00:27, 1162.21it/s]
packing model.layers.9.mlp.experts.47.down_proj:  11%|█         | 4070/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.48.gate_proj:  11%|█         | 4070/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.48.up_proj:  11%|█         | 4071/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.48.down_proj:  11%|█         | 4072/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.49.gate_proj:  11%|█         | 4073/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.49.up_proj:  11%|█         | 4074/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.49.down_proj:  11%|█         | 4075/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.50.gate_proj:  11%|█         | 4076/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.50.up_proj:  11%|█         | 4077/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.50.down_proj:  11%|█         | 4078/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.51.gate_proj:  11%|█         | 4079/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.51.up_proj:  11%|█         | 4080/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.51.down_proj:  11%|█         | 4081/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.52.gate_proj:  11%|█         | 4082/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.52.up_proj:  11%|█         | 4083/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.52.down_proj:  11%|█         | 4084/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.53.gate_proj:  11%|█         | 4085/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.53.up_proj:  11%|█         | 4086/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.53.down_proj:  11%|█         | 4087/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.54.gate_proj:  11%|█         | 4088/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.54.up_proj:  11%|█         | 4089/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.54.down_proj:  11%|█         | 4090/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.55.gate_proj:  11%|█         | 4091/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.55.up_proj:  11%|█         | 4092/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.55.down_proj:  11%|█         | 4093/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.56.gate_proj:  11%|█         | 4094/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.56.up_proj:  11%|█         | 4095/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.56.down_proj:  11%|█         | 4096/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.57.gate_proj:  11%|█         | 4097/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.57.up_proj:  11%|█         | 4098/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.57.down_proj:  11%|█         | 4099/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.58.gate_proj:  11%|█         | 4100/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.58.up_proj:  11%|█         | 4101/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.58.down_proj:  11%|█         | 4102/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.59.gate_proj:  11%|█         | 4103/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.59.up_proj:  11%|█         | 4104/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.59.down_proj:  11%|█         | 4105/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.60.gate_proj:  11%|█         | 4106/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.60.up_proj:  11%|█         | 4107/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.60.down_proj:  11%|█         | 4108/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.61.gate_proj:  11%|█         | 4109/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.61.up_proj:  11%|█         | 4110/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.61.down_proj:  11%|█         | 4111/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.62.gate_proj:  11%|█         | 4112/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.62.up_proj:  11%|█         | 4113/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.62.down_proj:  11%|█▏        | 4114/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.63.gate_proj:  11%|█▏        | 4115/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.63.up_proj:  11%|█▏        | 4116/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.63.down_proj:  11%|█▏        | 4117/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.64.gate_proj:  11%|█▏        | 4118/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.64.up_proj:  11%|█▏        | 4119/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.64.down_proj:  11%|█▏        | 4120/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.65.gate_proj:  11%|█▏        | 4121/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.65.up_proj:  11%|█▏        | 4122/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.65.down_proj:  11%|█▏        | 4123/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.66.gate_proj:  11%|█▏        | 4124/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.66.up_proj:  11%|█▏        | 4125/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.66.down_proj:  11%|█▏        | 4126/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.67.gate_proj:  11%|█▏        | 4127/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.67.up_proj:  11%|█▏        | 4128/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.67.down_proj:  11%|█▏        | 4129/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.68.gate_proj:  11%|█▏        | 4130/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.68.up_proj:  11%|█▏        | 4131/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.68.down_proj:  11%|█▏        | 4132/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.69.gate_proj:  11%|█▏        | 4133/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.69.up_proj:  11%|█▏        | 4134/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.69.down_proj:  11%|█▏        | 4135/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.70.gate_proj:  11%|█▏        | 4136/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.70.up_proj:  11%|█▏        | 4137/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.70.down_proj:  11%|█▏        | 4138/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.71.gate_proj:  11%|█▏        | 4139/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.71.up_proj:  11%|█▏        | 4140/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.71.down_proj:  11%|█▏        | 4141/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.72.gate_proj:  11%|█▏        | 4142/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.72.up_proj:  11%|█▏        | 4143/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.72.down_proj:  11%|█▏        | 4144/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.73.gate_proj:  11%|█▏        | 4145/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.73.up_proj:  11%|█▏        | 4146/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.73.down_proj:  11%|█▏        | 4147/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.74.gate_proj:  11%|█▏        | 4148/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.74.up_proj:  11%|█▏        | 4149/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.74.down_proj:  11%|█▏        | 4150/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.75.gate_proj:  11%|█▏        | 4151/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.75.up_proj:  11%|█▏        | 4152/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.75.down_proj:  11%|█▏        | 4153/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.76.gate_proj:  11%|█▏        | 4154/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.76.up_proj:  11%|█▏        | 4155/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.76.down_proj:  11%|█▏        | 4156/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.77.gate_proj:  11%|█▏        | 4157/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.77.up_proj:  11%|█▏        | 4158/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.77.down_proj:  11%|█▏        | 4159/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.78.gate_proj:  11%|█▏        | 4160/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.78.up_proj:  11%|█▏        | 4161/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.78.down_proj:  11%|█▏        | 4162/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.79.gate_proj:  11%|█▏        | 4163/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.79.up_proj:  11%|█▏        | 4164/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.79.down_proj:  11%|█▏        | 4165/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.80.gate_proj:  11%|█▏        | 4166/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.80.up_proj:  11%|█▏        | 4167/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.80.down_proj:  11%|█▏        | 4168/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.81.gate_proj:  11%|█▏        | 4169/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.81.up_proj:  11%|█▏        | 4170/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.81.down_proj:  11%|█▏        | 4171/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.82.gate_proj:  11%|█▏        | 4172/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.82.up_proj:  11%|█▏        | 4173/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.82.down_proj:  11%|█▏        | 4174/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.83.gate_proj:  11%|█▏        | 4175/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.83.up_proj:  11%|█▏        | 4176/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.83.down_proj:  11%|█▏        | 4177/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.84.gate_proj:  11%|█▏        | 4178/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.84.up_proj:  11%|█▏        | 4179/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.84.down_proj:  11%|█▏        | 4180/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.85.gate_proj:  11%|█▏        | 4181/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.85.up_proj:  11%|█▏        | 4182/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.85.down_proj:  11%|█▏        | 4183/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.86.gate_proj:  11%|█▏        | 4184/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.86.up_proj:  11%|█▏        | 4185/36566 [00:04<00:27, 1163.68it/s]  
packing model.layers.9.mlp.experts.86.down_proj:  11%|█▏        | 4186/36566 [00:04<00:27, 1163.68it/s]
packing model.layers.9.mlp.experts.86.down_proj:  11%|█▏        | 4187/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.87.gate_proj:  11%|█▏        | 4187/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.87.up_proj:  11%|█▏        | 4188/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.87.down_proj:  11%|█▏        | 4189/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.88.gate_proj:  11%|█▏        | 4190/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.88.up_proj:  11%|█▏        | 4191/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.88.down_proj:  11%|█▏        | 4192/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.89.gate_proj:  11%|█▏        | 4193/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.89.up_proj:  11%|█▏        | 4194/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.89.down_proj:  11%|█▏        | 4195/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.90.gate_proj:  11%|█▏        | 4196/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.90.up_proj:  11%|█▏        | 4197/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.90.down_proj:  11%|█▏        | 4198/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.91.gate_proj:  11%|█▏        | 4199/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.91.up_proj:  11%|█▏        | 4200/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.91.down_proj:  11%|█▏        | 4201/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.92.gate_proj:  11%|█▏        | 4202/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.92.up_proj:  11%|█▏        | 4203/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.92.down_proj:  11%|█▏        | 4204/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.93.gate_proj:  11%|█▏        | 4205/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.93.up_proj:  12%|█▏        | 4206/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.93.down_proj:  12%|█▏        | 4207/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.94.gate_proj:  12%|█▏        | 4208/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.94.up_proj:  12%|█▏        | 4209/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.94.down_proj:  12%|█▏        | 4210/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.95.gate_proj:  12%|█▏        | 4211/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.95.up_proj:  12%|█▏        | 4212/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.95.down_proj:  12%|█▏        | 4213/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.96.gate_proj:  12%|█▏        | 4214/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.96.up_proj:  12%|█▏        | 4215/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.96.down_proj:  12%|█▏        | 4216/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.97.gate_proj:  12%|█▏        | 4217/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.97.up_proj:  12%|█▏        | 4218/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.97.down_proj:  12%|█▏        | 4219/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.98.gate_proj:  12%|█▏        | 4220/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.98.up_proj:  12%|█▏        | 4221/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.98.down_proj:  12%|█▏        | 4222/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.99.gate_proj:  12%|█▏        | 4223/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.99.up_proj:  12%|█▏        | 4224/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.99.down_proj:  12%|█▏        | 4225/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.100.gate_proj:  12%|█▏        | 4226/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.100.up_proj:  12%|█▏        | 4227/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.100.down_proj:  12%|█▏        | 4228/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.101.gate_proj:  12%|█▏        | 4229/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.101.up_proj:  12%|█▏        | 4230/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.101.down_proj:  12%|█▏        | 4231/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.102.gate_proj:  12%|█▏        | 4232/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.102.up_proj:  12%|█▏        | 4233/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.102.down_proj:  12%|█▏        | 4234/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.103.gate_proj:  12%|█▏        | 4235/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.103.up_proj:  12%|█▏        | 4236/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.103.down_proj:  12%|█▏        | 4237/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.104.gate_proj:  12%|█▏        | 4238/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.104.up_proj:  12%|█▏        | 4239/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.104.down_proj:  12%|█▏        | 4240/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.105.gate_proj:  12%|█▏        | 4241/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.105.up_proj:  12%|█▏        | 4242/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.105.down_proj:  12%|█▏        | 4243/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.106.gate_proj:  12%|█▏        | 4244/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.106.up_proj:  12%|█▏        | 4245/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.106.down_proj:  12%|█▏        | 4246/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.107.gate_proj:  12%|█▏        | 4247/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.107.up_proj:  12%|█▏        | 4248/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.107.down_proj:  12%|█▏        | 4249/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.108.gate_proj:  12%|█▏        | 4250/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.108.up_proj:  12%|█▏        | 4251/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.108.down_proj:  12%|█▏        | 4252/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.109.gate_proj:  12%|█▏        | 4253/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.109.up_proj:  12%|█▏        | 4254/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.109.down_proj:  12%|█▏        | 4255/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.110.gate_proj:  12%|█▏        | 4256/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.110.up_proj:  12%|█▏        | 4257/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.110.down_proj:  12%|█▏        | 4258/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.111.gate_proj:  12%|█▏        | 4259/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.111.up_proj:  12%|█▏        | 4260/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.111.down_proj:  12%|█▏        | 4261/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.112.gate_proj:  12%|█▏        | 4262/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.112.up_proj:  12%|█▏        | 4263/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.112.down_proj:  12%|█▏        | 4264/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.113.gate_proj:  12%|█▏        | 4265/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.113.up_proj:  12%|█▏        | 4266/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.113.down_proj:  12%|█▏        | 4267/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.114.gate_proj:  12%|█▏        | 4268/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.114.up_proj:  12%|█▏        | 4269/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.114.down_proj:  12%|█▏        | 4270/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.115.gate_proj:  12%|█▏        | 4271/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.115.up_proj:  12%|█▏        | 4272/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.115.down_proj:  12%|█▏        | 4273/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.116.gate_proj:  12%|█▏        | 4274/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.116.up_proj:  12%|█▏        | 4275/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.116.down_proj:  12%|█▏        | 4276/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.117.gate_proj:  12%|█▏        | 4277/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.117.up_proj:  12%|█▏        | 4278/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.117.down_proj:  12%|█▏        | 4279/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.118.gate_proj:  12%|█▏        | 4280/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.118.up_proj:  12%|█▏        | 4281/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.118.down_proj:  12%|█▏        | 4282/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.119.gate_proj:  12%|█▏        | 4283/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.119.up_proj:  12%|█▏        | 4284/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.119.down_proj:  12%|█▏        | 4285/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.120.gate_proj:  12%|█▏        | 4286/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.120.up_proj:  12%|█▏        | 4287/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.120.down_proj:  12%|█▏        | 4288/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.121.gate_proj:  12%|█▏        | 4289/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.121.up_proj:  12%|█▏        | 4290/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.121.down_proj:  12%|█▏        | 4291/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.122.gate_proj:  12%|█▏        | 4292/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.122.up_proj:  12%|█▏        | 4293/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.122.down_proj:  12%|█▏        | 4294/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.123.gate_proj:  12%|█▏        | 4295/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.123.up_proj:  12%|█▏        | 4296/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.123.down_proj:  12%|█▏        | 4297/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.124.gate_proj:  12%|█▏        | 4298/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.124.up_proj:  12%|█▏        | 4299/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.124.down_proj:  12%|█▏        | 4300/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.125.gate_proj:  12%|█▏        | 4301/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.125.up_proj:  12%|█▏        | 4302/36566 [00:04<00:27, 1161.45it/s]  
packing model.layers.9.mlp.experts.125.down_proj:  12%|█▏        | 4303/36566 [00:04<00:27, 1161.45it/s]
packing model.layers.9.mlp.experts.125.down_proj:  12%|█▏        | 4304/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.9.mlp.experts.126.gate_proj:  12%|█▏        | 4304/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.9.mlp.experts.126.up_proj:  12%|█▏        | 4305/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.9.mlp.experts.126.down_proj:  12%|█▏        | 4306/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.9.mlp.experts.127.gate_proj:  12%|█▏        | 4307/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.9.mlp.experts.127.up_proj:  12%|█▏        | 4308/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.9.mlp.experts.127.down_proj:  12%|█▏        | 4309/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.0.gate_proj:  12%|█▏        | 4310/36566 [00:04<00:27, 1157.61it/s] 
packing model.layers.10.mlp.experts.0.up_proj:  12%|█▏        | 4311/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.0.down_proj:  12%|█▏        | 4312/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.1.gate_proj:  12%|█▏        | 4313/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.1.up_proj:  12%|█▏        | 4314/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.1.down_proj:  12%|█▏        | 4315/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.2.gate_proj:  12%|█▏        | 4316/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.2.up_proj:  12%|█▏        | 4317/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.2.down_proj:  12%|█▏        | 4318/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.3.gate_proj:  12%|█▏        | 4319/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.3.up_proj:  12%|█▏        | 4320/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.3.down_proj:  12%|█▏        | 4321/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.4.gate_proj:  12%|█▏        | 4322/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.4.up_proj:  12%|█▏        | 4323/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.4.down_proj:  12%|█▏        | 4324/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.5.gate_proj:  12%|█▏        | 4325/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.5.up_proj:  12%|█▏        | 4326/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.5.down_proj:  12%|█▏        | 4327/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.6.gate_proj:  12%|█▏        | 4328/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.6.up_proj:  12%|█▏        | 4329/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.6.down_proj:  12%|█▏        | 4330/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.7.gate_proj:  12%|█▏        | 4331/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.7.up_proj:  12%|█▏        | 4332/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.7.down_proj:  12%|█▏        | 4333/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.8.gate_proj:  12%|█▏        | 4334/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.8.up_proj:  12%|█▏        | 4335/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.8.down_proj:  12%|█▏        | 4336/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.9.gate_proj:  12%|█▏        | 4337/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.9.up_proj:  12%|█▏        | 4338/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.9.down_proj:  12%|█▏        | 4339/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.10.gate_proj:  12%|█▏        | 4340/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.10.up_proj:  12%|█▏        | 4341/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.10.down_proj:  12%|█▏        | 4342/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.11.gate_proj:  12%|█▏        | 4343/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.11.up_proj:  12%|█▏        | 4344/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.11.down_proj:  12%|█▏        | 4345/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.12.gate_proj:  12%|█▏        | 4346/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.12.up_proj:  12%|█▏        | 4347/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.12.down_proj:  12%|█▏        | 4348/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.13.gate_proj:  12%|█▏        | 4349/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.13.up_proj:  12%|█▏        | 4350/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.13.down_proj:  12%|█▏        | 4351/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.14.gate_proj:  12%|█▏        | 4352/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.14.up_proj:  12%|█▏        | 4353/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.14.down_proj:  12%|█▏        | 4354/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.15.gate_proj:  12%|█▏        | 4355/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.15.up_proj:  12%|█▏        | 4356/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.15.down_proj:  12%|█▏        | 4357/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.16.gate_proj:  12%|█▏        | 4358/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.16.up_proj:  12%|█▏        | 4359/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.16.down_proj:  12%|█▏        | 4360/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.17.gate_proj:  12%|█▏        | 4361/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.17.up_proj:  12%|█▏        | 4362/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.17.down_proj:  12%|█▏        | 4363/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.18.gate_proj:  12%|█▏        | 4364/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.18.up_proj:  12%|█▏        | 4365/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.18.down_proj:  12%|█▏        | 4366/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.19.gate_proj:  12%|█▏        | 4367/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.19.up_proj:  12%|█▏        | 4368/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.19.down_proj:  12%|█▏        | 4369/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.20.gate_proj:  12%|█▏        | 4370/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.20.up_proj:  12%|█▏        | 4371/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.20.down_proj:  12%|█▏        | 4372/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.21.gate_proj:  12%|█▏        | 4373/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.21.up_proj:  12%|█▏        | 4374/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.21.down_proj:  12%|█▏        | 4375/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.22.gate_proj:  12%|█▏        | 4376/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.22.up_proj:  12%|█▏        | 4377/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.22.down_proj:  12%|█▏        | 4378/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.23.gate_proj:  12%|█▏        | 4379/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.23.up_proj:  12%|█▏        | 4380/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.23.down_proj:  12%|█▏        | 4381/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.24.gate_proj:  12%|█▏        | 4382/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.24.up_proj:  12%|█▏        | 4383/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.24.down_proj:  12%|█▏        | 4384/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.25.gate_proj:  12%|█▏        | 4385/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.25.up_proj:  12%|█▏        | 4386/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.25.down_proj:  12%|█▏        | 4387/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.26.gate_proj:  12%|█▏        | 4388/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.26.up_proj:  12%|█▏        | 4389/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.26.down_proj:  12%|█▏        | 4390/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.27.gate_proj:  12%|█▏        | 4391/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.27.up_proj:  12%|█▏        | 4392/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.27.down_proj:  12%|█▏        | 4393/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.28.gate_proj:  12%|█▏        | 4394/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.28.up_proj:  12%|█▏        | 4395/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.28.down_proj:  12%|█▏        | 4396/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.29.gate_proj:  12%|█▏        | 4397/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.29.up_proj:  12%|█▏        | 4398/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.29.down_proj:  12%|█▏        | 4399/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.30.gate_proj:  12%|█▏        | 4400/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.30.up_proj:  12%|█▏        | 4401/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.30.down_proj:  12%|█▏        | 4402/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.31.gate_proj:  12%|█▏        | 4403/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.31.up_proj:  12%|█▏        | 4404/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.31.down_proj:  12%|█▏        | 4405/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.32.gate_proj:  12%|█▏        | 4406/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.32.up_proj:  12%|█▏        | 4407/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.32.down_proj:  12%|█▏        | 4408/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.33.gate_proj:  12%|█▏        | 4409/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.33.up_proj:  12%|█▏        | 4410/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.33.down_proj:  12%|█▏        | 4411/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.34.gate_proj:  12%|█▏        | 4412/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.34.up_proj:  12%|█▏        | 4413/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.34.down_proj:  12%|█▏        | 4414/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.35.gate_proj:  12%|█▏        | 4415/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.35.up_proj:  12%|█▏        | 4416/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.35.down_proj:  12%|█▏        | 4417/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.36.gate_proj:  12%|█▏        | 4418/36566 [00:04<00:27, 1157.61it/s]
packing model.layers.10.mlp.experts.36.up_proj:  12%|█▏        | 4419/36566 [00:04<00:27, 1157.61it/s]  
packing model.layers.10.mlp.experts.36.up_proj:  12%|█▏        | 4420/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.36.down_proj:  12%|█▏        | 4420/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.37.gate_proj:  12%|█▏        | 4421/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.37.up_proj:  12%|█▏        | 4422/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.37.down_proj:  12%|█▏        | 4423/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.38.gate_proj:  12%|█▏        | 4424/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.38.up_proj:  12%|█▏        | 4425/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.38.down_proj:  12%|█▏        | 4426/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.39.gate_proj:  12%|█▏        | 4427/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.39.up_proj:  12%|█▏        | 4428/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.39.down_proj:  12%|█▏        | 4429/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.40.gate_proj:  12%|█▏        | 4430/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.40.up_proj:  12%|█▏        | 4431/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.40.down_proj:  12%|█▏        | 4432/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.41.gate_proj:  12%|█▏        | 4433/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.41.up_proj:  12%|█▏        | 4434/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.41.down_proj:  12%|█▏        | 4435/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.42.gate_proj:  12%|█▏        | 4436/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.42.up_proj:  12%|█▏        | 4437/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.42.down_proj:  12%|█▏        | 4438/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.43.gate_proj:  12%|█▏        | 4439/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.43.up_proj:  12%|█▏        | 4440/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.43.down_proj:  12%|█▏        | 4441/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.44.gate_proj:  12%|█▏        | 4442/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.44.up_proj:  12%|█▏        | 4443/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.44.down_proj:  12%|█▏        | 4444/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.45.gate_proj:  12%|█▏        | 4445/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.45.up_proj:  12%|█▏        | 4446/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.45.down_proj:  12%|█▏        | 4447/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.46.gate_proj:  12%|█▏        | 4448/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.46.up_proj:  12%|█▏        | 4449/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.46.down_proj:  12%|█▏        | 4450/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.47.gate_proj:  12%|█▏        | 4451/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.47.up_proj:  12%|█▏        | 4452/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.47.down_proj:  12%|█▏        | 4453/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.48.gate_proj:  12%|█▏        | 4454/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.48.up_proj:  12%|█▏        | 4455/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.48.down_proj:  12%|█▏        | 4456/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.49.gate_proj:  12%|█▏        | 4457/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.49.up_proj:  12%|█▏        | 4458/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.49.down_proj:  12%|█▏        | 4459/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.50.gate_proj:  12%|█▏        | 4460/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.50.up_proj:  12%|█▏        | 4461/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.50.down_proj:  12%|█▏        | 4462/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.51.gate_proj:  12%|█▏        | 4463/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.51.up_proj:  12%|█▏        | 4464/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.51.down_proj:  12%|█▏        | 4465/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.52.gate_proj:  12%|█▏        | 4466/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.52.up_proj:  12%|█▏        | 4467/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.52.down_proj:  12%|█▏        | 4468/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.53.gate_proj:  12%|█▏        | 4469/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.53.up_proj:  12%|█▏        | 4470/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.53.down_proj:  12%|█▏        | 4471/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.54.gate_proj:  12%|█▏        | 4472/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.54.up_proj:  12%|█▏        | 4473/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.54.down_proj:  12%|█▏        | 4474/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.55.gate_proj:  12%|█▏        | 4475/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.55.up_proj:  12%|█▏        | 4476/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.55.down_proj:  12%|█▏        | 4477/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.56.gate_proj:  12%|█▏        | 4478/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.56.up_proj:  12%|█▏        | 4479/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.56.down_proj:  12%|█▏        | 4480/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.57.gate_proj:  12%|█▏        | 4481/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.57.up_proj:  12%|█▏        | 4482/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.57.down_proj:  12%|█▏        | 4483/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.58.gate_proj:  12%|█▏        | 4484/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.58.up_proj:  12%|█▏        | 4485/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.58.down_proj:  12%|█▏        | 4486/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.59.gate_proj:  12%|█▏        | 4487/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.59.up_proj:  12%|█▏        | 4488/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.59.down_proj:  12%|█▏        | 4489/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.60.gate_proj:  12%|█▏        | 4490/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.60.up_proj:  12%|█▏        | 4491/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.60.down_proj:  12%|█▏        | 4492/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.61.gate_proj:  12%|█▏        | 4493/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.61.up_proj:  12%|█▏        | 4494/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.61.down_proj:  12%|█▏        | 4495/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.62.gate_proj:  12%|█▏        | 4496/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.62.up_proj:  12%|█▏        | 4497/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.62.down_proj:  12%|█▏        | 4498/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.63.gate_proj:  12%|█▏        | 4499/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.63.up_proj:  12%|█▏        | 4500/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.63.down_proj:  12%|█▏        | 4501/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.64.gate_proj:  12%|█▏        | 4502/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.64.up_proj:  12%|█▏        | 4503/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.64.down_proj:  12%|█▏        | 4504/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.65.gate_proj:  12%|█▏        | 4505/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.65.up_proj:  12%|█▏        | 4506/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.65.down_proj:  12%|█▏        | 4507/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.66.gate_proj:  12%|█▏        | 4508/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.66.up_proj:  12%|█▏        | 4509/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.66.down_proj:  12%|█▏        | 4510/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.67.gate_proj:  12%|█▏        | 4511/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.67.up_proj:  12%|█▏        | 4512/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.67.down_proj:  12%|█▏        | 4513/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.68.gate_proj:  12%|█▏        | 4514/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.68.up_proj:  12%|█▏        | 4515/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.68.down_proj:  12%|█▏        | 4516/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.69.gate_proj:  12%|█▏        | 4517/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.69.up_proj:  12%|█▏        | 4518/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.69.down_proj:  12%|█▏        | 4519/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.70.gate_proj:  12%|█▏        | 4520/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.70.up_proj:  12%|█▏        | 4521/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.70.down_proj:  12%|█▏        | 4522/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.71.gate_proj:  12%|█▏        | 4523/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.71.up_proj:  12%|█▏        | 4524/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.71.down_proj:  12%|█▏        | 4525/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.72.gate_proj:  12%|█▏        | 4526/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.72.up_proj:  12%|█▏        | 4527/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.72.down_proj:  12%|█▏        | 4528/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.73.gate_proj:  12%|█▏        | 4529/36566 [00:04<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.73.up_proj:  12%|█▏        | 4530/36566 [00:04<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.73.down_proj:  12%|█▏        | 4531/36566 [00:05<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.74.gate_proj:  12%|█▏        | 4532/36566 [00:05<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.74.up_proj:  12%|█▏        | 4533/36566 [00:05<00:27, 1157.17it/s]  
packing model.layers.10.mlp.experts.74.down_proj:  12%|█▏        | 4534/36566 [00:05<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.75.gate_proj:  12%|█▏        | 4535/36566 [00:05<00:27, 1157.17it/s]
packing model.layers.10.mlp.experts.75.gate_proj:  12%|█▏        | 4536/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.75.up_proj:  12%|█▏        | 4536/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.75.down_proj:  12%|█▏        | 4537/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.76.gate_proj:  12%|█▏        | 4538/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.76.up_proj:  12%|█▏        | 4539/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.76.down_proj:  12%|█▏        | 4540/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.77.gate_proj:  12%|█▏        | 4541/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.77.up_proj:  12%|█▏        | 4542/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.77.down_proj:  12%|█▏        | 4543/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.78.gate_proj:  12%|█▏        | 4544/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.78.up_proj:  12%|█▏        | 4545/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.78.down_proj:  12%|█▏        | 4546/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.79.gate_proj:  12%|█▏        | 4547/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.79.up_proj:  12%|█▏        | 4548/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.79.down_proj:  12%|█▏        | 4549/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.80.gate_proj:  12%|█▏        | 4550/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.80.up_proj:  12%|█▏        | 4551/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.80.down_proj:  12%|█▏        | 4552/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.81.gate_proj:  12%|█▏        | 4553/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.81.up_proj:  12%|█▏        | 4554/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.81.down_proj:  12%|█▏        | 4555/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.82.gate_proj:  12%|█▏        | 4556/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.82.up_proj:  12%|█▏        | 4557/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.82.down_proj:  12%|█▏        | 4558/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.83.gate_proj:  12%|█▏        | 4559/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.83.up_proj:  12%|█▏        | 4560/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.83.down_proj:  12%|█▏        | 4561/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.84.gate_proj:  12%|█▏        | 4562/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.84.up_proj:  12%|█▏        | 4563/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.84.down_proj:  12%|█▏        | 4564/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.85.gate_proj:  12%|█▏        | 4565/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.85.up_proj:  12%|█▏        | 4566/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.85.down_proj:  12%|█▏        | 4567/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.86.gate_proj:  12%|█▏        | 4568/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.86.up_proj:  12%|█▏        | 4569/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.86.down_proj:  12%|█▏        | 4570/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.87.gate_proj:  13%|█▎        | 4571/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.87.up_proj:  13%|█▎        | 4572/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.87.down_proj:  13%|█▎        | 4573/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.88.gate_proj:  13%|█▎        | 4574/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.88.up_proj:  13%|█▎        | 4575/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.88.down_proj:  13%|█▎        | 4576/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.89.gate_proj:  13%|█▎        | 4577/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.89.up_proj:  13%|█▎        | 4578/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.89.down_proj:  13%|█▎        | 4579/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.90.gate_proj:  13%|█▎        | 4580/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.90.up_proj:  13%|█▎        | 4581/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.90.down_proj:  13%|█▎        | 4582/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.91.gate_proj:  13%|█▎        | 4583/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.91.up_proj:  13%|█▎        | 4584/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.91.down_proj:  13%|█▎        | 4585/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.92.gate_proj:  13%|█▎        | 4586/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.92.up_proj:  13%|█▎        | 4587/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.92.down_proj:  13%|█▎        | 4588/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.93.gate_proj:  13%|█▎        | 4589/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.93.up_proj:  13%|█▎        | 4590/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.93.down_proj:  13%|█▎        | 4591/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.94.gate_proj:  13%|█▎        | 4592/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.94.up_proj:  13%|█▎        | 4593/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.94.down_proj:  13%|█▎        | 4594/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.95.gate_proj:  13%|█▎        | 4595/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.95.up_proj:  13%|█▎        | 4596/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.95.down_proj:  13%|█▎        | 4597/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.96.gate_proj:  13%|█▎        | 4598/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.96.up_proj:  13%|█▎        | 4599/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.96.down_proj:  13%|█▎        | 4600/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.97.gate_proj:  13%|█▎        | 4601/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.97.up_proj:  13%|█▎        | 4602/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.97.down_proj:  13%|█▎        | 4603/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.98.gate_proj:  13%|█▎        | 4604/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.98.up_proj:  13%|█▎        | 4605/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.98.down_proj:  13%|█▎        | 4606/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.99.gate_proj:  13%|█▎        | 4607/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.99.up_proj:  13%|█▎        | 4608/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.99.down_proj:  13%|█▎        | 4609/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.100.gate_proj:  13%|█▎        | 4610/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.100.up_proj:  13%|█▎        | 4611/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.100.down_proj:  13%|█▎        | 4612/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.101.gate_proj:  13%|█▎        | 4613/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.101.up_proj:  13%|█▎        | 4614/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.101.down_proj:  13%|█▎        | 4615/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.102.gate_proj:  13%|█▎        | 4616/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.102.up_proj:  13%|█▎        | 4617/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.102.down_proj:  13%|█▎        | 4618/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.103.gate_proj:  13%|█▎        | 4619/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.103.up_proj:  13%|█▎        | 4620/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.103.down_proj:  13%|█▎        | 4621/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.104.gate_proj:  13%|█▎        | 4622/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.104.up_proj:  13%|█▎        | 4623/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.104.down_proj:  13%|█▎        | 4624/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.105.gate_proj:  13%|█▎        | 4625/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.105.up_proj:  13%|█▎        | 4626/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.105.down_proj:  13%|█▎        | 4627/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.106.gate_proj:  13%|█▎        | 4628/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.106.up_proj:  13%|█▎        | 4629/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.106.down_proj:  13%|█▎        | 4630/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.107.gate_proj:  13%|█▎        | 4631/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.107.up_proj:  13%|█▎        | 4632/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.107.down_proj:  13%|█▎        | 4633/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.108.gate_proj:  13%|█▎        | 4634/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.108.up_proj:  13%|█▎        | 4635/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.108.down_proj:  13%|█▎        | 4636/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.109.gate_proj:  13%|█▎        | 4637/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.109.up_proj:  13%|█▎        | 4638/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.109.down_proj:  13%|█▎        | 4639/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.110.gate_proj:  13%|█▎        | 4640/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.110.up_proj:  13%|█▎        | 4641/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.110.down_proj:  13%|█▎        | 4642/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.111.gate_proj:  13%|█▎        | 4643/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.111.up_proj:  13%|█▎        | 4644/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.111.down_proj:  13%|█▎        | 4645/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.112.gate_proj:  13%|█▎        | 4646/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.112.up_proj:  13%|█▎        | 4647/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.112.down_proj:  13%|█▎        | 4648/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.113.gate_proj:  13%|█▎        | 4649/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.113.up_proj:  13%|█▎        | 4650/36566 [00:05<00:27, 1156.49it/s]  
packing model.layers.10.mlp.experts.113.down_proj:  13%|█▎        | 4651/36566 [00:05<00:27, 1156.49it/s]
packing model.layers.10.mlp.experts.113.down_proj:  13%|█▎        | 4652/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.114.gate_proj:  13%|█▎        | 4652/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.114.up_proj:  13%|█▎        | 4653/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.114.down_proj:  13%|█▎        | 4654/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.115.gate_proj:  13%|█▎        | 4655/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.115.up_proj:  13%|█▎        | 4656/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.115.down_proj:  13%|█▎        | 4657/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.116.gate_proj:  13%|█▎        | 4658/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.116.up_proj:  13%|█▎        | 4659/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.116.down_proj:  13%|█▎        | 4660/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.117.gate_proj:  13%|█▎        | 4661/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.117.up_proj:  13%|█▎        | 4662/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.117.down_proj:  13%|█▎        | 4663/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.118.gate_proj:  13%|█▎        | 4664/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.118.up_proj:  13%|█▎        | 4665/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.118.down_proj:  13%|█▎        | 4666/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.119.gate_proj:  13%|█▎        | 4667/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.119.up_proj:  13%|█▎        | 4668/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.119.down_proj:  13%|█▎        | 4669/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.120.gate_proj:  13%|█▎        | 4670/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.120.up_proj:  13%|█▎        | 4671/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.120.down_proj:  13%|█▎        | 4672/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.121.gate_proj:  13%|█▎        | 4673/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.121.up_proj:  13%|█▎        | 4674/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.121.down_proj:  13%|█▎        | 4675/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.122.gate_proj:  13%|█▎        | 4676/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.122.up_proj:  13%|█▎        | 4677/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.122.down_proj:  13%|█▎        | 4678/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.123.gate_proj:  13%|█▎        | 4679/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.123.up_proj:  13%|█▎        | 4680/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.123.down_proj:  13%|█▎        | 4681/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.124.gate_proj:  13%|█▎        | 4682/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.124.up_proj:  13%|█▎        | 4683/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.124.down_proj:  13%|█▎        | 4684/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.125.gate_proj:  13%|█▎        | 4685/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.125.up_proj:  13%|█▎        | 4686/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.125.down_proj:  13%|█▎        | 4687/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.126.gate_proj:  13%|█▎        | 4688/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.126.up_proj:  13%|█▎        | 4689/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.126.down_proj:  13%|█▎        | 4690/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.127.gate_proj:  13%|█▎        | 4691/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.10.mlp.experts.127.up_proj:  13%|█▎        | 4692/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.10.mlp.experts.127.down_proj:  13%|█▎        | 4693/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.0.gate_proj:  13%|█▎        | 4694/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.0.up_proj:  13%|█▎        | 4695/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.0.down_proj:  13%|█▎        | 4696/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.1.gate_proj:  13%|█▎        | 4697/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.1.up_proj:  13%|█▎        | 4698/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.1.down_proj:  13%|█▎        | 4699/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.2.gate_proj:  13%|█▎        | 4700/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.2.up_proj:  13%|█▎        | 4701/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.2.down_proj:  13%|█▎        | 4702/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.3.gate_proj:  13%|█▎        | 4703/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.3.up_proj:  13%|█▎        | 4704/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.3.down_proj:  13%|█▎        | 4705/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.4.gate_proj:  13%|█▎        | 4706/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.4.up_proj:  13%|█▎        | 4707/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.4.down_proj:  13%|█▎        | 4708/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.5.gate_proj:  13%|█▎        | 4709/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.5.up_proj:  13%|█▎        | 4710/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.5.down_proj:  13%|█▎        | 4711/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.6.gate_proj:  13%|█▎        | 4712/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.6.up_proj:  13%|█▎        | 4713/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.6.down_proj:  13%|█▎        | 4714/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.7.gate_proj:  13%|█▎        | 4715/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.7.up_proj:  13%|█▎        | 4716/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.7.down_proj:  13%|█▎        | 4717/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.8.gate_proj:  13%|█▎        | 4718/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.8.up_proj:  13%|█▎        | 4719/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.8.down_proj:  13%|█▎        | 4720/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.9.gate_proj:  13%|█▎        | 4721/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.9.up_proj:  13%|█▎        | 4722/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.9.down_proj:  13%|█▎        | 4723/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.10.gate_proj:  13%|█▎        | 4724/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.10.up_proj:  13%|█▎        | 4725/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.10.down_proj:  13%|█▎        | 4726/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.11.gate_proj:  13%|█▎        | 4727/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.11.up_proj:  13%|█▎        | 4728/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.11.down_proj:  13%|█▎        | 4729/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.12.gate_proj:  13%|█▎        | 4730/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.12.up_proj:  13%|█▎        | 4731/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.12.down_proj:  13%|█▎        | 4732/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.13.gate_proj:  13%|█▎        | 4733/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.13.up_proj:  13%|█▎        | 4734/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.13.down_proj:  13%|█▎        | 4735/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.14.gate_proj:  13%|█▎        | 4736/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.14.up_proj:  13%|█▎        | 4737/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.14.down_proj:  13%|█▎        | 4738/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.15.gate_proj:  13%|█▎        | 4739/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.15.up_proj:  13%|█▎        | 4740/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.15.down_proj:  13%|█▎        | 4741/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.16.gate_proj:  13%|█▎        | 4742/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.16.up_proj:  13%|█▎        | 4743/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.16.down_proj:  13%|█▎        | 4744/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.17.gate_proj:  13%|█▎        | 4745/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.17.up_proj:  13%|█▎        | 4746/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.17.down_proj:  13%|█▎        | 4747/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.18.gate_proj:  13%|█▎        | 4748/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.18.up_proj:  13%|█▎        | 4749/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.18.down_proj:  13%|█▎        | 4750/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.19.gate_proj:  13%|█▎        | 4751/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.19.up_proj:  13%|█▎        | 4752/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.19.down_proj:  13%|█▎        | 4753/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.20.gate_proj:  13%|█▎        | 4754/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.20.up_proj:  13%|█▎        | 4755/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.20.down_proj:  13%|█▎        | 4756/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.21.gate_proj:  13%|█▎        | 4757/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.21.up_proj:  13%|█▎        | 4758/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.21.down_proj:  13%|█▎        | 4759/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.22.gate_proj:  13%|█▎        | 4760/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.22.up_proj:  13%|█▎        | 4761/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.22.down_proj:  13%|█▎        | 4762/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.23.gate_proj:  13%|█▎        | 4763/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.23.up_proj:  13%|█▎        | 4764/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.23.down_proj:  13%|█▎        | 4765/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.24.gate_proj:  13%|█▎        | 4766/36566 [00:05<00:27, 1156.62it/s]
packing model.layers.11.mlp.experts.24.up_proj:  13%|█▎        | 4767/36566 [00:05<00:27, 1156.62it/s]  
packing model.layers.11.mlp.experts.24.up_proj:  13%|█▎        | 4768/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.24.down_proj:  13%|█▎        | 4768/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.25.gate_proj:  13%|█▎        | 4769/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.25.up_proj:  13%|█▎        | 4770/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.25.down_proj:  13%|█▎        | 4771/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.26.gate_proj:  13%|█▎        | 4772/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.26.up_proj:  13%|█▎        | 4773/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.26.down_proj:  13%|█▎        | 4774/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.27.gate_proj:  13%|█▎        | 4775/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.27.up_proj:  13%|█▎        | 4776/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.27.down_proj:  13%|█▎        | 4777/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.28.gate_proj:  13%|█▎        | 4778/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.28.up_proj:  13%|█▎        | 4779/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.28.down_proj:  13%|█▎        | 4780/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.29.gate_proj:  13%|█▎        | 4781/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.29.up_proj:  13%|█▎        | 4782/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.29.down_proj:  13%|█▎        | 4783/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.30.gate_proj:  13%|█▎        | 4784/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.30.up_proj:  13%|█▎        | 4785/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.30.down_proj:  13%|█▎        | 4786/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.31.gate_proj:  13%|█▎        | 4787/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.31.up_proj:  13%|█▎        | 4788/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.31.down_proj:  13%|█▎        | 4789/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.32.gate_proj:  13%|█▎        | 4790/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.32.up_proj:  13%|█▎        | 4791/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.32.down_proj:  13%|█▎        | 4792/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.33.gate_proj:  13%|█▎        | 4793/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.33.up_proj:  13%|█▎        | 4794/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.33.down_proj:  13%|█▎        | 4795/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.34.gate_proj:  13%|█▎        | 4796/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.34.up_proj:  13%|█▎        | 4797/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.34.down_proj:  13%|█▎        | 4798/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.35.gate_proj:  13%|█▎        | 4799/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.35.up_proj:  13%|█▎        | 4800/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.35.down_proj:  13%|█▎        | 4801/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.36.gate_proj:  13%|█▎        | 4802/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.36.up_proj:  13%|█▎        | 4803/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.36.down_proj:  13%|█▎        | 4804/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.37.gate_proj:  13%|█▎        | 4805/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.37.up_proj:  13%|█▎        | 4806/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.37.down_proj:  13%|█▎        | 4807/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.38.gate_proj:  13%|█▎        | 4808/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.38.up_proj:  13%|█▎        | 4809/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.38.down_proj:  13%|█▎        | 4810/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.39.gate_proj:  13%|█▎        | 4811/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.39.up_proj:  13%|█▎        | 4812/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.39.down_proj:  13%|█▎        | 4813/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.40.gate_proj:  13%|█▎        | 4814/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.40.up_proj:  13%|█▎        | 4815/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.40.down_proj:  13%|█▎        | 4816/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.41.gate_proj:  13%|█▎        | 4817/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.41.up_proj:  13%|█▎        | 4818/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.41.down_proj:  13%|█▎        | 4819/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.42.gate_proj:  13%|█▎        | 4820/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.42.up_proj:  13%|█▎        | 4821/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.42.down_proj:  13%|█▎        | 4822/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.43.gate_proj:  13%|█▎        | 4823/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.43.up_proj:  13%|█▎        | 4824/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.43.down_proj:  13%|█▎        | 4825/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.44.gate_proj:  13%|█▎        | 4826/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.44.up_proj:  13%|█▎        | 4827/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.44.down_proj:  13%|█▎        | 4828/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.45.gate_proj:  13%|█▎        | 4829/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.45.up_proj:  13%|█▎        | 4830/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.45.down_proj:  13%|█▎        | 4831/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.46.gate_proj:  13%|█▎        | 4832/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.46.up_proj:  13%|█▎        | 4833/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.46.down_proj:  13%|█▎        | 4834/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.47.gate_proj:  13%|█▎        | 4835/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.47.up_proj:  13%|█▎        | 4836/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.47.down_proj:  13%|█▎        | 4837/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.48.gate_proj:  13%|█▎        | 4838/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.48.up_proj:  13%|█▎        | 4839/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.48.down_proj:  13%|█▎        | 4840/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.49.gate_proj:  13%|█▎        | 4841/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.49.up_proj:  13%|█▎        | 4842/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.49.down_proj:  13%|█▎        | 4843/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.50.gate_proj:  13%|█▎        | 4844/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.50.up_proj:  13%|█▎        | 4845/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.50.down_proj:  13%|█▎        | 4846/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.51.gate_proj:  13%|█▎        | 4847/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.51.up_proj:  13%|█▎        | 4848/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.51.down_proj:  13%|█▎        | 4849/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.52.gate_proj:  13%|█▎        | 4850/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.52.up_proj:  13%|█▎        | 4851/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.52.down_proj:  13%|█▎        | 4852/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.53.gate_proj:  13%|█▎        | 4853/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.53.up_proj:  13%|█▎        | 4854/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.53.down_proj:  13%|█▎        | 4855/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.54.gate_proj:  13%|█▎        | 4856/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.54.up_proj:  13%|█▎        | 4857/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.54.down_proj:  13%|█▎        | 4858/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.55.gate_proj:  13%|█▎        | 4859/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.55.up_proj:  13%|█▎        | 4860/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.55.down_proj:  13%|█▎        | 4861/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.56.gate_proj:  13%|█▎        | 4862/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.56.up_proj:  13%|█▎        | 4863/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.56.down_proj:  13%|█▎        | 4864/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.57.gate_proj:  13%|█▎        | 4865/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.57.up_proj:  13%|█▎        | 4866/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.57.down_proj:  13%|█▎        | 4867/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.58.gate_proj:  13%|█▎        | 4868/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.58.up_proj:  13%|█▎        | 4869/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.58.down_proj:  13%|█▎        | 4870/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.59.gate_proj:  13%|█▎        | 4871/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.59.up_proj:  13%|█▎        | 4872/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.59.down_proj:  13%|█▎        | 4873/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.60.gate_proj:  13%|█▎        | 4874/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.60.up_proj:  13%|█▎        | 4875/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.60.down_proj:  13%|█▎        | 4876/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.61.gate_proj:  13%|█▎        | 4877/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.61.up_proj:  13%|█▎        | 4878/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.61.down_proj:  13%|█▎        | 4879/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.62.gate_proj:  13%|█▎        | 4880/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.62.up_proj:  13%|█▎        | 4881/36566 [00:05<00:27, 1155.79it/s]  
packing model.layers.11.mlp.experts.62.down_proj:  13%|█▎        | 4882/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.63.gate_proj:  13%|█▎        | 4883/36566 [00:05<00:27, 1155.79it/s]
packing model.layers.11.mlp.experts.63.gate_proj:  13%|█▎        | 4884/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.63.up_proj:  13%|█▎        | 4884/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.63.down_proj:  13%|█▎        | 4885/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.64.gate_proj:  13%|█▎        | 4886/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.64.up_proj:  13%|█▎        | 4887/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.64.down_proj:  13%|█▎        | 4888/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.65.gate_proj:  13%|█▎        | 4889/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.65.up_proj:  13%|█▎        | 4890/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.65.down_proj:  13%|█▎        | 4891/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.66.gate_proj:  13%|█▎        | 4892/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.66.up_proj:  13%|█▎        | 4893/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.66.down_proj:  13%|█▎        | 4894/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.67.gate_proj:  13%|█▎        | 4895/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.67.up_proj:  13%|█▎        | 4896/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.67.down_proj:  13%|█▎        | 4897/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.68.gate_proj:  13%|█▎        | 4898/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.68.up_proj:  13%|█▎        | 4899/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.68.down_proj:  13%|█▎        | 4900/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.69.gate_proj:  13%|█▎        | 4901/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.69.up_proj:  13%|█▎        | 4902/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.69.down_proj:  13%|█▎        | 4903/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.70.gate_proj:  13%|█▎        | 4904/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.70.up_proj:  13%|█▎        | 4905/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.70.down_proj:  13%|█▎        | 4906/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.71.gate_proj:  13%|█▎        | 4907/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.71.up_proj:  13%|█▎        | 4908/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.71.down_proj:  13%|█▎        | 4909/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.72.gate_proj:  13%|█▎        | 4910/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.72.up_proj:  13%|█▎        | 4911/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.72.down_proj:  13%|█▎        | 4912/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.73.gate_proj:  13%|█▎        | 4913/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.73.up_proj:  13%|█▎        | 4914/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.73.down_proj:  13%|█▎        | 4915/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.74.gate_proj:  13%|█▎        | 4916/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.74.up_proj:  13%|█▎        | 4917/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.74.down_proj:  13%|█▎        | 4918/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.75.gate_proj:  13%|█▎        | 4919/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.75.up_proj:  13%|█▎        | 4920/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.75.down_proj:  13%|█▎        | 4921/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.76.gate_proj:  13%|█▎        | 4922/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.76.up_proj:  13%|█▎        | 4923/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.76.down_proj:  13%|█▎        | 4924/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.77.gate_proj:  13%|█▎        | 4925/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.77.up_proj:  13%|█▎        | 4926/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.77.down_proj:  13%|█▎        | 4927/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.78.gate_proj:  13%|█▎        | 4928/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.78.up_proj:  13%|█▎        | 4929/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.78.down_proj:  13%|█▎        | 4930/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.79.gate_proj:  13%|█▎        | 4931/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.79.up_proj:  13%|█▎        | 4932/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.79.down_proj:  13%|█▎        | 4933/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.80.gate_proj:  13%|█▎        | 4934/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.80.up_proj:  13%|█▎        | 4935/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.80.down_proj:  13%|█▎        | 4936/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.81.gate_proj:  14%|█▎        | 4937/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.81.up_proj:  14%|█▎        | 4938/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.81.down_proj:  14%|█▎        | 4939/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.82.gate_proj:  14%|█▎        | 4940/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.82.up_proj:  14%|█▎        | 4941/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.82.down_proj:  14%|█▎        | 4942/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.83.gate_proj:  14%|█▎        | 4943/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.83.up_proj:  14%|█▎        | 4944/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.83.down_proj:  14%|█▎        | 4945/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.84.gate_proj:  14%|█▎        | 4946/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.84.up_proj:  14%|█▎        | 4947/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.84.down_proj:  14%|█▎        | 4948/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.85.gate_proj:  14%|█▎        | 4949/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.85.up_proj:  14%|█▎        | 4950/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.85.down_proj:  14%|█▎        | 4951/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.86.gate_proj:  14%|█▎        | 4952/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.86.up_proj:  14%|█▎        | 4953/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.86.down_proj:  14%|█▎        | 4954/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.87.gate_proj:  14%|█▎        | 4955/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.87.up_proj:  14%|█▎        | 4956/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.87.down_proj:  14%|█▎        | 4957/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.88.gate_proj:  14%|█▎        | 4958/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.88.up_proj:  14%|█▎        | 4959/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.88.down_proj:  14%|█▎        | 4960/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.89.gate_proj:  14%|█▎        | 4961/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.89.up_proj:  14%|█▎        | 4962/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.89.down_proj:  14%|█▎        | 4963/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.90.gate_proj:  14%|█▎        | 4964/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.90.up_proj:  14%|█▎        | 4965/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.90.down_proj:  14%|█▎        | 4966/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.91.gate_proj:  14%|█▎        | 4967/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.91.up_proj:  14%|█▎        | 4968/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.91.down_proj:  14%|█▎        | 4969/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.92.gate_proj:  14%|█▎        | 4970/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.92.up_proj:  14%|█▎        | 4971/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.92.down_proj:  14%|█▎        | 4972/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.93.gate_proj:  14%|█▎        | 4973/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.93.up_proj:  14%|█▎        | 4974/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.93.down_proj:  14%|█▎        | 4975/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.94.gate_proj:  14%|█▎        | 4976/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.94.up_proj:  14%|█▎        | 4977/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.94.down_proj:  14%|█▎        | 4978/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.95.gate_proj:  14%|█▎        | 4979/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.95.up_proj:  14%|█▎        | 4980/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.95.down_proj:  14%|█▎        | 4981/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.96.gate_proj:  14%|█▎        | 4982/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.96.up_proj:  14%|█▎        | 4983/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.96.down_proj:  14%|█▎        | 4984/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.97.gate_proj:  14%|█▎        | 4985/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.97.up_proj:  14%|█▎        | 4986/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.97.down_proj:  14%|█▎        | 4987/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.98.gate_proj:  14%|█▎        | 4988/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.98.up_proj:  14%|█▎        | 4989/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.98.down_proj:  14%|█▎        | 4990/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.99.gate_proj:  14%|█▎        | 4991/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.99.up_proj:  14%|█▎        | 4992/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.99.down_proj:  14%|█▎        | 4993/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.100.gate_proj:  14%|█▎        | 4994/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.100.up_proj:  14%|█▎        | 4995/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.100.down_proj:  14%|█▎        | 4996/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.101.gate_proj:  14%|█▎        | 4997/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.101.up_proj:  14%|█▎        | 4998/36566 [00:05<00:27, 1154.49it/s]  
packing model.layers.11.mlp.experts.101.down_proj:  14%|█▎        | 4999/36566 [00:05<00:27, 1154.49it/s]
packing model.layers.11.mlp.experts.101.down_proj:  14%|█▎        | 5000/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.102.gate_proj:  14%|█▎        | 5000/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.102.up_proj:  14%|█▎        | 5001/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.102.down_proj:  14%|█▎        | 5002/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.103.gate_proj:  14%|█▎        | 5003/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.103.up_proj:  14%|█▎        | 5004/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.103.down_proj:  14%|█▎        | 5005/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.104.gate_proj:  14%|█▎        | 5006/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.104.up_proj:  14%|█▎        | 5007/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.104.down_proj:  14%|█▎        | 5008/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.105.gate_proj:  14%|█▎        | 5009/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.105.up_proj:  14%|█▎        | 5010/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.105.down_proj:  14%|█▎        | 5011/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.106.gate_proj:  14%|█▎        | 5012/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.106.up_proj:  14%|█▎        | 5013/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.106.down_proj:  14%|█▎        | 5014/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.107.gate_proj:  14%|█▎        | 5015/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.107.up_proj:  14%|█▎        | 5016/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.107.down_proj:  14%|█▎        | 5017/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.108.gate_proj:  14%|█▎        | 5018/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.108.up_proj:  14%|█▎        | 5019/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.108.down_proj:  14%|█▎        | 5020/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.109.gate_proj:  14%|█▎        | 5021/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.109.up_proj:  14%|█▎        | 5022/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.109.down_proj:  14%|█▎        | 5023/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.110.gate_proj:  14%|█▎        | 5024/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.110.up_proj:  14%|█▎        | 5025/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.110.down_proj:  14%|█▎        | 5026/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.111.gate_proj:  14%|█▎        | 5027/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.111.up_proj:  14%|█▍        | 5028/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.111.down_proj:  14%|█▍        | 5029/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.112.gate_proj:  14%|█▍        | 5030/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.112.up_proj:  14%|█▍        | 5031/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.112.down_proj:  14%|█▍        | 5032/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.113.gate_proj:  14%|█▍        | 5033/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.113.up_proj:  14%|█▍        | 5034/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.113.down_proj:  14%|█▍        | 5035/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.114.gate_proj:  14%|█▍        | 5036/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.114.up_proj:  14%|█▍        | 5037/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.114.down_proj:  14%|█▍        | 5038/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.115.gate_proj:  14%|█▍        | 5039/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.115.up_proj:  14%|█▍        | 5040/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.115.down_proj:  14%|█▍        | 5041/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.116.gate_proj:  14%|█▍        | 5042/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.116.up_proj:  14%|█▍        | 5043/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.116.down_proj:  14%|█▍        | 5044/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.117.gate_proj:  14%|█▍        | 5045/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.117.up_proj:  14%|█▍        | 5046/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.117.down_proj:  14%|█▍        | 5047/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.118.gate_proj:  14%|█▍        | 5048/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.118.up_proj:  14%|█▍        | 5049/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.118.down_proj:  14%|█▍        | 5050/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.119.gate_proj:  14%|█▍        | 5051/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.119.up_proj:  14%|█▍        | 5052/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.119.down_proj:  14%|█▍        | 5053/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.120.gate_proj:  14%|█▍        | 5054/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.120.up_proj:  14%|█▍        | 5055/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.120.down_proj:  14%|█▍        | 5056/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.121.gate_proj:  14%|█▍        | 5057/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.121.up_proj:  14%|█▍        | 5058/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.121.down_proj:  14%|█▍        | 5059/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.122.gate_proj:  14%|█▍        | 5060/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.122.up_proj:  14%|█▍        | 5061/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.122.down_proj:  14%|█▍        | 5062/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.123.gate_proj:  14%|█▍        | 5063/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.123.up_proj:  14%|█▍        | 5064/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.123.down_proj:  14%|█▍        | 5065/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.124.gate_proj:  14%|█▍        | 5066/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.124.up_proj:  14%|█▍        | 5067/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.124.down_proj:  14%|█▍        | 5068/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.125.gate_proj:  14%|█▍        | 5069/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.125.up_proj:  14%|█▍        | 5070/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.125.down_proj:  14%|█▍        | 5071/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.126.gate_proj:  14%|█▍        | 5072/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.126.up_proj:  14%|█▍        | 5073/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.126.down_proj:  14%|█▍        | 5074/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.127.gate_proj:  14%|█▍        | 5075/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.11.mlp.experts.127.up_proj:  14%|█▍        | 5076/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.11.mlp.experts.127.down_proj:  14%|█▍        | 5077/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.0.gate_proj:  14%|█▍        | 5078/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.0.up_proj:  14%|█▍        | 5079/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.0.down_proj:  14%|█▍        | 5080/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.1.gate_proj:  14%|█▍        | 5081/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.1.up_proj:  14%|█▍        | 5082/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.1.down_proj:  14%|█▍        | 5083/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.2.gate_proj:  14%|█▍        | 5084/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.2.up_proj:  14%|█▍        | 5085/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.2.down_proj:  14%|█▍        | 5086/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.3.gate_proj:  14%|█▍        | 5087/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.3.up_proj:  14%|█▍        | 5088/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.3.down_proj:  14%|█▍        | 5089/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.4.gate_proj:  14%|█▍        | 5090/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.4.up_proj:  14%|█▍        | 5091/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.4.down_proj:  14%|█▍        | 5092/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.5.gate_proj:  14%|█▍        | 5093/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.5.up_proj:  14%|█▍        | 5094/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.5.down_proj:  14%|█▍        | 5095/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.6.gate_proj:  14%|█▍        | 5096/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.6.up_proj:  14%|█▍        | 5097/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.6.down_proj:  14%|█▍        | 5098/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.7.gate_proj:  14%|█▍        | 5099/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.7.up_proj:  14%|█▍        | 5100/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.7.down_proj:  14%|█▍        | 5101/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.8.gate_proj:  14%|█▍        | 5102/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.8.up_proj:  14%|█▍        | 5103/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.8.down_proj:  14%|█▍        | 5104/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.9.gate_proj:  14%|█▍        | 5105/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.9.up_proj:  14%|█▍        | 5106/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.9.down_proj:  14%|█▍        | 5107/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.10.gate_proj:  14%|█▍        | 5108/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.10.up_proj:  14%|█▍        | 5109/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.10.down_proj:  14%|█▍        | 5110/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.11.gate_proj:  14%|█▍        | 5111/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.11.up_proj:  14%|█▍        | 5112/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.11.down_proj:  14%|█▍        | 5113/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.12.gate_proj:  14%|█▍        | 5114/36566 [00:05<00:27, 1154.54it/s]
packing model.layers.12.mlp.experts.12.up_proj:  14%|█▍        | 5115/36566 [00:05<00:27, 1154.54it/s]  
packing model.layers.12.mlp.experts.12.up_proj:  14%|█▍        | 5116/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.12.down_proj:  14%|█▍        | 5116/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.13.gate_proj:  14%|█▍        | 5117/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.13.up_proj:  14%|█▍        | 5118/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.13.down_proj:  14%|█▍        | 5119/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.14.gate_proj:  14%|█▍        | 5120/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.14.up_proj:  14%|█▍        | 5121/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.14.down_proj:  14%|█▍        | 5122/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.15.gate_proj:  14%|█▍        | 5123/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.15.up_proj:  14%|█▍        | 5124/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.15.down_proj:  14%|█▍        | 5125/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.16.gate_proj:  14%|█▍        | 5126/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.16.up_proj:  14%|█▍        | 5127/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.16.down_proj:  14%|█▍        | 5128/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.17.gate_proj:  14%|█▍        | 5129/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.17.up_proj:  14%|█▍        | 5130/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.17.down_proj:  14%|█▍        | 5131/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.18.gate_proj:  14%|█▍        | 5132/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.18.up_proj:  14%|█▍        | 5133/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.18.down_proj:  14%|█▍        | 5134/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.19.gate_proj:  14%|█▍        | 5135/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.19.up_proj:  14%|█▍        | 5136/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.19.down_proj:  14%|█▍        | 5137/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.20.gate_proj:  14%|█▍        | 5138/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.20.up_proj:  14%|█▍        | 5139/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.20.down_proj:  14%|█▍        | 5140/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.21.gate_proj:  14%|█▍        | 5141/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.21.up_proj:  14%|█▍        | 5142/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.21.down_proj:  14%|█▍        | 5143/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.22.gate_proj:  14%|█▍        | 5144/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.22.up_proj:  14%|█▍        | 5145/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.22.down_proj:  14%|█▍        | 5146/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.23.gate_proj:  14%|█▍        | 5147/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.23.up_proj:  14%|█▍        | 5148/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.23.down_proj:  14%|█▍        | 5149/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.24.gate_proj:  14%|█▍        | 5150/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.24.up_proj:  14%|█▍        | 5151/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.24.down_proj:  14%|█▍        | 5152/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.25.gate_proj:  14%|█▍        | 5153/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.25.up_proj:  14%|█▍        | 5154/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.25.down_proj:  14%|█▍        | 5155/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.26.gate_proj:  14%|█▍        | 5156/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.26.up_proj:  14%|█▍        | 5157/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.26.down_proj:  14%|█▍        | 5158/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.27.gate_proj:  14%|█▍        | 5159/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.27.up_proj:  14%|█▍        | 5160/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.27.down_proj:  14%|█▍        | 5161/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.28.gate_proj:  14%|█▍        | 5162/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.28.up_proj:  14%|█▍        | 5163/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.28.down_proj:  14%|█▍        | 5164/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.29.gate_proj:  14%|█▍        | 5165/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.29.up_proj:  14%|█▍        | 5166/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.29.down_proj:  14%|█▍        | 5167/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.30.gate_proj:  14%|█▍        | 5168/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.30.up_proj:  14%|█▍        | 5169/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.30.down_proj:  14%|█▍        | 5170/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.31.gate_proj:  14%|█▍        | 5171/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.31.up_proj:  14%|█▍        | 5172/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.31.down_proj:  14%|█▍        | 5173/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.32.gate_proj:  14%|█▍        | 5174/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.32.up_proj:  14%|█▍        | 5175/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.32.down_proj:  14%|█▍        | 5176/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.33.gate_proj:  14%|█▍        | 5177/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.33.up_proj:  14%|█▍        | 5178/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.33.down_proj:  14%|█▍        | 5179/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.34.gate_proj:  14%|█▍        | 5180/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.34.up_proj:  14%|█▍        | 5181/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.34.down_proj:  14%|█▍        | 5182/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.35.gate_proj:  14%|█▍        | 5183/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.35.up_proj:  14%|█▍        | 5184/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.35.down_proj:  14%|█▍        | 5185/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.36.gate_proj:  14%|█▍        | 5186/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.36.up_proj:  14%|█▍        | 5187/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.36.down_proj:  14%|█▍        | 5188/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.37.gate_proj:  14%|█▍        | 5189/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.37.up_proj:  14%|█▍        | 5190/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.37.down_proj:  14%|█▍        | 5191/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.38.gate_proj:  14%|█▍        | 5192/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.38.up_proj:  14%|█▍        | 5193/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.38.down_proj:  14%|█▍        | 5194/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.39.gate_proj:  14%|█▍        | 5195/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.39.up_proj:  14%|█▍        | 5196/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.39.down_proj:  14%|█▍        | 5197/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.40.gate_proj:  14%|█▍        | 5198/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.40.up_proj:  14%|█▍        | 5199/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.40.down_proj:  14%|█▍        | 5200/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.41.gate_proj:  14%|█▍        | 5201/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.41.up_proj:  14%|█▍        | 5202/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.41.down_proj:  14%|█▍        | 5203/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.42.gate_proj:  14%|█▍        | 5204/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.42.up_proj:  14%|█▍        | 5205/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.42.down_proj:  14%|█▍        | 5206/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.43.gate_proj:  14%|█▍        | 5207/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.43.up_proj:  14%|█▍        | 5208/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.43.down_proj:  14%|█▍        | 5209/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.44.gate_proj:  14%|█▍        | 5210/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.44.up_proj:  14%|█▍        | 5211/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.44.down_proj:  14%|█▍        | 5212/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.45.gate_proj:  14%|█▍        | 5213/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.45.up_proj:  14%|█▍        | 5214/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.45.down_proj:  14%|█▍        | 5215/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.46.gate_proj:  14%|█▍        | 5216/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.46.up_proj:  14%|█▍        | 5217/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.46.down_proj:  14%|█▍        | 5218/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.47.gate_proj:  14%|█▍        | 5219/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.47.up_proj:  14%|█▍        | 5220/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.47.down_proj:  14%|█▍        | 5221/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.48.gate_proj:  14%|█▍        | 5222/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.48.up_proj:  14%|█▍        | 5223/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.48.down_proj:  14%|█▍        | 5224/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.49.gate_proj:  14%|█▍        | 5225/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.49.up_proj:  14%|█▍        | 5226/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.49.down_proj:  14%|█▍        | 5227/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.50.gate_proj:  14%|█▍        | 5228/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.50.up_proj:  14%|█▍        | 5229/36566 [00:05<00:27, 1155.62it/s]  
packing model.layers.12.mlp.experts.50.down_proj:  14%|█▍        | 5230/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.51.gate_proj:  14%|█▍        | 5231/36566 [00:05<00:27, 1155.62it/s]
packing model.layers.12.mlp.experts.51.gate_proj:  14%|█▍        | 5232/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.51.up_proj:  14%|█▍        | 5232/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.51.down_proj:  14%|█▍        | 5233/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.52.gate_proj:  14%|█▍        | 5234/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.52.up_proj:  14%|█▍        | 5235/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.52.down_proj:  14%|█▍        | 5236/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.53.gate_proj:  14%|█▍        | 5237/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.53.up_proj:  14%|█▍        | 5238/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.53.down_proj:  14%|█▍        | 5239/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.54.gate_proj:  14%|█▍        | 5240/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.54.up_proj:  14%|█▍        | 5241/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.54.down_proj:  14%|█▍        | 5242/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.55.gate_proj:  14%|█▍        | 5243/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.55.up_proj:  14%|█▍        | 5244/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.55.down_proj:  14%|█▍        | 5245/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.56.gate_proj:  14%|█▍        | 5246/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.56.up_proj:  14%|█▍        | 5247/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.56.down_proj:  14%|█▍        | 5248/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.57.gate_proj:  14%|█▍        | 5249/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.57.up_proj:  14%|█▍        | 5250/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.57.down_proj:  14%|█▍        | 5251/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.58.gate_proj:  14%|█▍        | 5252/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.58.up_proj:  14%|█▍        | 5253/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.58.down_proj:  14%|█▍        | 5254/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.59.gate_proj:  14%|█▍        | 5255/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.59.up_proj:  14%|█▍        | 5256/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.59.down_proj:  14%|█▍        | 5257/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.60.gate_proj:  14%|█▍        | 5258/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.60.up_proj:  14%|█▍        | 5259/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.60.down_proj:  14%|█▍        | 5260/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.61.gate_proj:  14%|█▍        | 5261/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.61.up_proj:  14%|█▍        | 5262/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.61.down_proj:  14%|█▍        | 5263/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.62.gate_proj:  14%|█▍        | 5264/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.62.up_proj:  14%|█▍        | 5265/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.62.down_proj:  14%|█▍        | 5266/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.63.gate_proj:  14%|█▍        | 5267/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.63.up_proj:  14%|█▍        | 5268/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.63.down_proj:  14%|█▍        | 5269/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.64.gate_proj:  14%|█▍        | 5270/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.64.up_proj:  14%|█▍        | 5271/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.64.down_proj:  14%|█▍        | 5272/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.65.gate_proj:  14%|█▍        | 5273/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.65.up_proj:  14%|█▍        | 5274/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.65.down_proj:  14%|█▍        | 5275/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.66.gate_proj:  14%|█▍        | 5276/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.66.up_proj:  14%|█▍        | 5277/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.66.down_proj:  14%|█▍        | 5278/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.67.gate_proj:  14%|█▍        | 5279/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.67.up_proj:  14%|█▍        | 5280/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.67.down_proj:  14%|█▍        | 5281/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.68.gate_proj:  14%|█▍        | 5282/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.68.up_proj:  14%|█▍        | 5283/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.68.down_proj:  14%|█▍        | 5284/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.69.gate_proj:  14%|█▍        | 5285/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.69.up_proj:  14%|█▍        | 5286/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.69.down_proj:  14%|█▍        | 5287/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.70.gate_proj:  14%|█▍        | 5288/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.70.up_proj:  14%|█▍        | 5289/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.70.down_proj:  14%|█▍        | 5290/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.71.gate_proj:  14%|█▍        | 5291/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.71.up_proj:  14%|█▍        | 5292/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.71.down_proj:  14%|█▍        | 5293/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.72.gate_proj:  14%|█▍        | 5294/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.72.up_proj:  14%|█▍        | 5295/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.72.down_proj:  14%|█▍        | 5296/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.73.gate_proj:  14%|█▍        | 5297/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.73.up_proj:  14%|█▍        | 5298/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.73.down_proj:  14%|█▍        | 5299/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.74.gate_proj:  14%|█▍        | 5300/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.74.up_proj:  14%|█▍        | 5301/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.74.down_proj:  14%|█▍        | 5302/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.75.gate_proj:  15%|█▍        | 5303/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.75.up_proj:  15%|█▍        | 5304/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.75.down_proj:  15%|█▍        | 5305/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.76.gate_proj:  15%|█▍        | 5306/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.76.up_proj:  15%|█▍        | 5307/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.76.down_proj:  15%|█▍        | 5308/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.77.gate_proj:  15%|█▍        | 5309/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.77.up_proj:  15%|█▍        | 5310/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.77.down_proj:  15%|█▍        | 5311/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.78.gate_proj:  15%|█▍        | 5312/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.78.up_proj:  15%|█▍        | 5313/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.78.down_proj:  15%|█▍        | 5314/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.79.gate_proj:  15%|█▍        | 5315/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.79.up_proj:  15%|█▍        | 5316/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.79.down_proj:  15%|█▍        | 5317/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.80.gate_proj:  15%|█▍        | 5318/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.80.up_proj:  15%|█▍        | 5319/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.80.down_proj:  15%|█▍        | 5320/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.81.gate_proj:  15%|█▍        | 5321/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.81.up_proj:  15%|█▍        | 5322/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.81.down_proj:  15%|█▍        | 5323/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.82.gate_proj:  15%|█▍        | 5324/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.82.up_proj:  15%|█▍        | 5325/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.82.down_proj:  15%|█▍        | 5326/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.83.gate_proj:  15%|█▍        | 5327/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.83.up_proj:  15%|█▍        | 5328/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.83.down_proj:  15%|█▍        | 5329/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.84.gate_proj:  15%|█▍        | 5330/36566 [00:05<00:27, 1156.84it/s]
packing model.layers.12.mlp.experts.84.up_proj:  15%|█▍        | 5331/36566 [00:05<00:27, 1156.84it/s]  
packing model.layers.12.mlp.experts.84.down_proj:  15%|█▍        | 5332/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.85.gate_proj:  15%|█▍        | 5333/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.85.up_proj:  15%|█▍        | 5334/36566 [00:05<00:26, 1156.84it/s]  
packing model.layers.12.mlp.experts.85.down_proj:  15%|█▍        | 5335/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.86.gate_proj:  15%|█▍        | 5336/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.86.up_proj:  15%|█▍        | 5337/36566 [00:05<00:26, 1156.84it/s]  
packing model.layers.12.mlp.experts.86.down_proj:  15%|█▍        | 5338/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.87.gate_proj:  15%|█▍        | 5339/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.87.up_proj:  15%|█▍        | 5340/36566 [00:05<00:26, 1156.84it/s]  
packing model.layers.12.mlp.experts.87.down_proj:  15%|█▍        | 5341/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.88.gate_proj:  15%|█▍        | 5342/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.88.up_proj:  15%|█▍        | 5343/36566 [00:05<00:26, 1156.84it/s]  
packing model.layers.12.mlp.experts.88.down_proj:  15%|█▍        | 5344/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.89.gate_proj:  15%|█▍        | 5345/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.89.up_proj:  15%|█▍        | 5346/36566 [00:05<00:26, 1156.84it/s]  
packing model.layers.12.mlp.experts.89.down_proj:  15%|█▍        | 5347/36566 [00:05<00:26, 1156.84it/s]
packing model.layers.12.mlp.experts.89.down_proj:  15%|█▍        | 5348/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.90.gate_proj:  15%|█▍        | 5348/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.90.up_proj:  15%|█▍        | 5349/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.90.down_proj:  15%|█▍        | 5350/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.91.gate_proj:  15%|█▍        | 5351/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.91.up_proj:  15%|█▍        | 5352/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.91.down_proj:  15%|█▍        | 5353/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.92.gate_proj:  15%|█▍        | 5354/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.92.up_proj:  15%|█▍        | 5355/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.92.down_proj:  15%|█▍        | 5356/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.93.gate_proj:  15%|█▍        | 5357/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.93.up_proj:  15%|█▍        | 5358/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.93.down_proj:  15%|█▍        | 5359/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.94.gate_proj:  15%|█▍        | 5360/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.94.up_proj:  15%|█▍        | 5361/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.94.down_proj:  15%|█▍        | 5362/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.95.gate_proj:  15%|█▍        | 5363/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.95.up_proj:  15%|█▍        | 5364/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.95.down_proj:  15%|█▍        | 5365/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.96.gate_proj:  15%|█▍        | 5366/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.96.up_proj:  15%|█▍        | 5367/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.96.down_proj:  15%|█▍        | 5368/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.97.gate_proj:  15%|█▍        | 5369/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.97.up_proj:  15%|█▍        | 5370/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.97.down_proj:  15%|█▍        | 5371/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.98.gate_proj:  15%|█▍        | 5372/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.98.up_proj:  15%|█▍        | 5373/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.98.down_proj:  15%|█▍        | 5374/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.99.gate_proj:  15%|█▍        | 5375/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.99.up_proj:  15%|█▍        | 5376/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.99.down_proj:  15%|█▍        | 5377/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.100.gate_proj:  15%|█▍        | 5378/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.100.up_proj:  15%|█▍        | 5379/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.100.down_proj:  15%|█▍        | 5380/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.101.gate_proj:  15%|█▍        | 5381/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.101.up_proj:  15%|█▍        | 5382/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.101.down_proj:  15%|█▍        | 5383/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.102.gate_proj:  15%|█▍        | 5384/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.102.up_proj:  15%|█▍        | 5385/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.102.down_proj:  15%|█▍        | 5386/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.103.gate_proj:  15%|█▍        | 5387/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.103.up_proj:  15%|█▍        | 5388/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.103.down_proj:  15%|█▍        | 5389/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.104.gate_proj:  15%|█▍        | 5390/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.104.up_proj:  15%|█▍        | 5391/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.104.down_proj:  15%|█▍        | 5392/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.105.gate_proj:  15%|█▍        | 5393/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.105.up_proj:  15%|█▍        | 5394/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.105.down_proj:  15%|█▍        | 5395/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.106.gate_proj:  15%|█▍        | 5396/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.106.up_proj:  15%|█▍        | 5397/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.106.down_proj:  15%|█▍        | 5398/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.107.gate_proj:  15%|█▍        | 5399/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.107.up_proj:  15%|█▍        | 5400/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.107.down_proj:  15%|█▍        | 5401/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.108.gate_proj:  15%|█▍        | 5402/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.108.up_proj:  15%|█▍        | 5403/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.108.down_proj:  15%|█▍        | 5404/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.109.gate_proj:  15%|█▍        | 5405/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.109.up_proj:  15%|█▍        | 5406/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.109.down_proj:  15%|█▍        | 5407/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.110.gate_proj:  15%|█▍        | 5408/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.110.up_proj:  15%|█▍        | 5409/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.110.down_proj:  15%|█▍        | 5410/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.111.gate_proj:  15%|█▍        | 5411/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.111.up_proj:  15%|█▍        | 5412/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.111.down_proj:  15%|█▍        | 5413/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.112.gate_proj:  15%|█▍        | 5414/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.112.up_proj:  15%|█▍        | 5415/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.112.down_proj:  15%|█▍        | 5416/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.113.gate_proj:  15%|█▍        | 5417/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.113.up_proj:  15%|█▍        | 5418/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.113.down_proj:  15%|█▍        | 5419/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.114.gate_proj:  15%|█▍        | 5420/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.114.up_proj:  15%|█▍        | 5421/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.114.down_proj:  15%|█▍        | 5422/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.115.gate_proj:  15%|█▍        | 5423/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.115.up_proj:  15%|█▍        | 5424/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.115.down_proj:  15%|█▍        | 5425/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.116.gate_proj:  15%|█▍        | 5426/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.116.up_proj:  15%|█▍        | 5427/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.116.down_proj:  15%|█▍        | 5428/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.117.gate_proj:  15%|█▍        | 5429/36566 [00:05<00:27, 1153.18it/s]
packing model.layers.12.mlp.experts.117.up_proj:  15%|█▍        | 5430/36566 [00:05<00:27, 1153.18it/s]  
packing model.layers.12.mlp.experts.117.down_proj:  15%|█▍        | 5431/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.118.gate_proj:  15%|█▍        | 5432/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.118.up_proj:  15%|█▍        | 5433/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.118.down_proj:  15%|█▍        | 5434/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.119.gate_proj:  15%|█▍        | 5435/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.119.up_proj:  15%|█▍        | 5436/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.119.down_proj:  15%|█▍        | 5437/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.120.gate_proj:  15%|█▍        | 5438/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.120.up_proj:  15%|█▍        | 5439/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.120.down_proj:  15%|█▍        | 5440/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.121.gate_proj:  15%|█▍        | 5441/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.121.up_proj:  15%|█▍        | 5442/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.121.down_proj:  15%|█▍        | 5443/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.122.gate_proj:  15%|█▍        | 5444/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.122.up_proj:  15%|█▍        | 5445/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.122.down_proj:  15%|█▍        | 5446/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.123.gate_proj:  15%|█▍        | 5447/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.123.up_proj:  15%|█▍        | 5448/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.123.down_proj:  15%|█▍        | 5449/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.124.gate_proj:  15%|█▍        | 5450/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.124.up_proj:  15%|█▍        | 5451/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.124.down_proj:  15%|█▍        | 5452/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.125.gate_proj:  15%|█▍        | 5453/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.125.up_proj:  15%|█▍        | 5454/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.125.down_proj:  15%|█▍        | 5455/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.126.gate_proj:  15%|█▍        | 5456/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.126.up_proj:  15%|█▍        | 5457/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.126.down_proj:  15%|█▍        | 5458/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.127.gate_proj:  15%|█▍        | 5459/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.12.mlp.experts.127.up_proj:  15%|█▍        | 5460/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.12.mlp.experts.127.down_proj:  15%|█▍        | 5461/36566 [00:05<00:26, 1153.18it/s]
packing model.layers.13.mlp.experts.0.gate_proj:  15%|█▍        | 5462/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.13.mlp.experts.0.up_proj:  15%|█▍        | 5463/36566 [00:05<00:26, 1153.18it/s]  
packing model.layers.13.mlp.experts.0.up_proj:  15%|█▍        | 5464/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.0.down_proj:  15%|█▍        | 5464/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.1.gate_proj:  15%|█▍        | 5465/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.1.up_proj:  15%|█▍        | 5466/36566 [00:05<00:27, 1151.70it/s]  
packing model.layers.13.mlp.experts.1.down_proj:  15%|█▍        | 5467/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.2.gate_proj:  15%|█▍        | 5468/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.2.up_proj:  15%|█▍        | 5469/36566 [00:05<00:27, 1151.70it/s]  
packing model.layers.13.mlp.experts.2.down_proj:  15%|█▍        | 5470/36566 [00:05<00:27, 1151.70it/s]
packing model.layers.13.mlp.experts.3.gate_proj:  15%|█▍        | 5471/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.3.up_proj:  15%|█▍        | 5472/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.3.down_proj:  15%|█▍        | 5473/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.4.gate_proj:  15%|█▍        | 5474/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.4.up_proj:  15%|█▍        | 5475/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.4.down_proj:  15%|█▍        | 5476/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.5.gate_proj:  15%|█▍        | 5477/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.5.up_proj:  15%|█▍        | 5478/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.5.down_proj:  15%|█▍        | 5479/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.6.gate_proj:  15%|█▍        | 5480/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.6.up_proj:  15%|█▍        | 5481/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.6.down_proj:  15%|█▍        | 5482/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.7.gate_proj:  15%|█▍        | 5483/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.7.up_proj:  15%|█▍        | 5484/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.7.down_proj:  15%|█▌        | 5485/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.8.gate_proj:  15%|█▌        | 5486/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.8.up_proj:  15%|█▌        | 5487/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.8.down_proj:  15%|█▌        | 5488/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.9.gate_proj:  15%|█▌        | 5489/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.9.up_proj:  15%|█▌        | 5490/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.9.down_proj:  15%|█▌        | 5491/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.10.gate_proj:  15%|█▌        | 5492/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.10.up_proj:  15%|█▌        | 5493/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.10.down_proj:  15%|█▌        | 5494/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.11.gate_proj:  15%|█▌        | 5495/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.11.up_proj:  15%|█▌        | 5496/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.11.down_proj:  15%|█▌        | 5497/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.12.gate_proj:  15%|█▌        | 5498/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.12.up_proj:  15%|█▌        | 5499/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.12.down_proj:  15%|█▌        | 5500/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.13.gate_proj:  15%|█▌        | 5501/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.13.up_proj:  15%|█▌        | 5502/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.13.down_proj:  15%|█▌        | 5503/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.14.gate_proj:  15%|█▌        | 5504/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.14.up_proj:  15%|█▌        | 5505/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.14.down_proj:  15%|█▌        | 5506/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.15.gate_proj:  15%|█▌        | 5507/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.15.up_proj:  15%|█▌        | 5508/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.15.down_proj:  15%|█▌        | 5509/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.16.gate_proj:  15%|█▌        | 5510/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.16.up_proj:  15%|█▌        | 5511/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.16.down_proj:  15%|█▌        | 5512/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.17.gate_proj:  15%|█▌        | 5513/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.17.up_proj:  15%|█▌        | 5514/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.17.down_proj:  15%|█▌        | 5515/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.18.gate_proj:  15%|█▌        | 5516/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.18.up_proj:  15%|█▌        | 5517/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.18.down_proj:  15%|█▌        | 5518/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.19.gate_proj:  15%|█▌        | 5519/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.19.up_proj:  15%|█▌        | 5520/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.19.down_proj:  15%|█▌        | 5521/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.20.gate_proj:  15%|█▌        | 5522/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.20.up_proj:  15%|█▌        | 5523/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.20.down_proj:  15%|█▌        | 5524/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.21.gate_proj:  15%|█▌        | 5525/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.21.up_proj:  15%|█▌        | 5526/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.21.down_proj:  15%|█▌        | 5527/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.22.gate_proj:  15%|█▌        | 5528/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.22.up_proj:  15%|█▌        | 5529/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.22.down_proj:  15%|█▌        | 5530/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.23.gate_proj:  15%|█▌        | 5531/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.23.up_proj:  15%|█▌        | 5532/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.23.down_proj:  15%|█▌        | 5533/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.24.gate_proj:  15%|█▌        | 5534/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.24.up_proj:  15%|█▌        | 5535/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.24.down_proj:  15%|█▌        | 5536/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.25.gate_proj:  15%|█▌        | 5537/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.25.up_proj:  15%|█▌        | 5538/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.25.down_proj:  15%|█▌        | 5539/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.26.gate_proj:  15%|█▌        | 5540/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.26.up_proj:  15%|█▌        | 5541/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.26.down_proj:  15%|█▌        | 5542/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.27.gate_proj:  15%|█▌        | 5543/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.27.up_proj:  15%|█▌        | 5544/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.27.down_proj:  15%|█▌        | 5545/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.28.gate_proj:  15%|█▌        | 5546/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.28.up_proj:  15%|█▌        | 5547/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.28.down_proj:  15%|█▌        | 5548/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.29.gate_proj:  15%|█▌        | 5549/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.29.up_proj:  15%|█▌        | 5550/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.29.down_proj:  15%|█▌        | 5551/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.30.gate_proj:  15%|█▌        | 5552/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.30.up_proj:  15%|█▌        | 5553/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.30.down_proj:  15%|█▌        | 5554/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.31.gate_proj:  15%|█▌        | 5555/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.31.up_proj:  15%|█▌        | 5556/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.31.down_proj:  15%|█▌        | 5557/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.32.gate_proj:  15%|█▌        | 5558/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.32.up_proj:  15%|█▌        | 5559/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.32.down_proj:  15%|█▌        | 5560/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.33.gate_proj:  15%|█▌        | 5561/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.33.up_proj:  15%|█▌        | 5562/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.33.down_proj:  15%|█▌        | 5563/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.34.gate_proj:  15%|█▌        | 5564/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.34.up_proj:  15%|█▌        | 5565/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.34.down_proj:  15%|█▌        | 5566/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.35.gate_proj:  15%|█▌        | 5567/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.35.up_proj:  15%|█▌        | 5568/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.35.down_proj:  15%|█▌        | 5569/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.36.gate_proj:  15%|█▌        | 5570/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.36.up_proj:  15%|█▌        | 5571/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.36.down_proj:  15%|█▌        | 5572/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.37.gate_proj:  15%|█▌        | 5573/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.37.up_proj:  15%|█▌        | 5574/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.37.down_proj:  15%|█▌        | 5575/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.38.gate_proj:  15%|█▌        | 5576/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.38.up_proj:  15%|█▌        | 5577/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.38.down_proj:  15%|█▌        | 5578/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.39.gate_proj:  15%|█▌        | 5579/36566 [00:05<00:26, 1151.70it/s]
packing model.layers.13.mlp.experts.39.up_proj:  15%|█▌        | 5580/36566 [00:05<00:26, 1151.70it/s]  
packing model.layers.13.mlp.experts.39.up_proj:  15%|█▌        | 5581/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.39.down_proj:  15%|█▌        | 5581/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.40.gate_proj:  15%|█▌        | 5582/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.40.up_proj:  15%|█▌        | 5583/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.40.down_proj:  15%|█▌        | 5584/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.41.gate_proj:  15%|█▌        | 5585/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.41.up_proj:  15%|█▌        | 5586/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.41.down_proj:  15%|█▌        | 5587/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.42.gate_proj:  15%|█▌        | 5588/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.42.up_proj:  15%|█▌        | 5589/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.42.down_proj:  15%|█▌        | 5590/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.43.gate_proj:  15%|█▌        | 5591/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.43.up_proj:  15%|█▌        | 5592/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.43.down_proj:  15%|█▌        | 5593/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.44.gate_proj:  15%|█▌        | 5594/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.44.up_proj:  15%|█▌        | 5595/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.44.down_proj:  15%|█▌        | 5596/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.45.gate_proj:  15%|█▌        | 5597/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.45.up_proj:  15%|█▌        | 5598/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.45.down_proj:  15%|█▌        | 5599/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.46.gate_proj:  15%|█▌        | 5600/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.46.up_proj:  15%|█▌        | 5601/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.46.down_proj:  15%|█▌        | 5602/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.47.gate_proj:  15%|█▌        | 5603/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.47.up_proj:  15%|█▌        | 5604/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.47.down_proj:  15%|█▌        | 5605/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.48.gate_proj:  15%|█▌        | 5606/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.48.up_proj:  15%|█▌        | 5607/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.48.down_proj:  15%|█▌        | 5608/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.49.gate_proj:  15%|█▌        | 5609/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.49.up_proj:  15%|█▌        | 5610/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.49.down_proj:  15%|█▌        | 5611/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.50.gate_proj:  15%|█▌        | 5612/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.50.up_proj:  15%|█▌        | 5613/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.50.down_proj:  15%|█▌        | 5614/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.51.gate_proj:  15%|█▌        | 5615/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.51.up_proj:  15%|█▌        | 5616/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.51.down_proj:  15%|█▌        | 5617/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.52.gate_proj:  15%|█▌        | 5618/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.52.up_proj:  15%|█▌        | 5619/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.52.down_proj:  15%|█▌        | 5620/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.53.gate_proj:  15%|█▌        | 5621/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.53.up_proj:  15%|█▌        | 5622/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.53.down_proj:  15%|█▌        | 5623/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.54.gate_proj:  15%|█▌        | 5624/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.54.up_proj:  15%|█▌        | 5625/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.54.down_proj:  15%|█▌        | 5626/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.55.gate_proj:  15%|█▌        | 5627/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.55.up_proj:  15%|█▌        | 5628/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.55.down_proj:  15%|█▌        | 5629/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.56.gate_proj:  15%|█▌        | 5630/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.56.up_proj:  15%|█▌        | 5631/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.56.down_proj:  15%|█▌        | 5632/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.57.gate_proj:  15%|█▌        | 5633/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.57.up_proj:  15%|█▌        | 5634/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.57.down_proj:  15%|█▌        | 5635/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.58.gate_proj:  15%|█▌        | 5636/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.58.up_proj:  15%|█▌        | 5637/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.58.down_proj:  15%|█▌        | 5638/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.59.gate_proj:  15%|█▌        | 5639/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.59.up_proj:  15%|█▌        | 5640/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.59.down_proj:  15%|█▌        | 5641/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.60.gate_proj:  15%|█▌        | 5642/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.60.up_proj:  15%|█▌        | 5643/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.60.down_proj:  15%|█▌        | 5644/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.61.gate_proj:  15%|█▌        | 5645/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.61.up_proj:  15%|█▌        | 5646/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.61.down_proj:  15%|█▌        | 5647/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.62.gate_proj:  15%|█▌        | 5648/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.62.up_proj:  15%|█▌        | 5649/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.62.down_proj:  15%|█▌        | 5650/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.63.gate_proj:  15%|█▌        | 5651/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.63.up_proj:  15%|█▌        | 5652/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.63.down_proj:  15%|█▌        | 5653/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.64.gate_proj:  15%|█▌        | 5654/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.64.up_proj:  15%|█▌        | 5655/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.64.down_proj:  15%|█▌        | 5656/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.65.gate_proj:  15%|█▌        | 5657/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.65.up_proj:  15%|█▌        | 5658/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.65.down_proj:  15%|█▌        | 5659/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.66.gate_proj:  15%|█▌        | 5660/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.66.up_proj:  15%|█▌        | 5661/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.66.down_proj:  15%|█▌        | 5662/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.67.gate_proj:  15%|█▌        | 5663/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.67.up_proj:  15%|█▌        | 5664/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.67.down_proj:  15%|█▌        | 5665/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.68.gate_proj:  15%|█▌        | 5666/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.68.up_proj:  15%|█▌        | 5667/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.68.down_proj:  16%|█▌        | 5668/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.69.gate_proj:  16%|█▌        | 5669/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.69.up_proj:  16%|█▌        | 5670/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.69.down_proj:  16%|█▌        | 5671/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.70.gate_proj:  16%|█▌        | 5672/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.70.up_proj:  16%|█▌        | 5673/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.70.down_proj:  16%|█▌        | 5674/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.71.gate_proj:  16%|█▌        | 5675/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.71.up_proj:  16%|█▌        | 5676/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.71.down_proj:  16%|█▌        | 5677/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.72.gate_proj:  16%|█▌        | 5678/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.72.up_proj:  16%|█▌        | 5679/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.72.down_proj:  16%|█▌        | 5680/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.73.gate_proj:  16%|█▌        | 5681/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.73.up_proj:  16%|█▌        | 5682/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.73.down_proj:  16%|█▌        | 5683/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.74.gate_proj:  16%|█▌        | 5684/36566 [00:05<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.74.up_proj:  16%|█▌        | 5685/36566 [00:05<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.74.down_proj:  16%|█▌        | 5686/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.75.gate_proj:  16%|█▌        | 5687/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.75.up_proj:  16%|█▌        | 5688/36566 [00:06<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.75.down_proj:  16%|█▌        | 5689/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.76.gate_proj:  16%|█▌        | 5690/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.76.up_proj:  16%|█▌        | 5691/36566 [00:06<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.76.down_proj:  16%|█▌        | 5692/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.77.gate_proj:  16%|█▌        | 5693/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.77.up_proj:  16%|█▌        | 5694/36566 [00:06<00:26, 1154.45it/s]  
packing model.layers.13.mlp.experts.77.down_proj:  16%|█▌        | 5695/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.78.gate_proj:  16%|█▌        | 5696/36566 [00:06<00:26, 1154.45it/s]
packing model.layers.13.mlp.experts.78.gate_proj:  16%|█▌        | 5697/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.78.up_proj:  16%|█▌        | 5697/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.78.down_proj:  16%|█▌        | 5698/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.79.gate_proj:  16%|█▌        | 5699/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.79.up_proj:  16%|█▌        | 5700/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.79.down_proj:  16%|█▌        | 5701/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.80.gate_proj:  16%|█▌        | 5702/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.80.up_proj:  16%|█▌        | 5703/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.80.down_proj:  16%|█▌        | 5704/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.81.gate_proj:  16%|█▌        | 5705/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.81.up_proj:  16%|█▌        | 5706/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.81.down_proj:  16%|█▌        | 5707/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.82.gate_proj:  16%|█▌        | 5708/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.82.up_proj:  16%|█▌        | 5709/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.82.down_proj:  16%|█▌        | 5710/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.83.gate_proj:  16%|█▌        | 5711/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.83.up_proj:  16%|█▌        | 5712/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.83.down_proj:  16%|█▌        | 5713/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.84.gate_proj:  16%|█▌        | 5714/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.84.up_proj:  16%|█▌        | 5715/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.84.down_proj:  16%|█▌        | 5716/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.85.gate_proj:  16%|█▌        | 5717/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.85.up_proj:  16%|█▌        | 5718/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.85.down_proj:  16%|█▌        | 5719/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.86.gate_proj:  16%|█▌        | 5720/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.86.up_proj:  16%|█▌        | 5721/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.86.down_proj:  16%|█▌        | 5722/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.87.gate_proj:  16%|█▌        | 5723/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.87.up_proj:  16%|█▌        | 5724/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.87.down_proj:  16%|█▌        | 5725/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.88.gate_proj:  16%|█▌        | 5726/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.88.up_proj:  16%|█▌        | 5727/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.88.down_proj:  16%|█▌        | 5728/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.89.gate_proj:  16%|█▌        | 5729/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.89.up_proj:  16%|█▌        | 5730/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.89.down_proj:  16%|█▌        | 5731/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.90.gate_proj:  16%|█▌        | 5732/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.90.up_proj:  16%|█▌        | 5733/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.90.down_proj:  16%|█▌        | 5734/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.91.gate_proj:  16%|█▌        | 5735/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.91.up_proj:  16%|█▌        | 5736/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.91.down_proj:  16%|█▌        | 5737/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.92.gate_proj:  16%|█▌        | 5738/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.92.up_proj:  16%|█▌        | 5739/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.92.down_proj:  16%|█▌        | 5740/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.93.gate_proj:  16%|█▌        | 5741/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.93.up_proj:  16%|█▌        | 5742/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.93.down_proj:  16%|█▌        | 5743/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.94.gate_proj:  16%|█▌        | 5744/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.94.up_proj:  16%|█▌        | 5745/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.94.down_proj:  16%|█▌        | 5746/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.95.gate_proj:  16%|█▌        | 5747/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.95.up_proj:  16%|█▌        | 5748/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.95.down_proj:  16%|█▌        | 5749/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.96.gate_proj:  16%|█▌        | 5750/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.96.up_proj:  16%|█▌        | 5751/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.96.down_proj:  16%|█▌        | 5752/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.97.gate_proj:  16%|█▌        | 5753/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.97.up_proj:  16%|█▌        | 5754/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.97.down_proj:  16%|█▌        | 5755/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.98.gate_proj:  16%|█▌        | 5756/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.98.up_proj:  16%|█▌        | 5757/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.98.down_proj:  16%|█▌        | 5758/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.99.gate_proj:  16%|█▌        | 5759/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.99.up_proj:  16%|█▌        | 5760/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.99.down_proj:  16%|█▌        | 5761/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.100.gate_proj:  16%|█▌        | 5762/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.100.up_proj:  16%|█▌        | 5763/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.100.down_proj:  16%|█▌        | 5764/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.101.gate_proj:  16%|█▌        | 5765/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.101.up_proj:  16%|█▌        | 5766/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.101.down_proj:  16%|█▌        | 5767/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.102.gate_proj:  16%|█▌        | 5768/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.102.up_proj:  16%|█▌        | 5769/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.102.down_proj:  16%|█▌        | 5770/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.103.gate_proj:  16%|█▌        | 5771/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.103.up_proj:  16%|█▌        | 5772/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.103.down_proj:  16%|█▌        | 5773/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.104.gate_proj:  16%|█▌        | 5774/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.104.up_proj:  16%|█▌        | 5775/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.104.down_proj:  16%|█▌        | 5776/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.105.gate_proj:  16%|█▌        | 5777/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.105.up_proj:  16%|█▌        | 5778/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.105.down_proj:  16%|█▌        | 5779/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.106.gate_proj:  16%|█▌        | 5780/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.106.up_proj:  16%|█▌        | 5781/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.106.down_proj:  16%|█▌        | 5782/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.107.gate_proj:  16%|█▌        | 5783/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.107.up_proj:  16%|█▌        | 5784/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.107.down_proj:  16%|█▌        | 5785/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.108.gate_proj:  16%|█▌        | 5786/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.108.up_proj:  16%|█▌        | 5787/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.108.down_proj:  16%|█▌        | 5788/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.109.gate_proj:  16%|█▌        | 5789/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.109.up_proj:  16%|█▌        | 5790/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.109.down_proj:  16%|█▌        | 5791/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.110.gate_proj:  16%|█▌        | 5792/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.110.up_proj:  16%|█▌        | 5793/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.110.down_proj:  16%|█▌        | 5794/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.111.gate_proj:  16%|█▌        | 5795/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.111.up_proj:  16%|█▌        | 5796/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.111.down_proj:  16%|█▌        | 5797/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.112.gate_proj:  16%|█▌        | 5798/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.112.up_proj:  16%|█▌        | 5799/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.112.down_proj:  16%|█▌        | 5800/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.113.gate_proj:  16%|█▌        | 5801/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.113.up_proj:  16%|█▌        | 5802/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.113.down_proj:  16%|█▌        | 5803/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.114.gate_proj:  16%|█▌        | 5804/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.114.up_proj:  16%|█▌        | 5805/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.114.down_proj:  16%|█▌        | 5806/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.115.gate_proj:  16%|█▌        | 5807/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.115.up_proj:  16%|█▌        | 5808/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.115.down_proj:  16%|█▌        | 5809/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.116.gate_proj:  16%|█▌        | 5810/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.116.up_proj:  16%|█▌        | 5811/36566 [00:06<00:26, 1155.08it/s]  
packing model.layers.13.mlp.experts.116.down_proj:  16%|█▌        | 5812/36566 [00:06<00:26, 1155.08it/s]
packing model.layers.13.mlp.experts.116.down_proj:  16%|█▌        | 5813/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.117.gate_proj:  16%|█▌        | 5813/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.117.up_proj:  16%|█▌        | 5814/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.117.down_proj:  16%|█▌        | 5815/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.118.gate_proj:  16%|█▌        | 5816/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.118.up_proj:  16%|█▌        | 5817/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.118.down_proj:  16%|█▌        | 5818/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.119.gate_proj:  16%|█▌        | 5819/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.119.up_proj:  16%|█▌        | 5820/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.119.down_proj:  16%|█▌        | 5821/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.120.gate_proj:  16%|█▌        | 5822/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.120.up_proj:  16%|█▌        | 5823/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.120.down_proj:  16%|█▌        | 5824/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.121.gate_proj:  16%|█▌        | 5825/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.121.up_proj:  16%|█▌        | 5826/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.121.down_proj:  16%|█▌        | 5827/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.122.gate_proj:  16%|█▌        | 5828/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.122.up_proj:  16%|█▌        | 5829/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.122.down_proj:  16%|█▌        | 5830/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.123.gate_proj:  16%|█▌        | 5831/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.123.up_proj:  16%|█▌        | 5832/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.123.down_proj:  16%|█▌        | 5833/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.124.gate_proj:  16%|█▌        | 5834/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.124.up_proj:  16%|█▌        | 5835/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.124.down_proj:  16%|█▌        | 5836/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.125.gate_proj:  16%|█▌        | 5837/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.125.up_proj:  16%|█▌        | 5838/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.125.down_proj:  16%|█▌        | 5839/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.126.gate_proj:  16%|█▌        | 5840/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.126.up_proj:  16%|█▌        | 5841/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.126.down_proj:  16%|█▌        | 5842/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.127.gate_proj:  16%|█▌        | 5843/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.13.mlp.experts.127.up_proj:  16%|█▌        | 5844/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.13.mlp.experts.127.down_proj:  16%|█▌        | 5845/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.0.gate_proj:  16%|█▌        | 5846/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.0.up_proj:  16%|█▌        | 5847/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.0.down_proj:  16%|█▌        | 5848/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.1.gate_proj:  16%|█▌        | 5849/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.1.up_proj:  16%|█▌        | 5850/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.1.down_proj:  16%|█▌        | 5851/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.2.gate_proj:  16%|█▌        | 5852/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.2.up_proj:  16%|█▌        | 5853/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.2.down_proj:  16%|█▌        | 5854/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.3.gate_proj:  16%|█▌        | 5855/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.3.up_proj:  16%|█▌        | 5856/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.3.down_proj:  16%|█▌        | 5857/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.4.gate_proj:  16%|█▌        | 5858/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.4.up_proj:  16%|█▌        | 5859/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.4.down_proj:  16%|█▌        | 5860/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.5.gate_proj:  16%|█▌        | 5861/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.5.up_proj:  16%|█▌        | 5862/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.5.down_proj:  16%|█▌        | 5863/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.6.gate_proj:  16%|█▌        | 5864/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.6.up_proj:  16%|█▌        | 5865/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.6.down_proj:  16%|█▌        | 5866/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.7.gate_proj:  16%|█▌        | 5867/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.7.up_proj:  16%|█▌        | 5868/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.7.down_proj:  16%|█▌        | 5869/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.8.gate_proj:  16%|█▌        | 5870/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.8.up_proj:  16%|█▌        | 5871/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.8.down_proj:  16%|█▌        | 5872/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.9.gate_proj:  16%|█▌        | 5873/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.9.up_proj:  16%|█▌        | 5874/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.9.down_proj:  16%|█▌        | 5875/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.10.gate_proj:  16%|█▌        | 5876/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.10.up_proj:  16%|█▌        | 5877/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.10.down_proj:  16%|█▌        | 5878/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.11.gate_proj:  16%|█▌        | 5879/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.11.up_proj:  16%|█▌        | 5880/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.11.down_proj:  16%|█▌        | 5881/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.12.gate_proj:  16%|█▌        | 5882/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.12.up_proj:  16%|█▌        | 5883/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.12.down_proj:  16%|█▌        | 5884/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.13.gate_proj:  16%|█▌        | 5885/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.13.up_proj:  16%|█▌        | 5886/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.13.down_proj:  16%|█▌        | 5887/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.14.gate_proj:  16%|█▌        | 5888/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.14.up_proj:  16%|█▌        | 5889/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.14.down_proj:  16%|█▌        | 5890/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.15.gate_proj:  16%|█▌        | 5891/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.15.up_proj:  16%|█▌        | 5892/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.15.down_proj:  16%|█▌        | 5893/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.16.gate_proj:  16%|█▌        | 5894/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.16.up_proj:  16%|█▌        | 5895/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.16.down_proj:  16%|█▌        | 5896/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.17.gate_proj:  16%|█▌        | 5897/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.17.up_proj:  16%|█▌        | 5898/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.17.down_proj:  16%|█▌        | 5899/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.18.gate_proj:  16%|█▌        | 5900/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.18.up_proj:  16%|█▌        | 5901/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.18.down_proj:  16%|█▌        | 5902/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.19.gate_proj:  16%|█▌        | 5903/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.19.up_proj:  16%|█▌        | 5904/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.19.down_proj:  16%|█▌        | 5905/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.20.gate_proj:  16%|█▌        | 5906/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.20.up_proj:  16%|█▌        | 5907/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.20.down_proj:  16%|█▌        | 5908/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.21.gate_proj:  16%|█▌        | 5909/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.21.up_proj:  16%|█▌        | 5910/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.21.down_proj:  16%|█▌        | 5911/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.22.gate_proj:  16%|█▌        | 5912/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.22.up_proj:  16%|█▌        | 5913/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.22.down_proj:  16%|█▌        | 5914/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.23.gate_proj:  16%|█▌        | 5915/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.23.up_proj:  16%|█▌        | 5916/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.23.down_proj:  16%|█▌        | 5917/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.24.gate_proj:  16%|█▌        | 5918/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.24.up_proj:  16%|█▌        | 5919/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.24.down_proj:  16%|█▌        | 5920/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.25.gate_proj:  16%|█▌        | 5921/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.25.up_proj:  16%|█▌        | 5922/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.25.down_proj:  16%|█▌        | 5923/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.26.gate_proj:  16%|█▌        | 5924/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.26.up_proj:  16%|█▌        | 5925/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.26.down_proj:  16%|█▌        | 5926/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.27.gate_proj:  16%|█▌        | 5927/36566 [00:06<00:26, 1155.51it/s]
packing model.layers.14.mlp.experts.27.up_proj:  16%|█▌        | 5928/36566 [00:06<00:26, 1155.51it/s]  
packing model.layers.14.mlp.experts.27.up_proj:  16%|█▌        | 5929/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.27.down_proj:  16%|█▌        | 5929/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.28.gate_proj:  16%|█▌        | 5930/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.28.up_proj:  16%|█▌        | 5931/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.28.down_proj:  16%|█▌        | 5932/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.29.gate_proj:  16%|█▌        | 5933/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.29.up_proj:  16%|█▌        | 5934/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.29.down_proj:  16%|█▌        | 5935/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.30.gate_proj:  16%|█▌        | 5936/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.30.up_proj:  16%|█▌        | 5937/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.30.down_proj:  16%|█▌        | 5938/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.31.gate_proj:  16%|█▌        | 5939/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.31.up_proj:  16%|█▌        | 5940/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.31.down_proj:  16%|█▌        | 5941/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.32.gate_proj:  16%|█▋        | 5942/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.32.up_proj:  16%|█▋        | 5943/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.32.down_proj:  16%|█▋        | 5944/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.33.gate_proj:  16%|█▋        | 5945/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.33.up_proj:  16%|█▋        | 5946/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.33.down_proj:  16%|█▋        | 5947/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.34.gate_proj:  16%|█▋        | 5948/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.34.up_proj:  16%|█▋        | 5949/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.34.down_proj:  16%|█▋        | 5950/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.35.gate_proj:  16%|█▋        | 5951/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.35.up_proj:  16%|█▋        | 5952/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.35.down_proj:  16%|█▋        | 5953/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.36.gate_proj:  16%|█▋        | 5954/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.36.up_proj:  16%|█▋        | 5955/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.36.down_proj:  16%|█▋        | 5956/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.37.gate_proj:  16%|█▋        | 5957/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.37.up_proj:  16%|█▋        | 5958/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.37.down_proj:  16%|█▋        | 5959/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.38.gate_proj:  16%|█▋        | 5960/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.38.up_proj:  16%|█▋        | 5961/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.38.down_proj:  16%|█▋        | 5962/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.39.gate_proj:  16%|█▋        | 5963/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.39.up_proj:  16%|█▋        | 5964/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.39.down_proj:  16%|█▋        | 5965/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.40.gate_proj:  16%|█▋        | 5966/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.40.up_proj:  16%|█▋        | 5967/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.40.down_proj:  16%|█▋        | 5968/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.41.gate_proj:  16%|█▋        | 5969/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.41.up_proj:  16%|█▋        | 5970/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.41.down_proj:  16%|█▋        | 5971/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.42.gate_proj:  16%|█▋        | 5972/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.42.up_proj:  16%|█▋        | 5973/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.42.down_proj:  16%|█▋        | 5974/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.43.gate_proj:  16%|█▋        | 5975/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.43.up_proj:  16%|█▋        | 5976/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.43.down_proj:  16%|█▋        | 5977/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.44.gate_proj:  16%|█▋        | 5978/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.44.up_proj:  16%|█▋        | 5979/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.44.down_proj:  16%|█▋        | 5980/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.45.gate_proj:  16%|█▋        | 5981/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.45.up_proj:  16%|█▋        | 5982/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.45.down_proj:  16%|█▋        | 5983/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.46.gate_proj:  16%|█▋        | 5984/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.46.up_proj:  16%|█▋        | 5985/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.46.down_proj:  16%|█▋        | 5986/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.47.gate_proj:  16%|█▋        | 5987/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.47.up_proj:  16%|█▋        | 5988/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.47.down_proj:  16%|█▋        | 5989/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.48.gate_proj:  16%|█▋        | 5990/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.48.up_proj:  16%|█▋        | 5991/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.48.down_proj:  16%|█▋        | 5992/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.49.gate_proj:  16%|█▋        | 5993/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.49.up_proj:  16%|█▋        | 5994/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.49.down_proj:  16%|█▋        | 5995/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.50.gate_proj:  16%|█▋        | 5996/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.50.up_proj:  16%|█▋        | 5997/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.50.down_proj:  16%|█▋        | 5998/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.51.gate_proj:  16%|█▋        | 5999/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.51.up_proj:  16%|█▋        | 6000/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.51.down_proj:  16%|█▋        | 6001/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.52.gate_proj:  16%|█▋        | 6002/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.52.up_proj:  16%|█▋        | 6003/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.52.down_proj:  16%|█▋        | 6004/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.53.gate_proj:  16%|█▋        | 6005/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.53.up_proj:  16%|█▋        | 6006/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.53.down_proj:  16%|█▋        | 6007/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.54.gate_proj:  16%|█▋        | 6008/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.54.up_proj:  16%|█▋        | 6009/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.54.down_proj:  16%|█▋        | 6010/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.55.gate_proj:  16%|█▋        | 6011/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.55.up_proj:  16%|█▋        | 6012/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.55.down_proj:  16%|█▋        | 6013/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.56.gate_proj:  16%|█▋        | 6014/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.56.up_proj:  16%|█▋        | 6015/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.56.down_proj:  16%|█▋        | 6016/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.57.gate_proj:  16%|█▋        | 6017/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.57.up_proj:  16%|█▋        | 6018/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.57.down_proj:  16%|█▋        | 6019/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.58.gate_proj:  16%|█▋        | 6020/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.58.up_proj:  16%|█▋        | 6021/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.58.down_proj:  16%|█▋        | 6022/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.59.gate_proj:  16%|█▋        | 6023/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.59.up_proj:  16%|█▋        | 6024/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.59.down_proj:  16%|█▋        | 6025/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.60.gate_proj:  16%|█▋        | 6026/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.60.up_proj:  16%|█▋        | 6027/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.60.down_proj:  16%|█▋        | 6028/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.61.gate_proj:  16%|█▋        | 6029/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.61.up_proj:  16%|█▋        | 6030/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.61.down_proj:  16%|█▋        | 6031/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.62.gate_proj:  16%|█▋        | 6032/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.62.up_proj:  16%|█▋        | 6033/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.62.down_proj:  17%|█▋        | 6034/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.63.gate_proj:  17%|█▋        | 6035/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.63.up_proj:  17%|█▋        | 6036/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.63.down_proj:  17%|█▋        | 6037/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.64.gate_proj:  17%|█▋        | 6038/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.64.up_proj:  17%|█▋        | 6039/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.64.down_proj:  17%|█▋        | 6040/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.65.gate_proj:  17%|█▋        | 6041/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.65.up_proj:  17%|█▋        | 6042/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.65.down_proj:  17%|█▋        | 6043/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.66.gate_proj:  17%|█▋        | 6044/36566 [00:06<00:26, 1154.92it/s]
packing model.layers.14.mlp.experts.66.up_proj:  17%|█▋        | 6045/36566 [00:06<00:26, 1154.92it/s]  
packing model.layers.14.mlp.experts.66.up_proj:  17%|█▋        | 6046/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.66.down_proj:  17%|█▋        | 6046/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.67.gate_proj:  17%|█▋        | 6047/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.67.up_proj:  17%|█▋        | 6048/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.67.down_proj:  17%|█▋        | 6049/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.68.gate_proj:  17%|█▋        | 6050/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.68.up_proj:  17%|█▋        | 6051/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.68.down_proj:  17%|█▋        | 6052/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.69.gate_proj:  17%|█▋        | 6053/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.69.up_proj:  17%|█▋        | 6054/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.69.down_proj:  17%|█▋        | 6055/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.70.gate_proj:  17%|█▋        | 6056/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.70.up_proj:  17%|█▋        | 6057/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.70.down_proj:  17%|█▋        | 6058/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.71.gate_proj:  17%|█▋        | 6059/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.71.up_proj:  17%|█▋        | 6060/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.71.down_proj:  17%|█▋        | 6061/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.72.gate_proj:  17%|█▋        | 6062/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.72.up_proj:  17%|█▋        | 6063/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.72.down_proj:  17%|█▋        | 6064/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.73.gate_proj:  17%|█▋        | 6065/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.73.up_proj:  17%|█▋        | 6066/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.73.down_proj:  17%|█▋        | 6067/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.74.gate_proj:  17%|█▋        | 6068/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.74.up_proj:  17%|█▋        | 6069/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.74.down_proj:  17%|█▋        | 6070/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.75.gate_proj:  17%|█▋        | 6071/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.75.up_proj:  17%|█▋        | 6072/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.75.down_proj:  17%|█▋        | 6073/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.76.gate_proj:  17%|█▋        | 6074/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.76.up_proj:  17%|█▋        | 6075/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.76.down_proj:  17%|█▋        | 6076/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.77.gate_proj:  17%|█▋        | 6077/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.77.up_proj:  17%|█▋        | 6078/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.77.down_proj:  17%|█▋        | 6079/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.78.gate_proj:  17%|█▋        | 6080/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.78.up_proj:  17%|█▋        | 6081/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.78.down_proj:  17%|█▋        | 6082/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.79.gate_proj:  17%|█▋        | 6083/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.79.up_proj:  17%|█▋        | 6084/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.79.down_proj:  17%|█▋        | 6085/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.80.gate_proj:  17%|█▋        | 6086/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.80.up_proj:  17%|█▋        | 6087/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.80.down_proj:  17%|█▋        | 6088/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.81.gate_proj:  17%|█▋        | 6089/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.81.up_proj:  17%|█▋        | 6090/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.81.down_proj:  17%|█▋        | 6091/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.82.gate_proj:  17%|█▋        | 6092/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.82.up_proj:  17%|█▋        | 6093/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.82.down_proj:  17%|█▋        | 6094/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.83.gate_proj:  17%|█▋        | 6095/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.83.up_proj:  17%|█▋        | 6096/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.83.down_proj:  17%|█▋        | 6097/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.84.gate_proj:  17%|█▋        | 6098/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.84.up_proj:  17%|█▋        | 6099/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.84.down_proj:  17%|█▋        | 6100/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.85.gate_proj:  17%|█▋        | 6101/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.85.up_proj:  17%|█▋        | 6102/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.85.down_proj:  17%|█▋        | 6103/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.86.gate_proj:  17%|█▋        | 6104/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.86.up_proj:  17%|█▋        | 6105/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.86.down_proj:  17%|█▋        | 6106/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.87.gate_proj:  17%|█▋        | 6107/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.87.up_proj:  17%|█▋        | 6108/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.87.down_proj:  17%|█▋        | 6109/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.88.gate_proj:  17%|█▋        | 6110/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.88.up_proj:  17%|█▋        | 6111/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.88.down_proj:  17%|█▋        | 6112/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.89.gate_proj:  17%|█▋        | 6113/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.89.up_proj:  17%|█▋        | 6114/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.89.down_proj:  17%|█▋        | 6115/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.90.gate_proj:  17%|█▋        | 6116/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.90.up_proj:  17%|█▋        | 6117/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.90.down_proj:  17%|█▋        | 6118/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.91.gate_proj:  17%|█▋        | 6119/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.91.up_proj:  17%|█▋        | 6120/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.91.down_proj:  17%|█▋        | 6121/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.92.gate_proj:  17%|█▋        | 6122/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.92.up_proj:  17%|█▋        | 6123/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.92.down_proj:  17%|█▋        | 6124/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.93.gate_proj:  17%|█▋        | 6125/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.93.up_proj:  17%|█▋        | 6126/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.93.down_proj:  17%|█▋        | 6127/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.94.gate_proj:  17%|█▋        | 6128/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.94.up_proj:  17%|█▋        | 6129/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.94.down_proj:  17%|█▋        | 6130/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.95.gate_proj:  17%|█▋        | 6131/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.95.up_proj:  17%|█▋        | 6132/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.95.down_proj:  17%|█▋        | 6133/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.96.gate_proj:  17%|█▋        | 6134/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.96.up_proj:  17%|█▋        | 6135/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.96.down_proj:  17%|█▋        | 6136/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.97.gate_proj:  17%|█▋        | 6137/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.97.up_proj:  17%|█▋        | 6138/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.97.down_proj:  17%|█▋        | 6139/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.98.gate_proj:  17%|█▋        | 6140/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.98.up_proj:  17%|█▋        | 6141/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.98.down_proj:  17%|█▋        | 6142/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.99.gate_proj:  17%|█▋        | 6143/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.99.up_proj:  17%|█▋        | 6144/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.99.down_proj:  17%|█▋        | 6145/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.100.gate_proj:  17%|█▋        | 6146/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.100.up_proj:  17%|█▋        | 6147/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.100.down_proj:  17%|█▋        | 6148/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.101.gate_proj:  17%|█▋        | 6149/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.101.up_proj:  17%|█▋        | 6150/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.101.down_proj:  17%|█▋        | 6151/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.102.gate_proj:  17%|█▋        | 6152/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.102.up_proj:  17%|█▋        | 6153/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.102.down_proj:  17%|█▋        | 6154/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.103.gate_proj:  17%|█▋        | 6155/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.103.up_proj:  17%|█▋        | 6156/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.103.down_proj:  17%|█▋        | 6157/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.104.gate_proj:  17%|█▋        | 6158/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.104.up_proj:  17%|█▋        | 6159/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.104.down_proj:  17%|█▋        | 6160/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.105.gate_proj:  17%|█▋        | 6161/36566 [00:06<00:26, 1156.98it/s]
packing model.layers.14.mlp.experts.105.up_proj:  17%|█▋        | 6162/36566 [00:06<00:26, 1156.98it/s]  
packing model.layers.14.mlp.experts.105.up_proj:  17%|█▋        | 6163/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.105.down_proj:  17%|█▋        | 6163/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.106.gate_proj:  17%|█▋        | 6164/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.106.up_proj:  17%|█▋        | 6165/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.106.down_proj:  17%|█▋        | 6166/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.107.gate_proj:  17%|█▋        | 6167/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.107.up_proj:  17%|█▋        | 6168/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.107.down_proj:  17%|█▋        | 6169/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.108.gate_proj:  17%|█▋        | 6170/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.108.up_proj:  17%|█▋        | 6171/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.108.down_proj:  17%|█▋        | 6172/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.109.gate_proj:  17%|█▋        | 6173/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.109.up_proj:  17%|█▋        | 6174/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.109.down_proj:  17%|█▋        | 6175/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.110.gate_proj:  17%|█▋        | 6176/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.110.up_proj:  17%|█▋        | 6177/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.110.down_proj:  17%|█▋        | 6178/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.111.gate_proj:  17%|█▋        | 6179/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.111.up_proj:  17%|█▋        | 6180/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.111.down_proj:  17%|█▋        | 6181/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.112.gate_proj:  17%|█▋        | 6182/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.112.up_proj:  17%|█▋        | 6183/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.112.down_proj:  17%|█▋        | 6184/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.113.gate_proj:  17%|█▋        | 6185/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.113.up_proj:  17%|█▋        | 6186/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.113.down_proj:  17%|█▋        | 6187/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.114.gate_proj:  17%|█▋        | 6188/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.114.up_proj:  17%|█▋        | 6189/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.114.down_proj:  17%|█▋        | 6190/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.115.gate_proj:  17%|█▋        | 6191/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.115.up_proj:  17%|█▋        | 6192/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.115.down_proj:  17%|█▋        | 6193/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.116.gate_proj:  17%|█▋        | 6194/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.116.up_proj:  17%|█▋        | 6195/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.116.down_proj:  17%|█▋        | 6196/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.117.gate_proj:  17%|█▋        | 6197/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.117.up_proj:  17%|█▋        | 6198/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.117.down_proj:  17%|█▋        | 6199/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.118.gate_proj:  17%|█▋        | 6200/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.118.up_proj:  17%|█▋        | 6201/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.118.down_proj:  17%|█▋        | 6202/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.119.gate_proj:  17%|█▋        | 6203/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.119.up_proj:  17%|█▋        | 6204/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.119.down_proj:  17%|█▋        | 6205/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.120.gate_proj:  17%|█▋        | 6206/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.120.up_proj:  17%|█▋        | 6207/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.120.down_proj:  17%|█▋        | 6208/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.121.gate_proj:  17%|█▋        | 6209/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.121.up_proj:  17%|█▋        | 6210/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.121.down_proj:  17%|█▋        | 6211/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.122.gate_proj:  17%|█▋        | 6212/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.122.up_proj:  17%|█▋        | 6213/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.122.down_proj:  17%|█▋        | 6214/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.123.gate_proj:  17%|█▋        | 6215/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.123.up_proj:  17%|█▋        | 6216/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.123.down_proj:  17%|█▋        | 6217/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.124.gate_proj:  17%|█▋        | 6218/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.124.up_proj:  17%|█▋        | 6219/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.124.down_proj:  17%|█▋        | 6220/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.125.gate_proj:  17%|█▋        | 6221/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.125.up_proj:  17%|█▋        | 6222/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.125.down_proj:  17%|█▋        | 6223/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.126.gate_proj:  17%|█▋        | 6224/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.126.up_proj:  17%|█▋        | 6225/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.126.down_proj:  17%|█▋        | 6226/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.127.gate_proj:  17%|█▋        | 6227/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.14.mlp.experts.127.up_proj:  17%|█▋        | 6228/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.14.mlp.experts.127.down_proj:  17%|█▋        | 6229/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.0.gate_proj:  17%|█▋        | 6230/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.0.up_proj:  17%|█▋        | 6231/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.0.down_proj:  17%|█▋        | 6232/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.1.gate_proj:  17%|█▋        | 6233/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.1.up_proj:  17%|█▋        | 6234/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.1.down_proj:  17%|█▋        | 6235/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.2.gate_proj:  17%|█▋        | 6236/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.2.up_proj:  17%|█▋        | 6237/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.2.down_proj:  17%|█▋        | 6238/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.3.gate_proj:  17%|█▋        | 6239/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.3.up_proj:  17%|█▋        | 6240/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.3.down_proj:  17%|█▋        | 6241/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.4.gate_proj:  17%|█▋        | 6242/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.4.up_proj:  17%|█▋        | 6243/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.4.down_proj:  17%|█▋        | 6244/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.5.gate_proj:  17%|█▋        | 6245/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.5.up_proj:  17%|█▋        | 6246/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.5.down_proj:  17%|█▋        | 6247/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.6.gate_proj:  17%|█▋        | 6248/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.6.up_proj:  17%|█▋        | 6249/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.6.down_proj:  17%|█▋        | 6250/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.7.gate_proj:  17%|█▋        | 6251/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.7.up_proj:  17%|█▋        | 6252/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.7.down_proj:  17%|█▋        | 6253/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.8.gate_proj:  17%|█▋        | 6254/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.8.up_proj:  17%|█▋        | 6255/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.8.down_proj:  17%|█▋        | 6256/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.9.gate_proj:  17%|█▋        | 6257/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.9.up_proj:  17%|█▋        | 6258/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.9.down_proj:  17%|█▋        | 6259/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.10.gate_proj:  17%|█▋        | 6260/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.10.up_proj:  17%|█▋        | 6261/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.10.down_proj:  17%|█▋        | 6262/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.11.gate_proj:  17%|█▋        | 6263/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.11.up_proj:  17%|█▋        | 6264/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.11.down_proj:  17%|█▋        | 6265/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.12.gate_proj:  17%|█▋        | 6266/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.12.up_proj:  17%|█▋        | 6267/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.12.down_proj:  17%|█▋        | 6268/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.13.gate_proj:  17%|█▋        | 6269/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.13.up_proj:  17%|█▋        | 6270/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.13.down_proj:  17%|█▋        | 6271/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.14.gate_proj:  17%|█▋        | 6272/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.14.up_proj:  17%|█▋        | 6273/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.14.down_proj:  17%|█▋        | 6274/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.15.gate_proj:  17%|█▋        | 6275/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.15.up_proj:  17%|█▋        | 6276/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.15.down_proj:  17%|█▋        | 6277/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.16.gate_proj:  17%|█▋        | 6278/36566 [00:06<00:26, 1158.48it/s]
packing model.layers.15.mlp.experts.16.up_proj:  17%|█▋        | 6279/36566 [00:06<00:26, 1158.48it/s]  
packing model.layers.15.mlp.experts.16.up_proj:  17%|█▋        | 6280/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.16.down_proj:  17%|█▋        | 6280/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.17.gate_proj:  17%|█▋        | 6281/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.17.up_proj:  17%|█▋        | 6282/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.17.down_proj:  17%|█▋        | 6283/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.18.gate_proj:  17%|█▋        | 6284/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.18.up_proj:  17%|█▋        | 6285/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.18.down_proj:  17%|█▋        | 6286/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.19.gate_proj:  17%|█▋        | 6287/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.19.up_proj:  17%|█▋        | 6288/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.19.down_proj:  17%|█▋        | 6289/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.20.gate_proj:  17%|█▋        | 6290/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.20.up_proj:  17%|█▋        | 6291/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.20.down_proj:  17%|█▋        | 6292/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.21.gate_proj:  17%|█▋        | 6293/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.21.up_proj:  17%|█▋        | 6294/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.21.down_proj:  17%|█▋        | 6295/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.22.gate_proj:  17%|█▋        | 6296/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.22.up_proj:  17%|█▋        | 6297/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.22.down_proj:  17%|█▋        | 6298/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.23.gate_proj:  17%|█▋        | 6299/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.23.up_proj:  17%|█▋        | 6300/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.23.down_proj:  17%|█▋        | 6301/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.24.gate_proj:  17%|█▋        | 6302/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.24.up_proj:  17%|█▋        | 6303/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.24.down_proj:  17%|█▋        | 6304/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.25.gate_proj:  17%|█▋        | 6305/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.25.up_proj:  17%|█▋        | 6306/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.25.down_proj:  17%|█▋        | 6307/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.26.gate_proj:  17%|█▋        | 6308/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.26.up_proj:  17%|█▋        | 6309/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.26.down_proj:  17%|█▋        | 6310/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.27.gate_proj:  17%|█▋        | 6311/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.27.up_proj:  17%|█▋        | 6312/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.27.down_proj:  17%|█▋        | 6313/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.28.gate_proj:  17%|█▋        | 6314/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.28.up_proj:  17%|█▋        | 6315/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.28.down_proj:  17%|█▋        | 6316/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.29.gate_proj:  17%|█▋        | 6317/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.29.up_proj:  17%|█▋        | 6318/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.29.down_proj:  17%|█▋        | 6319/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.30.gate_proj:  17%|█▋        | 6320/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.30.up_proj:  17%|█▋        | 6321/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.30.down_proj:  17%|█▋        | 6322/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.31.gate_proj:  17%|█▋        | 6323/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.31.up_proj:  17%|█▋        | 6324/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.31.down_proj:  17%|█▋        | 6325/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.32.gate_proj:  17%|█▋        | 6326/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.32.up_proj:  17%|█▋        | 6327/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.32.down_proj:  17%|█▋        | 6328/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.33.gate_proj:  17%|█▋        | 6329/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.33.up_proj:  17%|█▋        | 6330/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.33.down_proj:  17%|█▋        | 6331/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.34.gate_proj:  17%|█▋        | 6332/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.34.up_proj:  17%|█▋        | 6333/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.34.down_proj:  17%|█▋        | 6334/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.35.gate_proj:  17%|█▋        | 6335/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.35.up_proj:  17%|█▋        | 6336/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.35.down_proj:  17%|█▋        | 6337/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.36.gate_proj:  17%|█▋        | 6338/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.36.up_proj:  17%|█▋        | 6339/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.36.down_proj:  17%|█▋        | 6340/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.37.gate_proj:  17%|█▋        | 6341/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.37.up_proj:  17%|█▋        | 6342/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.37.down_proj:  17%|█▋        | 6343/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.38.gate_proj:  17%|█▋        | 6344/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.38.up_proj:  17%|█▋        | 6345/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.38.down_proj:  17%|█▋        | 6346/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.39.gate_proj:  17%|█▋        | 6347/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.39.up_proj:  17%|█▋        | 6348/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.39.down_proj:  17%|█▋        | 6349/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.40.gate_proj:  17%|█▋        | 6350/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.40.up_proj:  17%|█▋        | 6351/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.40.down_proj:  17%|█▋        | 6352/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.41.gate_proj:  17%|█▋        | 6353/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.41.up_proj:  17%|█▋        | 6354/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.41.down_proj:  17%|█▋        | 6355/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.42.gate_proj:  17%|█▋        | 6356/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.42.up_proj:  17%|█▋        | 6357/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.42.down_proj:  17%|█▋        | 6358/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.43.gate_proj:  17%|█▋        | 6359/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.43.up_proj:  17%|█▋        | 6360/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.43.down_proj:  17%|█▋        | 6361/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.44.gate_proj:  17%|█▋        | 6362/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.44.up_proj:  17%|█▋        | 6363/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.44.down_proj:  17%|█▋        | 6364/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.45.gate_proj:  17%|█▋        | 6365/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.45.up_proj:  17%|█▋        | 6366/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.45.down_proj:  17%|█▋        | 6367/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.46.gate_proj:  17%|█▋        | 6368/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.46.up_proj:  17%|█▋        | 6369/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.46.down_proj:  17%|█▋        | 6370/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.47.gate_proj:  17%|█▋        | 6371/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.47.up_proj:  17%|█▋        | 6372/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.47.down_proj:  17%|█▋        | 6373/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.48.gate_proj:  17%|█▋        | 6374/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.48.up_proj:  17%|█▋        | 6375/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.48.down_proj:  17%|█▋        | 6376/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.49.gate_proj:  17%|█▋        | 6377/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.49.up_proj:  17%|█▋        | 6378/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.49.down_proj:  17%|█▋        | 6379/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.50.gate_proj:  17%|█▋        | 6380/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.50.up_proj:  17%|█▋        | 6381/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.50.down_proj:  17%|█▋        | 6382/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.51.gate_proj:  17%|█▋        | 6383/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.51.up_proj:  17%|█▋        | 6384/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.51.down_proj:  17%|█▋        | 6385/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.52.gate_proj:  17%|█▋        | 6386/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.52.up_proj:  17%|█▋        | 6387/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.52.down_proj:  17%|█▋        | 6388/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.53.gate_proj:  17%|█▋        | 6389/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.53.up_proj:  17%|█▋        | 6390/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.53.down_proj:  17%|█▋        | 6391/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.54.gate_proj:  17%|█▋        | 6392/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.54.up_proj:  17%|█▋        | 6393/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.54.down_proj:  17%|█▋        | 6394/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.55.gate_proj:  17%|█▋        | 6395/36566 [00:06<00:26, 1160.11it/s]
packing model.layers.15.mlp.experts.55.up_proj:  17%|█▋        | 6396/36566 [00:06<00:26, 1160.11it/s]  
packing model.layers.15.mlp.experts.55.up_proj:  17%|█▋        | 6397/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.55.down_proj:  17%|█▋        | 6397/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.56.gate_proj:  17%|█▋        | 6398/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.56.up_proj:  17%|█▋        | 6399/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.56.down_proj:  18%|█▊        | 6400/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.57.gate_proj:  18%|█▊        | 6401/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.57.up_proj:  18%|█▊        | 6402/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.57.down_proj:  18%|█▊        | 6403/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.58.gate_proj:  18%|█▊        | 6404/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.58.up_proj:  18%|█▊        | 6405/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.58.down_proj:  18%|█▊        | 6406/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.59.gate_proj:  18%|█▊        | 6407/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.59.up_proj:  18%|█▊        | 6408/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.59.down_proj:  18%|█▊        | 6409/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.60.gate_proj:  18%|█▊        | 6410/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.60.up_proj:  18%|█▊        | 6411/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.60.down_proj:  18%|█▊        | 6412/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.61.gate_proj:  18%|█▊        | 6413/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.61.up_proj:  18%|█▊        | 6414/36566 [00:06<00:26, 1159.64it/s]  
packing model.layers.15.mlp.experts.61.down_proj:  18%|█▊        | 6415/36566 [00:06<00:26, 1159.64it/s]
packing model.layers.15.mlp.experts.62.gate_proj:  18%|█▊        | 6416/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.62.up_proj:  18%|█▊        | 6417/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.62.down_proj:  18%|█▊        | 6418/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.63.gate_proj:  18%|█▊        | 6419/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.63.up_proj:  18%|█▊        | 6420/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.63.down_proj:  18%|█▊        | 6421/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.64.gate_proj:  18%|█▊        | 6422/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.64.up_proj:  18%|█▊        | 6423/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.64.down_proj:  18%|█▊        | 6424/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.65.gate_proj:  18%|█▊        | 6425/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.65.up_proj:  18%|█▊        | 6426/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.65.down_proj:  18%|█▊        | 6427/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.66.gate_proj:  18%|█▊        | 6428/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.66.up_proj:  18%|█▊        | 6429/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.66.down_proj:  18%|█▊        | 6430/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.67.gate_proj:  18%|█▊        | 6431/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.67.up_proj:  18%|█▊        | 6432/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.67.down_proj:  18%|█▊        | 6433/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.68.gate_proj:  18%|█▊        | 6434/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.68.up_proj:  18%|█▊        | 6435/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.68.down_proj:  18%|█▊        | 6436/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.69.gate_proj:  18%|█▊        | 6437/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.69.up_proj:  18%|█▊        | 6438/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.69.down_proj:  18%|█▊        | 6439/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.70.gate_proj:  18%|█▊        | 6440/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.70.up_proj:  18%|█▊        | 6441/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.70.down_proj:  18%|█▊        | 6442/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.71.gate_proj:  18%|█▊        | 6443/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.71.up_proj:  18%|█▊        | 6444/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.71.down_proj:  18%|█▊        | 6445/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.72.gate_proj:  18%|█▊        | 6446/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.72.up_proj:  18%|█▊        | 6447/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.72.down_proj:  18%|█▊        | 6448/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.73.gate_proj:  18%|█▊        | 6449/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.73.up_proj:  18%|█▊        | 6450/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.73.down_proj:  18%|█▊        | 6451/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.74.gate_proj:  18%|█▊        | 6452/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.74.up_proj:  18%|█▊        | 6453/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.74.down_proj:  18%|█▊        | 6454/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.75.gate_proj:  18%|█▊        | 6455/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.75.up_proj:  18%|█▊        | 6456/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.75.down_proj:  18%|█▊        | 6457/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.76.gate_proj:  18%|█▊        | 6458/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.76.up_proj:  18%|█▊        | 6459/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.76.down_proj:  18%|█▊        | 6460/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.77.gate_proj:  18%|█▊        | 6461/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.77.up_proj:  18%|█▊        | 6462/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.77.down_proj:  18%|█▊        | 6463/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.78.gate_proj:  18%|█▊        | 6464/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.78.up_proj:  18%|█▊        | 6465/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.78.down_proj:  18%|█▊        | 6466/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.79.gate_proj:  18%|█▊        | 6467/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.79.up_proj:  18%|█▊        | 6468/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.79.down_proj:  18%|█▊        | 6469/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.80.gate_proj:  18%|█▊        | 6470/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.80.up_proj:  18%|█▊        | 6471/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.80.down_proj:  18%|█▊        | 6472/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.81.gate_proj:  18%|█▊        | 6473/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.81.up_proj:  18%|█▊        | 6474/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.81.down_proj:  18%|█▊        | 6475/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.82.gate_proj:  18%|█▊        | 6476/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.82.up_proj:  18%|█▊        | 6477/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.82.down_proj:  18%|█▊        | 6478/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.83.gate_proj:  18%|█▊        | 6479/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.83.up_proj:  18%|█▊        | 6480/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.83.down_proj:  18%|█▊        | 6481/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.84.gate_proj:  18%|█▊        | 6482/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.84.up_proj:  18%|█▊        | 6483/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.84.down_proj:  18%|█▊        | 6484/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.85.gate_proj:  18%|█▊        | 6485/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.85.up_proj:  18%|█▊        | 6486/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.85.down_proj:  18%|█▊        | 6487/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.86.gate_proj:  18%|█▊        | 6488/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.86.up_proj:  18%|█▊        | 6489/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.86.down_proj:  18%|█▊        | 6490/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.87.gate_proj:  18%|█▊        | 6491/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.87.up_proj:  18%|█▊        | 6492/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.87.down_proj:  18%|█▊        | 6493/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.88.gate_proj:  18%|█▊        | 6494/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.88.up_proj:  18%|█▊        | 6495/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.88.down_proj:  18%|█▊        | 6496/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.89.gate_proj:  18%|█▊        | 6497/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.89.up_proj:  18%|█▊        | 6498/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.89.down_proj:  18%|█▊        | 6499/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.90.gate_proj:  18%|█▊        | 6500/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.90.up_proj:  18%|█▊        | 6501/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.90.down_proj:  18%|█▊        | 6502/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.91.gate_proj:  18%|█▊        | 6503/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.91.up_proj:  18%|█▊        | 6504/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.91.down_proj:  18%|█▊        | 6505/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.92.gate_proj:  18%|█▊        | 6506/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.92.up_proj:  18%|█▊        | 6507/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.92.down_proj:  18%|█▊        | 6508/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.93.gate_proj:  18%|█▊        | 6509/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.93.up_proj:  18%|█▊        | 6510/36566 [00:06<00:25, 1159.64it/s]  
packing model.layers.15.mlp.experts.93.down_proj:  18%|█▊        | 6511/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.94.gate_proj:  18%|█▊        | 6512/36566 [00:06<00:25, 1159.64it/s]
packing model.layers.15.mlp.experts.94.gate_proj:  18%|█▊        | 6513/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.94.up_proj:  18%|█▊        | 6513/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.94.down_proj:  18%|█▊        | 6514/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.95.gate_proj:  18%|█▊        | 6515/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.95.up_proj:  18%|█▊        | 6516/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.95.down_proj:  18%|█▊        | 6517/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.96.gate_proj:  18%|█▊        | 6518/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.96.up_proj:  18%|█▊        | 6519/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.96.down_proj:  18%|█▊        | 6520/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.97.gate_proj:  18%|█▊        | 6521/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.97.up_proj:  18%|█▊        | 6522/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.97.down_proj:  18%|█▊        | 6523/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.98.gate_proj:  18%|█▊        | 6524/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.98.up_proj:  18%|█▊        | 6525/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.98.down_proj:  18%|█▊        | 6526/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.99.gate_proj:  18%|█▊        | 6527/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.99.up_proj:  18%|█▊        | 6528/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.99.down_proj:  18%|█▊        | 6529/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.100.gate_proj:  18%|█▊        | 6530/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.100.up_proj:  18%|█▊        | 6531/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.100.down_proj:  18%|█▊        | 6532/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.101.gate_proj:  18%|█▊        | 6533/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.101.up_proj:  18%|█▊        | 6534/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.101.down_proj:  18%|█▊        | 6535/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.102.gate_proj:  18%|█▊        | 6536/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.102.up_proj:  18%|█▊        | 6537/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.102.down_proj:  18%|█▊        | 6538/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.103.gate_proj:  18%|█▊        | 6539/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.103.up_proj:  18%|█▊        | 6540/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.103.down_proj:  18%|█▊        | 6541/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.104.gate_proj:  18%|█▊        | 6542/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.104.up_proj:  18%|█▊        | 6543/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.104.down_proj:  18%|█▊        | 6544/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.105.gate_proj:  18%|█▊        | 6545/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.105.up_proj:  18%|█▊        | 6546/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.105.down_proj:  18%|█▊        | 6547/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.106.gate_proj:  18%|█▊        | 6548/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.106.up_proj:  18%|█▊        | 6549/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.106.down_proj:  18%|█▊        | 6550/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.107.gate_proj:  18%|█▊        | 6551/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.107.up_proj:  18%|█▊        | 6552/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.107.down_proj:  18%|█▊        | 6553/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.108.gate_proj:  18%|█▊        | 6554/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.108.up_proj:  18%|█▊        | 6555/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.108.down_proj:  18%|█▊        | 6556/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.109.gate_proj:  18%|█▊        | 6557/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.109.up_proj:  18%|█▊        | 6558/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.109.down_proj:  18%|█▊        | 6559/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.110.gate_proj:  18%|█▊        | 6560/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.110.up_proj:  18%|█▊        | 6561/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.110.down_proj:  18%|█▊        | 6562/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.111.gate_proj:  18%|█▊        | 6563/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.111.up_proj:  18%|█▊        | 6564/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.111.down_proj:  18%|█▊        | 6565/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.112.gate_proj:  18%|█▊        | 6566/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.112.up_proj:  18%|█▊        | 6567/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.112.down_proj:  18%|█▊        | 6568/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.113.gate_proj:  18%|█▊        | 6569/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.113.up_proj:  18%|█▊        | 6570/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.113.down_proj:  18%|█▊        | 6571/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.114.gate_proj:  18%|█▊        | 6572/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.114.up_proj:  18%|█▊        | 6573/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.114.down_proj:  18%|█▊        | 6574/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.115.gate_proj:  18%|█▊        | 6575/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.115.up_proj:  18%|█▊        | 6576/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.115.down_proj:  18%|█▊        | 6577/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.116.gate_proj:  18%|█▊        | 6578/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.116.up_proj:  18%|█▊        | 6579/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.116.down_proj:  18%|█▊        | 6580/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.117.gate_proj:  18%|█▊        | 6581/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.117.up_proj:  18%|█▊        | 6582/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.117.down_proj:  18%|█▊        | 6583/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.118.gate_proj:  18%|█▊        | 6584/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.118.up_proj:  18%|█▊        | 6585/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.118.down_proj:  18%|█▊        | 6586/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.119.gate_proj:  18%|█▊        | 6587/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.119.up_proj:  18%|█▊        | 6588/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.119.down_proj:  18%|█▊        | 6589/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.120.gate_proj:  18%|█▊        | 6590/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.120.up_proj:  18%|█▊        | 6591/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.120.down_proj:  18%|█▊        | 6592/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.121.gate_proj:  18%|█▊        | 6593/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.121.up_proj:  18%|█▊        | 6594/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.121.down_proj:  18%|█▊        | 6595/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.122.gate_proj:  18%|█▊        | 6596/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.122.up_proj:  18%|█▊        | 6597/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.122.down_proj:  18%|█▊        | 6598/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.123.gate_proj:  18%|█▊        | 6599/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.123.up_proj:  18%|█▊        | 6600/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.123.down_proj:  18%|█▊        | 6601/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.124.gate_proj:  18%|█▊        | 6602/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.124.up_proj:  18%|█▊        | 6603/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.124.down_proj:  18%|█▊        | 6604/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.125.gate_proj:  18%|█▊        | 6605/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.125.up_proj:  18%|█▊        | 6606/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.125.down_proj:  18%|█▊        | 6607/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.126.gate_proj:  18%|█▊        | 6608/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.126.up_proj:  18%|█▊        | 6609/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.126.down_proj:  18%|█▊        | 6610/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.127.gate_proj:  18%|█▊        | 6611/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.15.mlp.experts.127.up_proj:  18%|█▊        | 6612/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.15.mlp.experts.127.down_proj:  18%|█▊        | 6613/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.0.gate_proj:  18%|█▊        | 6614/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.0.up_proj:  18%|█▊        | 6615/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.0.down_proj:  18%|█▊        | 6616/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.1.gate_proj:  18%|█▊        | 6617/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.1.up_proj:  18%|█▊        | 6618/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.1.down_proj:  18%|█▊        | 6619/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.2.gate_proj:  18%|█▊        | 6620/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.2.up_proj:  18%|█▊        | 6621/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.2.down_proj:  18%|█▊        | 6622/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.3.gate_proj:  18%|█▊        | 6623/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.3.up_proj:  18%|█▊        | 6624/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.3.down_proj:  18%|█▊        | 6625/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.4.gate_proj:  18%|█▊        | 6626/36566 [00:06<00:26, 1141.94it/s]
packing model.layers.16.mlp.experts.4.up_proj:  18%|█▊        | 6627/36566 [00:06<00:26, 1141.94it/s]  
packing model.layers.16.mlp.experts.4.up_proj:  18%|█▊        | 6628/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.4.down_proj:  18%|█▊        | 6628/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.5.gate_proj:  18%|█▊        | 6629/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.5.up_proj:  18%|█▊        | 6630/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.5.down_proj:  18%|█▊        | 6631/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.6.gate_proj:  18%|█▊        | 6632/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.6.up_proj:  18%|█▊        | 6633/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.6.down_proj:  18%|█▊        | 6634/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.7.gate_proj:  18%|█▊        | 6635/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.7.up_proj:  18%|█▊        | 6636/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.7.down_proj:  18%|█▊        | 6637/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.8.gate_proj:  18%|█▊        | 6638/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.8.up_proj:  18%|█▊        | 6639/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.8.down_proj:  18%|█▊        | 6640/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.9.gate_proj:  18%|█▊        | 6641/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.9.up_proj:  18%|█▊        | 6642/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.9.down_proj:  18%|█▊        | 6643/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.10.gate_proj:  18%|█▊        | 6644/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.10.up_proj:  18%|█▊        | 6645/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.10.down_proj:  18%|█▊        | 6646/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.11.gate_proj:  18%|█▊        | 6647/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.11.up_proj:  18%|█▊        | 6648/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.11.down_proj:  18%|█▊        | 6649/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.12.gate_proj:  18%|█▊        | 6650/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.12.up_proj:  18%|█▊        | 6651/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.12.down_proj:  18%|█▊        | 6652/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.13.gate_proj:  18%|█▊        | 6653/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.13.up_proj:  18%|█▊        | 6654/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.13.down_proj:  18%|█▊        | 6655/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.14.gate_proj:  18%|█▊        | 6656/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.14.up_proj:  18%|█▊        | 6657/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.14.down_proj:  18%|█▊        | 6658/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.15.gate_proj:  18%|█▊        | 6659/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.15.up_proj:  18%|█▊        | 6660/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.15.down_proj:  18%|█▊        | 6661/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.16.gate_proj:  18%|█▊        | 6662/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.16.up_proj:  18%|█▊        | 6663/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.16.down_proj:  18%|█▊        | 6664/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.17.gate_proj:  18%|█▊        | 6665/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.17.up_proj:  18%|█▊        | 6666/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.17.down_proj:  18%|█▊        | 6667/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.18.gate_proj:  18%|█▊        | 6668/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.18.up_proj:  18%|█▊        | 6669/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.18.down_proj:  18%|█▊        | 6670/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.19.gate_proj:  18%|█▊        | 6671/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.19.up_proj:  18%|█▊        | 6672/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.19.down_proj:  18%|█▊        | 6673/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.20.gate_proj:  18%|█▊        | 6674/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.20.up_proj:  18%|█▊        | 6675/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.20.down_proj:  18%|█▊        | 6676/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.21.gate_proj:  18%|█▊        | 6677/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.21.up_proj:  18%|█▊        | 6678/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.21.down_proj:  18%|█▊        | 6679/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.22.gate_proj:  18%|█▊        | 6680/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.22.up_proj:  18%|█▊        | 6681/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.22.down_proj:  18%|█▊        | 6682/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.23.gate_proj:  18%|█▊        | 6683/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.23.up_proj:  18%|█▊        | 6684/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.23.down_proj:  18%|█▊        | 6685/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.24.gate_proj:  18%|█▊        | 6686/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.24.up_proj:  18%|█▊        | 6687/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.24.down_proj:  18%|█▊        | 6688/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.25.gate_proj:  18%|█▊        | 6689/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.25.up_proj:  18%|█▊        | 6690/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.25.down_proj:  18%|█▊        | 6691/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.26.gate_proj:  18%|█▊        | 6692/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.26.up_proj:  18%|█▊        | 6693/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.26.down_proj:  18%|█▊        | 6694/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.27.gate_proj:  18%|█▊        | 6695/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.27.up_proj:  18%|█▊        | 6696/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.27.down_proj:  18%|█▊        | 6697/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.28.gate_proj:  18%|█▊        | 6698/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.28.up_proj:  18%|█▊        | 6699/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.28.down_proj:  18%|█▊        | 6700/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.29.gate_proj:  18%|█▊        | 6701/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.29.up_proj:  18%|█▊        | 6702/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.29.down_proj:  18%|█▊        | 6703/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.30.gate_proj:  18%|█▊        | 6704/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.30.up_proj:  18%|█▊        | 6705/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.30.down_proj:  18%|█▊        | 6706/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.31.gate_proj:  18%|█▊        | 6707/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.31.up_proj:  18%|█▊        | 6708/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.31.down_proj:  18%|█▊        | 6709/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.32.gate_proj:  18%|█▊        | 6710/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.32.up_proj:  18%|█▊        | 6711/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.32.down_proj:  18%|█▊        | 6712/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.33.gate_proj:  18%|█▊        | 6713/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.33.up_proj:  18%|█▊        | 6714/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.33.down_proj:  18%|█▊        | 6715/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.34.gate_proj:  18%|█▊        | 6716/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.34.up_proj:  18%|█▊        | 6717/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.34.down_proj:  18%|█▊        | 6718/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.35.gate_proj:  18%|█▊        | 6719/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.35.up_proj:  18%|█▊        | 6720/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.35.down_proj:  18%|█▊        | 6721/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.36.gate_proj:  18%|█▊        | 6722/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.36.up_proj:  18%|█▊        | 6723/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.36.down_proj:  18%|█▊        | 6724/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.37.gate_proj:  18%|█▊        | 6725/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.37.up_proj:  18%|█▊        | 6726/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.37.down_proj:  18%|█▊        | 6727/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.38.gate_proj:  18%|█▊        | 6728/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.38.up_proj:  18%|█▊        | 6729/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.38.down_proj:  18%|█▊        | 6730/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.39.gate_proj:  18%|█▊        | 6731/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.39.up_proj:  18%|█▊        | 6732/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.39.down_proj:  18%|█▊        | 6733/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.40.gate_proj:  18%|█▊        | 6734/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.40.up_proj:  18%|█▊        | 6735/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.40.down_proj:  18%|█▊        | 6736/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.41.gate_proj:  18%|█▊        | 6737/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.41.up_proj:  18%|█▊        | 6738/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.41.down_proj:  18%|█▊        | 6739/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.42.gate_proj:  18%|█▊        | 6740/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.42.up_proj:  18%|█▊        | 6741/36566 [00:06<00:26, 1132.10it/s]  
packing model.layers.16.mlp.experts.42.down_proj:  18%|█▊        | 6742/36566 [00:06<00:26, 1132.10it/s]
packing model.layers.16.mlp.experts.42.down_proj:  18%|█▊        | 6743/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.43.gate_proj:  18%|█▊        | 6743/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.43.up_proj:  18%|█▊        | 6744/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.43.down_proj:  18%|█▊        | 6745/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.44.gate_proj:  18%|█▊        | 6746/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.44.up_proj:  18%|█▊        | 6747/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.44.down_proj:  18%|█▊        | 6748/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.45.gate_proj:  18%|█▊        | 6749/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.45.up_proj:  18%|█▊        | 6750/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.45.down_proj:  18%|█▊        | 6751/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.46.gate_proj:  18%|█▊        | 6752/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.46.up_proj:  18%|█▊        | 6753/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.46.down_proj:  18%|█▊        | 6754/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.47.gate_proj:  18%|█▊        | 6755/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.47.up_proj:  18%|█▊        | 6756/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.47.down_proj:  18%|█▊        | 6757/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.48.gate_proj:  18%|█▊        | 6758/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.48.up_proj:  18%|█▊        | 6759/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.48.down_proj:  18%|█▊        | 6760/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.49.gate_proj:  18%|█▊        | 6761/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.49.up_proj:  18%|█▊        | 6762/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.49.down_proj:  18%|█▊        | 6763/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.50.gate_proj:  18%|█▊        | 6764/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.50.up_proj:  19%|█▊        | 6765/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.50.down_proj:  19%|█▊        | 6766/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.51.gate_proj:  19%|█▊        | 6767/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.51.up_proj:  19%|█▊        | 6768/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.51.down_proj:  19%|█▊        | 6769/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.52.gate_proj:  19%|█▊        | 6770/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.52.up_proj:  19%|█▊        | 6771/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.52.down_proj:  19%|█▊        | 6772/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.53.gate_proj:  19%|█▊        | 6773/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.53.up_proj:  19%|█▊        | 6774/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.53.down_proj:  19%|█▊        | 6775/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.54.gate_proj:  19%|█▊        | 6776/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.54.up_proj:  19%|█▊        | 6777/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.54.down_proj:  19%|█▊        | 6778/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.55.gate_proj:  19%|█▊        | 6779/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.55.up_proj:  19%|█▊        | 6780/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.55.down_proj:  19%|█▊        | 6781/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.56.gate_proj:  19%|█▊        | 6782/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.56.up_proj:  19%|█▊        | 6783/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.56.down_proj:  19%|█▊        | 6784/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.57.gate_proj:  19%|█▊        | 6785/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.57.up_proj:  19%|█▊        | 6786/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.57.down_proj:  19%|█▊        | 6787/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.58.gate_proj:  19%|█▊        | 6788/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.58.up_proj:  19%|█▊        | 6789/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.58.down_proj:  19%|█▊        | 6790/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.59.gate_proj:  19%|█▊        | 6791/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.59.up_proj:  19%|█▊        | 6792/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.59.down_proj:  19%|█▊        | 6793/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.60.gate_proj:  19%|█▊        | 6794/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.60.up_proj:  19%|█▊        | 6795/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.60.down_proj:  19%|█▊        | 6796/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.61.gate_proj:  19%|█▊        | 6797/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.61.up_proj:  19%|█▊        | 6798/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.61.down_proj:  19%|█▊        | 6799/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.62.gate_proj:  19%|█▊        | 6800/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.62.up_proj:  19%|█▊        | 6801/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.62.down_proj:  19%|█▊        | 6802/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.63.gate_proj:  19%|█▊        | 6803/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.63.up_proj:  19%|█▊        | 6804/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.63.down_proj:  19%|█▊        | 6805/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.64.gate_proj:  19%|█▊        | 6806/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.64.up_proj:  19%|█▊        | 6807/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.64.down_proj:  19%|█▊        | 6808/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.65.gate_proj:  19%|█▊        | 6809/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.65.up_proj:  19%|█▊        | 6810/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.65.down_proj:  19%|█▊        | 6811/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.66.gate_proj:  19%|█▊        | 6812/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.66.up_proj:  19%|█▊        | 6813/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.66.down_proj:  19%|█▊        | 6814/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.67.gate_proj:  19%|█▊        | 6815/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.67.up_proj:  19%|█▊        | 6816/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.67.down_proj:  19%|█▊        | 6817/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.68.gate_proj:  19%|█▊        | 6818/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.68.up_proj:  19%|█▊        | 6819/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.68.down_proj:  19%|█▊        | 6820/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.69.gate_proj:  19%|█▊        | 6821/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.69.up_proj:  19%|█▊        | 6822/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.69.down_proj:  19%|█▊        | 6823/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.70.gate_proj:  19%|█▊        | 6824/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.70.up_proj:  19%|█▊        | 6825/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.70.down_proj:  19%|█▊        | 6826/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.71.gate_proj:  19%|█▊        | 6827/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.71.up_proj:  19%|█▊        | 6828/36566 [00:06<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.71.down_proj:  19%|█▊        | 6829/36566 [00:06<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.72.gate_proj:  19%|█▊        | 6830/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.72.up_proj:  19%|█▊        | 6831/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.72.down_proj:  19%|█▊        | 6832/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.73.gate_proj:  19%|█▊        | 6833/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.73.up_proj:  19%|█▊        | 6834/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.73.down_proj:  19%|█▊        | 6835/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.74.gate_proj:  19%|█▊        | 6836/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.74.up_proj:  19%|█▊        | 6837/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.74.down_proj:  19%|█▊        | 6838/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.75.gate_proj:  19%|█▊        | 6839/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.75.up_proj:  19%|█▊        | 6840/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.75.down_proj:  19%|█▊        | 6841/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.76.gate_proj:  19%|█▊        | 6842/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.76.up_proj:  19%|█▊        | 6843/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.76.down_proj:  19%|█▊        | 6844/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.77.gate_proj:  19%|█▊        | 6845/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.77.up_proj:  19%|█▊        | 6846/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.77.down_proj:  19%|█▊        | 6847/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.78.gate_proj:  19%|█▊        | 6848/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.78.up_proj:  19%|█▊        | 6849/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.78.down_proj:  19%|█▊        | 6850/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.79.gate_proj:  19%|█▊        | 6851/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.79.up_proj:  19%|█▊        | 6852/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.79.down_proj:  19%|█▊        | 6853/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.80.gate_proj:  19%|█▊        | 6854/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.80.up_proj:  19%|█▊        | 6855/36566 [00:07<00:26, 1135.55it/s]  
packing model.layers.16.mlp.experts.80.down_proj:  19%|█▊        | 6856/36566 [00:07<00:26, 1135.55it/s]
packing model.layers.16.mlp.experts.80.down_proj:  19%|█▉        | 6857/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.81.gate_proj:  19%|█▉        | 6857/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.81.up_proj:  19%|█▉        | 6858/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.81.down_proj:  19%|█▉        | 6859/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.82.gate_proj:  19%|█▉        | 6860/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.82.up_proj:  19%|█▉        | 6861/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.82.down_proj:  19%|█▉        | 6862/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.83.gate_proj:  19%|█▉        | 6863/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.83.up_proj:  19%|█▉        | 6864/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.83.down_proj:  19%|█▉        | 6865/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.84.gate_proj:  19%|█▉        | 6866/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.84.up_proj:  19%|█▉        | 6867/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.84.down_proj:  19%|█▉        | 6868/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.85.gate_proj:  19%|█▉        | 6869/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.85.up_proj:  19%|█▉        | 6870/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.85.down_proj:  19%|█▉        | 6871/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.86.gate_proj:  19%|█▉        | 6872/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.86.up_proj:  19%|█▉        | 6873/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.86.down_proj:  19%|█▉        | 6874/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.87.gate_proj:  19%|█▉        | 6875/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.87.up_proj:  19%|█▉        | 6876/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.87.down_proj:  19%|█▉        | 6877/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.88.gate_proj:  19%|█▉        | 6878/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.88.up_proj:  19%|█▉        | 6879/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.88.down_proj:  19%|█▉        | 6880/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.89.gate_proj:  19%|█▉        | 6881/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.89.up_proj:  19%|█▉        | 6882/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.89.down_proj:  19%|█▉        | 6883/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.90.gate_proj:  19%|█▉        | 6884/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.90.up_proj:  19%|█▉        | 6885/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.90.down_proj:  19%|█▉        | 6886/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.91.gate_proj:  19%|█▉        | 6887/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.91.up_proj:  19%|█▉        | 6888/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.91.down_proj:  19%|█▉        | 6889/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.92.gate_proj:  19%|█▉        | 6890/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.92.up_proj:  19%|█▉        | 6891/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.92.down_proj:  19%|█▉        | 6892/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.93.gate_proj:  19%|█▉        | 6893/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.93.up_proj:  19%|█▉        | 6894/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.93.down_proj:  19%|█▉        | 6895/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.94.gate_proj:  19%|█▉        | 6896/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.94.up_proj:  19%|█▉        | 6897/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.94.down_proj:  19%|█▉        | 6898/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.95.gate_proj:  19%|█▉        | 6899/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.95.up_proj:  19%|█▉        | 6900/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.95.down_proj:  19%|█▉        | 6901/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.96.gate_proj:  19%|█▉        | 6902/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.96.up_proj:  19%|█▉        | 6903/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.96.down_proj:  19%|█▉        | 6904/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.97.gate_proj:  19%|█▉        | 6905/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.97.up_proj:  19%|█▉        | 6906/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.97.down_proj:  19%|█▉        | 6907/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.98.gate_proj:  19%|█▉        | 6908/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.98.up_proj:  19%|█▉        | 6909/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.98.down_proj:  19%|█▉        | 6910/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.99.gate_proj:  19%|█▉        | 6911/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.99.up_proj:  19%|█▉        | 6912/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.99.down_proj:  19%|█▉        | 6913/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.100.gate_proj:  19%|█▉        | 6914/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.100.up_proj:  19%|█▉        | 6915/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.100.down_proj:  19%|█▉        | 6916/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.101.gate_proj:  19%|█▉        | 6917/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.101.up_proj:  19%|█▉        | 6918/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.101.down_proj:  19%|█▉        | 6919/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.102.gate_proj:  19%|█▉        | 6920/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.102.up_proj:  19%|█▉        | 6921/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.102.down_proj:  19%|█▉        | 6922/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.103.gate_proj:  19%|█▉        | 6923/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.103.up_proj:  19%|█▉        | 6924/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.103.down_proj:  19%|█▉        | 6925/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.104.gate_proj:  19%|█▉        | 6926/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.104.up_proj:  19%|█▉        | 6927/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.104.down_proj:  19%|█▉        | 6928/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.105.gate_proj:  19%|█▉        | 6929/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.105.up_proj:  19%|█▉        | 6930/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.105.down_proj:  19%|█▉        | 6931/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.106.gate_proj:  19%|█▉        | 6932/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.106.up_proj:  19%|█▉        | 6933/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.106.down_proj:  19%|█▉        | 6934/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.107.gate_proj:  19%|█▉        | 6935/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.107.up_proj:  19%|█▉        | 6936/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.107.down_proj:  19%|█▉        | 6937/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.108.gate_proj:  19%|█▉        | 6938/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.108.up_proj:  19%|█▉        | 6939/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.108.down_proj:  19%|█▉        | 6940/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.109.gate_proj:  19%|█▉        | 6941/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.109.up_proj:  19%|█▉        | 6942/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.109.down_proj:  19%|█▉        | 6943/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.110.gate_proj:  19%|█▉        | 6944/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.110.up_proj:  19%|█▉        | 6945/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.110.down_proj:  19%|█▉        | 6946/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.111.gate_proj:  19%|█▉        | 6947/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.111.up_proj:  19%|█▉        | 6948/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.111.down_proj:  19%|█▉        | 6949/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.112.gate_proj:  19%|█▉        | 6950/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.112.up_proj:  19%|█▉        | 6951/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.112.down_proj:  19%|█▉        | 6952/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.113.gate_proj:  19%|█▉        | 6953/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.113.up_proj:  19%|█▉        | 6954/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.113.down_proj:  19%|█▉        | 6955/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.114.gate_proj:  19%|█▉        | 6956/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.114.up_proj:  19%|█▉        | 6957/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.114.down_proj:  19%|█▉        | 6958/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.115.gate_proj:  19%|█▉        | 6959/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.115.up_proj:  19%|█▉        | 6960/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.115.down_proj:  19%|█▉        | 6961/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.116.gate_proj:  19%|█▉        | 6962/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.116.up_proj:  19%|█▉        | 6963/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.116.down_proj:  19%|█▉        | 6964/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.117.gate_proj:  19%|█▉        | 6965/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.117.up_proj:  19%|█▉        | 6966/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.117.down_proj:  19%|█▉        | 6967/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.118.gate_proj:  19%|█▉        | 6968/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.118.up_proj:  19%|█▉        | 6969/36566 [00:07<00:26, 1133.67it/s]  
packing model.layers.16.mlp.experts.118.down_proj:  19%|█▉        | 6970/36566 [00:07<00:26, 1133.67it/s]
packing model.layers.16.mlp.experts.118.down_proj:  19%|█▉        | 6971/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.119.gate_proj:  19%|█▉        | 6971/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.119.up_proj:  19%|█▉        | 6972/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.119.down_proj:  19%|█▉        | 6973/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.120.gate_proj:  19%|█▉        | 6974/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.120.up_proj:  19%|█▉        | 6975/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.120.down_proj:  19%|█▉        | 6976/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.121.gate_proj:  19%|█▉        | 6977/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.121.up_proj:  19%|█▉        | 6978/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.121.down_proj:  19%|█▉        | 6979/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.122.gate_proj:  19%|█▉        | 6980/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.122.up_proj:  19%|█▉        | 6981/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.122.down_proj:  19%|█▉        | 6982/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.123.gate_proj:  19%|█▉        | 6983/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.123.up_proj:  19%|█▉        | 6984/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.123.down_proj:  19%|█▉        | 6985/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.124.gate_proj:  19%|█▉        | 6986/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.124.up_proj:  19%|█▉        | 6987/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.124.down_proj:  19%|█▉        | 6988/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.125.gate_proj:  19%|█▉        | 6989/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.125.up_proj:  19%|█▉        | 6990/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.125.down_proj:  19%|█▉        | 6991/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.126.gate_proj:  19%|█▉        | 6992/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.126.up_proj:  19%|█▉        | 6993/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.126.down_proj:  19%|█▉        | 6994/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.127.gate_proj:  19%|█▉        | 6995/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.16.mlp.experts.127.up_proj:  19%|█▉        | 6996/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.16.mlp.experts.127.down_proj:  19%|█▉        | 6997/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.0.gate_proj:  19%|█▉        | 6998/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.0.up_proj:  19%|█▉        | 6999/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.0.down_proj:  19%|█▉        | 7000/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.1.gate_proj:  19%|█▉        | 7001/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.1.up_proj:  19%|█▉        | 7002/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.1.down_proj:  19%|█▉        | 7003/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.2.gate_proj:  19%|█▉        | 7004/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.2.up_proj:  19%|█▉        | 7005/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.2.down_proj:  19%|█▉        | 7006/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.3.gate_proj:  19%|█▉        | 7007/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.3.up_proj:  19%|█▉        | 7008/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.3.down_proj:  19%|█▉        | 7009/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.4.gate_proj:  19%|█▉        | 7010/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.4.up_proj:  19%|█▉        | 7011/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.4.down_proj:  19%|█▉        | 7012/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.5.gate_proj:  19%|█▉        | 7013/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.5.up_proj:  19%|█▉        | 7014/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.5.down_proj:  19%|█▉        | 7015/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.6.gate_proj:  19%|█▉        | 7016/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.6.up_proj:  19%|█▉        | 7017/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.6.down_proj:  19%|█▉        | 7018/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.7.gate_proj:  19%|█▉        | 7019/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.7.up_proj:  19%|█▉        | 7020/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.7.down_proj:  19%|█▉        | 7021/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.8.gate_proj:  19%|█▉        | 7022/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.8.up_proj:  19%|█▉        | 7023/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.8.down_proj:  19%|█▉        | 7024/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.9.gate_proj:  19%|█▉        | 7025/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.9.up_proj:  19%|█▉        | 7026/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.9.down_proj:  19%|█▉        | 7027/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.10.gate_proj:  19%|█▉        | 7028/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.10.up_proj:  19%|█▉        | 7029/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.10.down_proj:  19%|█▉        | 7030/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.11.gate_proj:  19%|█▉        | 7031/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.11.up_proj:  19%|█▉        | 7032/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.11.down_proj:  19%|█▉        | 7033/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.12.gate_proj:  19%|█▉        | 7034/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.12.up_proj:  19%|█▉        | 7035/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.12.down_proj:  19%|█▉        | 7036/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.13.gate_proj:  19%|█▉        | 7037/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.13.up_proj:  19%|█▉        | 7038/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.13.down_proj:  19%|█▉        | 7039/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.14.gate_proj:  19%|█▉        | 7040/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.14.up_proj:  19%|█▉        | 7041/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.14.down_proj:  19%|█▉        | 7042/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.15.gate_proj:  19%|█▉        | 7043/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.15.up_proj:  19%|█▉        | 7044/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.15.down_proj:  19%|█▉        | 7045/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.16.gate_proj:  19%|█▉        | 7046/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.16.up_proj:  19%|█▉        | 7047/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.16.down_proj:  19%|█▉        | 7048/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.17.gate_proj:  19%|█▉        | 7049/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.17.up_proj:  19%|█▉        | 7050/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.17.down_proj:  19%|█▉        | 7051/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.18.gate_proj:  19%|█▉        | 7052/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.18.up_proj:  19%|█▉        | 7053/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.18.down_proj:  19%|█▉        | 7054/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.19.gate_proj:  19%|█▉        | 7055/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.19.up_proj:  19%|█▉        | 7056/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.19.down_proj:  19%|█▉        | 7057/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.20.gate_proj:  19%|█▉        | 7058/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.20.up_proj:  19%|█▉        | 7059/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.20.down_proj:  19%|█▉        | 7060/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.21.gate_proj:  19%|█▉        | 7061/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.21.up_proj:  19%|█▉        | 7062/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.21.down_proj:  19%|█▉        | 7063/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.22.gate_proj:  19%|█▉        | 7064/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.22.up_proj:  19%|█▉        | 7065/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.22.down_proj:  19%|█▉        | 7066/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.23.gate_proj:  19%|█▉        | 7067/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.23.up_proj:  19%|█▉        | 7068/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.23.down_proj:  19%|█▉        | 7069/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.24.gate_proj:  19%|█▉        | 7070/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.24.up_proj:  19%|█▉        | 7071/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.24.down_proj:  19%|█▉        | 7072/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.25.gate_proj:  19%|█▉        | 7073/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.25.up_proj:  19%|█▉        | 7074/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.25.down_proj:  19%|█▉        | 7075/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.26.gate_proj:  19%|█▉        | 7076/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.26.up_proj:  19%|█▉        | 7077/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.26.down_proj:  19%|█▉        | 7078/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.27.gate_proj:  19%|█▉        | 7079/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.27.up_proj:  19%|█▉        | 7080/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.27.down_proj:  19%|█▉        | 7081/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.28.gate_proj:  19%|█▉        | 7082/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.28.up_proj:  19%|█▉        | 7083/36566 [00:07<00:26, 1131.84it/s]  
packing model.layers.17.mlp.experts.28.down_proj:  19%|█▉        | 7084/36566 [00:07<00:26, 1131.84it/s]
packing model.layers.17.mlp.experts.28.down_proj:  19%|█▉        | 7085/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.29.gate_proj:  19%|█▉        | 7085/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.29.up_proj:  19%|█▉        | 7086/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.29.down_proj:  19%|█▉        | 7087/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.30.gate_proj:  19%|█▉        | 7088/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.30.up_proj:  19%|█▉        | 7089/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.30.down_proj:  19%|█▉        | 7090/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.31.gate_proj:  19%|█▉        | 7091/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.31.up_proj:  19%|█▉        | 7092/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.31.down_proj:  19%|█▉        | 7093/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.32.gate_proj:  19%|█▉        | 7094/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.32.up_proj:  19%|█▉        | 7095/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.32.down_proj:  19%|█▉        | 7096/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.33.gate_proj:  19%|█▉        | 7097/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.33.up_proj:  19%|█▉        | 7098/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.33.down_proj:  19%|█▉        | 7099/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.34.gate_proj:  19%|█▉        | 7100/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.34.up_proj:  19%|█▉        | 7101/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.34.down_proj:  19%|█▉        | 7102/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.35.gate_proj:  19%|█▉        | 7103/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.35.up_proj:  19%|█▉        | 7104/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.35.down_proj:  19%|█▉        | 7105/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.36.gate_proj:  19%|█▉        | 7106/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.36.up_proj:  19%|█▉        | 7107/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.36.down_proj:  19%|█▉        | 7108/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.37.gate_proj:  19%|█▉        | 7109/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.37.up_proj:  19%|█▉        | 7110/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.37.down_proj:  19%|█▉        | 7111/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.38.gate_proj:  19%|█▉        | 7112/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.38.up_proj:  19%|█▉        | 7113/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.38.down_proj:  19%|█▉        | 7114/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.39.gate_proj:  19%|█▉        | 7115/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.39.up_proj:  19%|█▉        | 7116/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.39.down_proj:  19%|█▉        | 7117/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.40.gate_proj:  19%|█▉        | 7118/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.40.up_proj:  19%|█▉        | 7119/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.40.down_proj:  19%|█▉        | 7120/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.41.gate_proj:  19%|█▉        | 7121/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.41.up_proj:  19%|█▉        | 7122/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.41.down_proj:  19%|█▉        | 7123/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.42.gate_proj:  19%|█▉        | 7124/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.42.up_proj:  19%|█▉        | 7125/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.42.down_proj:  19%|█▉        | 7126/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.43.gate_proj:  19%|█▉        | 7127/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.43.up_proj:  19%|█▉        | 7128/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.43.down_proj:  19%|█▉        | 7129/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.44.gate_proj:  19%|█▉        | 7130/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.44.up_proj:  20%|█▉        | 7131/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.44.down_proj:  20%|█▉        | 7132/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.45.gate_proj:  20%|█▉        | 7133/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.45.up_proj:  20%|█▉        | 7134/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.45.down_proj:  20%|█▉        | 7135/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.46.gate_proj:  20%|█▉        | 7136/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.46.up_proj:  20%|█▉        | 7137/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.46.down_proj:  20%|█▉        | 7138/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.47.gate_proj:  20%|█▉        | 7139/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.47.up_proj:  20%|█▉        | 7140/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.47.down_proj:  20%|█▉        | 7141/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.48.gate_proj:  20%|█▉        | 7142/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.48.up_proj:  20%|█▉        | 7143/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.48.down_proj:  20%|█▉        | 7144/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.49.gate_proj:  20%|█▉        | 7145/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.49.up_proj:  20%|█▉        | 7146/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.49.down_proj:  20%|█▉        | 7147/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.50.gate_proj:  20%|█▉        | 7148/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.50.up_proj:  20%|█▉        | 7149/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.50.down_proj:  20%|█▉        | 7150/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.51.gate_proj:  20%|█▉        | 7151/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.51.up_proj:  20%|█▉        | 7152/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.51.down_proj:  20%|█▉        | 7153/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.52.gate_proj:  20%|█▉        | 7154/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.52.up_proj:  20%|█▉        | 7155/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.52.down_proj:  20%|█▉        | 7156/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.53.gate_proj:  20%|█▉        | 7157/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.53.up_proj:  20%|█▉        | 7158/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.53.down_proj:  20%|█▉        | 7159/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.54.gate_proj:  20%|█▉        | 7160/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.54.up_proj:  20%|█▉        | 7161/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.54.down_proj:  20%|█▉        | 7162/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.55.gate_proj:  20%|█▉        | 7163/36566 [00:07<00:26, 1130.81it/s]
packing model.layers.17.mlp.experts.55.up_proj:  20%|█▉        | 7164/36566 [00:07<00:26, 1130.81it/s]  
packing model.layers.17.mlp.experts.55.down_proj:  20%|█▉        | 7165/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.56.gate_proj:  20%|█▉        | 7166/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.56.up_proj:  20%|█▉        | 7167/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.56.down_proj:  20%|█▉        | 7168/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.57.gate_proj:  20%|█▉        | 7169/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.57.up_proj:  20%|█▉        | 7170/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.57.down_proj:  20%|█▉        | 7171/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.58.gate_proj:  20%|█▉        | 7172/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.58.up_proj:  20%|█▉        | 7173/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.58.down_proj:  20%|█▉        | 7174/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.59.gate_proj:  20%|█▉        | 7175/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.59.up_proj:  20%|█▉        | 7176/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.59.down_proj:  20%|█▉        | 7177/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.60.gate_proj:  20%|█▉        | 7178/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.60.up_proj:  20%|█▉        | 7179/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.60.down_proj:  20%|█▉        | 7180/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.61.gate_proj:  20%|█▉        | 7181/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.61.up_proj:  20%|█▉        | 7182/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.61.down_proj:  20%|█▉        | 7183/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.62.gate_proj:  20%|█▉        | 7184/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.62.up_proj:  20%|█▉        | 7185/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.62.down_proj:  20%|█▉        | 7186/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.63.gate_proj:  20%|█▉        | 7187/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.63.up_proj:  20%|█▉        | 7188/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.63.down_proj:  20%|█▉        | 7189/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.64.gate_proj:  20%|█▉        | 7190/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.64.up_proj:  20%|█▉        | 7191/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.64.down_proj:  20%|█▉        | 7192/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.65.gate_proj:  20%|█▉        | 7193/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.65.up_proj:  20%|█▉        | 7194/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.65.down_proj:  20%|█▉        | 7195/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.66.gate_proj:  20%|█▉        | 7196/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.66.up_proj:  20%|█▉        | 7197/36566 [00:07<00:25, 1130.81it/s]  
packing model.layers.17.mlp.experts.66.down_proj:  20%|█▉        | 7198/36566 [00:07<00:25, 1130.81it/s]
packing model.layers.17.mlp.experts.66.down_proj:  20%|█▉        | 7199/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.67.gate_proj:  20%|█▉        | 7199/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.67.up_proj:  20%|█▉        | 7200/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.67.down_proj:  20%|█▉        | 7201/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.68.gate_proj:  20%|█▉        | 7202/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.68.up_proj:  20%|█▉        | 7203/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.68.down_proj:  20%|█▉        | 7204/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.69.gate_proj:  20%|█▉        | 7205/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.69.up_proj:  20%|█▉        | 7206/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.69.down_proj:  20%|█▉        | 7207/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.70.gate_proj:  20%|█▉        | 7208/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.70.up_proj:  20%|█▉        | 7209/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.70.down_proj:  20%|█▉        | 7210/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.71.gate_proj:  20%|█▉        | 7211/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.71.up_proj:  20%|█▉        | 7212/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.71.down_proj:  20%|█▉        | 7213/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.72.gate_proj:  20%|█▉        | 7214/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.72.up_proj:  20%|█▉        | 7215/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.72.down_proj:  20%|█▉        | 7216/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.73.gate_proj:  20%|█▉        | 7217/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.73.up_proj:  20%|█▉        | 7218/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.73.down_proj:  20%|█▉        | 7219/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.74.gate_proj:  20%|█▉        | 7220/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.74.up_proj:  20%|█▉        | 7221/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.74.down_proj:  20%|█▉        | 7222/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.75.gate_proj:  20%|█▉        | 7223/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.75.up_proj:  20%|█▉        | 7224/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.75.down_proj:  20%|█▉        | 7225/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.76.gate_proj:  20%|█▉        | 7226/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.76.up_proj:  20%|█▉        | 7227/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.76.down_proj:  20%|█▉        | 7228/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.77.gate_proj:  20%|█▉        | 7229/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.77.up_proj:  20%|█▉        | 7230/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.77.down_proj:  20%|█▉        | 7231/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.78.gate_proj:  20%|█▉        | 7232/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.78.up_proj:  20%|█▉        | 7233/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.78.down_proj:  20%|█▉        | 7234/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.79.gate_proj:  20%|█▉        | 7235/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.79.up_proj:  20%|█▉        | 7236/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.79.down_proj:  20%|█▉        | 7237/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.80.gate_proj:  20%|█▉        | 7238/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.80.up_proj:  20%|█▉        | 7239/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.80.down_proj:  20%|█▉        | 7240/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.81.gate_proj:  20%|█▉        | 7241/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.81.up_proj:  20%|█▉        | 7242/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.81.down_proj:  20%|█▉        | 7243/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.82.gate_proj:  20%|█▉        | 7244/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.82.up_proj:  20%|█▉        | 7245/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.82.down_proj:  20%|█▉        | 7246/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.83.gate_proj:  20%|█▉        | 7247/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.83.up_proj:  20%|█▉        | 7248/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.83.down_proj:  20%|█▉        | 7249/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.84.gate_proj:  20%|█▉        | 7250/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.84.up_proj:  20%|█▉        | 7251/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.84.down_proj:  20%|█▉        | 7252/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.85.gate_proj:  20%|█▉        | 7253/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.85.up_proj:  20%|█▉        | 7254/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.85.down_proj:  20%|█▉        | 7255/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.86.gate_proj:  20%|█▉        | 7256/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.86.up_proj:  20%|█▉        | 7257/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.86.down_proj:  20%|█▉        | 7258/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.87.gate_proj:  20%|█▉        | 7259/36566 [00:07<00:26, 1127.14it/s]
packing model.layers.17.mlp.experts.87.up_proj:  20%|█▉        | 7260/36566 [00:07<00:26, 1127.14it/s]  
packing model.layers.17.mlp.experts.87.down_proj:  20%|█▉        | 7261/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.88.gate_proj:  20%|█▉        | 7262/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.88.up_proj:  20%|█▉        | 7263/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.88.down_proj:  20%|█▉        | 7264/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.89.gate_proj:  20%|█▉        | 7265/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.89.up_proj:  20%|█▉        | 7266/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.89.down_proj:  20%|█▉        | 7267/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.90.gate_proj:  20%|█▉        | 7268/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.90.up_proj:  20%|█▉        | 7269/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.90.down_proj:  20%|█▉        | 7270/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.91.gate_proj:  20%|█▉        | 7271/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.91.up_proj:  20%|█▉        | 7272/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.91.down_proj:  20%|█▉        | 7273/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.92.gate_proj:  20%|█▉        | 7274/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.92.up_proj:  20%|█▉        | 7275/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.92.down_proj:  20%|█▉        | 7276/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.93.gate_proj:  20%|█▉        | 7277/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.93.up_proj:  20%|█▉        | 7278/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.93.down_proj:  20%|█▉        | 7279/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.94.gate_proj:  20%|█▉        | 7280/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.94.up_proj:  20%|█▉        | 7281/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.94.down_proj:  20%|█▉        | 7282/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.95.gate_proj:  20%|█▉        | 7283/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.95.up_proj:  20%|█▉        | 7284/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.95.down_proj:  20%|█▉        | 7285/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.96.gate_proj:  20%|█▉        | 7286/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.96.up_proj:  20%|█▉        | 7287/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.96.down_proj:  20%|█▉        | 7288/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.97.gate_proj:  20%|█▉        | 7289/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.97.up_proj:  20%|█▉        | 7290/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.97.down_proj:  20%|█▉        | 7291/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.98.gate_proj:  20%|█▉        | 7292/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.98.up_proj:  20%|█▉        | 7293/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.98.down_proj:  20%|█▉        | 7294/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.99.gate_proj:  20%|█▉        | 7295/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.99.up_proj:  20%|█▉        | 7296/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.99.down_proj:  20%|█▉        | 7297/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.100.gate_proj:  20%|█▉        | 7298/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.100.up_proj:  20%|█▉        | 7299/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.100.down_proj:  20%|█▉        | 7300/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.101.gate_proj:  20%|█▉        | 7301/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.101.up_proj:  20%|█▉        | 7302/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.101.down_proj:  20%|█▉        | 7303/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.102.gate_proj:  20%|█▉        | 7304/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.102.up_proj:  20%|█▉        | 7305/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.102.down_proj:  20%|█▉        | 7306/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.103.gate_proj:  20%|█▉        | 7307/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.103.up_proj:  20%|█▉        | 7308/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.103.down_proj:  20%|█▉        | 7309/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.104.gate_proj:  20%|█▉        | 7310/36566 [00:07<00:25, 1127.14it/s]
packing model.layers.17.mlp.experts.104.up_proj:  20%|█▉        | 7311/36566 [00:07<00:25, 1127.14it/s]  
packing model.layers.17.mlp.experts.104.up_proj:  20%|█▉        | 7312/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.104.down_proj:  20%|█▉        | 7312/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.105.gate_proj:  20%|█▉        | 7313/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.105.up_proj:  20%|██        | 7314/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.105.down_proj:  20%|██        | 7315/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.106.gate_proj:  20%|██        | 7316/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.106.up_proj:  20%|██        | 7317/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.106.down_proj:  20%|██        | 7318/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.107.gate_proj:  20%|██        | 7319/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.107.up_proj:  20%|██        | 7320/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.107.down_proj:  20%|██        | 7321/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.108.gate_proj:  20%|██        | 7322/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.108.up_proj:  20%|██        | 7323/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.108.down_proj:  20%|██        | 7324/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.109.gate_proj:  20%|██        | 7325/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.109.up_proj:  20%|██        | 7326/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.109.down_proj:  20%|██        | 7327/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.110.gate_proj:  20%|██        | 7328/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.110.up_proj:  20%|██        | 7329/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.110.down_proj:  20%|██        | 7330/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.111.gate_proj:  20%|██        | 7331/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.111.up_proj:  20%|██        | 7332/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.111.down_proj:  20%|██        | 7333/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.112.gate_proj:  20%|██        | 7334/36566 [00:07<00:26, 1124.25it/s]
packing model.layers.17.mlp.experts.112.up_proj:  20%|██        | 7335/36566 [00:07<00:26, 1124.25it/s]  
packing model.layers.17.mlp.experts.112.down_proj:  20%|██        | 7336/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.113.gate_proj:  20%|██        | 7337/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.113.up_proj:  20%|██        | 7338/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.113.down_proj:  20%|██        | 7339/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.114.gate_proj:  20%|██        | 7340/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.114.up_proj:  20%|██        | 7341/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.114.down_proj:  20%|██        | 7342/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.115.gate_proj:  20%|██        | 7343/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.115.up_proj:  20%|██        | 7344/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.115.down_proj:  20%|██        | 7345/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.116.gate_proj:  20%|██        | 7346/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.116.up_proj:  20%|██        | 7347/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.116.down_proj:  20%|██        | 7348/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.117.gate_proj:  20%|██        | 7349/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.117.up_proj:  20%|██        | 7350/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.117.down_proj:  20%|██        | 7351/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.118.gate_proj:  20%|██        | 7352/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.118.up_proj:  20%|██        | 7353/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.118.down_proj:  20%|██        | 7354/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.119.gate_proj:  20%|██        | 7355/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.119.up_proj:  20%|██        | 7356/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.119.down_proj:  20%|██        | 7357/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.120.gate_proj:  20%|██        | 7358/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.120.up_proj:  20%|██        | 7359/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.120.down_proj:  20%|██        | 7360/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.121.gate_proj:  20%|██        | 7361/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.121.up_proj:  20%|██        | 7362/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.121.down_proj:  20%|██        | 7363/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.122.gate_proj:  20%|██        | 7364/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.122.up_proj:  20%|██        | 7365/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.122.down_proj:  20%|██        | 7366/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.123.gate_proj:  20%|██        | 7367/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.123.up_proj:  20%|██        | 7368/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.123.down_proj:  20%|██        | 7369/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.124.gate_proj:  20%|██        | 7370/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.124.up_proj:  20%|██        | 7371/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.124.down_proj:  20%|██        | 7372/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.125.gate_proj:  20%|██        | 7373/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.125.up_proj:  20%|██        | 7374/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.125.down_proj:  20%|██        | 7375/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.126.gate_proj:  20%|██        | 7376/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.126.up_proj:  20%|██        | 7377/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.126.down_proj:  20%|██        | 7378/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.127.gate_proj:  20%|██        | 7379/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.17.mlp.experts.127.up_proj:  20%|██        | 7380/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.17.mlp.experts.127.down_proj:  20%|██        | 7381/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.0.gate_proj:  20%|██        | 7382/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.0.up_proj:  20%|██        | 7383/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.0.down_proj:  20%|██        | 7384/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.1.gate_proj:  20%|██        | 7385/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.1.up_proj:  20%|██        | 7386/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.1.down_proj:  20%|██        | 7387/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.2.gate_proj:  20%|██        | 7388/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.2.up_proj:  20%|██        | 7389/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.2.down_proj:  20%|██        | 7390/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.3.gate_proj:  20%|██        | 7391/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.3.up_proj:  20%|██        | 7392/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.3.down_proj:  20%|██        | 7393/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.4.gate_proj:  20%|██        | 7394/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.4.up_proj:  20%|██        | 7395/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.4.down_proj:  20%|██        | 7396/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.5.gate_proj:  20%|██        | 7397/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.5.up_proj:  20%|██        | 7398/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.5.down_proj:  20%|██        | 7399/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.6.gate_proj:  20%|██        | 7400/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.6.up_proj:  20%|██        | 7401/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.6.down_proj:  20%|██        | 7402/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.7.gate_proj:  20%|██        | 7403/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.7.up_proj:  20%|██        | 7404/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.7.down_proj:  20%|██        | 7405/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.8.gate_proj:  20%|██        | 7406/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.8.up_proj:  20%|██        | 7407/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.8.down_proj:  20%|██        | 7408/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.9.gate_proj:  20%|██        | 7409/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.9.up_proj:  20%|██        | 7410/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.9.down_proj:  20%|██        | 7411/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.10.gate_proj:  20%|██        | 7412/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.10.up_proj:  20%|██        | 7413/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.10.down_proj:  20%|██        | 7414/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.11.gate_proj:  20%|██        | 7415/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.11.up_proj:  20%|██        | 7416/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.11.down_proj:  20%|██        | 7417/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.12.gate_proj:  20%|██        | 7418/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.12.up_proj:  20%|██        | 7419/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.12.down_proj:  20%|██        | 7420/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.13.gate_proj:  20%|██        | 7421/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.13.up_proj:  20%|██        | 7422/36566 [00:07<00:25, 1124.25it/s]  
packing model.layers.18.mlp.experts.13.down_proj:  20%|██        | 7423/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.14.gate_proj:  20%|██        | 7424/36566 [00:07<00:25, 1124.25it/s]
packing model.layers.18.mlp.experts.14.gate_proj:  20%|██        | 7425/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.14.up_proj:  20%|██        | 7425/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.14.down_proj:  20%|██        | 7426/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.15.gate_proj:  20%|██        | 7427/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.15.up_proj:  20%|██        | 7428/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.15.down_proj:  20%|██        | 7429/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.16.gate_proj:  20%|██        | 7430/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.16.up_proj:  20%|██        | 7431/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.16.down_proj:  20%|██        | 7432/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.17.gate_proj:  20%|██        | 7433/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.17.up_proj:  20%|██        | 7434/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.17.down_proj:  20%|██        | 7435/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.18.gate_proj:  20%|██        | 7436/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.18.up_proj:  20%|██        | 7437/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.18.down_proj:  20%|██        | 7438/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.19.gate_proj:  20%|██        | 7439/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.19.up_proj:  20%|██        | 7440/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.19.down_proj:  20%|██        | 7441/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.20.gate_proj:  20%|██        | 7442/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.20.up_proj:  20%|██        | 7443/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.20.down_proj:  20%|██        | 7444/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.21.gate_proj:  20%|██        | 7445/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.21.up_proj:  20%|██        | 7446/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.21.down_proj:  20%|██        | 7447/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.22.gate_proj:  20%|██        | 7448/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.22.up_proj:  20%|██        | 7449/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.22.down_proj:  20%|██        | 7450/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.23.gate_proj:  20%|██        | 7451/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.23.up_proj:  20%|██        | 7452/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.23.down_proj:  20%|██        | 7453/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.24.gate_proj:  20%|██        | 7454/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.24.up_proj:  20%|██        | 7455/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.24.down_proj:  20%|██        | 7456/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.25.gate_proj:  20%|██        | 7457/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.25.up_proj:  20%|██        | 7458/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.25.down_proj:  20%|██        | 7459/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.26.gate_proj:  20%|██        | 7460/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.26.up_proj:  20%|██        | 7461/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.26.down_proj:  20%|██        | 7462/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.27.gate_proj:  20%|██        | 7463/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.27.up_proj:  20%|██        | 7464/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.27.down_proj:  20%|██        | 7465/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.28.gate_proj:  20%|██        | 7466/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.28.up_proj:  20%|██        | 7467/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.28.down_proj:  20%|██        | 7468/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.29.gate_proj:  20%|██        | 7469/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.29.up_proj:  20%|██        | 7470/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.29.down_proj:  20%|██        | 7471/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.30.gate_proj:  20%|██        | 7472/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.30.up_proj:  20%|██        | 7473/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.30.down_proj:  20%|██        | 7474/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.31.gate_proj:  20%|██        | 7475/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.31.up_proj:  20%|██        | 7476/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.31.down_proj:  20%|██        | 7477/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.32.gate_proj:  20%|██        | 7478/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.32.up_proj:  20%|██        | 7479/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.32.down_proj:  20%|██        | 7480/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.33.gate_proj:  20%|██        | 7481/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.33.up_proj:  20%|██        | 7482/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.33.down_proj:  20%|██        | 7483/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.34.gate_proj:  20%|██        | 7484/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.34.up_proj:  20%|██        | 7485/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.34.down_proj:  20%|██        | 7486/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.35.gate_proj:  20%|██        | 7487/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.35.up_proj:  20%|██        | 7488/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.35.down_proj:  20%|██        | 7489/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.36.gate_proj:  20%|██        | 7490/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.36.up_proj:  20%|██        | 7491/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.36.down_proj:  20%|██        | 7492/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.37.gate_proj:  20%|██        | 7493/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.37.up_proj:  20%|██        | 7494/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.37.down_proj:  20%|██        | 7495/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.38.gate_proj:  20%|██        | 7496/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.38.up_proj:  21%|██        | 7497/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.38.down_proj:  21%|██        | 7498/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.39.gate_proj:  21%|██        | 7499/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.39.up_proj:  21%|██        | 7500/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.39.down_proj:  21%|██        | 7501/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.40.gate_proj:  21%|██        | 7502/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.40.up_proj:  21%|██        | 7503/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.40.down_proj:  21%|██        | 7504/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.41.gate_proj:  21%|██        | 7505/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.41.up_proj:  21%|██        | 7506/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.41.down_proj:  21%|██        | 7507/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.42.gate_proj:  21%|██        | 7508/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.42.up_proj:  21%|██        | 7509/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.42.down_proj:  21%|██        | 7510/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.43.gate_proj:  21%|██        | 7511/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.43.up_proj:  21%|██        | 7512/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.43.down_proj:  21%|██        | 7513/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.44.gate_proj:  21%|██        | 7514/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.44.up_proj:  21%|██        | 7515/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.44.down_proj:  21%|██        | 7516/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.45.gate_proj:  21%|██        | 7517/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.45.up_proj:  21%|██        | 7518/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.45.down_proj:  21%|██        | 7519/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.46.gate_proj:  21%|██        | 7520/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.46.up_proj:  21%|██        | 7521/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.46.down_proj:  21%|██        | 7522/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.47.gate_proj:  21%|██        | 7523/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.47.up_proj:  21%|██        | 7524/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.47.down_proj:  21%|██        | 7525/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.48.gate_proj:  21%|██        | 7526/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.48.up_proj:  21%|██        | 7527/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.48.down_proj:  21%|██        | 7528/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.49.gate_proj:  21%|██        | 7529/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.49.up_proj:  21%|██        | 7530/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.49.down_proj:  21%|██        | 7531/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.50.gate_proj:  21%|██        | 7532/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.50.up_proj:  21%|██        | 7533/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.50.down_proj:  21%|██        | 7534/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.51.gate_proj:  21%|██        | 7535/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.51.up_proj:  21%|██        | 7536/36566 [00:07<00:25, 1121.80it/s]  
packing model.layers.18.mlp.experts.51.down_proj:  21%|██        | 7537/36566 [00:07<00:25, 1121.80it/s]
packing model.layers.18.mlp.experts.51.down_proj:  21%|██        | 7538/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.52.gate_proj:  21%|██        | 7538/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.52.up_proj:  21%|██        | 7539/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.52.down_proj:  21%|██        | 7540/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.53.gate_proj:  21%|██        | 7541/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.53.up_proj:  21%|██        | 7542/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.53.down_proj:  21%|██        | 7543/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.54.gate_proj:  21%|██        | 7544/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.54.up_proj:  21%|██        | 7545/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.54.down_proj:  21%|██        | 7546/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.55.gate_proj:  21%|██        | 7547/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.55.up_proj:  21%|██        | 7548/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.55.down_proj:  21%|██        | 7549/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.56.gate_proj:  21%|██        | 7550/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.56.up_proj:  21%|██        | 7551/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.56.down_proj:  21%|██        | 7552/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.57.gate_proj:  21%|██        | 7553/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.57.up_proj:  21%|██        | 7554/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.57.down_proj:  21%|██        | 7555/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.58.gate_proj:  21%|██        | 7556/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.58.up_proj:  21%|██        | 7557/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.58.down_proj:  21%|██        | 7558/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.59.gate_proj:  21%|██        | 7559/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.59.up_proj:  21%|██        | 7560/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.59.down_proj:  21%|██        | 7561/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.60.gate_proj:  21%|██        | 7562/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.60.up_proj:  21%|██        | 7563/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.60.down_proj:  21%|██        | 7564/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.61.gate_proj:  21%|██        | 7565/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.61.up_proj:  21%|██        | 7566/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.61.down_proj:  21%|██        | 7567/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.62.gate_proj:  21%|██        | 7568/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.62.up_proj:  21%|██        | 7569/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.62.down_proj:  21%|██        | 7570/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.63.gate_proj:  21%|██        | 7571/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.63.up_proj:  21%|██        | 7572/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.63.down_proj:  21%|██        | 7573/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.64.gate_proj:  21%|██        | 7574/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.64.up_proj:  21%|██        | 7575/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.64.down_proj:  21%|██        | 7576/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.65.gate_proj:  21%|██        | 7577/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.65.up_proj:  21%|██        | 7578/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.65.down_proj:  21%|██        | 7579/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.66.gate_proj:  21%|██        | 7580/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.66.up_proj:  21%|██        | 7581/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.66.down_proj:  21%|██        | 7582/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.67.gate_proj:  21%|██        | 7583/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.67.up_proj:  21%|██        | 7584/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.67.down_proj:  21%|██        | 7585/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.68.gate_proj:  21%|██        | 7586/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.68.up_proj:  21%|██        | 7587/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.68.down_proj:  21%|██        | 7588/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.69.gate_proj:  21%|██        | 7589/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.69.up_proj:  21%|██        | 7590/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.69.down_proj:  21%|██        | 7591/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.70.gate_proj:  21%|██        | 7592/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.70.up_proj:  21%|██        | 7593/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.70.down_proj:  21%|██        | 7594/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.71.gate_proj:  21%|██        | 7595/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.71.up_proj:  21%|██        | 7596/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.71.down_proj:  21%|██        | 7597/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.72.gate_proj:  21%|██        | 7598/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.72.up_proj:  21%|██        | 7599/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.72.down_proj:  21%|██        | 7600/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.73.gate_proj:  21%|██        | 7601/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.73.up_proj:  21%|██        | 7602/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.73.down_proj:  21%|██        | 7603/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.74.gate_proj:  21%|██        | 7604/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.74.up_proj:  21%|██        | 7605/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.74.down_proj:  21%|██        | 7606/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.75.gate_proj:  21%|██        | 7607/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.75.up_proj:  21%|██        | 7608/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.75.down_proj:  21%|██        | 7609/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.76.gate_proj:  21%|██        | 7610/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.76.up_proj:  21%|██        | 7611/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.76.down_proj:  21%|██        | 7612/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.77.gate_proj:  21%|██        | 7613/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.77.up_proj:  21%|██        | 7614/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.77.down_proj:  21%|██        | 7615/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.78.gate_proj:  21%|██        | 7616/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.78.up_proj:  21%|██        | 7617/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.78.down_proj:  21%|██        | 7618/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.79.gate_proj:  21%|██        | 7619/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.79.up_proj:  21%|██        | 7620/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.79.down_proj:  21%|██        | 7621/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.80.gate_proj:  21%|██        | 7622/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.80.up_proj:  21%|██        | 7623/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.80.down_proj:  21%|██        | 7624/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.81.gate_proj:  21%|██        | 7625/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.81.up_proj:  21%|██        | 7626/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.81.down_proj:  21%|██        | 7627/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.82.gate_proj:  21%|██        | 7628/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.82.up_proj:  21%|██        | 7629/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.82.down_proj:  21%|██        | 7630/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.83.gate_proj:  21%|██        | 7631/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.83.up_proj:  21%|██        | 7632/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.83.down_proj:  21%|██        | 7633/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.84.gate_proj:  21%|██        | 7634/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.84.up_proj:  21%|██        | 7635/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.84.down_proj:  21%|██        | 7636/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.85.gate_proj:  21%|██        | 7637/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.85.up_proj:  21%|██        | 7638/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.85.down_proj:  21%|██        | 7639/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.86.gate_proj:  21%|██        | 7640/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.86.up_proj:  21%|██        | 7641/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.86.down_proj:  21%|██        | 7642/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.87.gate_proj:  21%|██        | 7643/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.87.up_proj:  21%|██        | 7644/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.87.down_proj:  21%|██        | 7645/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.88.gate_proj:  21%|██        | 7646/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.88.up_proj:  21%|██        | 7647/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.88.down_proj:  21%|██        | 7648/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.89.gate_proj:  21%|██        | 7649/36566 [00:07<00:25, 1121.61it/s]
packing model.layers.18.mlp.experts.89.up_proj:  21%|██        | 7650/36566 [00:07<00:25, 1121.61it/s]  
packing model.layers.18.mlp.experts.89.up_proj:  21%|██        | 7651/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.89.down_proj:  21%|██        | 7651/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.90.gate_proj:  21%|██        | 7652/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.90.up_proj:  21%|██        | 7653/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.90.down_proj:  21%|██        | 7654/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.91.gate_proj:  21%|██        | 7655/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.91.up_proj:  21%|██        | 7656/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.91.down_proj:  21%|██        | 7657/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.92.gate_proj:  21%|██        | 7658/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.92.up_proj:  21%|██        | 7659/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.92.down_proj:  21%|██        | 7660/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.93.gate_proj:  21%|██        | 7661/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.93.up_proj:  21%|██        | 7662/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.93.down_proj:  21%|██        | 7663/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.94.gate_proj:  21%|██        | 7664/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.94.up_proj:  21%|██        | 7665/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.94.down_proj:  21%|██        | 7666/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.95.gate_proj:  21%|██        | 7667/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.95.up_proj:  21%|██        | 7668/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.95.down_proj:  21%|██        | 7669/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.96.gate_proj:  21%|██        | 7670/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.96.up_proj:  21%|██        | 7671/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.96.down_proj:  21%|██        | 7672/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.97.gate_proj:  21%|██        | 7673/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.97.up_proj:  21%|██        | 7674/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.97.down_proj:  21%|██        | 7675/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.98.gate_proj:  21%|██        | 7676/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.98.up_proj:  21%|██        | 7677/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.98.down_proj:  21%|██        | 7678/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.99.gate_proj:  21%|██        | 7679/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.99.up_proj:  21%|██        | 7680/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.99.down_proj:  21%|██        | 7681/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.100.gate_proj:  21%|██        | 7682/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.100.up_proj:  21%|██        | 7683/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.100.down_proj:  21%|██        | 7684/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.101.gate_proj:  21%|██        | 7685/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.101.up_proj:  21%|██        | 7686/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.101.down_proj:  21%|██        | 7687/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.102.gate_proj:  21%|██        | 7688/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.102.up_proj:  21%|██        | 7689/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.102.down_proj:  21%|██        | 7690/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.103.gate_proj:  21%|██        | 7691/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.103.up_proj:  21%|██        | 7692/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.103.down_proj:  21%|██        | 7693/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.104.gate_proj:  21%|██        | 7694/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.104.up_proj:  21%|██        | 7695/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.104.down_proj:  21%|██        | 7696/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.105.gate_proj:  21%|██        | 7697/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.105.up_proj:  21%|██        | 7698/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.105.down_proj:  21%|██        | 7699/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.106.gate_proj:  21%|██        | 7700/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.106.up_proj:  21%|██        | 7701/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.106.down_proj:  21%|██        | 7702/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.107.gate_proj:  21%|██        | 7703/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.107.up_proj:  21%|██        | 7704/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.107.down_proj:  21%|██        | 7705/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.108.gate_proj:  21%|██        | 7706/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.108.up_proj:  21%|██        | 7707/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.108.down_proj:  21%|██        | 7708/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.109.gate_proj:  21%|██        | 7709/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.109.up_proj:  21%|██        | 7710/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.109.down_proj:  21%|██        | 7711/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.110.gate_proj:  21%|██        | 7712/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.110.up_proj:  21%|██        | 7713/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.110.down_proj:  21%|██        | 7714/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.111.gate_proj:  21%|██        | 7715/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.111.up_proj:  21%|██        | 7716/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.111.down_proj:  21%|██        | 7717/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.112.gate_proj:  21%|██        | 7718/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.112.up_proj:  21%|██        | 7719/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.112.down_proj:  21%|██        | 7720/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.113.gate_proj:  21%|██        | 7721/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.113.up_proj:  21%|██        | 7722/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.113.down_proj:  21%|██        | 7723/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.114.gate_proj:  21%|██        | 7724/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.114.up_proj:  21%|██        | 7725/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.114.down_proj:  21%|██        | 7726/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.115.gate_proj:  21%|██        | 7727/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.115.up_proj:  21%|██        | 7728/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.115.down_proj:  21%|██        | 7729/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.116.gate_proj:  21%|██        | 7730/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.116.up_proj:  21%|██        | 7731/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.116.down_proj:  21%|██        | 7732/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.117.gate_proj:  21%|██        | 7733/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.117.up_proj:  21%|██        | 7734/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.117.down_proj:  21%|██        | 7735/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.118.gate_proj:  21%|██        | 7736/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.118.up_proj:  21%|██        | 7737/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.118.down_proj:  21%|██        | 7738/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.119.gate_proj:  21%|██        | 7739/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.119.up_proj:  21%|██        | 7740/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.119.down_proj:  21%|██        | 7741/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.120.gate_proj:  21%|██        | 7742/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.120.up_proj:  21%|██        | 7743/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.120.down_proj:  21%|██        | 7744/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.121.gate_proj:  21%|██        | 7745/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.121.up_proj:  21%|██        | 7746/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.121.down_proj:  21%|██        | 7747/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.122.gate_proj:  21%|██        | 7748/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.122.up_proj:  21%|██        | 7749/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.122.down_proj:  21%|██        | 7750/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.123.gate_proj:  21%|██        | 7751/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.123.up_proj:  21%|██        | 7752/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.123.down_proj:  21%|██        | 7753/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.124.gate_proj:  21%|██        | 7754/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.124.up_proj:  21%|██        | 7755/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.124.down_proj:  21%|██        | 7756/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.125.gate_proj:  21%|██        | 7757/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.125.up_proj:  21%|██        | 7758/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.125.down_proj:  21%|██        | 7759/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.126.gate_proj:  21%|██        | 7760/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.126.up_proj:  21%|██        | 7761/36566 [00:07<00:25, 1123.05it/s]  
packing model.layers.18.mlp.experts.126.down_proj:  21%|██        | 7762/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.127.gate_proj:  21%|██        | 7763/36566 [00:07<00:25, 1123.05it/s]
packing model.layers.18.mlp.experts.127.gate_proj:  21%|██        | 7764/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.18.mlp.experts.127.up_proj:  21%|██        | 7764/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.18.mlp.experts.127.down_proj:  21%|██        | 7765/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.0.gate_proj:  21%|██        | 7766/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.0.up_proj:  21%|██        | 7767/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.0.down_proj:  21%|██        | 7768/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.1.gate_proj:  21%|██        | 7769/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.1.up_proj:  21%|██        | 7770/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.1.down_proj:  21%|██▏       | 7771/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.2.gate_proj:  21%|██▏       | 7772/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.2.up_proj:  21%|██▏       | 7773/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.2.down_proj:  21%|██▏       | 7774/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.3.gate_proj:  21%|██▏       | 7775/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.3.up_proj:  21%|██▏       | 7776/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.3.down_proj:  21%|██▏       | 7777/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.4.gate_proj:  21%|██▏       | 7778/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.4.up_proj:  21%|██▏       | 7779/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.4.down_proj:  21%|██▏       | 7780/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.5.gate_proj:  21%|██▏       | 7781/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.5.up_proj:  21%|██▏       | 7782/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.5.down_proj:  21%|██▏       | 7783/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.6.gate_proj:  21%|██▏       | 7784/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.6.up_proj:  21%|██▏       | 7785/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.6.down_proj:  21%|██▏       | 7786/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.7.gate_proj:  21%|██▏       | 7787/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.7.up_proj:  21%|██▏       | 7788/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.7.down_proj:  21%|██▏       | 7789/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.8.gate_proj:  21%|██▏       | 7790/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.8.up_proj:  21%|██▏       | 7791/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.8.down_proj:  21%|██▏       | 7792/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.9.gate_proj:  21%|██▏       | 7793/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.9.up_proj:  21%|██▏       | 7794/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.9.down_proj:  21%|██▏       | 7795/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.10.gate_proj:  21%|██▏       | 7796/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.10.up_proj:  21%|██▏       | 7797/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.10.down_proj:  21%|██▏       | 7798/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.11.gate_proj:  21%|██▏       | 7799/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.11.up_proj:  21%|██▏       | 7800/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.11.down_proj:  21%|██▏       | 7801/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.12.gate_proj:  21%|██▏       | 7802/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.12.up_proj:  21%|██▏       | 7803/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.12.down_proj:  21%|██▏       | 7804/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.13.gate_proj:  21%|██▏       | 7805/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.13.up_proj:  21%|██▏       | 7806/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.13.down_proj:  21%|██▏       | 7807/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.14.gate_proj:  21%|██▏       | 7808/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.14.up_proj:  21%|██▏       | 7809/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.14.down_proj:  21%|██▏       | 7810/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.15.gate_proj:  21%|██▏       | 7811/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.15.up_proj:  21%|██▏       | 7812/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.15.down_proj:  21%|██▏       | 7813/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.16.gate_proj:  21%|██▏       | 7814/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.16.up_proj:  21%|██▏       | 7815/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.16.down_proj:  21%|██▏       | 7816/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.17.gate_proj:  21%|██▏       | 7817/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.17.up_proj:  21%|██▏       | 7818/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.17.down_proj:  21%|██▏       | 7819/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.18.gate_proj:  21%|██▏       | 7820/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.18.up_proj:  21%|██▏       | 7821/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.18.down_proj:  21%|██▏       | 7822/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.19.gate_proj:  21%|██▏       | 7823/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.19.up_proj:  21%|██▏       | 7824/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.19.down_proj:  21%|██▏       | 7825/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.20.gate_proj:  21%|██▏       | 7826/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.20.up_proj:  21%|██▏       | 7827/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.20.down_proj:  21%|██▏       | 7828/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.21.gate_proj:  21%|██▏       | 7829/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.21.up_proj:  21%|██▏       | 7830/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.21.down_proj:  21%|██▏       | 7831/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.22.gate_proj:  21%|██▏       | 7832/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.22.up_proj:  21%|██▏       | 7833/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.22.down_proj:  21%|██▏       | 7834/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.23.gate_proj:  21%|██▏       | 7835/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.23.up_proj:  21%|██▏       | 7836/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.23.down_proj:  21%|██▏       | 7837/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.24.gate_proj:  21%|██▏       | 7838/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.24.up_proj:  21%|██▏       | 7839/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.24.down_proj:  21%|██▏       | 7840/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.25.gate_proj:  21%|██▏       | 7841/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.25.up_proj:  21%|██▏       | 7842/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.25.down_proj:  21%|██▏       | 7843/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.26.gate_proj:  21%|██▏       | 7844/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.26.up_proj:  21%|██▏       | 7845/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.26.down_proj:  21%|██▏       | 7846/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.27.gate_proj:  21%|██▏       | 7847/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.27.up_proj:  21%|██▏       | 7848/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.27.down_proj:  21%|██▏       | 7849/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.28.gate_proj:  21%|██▏       | 7850/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.28.up_proj:  21%|██▏       | 7851/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.28.down_proj:  21%|██▏       | 7852/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.29.gate_proj:  21%|██▏       | 7853/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.29.up_proj:  21%|██▏       | 7854/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.29.down_proj:  21%|██▏       | 7855/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.30.gate_proj:  21%|██▏       | 7856/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.30.up_proj:  21%|██▏       | 7857/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.30.down_proj:  21%|██▏       | 7858/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.31.gate_proj:  21%|██▏       | 7859/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.31.up_proj:  21%|██▏       | 7860/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.31.down_proj:  21%|██▏       | 7861/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.32.gate_proj:  22%|██▏       | 7862/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.32.up_proj:  22%|██▏       | 7863/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.32.down_proj:  22%|██▏       | 7864/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.33.gate_proj:  22%|██▏       | 7865/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.33.up_proj:  22%|██▏       | 7866/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.33.down_proj:  22%|██▏       | 7867/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.34.gate_proj:  22%|██▏       | 7868/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.34.up_proj:  22%|██▏       | 7869/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.34.down_proj:  22%|██▏       | 7870/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.35.gate_proj:  22%|██▏       | 7871/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.35.up_proj:  22%|██▏       | 7872/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.35.down_proj:  22%|██▏       | 7873/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.36.gate_proj:  22%|██▏       | 7874/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.36.up_proj:  22%|██▏       | 7875/36566 [00:07<00:25, 1121.98it/s]  
packing model.layers.19.mlp.experts.36.down_proj:  22%|██▏       | 7876/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.37.gate_proj:  22%|██▏       | 7877/36566 [00:07<00:25, 1121.98it/s]
packing model.layers.19.mlp.experts.37.gate_proj:  22%|██▏       | 7878/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.37.up_proj:  22%|██▏       | 7878/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.37.down_proj:  22%|██▏       | 7879/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.38.gate_proj:  22%|██▏       | 7880/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.38.up_proj:  22%|██▏       | 7881/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.38.down_proj:  22%|██▏       | 7882/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.39.gate_proj:  22%|██▏       | 7883/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.39.up_proj:  22%|██▏       | 7884/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.39.down_proj:  22%|██▏       | 7885/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.40.gate_proj:  22%|██▏       | 7886/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.40.up_proj:  22%|██▏       | 7887/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.40.down_proj:  22%|██▏       | 7888/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.41.gate_proj:  22%|██▏       | 7889/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.41.up_proj:  22%|██▏       | 7890/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.41.down_proj:  22%|██▏       | 7891/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.42.gate_proj:  22%|██▏       | 7892/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.42.up_proj:  22%|██▏       | 7893/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.42.down_proj:  22%|██▏       | 7894/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.43.gate_proj:  22%|██▏       | 7895/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.43.up_proj:  22%|██▏       | 7896/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.43.down_proj:  22%|██▏       | 7897/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.44.gate_proj:  22%|██▏       | 7898/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.44.up_proj:  22%|██▏       | 7899/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.44.down_proj:  22%|██▏       | 7900/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.45.gate_proj:  22%|██▏       | 7901/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.45.up_proj:  22%|██▏       | 7902/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.45.down_proj:  22%|██▏       | 7903/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.46.gate_proj:  22%|██▏       | 7904/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.46.up_proj:  22%|██▏       | 7905/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.46.down_proj:  22%|██▏       | 7906/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.47.gate_proj:  22%|██▏       | 7907/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.47.up_proj:  22%|██▏       | 7908/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.47.down_proj:  22%|██▏       | 7909/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.48.gate_proj:  22%|██▏       | 7910/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.48.up_proj:  22%|██▏       | 7911/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.48.down_proj:  22%|██▏       | 7912/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.49.gate_proj:  22%|██▏       | 7913/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.49.up_proj:  22%|██▏       | 7914/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.49.down_proj:  22%|██▏       | 7915/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.50.gate_proj:  22%|██▏       | 7916/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.50.up_proj:  22%|██▏       | 7917/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.50.down_proj:  22%|██▏       | 7918/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.51.gate_proj:  22%|██▏       | 7919/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.51.up_proj:  22%|██▏       | 7920/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.51.down_proj:  22%|██▏       | 7921/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.52.gate_proj:  22%|██▏       | 7922/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.52.up_proj:  22%|██▏       | 7923/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.52.down_proj:  22%|██▏       | 7924/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.53.gate_proj:  22%|██▏       | 7925/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.53.up_proj:  22%|██▏       | 7926/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.53.down_proj:  22%|██▏       | 7927/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.54.gate_proj:  22%|██▏       | 7928/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.54.up_proj:  22%|██▏       | 7929/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.54.down_proj:  22%|██▏       | 7930/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.55.gate_proj:  22%|██▏       | 7931/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.55.up_proj:  22%|██▏       | 7932/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.55.down_proj:  22%|██▏       | 7933/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.56.gate_proj:  22%|██▏       | 7934/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.56.up_proj:  22%|██▏       | 7935/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.56.down_proj:  22%|██▏       | 7936/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.57.gate_proj:  22%|██▏       | 7937/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.57.up_proj:  22%|██▏       | 7938/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.57.down_proj:  22%|██▏       | 7939/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.58.gate_proj:  22%|██▏       | 7940/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.58.up_proj:  22%|██▏       | 7941/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.58.down_proj:  22%|██▏       | 7942/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.59.gate_proj:  22%|██▏       | 7943/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.59.up_proj:  22%|██▏       | 7944/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.59.down_proj:  22%|██▏       | 7945/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.60.gate_proj:  22%|██▏       | 7946/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.60.up_proj:  22%|██▏       | 7947/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.60.down_proj:  22%|██▏       | 7948/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.61.gate_proj:  22%|██▏       | 7949/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.61.up_proj:  22%|██▏       | 7950/36566 [00:07<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.61.down_proj:  22%|██▏       | 7951/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.62.gate_proj:  22%|██▏       | 7952/36566 [00:07<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.62.up_proj:  22%|██▏       | 7953/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.62.down_proj:  22%|██▏       | 7954/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.63.gate_proj:  22%|██▏       | 7955/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.63.up_proj:  22%|██▏       | 7956/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.63.down_proj:  22%|██▏       | 7957/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.64.gate_proj:  22%|██▏       | 7958/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.64.up_proj:  22%|██▏       | 7959/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.64.down_proj:  22%|██▏       | 7960/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.65.gate_proj:  22%|██▏       | 7961/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.65.up_proj:  22%|██▏       | 7962/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.65.down_proj:  22%|██▏       | 7963/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.66.gate_proj:  22%|██▏       | 7964/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.66.up_proj:  22%|██▏       | 7965/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.66.down_proj:  22%|██▏       | 7966/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.67.gate_proj:  22%|██▏       | 7967/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.67.up_proj:  22%|██▏       | 7968/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.67.down_proj:  22%|██▏       | 7969/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.68.gate_proj:  22%|██▏       | 7970/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.68.up_proj:  22%|██▏       | 7971/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.68.down_proj:  22%|██▏       | 7972/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.69.gate_proj:  22%|██▏       | 7973/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.69.up_proj:  22%|██▏       | 7974/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.69.down_proj:  22%|██▏       | 7975/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.70.gate_proj:  22%|██▏       | 7976/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.70.up_proj:  22%|██▏       | 7977/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.70.down_proj:  22%|██▏       | 7978/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.71.gate_proj:  22%|██▏       | 7979/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.71.up_proj:  22%|██▏       | 7980/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.71.down_proj:  22%|██▏       | 7981/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.72.gate_proj:  22%|██▏       | 7982/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.72.up_proj:  22%|██▏       | 7983/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.72.down_proj:  22%|██▏       | 7984/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.73.gate_proj:  22%|██▏       | 7985/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.73.up_proj:  22%|██▏       | 7986/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.73.down_proj:  22%|██▏       | 7987/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.74.gate_proj:  22%|██▏       | 7988/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.74.up_proj:  22%|██▏       | 7989/36566 [00:08<00:25, 1124.96it/s]  
packing model.layers.19.mlp.experts.74.down_proj:  22%|██▏       | 7990/36566 [00:08<00:25, 1124.96it/s]
packing model.layers.19.mlp.experts.74.down_proj:  22%|██▏       | 7991/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.75.gate_proj:  22%|██▏       | 7991/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.75.up_proj:  22%|██▏       | 7992/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.75.down_proj:  22%|██▏       | 7993/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.76.gate_proj:  22%|██▏       | 7994/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.76.up_proj:  22%|██▏       | 7995/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.76.down_proj:  22%|██▏       | 7996/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.77.gate_proj:  22%|██▏       | 7997/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.77.up_proj:  22%|██▏       | 7998/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.77.down_proj:  22%|██▏       | 7999/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.78.gate_proj:  22%|██▏       | 8000/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.78.up_proj:  22%|██▏       | 8001/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.78.down_proj:  22%|██▏       | 8002/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.79.gate_proj:  22%|██▏       | 8003/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.79.up_proj:  22%|██▏       | 8004/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.79.down_proj:  22%|██▏       | 8005/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.80.gate_proj:  22%|██▏       | 8006/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.80.up_proj:  22%|██▏       | 8007/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.80.down_proj:  22%|██▏       | 8008/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.81.gate_proj:  22%|██▏       | 8009/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.81.up_proj:  22%|██▏       | 8010/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.81.down_proj:  22%|██▏       | 8011/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.82.gate_proj:  22%|██▏       | 8012/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.82.up_proj:  22%|██▏       | 8013/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.82.down_proj:  22%|██▏       | 8014/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.83.gate_proj:  22%|██▏       | 8015/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.83.up_proj:  22%|██▏       | 8016/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.83.down_proj:  22%|██▏       | 8017/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.84.gate_proj:  22%|██▏       | 8018/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.84.up_proj:  22%|██▏       | 8019/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.84.down_proj:  22%|██▏       | 8020/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.85.gate_proj:  22%|██▏       | 8021/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.85.up_proj:  22%|██▏       | 8022/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.85.down_proj:  22%|██▏       | 8023/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.86.gate_proj:  22%|██▏       | 8024/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.86.up_proj:  22%|██▏       | 8025/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.86.down_proj:  22%|██▏       | 8026/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.87.gate_proj:  22%|██▏       | 8027/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.87.up_proj:  22%|██▏       | 8028/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.87.down_proj:  22%|██▏       | 8029/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.88.gate_proj:  22%|██▏       | 8030/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.88.up_proj:  22%|██▏       | 8031/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.88.down_proj:  22%|██▏       | 8032/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.89.gate_proj:  22%|██▏       | 8033/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.89.up_proj:  22%|██▏       | 8034/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.89.down_proj:  22%|██▏       | 8035/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.90.gate_proj:  22%|██▏       | 8036/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.90.up_proj:  22%|██▏       | 8037/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.90.down_proj:  22%|██▏       | 8038/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.91.gate_proj:  22%|██▏       | 8039/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.91.up_proj:  22%|██▏       | 8040/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.91.down_proj:  22%|██▏       | 8041/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.92.gate_proj:  22%|██▏       | 8042/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.92.up_proj:  22%|██▏       | 8043/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.92.down_proj:  22%|██▏       | 8044/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.93.gate_proj:  22%|██▏       | 8045/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.93.up_proj:  22%|██▏       | 8046/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.93.down_proj:  22%|██▏       | 8047/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.94.gate_proj:  22%|██▏       | 8048/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.94.up_proj:  22%|██▏       | 8049/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.94.down_proj:  22%|██▏       | 8050/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.95.gate_proj:  22%|██▏       | 8051/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.95.up_proj:  22%|██▏       | 8052/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.95.down_proj:  22%|██▏       | 8053/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.96.gate_proj:  22%|██▏       | 8054/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.96.up_proj:  22%|██▏       | 8055/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.96.down_proj:  22%|██▏       | 8056/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.97.gate_proj:  22%|██▏       | 8057/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.97.up_proj:  22%|██▏       | 8058/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.97.down_proj:  22%|██▏       | 8059/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.98.gate_proj:  22%|██▏       | 8060/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.98.up_proj:  22%|██▏       | 8061/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.98.down_proj:  22%|██▏       | 8062/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.99.gate_proj:  22%|██▏       | 8063/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.99.up_proj:  22%|██▏       | 8064/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.99.down_proj:  22%|██▏       | 8065/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.100.gate_proj:  22%|██▏       | 8066/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.100.up_proj:  22%|██▏       | 8067/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.100.down_proj:  22%|██▏       | 8068/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.101.gate_proj:  22%|██▏       | 8069/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.101.up_proj:  22%|██▏       | 8070/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.101.down_proj:  22%|██▏       | 8071/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.102.gate_proj:  22%|██▏       | 8072/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.102.up_proj:  22%|██▏       | 8073/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.102.down_proj:  22%|██▏       | 8074/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.103.gate_proj:  22%|██▏       | 8075/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.103.up_proj:  22%|██▏       | 8076/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.103.down_proj:  22%|██▏       | 8077/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.104.gate_proj:  22%|██▏       | 8078/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.104.up_proj:  22%|██▏       | 8079/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.104.down_proj:  22%|██▏       | 8080/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.105.gate_proj:  22%|██▏       | 8081/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.105.up_proj:  22%|██▏       | 8082/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.105.down_proj:  22%|██▏       | 8083/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.106.gate_proj:  22%|██▏       | 8084/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.106.up_proj:  22%|██▏       | 8085/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.106.down_proj:  22%|██▏       | 8086/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.107.gate_proj:  22%|██▏       | 8087/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.107.up_proj:  22%|██▏       | 8088/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.107.down_proj:  22%|██▏       | 8089/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.108.gate_proj:  22%|██▏       | 8090/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.108.up_proj:  22%|██▏       | 8091/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.108.down_proj:  22%|██▏       | 8092/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.109.gate_proj:  22%|██▏       | 8093/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.109.up_proj:  22%|██▏       | 8094/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.109.down_proj:  22%|██▏       | 8095/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.110.gate_proj:  22%|██▏       | 8096/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.110.up_proj:  22%|██▏       | 8097/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.110.down_proj:  22%|██▏       | 8098/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.111.gate_proj:  22%|██▏       | 8099/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.111.up_proj:  22%|██▏       | 8100/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.111.down_proj:  22%|██▏       | 8101/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.112.gate_proj:  22%|██▏       | 8102/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.112.up_proj:  22%|██▏       | 8103/36566 [00:08<00:25, 1125.25it/s]  
packing model.layers.19.mlp.experts.112.down_proj:  22%|██▏       | 8104/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.113.gate_proj:  22%|██▏       | 8105/36566 [00:08<00:25, 1125.25it/s]
packing model.layers.19.mlp.experts.113.gate_proj:  22%|██▏       | 8106/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.113.up_proj:  22%|██▏       | 8106/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.113.down_proj:  22%|██▏       | 8107/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.114.gate_proj:  22%|██▏       | 8108/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.114.up_proj:  22%|██▏       | 8109/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.114.down_proj:  22%|██▏       | 8110/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.115.gate_proj:  22%|██▏       | 8111/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.115.up_proj:  22%|██▏       | 8112/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.115.down_proj:  22%|██▏       | 8113/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.116.gate_proj:  22%|██▏       | 8114/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.116.up_proj:  22%|██▏       | 8115/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.116.down_proj:  22%|██▏       | 8116/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.117.gate_proj:  22%|██▏       | 8117/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.117.up_proj:  22%|██▏       | 8118/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.117.down_proj:  22%|██▏       | 8119/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.118.gate_proj:  22%|██▏       | 8120/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.118.up_proj:  22%|██▏       | 8121/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.118.down_proj:  22%|██▏       | 8122/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.119.gate_proj:  22%|██▏       | 8123/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.119.up_proj:  22%|██▏       | 8124/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.119.down_proj:  22%|██▏       | 8125/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.120.gate_proj:  22%|██▏       | 8126/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.120.up_proj:  22%|██▏       | 8127/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.120.down_proj:  22%|██▏       | 8128/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.121.gate_proj:  22%|██▏       | 8129/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.121.up_proj:  22%|██▏       | 8130/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.121.down_proj:  22%|██▏       | 8131/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.122.gate_proj:  22%|██▏       | 8132/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.122.up_proj:  22%|██▏       | 8133/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.122.down_proj:  22%|██▏       | 8134/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.123.gate_proj:  22%|██▏       | 8135/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.123.up_proj:  22%|██▏       | 8136/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.123.down_proj:  22%|██▏       | 8137/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.124.gate_proj:  22%|██▏       | 8138/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.124.up_proj:  22%|██▏       | 8139/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.124.down_proj:  22%|██▏       | 8140/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.125.gate_proj:  22%|██▏       | 8141/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.125.up_proj:  22%|██▏       | 8142/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.125.down_proj:  22%|██▏       | 8143/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.126.gate_proj:  22%|██▏       | 8144/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.126.up_proj:  22%|██▏       | 8145/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.126.down_proj:  22%|██▏       | 8146/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.127.gate_proj:  22%|██▏       | 8147/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.19.mlp.experts.127.up_proj:  22%|██▏       | 8148/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.19.mlp.experts.127.down_proj:  22%|██▏       | 8149/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.0.gate_proj:  22%|██▏       | 8150/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.0.up_proj:  22%|██▏       | 8151/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.0.down_proj:  22%|██▏       | 8152/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.1.gate_proj:  22%|██▏       | 8153/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.1.up_proj:  22%|██▏       | 8154/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.1.down_proj:  22%|██▏       | 8155/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.2.gate_proj:  22%|██▏       | 8156/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.2.up_proj:  22%|██▏       | 8157/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.2.down_proj:  22%|██▏       | 8158/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.3.gate_proj:  22%|██▏       | 8159/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.3.up_proj:  22%|██▏       | 8160/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.3.down_proj:  22%|██▏       | 8161/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.4.gate_proj:  22%|██▏       | 8162/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.4.up_proj:  22%|██▏       | 8163/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.4.down_proj:  22%|██▏       | 8164/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.5.gate_proj:  22%|██▏       | 8165/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.5.up_proj:  22%|██▏       | 8166/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.5.down_proj:  22%|██▏       | 8167/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.6.gate_proj:  22%|██▏       | 8168/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.6.up_proj:  22%|██▏       | 8169/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.6.down_proj:  22%|██▏       | 8170/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.7.gate_proj:  22%|██▏       | 8171/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.7.up_proj:  22%|██▏       | 8172/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.7.down_proj:  22%|██▏       | 8173/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.8.gate_proj:  22%|██▏       | 8174/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.8.up_proj:  22%|██▏       | 8175/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.8.down_proj:  22%|██▏       | 8176/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.9.gate_proj:  22%|██▏       | 8177/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.9.up_proj:  22%|██▏       | 8178/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.9.down_proj:  22%|██▏       | 8179/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.10.gate_proj:  22%|██▏       | 8180/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.10.up_proj:  22%|██▏       | 8181/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.10.down_proj:  22%|██▏       | 8182/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.11.gate_proj:  22%|██▏       | 8183/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.11.up_proj:  22%|██▏       | 8184/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.11.down_proj:  22%|██▏       | 8185/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.12.gate_proj:  22%|██▏       | 8186/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.12.up_proj:  22%|██▏       | 8187/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.12.down_proj:  22%|██▏       | 8188/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.13.gate_proj:  22%|██▏       | 8189/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.13.up_proj:  22%|██▏       | 8190/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.13.down_proj:  22%|██▏       | 8191/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.14.gate_proj:  22%|██▏       | 8192/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.14.up_proj:  22%|██▏       | 8193/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.14.down_proj:  22%|██▏       | 8194/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.15.gate_proj:  22%|██▏       | 8195/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.15.up_proj:  22%|██▏       | 8196/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.15.down_proj:  22%|██▏       | 8197/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.16.gate_proj:  22%|██▏       | 8198/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.16.up_proj:  22%|██▏       | 8199/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.16.down_proj:  22%|██▏       | 8200/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.17.gate_proj:  22%|██▏       | 8201/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.17.up_proj:  22%|██▏       | 8202/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.17.down_proj:  22%|██▏       | 8203/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.18.gate_proj:  22%|██▏       | 8204/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.18.up_proj:  22%|██▏       | 8205/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.18.down_proj:  22%|██▏       | 8206/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.19.gate_proj:  22%|██▏       | 8207/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.19.up_proj:  22%|██▏       | 8208/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.19.down_proj:  22%|██▏       | 8209/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.20.gate_proj:  22%|██▏       | 8210/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.20.up_proj:  22%|██▏       | 8211/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.20.down_proj:  22%|██▏       | 8212/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.21.gate_proj:  22%|██▏       | 8213/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.21.up_proj:  22%|██▏       | 8214/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.21.down_proj:  22%|██▏       | 8215/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.22.gate_proj:  22%|██▏       | 8216/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.22.up_proj:  22%|██▏       | 8217/36566 [00:08<00:25, 1130.62it/s]  
packing model.layers.20.mlp.experts.22.down_proj:  22%|██▏       | 8218/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.23.gate_proj:  22%|██▏       | 8219/36566 [00:08<00:25, 1130.62it/s]
packing model.layers.20.mlp.experts.23.gate_proj:  22%|██▏       | 8220/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.23.up_proj:  22%|██▏       | 8220/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.23.down_proj:  22%|██▏       | 8221/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.24.gate_proj:  22%|██▏       | 8222/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.24.up_proj:  22%|██▏       | 8223/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.24.down_proj:  22%|██▏       | 8224/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.25.gate_proj:  22%|██▏       | 8225/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.25.up_proj:  22%|██▏       | 8226/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.25.down_proj:  22%|██▏       | 8227/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.26.gate_proj:  23%|██▎       | 8228/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.26.up_proj:  23%|██▎       | 8229/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.26.down_proj:  23%|██▎       | 8230/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.27.gate_proj:  23%|██▎       | 8231/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.27.up_proj:  23%|██▎       | 8232/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.27.down_proj:  23%|██▎       | 8233/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.28.gate_proj:  23%|██▎       | 8234/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.28.up_proj:  23%|██▎       | 8235/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.28.down_proj:  23%|██▎       | 8236/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.29.gate_proj:  23%|██▎       | 8237/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.29.up_proj:  23%|██▎       | 8238/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.29.down_proj:  23%|██▎       | 8239/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.30.gate_proj:  23%|██▎       | 8240/36566 [00:08<00:25, 1132.97it/s]
packing model.layers.20.mlp.experts.30.up_proj:  23%|██▎       | 8241/36566 [00:08<00:25, 1132.97it/s]  
packing model.layers.20.mlp.experts.30.down_proj:  23%|██▎       | 8242/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.31.gate_proj:  23%|██▎       | 8243/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.31.up_proj:  23%|██▎       | 8244/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.31.down_proj:  23%|██▎       | 8245/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.32.gate_proj:  23%|██▎       | 8246/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.32.up_proj:  23%|██▎       | 8247/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.32.down_proj:  23%|██▎       | 8248/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.33.gate_proj:  23%|██▎       | 8249/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.33.up_proj:  23%|██▎       | 8250/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.33.down_proj:  23%|██▎       | 8251/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.34.gate_proj:  23%|██▎       | 8252/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.34.up_proj:  23%|██▎       | 8253/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.34.down_proj:  23%|██▎       | 8254/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.35.gate_proj:  23%|██▎       | 8255/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.35.up_proj:  23%|██▎       | 8256/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.35.down_proj:  23%|██▎       | 8257/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.36.gate_proj:  23%|██▎       | 8258/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.36.up_proj:  23%|██▎       | 8259/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.36.down_proj:  23%|██▎       | 8260/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.37.gate_proj:  23%|██▎       | 8261/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.37.up_proj:  23%|██▎       | 8262/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.37.down_proj:  23%|██▎       | 8263/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.38.gate_proj:  23%|██▎       | 8264/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.38.up_proj:  23%|██▎       | 8265/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.38.down_proj:  23%|██▎       | 8266/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.39.gate_proj:  23%|██▎       | 8267/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.39.up_proj:  23%|██▎       | 8268/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.39.down_proj:  23%|██▎       | 8269/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.40.gate_proj:  23%|██▎       | 8270/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.40.up_proj:  23%|██▎       | 8271/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.40.down_proj:  23%|██▎       | 8272/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.41.gate_proj:  23%|██▎       | 8273/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.41.up_proj:  23%|██▎       | 8274/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.41.down_proj:  23%|██▎       | 8275/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.42.gate_proj:  23%|██▎       | 8276/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.42.up_proj:  23%|██▎       | 8277/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.42.down_proj:  23%|██▎       | 8278/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.43.gate_proj:  23%|██▎       | 8279/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.43.up_proj:  23%|██▎       | 8280/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.43.down_proj:  23%|██▎       | 8281/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.44.gate_proj:  23%|██▎       | 8282/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.44.up_proj:  23%|██▎       | 8283/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.44.down_proj:  23%|██▎       | 8284/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.45.gate_proj:  23%|██▎       | 8285/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.45.up_proj:  23%|██▎       | 8286/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.45.down_proj:  23%|██▎       | 8287/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.46.gate_proj:  23%|██▎       | 8288/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.46.up_proj:  23%|██▎       | 8289/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.46.down_proj:  23%|██▎       | 8290/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.47.gate_proj:  23%|██▎       | 8291/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.47.up_proj:  23%|██▎       | 8292/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.47.down_proj:  23%|██▎       | 8293/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.48.gate_proj:  23%|██▎       | 8294/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.48.up_proj:  23%|██▎       | 8295/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.48.down_proj:  23%|██▎       | 8296/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.49.gate_proj:  23%|██▎       | 8297/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.49.up_proj:  23%|██▎       | 8298/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.49.down_proj:  23%|██▎       | 8299/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.50.gate_proj:  23%|██▎       | 8300/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.50.up_proj:  23%|██▎       | 8301/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.50.down_proj:  23%|██▎       | 8302/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.51.gate_proj:  23%|██▎       | 8303/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.51.up_proj:  23%|██▎       | 8304/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.51.down_proj:  23%|██▎       | 8305/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.52.gate_proj:  23%|██▎       | 8306/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.52.up_proj:  23%|██▎       | 8307/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.52.down_proj:  23%|██▎       | 8308/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.53.gate_proj:  23%|██▎       | 8309/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.53.up_proj:  23%|██▎       | 8310/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.53.down_proj:  23%|██▎       | 8311/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.54.gate_proj:  23%|██▎       | 8312/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.54.up_proj:  23%|██▎       | 8313/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.54.down_proj:  23%|██▎       | 8314/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.55.gate_proj:  23%|██▎       | 8315/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.55.up_proj:  23%|██▎       | 8316/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.55.down_proj:  23%|██▎       | 8317/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.56.gate_proj:  23%|██▎       | 8318/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.56.up_proj:  23%|██▎       | 8319/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.56.down_proj:  23%|██▎       | 8320/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.57.gate_proj:  23%|██▎       | 8321/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.57.up_proj:  23%|██▎       | 8322/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.57.down_proj:  23%|██▎       | 8323/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.58.gate_proj:  23%|██▎       | 8324/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.58.up_proj:  23%|██▎       | 8325/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.58.down_proj:  23%|██▎       | 8326/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.59.gate_proj:  23%|██▎       | 8327/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.59.up_proj:  23%|██▎       | 8328/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.59.down_proj:  23%|██▎       | 8329/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.60.gate_proj:  23%|██▎       | 8330/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.60.up_proj:  23%|██▎       | 8331/36566 [00:08<00:24, 1132.97it/s]  
packing model.layers.20.mlp.experts.60.down_proj:  23%|██▎       | 8332/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.61.gate_proj:  23%|██▎       | 8333/36566 [00:08<00:24, 1132.97it/s]
packing model.layers.20.mlp.experts.61.gate_proj:  23%|██▎       | 8334/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.61.up_proj:  23%|██▎       | 8334/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.61.down_proj:  23%|██▎       | 8335/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.62.gate_proj:  23%|██▎       | 8336/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.62.up_proj:  23%|██▎       | 8337/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.62.down_proj:  23%|██▎       | 8338/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.63.gate_proj:  23%|██▎       | 8339/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.63.up_proj:  23%|██▎       | 8340/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.63.down_proj:  23%|██▎       | 8341/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.64.gate_proj:  23%|██▎       | 8342/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.64.up_proj:  23%|██▎       | 8343/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.64.down_proj:  23%|██▎       | 8344/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.65.gate_proj:  23%|██▎       | 8345/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.65.up_proj:  23%|██▎       | 8346/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.65.down_proj:  23%|██▎       | 8347/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.66.gate_proj:  23%|██▎       | 8348/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.66.up_proj:  23%|██▎       | 8349/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.66.down_proj:  23%|██▎       | 8350/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.67.gate_proj:  23%|██▎       | 8351/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.67.up_proj:  23%|██▎       | 8352/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.67.down_proj:  23%|██▎       | 8353/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.68.gate_proj:  23%|██▎       | 8354/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.68.up_proj:  23%|██▎       | 8355/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.68.down_proj:  23%|██▎       | 8356/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.69.gate_proj:  23%|██▎       | 8357/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.69.up_proj:  23%|██▎       | 8358/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.69.down_proj:  23%|██▎       | 8359/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.70.gate_proj:  23%|██▎       | 8360/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.70.up_proj:  23%|██▎       | 8361/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.70.down_proj:  23%|██▎       | 8362/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.71.gate_proj:  23%|██▎       | 8363/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.71.up_proj:  23%|██▎       | 8364/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.71.down_proj:  23%|██▎       | 8365/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.72.gate_proj:  23%|██▎       | 8366/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.72.up_proj:  23%|██▎       | 8367/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.72.down_proj:  23%|██▎       | 8368/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.73.gate_proj:  23%|██▎       | 8369/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.73.up_proj:  23%|██▎       | 8370/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.73.down_proj:  23%|██▎       | 8371/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.74.gate_proj:  23%|██▎       | 8372/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.74.up_proj:  23%|██▎       | 8373/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.74.down_proj:  23%|██▎       | 8374/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.75.gate_proj:  23%|██▎       | 8375/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.75.up_proj:  23%|██▎       | 8376/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.75.down_proj:  23%|██▎       | 8377/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.76.gate_proj:  23%|██▎       | 8378/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.76.up_proj:  23%|██▎       | 8379/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.76.down_proj:  23%|██▎       | 8380/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.77.gate_proj:  23%|██▎       | 8381/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.77.up_proj:  23%|██▎       | 8382/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.77.down_proj:  23%|██▎       | 8383/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.78.gate_proj:  23%|██▎       | 8384/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.78.up_proj:  23%|██▎       | 8385/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.78.down_proj:  23%|██▎       | 8386/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.79.gate_proj:  23%|██▎       | 8387/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.79.up_proj:  23%|██▎       | 8388/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.79.down_proj:  23%|██▎       | 8389/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.80.gate_proj:  23%|██▎       | 8390/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.80.up_proj:  23%|██▎       | 8391/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.80.down_proj:  23%|██▎       | 8392/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.81.gate_proj:  23%|██▎       | 8393/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.81.up_proj:  23%|██▎       | 8394/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.81.down_proj:  23%|██▎       | 8395/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.82.gate_proj:  23%|██▎       | 8396/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.82.up_proj:  23%|██▎       | 8397/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.82.down_proj:  23%|██▎       | 8398/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.83.gate_proj:  23%|██▎       | 8399/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.83.up_proj:  23%|██▎       | 8400/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.83.down_proj:  23%|██▎       | 8401/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.84.gate_proj:  23%|██▎       | 8402/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.84.up_proj:  23%|██▎       | 8403/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.84.down_proj:  23%|██▎       | 8404/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.85.gate_proj:  23%|██▎       | 8405/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.85.up_proj:  23%|██▎       | 8406/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.85.down_proj:  23%|██▎       | 8407/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.86.gate_proj:  23%|██▎       | 8408/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.86.up_proj:  23%|██▎       | 8409/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.86.down_proj:  23%|██▎       | 8410/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.87.gate_proj:  23%|██▎       | 8411/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.87.up_proj:  23%|██▎       | 8412/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.87.down_proj:  23%|██▎       | 8413/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.88.gate_proj:  23%|██▎       | 8414/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.88.up_proj:  23%|██▎       | 8415/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.88.down_proj:  23%|██▎       | 8416/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.89.gate_proj:  23%|██▎       | 8417/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.89.up_proj:  23%|██▎       | 8418/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.89.down_proj:  23%|██▎       | 8419/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.90.gate_proj:  23%|██▎       | 8420/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.90.up_proj:  23%|██▎       | 8421/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.90.down_proj:  23%|██▎       | 8422/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.91.gate_proj:  23%|██▎       | 8423/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.91.up_proj:  23%|██▎       | 8424/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.91.down_proj:  23%|██▎       | 8425/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.92.gate_proj:  23%|██▎       | 8426/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.92.up_proj:  23%|██▎       | 8427/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.92.down_proj:  23%|██▎       | 8428/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.93.gate_proj:  23%|██▎       | 8429/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.93.up_proj:  23%|██▎       | 8430/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.93.down_proj:  23%|██▎       | 8431/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.94.gate_proj:  23%|██▎       | 8432/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.94.up_proj:  23%|██▎       | 8433/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.94.down_proj:  23%|██▎       | 8434/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.95.gate_proj:  23%|██▎       | 8435/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.95.up_proj:  23%|██▎       | 8436/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.95.down_proj:  23%|██▎       | 8437/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.96.gate_proj:  23%|██▎       | 8438/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.96.up_proj:  23%|██▎       | 8439/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.96.down_proj:  23%|██▎       | 8440/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.97.gate_proj:  23%|██▎       | 8441/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.97.up_proj:  23%|██▎       | 8442/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.97.down_proj:  23%|██▎       | 8443/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.98.gate_proj:  23%|██▎       | 8444/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.98.up_proj:  23%|██▎       | 8445/36566 [00:08<00:24, 1132.94it/s]  
packing model.layers.20.mlp.experts.98.down_proj:  23%|██▎       | 8446/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.99.gate_proj:  23%|██▎       | 8447/36566 [00:08<00:24, 1132.94it/s]
packing model.layers.20.mlp.experts.99.gate_proj:  23%|██▎       | 8448/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.99.up_proj:  23%|██▎       | 8448/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.99.down_proj:  23%|██▎       | 8449/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.100.gate_proj:  23%|██▎       | 8450/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.100.up_proj:  23%|██▎       | 8451/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.100.down_proj:  23%|██▎       | 8452/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.101.gate_proj:  23%|██▎       | 8453/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.101.up_proj:  23%|██▎       | 8454/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.101.down_proj:  23%|██▎       | 8455/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.102.gate_proj:  23%|██▎       | 8456/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.102.up_proj:  23%|██▎       | 8457/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.102.down_proj:  23%|██▎       | 8458/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.103.gate_proj:  23%|██▎       | 8459/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.103.up_proj:  23%|██▎       | 8460/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.103.down_proj:  23%|██▎       | 8461/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.104.gate_proj:  23%|██▎       | 8462/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.104.up_proj:  23%|██▎       | 8463/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.104.down_proj:  23%|██▎       | 8464/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.105.gate_proj:  23%|██▎       | 8465/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.105.up_proj:  23%|██▎       | 8466/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.105.down_proj:  23%|██▎       | 8467/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.106.gate_proj:  23%|██▎       | 8468/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.106.up_proj:  23%|██▎       | 8469/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.106.down_proj:  23%|██▎       | 8470/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.107.gate_proj:  23%|██▎       | 8471/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.107.up_proj:  23%|██▎       | 8472/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.107.down_proj:  23%|██▎       | 8473/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.108.gate_proj:  23%|██▎       | 8474/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.108.up_proj:  23%|██▎       | 8475/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.108.down_proj:  23%|██▎       | 8476/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.109.gate_proj:  23%|██▎       | 8477/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.109.up_proj:  23%|██▎       | 8478/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.109.down_proj:  23%|██▎       | 8479/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.110.gate_proj:  23%|██▎       | 8480/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.110.up_proj:  23%|██▎       | 8481/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.110.down_proj:  23%|██▎       | 8482/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.111.gate_proj:  23%|██▎       | 8483/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.111.up_proj:  23%|██▎       | 8484/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.111.down_proj:  23%|██▎       | 8485/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.112.gate_proj:  23%|██▎       | 8486/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.112.up_proj:  23%|██▎       | 8487/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.112.down_proj:  23%|██▎       | 8488/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.113.gate_proj:  23%|██▎       | 8489/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.113.up_proj:  23%|██▎       | 8490/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.113.down_proj:  23%|██▎       | 8491/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.114.gate_proj:  23%|██▎       | 8492/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.114.up_proj:  23%|██▎       | 8493/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.114.down_proj:  23%|██▎       | 8494/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.115.gate_proj:  23%|██▎       | 8495/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.115.up_proj:  23%|██▎       | 8496/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.115.down_proj:  23%|██▎       | 8497/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.116.gate_proj:  23%|██▎       | 8498/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.116.up_proj:  23%|██▎       | 8499/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.116.down_proj:  23%|██▎       | 8500/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.117.gate_proj:  23%|██▎       | 8501/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.117.up_proj:  23%|██▎       | 8502/36566 [00:08<00:25, 1122.50it/s]  
packing model.layers.20.mlp.experts.117.down_proj:  23%|██▎       | 8503/36566 [00:08<00:25, 1122.50it/s]
packing model.layers.20.mlp.experts.118.gate_proj:  23%|██▎       | 8504/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.118.up_proj:  23%|██▎       | 8505/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.118.down_proj:  23%|██▎       | 8506/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.119.gate_proj:  23%|██▎       | 8507/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.119.up_proj:  23%|██▎       | 8508/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.119.down_proj:  23%|██▎       | 8509/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.120.gate_proj:  23%|██▎       | 8510/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.120.up_proj:  23%|██▎       | 8511/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.120.down_proj:  23%|██▎       | 8512/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.121.gate_proj:  23%|██▎       | 8513/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.121.up_proj:  23%|██▎       | 8514/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.121.down_proj:  23%|██▎       | 8515/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.122.gate_proj:  23%|██▎       | 8516/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.122.up_proj:  23%|██▎       | 8517/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.122.down_proj:  23%|██▎       | 8518/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.123.gate_proj:  23%|██▎       | 8519/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.123.up_proj:  23%|██▎       | 8520/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.123.down_proj:  23%|██▎       | 8521/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.124.gate_proj:  23%|██▎       | 8522/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.124.up_proj:  23%|██▎       | 8523/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.124.down_proj:  23%|██▎       | 8524/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.125.gate_proj:  23%|██▎       | 8525/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.125.up_proj:  23%|██▎       | 8526/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.125.down_proj:  23%|██▎       | 8527/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.126.gate_proj:  23%|██▎       | 8528/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.126.up_proj:  23%|██▎       | 8529/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.126.down_proj:  23%|██▎       | 8530/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.127.gate_proj:  23%|██▎       | 8531/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.20.mlp.experts.127.up_proj:  23%|██▎       | 8532/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.20.mlp.experts.127.down_proj:  23%|██▎       | 8533/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.0.gate_proj:  23%|██▎       | 8534/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.0.up_proj:  23%|██▎       | 8535/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.0.down_proj:  23%|██▎       | 8536/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.1.gate_proj:  23%|██▎       | 8537/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.1.up_proj:  23%|██▎       | 8538/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.1.down_proj:  23%|██▎       | 8539/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.2.gate_proj:  23%|██▎       | 8540/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.2.up_proj:  23%|██▎       | 8541/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.2.down_proj:  23%|██▎       | 8542/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.3.gate_proj:  23%|██▎       | 8543/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.3.up_proj:  23%|██▎       | 8544/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.3.down_proj:  23%|██▎       | 8545/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.4.gate_proj:  23%|██▎       | 8546/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.4.up_proj:  23%|██▎       | 8547/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.4.down_proj:  23%|██▎       | 8548/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.5.gate_proj:  23%|██▎       | 8549/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.5.up_proj:  23%|██▎       | 8550/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.5.down_proj:  23%|██▎       | 8551/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.6.gate_proj:  23%|██▎       | 8552/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.6.up_proj:  23%|██▎       | 8553/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.6.down_proj:  23%|██▎       | 8554/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.7.gate_proj:  23%|██▎       | 8555/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.7.up_proj:  23%|██▎       | 8556/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.7.down_proj:  23%|██▎       | 8557/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.8.gate_proj:  23%|██▎       | 8558/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.8.up_proj:  23%|██▎       | 8559/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.8.down_proj:  23%|██▎       | 8560/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.9.gate_proj:  23%|██▎       | 8561/36566 [00:08<00:24, 1122.50it/s]
packing model.layers.21.mlp.experts.9.up_proj:  23%|██▎       | 8562/36566 [00:08<00:24, 1122.50it/s]  
packing model.layers.21.mlp.experts.9.up_proj:  23%|██▎       | 8563/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.9.down_proj:  23%|██▎       | 8563/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.10.gate_proj:  23%|██▎       | 8564/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.10.up_proj:  23%|██▎       | 8565/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.10.down_proj:  23%|██▎       | 8566/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.11.gate_proj:  23%|██▎       | 8567/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.11.up_proj:  23%|██▎       | 8568/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.11.down_proj:  23%|██▎       | 8569/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.12.gate_proj:  23%|██▎       | 8570/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.12.up_proj:  23%|██▎       | 8571/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.12.down_proj:  23%|██▎       | 8572/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.13.gate_proj:  23%|██▎       | 8573/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.13.up_proj:  23%|██▎       | 8574/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.13.down_proj:  23%|██▎       | 8575/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.14.gate_proj:  23%|██▎       | 8576/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.14.up_proj:  23%|██▎       | 8577/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.14.down_proj:  23%|██▎       | 8578/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.15.gate_proj:  23%|██▎       | 8579/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.15.up_proj:  23%|██▎       | 8580/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.15.down_proj:  23%|██▎       | 8581/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.16.gate_proj:  23%|██▎       | 8582/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.16.up_proj:  23%|██▎       | 8583/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.16.down_proj:  23%|██▎       | 8584/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.17.gate_proj:  23%|██▎       | 8585/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.17.up_proj:  23%|██▎       | 8586/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.17.down_proj:  23%|██▎       | 8587/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.18.gate_proj:  23%|██▎       | 8588/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.18.up_proj:  23%|██▎       | 8589/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.18.down_proj:  23%|██▎       | 8590/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.19.gate_proj:  23%|██▎       | 8591/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.19.up_proj:  23%|██▎       | 8592/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.19.down_proj:  23%|██▎       | 8593/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.20.gate_proj:  24%|██▎       | 8594/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.20.up_proj:  24%|██▎       | 8595/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.20.down_proj:  24%|██▎       | 8596/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.21.gate_proj:  24%|██▎       | 8597/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.21.up_proj:  24%|██▎       | 8598/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.21.down_proj:  24%|██▎       | 8599/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.22.gate_proj:  24%|██▎       | 8600/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.22.up_proj:  24%|██▎       | 8601/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.22.down_proj:  24%|██▎       | 8602/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.23.gate_proj:  24%|██▎       | 8603/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.23.up_proj:  24%|██▎       | 8604/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.23.down_proj:  24%|██▎       | 8605/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.24.gate_proj:  24%|██▎       | 8606/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.24.up_proj:  24%|██▎       | 8607/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.24.down_proj:  24%|██▎       | 8608/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.25.gate_proj:  24%|██▎       | 8609/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.25.up_proj:  24%|██▎       | 8610/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.25.down_proj:  24%|██▎       | 8611/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.26.gate_proj:  24%|██▎       | 8612/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.26.up_proj:  24%|██▎       | 8613/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.26.down_proj:  24%|██▎       | 8614/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.27.gate_proj:  24%|██▎       | 8615/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.27.up_proj:  24%|██▎       | 8616/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.27.down_proj:  24%|██▎       | 8617/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.28.gate_proj:  24%|██▎       | 8618/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.28.up_proj:  24%|██▎       | 8619/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.28.down_proj:  24%|██▎       | 8620/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.29.gate_proj:  24%|██▎       | 8621/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.29.up_proj:  24%|██▎       | 8622/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.29.down_proj:  24%|██▎       | 8623/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.30.gate_proj:  24%|██▎       | 8624/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.30.up_proj:  24%|██▎       | 8625/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.30.down_proj:  24%|██▎       | 8626/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.31.gate_proj:  24%|██▎       | 8627/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.31.up_proj:  24%|██▎       | 8628/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.31.down_proj:  24%|██▎       | 8629/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.32.gate_proj:  24%|██▎       | 8630/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.32.up_proj:  24%|██▎       | 8631/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.32.down_proj:  24%|██▎       | 8632/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.33.gate_proj:  24%|██▎       | 8633/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.33.up_proj:  24%|██▎       | 8634/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.33.down_proj:  24%|██▎       | 8635/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.34.gate_proj:  24%|██▎       | 8636/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.34.up_proj:  24%|██▎       | 8637/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.34.down_proj:  24%|██▎       | 8638/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.35.gate_proj:  24%|██▎       | 8639/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.35.up_proj:  24%|██▎       | 8640/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.35.down_proj:  24%|██▎       | 8641/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.36.gate_proj:  24%|██▎       | 8642/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.36.up_proj:  24%|██▎       | 8643/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.36.down_proj:  24%|██▎       | 8644/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.37.gate_proj:  24%|██▎       | 8645/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.37.up_proj:  24%|██▎       | 8646/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.37.down_proj:  24%|██▎       | 8647/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.38.gate_proj:  24%|██▎       | 8648/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.38.up_proj:  24%|██▎       | 8649/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.38.down_proj:  24%|██▎       | 8650/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.39.gate_proj:  24%|██▎       | 8651/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.39.up_proj:  24%|██▎       | 8652/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.39.down_proj:  24%|██▎       | 8653/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.40.gate_proj:  24%|██▎       | 8654/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.40.up_proj:  24%|██▎       | 8655/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.40.down_proj:  24%|██▎       | 8656/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.41.gate_proj:  24%|██▎       | 8657/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.41.up_proj:  24%|██▎       | 8658/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.41.down_proj:  24%|██▎       | 8659/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.42.gate_proj:  24%|██▎       | 8660/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.42.up_proj:  24%|██▎       | 8661/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.42.down_proj:  24%|██▎       | 8662/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.43.gate_proj:  24%|██▎       | 8663/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.43.up_proj:  24%|██▎       | 8664/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.43.down_proj:  24%|██▎       | 8665/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.44.gate_proj:  24%|██▎       | 8666/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.44.up_proj:  24%|██▎       | 8667/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.44.down_proj:  24%|██▎       | 8668/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.45.gate_proj:  24%|██▎       | 8669/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.45.up_proj:  24%|██▎       | 8670/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.45.down_proj:  24%|██▎       | 8671/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.46.gate_proj:  24%|██▎       | 8672/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.46.up_proj:  24%|██▎       | 8673/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.46.down_proj:  24%|██▎       | 8674/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.47.gate_proj:  24%|██▎       | 8675/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.47.up_proj:  24%|██▎       | 8676/36566 [00:08<00:24, 1130.10it/s]  
packing model.layers.21.mlp.experts.47.down_proj:  24%|██▎       | 8677/36566 [00:08<00:24, 1130.10it/s]
packing model.layers.21.mlp.experts.47.down_proj:  24%|██▎       | 8678/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.48.gate_proj:  24%|██▎       | 8678/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.48.up_proj:  24%|██▎       | 8679/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.48.down_proj:  24%|██▎       | 8680/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.49.gate_proj:  24%|██▎       | 8681/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.49.up_proj:  24%|██▎       | 8682/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.49.down_proj:  24%|██▎       | 8683/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.50.gate_proj:  24%|██▎       | 8684/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.50.up_proj:  24%|██▍       | 8685/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.50.down_proj:  24%|██▍       | 8686/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.51.gate_proj:  24%|██▍       | 8687/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.51.up_proj:  24%|██▍       | 8688/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.51.down_proj:  24%|██▍       | 8689/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.52.gate_proj:  24%|██▍       | 8690/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.52.up_proj:  24%|██▍       | 8691/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.52.down_proj:  24%|██▍       | 8692/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.53.gate_proj:  24%|██▍       | 8693/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.53.up_proj:  24%|██▍       | 8694/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.53.down_proj:  24%|██▍       | 8695/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.54.gate_proj:  24%|██▍       | 8696/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.54.up_proj:  24%|██▍       | 8697/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.54.down_proj:  24%|██▍       | 8698/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.55.gate_proj:  24%|██▍       | 8699/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.55.up_proj:  24%|██▍       | 8700/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.55.down_proj:  24%|██▍       | 8701/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.56.gate_proj:  24%|██▍       | 8702/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.56.up_proj:  24%|██▍       | 8703/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.56.down_proj:  24%|██▍       | 8704/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.57.gate_proj:  24%|██▍       | 8705/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.57.up_proj:  24%|██▍       | 8706/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.57.down_proj:  24%|██▍       | 8707/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.58.gate_proj:  24%|██▍       | 8708/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.58.up_proj:  24%|██▍       | 8709/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.58.down_proj:  24%|██▍       | 8710/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.59.gate_proj:  24%|██▍       | 8711/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.59.up_proj:  24%|██▍       | 8712/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.59.down_proj:  24%|██▍       | 8713/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.60.gate_proj:  24%|██▍       | 8714/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.60.up_proj:  24%|██▍       | 8715/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.60.down_proj:  24%|██▍       | 8716/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.61.gate_proj:  24%|██▍       | 8717/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.61.up_proj:  24%|██▍       | 8718/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.61.down_proj:  24%|██▍       | 8719/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.62.gate_proj:  24%|██▍       | 8720/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.62.up_proj:  24%|██▍       | 8721/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.62.down_proj:  24%|██▍       | 8722/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.63.gate_proj:  24%|██▍       | 8723/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.63.up_proj:  24%|██▍       | 8724/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.63.down_proj:  24%|██▍       | 8725/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.64.gate_proj:  24%|██▍       | 8726/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.64.up_proj:  24%|██▍       | 8727/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.64.down_proj:  24%|██▍       | 8728/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.65.gate_proj:  24%|██▍       | 8729/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.65.up_proj:  24%|██▍       | 8730/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.65.down_proj:  24%|██▍       | 8731/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.66.gate_proj:  24%|██▍       | 8732/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.66.up_proj:  24%|██▍       | 8733/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.66.down_proj:  24%|██▍       | 8734/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.67.gate_proj:  24%|██▍       | 8735/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.67.up_proj:  24%|██▍       | 8736/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.67.down_proj:  24%|██▍       | 8737/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.68.gate_proj:  24%|██▍       | 8738/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.68.up_proj:  24%|██▍       | 8739/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.68.down_proj:  24%|██▍       | 8740/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.69.gate_proj:  24%|██▍       | 8741/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.69.up_proj:  24%|██▍       | 8742/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.69.down_proj:  24%|██▍       | 8743/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.70.gate_proj:  24%|██▍       | 8744/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.70.up_proj:  24%|██▍       | 8745/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.70.down_proj:  24%|██▍       | 8746/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.71.gate_proj:  24%|██▍       | 8747/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.71.up_proj:  24%|██▍       | 8748/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.71.down_proj:  24%|██▍       | 8749/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.72.gate_proj:  24%|██▍       | 8750/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.72.up_proj:  24%|██▍       | 8751/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.72.down_proj:  24%|██▍       | 8752/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.73.gate_proj:  24%|██▍       | 8753/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.73.up_proj:  24%|██▍       | 8754/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.73.down_proj:  24%|██▍       | 8755/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.74.gate_proj:  24%|██▍       | 8756/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.74.up_proj:  24%|██▍       | 8757/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.74.down_proj:  24%|██▍       | 8758/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.75.gate_proj:  24%|██▍       | 8759/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.75.up_proj:  24%|██▍       | 8760/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.75.down_proj:  24%|██▍       | 8761/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.76.gate_proj:  24%|██▍       | 8762/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.76.up_proj:  24%|██▍       | 8763/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.76.down_proj:  24%|██▍       | 8764/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.77.gate_proj:  24%|██▍       | 8765/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.77.up_proj:  24%|██▍       | 8766/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.77.down_proj:  24%|██▍       | 8767/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.78.gate_proj:  24%|██▍       | 8768/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.78.up_proj:  24%|██▍       | 8769/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.78.down_proj:  24%|██▍       | 8770/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.79.gate_proj:  24%|██▍       | 8771/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.79.up_proj:  24%|██▍       | 8772/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.79.down_proj:  24%|██▍       | 8773/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.80.gate_proj:  24%|██▍       | 8774/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.80.up_proj:  24%|██▍       | 8775/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.80.down_proj:  24%|██▍       | 8776/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.81.gate_proj:  24%|██▍       | 8777/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.81.up_proj:  24%|██▍       | 8778/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.81.down_proj:  24%|██▍       | 8779/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.82.gate_proj:  24%|██▍       | 8780/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.82.up_proj:  24%|██▍       | 8781/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.82.down_proj:  24%|██▍       | 8782/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.83.gate_proj:  24%|██▍       | 8783/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.83.up_proj:  24%|██▍       | 8784/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.83.down_proj:  24%|██▍       | 8785/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.84.gate_proj:  24%|██▍       | 8786/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.84.up_proj:  24%|██▍       | 8787/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.84.down_proj:  24%|██▍       | 8788/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.85.gate_proj:  24%|██▍       | 8789/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.85.up_proj:  24%|██▍       | 8790/36566 [00:08<00:24, 1133.67it/s]  
packing model.layers.21.mlp.experts.85.down_proj:  24%|██▍       | 8791/36566 [00:08<00:24, 1133.67it/s]
packing model.layers.21.mlp.experts.85.down_proj:  24%|██▍       | 8792/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.86.gate_proj:  24%|██▍       | 8792/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.86.up_proj:  24%|██▍       | 8793/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.86.down_proj:  24%|██▍       | 8794/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.87.gate_proj:  24%|██▍       | 8795/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.87.up_proj:  24%|██▍       | 8796/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.87.down_proj:  24%|██▍       | 8797/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.88.gate_proj:  24%|██▍       | 8798/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.88.up_proj:  24%|██▍       | 8799/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.88.down_proj:  24%|██▍       | 8800/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.89.gate_proj:  24%|██▍       | 8801/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.89.up_proj:  24%|██▍       | 8802/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.89.down_proj:  24%|██▍       | 8803/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.90.gate_proj:  24%|██▍       | 8804/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.90.up_proj:  24%|██▍       | 8805/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.90.down_proj:  24%|██▍       | 8806/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.91.gate_proj:  24%|██▍       | 8807/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.91.up_proj:  24%|██▍       | 8808/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.91.down_proj:  24%|██▍       | 8809/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.92.gate_proj:  24%|██▍       | 8810/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.92.up_proj:  24%|██▍       | 8811/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.92.down_proj:  24%|██▍       | 8812/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.93.gate_proj:  24%|██▍       | 8813/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.93.up_proj:  24%|██▍       | 8814/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.93.down_proj:  24%|██▍       | 8815/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.94.gate_proj:  24%|██▍       | 8816/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.94.up_proj:  24%|██▍       | 8817/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.94.down_proj:  24%|██▍       | 8818/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.95.gate_proj:  24%|██▍       | 8819/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.95.up_proj:  24%|██▍       | 8820/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.95.down_proj:  24%|██▍       | 8821/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.96.gate_proj:  24%|██▍       | 8822/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.96.up_proj:  24%|██▍       | 8823/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.96.down_proj:  24%|██▍       | 8824/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.97.gate_proj:  24%|██▍       | 8825/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.97.up_proj:  24%|██▍       | 8826/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.97.down_proj:  24%|██▍       | 8827/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.98.gate_proj:  24%|██▍       | 8828/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.98.up_proj:  24%|██▍       | 8829/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.98.down_proj:  24%|██▍       | 8830/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.99.gate_proj:  24%|██▍       | 8831/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.99.up_proj:  24%|██▍       | 8832/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.99.down_proj:  24%|██▍       | 8833/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.100.gate_proj:  24%|██▍       | 8834/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.100.up_proj:  24%|██▍       | 8835/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.100.down_proj:  24%|██▍       | 8836/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.101.gate_proj:  24%|██▍       | 8837/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.101.up_proj:  24%|██▍       | 8838/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.101.down_proj:  24%|██▍       | 8839/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.102.gate_proj:  24%|██▍       | 8840/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.102.up_proj:  24%|██▍       | 8841/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.102.down_proj:  24%|██▍       | 8842/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.103.gate_proj:  24%|██▍       | 8843/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.103.up_proj:  24%|██▍       | 8844/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.103.down_proj:  24%|██▍       | 8845/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.104.gate_proj:  24%|██▍       | 8846/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.104.up_proj:  24%|██▍       | 8847/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.104.down_proj:  24%|██▍       | 8848/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.105.gate_proj:  24%|██▍       | 8849/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.105.up_proj:  24%|██▍       | 8850/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.105.down_proj:  24%|██▍       | 8851/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.106.gate_proj:  24%|██▍       | 8852/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.106.up_proj:  24%|██▍       | 8853/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.106.down_proj:  24%|██▍       | 8854/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.107.gate_proj:  24%|██▍       | 8855/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.107.up_proj:  24%|██▍       | 8856/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.107.down_proj:  24%|██▍       | 8857/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.108.gate_proj:  24%|██▍       | 8858/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.108.up_proj:  24%|██▍       | 8859/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.108.down_proj:  24%|██▍       | 8860/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.109.gate_proj:  24%|██▍       | 8861/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.109.up_proj:  24%|██▍       | 8862/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.109.down_proj:  24%|██▍       | 8863/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.110.gate_proj:  24%|██▍       | 8864/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.110.up_proj:  24%|██▍       | 8865/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.110.down_proj:  24%|██▍       | 8866/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.111.gate_proj:  24%|██▍       | 8867/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.111.up_proj:  24%|██▍       | 8868/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.111.down_proj:  24%|██▍       | 8869/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.112.gate_proj:  24%|██▍       | 8870/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.112.up_proj:  24%|██▍       | 8871/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.112.down_proj:  24%|██▍       | 8872/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.113.gate_proj:  24%|██▍       | 8873/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.113.up_proj:  24%|██▍       | 8874/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.113.down_proj:  24%|██▍       | 8875/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.114.gate_proj:  24%|██▍       | 8876/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.114.up_proj:  24%|██▍       | 8877/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.114.down_proj:  24%|██▍       | 8878/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.115.gate_proj:  24%|██▍       | 8879/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.115.up_proj:  24%|██▍       | 8880/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.115.down_proj:  24%|██▍       | 8881/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.116.gate_proj:  24%|██▍       | 8882/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.116.up_proj:  24%|██▍       | 8883/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.116.down_proj:  24%|██▍       | 8884/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.117.gate_proj:  24%|██▍       | 8885/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.117.up_proj:  24%|██▍       | 8886/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.117.down_proj:  24%|██▍       | 8887/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.118.gate_proj:  24%|██▍       | 8888/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.118.up_proj:  24%|██▍       | 8889/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.118.down_proj:  24%|██▍       | 8890/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.119.gate_proj:  24%|██▍       | 8891/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.119.up_proj:  24%|██▍       | 8892/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.119.down_proj:  24%|██▍       | 8893/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.120.gate_proj:  24%|██▍       | 8894/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.120.up_proj:  24%|██▍       | 8895/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.120.down_proj:  24%|██▍       | 8896/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.121.gate_proj:  24%|██▍       | 8897/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.121.up_proj:  24%|██▍       | 8898/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.121.down_proj:  24%|██▍       | 8899/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.122.gate_proj:  24%|██▍       | 8900/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.122.up_proj:  24%|██▍       | 8901/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.122.down_proj:  24%|██▍       | 8902/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.123.gate_proj:  24%|██▍       | 8903/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.123.up_proj:  24%|██▍       | 8904/36566 [00:08<00:24, 1130.24it/s]  
packing model.layers.21.mlp.experts.123.down_proj:  24%|██▍       | 8905/36566 [00:08<00:24, 1130.24it/s]
packing model.layers.21.mlp.experts.123.down_proj:  24%|██▍       | 8906/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.124.gate_proj:  24%|██▍       | 8906/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.124.up_proj:  24%|██▍       | 8907/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.21.mlp.experts.124.down_proj:  24%|██▍       | 8908/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.125.gate_proj:  24%|██▍       | 8909/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.125.up_proj:  24%|██▍       | 8910/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.21.mlp.experts.125.down_proj:  24%|██▍       | 8911/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.126.gate_proj:  24%|██▍       | 8912/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.126.up_proj:  24%|██▍       | 8913/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.21.mlp.experts.126.down_proj:  24%|██▍       | 8914/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.127.gate_proj:  24%|██▍       | 8915/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.21.mlp.experts.127.up_proj:  24%|██▍       | 8916/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.21.mlp.experts.127.down_proj:  24%|██▍       | 8917/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.0.gate_proj:  24%|██▍       | 8918/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.0.up_proj:  24%|██▍       | 8919/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.0.down_proj:  24%|██▍       | 8920/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.1.gate_proj:  24%|██▍       | 8921/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.1.up_proj:  24%|██▍       | 8922/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.1.down_proj:  24%|██▍       | 8923/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.2.gate_proj:  24%|██▍       | 8924/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.2.up_proj:  24%|██▍       | 8925/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.2.down_proj:  24%|██▍       | 8926/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.3.gate_proj:  24%|██▍       | 8927/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.3.up_proj:  24%|██▍       | 8928/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.3.down_proj:  24%|██▍       | 8929/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.4.gate_proj:  24%|██▍       | 8930/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.4.up_proj:  24%|██▍       | 8931/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.4.down_proj:  24%|██▍       | 8932/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.5.gate_proj:  24%|██▍       | 8933/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.5.up_proj:  24%|██▍       | 8934/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.5.down_proj:  24%|██▍       | 8935/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.6.gate_proj:  24%|██▍       | 8936/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.6.up_proj:  24%|██▍       | 8937/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.6.down_proj:  24%|██▍       | 8938/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.7.gate_proj:  24%|██▍       | 8939/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.7.up_proj:  24%|██▍       | 8940/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.7.down_proj:  24%|██▍       | 8941/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.8.gate_proj:  24%|██▍       | 8942/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.8.up_proj:  24%|██▍       | 8943/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.8.down_proj:  24%|██▍       | 8944/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.9.gate_proj:  24%|██▍       | 8945/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.9.up_proj:  24%|██▍       | 8946/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.9.down_proj:  24%|██▍       | 8947/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.10.gate_proj:  24%|██▍       | 8948/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.10.up_proj:  24%|██▍       | 8949/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.10.down_proj:  24%|██▍       | 8950/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.11.gate_proj:  24%|██▍       | 8951/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.11.up_proj:  24%|██▍       | 8952/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.11.down_proj:  24%|██▍       | 8953/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.12.gate_proj:  24%|██▍       | 8954/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.12.up_proj:  24%|██▍       | 8955/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.12.down_proj:  24%|██▍       | 8956/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.13.gate_proj:  24%|██▍       | 8957/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.13.up_proj:  24%|██▍       | 8958/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.13.down_proj:  25%|██▍       | 8959/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.14.gate_proj:  25%|██▍       | 8960/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.14.up_proj:  25%|██▍       | 8961/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.14.down_proj:  25%|██▍       | 8962/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.15.gate_proj:  25%|██▍       | 8963/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.15.up_proj:  25%|██▍       | 8964/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.15.down_proj:  25%|██▍       | 8965/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.16.gate_proj:  25%|██▍       | 8966/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.16.up_proj:  25%|██▍       | 8967/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.16.down_proj:  25%|██▍       | 8968/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.17.gate_proj:  25%|██▍       | 8969/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.17.up_proj:  25%|██▍       | 8970/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.17.down_proj:  25%|██▍       | 8971/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.18.gate_proj:  25%|██▍       | 8972/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.18.up_proj:  25%|██▍       | 8973/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.18.down_proj:  25%|██▍       | 8974/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.19.gate_proj:  25%|██▍       | 8975/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.19.up_proj:  25%|██▍       | 8976/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.19.down_proj:  25%|██▍       | 8977/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.20.gate_proj:  25%|██▍       | 8978/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.20.up_proj:  25%|██▍       | 8979/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.20.down_proj:  25%|██▍       | 8980/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.21.gate_proj:  25%|██▍       | 8981/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.21.up_proj:  25%|██▍       | 8982/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.21.down_proj:  25%|██▍       | 8983/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.22.gate_proj:  25%|██▍       | 8984/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.22.up_proj:  25%|██▍       | 8985/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.22.down_proj:  25%|██▍       | 8986/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.23.gate_proj:  25%|██▍       | 8987/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.23.up_proj:  25%|██▍       | 8988/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.23.down_proj:  25%|██▍       | 8989/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.24.gate_proj:  25%|██▍       | 8990/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.24.up_proj:  25%|██▍       | 8991/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.24.down_proj:  25%|██▍       | 8992/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.25.gate_proj:  25%|██▍       | 8993/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.25.up_proj:  25%|██▍       | 8994/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.25.down_proj:  25%|██▍       | 8995/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.26.gate_proj:  25%|██▍       | 8996/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.26.up_proj:  25%|██▍       | 8997/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.26.down_proj:  25%|██▍       | 8998/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.27.gate_proj:  25%|██▍       | 8999/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.27.up_proj:  25%|██▍       | 9000/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.27.down_proj:  25%|██▍       | 9001/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.28.gate_proj:  25%|██▍       | 9002/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.28.up_proj:  25%|██▍       | 9003/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.28.down_proj:  25%|██▍       | 9004/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.29.gate_proj:  25%|██▍       | 9005/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.29.up_proj:  25%|██▍       | 9006/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.29.down_proj:  25%|██▍       | 9007/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.30.gate_proj:  25%|██▍       | 9008/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.30.up_proj:  25%|██▍       | 9009/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.30.down_proj:  25%|██▍       | 9010/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.31.gate_proj:  25%|██▍       | 9011/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.31.up_proj:  25%|██▍       | 9012/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.31.down_proj:  25%|██▍       | 9013/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.32.gate_proj:  25%|██▍       | 9014/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.32.up_proj:  25%|██▍       | 9015/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.32.down_proj:  25%|██▍       | 9016/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.33.gate_proj:  25%|██▍       | 9017/36566 [00:08<00:24, 1125.74it/s]
packing model.layers.22.mlp.experts.33.up_proj:  25%|██▍       | 9018/36566 [00:08<00:24, 1125.74it/s]  
packing model.layers.22.mlp.experts.33.up_proj:  25%|██▍       | 9019/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.33.down_proj:  25%|██▍       | 9019/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.34.gate_proj:  25%|██▍       | 9020/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.34.up_proj:  25%|██▍       | 9021/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.34.down_proj:  25%|██▍       | 9022/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.35.gate_proj:  25%|██▍       | 9023/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.35.up_proj:  25%|██▍       | 9024/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.35.down_proj:  25%|██▍       | 9025/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.36.gate_proj:  25%|██▍       | 9026/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.36.up_proj:  25%|██▍       | 9027/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.36.down_proj:  25%|██▍       | 9028/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.37.gate_proj:  25%|██▍       | 9029/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.37.up_proj:  25%|██▍       | 9030/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.37.down_proj:  25%|██▍       | 9031/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.38.gate_proj:  25%|██▍       | 9032/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.38.up_proj:  25%|██▍       | 9033/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.38.down_proj:  25%|██▍       | 9034/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.39.gate_proj:  25%|██▍       | 9035/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.39.up_proj:  25%|██▍       | 9036/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.39.down_proj:  25%|██▍       | 9037/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.40.gate_proj:  25%|██▍       | 9038/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.40.up_proj:  25%|██▍       | 9039/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.40.down_proj:  25%|██▍       | 9040/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.41.gate_proj:  25%|██▍       | 9041/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.41.up_proj:  25%|██▍       | 9042/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.41.down_proj:  25%|██▍       | 9043/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.42.gate_proj:  25%|██▍       | 9044/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.42.up_proj:  25%|██▍       | 9045/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.42.down_proj:  25%|██▍       | 9046/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.43.gate_proj:  25%|██▍       | 9047/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.43.up_proj:  25%|██▍       | 9048/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.43.down_proj:  25%|██▍       | 9049/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.44.gate_proj:  25%|██▍       | 9050/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.44.up_proj:  25%|██▍       | 9051/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.44.down_proj:  25%|██▍       | 9052/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.45.gate_proj:  25%|██▍       | 9053/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.45.up_proj:  25%|██▍       | 9054/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.45.down_proj:  25%|██▍       | 9055/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.46.gate_proj:  25%|██▍       | 9056/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.46.up_proj:  25%|██▍       | 9057/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.46.down_proj:  25%|██▍       | 9058/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.47.gate_proj:  25%|██▍       | 9059/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.47.up_proj:  25%|██▍       | 9060/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.47.down_proj:  25%|██▍       | 9061/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.48.gate_proj:  25%|██▍       | 9062/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.48.up_proj:  25%|██▍       | 9063/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.48.down_proj:  25%|██▍       | 9064/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.49.gate_proj:  25%|██▍       | 9065/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.49.up_proj:  25%|██▍       | 9066/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.49.down_proj:  25%|██▍       | 9067/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.50.gate_proj:  25%|██▍       | 9068/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.50.up_proj:  25%|██▍       | 9069/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.50.down_proj:  25%|██▍       | 9070/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.51.gate_proj:  25%|██▍       | 9071/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.51.up_proj:  25%|██▍       | 9072/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.51.down_proj:  25%|██▍       | 9073/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.52.gate_proj:  25%|██▍       | 9074/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.52.up_proj:  25%|██▍       | 9075/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.52.down_proj:  25%|██▍       | 9076/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.53.gate_proj:  25%|██▍       | 9077/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.53.up_proj:  25%|██▍       | 9078/36566 [00:08<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.53.down_proj:  25%|██▍       | 9079/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.54.gate_proj:  25%|██▍       | 9080/36566 [00:08<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.54.up_proj:  25%|██▍       | 9081/36566 [00:09<00:24, 1120.84it/s]  
packing model.layers.22.mlp.experts.54.down_proj:  25%|██▍       | 9082/36566 [00:09<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.55.gate_proj:  25%|██▍       | 9083/36566 [00:09<00:24, 1120.84it/s]
packing model.layers.22.mlp.experts.55.up_proj:  25%|██▍       | 9084/
chaiml-muster-v2-q235b-77862-v1-uploader: packing model.layers.23.mlp.experts.122.up_proj:  26%|██▋       | 9669/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.122.down_proj:  26%|██▋       | 9670/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.123.gate_proj:  26%|██▋       | 9671/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.123.up_proj:  26%|██▋       | 9672/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.123.down_proj:  26%|██▋       | 9673/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.124.gate_proj:  26%|██▋       | 9674/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.124.up_proj:  26%|██▋       | 9675/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.124.down_proj:  26%|██▋       | 9676/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.125.gate_proj:  26%|██▋       | 9677/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.125.up_proj:  26%|██▋       | 9678/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.125.down_proj:  26%|██▋       | 9679/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.126.gate_proj:  26%|██▋       | 9680/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.126.up_proj:  26%|██▋       | 9681/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.126.down_proj:  26%|██▋       | 9682/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.127.gate_proj:  26%|██▋       | 9683/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.23.mlp.experts.127.up_proj:  26%|██▋       | 9684/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.23.mlp.experts.127.down_proj:  26%|██▋       | 9685/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.0.gate_proj:  26%|██▋       | 9686/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.24.mlp.experts.0.up_proj:  26%|██▋       | 9687/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.24.mlp.experts.0.down_proj:  26%|██▋       | 9688/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.1.gate_proj:  26%|██▋       | 9689/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.1.up_proj:  27%|██▋       | 9690/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.24.mlp.experts.1.down_proj:  27%|██▋       | 9691/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.2.gate_proj:  27%|██▋       | 9692/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.2.up_proj:  27%|██▋       | 9693/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.24.mlp.experts.2.down_proj:  27%|██▋       | 9694/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.3.gate_proj:  27%|██▋       | 9695/36566 [00:09<00:23, 1123.73it/s]
packing model.layers.24.mlp.experts.3.up_proj:  27%|██▋       | 9696/36566 [00:09<00:23, 1123.73it/s]  
packing model.layers.24.mlp.experts.3.up_proj:  27%|██▋       | 9697/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.3.down_proj:  27%|██▋       | 9697/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.4.gate_proj:  27%|██▋       | 9698/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.4.up_proj:  27%|██▋       | 9699/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.4.down_proj:  27%|██▋       | 9700/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.5.gate_proj:  27%|██▋       | 9701/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.5.up_proj:  27%|██▋       | 9702/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.5.down_proj:  27%|██▋       | 9703/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.6.gate_proj:  27%|██▋       | 9704/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.6.up_proj:  27%|██▋       | 9705/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.6.down_proj:  27%|██▋       | 9706/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.7.gate_proj:  27%|██▋       | 9707/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.7.up_proj:  27%|██▋       | 9708/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.7.down_proj:  27%|██▋       | 9709/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.8.gate_proj:  27%|██▋       | 9710/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.8.up_proj:  27%|██▋       | 9711/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.8.down_proj:  27%|██▋       | 9712/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.9.gate_proj:  27%|██▋       | 9713/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.9.up_proj:  27%|██▋       | 9714/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.9.down_proj:  27%|██▋       | 9715/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.10.gate_proj:  27%|██▋       | 9716/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.10.up_proj:  27%|██▋       | 9717/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.10.down_proj:  27%|██▋       | 9718/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.11.gate_proj:  27%|██▋       | 9719/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.11.up_proj:  27%|██▋       | 9720/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.11.down_proj:  27%|██▋       | 9721/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.12.gate_proj:  27%|██▋       | 9722/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.12.up_proj:  27%|██▋       | 9723/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.12.down_proj:  27%|██▋       | 9724/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.13.gate_proj:  27%|██▋       | 9725/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.13.up_proj:  27%|██▋       | 9726/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.13.down_proj:  27%|██▋       | 9727/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.14.gate_proj:  27%|██▋       | 9728/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.14.up_proj:  27%|██▋       | 9729/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.14.down_proj:  27%|██▋       | 9730/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.15.gate_proj:  27%|██▋       | 9731/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.15.up_proj:  27%|██▋       | 9732/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.15.down_proj:  27%|██▋       | 9733/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.16.gate_proj:  27%|██▋       | 9734/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.16.up_proj:  27%|██▋       | 9735/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.16.down_proj:  27%|██▋       | 9736/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.17.gate_proj:  27%|██▋       | 9737/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.17.up_proj:  27%|██▋       | 9738/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.17.down_proj:  27%|██▋       | 9739/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.18.gate_proj:  27%|██▋       | 9740/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.18.up_proj:  27%|██▋       | 9741/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.18.down_proj:  27%|██▋       | 9742/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.19.gate_proj:  27%|██▋       | 9743/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.19.up_proj:  27%|██▋       | 9744/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.19.down_proj:  27%|██▋       | 9745/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.20.gate_proj:  27%|██▋       | 9746/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.20.up_proj:  27%|██▋       | 9747/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.20.down_proj:  27%|██▋       | 9748/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.21.gate_proj:  27%|██▋       | 9749/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.21.up_proj:  27%|██▋       | 9750/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.21.down_proj:  27%|██▋       | 9751/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.22.gate_proj:  27%|██▋       | 9752/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.22.up_proj:  27%|██▋       | 9753/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.22.down_proj:  27%|██▋       | 9754/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.23.gate_proj:  27%|██▋       | 9755/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.23.up_proj:  27%|██▋       | 9756/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.23.down_proj:  27%|██▋       | 9757/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.24.gate_proj:  27%|██▋       | 9758/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.24.up_proj:  27%|██▋       | 9759/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.24.down_proj:  27%|██▋       | 9760/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.25.gate_proj:  27%|██▋       | 9761/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.25.up_proj:  27%|██▋       | 9762/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.25.down_proj:  27%|██▋       | 9763/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.26.gate_proj:  27%|██▋       | 9764/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.26.up_proj:  27%|██▋       | 9765/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.26.down_proj:  27%|██▋       | 9766/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.27.gate_proj:  27%|██▋       | 9767/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.27.up_proj:  27%|██▋       | 9768/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.27.down_proj:  27%|██▋       | 9769/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.28.gate_proj:  27%|██▋       | 9770/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.28.up_proj:  27%|██▋       | 9771/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.28.down_proj:  27%|██▋       | 9772/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.29.gate_proj:  27%|██▋       | 9773/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.29.up_proj:  27%|██▋       | 9774/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.29.down_proj:  27%|██▋       | 9775/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.30.gate_proj:  27%|██▋       | 9776/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.30.up_proj:  27%|██▋       | 9777/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.30.down_proj:  27%|██▋       | 9778/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.31.gate_proj:  27%|██▋       | 9779/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.31.up_proj:  27%|██▋       | 9780/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.31.down_proj:  27%|██▋       | 9781/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.32.gate_proj:  27%|██▋       | 9782/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.32.up_proj:  27%|██▋       | 9783/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.32.down_proj:  27%|██▋       | 9784/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.33.gate_proj:  27%|██▋       | 9785/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.33.up_proj:  27%|██▋       | 9786/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.33.down_proj:  27%|██▋       | 9787/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.34.gate_proj:  27%|██▋       | 9788/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.34.up_proj:  27%|██▋       | 9789/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.34.down_proj:  27%|██▋       | 9790/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.35.gate_proj:  27%|██▋       | 9791/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.35.up_proj:  27%|██▋       | 9792/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.35.down_proj:  27%|██▋       | 9793/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.36.gate_proj:  27%|██▋       | 9794/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.36.up_proj:  27%|██▋       | 9795/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.36.down_proj:  27%|██▋       | 9796/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.37.gate_proj:  27%|██▋       | 9797/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.37.up_proj:  27%|██▋       | 9798/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.37.down_proj:  27%|██▋       | 9799/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.38.gate_proj:  27%|██▋       | 9800/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.38.up_proj:  27%|██▋       | 9801/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.38.down_proj:  27%|██▋       | 9802/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.39.gate_proj:  27%|██▋       | 9803/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.39.up_proj:  27%|██▋       | 9804/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.39.down_proj:  27%|██▋       | 9805/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.40.gate_proj:  27%|██▋       | 9806/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.40.up_proj:  27%|██▋       | 9807/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.40.down_proj:  27%|██▋       | 9808/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.41.gate_proj:  27%|██▋       | 9809/36566 [00:09<00:23, 1123.33it/s]
packing model.layers.24.mlp.experts.41.up_proj:  27%|██▋       | 9810/36566 [00:09<00:23, 1123.33it/s]  
packing model.layers.24.mlp.experts.41.up_proj:  27%|██▋       | 9811/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.41.down_proj:  27%|██▋       | 9811/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.42.gate_proj:  27%|██▋       | 9812/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.42.up_proj:  27%|██▋       | 9813/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.42.down_proj:  27%|██▋       | 9814/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.43.gate_proj:  27%|██▋       | 9815/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.43.up_proj:  27%|██▋       | 9816/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.43.down_proj:  27%|██▋       | 9817/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.44.gate_proj:  27%|██▋       | 9818/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.44.up_proj:  27%|██▋       | 9819/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.44.down_proj:  27%|██▋       | 9820/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.45.gate_proj:  27%|██▋       | 9821/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.45.up_proj:  27%|██▋       | 9822/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.45.down_proj:  27%|██▋       | 9823/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.46.gate_proj:  27%|██▋       | 9824/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.46.up_proj:  27%|██▋       | 9825/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.46.down_proj:  27%|██▋       | 9826/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.47.gate_proj:  27%|██▋       | 9827/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.47.up_proj:  27%|██▋       | 9828/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.47.down_proj:  27%|██▋       | 9829/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.48.gate_proj:  27%|██▋       | 9830/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.48.up_proj:  27%|██▋       | 9831/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.48.down_proj:  27%|██▋       | 9832/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.49.gate_proj:  27%|██▋       | 9833/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.49.up_proj:  27%|██▋       | 9834/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.49.down_proj:  27%|██▋       | 9835/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.50.gate_proj:  27%|██▋       | 9836/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.50.up_proj:  27%|██▋       | 9837/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.50.down_proj:  27%|██▋       | 9838/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.51.gate_proj:  27%|██▋       | 9839/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.51.up_proj:  27%|██▋       | 9840/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.51.down_proj:  27%|██▋       | 9841/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.52.gate_proj:  27%|██▋       | 9842/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.52.up_proj:  27%|██▋       | 9843/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.52.down_proj:  27%|██▋       | 9844/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.53.gate_proj:  27%|██▋       | 9845/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.53.up_proj:  27%|██▋       | 9846/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.53.down_proj:  27%|██▋       | 9847/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.54.gate_proj:  27%|██▋       | 9848/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.54.up_proj:  27%|██▋       | 9849/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.54.down_proj:  27%|██▋       | 9850/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.55.gate_proj:  27%|██▋       | 9851/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.55.up_proj:  27%|██▋       | 9852/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.55.down_proj:  27%|██▋       | 9853/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.56.gate_proj:  27%|██▋       | 9854/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.56.up_proj:  27%|██▋       | 9855/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.56.down_proj:  27%|██▋       | 9856/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.57.gate_proj:  27%|██▋       | 9857/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.57.up_proj:  27%|██▋       | 9858/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.57.down_proj:  27%|██▋       | 9859/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.58.gate_proj:  27%|██▋       | 9860/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.58.up_proj:  27%|██▋       | 9861/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.58.down_proj:  27%|██▋       | 9862/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.59.gate_proj:  27%|██▋       | 9863/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.59.up_proj:  27%|██▋       | 9864/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.59.down_proj:  27%|██▋       | 9865/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.60.gate_proj:  27%|██▋       | 9866/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.60.up_proj:  27%|██▋       | 9867/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.60.down_proj:  27%|██▋       | 9868/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.61.gate_proj:  27%|██▋       | 9869/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.61.up_proj:  27%|██▋       | 9870/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.61.down_proj:  27%|██▋       | 9871/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.62.gate_proj:  27%|██▋       | 9872/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.62.up_proj:  27%|██▋       | 9873/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.62.down_proj:  27%|██▋       | 9874/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.63.gate_proj:  27%|██▋       | 9875/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.63.up_proj:  27%|██▋       | 9876/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.63.down_proj:  27%|██▋       | 9877/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.64.gate_proj:  27%|██▋       | 9878/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.64.up_proj:  27%|██▋       | 9879/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.64.down_proj:  27%|██▋       | 9880/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.65.gate_proj:  27%|██▋       | 9881/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.65.up_proj:  27%|██▋       | 9882/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.65.down_proj:  27%|██▋       | 9883/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.66.gate_proj:  27%|██▋       | 9884/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.66.up_proj:  27%|██▋       | 9885/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.66.down_proj:  27%|██▋       | 9886/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.67.gate_proj:  27%|██▋       | 9887/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.67.up_proj:  27%|██▋       | 9888/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.67.down_proj:  27%|██▋       | 9889/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.68.gate_proj:  27%|██▋       | 9890/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.68.up_proj:  27%|██▋       | 9891/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.68.down_proj:  27%|██▋       | 9892/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.69.gate_proj:  27%|██▋       | 9893/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.69.up_proj:  27%|██▋       | 9894/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.69.down_proj:  27%|██▋       | 9895/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.70.gate_proj:  27%|██▋       | 9896/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.70.up_proj:  27%|██▋       | 9897/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.70.down_proj:  27%|██▋       | 9898/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.71.gate_proj:  27%|██▋       | 9899/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.71.up_proj:  27%|██▋       | 9900/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.71.down_proj:  27%|██▋       | 9901/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.72.gate_proj:  27%|██▋       | 9902/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.72.up_proj:  27%|██▋       | 9903/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.72.down_proj:  27%|██▋       | 9904/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.73.gate_proj:  27%|██▋       | 9905/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.73.up_proj:  27%|██▋       | 9906/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.73.down_proj:  27%|██▋       | 9907/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.74.gate_proj:  27%|██▋       | 9908/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.74.up_proj:  27%|██▋       | 9909/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.74.down_proj:  27%|██▋       | 9910/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.75.gate_proj:  27%|██▋       | 9911/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.75.up_proj:  27%|██▋       | 9912/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.75.down_proj:  27%|██▋       | 9913/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.76.gate_proj:  27%|██▋       | 9914/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.76.up_proj:  27%|██▋       | 9915/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.76.down_proj:  27%|██▋       | 9916/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.77.gate_proj:  27%|██▋       | 9917/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.77.up_proj:  27%|██▋       | 9918/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.77.down_proj:  27%|██▋       | 9919/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.78.gate_proj:  27%|██▋       | 9920/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.78.up_proj:  27%|██▋       | 9921/36566 [00:09<00:23, 1127.20it/s]  
packing model.layers.24.mlp.experts.78.down_proj:  27%|██▋       | 9922/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.79.gate_proj:  27%|██▋       | 9923/36566 [00:09<00:23, 1127.20it/s]
packing model.layers.24.mlp.experts.79.gate_proj:  27%|██▋       | 9924/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.79.up_proj:  27%|██▋       | 9924/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.79.down_proj:  27%|██▋       | 9925/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.80.gate_proj:  27%|██▋       | 9926/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.80.up_proj:  27%|██▋       | 9927/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.80.down_proj:  27%|██▋       | 9928/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.81.gate_proj:  27%|██▋       | 9929/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.81.up_proj:  27%|██▋       | 9930/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.81.down_proj:  27%|██▋       | 9931/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.82.gate_proj:  27%|██▋       | 9932/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.82.up_proj:  27%|██▋       | 9933/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.82.down_proj:  27%|██▋       | 9934/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.83.gate_proj:  27%|██▋       | 9935/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.83.up_proj:  27%|██▋       | 9936/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.83.down_proj:  27%|██▋       | 9937/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.84.gate_proj:  27%|██▋       | 9938/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.84.up_proj:  27%|██▋       | 9939/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.84.down_proj:  27%|██▋       | 9940/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.85.gate_proj:  27%|██▋       | 9941/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.85.up_proj:  27%|██▋       | 9942/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.85.down_proj:  27%|██▋       | 9943/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.86.gate_proj:  27%|██▋       | 9944/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.86.up_proj:  27%|██▋       | 9945/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.86.down_proj:  27%|██▋       | 9946/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.87.gate_proj:  27%|██▋       | 9947/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.87.up_proj:  27%|██▋       | 9948/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.87.down_proj:  27%|██▋       | 9949/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.88.gate_proj:  27%|██▋       | 9950/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.88.up_proj:  27%|██▋       | 9951/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.88.down_proj:  27%|██▋       | 9952/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.89.gate_proj:  27%|██▋       | 9953/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.89.up_proj:  27%|██▋       | 9954/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.89.down_proj:  27%|██▋       | 9955/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.90.gate_proj:  27%|██▋       | 9956/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.90.up_proj:  27%|██▋       | 9957/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.90.down_proj:  27%|██▋       | 9958/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.91.gate_proj:  27%|██▋       | 9959/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.91.up_proj:  27%|██▋       | 9960/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.91.down_proj:  27%|██▋       | 9961/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.92.gate_proj:  27%|██▋       | 9962/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.92.up_proj:  27%|██▋       | 9963/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.92.down_proj:  27%|██▋       | 9964/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.93.gate_proj:  27%|██▋       | 9965/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.93.up_proj:  27%|██▋       | 9966/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.93.down_proj:  27%|██▋       | 9967/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.94.gate_proj:  27%|██▋       | 9968/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.94.up_proj:  27%|██▋       | 9969/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.94.down_proj:  27%|██▋       | 9970/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.95.gate_proj:  27%|██▋       | 9971/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.95.up_proj:  27%|██▋       | 9972/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.95.down_proj:  27%|██▋       | 9973/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.96.gate_proj:  27%|██▋       | 9974/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.96.up_proj:  27%|██▋       | 9975/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.96.down_proj:  27%|██▋       | 9976/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.97.gate_proj:  27%|██▋       | 9977/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.97.up_proj:  27%|██▋       | 9978/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.97.down_proj:  27%|██▋       | 9979/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.98.gate_proj:  27%|██▋       | 9980/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.98.up_proj:  27%|██▋       | 9981/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.98.down_proj:  27%|██▋       | 9982/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.99.gate_proj:  27%|██▋       | 9983/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.99.up_proj:  27%|██▋       | 9984/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.99.down_proj:  27%|██▋       | 9985/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.100.gate_proj:  27%|██▋       | 9986/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.100.up_proj:  27%|██▋       | 9987/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.100.down_proj:  27%|██▋       | 9988/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.101.gate_proj:  27%|██▋       | 9989/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.101.up_proj:  27%|██▋       | 9990/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.101.down_proj:  27%|██▋       | 9991/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.102.gate_proj:  27%|██▋       | 9992/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.102.up_proj:  27%|██▋       | 9993/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.102.down_proj:  27%|██▋       | 9994/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.103.gate_proj:  27%|██▋       | 9995/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.103.up_proj:  27%|██▋       | 9996/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.103.down_proj:  27%|██▋       | 9997/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.104.gate_proj:  27%|██▋       | 9998/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.104.up_proj:  27%|██▋       | 9999/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.104.down_proj:  27%|██▋       | 10000/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.105.gate_proj:  27%|██▋       | 10001/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.105.up_proj:  27%|██▋       | 10002/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.105.down_proj:  27%|██▋       | 10003/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.106.gate_proj:  27%|██▋       | 10004/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.106.up_proj:  27%|██▋       | 10005/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.106.down_proj:  27%|██▋       | 10006/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.107.gate_proj:  27%|██▋       | 10007/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.107.up_proj:  27%|██▋       | 10008/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.107.down_proj:  27%|██▋       | 10009/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.108.gate_proj:  27%|██▋       | 10010/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.108.up_proj:  27%|██▋       | 10011/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.108.down_proj:  27%|██▋       | 10012/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.109.gate_proj:  27%|██▋       | 10013/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.109.up_proj:  27%|██▋       | 10014/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.109.down_proj:  27%|██▋       | 10015/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.110.gate_proj:  27%|██▋       | 10016/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.110.up_proj:  27%|██▋       | 10017/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.110.down_proj:  27%|██▋       | 10018/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.111.gate_proj:  27%|██▋       | 10019/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.111.up_proj:  27%|██▋       | 10020/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.111.down_proj:  27%|██▋       | 10021/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.112.gate_proj:  27%|██▋       | 10022/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.112.up_proj:  27%|██▋       | 10023/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.112.down_proj:  27%|██▋       | 10024/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.113.gate_proj:  27%|██▋       | 10025/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.113.up_proj:  27%|██▋       | 10026/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.113.down_proj:  27%|██▋       | 10027/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.114.gate_proj:  27%|██▋       | 10028/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.114.up_proj:  27%|██▋       | 10029/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.114.down_proj:  27%|██▋       | 10030/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.115.gate_proj:  27%|██▋       | 10031/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.115.up_proj:  27%|██▋       | 10032/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.115.down_proj:  27%|██▋       | 10033/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.116.gate_proj:  27%|██▋       | 10034/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.116.up_proj:  27%|██▋       | 10035/36566 [00:09<00:23, 1125.45it/s]  
packing model.layers.24.mlp.experts.116.down_proj:  27%|██▋       | 10036/36566 [00:09<00:23, 1125.45it/s]
packing model.layers.24.mlp.experts.116.down_proj:  27%|██▋       | 10037/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.117.gate_proj:  27%|██▋       | 10037/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.117.up_proj:  27%|██▋       | 10038/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.117.down_proj:  27%|██▋       | 10039/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.118.gate_proj:  27%|██▋       | 10040/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.118.up_proj:  27%|██▋       | 10041/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.118.down_proj:  27%|██▋       | 10042/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.119.gate_proj:  27%|██▋       | 10043/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.119.up_proj:  27%|██▋       | 10044/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.119.down_proj:  27%|██▋       | 10045/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.120.gate_proj:  27%|██▋       | 10046/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.120.up_proj:  27%|██▋       | 10047/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.120.down_proj:  27%|██▋       | 10048/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.121.gate_proj:  27%|██▋       | 10049/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.121.up_proj:  27%|██▋       | 10050/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.121.down_proj:  27%|██▋       | 10051/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.122.gate_proj:  27%|██▋       | 10052/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.122.up_proj:  27%|██▋       | 10053/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.122.down_proj:  27%|██▋       | 10054/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.123.gate_proj:  27%|██▋       | 10055/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.123.up_proj:  28%|██▊       | 10056/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.123.down_proj:  28%|██▊       | 10057/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.124.gate_proj:  28%|██▊       | 10058/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.124.up_proj:  28%|██▊       | 10059/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.124.down_proj:  28%|██▊       | 10060/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.125.gate_proj:  28%|██▊       | 10061/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.125.up_proj:  28%|██▊       | 10062/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.125.down_proj:  28%|██▊       | 10063/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.126.gate_proj:  28%|██▊       | 10064/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.126.up_proj:  28%|██▊       | 10065/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.126.down_proj:  28%|██▊       | 10066/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.127.gate_proj:  28%|██▊       | 10067/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.24.mlp.experts.127.up_proj:  28%|██▊       | 10068/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.24.mlp.experts.127.down_proj:  28%|██▊       | 10069/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.0.gate_proj:  28%|██▊       | 10070/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.0.up_proj:  28%|██▊       | 10071/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.0.down_proj:  28%|██▊       | 10072/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.1.gate_proj:  28%|██▊       | 10073/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.1.up_proj:  28%|██▊       | 10074/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.1.down_proj:  28%|██▊       | 10075/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.2.gate_proj:  28%|██▊       | 10076/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.2.up_proj:  28%|██▊       | 10077/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.2.down_proj:  28%|██▊       | 10078/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.3.gate_proj:  28%|██▊       | 10079/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.3.up_proj:  28%|██▊       | 10080/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.3.down_proj:  28%|██▊       | 10081/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.4.gate_proj:  28%|██▊       | 10082/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.4.up_proj:  28%|██▊       | 10083/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.4.down_proj:  28%|██▊       | 10084/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.5.gate_proj:  28%|██▊       | 10085/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.5.up_proj:  28%|██▊       | 10086/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.5.down_proj:  28%|██▊       | 10087/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.6.gate_proj:  28%|██▊       | 10088/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.6.up_proj:  28%|██▊       | 10089/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.6.down_proj:  28%|██▊       | 10090/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.7.gate_proj:  28%|██▊       | 10091/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.7.up_proj:  28%|██▊       | 10092/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.7.down_proj:  28%|██▊       | 10093/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.8.gate_proj:  28%|██▊       | 10094/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.8.up_proj:  28%|██▊       | 10095/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.8.down_proj:  28%|██▊       | 10096/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.9.gate_proj:  28%|██▊       | 10097/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.9.up_proj:  28%|██▊       | 10098/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.9.down_proj:  28%|██▊       | 10099/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.10.gate_proj:  28%|██▊       | 10100/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.10.up_proj:  28%|██▊       | 10101/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.10.down_proj:  28%|██▊       | 10102/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.11.gate_proj:  28%|██▊       | 10103/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.11.up_proj:  28%|██▊       | 10104/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.11.down_proj:  28%|██▊       | 10105/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.12.gate_proj:  28%|██▊       | 10106/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.12.up_proj:  28%|██▊       | 10107/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.12.down_proj:  28%|██▊       | 10108/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.13.gate_proj:  28%|██▊       | 10109/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.13.up_proj:  28%|██▊       | 10110/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.13.down_proj:  28%|██▊       | 10111/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.14.gate_proj:  28%|██▊       | 10112/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.14.up_proj:  28%|██▊       | 10113/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.14.down_proj:  28%|██▊       | 10114/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.15.gate_proj:  28%|██▊       | 10115/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.15.up_proj:  28%|██▊       | 10116/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.15.down_proj:  28%|██▊       | 10117/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.16.gate_proj:  28%|██▊       | 10118/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.16.up_proj:  28%|██▊       | 10119/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.16.down_proj:  28%|██▊       | 10120/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.17.gate_proj:  28%|██▊       | 10121/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.17.up_proj:  28%|██▊       | 10122/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.17.down_proj:  28%|██▊       | 10123/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.18.gate_proj:  28%|██▊       | 10124/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.18.up_proj:  28%|██▊       | 10125/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.18.down_proj:  28%|██▊       | 10126/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.19.gate_proj:  28%|██▊       | 10127/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.19.up_proj:  28%|██▊       | 10128/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.19.down_proj:  28%|██▊       | 10129/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.20.gate_proj:  28%|██▊       | 10130/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.20.up_proj:  28%|██▊       | 10131/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.20.down_proj:  28%|██▊       | 10132/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.21.gate_proj:  28%|██▊       | 10133/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.21.up_proj:  28%|██▊       | 10134/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.21.down_proj:  28%|██▊       | 10135/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.22.gate_proj:  28%|██▊       | 10136/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.22.up_proj:  28%|██▊       | 10137/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.22.down_proj:  28%|██▊       | 10138/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.23.gate_proj:  28%|██▊       | 10139/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.23.up_proj:  28%|██▊       | 10140/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.23.down_proj:  28%|██▊       | 10141/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.24.gate_proj:  28%|██▊       | 10142/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.24.up_proj:  28%|██▊       | 10143/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.24.down_proj:  28%|██▊       | 10144/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.25.gate_proj:  28%|██▊       | 10145/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.25.up_proj:  28%|██▊       | 10146/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.25.down_proj:  28%|██▊       | 10147/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.26.gate_proj:  28%|██▊       | 10148/36566 [00:09<00:23, 1125.35it/s]
packing model.layers.25.mlp.experts.26.up_proj:  28%|██▊       | 10149/36566 [00:09<00:23, 1125.35it/s]  
packing model.layers.25.mlp.experts.26.up_proj:  28%|██▊       | 10150/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.26.down_proj:  28%|██▊       | 10150/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.27.gate_proj:  28%|██▊       | 10151/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.27.up_proj:  28%|██▊       | 10152/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.27.down_proj:  28%|██▊       | 10153/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.28.gate_proj:  28%|██▊       | 10154/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.28.up_proj:  28%|██▊       | 10155/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.28.down_proj:  28%|██▊       | 10156/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.29.gate_proj:  28%|██▊       | 10157/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.29.up_proj:  28%|██▊       | 10158/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.29.down_proj:  28%|██▊       | 10159/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.30.gate_proj:  28%|██▊       | 10160/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.30.up_proj:  28%|██▊       | 10161/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.30.down_proj:  28%|██▊       | 10162/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.31.gate_proj:  28%|██▊       | 10163/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.31.up_proj:  28%|██▊       | 10164/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.31.down_proj:  28%|██▊       | 10165/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.32.gate_proj:  28%|██▊       | 10166/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.32.up_proj:  28%|██▊       | 10167/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.32.down_proj:  28%|██▊       | 10168/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.33.gate_proj:  28%|██▊       | 10169/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.33.up_proj:  28%|██▊       | 10170/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.33.down_proj:  28%|██▊       | 10171/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.34.gate_proj:  28%|██▊       | 10172/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.34.up_proj:  28%|██▊       | 10173/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.34.down_proj:  28%|██▊       | 10174/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.35.gate_proj:  28%|██▊       | 10175/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.35.up_proj:  28%|██▊       | 10176/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.35.down_proj:  28%|██▊       | 10177/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.36.gate_proj:  28%|██▊       | 10178/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.36.up_proj:  28%|██▊       | 10179/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.36.down_proj:  28%|██▊       | 10180/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.37.gate_proj:  28%|██▊       | 10181/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.37.up_proj:  28%|██▊       | 10182/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.37.down_proj:  28%|██▊       | 10183/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.38.gate_proj:  28%|██▊       | 10184/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.38.up_proj:  28%|██▊       | 10185/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.38.down_proj:  28%|██▊       | 10186/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.39.gate_proj:  28%|██▊       | 10187/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.39.up_proj:  28%|██▊       | 10188/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.39.down_proj:  28%|██▊       | 10189/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.40.gate_proj:  28%|██▊       | 10190/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.40.up_proj:  28%|██▊       | 10191/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.40.down_proj:  28%|██▊       | 10192/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.41.gate_proj:  28%|██▊       | 10193/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.41.up_proj:  28%|██▊       | 10194/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.41.down_proj:  28%|██▊       | 10195/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.42.gate_proj:  28%|██▊       | 10196/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.42.up_proj:  28%|██▊       | 10197/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.42.down_proj:  28%|██▊       | 10198/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.43.gate_proj:  28%|██▊       | 10199/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.43.up_proj:  28%|██▊       | 10200/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.43.down_proj:  28%|██▊       | 10201/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.44.gate_proj:  28%|██▊       | 10202/36566 [00:09<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.44.up_proj:  28%|██▊       | 10203/36566 [00:09<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.44.down_proj:  28%|██▊       | 10204/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.45.gate_proj:  28%|██▊       | 10205/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.45.up_proj:  28%|██▊       | 10206/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.45.down_proj:  28%|██▊       | 10207/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.46.gate_proj:  28%|██▊       | 10208/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.46.up_proj:  28%|██▊       | 10209/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.46.down_proj:  28%|██▊       | 10210/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.47.gate_proj:  28%|██▊       | 10211/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.47.up_proj:  28%|██▊       | 10212/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.47.down_proj:  28%|██▊       | 10213/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.48.gate_proj:  28%|██▊       | 10214/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.48.up_proj:  28%|██▊       | 10215/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.48.down_proj:  28%|██▊       | 10216/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.49.gate_proj:  28%|██▊       | 10217/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.49.up_proj:  28%|██▊       | 10218/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.49.down_proj:  28%|██▊       | 10219/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.50.gate_proj:  28%|██▊       | 10220/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.50.up_proj:  28%|██▊       | 10221/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.50.down_proj:  28%|██▊       | 10222/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.51.gate_proj:  28%|██▊       | 10223/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.51.up_proj:  28%|██▊       | 10224/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.51.down_proj:  28%|██▊       | 10225/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.52.gate_proj:  28%|██▊       | 10226/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.52.up_proj:  28%|██▊       | 10227/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.52.down_proj:  28%|██▊       | 10228/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.53.gate_proj:  28%|██▊       | 10229/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.53.up_proj:  28%|██▊       | 10230/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.53.down_proj:  28%|██▊       | 10231/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.54.gate_proj:  28%|██▊       | 10232/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.54.up_proj:  28%|██▊       | 10233/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.54.down_proj:  28%|██▊       | 10234/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.55.gate_proj:  28%|██▊       | 10235/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.55.up_proj:  28%|██▊       | 10236/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.55.down_proj:  28%|██▊       | 10237/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.56.gate_proj:  28%|██▊       | 10238/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.56.up_proj:  28%|██▊       | 10239/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.56.down_proj:  28%|██▊       | 10240/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.57.gate_proj:  28%|██▊       | 10241/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.57.up_proj:  28%|██▊       | 10242/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.57.down_proj:  28%|██▊       | 10243/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.58.gate_proj:  28%|██▊       | 10244/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.58.up_proj:  28%|██▊       | 10245/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.58.down_proj:  28%|██▊       | 10246/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.59.gate_proj:  28%|██▊       | 10247/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.59.up_proj:  28%|██▊       | 10248/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.59.down_proj:  28%|██▊       | 10249/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.60.gate_proj:  28%|██▊       | 10250/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.60.up_proj:  28%|██▊       | 10251/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.60.down_proj:  28%|██▊       | 10252/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.61.gate_proj:  28%|██▊       | 10253/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.61.up_proj:  28%|██▊       | 10254/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.61.down_proj:  28%|██▊       | 10255/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.62.gate_proj:  28%|██▊       | 10256/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.62.up_proj:  28%|██▊       | 10257/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.62.down_proj:  28%|██▊       | 10258/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.63.gate_proj:  28%|██▊       | 10259/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.63.up_proj:  28%|██▊       | 10260/36566 [00:10<00:23, 1123.94it/s]  
packing model.layers.25.mlp.experts.63.down_proj:  28%|██▊       | 10261/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.64.gate_proj:  28%|██▊       | 10262/36566 [00:10<00:23, 1123.94it/s]
packing model.layers.25.mlp.experts.64.gate_proj:  28%|██▊       | 10263/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.64.up_proj:  28%|██▊       | 10263/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.64.down_proj:  28%|██▊       | 10264/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.65.gate_proj:  28%|██▊       | 10265/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.65.up_proj:  28%|██▊       | 10266/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.65.down_proj:  28%|██▊       | 10267/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.66.gate_proj:  28%|██▊       | 10268/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.66.up_proj:  28%|██▊       | 10269/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.66.down_proj:  28%|██▊       | 10270/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.67.gate_proj:  28%|██▊       | 10271/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.67.up_proj:  28%|██▊       | 10272/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.67.down_proj:  28%|██▊       | 10273/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.68.gate_proj:  28%|██▊       | 10274/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.68.up_proj:  28%|██▊       | 10275/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.68.down_proj:  28%|██▊       | 10276/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.69.gate_proj:  28%|██▊       | 10277/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.69.up_proj:  28%|██▊       | 10278/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.69.down_proj:  28%|██▊       | 10279/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.70.gate_proj:  28%|██▊       | 10280/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.70.up_proj:  28%|██▊       | 10281/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.70.down_proj:  28%|██▊       | 10282/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.71.gate_proj:  28%|██▊       | 10283/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.71.up_proj:  28%|██▊       | 10284/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.71.down_proj:  28%|██▊       | 10285/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.72.gate_proj:  28%|██▊       | 10286/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.72.up_proj:  28%|██▊       | 10287/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.72.down_proj:  28%|██▊       | 10288/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.73.gate_proj:  28%|██▊       | 10289/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.73.up_proj:  28%|██▊       | 10290/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.73.down_proj:  28%|██▊       | 10291/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.74.gate_proj:  28%|██▊       | 10292/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.74.up_proj:  28%|██▊       | 10293/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.74.down_proj:  28%|██▊       | 10294/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.75.gate_proj:  28%|██▊       | 10295/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.75.up_proj:  28%|██▊       | 10296/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.75.down_proj:  28%|██▊       | 10297/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.76.gate_proj:  28%|██▊       | 10298/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.76.up_proj:  28%|██▊       | 10299/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.76.down_proj:  28%|██▊       | 10300/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.77.gate_proj:  28%|██▊       | 10301/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.77.up_proj:  28%|██▊       | 10302/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.77.down_proj:  28%|██▊       | 10303/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.78.gate_proj:  28%|██▊       | 10304/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.78.up_proj:  28%|██▊       | 10305/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.78.down_proj:  28%|██▊       | 10306/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.79.gate_proj:  28%|██▊       | 10307/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.79.up_proj:  28%|██▊       | 10308/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.79.down_proj:  28%|██▊       | 10309/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.80.gate_proj:  28%|██▊       | 10310/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.80.up_proj:  28%|██▊       | 10311/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.80.down_proj:  28%|██▊       | 10312/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.81.gate_proj:  28%|██▊       | 10313/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.81.up_proj:  28%|██▊       | 10314/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.81.down_proj:  28%|██▊       | 10315/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.82.gate_proj:  28%|██▊       | 10316/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.82.up_proj:  28%|██▊       | 10317/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.82.down_proj:  28%|██▊       | 10318/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.83.gate_proj:  28%|██▊       | 10319/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.83.up_proj:  28%|██▊       | 10320/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.83.down_proj:  28%|██▊       | 10321/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.84.gate_proj:  28%|██▊       | 10322/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.84.up_proj:  28%|██▊       | 10323/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.84.down_proj:  28%|██▊       | 10324/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.85.gate_proj:  28%|██▊       | 10325/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.85.up_proj:  28%|██▊       | 10326/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.85.down_proj:  28%|██▊       | 10327/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.86.gate_proj:  28%|██▊       | 10328/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.86.up_proj:  28%|██▊       | 10329/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.86.down_proj:  28%|██▊       | 10330/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.87.gate_proj:  28%|██▊       | 10331/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.87.up_proj:  28%|██▊       | 10332/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.87.down_proj:  28%|██▊       | 10333/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.88.gate_proj:  28%|██▊       | 10334/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.88.up_proj:  28%|██▊       | 10335/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.88.down_proj:  28%|██▊       | 10336/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.89.gate_proj:  28%|██▊       | 10337/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.89.up_proj:  28%|██▊       | 10338/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.89.down_proj:  28%|██▊       | 10339/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.90.gate_proj:  28%|██▊       | 10340/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.90.up_proj:  28%|██▊       | 10341/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.90.down_proj:  28%|██▊       | 10342/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.91.gate_proj:  28%|██▊       | 10343/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.91.up_proj:  28%|██▊       | 10344/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.91.down_proj:  28%|██▊       | 10345/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.92.gate_proj:  28%|██▊       | 10346/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.92.up_proj:  28%|██▊       | 10347/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.92.down_proj:  28%|██▊       | 10348/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.93.gate_proj:  28%|██▊       | 10349/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.93.up_proj:  28%|██▊       | 10350/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.93.down_proj:  28%|██▊       | 10351/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.94.gate_proj:  28%|██▊       | 10352/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.94.up_proj:  28%|██▊       | 10353/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.94.down_proj:  28%|██▊       | 10354/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.95.gate_proj:  28%|██▊       | 10355/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.95.up_proj:  28%|██▊       | 10356/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.95.down_proj:  28%|██▊       | 10357/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.96.gate_proj:  28%|██▊       | 10358/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.96.up_proj:  28%|██▊       | 10359/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.96.down_proj:  28%|██▊       | 10360/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.97.gate_proj:  28%|██▊       | 10361/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.97.up_proj:  28%|██▊       | 10362/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.97.down_proj:  28%|██▊       | 10363/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.98.gate_proj:  28%|██▊       | 10364/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.98.up_proj:  28%|██▊       | 10365/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.98.down_proj:  28%|██▊       | 10366/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.99.gate_proj:  28%|██▊       | 10367/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.99.up_proj:  28%|██▊       | 10368/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.99.down_proj:  28%|██▊       | 10369/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.100.gate_proj:  28%|██▊       | 10370/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.100.up_proj:  28%|██▊       | 10371/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.100.down_proj:  28%|██▊       | 10372/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.101.gate_proj:  28%|██▊       | 10373/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.101.up_proj:  28%|██▊       | 10374/36566 [00:10<00:23, 1120.91it/s]  
packing model.layers.25.mlp.experts.101.down_proj:  28%|██▊       | 10375/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.102.gate_proj:  28%|██▊       | 10376/36566 [00:10<00:23, 1120.91it/s]
packing model.layers.25.mlp.experts.102.gate_proj:  28%|██▊       | 10377/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.102.up_proj:  28%|██▊       | 10377/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.102.down_proj:  28%|██▊       | 10378/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.103.gate_proj:  28%|██▊       | 10379/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.103.up_proj:  28%|██▊       | 10380/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.103.down_proj:  28%|██▊       | 10381/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.104.gate_proj:  28%|██▊       | 10382/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.104.up_proj:  28%|██▊       | 10383/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.104.down_proj:  28%|██▊       | 10384/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.105.gate_proj:  28%|██▊       | 10385/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.105.up_proj:  28%|██▊       | 10386/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.105.down_proj:  28%|██▊       | 10387/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.106.gate_proj:  28%|██▊       | 10388/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.106.up_proj:  28%|██▊       | 10389/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.106.down_proj:  28%|██▊       | 10390/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.107.gate_proj:  28%|██▊       | 10391/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.107.up_proj:  28%|██▊       | 10392/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.107.down_proj:  28%|██▊       | 10393/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.108.gate_proj:  28%|██▊       | 10394/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.108.up_proj:  28%|██▊       | 10395/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.108.down_proj:  28%|██▊       | 10396/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.109.gate_proj:  28%|██▊       | 10397/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.109.up_proj:  28%|██▊       | 10398/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.109.down_proj:  28%|██▊       | 10399/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.110.gate_proj:  28%|██▊       | 10400/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.110.up_proj:  28%|██▊       | 10401/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.110.down_proj:  28%|██▊       | 10402/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.111.gate_proj:  28%|██▊       | 10403/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.111.up_proj:  28%|██▊       | 10404/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.111.down_proj:  28%|██▊       | 10405/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.112.gate_proj:  28%|██▊       | 10406/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.112.up_proj:  28%|██▊       | 10407/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.112.down_proj:  28%|██▊       | 10408/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.113.gate_proj:  28%|██▊       | 10409/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.113.up_proj:  28%|██▊       | 10410/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.113.down_proj:  28%|██▊       | 10411/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.114.gate_proj:  28%|██▊       | 10412/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.114.up_proj:  28%|██▊       | 10413/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.114.down_proj:  28%|██▊       | 10414/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.115.gate_proj:  28%|██▊       | 10415/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.115.up_proj:  28%|██▊       | 10416/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.115.down_proj:  28%|██▊       | 10417/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.116.gate_proj:  28%|██▊       | 10418/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.116.up_proj:  28%|██▊       | 10419/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.116.down_proj:  28%|██▊       | 10420/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.117.gate_proj:  28%|██▊       | 10421/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.117.up_proj:  29%|██▊       | 10422/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.117.down_proj:  29%|██▊       | 10423/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.118.gate_proj:  29%|██▊       | 10424/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.118.up_proj:  29%|██▊       | 10425/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.118.down_proj:  29%|██▊       | 10426/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.119.gate_proj:  29%|██▊       | 10427/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.119.up_proj:  29%|██▊       | 10428/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.119.down_proj:  29%|██▊       | 10429/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.120.gate_proj:  29%|██▊       | 10430/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.120.up_proj:  29%|██▊       | 10431/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.120.down_proj:  29%|██▊       | 10432/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.121.gate_proj:  29%|██▊       | 10433/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.121.up_proj:  29%|██▊       | 10434/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.121.down_proj:  29%|██▊       | 10435/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.122.gate_proj:  29%|██▊       | 10436/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.122.up_proj:  29%|██▊       | 10437/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.122.down_proj:  29%|██▊       | 10438/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.123.gate_proj:  29%|██▊       | 10439/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.123.up_proj:  29%|██▊       | 10440/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.123.down_proj:  29%|██▊       | 10441/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.124.gate_proj:  29%|██▊       | 10442/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.124.up_proj:  29%|██▊       | 10443/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.124.down_proj:  29%|██▊       | 10444/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.125.gate_proj:  29%|██▊       | 10445/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.125.up_proj:  29%|██▊       | 10446/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.125.down_proj:  29%|██▊       | 10447/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.126.gate_proj:  29%|██▊       | 10448/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.126.up_proj:  29%|██▊       | 10449/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.126.down_proj:  29%|██▊       | 10450/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.127.gate_proj:  29%|██▊       | 10451/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.25.mlp.experts.127.up_proj:  29%|██▊       | 10452/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.25.mlp.experts.127.down_proj:  29%|██▊       | 10453/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.0.gate_proj:  29%|██▊       | 10454/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.0.up_proj:  29%|██▊       | 10455/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.0.down_proj:  29%|██▊       | 10456/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.1.gate_proj:  29%|██▊       | 10457/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.1.up_proj:  29%|██▊       | 10458/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.1.down_proj:  29%|██▊       | 10459/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.2.gate_proj:  29%|██▊       | 10460/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.2.up_proj:  29%|██▊       | 10461/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.2.down_proj:  29%|██▊       | 10462/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.3.gate_proj:  29%|██▊       | 10463/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.3.up_proj:  29%|██▊       | 10464/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.3.down_proj:  29%|██▊       | 10465/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.4.gate_proj:  29%|██▊       | 10466/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.4.up_proj:  29%|██▊       | 10467/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.4.down_proj:  29%|██▊       | 10468/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.5.gate_proj:  29%|██▊       | 10469/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.5.up_proj:  29%|██▊       | 10470/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.5.down_proj:  29%|██▊       | 10471/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.6.gate_proj:  29%|██▊       | 10472/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.6.up_proj:  29%|██▊       | 10473/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.6.down_proj:  29%|██▊       | 10474/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.7.gate_proj:  29%|██▊       | 10475/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.7.up_proj:  29%|██▊       | 10476/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.7.down_proj:  29%|██▊       | 10477/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.8.gate_proj:  29%|██▊       | 10478/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.8.up_proj:  29%|██▊       | 10479/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.8.down_proj:  29%|██▊       | 10480/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.9.gate_proj:  29%|██▊       | 10481/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.9.up_proj:  29%|██▊       | 10482/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.9.down_proj:  29%|██▊       | 10483/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.10.gate_proj:  29%|██▊       | 10484/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.10.up_proj:  29%|██▊       | 10485/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.10.down_proj:  29%|██▊       | 10486/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.11.gate_proj:  29%|██▊       | 10487/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.11.up_proj:  29%|██▊       | 10488/36566 [00:10<00:23, 1125.34it/s]  
packing model.layers.26.mlp.experts.11.down_proj:  29%|██▊       | 10489/36566 [00:10<00:23, 1125.34it/s]
packing model.layers.26.mlp.experts.11.down_proj:  29%|██▊       | 10490/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.12.gate_proj:  29%|██▊       | 10490/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.12.up_proj:  29%|██▊       | 10491/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.12.down_proj:  29%|██▊       | 10492/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.13.gate_proj:  29%|██▊       | 10493/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.13.up_proj:  29%|██▊       | 10494/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.13.down_proj:  29%|██▊       | 10495/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.14.gate_proj:  29%|██▊       | 10496/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.14.up_proj:  29%|██▊       | 10497/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.14.down_proj:  29%|██▊       | 10498/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.15.gate_proj:  29%|██▊       | 10499/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.15.up_proj:  29%|██▊       | 10500/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.15.down_proj:  29%|██▊       | 10501/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.16.gate_proj:  29%|██▊       | 10502/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.16.up_proj:  29%|██▊       | 10503/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.16.down_proj:  29%|██▊       | 10504/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.17.gate_proj:  29%|██▊       | 10505/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.17.up_proj:  29%|██▊       | 10506/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.17.down_proj:  29%|██▊       | 10507/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.18.gate_proj:  29%|██▊       | 10508/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.18.up_proj:  29%|██▊       | 10509/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.18.down_proj:  29%|██▊       | 10510/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.19.gate_proj:  29%|██▊       | 10511/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.19.up_proj:  29%|██▊       | 10512/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.19.down_proj:  29%|██▉       | 10513/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.20.gate_proj:  29%|██▉       | 10514/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.20.up_proj:  29%|██▉       | 10515/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.20.down_proj:  29%|██▉       | 10516/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.21.gate_proj:  29%|██▉       | 10517/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.21.up_proj:  29%|██▉       | 10518/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.21.down_proj:  29%|██▉       | 10519/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.22.gate_proj:  29%|██▉       | 10520/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.22.up_proj:  29%|██▉       | 10521/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.22.down_proj:  29%|██▉       | 10522/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.23.gate_proj:  29%|██▉       | 10523/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.23.up_proj:  29%|██▉       | 10524/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.23.down_proj:  29%|██▉       | 10525/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.24.gate_proj:  29%|██▉       | 10526/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.24.up_proj:  29%|██▉       | 10527/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.24.down_proj:  29%|██▉       | 10528/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.25.gate_proj:  29%|██▉       | 10529/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.25.up_proj:  29%|██▉       | 10530/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.25.down_proj:  29%|██▉       | 10531/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.26.gate_proj:  29%|██▉       | 10532/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.26.up_proj:  29%|██▉       | 10533/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.26.down_proj:  29%|██▉       | 10534/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.27.gate_proj:  29%|██▉       | 10535/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.27.up_proj:  29%|██▉       | 10536/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.27.down_proj:  29%|██▉       | 10537/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.28.gate_proj:  29%|██▉       | 10538/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.28.up_proj:  29%|██▉       | 10539/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.28.down_proj:  29%|██▉       | 10540/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.29.gate_proj:  29%|██▉       | 10541/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.29.up_proj:  29%|██▉       | 10542/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.29.down_proj:  29%|██▉       | 10543/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.30.gate_proj:  29%|██▉       | 10544/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.30.up_proj:  29%|██▉       | 10545/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.30.down_proj:  29%|██▉       | 10546/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.31.gate_proj:  29%|██▉       | 10547/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.31.up_proj:  29%|██▉       | 10548/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.31.down_proj:  29%|██▉       | 10549/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.32.gate_proj:  29%|██▉       | 10550/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.32.up_proj:  29%|██▉       | 10551/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.32.down_proj:  29%|██▉       | 10552/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.33.gate_proj:  29%|██▉       | 10553/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.33.up_proj:  29%|██▉       | 10554/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.33.down_proj:  29%|██▉       | 10555/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.34.gate_proj:  29%|██▉       | 10556/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.34.up_proj:  29%|██▉       | 10557/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.34.down_proj:  29%|██▉       | 10558/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.35.gate_proj:  29%|██▉       | 10559/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.35.up_proj:  29%|██▉       | 10560/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.35.down_proj:  29%|██▉       | 10561/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.36.gate_proj:  29%|██▉       | 10562/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.36.up_proj:  29%|██▉       | 10563/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.36.down_proj:  29%|██▉       | 10564/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.37.gate_proj:  29%|██▉       | 10565/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.37.up_proj:  29%|██▉       | 10566/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.37.down_proj:  29%|██▉       | 10567/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.38.gate_proj:  29%|██▉       | 10568/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.38.up_proj:  29%|██▉       | 10569/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.38.down_proj:  29%|██▉       | 10570/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.39.gate_proj:  29%|██▉       | 10571/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.39.up_proj:  29%|██▉       | 10572/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.39.down_proj:  29%|██▉       | 10573/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.40.gate_proj:  29%|██▉       | 10574/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.40.up_proj:  29%|██▉       | 10575/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.40.down_proj:  29%|██▉       | 10576/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.41.gate_proj:  29%|██▉       | 10577/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.41.up_proj:  29%|██▉       | 10578/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.41.down_proj:  29%|██▉       | 10579/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.42.gate_proj:  29%|██▉       | 10580/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.42.up_proj:  29%|██▉       | 10581/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.42.down_proj:  29%|██▉       | 10582/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.43.gate_proj:  29%|██▉       | 10583/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.43.up_proj:  29%|██▉       | 10584/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.43.down_proj:  29%|██▉       | 10585/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.44.gate_proj:  29%|██▉       | 10586/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.44.up_proj:  29%|██▉       | 10587/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.44.down_proj:  29%|██▉       | 10588/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.45.gate_proj:  29%|██▉       | 10589/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.45.up_proj:  29%|██▉       | 10590/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.45.down_proj:  29%|██▉       | 10591/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.46.gate_proj:  29%|██▉       | 10592/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.46.up_proj:  29%|██▉       | 10593/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.46.down_proj:  29%|██▉       | 10594/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.47.gate_proj:  29%|██▉       | 10595/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.47.up_proj:  29%|██▉       | 10596/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.47.down_proj:  29%|██▉       | 10597/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.48.gate_proj:  29%|██▉       | 10598/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.48.up_proj:  29%|██▉       | 10599/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.48.down_proj:  29%|██▉       | 10600/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.49.gate_proj:  29%|██▉       | 10601/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.49.up_proj:  29%|██▉       | 10602/36566 [00:10<00:23, 1122.12it/s]  
packing model.layers.26.mlp.experts.49.down_proj:  29%|██▉       | 10603/36566 [00:10<00:23, 1122.12it/s]
packing model.layers.26.mlp.experts.49.down_proj:  29%|██▉       | 10604/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.50.gate_proj:  29%|██▉       | 10604/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.50.up_proj:  29%|██▉       | 10605/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.50.down_proj:  29%|██▉       | 10606/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.51.gate_proj:  29%|██▉       | 10607/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.51.up_proj:  29%|██▉       | 10608/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.51.down_proj:  29%|██▉       | 10609/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.52.gate_proj:  29%|██▉       | 10610/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.52.up_proj:  29%|██▉       | 10611/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.52.down_proj:  29%|██▉       | 10612/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.53.gate_proj:  29%|██▉       | 10613/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.53.up_proj:  29%|██▉       | 10614/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.53.down_proj:  29%|██▉       | 10615/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.54.gate_proj:  29%|██▉       | 10616/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.54.up_proj:  29%|██▉       | 10617/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.54.down_proj:  29%|██▉       | 10618/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.55.gate_proj:  29%|██▉       | 10619/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.55.up_proj:  29%|██▉       | 10620/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.55.down_proj:  29%|██▉       | 10621/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.56.gate_proj:  29%|██▉       | 10622/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.56.up_proj:  29%|██▉       | 10623/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.56.down_proj:  29%|██▉       | 10624/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.57.gate_proj:  29%|██▉       | 10625/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.57.up_proj:  29%|██▉       | 10626/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.57.down_proj:  29%|██▉       | 10627/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.58.gate_proj:  29%|██▉       | 10628/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.58.up_proj:  29%|██▉       | 10629/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.58.down_proj:  29%|██▉       | 10630/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.59.gate_proj:  29%|██▉       | 10631/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.59.up_proj:  29%|██▉       | 10632/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.59.down_proj:  29%|██▉       | 10633/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.60.gate_proj:  29%|██▉       | 10634/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.60.up_proj:  29%|██▉       | 10635/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.60.down_proj:  29%|██▉       | 10636/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.61.gate_proj:  29%|██▉       | 10637/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.61.up_proj:  29%|██▉       | 10638/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.61.down_proj:  29%|██▉       | 10639/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.62.gate_proj:  29%|██▉       | 10640/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.62.up_proj:  29%|██▉       | 10641/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.62.down_proj:  29%|██▉       | 10642/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.63.gate_proj:  29%|██▉       | 10643/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.63.up_proj:  29%|██▉       | 10644/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.63.down_proj:  29%|██▉       | 10645/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.64.gate_proj:  29%|██▉       | 10646/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.64.up_proj:  29%|██▉       | 10647/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.64.down_proj:  29%|██▉       | 10648/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.65.gate_proj:  29%|██▉       | 10649/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.65.up_proj:  29%|██▉       | 10650/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.65.down_proj:  29%|██▉       | 10651/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.66.gate_proj:  29%|██▉       | 10652/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.66.up_proj:  29%|██▉       | 10653/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.66.down_proj:  29%|██▉       | 10654/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.67.gate_proj:  29%|██▉       | 10655/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.67.up_proj:  29%|██▉       | 10656/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.67.down_proj:  29%|██▉       | 10657/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.68.gate_proj:  29%|██▉       | 10658/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.68.up_proj:  29%|██▉       | 10659/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.68.down_proj:  29%|██▉       | 10660/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.69.gate_proj:  29%|██▉       | 10661/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.69.up_proj:  29%|██▉       | 10662/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.69.down_proj:  29%|██▉       | 10663/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.70.gate_proj:  29%|██▉       | 10664/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.70.up_proj:  29%|██▉       | 10665/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.70.down_proj:  29%|██▉       | 10666/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.71.gate_proj:  29%|██▉       | 10667/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.71.up_proj:  29%|██▉       | 10668/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.71.down_proj:  29%|██▉       | 10669/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.72.gate_proj:  29%|██▉       | 10670/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.72.up_proj:  29%|██▉       | 10671/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.72.down_proj:  29%|██▉       | 10672/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.73.gate_proj:  29%|██▉       | 10673/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.73.up_proj:  29%|██▉       | 10674/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.73.down_proj:  29%|██▉       | 10675/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.74.gate_proj:  29%|██▉       | 10676/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.74.up_proj:  29%|██▉       | 10677/36566 [00:10<00:23, 1125.48it/s]  
packing model.layers.26.mlp.experts.74.down_proj:  29%|██▉       | 10678/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.75.gate_proj:  29%|██▉       | 10679/36566 [00:10<00:23, 1125.48it/s]
packing model.layers.26.mlp.experts.75.up_proj:  29%|██▉       | 10680/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.75.down_proj:  29%|██▉       | 10681/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.76.gate_proj:  29%|██▉       | 10682/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.76.up_proj:  29%|██▉       | 10683/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.76.down_proj:  29%|██▉       | 10684/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.77.gate_proj:  29%|██▉       | 10685/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.77.up_proj:  29%|██▉       | 10686/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.77.down_proj:  29%|██▉       | 10687/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.78.gate_proj:  29%|██▉       | 10688/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.78.up_proj:  29%|██▉       | 10689/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.78.down_proj:  29%|██▉       | 10690/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.79.gate_proj:  29%|██▉       | 10691/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.79.up_proj:  29%|██▉       | 10692/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.79.down_proj:  29%|██▉       | 10693/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.80.gate_proj:  29%|██▉       | 10694/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.80.up_proj:  29%|██▉       | 10695/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.80.down_proj:  29%|██▉       | 10696/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.81.gate_proj:  29%|██▉       | 10697/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.81.up_proj:  29%|██▉       | 10698/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.81.down_proj:  29%|██▉       | 10699/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.82.gate_proj:  29%|██▉       | 10700/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.82.up_proj:  29%|██▉       | 10701/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.82.down_proj:  29%|██▉       | 10702/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.83.gate_proj:  29%|██▉       | 10703/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.83.up_proj:  29%|██▉       | 10704/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.83.down_proj:  29%|██▉       | 10705/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.84.gate_proj:  29%|██▉       | 10706/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.84.up_proj:  29%|██▉       | 10707/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.84.down_proj:  29%|██▉       | 10708/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.85.gate_proj:  29%|██▉       | 10709/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.85.up_proj:  29%|██▉       | 10710/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.85.down_proj:  29%|██▉       | 10711/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.86.gate_proj:  29%|██▉       | 10712/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.86.up_proj:  29%|██▉       | 10713/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.86.down_proj:  29%|██▉       | 10714/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.87.gate_proj:  29%|██▉       | 10715/36566 [00:10<00:22, 1125.48it/s]
packing model.layers.26.mlp.experts.87.up_proj:  29%|██▉       | 10716/36566 [00:10<00:22, 1125.48it/s]  
packing model.layers.26.mlp.experts.87.up_proj:  29%|██▉       | 10717/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.87.down_proj:  29%|██▉       | 10717/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.88.gate_proj:  29%|██▉       | 10718/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.88.up_proj:  29%|██▉       | 10719/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.88.down_proj:  29%|██▉       | 10720/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.89.gate_proj:  29%|██▉       | 10721/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.89.up_proj:  29%|██▉       | 10722/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.89.down_proj:  29%|██▉       | 10723/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.90.gate_proj:  29%|██▉       | 10724/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.90.up_proj:  29%|██▉       | 10725/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.90.down_proj:  29%|██▉       | 10726/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.91.gate_proj:  29%|██▉       | 10727/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.91.up_proj:  29%|██▉       | 10728/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.91.down_proj:  29%|██▉       | 10729/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.92.gate_proj:  29%|██▉       | 10730/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.92.up_proj:  29%|██▉       | 10731/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.92.down_proj:  29%|██▉       | 10732/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.93.gate_proj:  29%|██▉       | 10733/36566 [00:10<00:23, 1123.12it/s]
packing model.layers.26.mlp.experts.93.up_proj:  29%|██▉       | 10734/36566 [00:10<00:23, 1123.12it/s]  
packing model.layers.26.mlp.experts.93.down_proj:  29%|██▉       | 10735/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.94.gate_proj:  29%|██▉       | 10736/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.94.up_proj:  29%|██▉       | 10737/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.94.down_proj:  29%|██▉       | 10738/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.95.gate_proj:  29%|██▉       | 10739/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.95.up_proj:  29%|██▉       | 10740/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.95.down_proj:  29%|██▉       | 10741/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.96.gate_proj:  29%|██▉       | 10742/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.96.up_proj:  29%|██▉       | 10743/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.96.down_proj:  29%|██▉       | 10744/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.97.gate_proj:  29%|██▉       | 10745/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.97.up_proj:  29%|██▉       | 10746/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.97.down_proj:  29%|██▉       | 10747/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.98.gate_proj:  29%|██▉       | 10748/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.98.up_proj:  29%|██▉       | 10749/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.98.down_proj:  29%|██▉       | 10750/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.99.gate_proj:  29%|██▉       | 10751/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.99.up_proj:  29%|██▉       | 10752/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.99.down_proj:  29%|██▉       | 10753/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.100.gate_proj:  29%|██▉       | 10754/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.100.up_proj:  29%|██▉       | 10755/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.100.down_proj:  29%|██▉       | 10756/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.101.gate_proj:  29%|██▉       | 10757/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.101.up_proj:  29%|██▉       | 10758/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.101.down_proj:  29%|██▉       | 10759/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.102.gate_proj:  29%|██▉       | 10760/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.102.up_proj:  29%|██▉       | 10761/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.102.down_proj:  29%|██▉       | 10762/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.103.gate_proj:  29%|██▉       | 10763/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.103.up_proj:  29%|██▉       | 10764/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.103.down_proj:  29%|██▉       | 10765/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.104.gate_proj:  29%|██▉       | 10766/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.104.up_proj:  29%|██▉       | 10767/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.104.down_proj:  29%|██▉       | 10768/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.105.gate_proj:  29%|██▉       | 10769/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.105.up_proj:  29%|██▉       | 10770/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.105.down_proj:  29%|██▉       | 10771/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.106.gate_proj:  29%|██▉       | 10772/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.106.up_proj:  29%|██▉       | 10773/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.106.down_proj:  29%|██▉       | 10774/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.107.gate_proj:  29%|██▉       | 10775/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.107.up_proj:  29%|██▉       | 10776/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.107.down_proj:  29%|██▉       | 10777/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.108.gate_proj:  29%|██▉       | 10778/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.108.up_proj:  29%|██▉       | 10779/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.108.down_proj:  29%|██▉       | 10780/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.109.gate_proj:  29%|██▉       | 10781/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.109.up_proj:  29%|██▉       | 10782/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.109.down_proj:  29%|██▉       | 10783/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.110.gate_proj:  29%|██▉       | 10784/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.110.up_proj:  29%|██▉       | 10785/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.110.down_proj:  29%|██▉       | 10786/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.111.gate_proj:  30%|██▉       | 10787/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.111.up_proj:  30%|██▉       | 10788/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.111.down_proj:  30%|██▉       | 10789/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.112.gate_proj:  30%|██▉       | 10790/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.112.up_proj:  30%|██▉       | 10791/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.112.down_proj:  30%|██▉       | 10792/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.113.gate_proj:  30%|██▉       | 10793/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.113.up_proj:  30%|██▉       | 10794/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.113.down_proj:  30%|██▉       | 10795/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.114.gate_proj:  30%|██▉       | 10796/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.114.up_proj:  30%|██▉       | 10797/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.114.down_proj:  30%|██▉       | 10798/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.115.gate_proj:  30%|██▉       | 10799/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.115.up_proj:  30%|██▉       | 10800/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.115.down_proj:  30%|██▉       | 10801/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.116.gate_proj:  30%|██▉       | 10802/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.116.up_proj:  30%|██▉       | 10803/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.116.down_proj:  30%|██▉       | 10804/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.117.gate_proj:  30%|██▉       | 10805/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.117.up_proj:  30%|██▉       | 10806/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.117.down_proj:  30%|██▉       | 10807/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.118.gate_proj:  30%|██▉       | 10808/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.118.up_proj:  30%|██▉       | 10809/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.118.down_proj:  30%|██▉       | 10810/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.119.gate_proj:  30%|██▉       | 10811/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.119.up_proj:  30%|██▉       | 10812/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.119.down_proj:  30%|██▉       | 10813/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.120.gate_proj:  30%|██▉       | 10814/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.120.up_proj:  30%|██▉       | 10815/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.120.down_proj:  30%|██▉       | 10816/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.121.gate_proj:  30%|██▉       | 10817/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.121.up_proj:  30%|██▉       | 10818/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.121.down_proj:  30%|██▉       | 10819/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.122.gate_proj:  30%|██▉       | 10820/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.122.up_proj:  30%|██▉       | 10821/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.122.down_proj:  30%|██▉       | 10822/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.123.gate_proj:  30%|██▉       | 10823/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.123.up_proj:  30%|██▉       | 10824/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.123.down_proj:  30%|██▉       | 10825/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.124.gate_proj:  30%|██▉       | 10826/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.124.up_proj:  30%|██▉       | 10827/36566 [00:10<00:22, 1123.12it/s]  
packing model.layers.26.mlp.experts.124.down_proj:  30%|██▉       | 10828/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.125.gate_proj:  30%|██▉       | 10829/36566 [00:10<00:22, 1123.12it/s]
packing model.layers.26.mlp.experts.125.gate_proj:  30%|██▉       | 10830/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.26.mlp.experts.125.up_proj:  30%|██▉       | 10830/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.26.mlp.experts.125.down_proj:  30%|██▉       | 10831/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.26.mlp.experts.126.gate_proj:  30%|██▉       | 10832/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.26.mlp.experts.126.up_proj:  30%|██▉       | 10833/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.26.mlp.experts.126.down_proj:  30%|██▉       | 10834/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.26.mlp.experts.127.gate_proj:  30%|██▉       | 10835/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.26.mlp.experts.127.up_proj:  30%|██▉       | 10836/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.26.mlp.experts.127.down_proj:  30%|██▉       | 10837/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.27.mlp.experts.0.gate_proj:  30%|██▉       | 10838/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.27.mlp.experts.0.up_proj:  30%|██▉       | 10839/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.27.mlp.experts.0.down_proj:  30%|██▉       | 10840/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.27.mlp.experts.1.gate_proj:  30%|██▉       | 10841/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.27.mlp.experts.1.up_proj:  30%|██▉       | 10842/36566 [00:10<00:23, 1118.35it/s]  
packing model.layers.27.mlp.experts.1.down_proj:  30%|██▉       | 10843/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.27.mlp.experts.2.gate_proj:  30%|██▉       | 10844/36566 [00:10<00:23, 1118.35it/s]
packing model.layers.27.mlp.experts.2.up_proj:  30%|██▉       | 10845/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.2.down_proj:  30%|██▉       | 10846/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.3.gate_proj:  30%|██▉       | 10847/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.3.up_proj:  30%|██▉       | 10848/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.3.down_proj:  30%|██▉       | 10849/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.4.gate_proj:  30%|██▉       | 10850/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.4.up_proj:  30%|██▉       | 10851/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.4.down_proj:  30%|██▉       | 10852/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.5.gate_proj:  30%|██▉       | 10853/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.5.up_proj:  30%|██▉       | 10854/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.5.down_proj:  30%|██▉       | 10855/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.6.gate_proj:  30%|██▉       | 10856/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.6.up_proj:  30%|██▉       | 10857/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.6.down_proj:  30%|██▉       | 10858/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.7.gate_proj:  30%|██▉       | 10859/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.7.up_proj:  30%|██▉       | 10860/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.7.down_proj:  30%|██▉       | 10861/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.8.gate_proj:  30%|██▉       | 10862/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.8.up_proj:  30%|██▉       | 10863/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.8.down_proj:  30%|██▉       | 10864/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.9.gate_proj:  30%|██▉       | 10865/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.9.up_proj:  30%|██▉       | 10866/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.9.down_proj:  30%|██▉       | 10867/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.10.gate_proj:  30%|██▉       | 10868/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.10.up_proj:  30%|██▉       | 10869/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.10.down_proj:  30%|██▉       | 10870/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.11.gate_proj:  30%|██▉       | 10871/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.11.up_proj:  30%|██▉       | 10872/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.11.down_proj:  30%|██▉       | 10873/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.12.gate_proj:  30%|██▉       | 10874/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.12.up_proj:  30%|██▉       | 10875/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.12.down_proj:  30%|██▉       | 10876/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.13.gate_proj:  30%|██▉       | 10877/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.13.up_proj:  30%|██▉       | 10878/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.13.down_proj:  30%|██▉       | 10879/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.14.gate_proj:  30%|██▉       | 10880/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.14.up_proj:  30%|██▉       | 10881/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.14.down_proj:  30%|██▉       | 10882/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.15.gate_proj:  30%|██▉       | 10883/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.15.up_proj:  30%|██▉       | 10884/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.15.down_proj:  30%|██▉       | 10885/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.16.gate_proj:  30%|██▉       | 10886/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.16.up_proj:  30%|██▉       | 10887/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.16.down_proj:  30%|██▉       | 10888/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.17.gate_proj:  30%|██▉       | 10889/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.17.up_proj:  30%|██▉       | 10890/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.17.down_proj:  30%|██▉       | 10891/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.18.gate_proj:  30%|██▉       | 10892/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.18.up_proj:  30%|██▉       | 10893/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.18.down_proj:  30%|██▉       | 10894/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.19.gate_proj:  30%|██▉       | 10895/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.19.up_proj:  30%|██▉       | 10896/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.19.down_proj:  30%|██▉       | 10897/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.20.gate_proj:  30%|██▉       | 10898/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.20.up_proj:  30%|██▉       | 10899/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.20.down_proj:  30%|██▉       | 10900/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.21.gate_proj:  30%|██▉       | 10901/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.21.up_proj:  30%|██▉       | 10902/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.21.down_proj:  30%|██▉       | 10903/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.22.gate_proj:  30%|██▉       | 10904/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.22.up_proj:  30%|██▉       | 10905/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.22.down_proj:  30%|██▉       | 10906/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.23.gate_proj:  30%|██▉       | 10907/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.23.up_proj:  30%|██▉       | 10908/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.23.down_proj:  30%|██▉       | 10909/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.24.gate_proj:  30%|██▉       | 10910/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.24.up_proj:  30%|██▉       | 10911/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.24.down_proj:  30%|██▉       | 10912/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.25.gate_proj:  30%|██▉       | 10913/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.25.up_proj:  30%|██▉       | 10914/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.25.down_proj:  30%|██▉       | 10915/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.26.gate_proj:  30%|██▉       | 10916/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.26.up_proj:  30%|██▉       | 10917/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.26.down_proj:  30%|██▉       | 10918/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.27.gate_proj:  30%|██▉       | 10919/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.27.up_proj:  30%|██▉       | 10920/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.27.down_proj:  30%|██▉       | 10921/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.28.gate_proj:  30%|██▉       | 10922/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.28.up_proj:  30%|██▉       | 10923/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.28.down_proj:  30%|██▉       | 10924/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.29.gate_proj:  30%|██▉       | 10925/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.29.up_proj:  30%|██▉       | 10926/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.29.down_proj:  30%|██▉       | 10927/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.30.gate_proj:  30%|██▉       | 10928/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.30.up_proj:  30%|██▉       | 10929/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.30.down_proj:  30%|██▉       | 10930/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.31.gate_proj:  30%|██▉       | 10931/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.31.up_proj:  30%|██▉       | 10932/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.31.down_proj:  30%|██▉       | 10933/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.32.gate_proj:  30%|██▉       | 10934/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.32.up_proj:  30%|██▉       | 10935/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.32.down_proj:  30%|██▉       | 10936/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.33.gate_proj:  30%|██▉       | 10937/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.33.up_proj:  30%|██▉       | 10938/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.33.down_proj:  30%|██▉       | 10939/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.34.gate_proj:  30%|██▉       | 10940/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.34.up_proj:  30%|██▉       | 10941/36566 [00:10<00:22, 1118.35it/s]  
packing model.layers.27.mlp.experts.34.down_proj:  30%|██▉       | 10942/36566 [00:10<00:22, 1118.35it/s]
packing model.layers.27.mlp.experts.34.down_proj:  30%|██▉       | 10943/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.35.gate_proj:  30%|██▉       | 10943/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.35.up_proj:  30%|██▉       | 10944/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.35.down_proj:  30%|██▉       | 10945/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.36.gate_proj:  30%|██▉       | 10946/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.36.up_proj:  30%|██▉       | 10947/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.36.down_proj:  30%|██▉       | 10948/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.37.gate_proj:  30%|██▉       | 10949/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.37.up_proj:  30%|██▉       | 10950/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.37.down_proj:  30%|██▉       | 10951/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.38.gate_proj:  30%|██▉       | 10952/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.38.up_proj:  30%|██▉       | 10953/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.38.down_proj:  30%|██▉       | 10954/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.39.gate_proj:  30%|██▉       | 10955/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.39.up_proj:  30%|██▉       | 10956/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.39.down_proj:  30%|██▉       | 10957/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.40.gate_proj:  30%|██▉       | 10958/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.40.up_proj:  30%|██▉       | 10959/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.40.down_proj:  30%|██▉       | 10960/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.41.gate_proj:  30%|██▉       | 10961/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.41.up_proj:  30%|██▉       | 10962/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.41.down_proj:  30%|██▉       | 10963/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.42.gate_proj:  30%|██▉       | 10964/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.42.up_proj:  30%|██▉       | 10965/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.42.down_proj:  30%|██▉       | 10966/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.43.gate_proj:  30%|██▉       | 10967/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.43.up_proj:  30%|██▉       | 10968/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.43.down_proj:  30%|██▉       | 10969/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.44.gate_proj:  30%|███       | 10970/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.44.up_proj:  30%|███       | 10971/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.44.down_proj:  30%|███       | 10972/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.45.gate_proj:  30%|███       | 10973/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.45.up_proj:  30%|███       | 10974/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.45.down_proj:  30%|███       | 10975/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.46.gate_proj:  30%|███       | 10976/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.46.up_proj:  30%|███       | 10977/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.46.down_proj:  30%|███       | 10978/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.47.gate_proj:  30%|███       | 10979/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.47.up_proj:  30%|███       | 10980/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.47.down_proj:  30%|███       | 10981/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.48.gate_proj:  30%|███       | 10982/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.48.up_proj:  30%|███       | 10983/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.48.down_proj:  30%|███       | 10984/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.49.gate_proj:  30%|███       | 10985/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.49.up_proj:  30%|███       | 10986/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.49.down_proj:  30%|███       | 10987/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.50.gate_proj:  30%|███       | 10988/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.50.up_proj:  30%|███       | 10989/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.50.down_proj:  30%|███       | 10990/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.51.gate_proj:  30%|███       | 10991/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.51.up_proj:  30%|███       | 10992/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.51.down_proj:  30%|███       | 10993/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.52.gate_proj:  30%|███       | 10994/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.52.up_proj:  30%|███       | 10995/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.52.down_proj:  30%|███       | 10996/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.53.gate_proj:  30%|███       | 10997/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.53.up_proj:  30%|███       | 10998/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.53.down_proj:  30%|███       | 10999/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.54.gate_proj:  30%|███       | 11000/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.54.up_proj:  30%|███       | 11001/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.54.down_proj:  30%|███       | 11002/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.55.gate_proj:  30%|███       | 11003/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.55.up_proj:  30%|███       | 11004/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.55.down_proj:  30%|███       | 11005/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.56.gate_proj:  30%|███       | 11006/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.56.up_proj:  30%|███       | 11007/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.56.down_proj:  30%|███       | 11008/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.57.gate_proj:  30%|███       | 11009/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.57.up_proj:  30%|███       | 11010/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.57.down_proj:  30%|███       | 11011/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.58.gate_proj:  30%|███       | 11012/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.58.up_proj:  30%|███       | 11013/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.58.down_proj:  30%|███       | 11014/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.59.gate_proj:  30%|███       | 11015/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.59.up_proj:  30%|███       | 11016/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.59.down_proj:  30%|███       | 11017/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.60.gate_proj:  30%|███       | 11018/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.60.up_proj:  30%|███       | 11019/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.60.down_proj:  30%|███       | 11020/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.61.gate_proj:  30%|███       | 11021/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.61.up_proj:  30%|███       | 11022/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.61.down_proj:  30%|███       | 11023/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.62.gate_proj:  30%|███       | 11024/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.62.up_proj:  30%|███       | 11025/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.62.down_proj:  30%|███       | 11026/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.63.gate_proj:  30%|███       | 11027/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.63.up_proj:  30%|███       | 11028/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.63.down_proj:  30%|███       | 11029/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.64.gate_proj:  30%|███       | 11030/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.64.up_proj:  30%|███       | 11031/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.64.down_proj:  30%|███       | 11032/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.65.gate_proj:  30%|███       | 11033/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.65.up_proj:  30%|███       | 11034/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.65.down_proj:  30%|███       | 11035/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.66.gate_proj:  30%|███       | 11036/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.66.up_proj:  30%|███       | 11037/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.66.down_proj:  30%|███       | 11038/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.67.gate_proj:  30%|███       | 11039/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.67.up_proj:  30%|███       | 11040/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.67.down_proj:  30%|███       | 11041/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.68.gate_proj:  30%|███       | 11042/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.68.up_proj:  30%|███       | 11043/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.68.down_proj:  30%|███       | 11044/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.69.gate_proj:  30%|███       | 11045/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.69.up_proj:  30%|███       | 11046/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.69.down_proj:  30%|███       | 11047/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.70.gate_proj:  30%|███       | 11048/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.70.up_proj:  30%|███       | 11049/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.70.down_proj:  30%|███       | 11050/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.71.gate_proj:  30%|███       | 11051/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.71.up_proj:  30%|███       | 11052/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.71.down_proj:  30%|███       | 11053/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.72.gate_proj:  30%|███       | 11054/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.72.up_proj:  30%|███       | 11055/36566 [00:10<00:22, 1118.79it/s]  
packing model.layers.27.mlp.experts.72.down_proj:  30%|███       | 11056/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.73.gate_proj:  30%|███       | 11057/36566 [00:10<00:22, 1118.79it/s]
packing model.layers.27.mlp.experts.73.gate_proj:  30%|███       | 11058/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.73.up_proj:  30%|███       | 11058/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.73.down_proj:  30%|███       | 11059/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.74.gate_proj:  30%|███       | 11060/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.74.up_proj:  30%|███       | 11061/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.74.down_proj:  30%|███       | 11062/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.75.gate_proj:  30%|███       | 11063/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.75.up_proj:  30%|███       | 11064/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.75.down_proj:  30%|███       | 11065/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.76.gate_proj:  30%|███       | 11066/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.76.up_proj:  30%|███       | 11067/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.76.down_proj:  30%|███       | 11068/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.77.gate_proj:  30%|███       | 11069/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.77.up_proj:  30%|███       | 11070/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.77.down_proj:  30%|███       | 11071/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.78.gate_proj:  30%|███       | 11072/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.78.up_proj:  30%|███       | 11073/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.78.down_proj:  30%|███       | 11074/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.79.gate_proj:  30%|███       | 11075/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.79.up_proj:  30%|███       | 11076/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.79.down_proj:  30%|███       | 11077/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.80.gate_proj:  30%|███       | 11078/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.80.up_proj:  30%|███       | 11079/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.80.down_proj:  30%|███       | 11080/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.81.gate_proj:  30%|███       | 11081/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.81.up_proj:  30%|███       | 11082/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.81.down_proj:  30%|███       | 11083/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.82.gate_proj:  30%|███       | 11084/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.82.up_proj:  30%|███       | 11085/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.82.down_proj:  30%|███       | 11086/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.83.gate_proj:  30%|███       | 11087/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.83.up_proj:  30%|███       | 11088/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.83.down_proj:  30%|███       | 11089/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.84.gate_proj:  30%|███       | 11090/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.84.up_proj:  30%|███       | 11091/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.84.down_proj:  30%|███       | 11092/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.85.gate_proj:  30%|███       | 11093/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.85.up_proj:  30%|███       | 11094/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.85.down_proj:  30%|███       | 11095/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.86.gate_proj:  30%|███       | 11096/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.86.up_proj:  30%|███       | 11097/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.86.down_proj:  30%|███       | 11098/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.87.gate_proj:  30%|███       | 11099/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.87.up_proj:  30%|███       | 11100/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.87.down_proj:  30%|███       | 11101/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.88.gate_proj:  30%|███       | 11102/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.88.up_proj:  30%|███       | 11103/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.88.down_proj:  30%|███       | 11104/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.89.gate_proj:  30%|███       | 11105/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.89.up_proj:  30%|███       | 11106/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.89.down_proj:  30%|███       | 11107/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.90.gate_proj:  30%|███       | 11108/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.90.up_proj:  30%|███       | 11109/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.90.down_proj:  30%|███       | 11110/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.91.gate_proj:  30%|███       | 11111/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.91.up_proj:  30%|███       | 11112/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.91.down_proj:  30%|███       | 11113/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.92.gate_proj:  30%|███       | 11114/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.92.up_proj:  30%|███       | 11115/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.92.down_proj:  30%|███       | 11116/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.93.gate_proj:  30%|███       | 11117/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.93.up_proj:  30%|███       | 11118/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.93.down_proj:  30%|███       | 11119/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.94.gate_proj:  30%|███       | 11120/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.94.up_proj:  30%|███       | 11121/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.94.down_proj:  30%|███       | 11122/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.95.gate_proj:  30%|███       | 11123/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.95.up_proj:  30%|███       | 11124/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.95.down_proj:  30%|███       | 11125/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.96.gate_proj:  30%|███       | 11126/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.96.up_proj:  30%|███       | 11127/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.96.down_proj:  30%|███       | 11128/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.97.gate_proj:  30%|███       | 11129/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.97.up_proj:  30%|███       | 11130/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.97.down_proj:  30%|███       | 11131/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.98.gate_proj:  30%|███       | 11132/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.98.up_proj:  30%|███       | 11133/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.98.down_proj:  30%|███       | 11134/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.99.gate_proj:  30%|███       | 11135/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.99.up_proj:  30%|███       | 11136/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.99.down_proj:  30%|███       | 11137/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.100.gate_proj:  30%|███       | 11138/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.100.up_proj:  30%|███       | 11139/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.100.down_proj:  30%|███       | 11140/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.101.gate_proj:  30%|███       | 11141/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.101.up_proj:  30%|███       | 11142/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.101.down_proj:  30%|███       | 11143/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.102.gate_proj:  30%|███       | 11144/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.102.up_proj:  30%|███       | 11145/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.102.down_proj:  30%|███       | 11146/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.103.gate_proj:  30%|███       | 11147/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.103.up_proj:  30%|███       | 11148/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.103.down_proj:  30%|███       | 11149/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.104.gate_proj:  30%|███       | 11150/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.104.up_proj:  30%|███       | 11151/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.104.down_proj:  30%|███       | 11152/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.105.gate_proj:  31%|███       | 11153/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.105.up_proj:  31%|███       | 11154/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.105.down_proj:  31%|███       | 11155/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.106.gate_proj:  31%|███       | 11156/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.106.up_proj:  31%|███       | 11157/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.106.down_proj:  31%|███       | 11158/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.107.gate_proj:  31%|███       | 11159/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.107.up_proj:  31%|███       | 11160/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.107.down_proj:  31%|███       | 11161/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.108.gate_proj:  31%|███       | 11162/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.108.up_proj:  31%|███       | 11163/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.108.down_proj:  31%|███       | 11164/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.109.gate_proj:  31%|███       | 11165/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.109.up_proj:  31%|███       | 11166/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.109.down_proj:  31%|███       | 11167/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.110.gate_proj:  31%|███       | 11168/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.110.up_proj:  31%|███       | 11169/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.110.down_proj:  31%|███       | 11170/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.111.gate_proj:  31%|███       | 11171/36566 [00:10<00:22, 1126.35it/s]
packing model.layers.27.mlp.experts.111.up_proj:  31%|███       | 11172/36566 [00:10<00:22, 1126.35it/s]  
packing model.layers.27.mlp.experts.111.up_proj:  31%|███       | 11173/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.111.down_proj:  31%|███       | 11173/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.112.gate_proj:  31%|███       | 11174/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.112.up_proj:  31%|███       | 11175/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.112.down_proj:  31%|███       | 11176/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.113.gate_proj:  31%|███       | 11177/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.113.up_proj:  31%|███       | 11178/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.113.down_proj:  31%|███       | 11179/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.114.gate_proj:  31%|███       | 11180/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.114.up_proj:  31%|███       | 11181/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.114.down_proj:  31%|███       | 11182/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.115.gate_proj:  31%|███       | 11183/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.115.up_proj:  31%|███       | 11184/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.115.down_proj:  31%|███       | 11185/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.116.gate_proj:  31%|███       | 11186/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.116.up_proj:  31%|███       | 11187/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.116.down_proj:  31%|███       | 11188/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.117.gate_proj:  31%|███       | 11189/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.117.up_proj:  31%|███       | 11190/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.117.down_proj:  31%|███       | 11191/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.118.gate_proj:  31%|███       | 11192/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.118.up_proj:  31%|███       | 11193/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.118.down_proj:  31%|███       | 11194/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.119.gate_proj:  31%|███       | 11195/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.119.up_proj:  31%|███       | 11196/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.119.down_proj:  31%|███       | 11197/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.120.gate_proj:  31%|███       | 11198/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.120.up_proj:  31%|███       | 11199/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.120.down_proj:  31%|███       | 11200/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.121.gate_proj:  31%|███       | 11201/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.121.up_proj:  31%|███       | 11202/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.121.down_proj:  31%|███       | 11203/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.122.gate_proj:  31%|███       | 11204/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.122.up_proj:  31%|███       | 11205/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.122.down_proj:  31%|███       | 11206/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.123.gate_proj:  31%|███       | 11207/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.123.up_proj:  31%|███       | 11208/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.123.down_proj:  31%|███       | 11209/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.124.gate_proj:  31%|███       | 11210/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.124.up_proj:  31%|███       | 11211/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.124.down_proj:  31%|███       | 11212/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.125.gate_proj:  31%|███       | 11213/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.125.up_proj:  31%|███       | 11214/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.125.down_proj:  31%|███       | 11215/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.126.gate_proj:  31%|███       | 11216/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.126.up_proj:  31%|███       | 11217/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.126.down_proj:  31%|███       | 11218/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.127.gate_proj:  31%|███       | 11219/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.27.mlp.experts.127.up_proj:  31%|███       | 11220/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.27.mlp.experts.127.down_proj:  31%|███       | 11221/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.0.gate_proj:  31%|███       | 11222/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.0.up_proj:  31%|███       | 11223/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.0.down_proj:  31%|███       | 11224/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.1.gate_proj:  31%|███       | 11225/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.1.up_proj:  31%|███       | 11226/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.1.down_proj:  31%|███       | 11227/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.2.gate_proj:  31%|███       | 11228/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.2.up_proj:  31%|███       | 11229/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.2.down_proj:  31%|███       | 11230/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.3.gate_proj:  31%|███       | 11231/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.3.up_proj:  31%|███       | 11232/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.3.down_proj:  31%|███       | 11233/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.4.gate_proj:  31%|███       | 11234/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.4.up_proj:  31%|███       | 11235/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.4.down_proj:  31%|███       | 11236/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.5.gate_proj:  31%|███       | 11237/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.5.up_proj:  31%|███       | 11238/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.5.down_proj:  31%|███       | 11239/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.6.gate_proj:  31%|███       | 11240/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.6.up_proj:  31%|███       | 11241/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.6.down_proj:  31%|███       | 11242/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.7.gate_proj:  31%|███       | 11243/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.7.up_proj:  31%|███       | 11244/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.7.down_proj:  31%|███       | 11245/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.8.gate_proj:  31%|███       | 11246/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.8.up_proj:  31%|███       | 11247/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.8.down_proj:  31%|███       | 11248/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.9.gate_proj:  31%|███       | 11249/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.9.up_proj:  31%|███       | 11250/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.9.down_proj:  31%|███       | 11251/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.10.gate_proj:  31%|███       | 11252/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.10.up_proj:  31%|███       | 11253/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.10.down_proj:  31%|███       | 11254/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.11.gate_proj:  31%|███       | 11255/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.11.up_proj:  31%|███       | 11256/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.11.down_proj:  31%|███       | 11257/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.12.gate_proj:  31%|███       | 11258/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.12.up_proj:  31%|███       | 11259/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.12.down_proj:  31%|███       | 11260/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.13.gate_proj:  31%|███       | 11261/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.13.up_proj:  31%|███       | 11262/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.13.down_proj:  31%|███       | 11263/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.14.gate_proj:  31%|███       | 11264/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.14.up_proj:  31%|███       | 11265/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.14.down_proj:  31%|███       | 11266/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.15.gate_proj:  31%|███       | 11267/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.15.up_proj:  31%|███       | 11268/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.15.down_proj:  31%|███       | 11269/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.16.gate_proj:  31%|███       | 11270/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.16.up_proj:  31%|███       | 11271/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.16.down_proj:  31%|███       | 11272/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.17.gate_proj:  31%|███       | 11273/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.17.up_proj:  31%|███       | 11274/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.17.down_proj:  31%|███       | 11275/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.18.gate_proj:  31%|███       | 11276/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.18.up_proj:  31%|███       | 11277/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.18.down_proj:  31%|███       | 11278/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.19.gate_proj:  31%|███       | 11279/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.19.up_proj:  31%|███       | 11280/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.19.down_proj:  31%|███       | 11281/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.20.gate_proj:  31%|███       | 11282/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.20.up_proj:  31%|███       | 11283/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.20.down_proj:  31%|███       | 11284/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.21.gate_proj:  31%|███       | 11285/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.21.up_proj:  31%|███       | 11286/36566 [00:10<00:22, 1133.27it/s]  
packing model.layers.28.mlp.experts.21.down_proj:  31%|███       | 11287/36566 [00:10<00:22, 1133.27it/s]
packing model.layers.28.mlp.experts.21.down_proj:  31%|███       | 11288/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.22.gate_proj:  31%|███       | 11288/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.22.up_proj:  31%|███       | 11289/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.22.down_proj:  31%|███       | 11290/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.23.gate_proj:  31%|███       | 11291/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.23.up_proj:  31%|███       | 11292/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.23.down_proj:  31%|███       | 11293/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.24.gate_proj:  31%|███       | 11294/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.24.up_proj:  31%|███       | 11295/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.24.down_proj:  31%|███       | 11296/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.25.gate_proj:  31%|███       | 11297/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.25.up_proj:  31%|███       | 11298/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.25.down_proj:  31%|███       | 11299/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.26.gate_proj:  31%|███       | 11300/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.26.up_proj:  31%|███       | 11301/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.26.down_proj:  31%|███       | 11302/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.27.gate_proj:  31%|███       | 11303/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.27.up_proj:  31%|███       | 11304/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.27.down_proj:  31%|███       | 11305/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.28.gate_proj:  31%|███       | 11306/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.28.up_proj:  31%|███       | 11307/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.28.down_proj:  31%|███       | 11308/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.29.gate_proj:  31%|███       | 11309/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.29.up_proj:  31%|███       | 11310/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.29.down_proj:  31%|███       | 11311/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.30.gate_proj:  31%|███       | 11312/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.30.up_proj:  31%|███       | 11313/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.30.down_proj:  31%|███       | 11314/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.31.gate_proj:  31%|███       | 11315/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.31.up_proj:  31%|███       | 11316/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.31.down_proj:  31%|███       | 11317/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.32.gate_proj:  31%|███       | 11318/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.32.up_proj:  31%|███       | 11319/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.32.down_proj:  31%|███       | 11320/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.33.gate_proj:  31%|███       | 11321/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.33.up_proj:  31%|███       | 11322/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.33.down_proj:  31%|███       | 11323/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.34.gate_proj:  31%|███       | 11324/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.34.up_proj:  31%|███       | 11325/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.34.down_proj:  31%|███       | 11326/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.35.gate_proj:  31%|███       | 11327/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.35.up_proj:  31%|███       | 11328/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.35.down_proj:  31%|███       | 11329/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.36.gate_proj:  31%|███       | 11330/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.36.up_proj:  31%|███       | 11331/36566 [00:10<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.36.down_proj:  31%|███       | 11332/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.37.gate_proj:  31%|███       | 11333/36566 [00:10<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.37.up_proj:  31%|███       | 11334/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.37.down_proj:  31%|███       | 11335/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.38.gate_proj:  31%|███       | 11336/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.38.up_proj:  31%|███       | 11337/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.38.down_proj:  31%|███       | 11338/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.39.gate_proj:  31%|███       | 11339/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.39.up_proj:  31%|███       | 11340/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.39.down_proj:  31%|███       | 11341/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.40.gate_proj:  31%|███       | 11342/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.40.up_proj:  31%|███       | 11343/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.40.down_proj:  31%|███       | 11344/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.41.gate_proj:  31%|███       | 11345/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.41.up_proj:  31%|███       | 11346/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.41.down_proj:  31%|███       | 11347/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.42.gate_proj:  31%|███       | 11348/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.42.up_proj:  31%|███       | 11349/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.42.down_proj:  31%|███       | 11350/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.43.gate_proj:  31%|███       | 11351/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.43.up_proj:  31%|███       | 11352/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.43.down_proj:  31%|███       | 11353/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.44.gate_proj:  31%|███       | 11354/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.44.up_proj:  31%|███       | 11355/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.44.down_proj:  31%|███       | 11356/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.45.gate_proj:  31%|███       | 11357/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.45.up_proj:  31%|███       | 11358/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.45.down_proj:  31%|███       | 11359/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.46.gate_proj:  31%|███       | 11360/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.46.up_proj:  31%|███       | 11361/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.46.down_proj:  31%|███       | 11362/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.47.gate_proj:  31%|███       | 11363/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.47.up_proj:  31%|███       | 11364/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.47.down_proj:  31%|███       | 11365/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.48.gate_proj:  31%|███       | 11366/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.48.up_proj:  31%|███       | 11367/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.48.down_proj:  31%|███       | 11368/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.49.gate_proj:  31%|███       | 11369/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.49.up_proj:  31%|███       | 11370/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.49.down_proj:  31%|███       | 11371/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.50.gate_proj:  31%|███       | 11372/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.50.up_proj:  31%|███       | 11373/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.50.down_proj:  31%|███       | 11374/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.51.gate_proj:  31%|███       | 11375/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.51.up_proj:  31%|███       | 11376/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.51.down_proj:  31%|███       | 11377/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.52.gate_proj:  31%|███       | 11378/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.52.up_proj:  31%|███       | 11379/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.52.down_proj:  31%|███       | 11380/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.53.gate_proj:  31%|███       | 11381/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.53.up_proj:  31%|███       | 11382/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.53.down_proj:  31%|███       | 11383/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.54.gate_proj:  31%|███       | 11384/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.54.up_proj:  31%|███       | 11385/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.54.down_proj:  31%|███       | 11386/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.55.gate_proj:  31%|███       | 11387/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.55.up_proj:  31%|███       | 11388/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.55.down_proj:  31%|███       | 11389/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.56.gate_proj:  31%|███       | 11390/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.56.up_proj:  31%|███       | 11391/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.56.down_proj:  31%|███       | 11392/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.57.gate_proj:  31%|███       | 11393/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.57.up_proj:  31%|███       | 11394/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.57.down_proj:  31%|███       | 11395/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.58.gate_proj:  31%|███       | 11396/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.58.up_proj:  31%|███       | 11397/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.58.down_proj:  31%|███       | 11398/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.59.gate_proj:  31%|███       | 11399/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.59.up_proj:  31%|███       | 11400/36566 [00:11<00:22, 1137.34it/s]  
packing model.layers.28.mlp.experts.59.down_proj:  31%|███       | 11401/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.60.gate_proj:  31%|███       | 11402/36566 [00:11<00:22, 1137.34it/s]
packing model.layers.28.mlp.experts.60.gate_proj:  31%|███       | 11403/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.60.up_proj:  31%|███       | 11403/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.60.down_proj:  31%|███       | 11404/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.61.gate_proj:  31%|███       | 11405/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.61.up_proj:  31%|███       | 11406/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.61.down_proj:  31%|███       | 11407/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.62.gate_proj:  31%|███       | 11408/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.62.up_proj:  31%|███       | 11409/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.62.down_proj:  31%|███       | 11410/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.63.gate_proj:  31%|███       | 11411/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.63.up_proj:  31%|███       | 11412/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.63.down_proj:  31%|███       | 11413/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.64.gate_proj:  31%|███       | 11414/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.64.up_proj:  31%|███       | 11415/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.64.down_proj:  31%|███       | 11416/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.65.gate_proj:  31%|███       | 11417/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.65.up_proj:  31%|███       | 11418/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.65.down_proj:  31%|███       | 11419/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.66.gate_proj:  31%|███       | 11420/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.66.up_proj:  31%|███       | 11421/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.66.down_proj:  31%|███       | 11422/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.67.gate_proj:  31%|███       | 11423/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.67.up_proj:  31%|███       | 11424/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.67.down_proj:  31%|███       | 11425/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.68.gate_proj:  31%|███       | 11426/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.68.up_proj:  31%|███▏      | 11427/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.68.down_proj:  31%|███▏      | 11428/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.69.gate_proj:  31%|███▏      | 11429/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.69.up_proj:  31%|███▏      | 11430/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.69.down_proj:  31%|███▏      | 11431/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.70.gate_proj:  31%|███▏      | 11432/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.70.up_proj:  31%|███▏      | 11433/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.70.down_proj:  31%|███▏      | 11434/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.71.gate_proj:  31%|███▏      | 11435/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.71.up_proj:  31%|███▏      | 11436/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.71.down_proj:  31%|███▏      | 11437/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.72.gate_proj:  31%|███▏      | 11438/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.72.up_proj:  31%|███▏      | 11439/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.72.down_proj:  31%|███▏      | 11440/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.73.gate_proj:  31%|███▏      | 11441/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.73.up_proj:  31%|███▏      | 11442/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.73.down_proj:  31%|███▏      | 11443/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.74.gate_proj:  31%|███▏      | 11444/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.74.up_proj:  31%|███▏      | 11445/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.74.down_proj:  31%|███▏      | 11446/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.75.gate_proj:  31%|███▏      | 11447/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.75.up_proj:  31%|███▏      | 11448/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.75.down_proj:  31%|███▏      | 11449/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.76.gate_proj:  31%|███▏      | 11450/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.76.up_proj:  31%|███▏      | 11451/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.76.down_proj:  31%|███▏      | 11452/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.77.gate_proj:  31%|███▏      | 11453/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.77.up_proj:  31%|███▏      | 11454/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.77.down_proj:  31%|███▏      | 11455/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.78.gate_proj:  31%|███▏      | 11456/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.78.up_proj:  31%|███▏      | 11457/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.78.down_proj:  31%|███▏      | 11458/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.79.gate_proj:  31%|███▏      | 11459/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.79.up_proj:  31%|███▏      | 11460/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.79.down_proj:  31%|███▏      | 11461/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.80.gate_proj:  31%|███▏      | 11462/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.80.up_proj:  31%|███▏      | 11463/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.80.down_proj:  31%|███▏      | 11464/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.81.gate_proj:  31%|███▏      | 11465/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.81.up_proj:  31%|███▏      | 11466/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.81.down_proj:  31%|███▏      | 11467/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.82.gate_proj:  31%|███▏      | 11468/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.82.up_proj:  31%|███▏      | 11469/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.82.down_proj:  31%|███▏      | 11470/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.83.gate_proj:  31%|███▏      | 11471/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.83.up_proj:  31%|███▏      | 11472/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.83.down_proj:  31%|███▏      | 11473/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.84.gate_proj:  31%|███▏      | 11474/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.84.up_proj:  31%|███▏      | 11475/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.84.down_proj:  31%|███▏      | 11476/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.85.gate_proj:  31%|███▏      | 11477/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.85.up_proj:  31%|███▏      | 11478/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.85.down_proj:  31%|███▏      | 11479/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.86.gate_proj:  31%|███▏      | 11480/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.86.up_proj:  31%|███▏      | 11481/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.86.down_proj:  31%|███▏      | 11482/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.87.gate_proj:  31%|███▏      | 11483/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.87.up_proj:  31%|███▏      | 11484/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.87.down_proj:  31%|███▏      | 11485/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.88.gate_proj:  31%|███▏      | 11486/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.88.up_proj:  31%|███▏      | 11487/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.88.down_proj:  31%|███▏      | 11488/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.89.gate_proj:  31%|███▏      | 11489/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.89.up_proj:  31%|███▏      | 11490/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.89.down_proj:  31%|███▏      | 11491/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.90.gate_proj:  31%|███▏      | 11492/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.90.up_proj:  31%|███▏      | 11493/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.90.down_proj:  31%|███▏      | 11494/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.91.gate_proj:  31%|███▏      | 11495/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.91.up_proj:  31%|███▏      | 11496/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.91.down_proj:  31%|███▏      | 11497/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.92.gate_proj:  31%|███▏      | 11498/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.92.up_proj:  31%|███▏      | 11499/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.92.down_proj:  31%|███▏      | 11500/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.93.gate_proj:  31%|███▏      | 11501/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.93.up_proj:  31%|███▏      | 11502/36566 [00:11<00:22, 1139.15it/s]  
packing model.layers.28.mlp.experts.93.down_proj:  31%|███▏      | 11503/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.94.gate_proj:  31%|███▏      | 11504/36566 [00:11<00:22, 1139.15it/s]
packing model.layers.28.mlp.experts.94.up_proj:  31%|███▏      | 11505/36566 [00:11<00:21, 1139.15it/s]  
packing model.layers.28.mlp.experts.94.down_proj:  31%|███▏      | 11506/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.95.gate_proj:  31%|███▏      | 11507/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.95.up_proj:  31%|███▏      | 11508/36566 [00:11<00:21, 1139.15it/s]  
packing model.layers.28.mlp.experts.95.down_proj:  31%|███▏      | 11509/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.96.gate_proj:  31%|███▏      | 11510/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.96.up_proj:  31%|███▏      | 11511/36566 [00:11<00:21, 1139.15it/s]  
packing model.layers.28.mlp.experts.96.down_proj:  31%|███▏      | 11512/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.97.gate_proj:  31%|███▏      | 11513/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.97.up_proj:  31%|███▏      | 11514/36566 [00:11<00:21, 1139.15it/s]  
packing model.layers.28.mlp.experts.97.down_proj:  31%|███▏      | 11515/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.98.gate_proj:  31%|███▏      | 11516/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.98.up_proj:  31%|███▏      | 11517/36566 [00:11<00:21, 1139.15it/s]  
packing model.layers.28.mlp.experts.98.down_proj:  31%|███▏      | 11518/36566 [00:11<00:21, 1139.15it/s]
packing model.layers.28.mlp.experts.98.down_proj:  32%|███▏      | 11519/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.99.gate_proj:  32%|███▏      | 11519/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.99.up_proj:  32%|███▏      | 11520/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.99.down_proj:  32%|███▏      | 11521/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.100.gate_proj:  32%|███▏      | 11522/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.100.up_proj:  32%|███▏      | 11523/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.100.down_proj:  32%|███▏      | 11524/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.101.gate_proj:  32%|███▏      | 11525/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.101.up_proj:  32%|███▏      | 11526/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.101.down_proj:  32%|███▏      | 11527/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.102.gate_proj:  32%|███▏      | 11528/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.102.up_proj:  32%|███▏      | 11529/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.102.down_proj:  32%|███▏      | 11530/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.103.gate_proj:  32%|███▏      | 11531/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.103.up_proj:  32%|███▏      | 11532/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.103.down_proj:  32%|███▏      | 11533/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.104.gate_proj:  32%|███▏      | 11534/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.104.up_proj:  32%|███▏      | 11535/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.104.down_proj:  32%|███▏      | 11536/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.105.gate_proj:  32%|███▏      | 11537/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.105.up_proj:  32%|███▏      | 11538/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.105.down_proj:  32%|███▏      | 11539/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.106.gate_proj:  32%|███▏      | 11540/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.106.up_proj:  32%|███▏      | 11541/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.106.down_proj:  32%|███▏      | 11542/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.107.gate_proj:  32%|███▏      | 11543/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.107.up_proj:  32%|███▏      | 11544/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.107.down_proj:  32%|███▏      | 11545/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.108.gate_proj:  32%|███▏      | 11546/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.108.up_proj:  32%|███▏      | 11547/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.108.down_proj:  32%|███▏      | 11548/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.109.gate_proj:  32%|███▏      | 11549/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.109.up_proj:  32%|███▏      | 11550/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.109.down_proj:  32%|███▏      | 11551/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.110.gate_proj:  32%|███▏      | 11552/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.110.up_proj:  32%|███▏      | 11553/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.110.down_proj:  32%|███▏      | 11554/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.111.gate_proj:  32%|███▏      | 11555/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.111.up_proj:  32%|███▏      | 11556/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.111.down_proj:  32%|███▏      | 11557/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.112.gate_proj:  32%|███▏      | 11558/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.112.up_proj:  32%|███▏      | 11559/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.112.down_proj:  32%|███▏      | 11560/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.113.gate_proj:  32%|███▏      | 11561/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.113.up_proj:  32%|███▏      | 11562/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.113.down_proj:  32%|███▏      | 11563/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.114.gate_proj:  32%|███▏      | 11564/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.114.up_proj:  32%|███▏      | 11565/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.114.down_proj:  32%|███▏      | 11566/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.115.gate_proj:  32%|███▏      | 11567/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.115.up_proj:  32%|███▏      | 11568/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.115.down_proj:  32%|███▏      | 11569/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.116.gate_proj:  32%|███▏      | 11570/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.116.up_proj:  32%|███▏      | 11571/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.116.down_proj:  32%|███▏      | 11572/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.117.gate_proj:  32%|███▏      | 11573/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.117.up_proj:  32%|███▏      | 11574/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.117.down_proj:  32%|███▏      | 11575/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.118.gate_proj:  32%|███▏      | 11576/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.118.up_proj:  32%|███▏      | 11577/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.118.down_proj:  32%|███▏      | 11578/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.119.gate_proj:  32%|███▏      | 11579/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.119.up_proj:  32%|███▏      | 11580/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.119.down_proj:  32%|███▏      | 11581/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.120.gate_proj:  32%|███▏      | 11582/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.120.up_proj:  32%|███▏      | 11583/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.120.down_proj:  32%|███▏      | 11584/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.121.gate_proj:  32%|███▏      | 11585/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.121.up_proj:  32%|███▏      | 11586/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.121.down_proj:  32%|███▏      | 11587/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.122.gate_proj:  32%|███▏      | 11588/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.122.up_proj:  32%|███▏      | 11589/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.122.down_proj:  32%|███▏      | 11590/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.123.gate_proj:  32%|███▏      | 11591/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.123.up_proj:  32%|███▏      | 11592/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.123.down_proj:  32%|███▏      | 11593/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.124.gate_proj:  32%|███▏      | 11594/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.124.up_proj:  32%|███▏      | 11595/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.124.down_proj:  32%|███▏      | 11596/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.125.gate_proj:  32%|███▏      | 11597/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.125.up_proj:  32%|███▏      | 11598/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.125.down_proj:  32%|███▏      | 11599/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.126.gate_proj:  32%|███▏      | 11600/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.126.up_proj:  32%|███▏      | 11601/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.126.down_proj:  32%|███▏      | 11602/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.127.gate_proj:  32%|███▏      | 11603/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.28.mlp.experts.127.up_proj:  32%|███▏      | 11604/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.28.mlp.experts.127.down_proj:  32%|███▏      | 11605/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.0.gate_proj:  32%|███▏      | 11606/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.0.up_proj:  32%|███▏      | 11607/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.0.down_proj:  32%|███▏      | 11608/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.1.gate_proj:  32%|███▏      | 11609/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.1.up_proj:  32%|███▏      | 11610/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.1.down_proj:  32%|███▏      | 11611/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.2.gate_proj:  32%|███▏      | 11612/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.2.up_proj:  32%|███▏      | 11613/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.2.down_proj:  32%|███▏      | 11614/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.3.gate_proj:  32%|███▏      | 11615/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.3.up_proj:  32%|███▏      | 11616/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.3.down_proj:  32%|███▏      | 11617/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.4.gate_proj:  32%|███▏      | 11618/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.4.up_proj:  32%|███▏      | 11619/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.4.down_proj:  32%|███▏      | 11620/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.5.gate_proj:  32%|███▏      | 11621/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.5.up_proj:  32%|███▏      | 11622/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.5.down_proj:  32%|███▏      | 11623/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.6.gate_proj:  32%|███▏      | 11624/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.6.up_proj:  32%|███▏      | 11625/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.6.down_proj:  32%|███▏      | 11626/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.7.gate_proj:  32%|███▏      | 11627/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.7.up_proj:  32%|███▏      | 11628/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.7.down_proj:  32%|███▏      | 11629/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.8.gate_proj:  32%|███▏      | 11630/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.8.up_proj:  32%|███▏      | 11631/36566 [00:11<00:21, 1142.71it/s]  
packing model.layers.29.mlp.experts.8.down_proj:  32%|███▏      | 11632/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.9.gate_proj:  32%|███▏      | 11633/36566 [00:11<00:21, 1142.71it/s]
packing model.layers.29.mlp.experts.9.gate_proj:  32%|███▏      | 11634/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.9.up_proj:  32%|███▏      | 11634/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.9.down_proj:  32%|███▏      | 11635/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.10.gate_proj:  32%|███▏      | 11636/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.10.up_proj:  32%|███▏      | 11637/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.10.down_proj:  32%|███▏      | 11638/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.11.gate_proj:  32%|███▏      | 11639/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.11.up_proj:  32%|███▏      | 11640/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.11.down_proj:  32%|███▏      | 11641/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.12.gate_proj:  32%|███▏      | 11642/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.12.up_proj:  32%|███▏      | 11643/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.12.down_proj:  32%|███▏      | 11644/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.13.gate_proj:  32%|███▏      | 11645/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.13.up_proj:  32%|███▏      | 11646/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.13.down_proj:  32%|███▏      | 11647/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.14.gate_proj:  32%|███▏      | 11648/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.14.up_proj:  32%|███▏      | 11649/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.14.down_proj:  32%|███▏      | 11650/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.15.gate_proj:  32%|███▏      | 11651/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.15.up_proj:  32%|███▏      | 11652/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.15.down_proj:  32%|███▏      | 11653/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.16.gate_proj:  32%|███▏      | 11654/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.16.up_proj:  32%|███▏      | 11655/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.16.down_proj:  32%|███▏      | 11656/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.17.gate_proj:  32%|███▏      | 11657/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.17.up_proj:  32%|███▏      | 11658/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.17.down_proj:  32%|███▏      | 11659/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.18.gate_proj:  32%|███▏      | 11660/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.18.up_proj:  32%|███▏      | 11661/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.18.down_proj:  32%|███▏      | 11662/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.19.gate_proj:  32%|███▏      | 11663/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.19.up_proj:  32%|███▏      | 11664/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.19.down_proj:  32%|███▏      | 11665/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.20.gate_proj:  32%|███▏      | 11666/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.20.up_proj:  32%|███▏      | 11667/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.20.down_proj:  32%|███▏      | 11668/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.21.gate_proj:  32%|███▏      | 11669/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.21.up_proj:  32%|███▏      | 11670/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.21.down_proj:  32%|███▏      | 11671/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.22.gate_proj:  32%|███▏      | 11672/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.22.up_proj:  32%|███▏      | 11673/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.22.down_proj:  32%|███▏      | 11674/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.23.gate_proj:  32%|███▏      | 11675/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.23.up_proj:  32%|███▏      | 11676/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.23.down_proj:  32%|███▏      | 11677/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.24.gate_proj:  32%|███▏      | 11678/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.24.up_proj:  32%|███▏      | 11679/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.24.down_proj:  32%|███▏      | 11680/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.25.gate_proj:  32%|███▏      | 11681/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.25.up_proj:  32%|███▏      | 11682/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.25.down_proj:  32%|███▏      | 11683/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.26.gate_proj:  32%|███▏      | 11684/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.26.up_proj:  32%|███▏      | 11685/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.26.down_proj:  32%|███▏      | 11686/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.27.gate_proj:  32%|███▏      | 11687/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.27.up_proj:  32%|███▏      | 11688/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.27.down_proj:  32%|███▏      | 11689/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.28.gate_proj:  32%|███▏      | 11690/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.28.up_proj:  32%|███▏      | 11691/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.28.down_proj:  32%|███▏      | 11692/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.29.gate_proj:  32%|███▏      | 11693/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.29.up_proj:  32%|███▏      | 11694/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.29.down_proj:  32%|███▏      | 11695/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.30.gate_proj:  32%|███▏      | 11696/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.30.up_proj:  32%|███▏      | 11697/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.30.down_proj:  32%|███▏      | 11698/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.31.gate_proj:  32%|███▏      | 11699/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.31.up_proj:  32%|███▏      | 11700/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.31.down_proj:  32%|███▏      | 11701/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.32.gate_proj:  32%|███▏      | 11702/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.32.up_proj:  32%|███▏      | 11703/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.32.down_proj:  32%|███▏      | 11704/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.33.gate_proj:  32%|███▏      | 11705/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.33.up_proj:  32%|███▏      | 11706/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.33.down_proj:  32%|███▏      | 11707/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.34.gate_proj:  32%|███▏      | 11708/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.34.up_proj:  32%|███▏      | 11709/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.34.down_proj:  32%|███▏      | 11710/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.35.gate_proj:  32%|███▏      | 11711/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.35.up_proj:  32%|███▏      | 11712/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.35.down_proj:  32%|███▏      | 11713/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.36.gate_proj:  32%|███▏      | 11714/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.36.up_proj:  32%|███▏      | 11715/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.36.down_proj:  32%|███▏      | 11716/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.37.gate_proj:  32%|███▏      | 11717/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.37.up_proj:  32%|███▏      | 11718/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.37.down_proj:  32%|███▏      | 11719/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.38.gate_proj:  32%|███▏      | 11720/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.38.up_proj:  32%|███▏      | 11721/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.38.down_proj:  32%|███▏      | 11722/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.39.gate_proj:  32%|███▏      | 11723/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.39.up_proj:  32%|███▏      | 11724/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.39.down_proj:  32%|███▏      | 11725/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.40.gate_proj:  32%|███▏      | 11726/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.40.up_proj:  32%|███▏      | 11727/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.40.down_proj:  32%|███▏      | 11728/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.41.gate_proj:  32%|███▏      | 11729/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.41.up_proj:  32%|███▏      | 11730/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.41.down_proj:  32%|███▏      | 11731/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.42.gate_proj:  32%|███▏      | 11732/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.42.up_proj:  32%|███▏      | 11733/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.42.down_proj:  32%|███▏      | 11734/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.43.gate_proj:  32%|███▏      | 11735/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.43.up_proj:  32%|███▏      | 11736/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.43.down_proj:  32%|███▏      | 11737/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.44.gate_proj:  32%|███▏      | 11738/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.44.up_proj:  32%|███▏      | 11739/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.44.down_proj:  32%|███▏      | 11740/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.45.gate_proj:  32%|███▏      | 11741/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.45.up_proj:  32%|███▏      | 11742/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.45.down_proj:  32%|███▏      | 11743/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.46.gate_proj:  32%|███▏      | 11744/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.46.up_proj:  32%|███▏      | 11745/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.46.down_proj:  32%|███▏      | 11746/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.47.gate_proj:  32%|███▏      | 11747/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.47.up_proj:  32%|███▏      | 11748/36566 [00:11<00:21, 1144.20it/s]  
packing model.layers.29.mlp.experts.47.down_proj:  32%|███▏      | 11749/36566 [00:11<00:21, 1144.20it/s]
packing model.layers.29.mlp.experts.47.down_proj:  32%|███▏      | 11750/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.48.gate_proj:  32%|███▏      | 11750/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.48.up_proj:  32%|███▏      | 11751/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.48.down_proj:  32%|███▏      | 11752/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.49.gate_proj:  32%|███▏      | 11753/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.49.up_proj:  32%|███▏      | 11754/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.49.down_proj:  32%|███▏      | 11755/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.50.gate_proj:  32%|███▏      | 11756/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.50.up_proj:  32%|███▏      | 11757/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.50.down_proj:  32%|███▏      | 11758/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.51.gate_proj:  32%|███▏      | 11759/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.51.up_proj:  32%|███▏      | 11760/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.51.down_proj:  32%|███▏      | 11761/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.52.gate_proj:  32%|███▏      | 11762/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.52.up_proj:  32%|███▏      | 11763/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.52.down_proj:  32%|███▏      | 11764/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.53.gate_proj:  32%|███▏      | 11765/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.53.up_proj:  32%|███▏      | 11766/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.53.down_proj:  32%|███▏      | 11767/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.54.gate_proj:  32%|███▏      | 11768/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.54.up_proj:  32%|███▏      | 11769/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.54.down_proj:  32%|███▏      | 11770/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.55.gate_proj:  32%|███▏      | 11771/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.55.up_proj:  32%|███▏      | 11772/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.55.down_proj:  32%|███▏      | 11773/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.56.gate_proj:  32%|███▏      | 11774/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.56.up_proj:  32%|███▏      | 11775/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.56.down_proj:  32%|███▏      | 11776/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.57.gate_proj:  32%|███▏      | 11777/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.57.up_proj:  32%|███▏      | 11778/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.57.down_proj:  32%|███▏      | 11779/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.58.gate_proj:  32%|███▏      | 11780/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.58.up_proj:  32%|███▏      | 11781/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.58.down_proj:  32%|███▏      | 11782/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.59.gate_proj:  32%|███▏      | 11783/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.59.up_proj:  32%|███▏      | 11784/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.59.down_proj:  32%|███▏      | 11785/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.60.gate_proj:  32%|███▏      | 11786/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.60.up_proj:  32%|███▏      | 11787/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.60.down_proj:  32%|███▏      | 11788/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.61.gate_proj:  32%|███▏      | 11789/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.61.up_proj:  32%|███▏      | 11790/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.61.down_proj:  32%|███▏      | 11791/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.62.gate_proj:  32%|███▏      | 11792/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.62.up_proj:  32%|███▏      | 11793/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.62.down_proj:  32%|███▏      | 11794/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.63.gate_proj:  32%|███▏      | 11795/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.63.up_proj:  32%|███▏      | 11796/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.63.down_proj:  32%|███▏      | 11797/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.64.gate_proj:  32%|███▏      | 11798/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.64.up_proj:  32%|███▏      | 11799/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.64.down_proj:  32%|███▏      | 11800/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.65.gate_proj:  32%|███▏      | 11801/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.65.up_proj:  32%|███▏      | 11802/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.65.down_proj:  32%|███▏      | 11803/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.66.gate_proj:  32%|███▏      | 11804/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.66.up_proj:  32%|███▏      | 11805/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.66.down_proj:  32%|███▏      | 11806/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.67.gate_proj:  32%|███▏      | 11807/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.67.up_proj:  32%|███▏      | 11808/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.67.down_proj:  32%|███▏      | 11809/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.68.gate_proj:  32%|███▏      | 11810/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.68.up_proj:  32%|███▏      | 11811/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.68.down_proj:  32%|███▏      | 11812/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.69.gate_proj:  32%|███▏      | 11813/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.69.up_proj:  32%|███▏      | 11814/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.69.down_proj:  32%|███▏      | 11815/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.70.gate_proj:  32%|███▏      | 11816/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.70.up_proj:  32%|███▏      | 11817/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.70.down_proj:  32%|███▏      | 11818/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.71.gate_proj:  32%|███▏      | 11819/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.71.up_proj:  32%|███▏      | 11820/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.71.down_proj:  32%|███▏      | 11821/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.72.gate_proj:  32%|███▏      | 11822/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.72.up_proj:  32%|███▏      | 11823/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.72.down_proj:  32%|███▏      | 11824/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.73.gate_proj:  32%|███▏      | 11825/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.73.up_proj:  32%|███▏      | 11826/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.73.down_proj:  32%|███▏      | 11827/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.74.gate_proj:  32%|███▏      | 11828/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.74.up_proj:  32%|███▏      | 11829/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.74.down_proj:  32%|███▏      | 11830/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.75.gate_proj:  32%|███▏      | 11831/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.75.up_proj:  32%|███▏      | 11832/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.75.down_proj:  32%|███▏      | 11833/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.76.gate_proj:  32%|███▏      | 11834/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.76.up_proj:  32%|███▏      | 11835/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.76.down_proj:  32%|███▏      | 11836/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.77.gate_proj:  32%|███▏      | 11837/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.77.up_proj:  32%|███▏      | 11838/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.77.down_proj:  32%|███▏      | 11839/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.78.gate_proj:  32%|███▏      | 11840/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.78.up_proj:  32%|███▏      | 11841/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.78.down_proj:  32%|███▏      | 11842/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.79.gate_proj:  32%|███▏      | 11843/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.79.up_proj:  32%|███▏      | 11844/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.79.down_proj:  32%|███▏      | 11845/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.80.gate_proj:  32%|███▏      | 11846/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.80.up_proj:  32%|███▏      | 11847/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.80.down_proj:  32%|███▏      | 11848/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.81.gate_proj:  32%|███▏      | 11849/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.81.up_proj:  32%|███▏      | 11850/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.81.down_proj:  32%|███▏      | 11851/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.82.gate_proj:  32%|███▏      | 11852/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.82.up_proj:  32%|███▏      | 11853/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.82.down_proj:  32%|███▏      | 11854/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.83.gate_proj:  32%|███▏      | 11855/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.83.up_proj:  32%|███▏      | 11856/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.83.down_proj:  32%|███▏      | 11857/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.84.gate_proj:  32%|███▏      | 11858/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.84.up_proj:  32%|███▏      | 11859/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.84.down_proj:  32%|███▏      | 11860/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.85.gate_proj:  32%|███▏      | 11861/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.85.up_proj:  32%|███▏      | 11862/36566 [00:11<00:21, 1146.98it/s]  
packing model.layers.29.mlp.experts.85.down_proj:  32%|███▏      | 11863/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.86.gate_proj:  32%|███▏      | 11864/36566 [00:11<00:21, 1146.98it/s]
packing model.layers.29.mlp.experts.86.gate_proj:  32%|███▏      | 11865/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.86.up_proj:  32%|███▏      | 11865/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.86.down_proj:  32%|███▏      | 11866/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.87.gate_proj:  32%|███▏      | 11867/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.87.up_proj:  32%|███▏      | 11868/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.87.down_proj:  32%|███▏      | 11869/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.88.gate_proj:  32%|███▏      | 11870/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.88.up_proj:  32%|███▏      | 11871/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.88.down_proj:  32%|███▏      | 11872/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.89.gate_proj:  32%|███▏      | 11873/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.89.up_proj:  32%|███▏      | 11874/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.89.down_proj:  32%|███▏      | 11875/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.90.gate_proj:  32%|███▏      | 11876/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.90.up_proj:  32%|███▏      | 11877/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.90.down_proj:  32%|███▏      | 11878/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.91.gate_proj:  32%|███▏      | 11879/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.91.up_proj:  32%|███▏      | 11880/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.91.down_proj:  32%|███▏      | 11881/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.92.gate_proj:  32%|███▏      | 11882/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.92.up_proj:  32%|███▏      | 11883/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.92.down_proj:  33%|███▎      | 11884/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.93.gate_proj:  33%|███▎      | 11885/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.93.up_proj:  33%|███▎      | 11886/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.93.down_proj:  33%|███▎      | 11887/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.94.gate_proj:  33%|███▎      | 11888/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.94.up_proj:  33%|███▎      | 11889/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.94.down_proj:  33%|███▎      | 11890/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.95.gate_proj:  33%|███▎      | 11891/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.95.up_proj:  33%|███▎      | 11892/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.95.down_proj:  33%|███▎      | 11893/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.96.gate_proj:  33%|███▎      | 11894/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.96.up_proj:  33%|███▎      | 11895/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.96.down_proj:  33%|███▎      | 11896/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.97.gate_proj:  33%|███▎      | 11897/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.97.up_proj:  33%|███▎      | 11898/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.97.down_proj:  33%|███▎      | 11899/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.98.gate_proj:  33%|███▎      | 11900/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.98.up_proj:  33%|███▎      | 11901/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.98.down_proj:  33%|███▎      | 11902/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.99.gate_proj:  33%|███▎      | 11903/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.99.up_proj:  33%|███▎      | 11904/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.99.down_proj:  33%|███▎      | 11905/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.100.gate_proj:  33%|███▎      | 11906/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.100.up_proj:  33%|███▎      | 11907/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.100.down_proj:  33%|███▎      | 11908/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.101.gate_proj:  33%|███▎      | 11909/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.101.up_proj:  33%|███▎      | 11910/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.101.down_proj:  33%|███▎      | 11911/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.102.gate_proj:  33%|███▎      | 11912/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.102.up_proj:  33%|███▎      | 11913/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.102.down_proj:  33%|███▎      | 11914/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.103.gate_proj:  33%|███▎      | 11915/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.103.up_proj:  33%|███▎      | 11916/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.103.down_proj:  33%|███▎      | 11917/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.104.gate_proj:  33%|███▎      | 11918/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.104.up_proj:  33%|███▎      | 11919/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.104.down_proj:  33%|███▎      | 11920/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.105.gate_proj:  33%|███▎      | 11921/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.105.up_proj:  33%|███▎      | 11922/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.105.down_proj:  33%|███▎      | 11923/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.106.gate_proj:  33%|███▎      | 11924/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.106.up_proj:  33%|███▎      | 11925/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.106.down_proj:  33%|███▎      | 11926/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.107.gate_proj:  33%|███▎      | 11927/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.107.up_proj:  33%|███▎      | 11928/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.107.down_proj:  33%|███▎      | 11929/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.108.gate_proj:  33%|███▎      | 11930/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.108.up_proj:  33%|███▎      | 11931/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.108.down_proj:  33%|███▎      | 11932/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.109.gate_proj:  33%|███▎      | 11933/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.109.up_proj:  33%|███▎      | 11934/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.109.down_proj:  33%|███▎      | 11935/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.110.gate_proj:  33%|███▎      | 11936/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.110.up_proj:  33%|███▎      | 11937/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.110.down_proj:  33%|███▎      | 11938/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.111.gate_proj:  33%|███▎      | 11939/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.111.up_proj:  33%|███▎      | 11940/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.111.down_proj:  33%|███▎      | 11941/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.112.gate_proj:  33%|███▎      | 11942/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.112.up_proj:  33%|███▎      | 11943/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.112.down_proj:  33%|███▎      | 11944/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.113.gate_proj:  33%|███▎      | 11945/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.113.up_proj:  33%|███▎      | 11946/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.113.down_proj:  33%|███▎      | 11947/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.114.gate_proj:  33%|███▎      | 11948/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.114.up_proj:  33%|███▎      | 11949/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.114.down_proj:  33%|███▎      | 11950/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.115.gate_proj:  33%|███▎      | 11951/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.115.up_proj:  33%|███▎      | 11952/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.115.down_proj:  33%|███▎      | 11953/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.116.gate_proj:  33%|███▎      | 11954/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.116.up_proj:  33%|███▎      | 11955/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.116.down_proj:  33%|███▎      | 11956/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.117.gate_proj:  33%|███▎      | 11957/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.117.up_proj:  33%|███▎      | 11958/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.117.down_proj:  33%|███▎      | 11959/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.118.gate_proj:  33%|███▎      | 11960/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.118.up_proj:  33%|███▎      | 11961/36566 [00:11<00:22, 1118.35it/s]  
packing model.layers.29.mlp.experts.118.down_proj:  33%|███▎      | 11962/36566 [00:11<00:22, 1118.35it/s]
packing model.layers.29.mlp.experts.119.gate_proj:  33%|███▎      | 11963/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.119.up_proj:  33%|███▎      | 11964/36566 [00:11<00:21, 1118.35it/s]  
packing model.layers.29.mlp.experts.119.down_proj:  33%|███▎      | 11965/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.120.gate_proj:  33%|███▎      | 11966/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.120.up_proj:  33%|███▎      | 11967/36566 [00:11<00:21, 1118.35it/s]  
packing model.layers.29.mlp.experts.120.down_proj:  33%|███▎      | 11968/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.121.gate_proj:  33%|███▎      | 11969/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.121.up_proj:  33%|███▎      | 11970/36566 [00:11<00:21, 1118.35it/s]  
packing model.layers.29.mlp.experts.121.down_proj:  33%|███▎      | 11971/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.122.gate_proj:  33%|███▎      | 11972/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.122.up_proj:  33%|███▎      | 11973/36566 [00:11<00:21, 1118.35it/s]  
packing model.layers.29.mlp.experts.122.down_proj:  33%|███▎      | 11974/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.123.gate_proj:  33%|███▎      | 11975/36566 [00:11<00:21, 1118.35it/s]
packing model.layers.29.mlp.experts.123.up_proj:  33%|███▎      | 11976/36566 [00:11<00:21, 1118.35it/s]  
packing model.layers.29.mlp.experts.123.up_proj:  33%|███▎      | 11977/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.123.down_proj:  33%|███▎      | 11977/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.124.gate_proj:  33%|███▎      | 11978/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.124.up_proj:  33%|███▎      | 11979/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.29.mlp.experts.124.down_proj:  33%|███▎      | 11980/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.125.gate_proj:  33%|███▎      | 11981/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.125.up_proj:  33%|███▎      | 11982/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.29.mlp.experts.125.down_proj:  33%|███▎      | 11983/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.126.gate_proj:  33%|███▎      | 11984/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.126.up_proj:  33%|███▎      | 11985/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.29.mlp.experts.126.down_proj:  33%|███▎      | 11986/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.127.gate_proj:  33%|███▎      | 11987/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.29.mlp.experts.127.up_proj:  33%|███▎      | 11988/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.29.mlp.experts.127.down_proj:  33%|███▎      | 11989/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.0.gate_proj:  33%|███▎      | 11990/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.0.up_proj:  33%|███▎      | 11991/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.0.down_proj:  33%|███▎      | 11992/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.1.gate_proj:  33%|███▎      | 11993/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.1.up_proj:  33%|███▎      | 11994/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.1.down_proj:  33%|███▎      | 11995/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.2.gate_proj:  33%|███▎      | 11996/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.2.up_proj:  33%|███▎      | 11997/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.2.down_proj:  33%|███▎      | 11998/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.3.gate_proj:  33%|███▎      | 11999/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.3.up_proj:  33%|███▎      | 12000/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.3.down_proj:  33%|███▎      | 12001/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.4.gate_proj:  33%|███▎      | 12002/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.4.up_proj:  33%|███▎      | 12003/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.4.down_proj:  33%|███▎      | 12004/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.5.gate_proj:  33%|███▎      | 12005/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.5.up_proj:  33%|███▎      | 12006/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.5.down_proj:  33%|███▎      | 12007/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.6.gate_proj:  33%|███▎      | 12008/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.6.up_proj:  33%|███▎      | 12009/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.6.down_proj:  33%|███▎      | 12010/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.7.gate_proj:  33%|███▎      | 12011/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.7.up_proj:  33%|███▎      | 12012/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.7.down_proj:  33%|███▎      | 12013/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.8.gate_proj:  33%|███▎      | 12014/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.8.up_proj:  33%|███▎      | 12015/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.8.down_proj:  33%|███▎      | 12016/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.9.gate_proj:  33%|███▎      | 12017/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.9.up_proj:  33%|███▎      | 12018/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.9.down_proj:  33%|███▎      | 12019/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.10.gate_proj:  33%|███▎      | 12020/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.10.up_proj:  33%|███▎      | 12021/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.10.down_proj:  33%|███▎      | 12022/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.11.gate_proj:  33%|███▎      | 12023/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.11.up_proj:  33%|███▎      | 12024/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.11.down_proj:  33%|███▎      | 12025/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.12.gate_proj:  33%|███▎      | 12026/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.12.up_proj:  33%|███▎      | 12027/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.12.down_proj:  33%|███▎      | 12028/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.13.gate_proj:  33%|███▎      | 12029/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.13.up_proj:  33%|███▎      | 12030/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.13.down_proj:  33%|███▎      | 12031/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.14.gate_proj:  33%|███▎      | 12032/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.14.up_proj:  33%|███▎      | 12033/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.14.down_proj:  33%|███▎      | 12034/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.15.gate_proj:  33%|███▎      | 12035/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.15.up_proj:  33%|███▎      | 12036/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.15.down_proj:  33%|███▎      | 12037/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.16.gate_proj:  33%|███▎      | 12038/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.16.up_proj:  33%|███▎      | 12039/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.16.down_proj:  33%|███▎      | 12040/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.17.gate_proj:  33%|███▎      | 12041/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.17.up_proj:  33%|███▎      | 12042/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.17.down_proj:  33%|███▎      | 12043/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.18.gate_proj:  33%|███▎      | 12044/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.18.up_proj:  33%|███▎      | 12045/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.18.down_proj:  33%|███▎      | 12046/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.19.gate_proj:  33%|███▎      | 12047/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.19.up_proj:  33%|███▎      | 12048/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.19.down_proj:  33%|███▎      | 12049/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.20.gate_proj:  33%|███▎      | 12050/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.20.up_proj:  33%|███▎      | 12051/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.20.down_proj:  33%|███▎      | 12052/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.21.gate_proj:  33%|███▎      | 12053/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.21.up_proj:  33%|███▎      | 12054/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.21.down_proj:  33%|███▎      | 12055/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.22.gate_proj:  33%|███▎      | 12056/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.22.up_proj:  33%|███▎      | 12057/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.22.down_proj:  33%|███▎      | 12058/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.23.gate_proj:  33%|███▎      | 12059/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.23.up_proj:  33%|███▎      | 12060/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.23.down_proj:  33%|███▎      | 12061/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.24.gate_proj:  33%|███▎      | 12062/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.24.up_proj:  33%|███▎      | 12063/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.24.down_proj:  33%|███▎      | 12064/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.25.gate_proj:  33%|███▎      | 12065/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.25.up_proj:  33%|███▎      | 12066/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.25.down_proj:  33%|███▎      | 12067/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.26.gate_proj:  33%|███▎      | 12068/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.26.up_proj:  33%|███▎      | 12069/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.26.down_proj:  33%|███▎      | 12070/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.27.gate_proj:  33%|███▎      | 12071/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.27.up_proj:  33%|███▎      | 12072/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.27.down_proj:  33%|███▎      | 12073/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.28.gate_proj:  33%|███▎      | 12074/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.28.up_proj:  33%|███▎      | 12075/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.28.down_proj:  33%|███▎      | 12076/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.29.gate_proj:  33%|███▎      | 12077/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.29.up_proj:  33%|███▎      | 12078/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.29.down_proj:  33%|███▎      | 12079/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.30.gate_proj:  33%|███▎      | 12080/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.30.up_proj:  33%|███▎      | 12081/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.30.down_proj:  33%|███▎      | 12082/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.31.gate_proj:  33%|███▎      | 12083/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.31.up_proj:  33%|███▎      | 12084/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.31.down_proj:  33%|███▎      | 12085/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.32.gate_proj:  33%|███▎      | 12086/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.32.up_proj:  33%|███▎      | 12087/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.32.down_proj:  33%|███▎      | 12088/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.33.gate_proj:  33%|███▎      | 12089/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.33.up_proj:  33%|███▎      | 12090/36566 [00:11<00:22, 1100.35it/s]  
packing model.layers.30.mlp.experts.33.down_proj:  33%|███▎      | 12091/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.34.gate_proj:  33%|███▎      | 12092/36566 [00:11<00:22, 1100.35it/s]
packing model.layers.30.mlp.experts.34.gate_proj:  33%|███▎      | 12093/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.34.up_proj:  33%|███▎      | 12093/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.34.down_proj:  33%|███▎      | 12094/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.35.gate_proj:  33%|███▎      | 12095/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.35.up_proj:  33%|███▎      | 12096/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.35.down_proj:  33%|███▎      | 12097/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.36.gate_proj:  33%|███▎      | 12098/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.36.up_proj:  33%|███▎      | 12099/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.36.down_proj:  33%|███▎      | 12100/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.37.gate_proj:  33%|███▎      | 12101/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.37.up_proj:  33%|███▎      | 12102/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.37.down_proj:  33%|███▎      | 12103/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.38.gate_proj:  33%|███▎      | 12104/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.38.up_proj:  33%|███▎      | 12105/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.38.down_proj:  33%|███▎      | 12106/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.39.gate_proj:  33%|███▎      | 12107/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.39.up_proj:  33%|███▎      | 12108/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.39.down_proj:  33%|███▎      | 12109/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.40.gate_proj:  33%|███▎      | 12110/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.40.up_proj:  33%|███▎      | 12111/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.40.down_proj:  33%|███▎      | 12112/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.41.gate_proj:  33%|███▎      | 12113/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.41.up_proj:  33%|███▎      | 12114/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.41.down_proj:  33%|███▎      | 12115/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.42.gate_proj:  33%|███▎      | 12116/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.42.up_proj:  33%|███▎      | 12117/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.42.down_proj:  33%|███▎      | 12118/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.43.gate_proj:  33%|███▎      | 12119/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.43.up_proj:  33%|███▎      | 12120/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.43.down_proj:  33%|███▎      | 12121/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.44.gate_proj:  33%|███▎      | 12122/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.44.up_proj:  33%|███▎      | 12123/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.44.down_proj:  33%|███▎      | 12124/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.45.gate_proj:  33%|███▎      | 12125/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.45.up_proj:  33%|███▎      | 12126/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.45.down_proj:  33%|███▎      | 12127/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.46.gate_proj:  33%|███▎      | 12128/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.46.up_proj:  33%|███▎      | 12129/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.46.down_proj:  33%|███▎      | 12130/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.47.gate_proj:  33%|███▎      | 12131/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.47.up_proj:  33%|███▎      | 12132/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.47.down_proj:  33%|███▎      | 12133/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.48.gate_proj:  33%|███▎      | 12134/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.48.up_proj:  33%|███▎      | 12135/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.48.down_proj:  33%|███▎      | 12136/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.49.gate_proj:  33%|███▎      | 12137/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.49.up_proj:  33%|███▎      | 12138/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.49.down_proj:  33%|███▎      | 12139/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.50.gate_proj:  33%|███▎      | 12140/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.50.up_proj:  33%|███▎      | 12141/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.50.down_proj:  33%|███▎      | 12142/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.51.gate_proj:  33%|███▎      | 12143/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.51.up_proj:  33%|███▎      | 12144/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.51.down_proj:  33%|███▎      | 12145/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.52.gate_proj:  33%|███▎      | 12146/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.52.up_proj:  33%|███▎      | 12147/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.52.down_proj:  33%|███▎      | 12148/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.53.gate_proj:  33%|███▎      | 12149/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.53.up_proj:  33%|███▎      | 12150/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.53.down_proj:  33%|███▎      | 12151/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.54.gate_proj:  33%|███▎      | 12152/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.54.up_proj:  33%|███▎      | 12153/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.54.down_proj:  33%|███▎      | 12154/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.55.gate_proj:  33%|███▎      | 12155/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.55.up_proj:  33%|███▎      | 12156/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.55.down_proj:  33%|███▎      | 12157/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.56.gate_proj:  33%|███▎      | 12158/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.56.up_proj:  33%|███▎      | 12159/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.56.down_proj:  33%|███▎      | 12160/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.57.gate_proj:  33%|███▎      | 12161/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.57.up_proj:  33%|███▎      | 12162/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.57.down_proj:  33%|███▎      | 12163/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.58.gate_proj:  33%|███▎      | 12164/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.58.up_proj:  33%|███▎      | 12165/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.58.down_proj:  33%|███▎      | 12166/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.59.gate_proj:  33%|███▎      | 12167/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.59.up_proj:  33%|███▎      | 12168/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.59.down_proj:  33%|███▎      | 12169/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.60.gate_proj:  33%|███▎      | 12170/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.60.up_proj:  33%|███▎      | 12171/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.60.down_proj:  33%|███▎      | 12172/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.61.gate_proj:  33%|███▎      | 12173/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.61.up_proj:  33%|███▎      | 12174/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.61.down_proj:  33%|███▎      | 12175/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.62.gate_proj:  33%|███▎      | 12176/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.62.up_proj:  33%|███▎      | 12177/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.62.down_proj:  33%|███▎      | 12178/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.63.gate_proj:  33%|███▎      | 12179/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.63.up_proj:  33%|███▎      | 12180/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.63.down_proj:  33%|███▎      | 12181/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.64.gate_proj:  33%|███▎      | 12182/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.64.up_proj:  33%|███▎      | 12183/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.64.down_proj:  33%|███▎      | 12184/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.65.gate_proj:  33%|███▎      | 12185/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.65.up_proj:  33%|███▎      | 12186/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.65.down_proj:  33%|███▎      | 12187/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.66.gate_proj:  33%|███▎      | 12188/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.66.up_proj:  33%|███▎      | 12189/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.66.down_proj:  33%|███▎      | 12190/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.67.gate_proj:  33%|███▎      | 12191/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.67.up_proj:  33%|███▎      | 12192/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.67.down_proj:  33%|███▎      | 12193/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.68.gate_proj:  33%|███▎      | 12194/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.68.up_proj:  33%|███▎      | 12195/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.68.down_proj:  33%|███▎      | 12196/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.69.gate_proj:  33%|███▎      | 12197/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.69.up_proj:  33%|███▎      | 12198/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.69.down_proj:  33%|███▎      | 12199/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.70.gate_proj:  33%|███▎      | 12200/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.70.up_proj:  33%|███▎      | 12201/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.70.down_proj:  33%|███▎      | 12202/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.71.gate_proj:  33%|███▎      | 12203/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.71.up_proj:  33%|███▎      | 12204/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.71.down_proj:  33%|███▎      | 12205/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.72.gate_proj:  33%|███▎      | 12206/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.72.up_proj:  33%|███▎      | 12207/36566 [00:11<00:21, 1116.12it/s]  
packing model.layers.30.mlp.experts.72.down_proj:  33%|███▎      | 12208/36566 [00:11<00:21, 1116.12it/s]
packing model.layers.30.mlp.experts.72.down_proj:  33%|███▎      | 12209/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.73.gate_proj:  33%|███▎      | 12209/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.73.up_proj:  33%|███▎      | 12210/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.73.down_proj:  33%|███▎      | 12211/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.74.gate_proj:  33%|███▎      | 12212/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.74.up_proj:  33%|███▎      | 12213/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.74.down_proj:  33%|███▎      | 12214/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.75.gate_proj:  33%|███▎      | 12215/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.75.up_proj:  33%|███▎      | 12216/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.75.down_proj:  33%|███▎      | 12217/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.76.gate_proj:  33%|███▎      | 12218/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.76.up_proj:  33%|███▎      | 12219/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.76.down_proj:  33%|███▎      | 12220/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.77.gate_proj:  33%|███▎      | 12221/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.77.up_proj:  33%|███▎      | 12222/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.77.down_proj:  33%|███▎      | 12223/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.78.gate_proj:  33%|███▎      | 12224/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.78.up_proj:  33%|███▎      | 12225/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.78.down_proj:  33%|███▎      | 12226/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.79.gate_proj:  33%|███▎      | 12227/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.79.up_proj:  33%|███▎      | 12228/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.79.down_proj:  33%|███▎      | 12229/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.80.gate_proj:  33%|███▎      | 12230/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.80.up_proj:  33%|███▎      | 12231/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.80.down_proj:  33%|███▎      | 12232/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.81.gate_proj:  33%|███▎      | 12233/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.81.up_proj:  33%|███▎      | 12234/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.81.down_proj:  33%|███▎      | 12235/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.82.gate_proj:  33%|███▎      | 12236/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.82.up_proj:  33%|███▎      | 12237/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.82.down_proj:  33%|███▎      | 12238/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.83.gate_proj:  33%|███▎      | 12239/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.83.up_proj:  33%|███▎      | 12240/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.83.down_proj:  33%|███▎      | 12241/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.84.gate_proj:  33%|███▎      | 12242/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.84.up_proj:  33%|███▎      | 12243/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.84.down_proj:  33%|███▎      | 12244/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.85.gate_proj:  33%|███▎      | 12245/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.85.up_proj:  33%|███▎      | 12246/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.85.down_proj:  33%|███▎      | 12247/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.86.gate_proj:  33%|███▎      | 12248/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.86.up_proj:  33%|███▎      | 12249/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.86.down_proj:  34%|███▎      | 12250/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.87.gate_proj:  34%|███▎      | 12251/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.87.up_proj:  34%|███▎      | 12252/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.87.down_proj:  34%|███▎      | 12253/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.88.gate_proj:  34%|███▎      | 12254/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.88.up_proj:  34%|███▎      | 12255/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.88.down_proj:  34%|███▎      | 12256/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.89.gate_proj:  34%|███▎      | 12257/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.89.up_proj:  34%|███▎      | 12258/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.89.down_proj:  34%|███▎      | 12259/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.90.gate_proj:  34%|███▎      | 12260/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.90.up_proj:  34%|███▎      | 12261/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.90.down_proj:  34%|███▎      | 12262/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.91.gate_proj:  34%|███▎      | 12263/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.91.up_proj:  34%|███▎      | 12264/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.91.down_proj:  34%|███▎      | 12265/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.92.gate_proj:  34%|███▎      | 12266/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.92.up_proj:  34%|███▎      | 12267/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.92.down_proj:  34%|███▎      | 12268/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.93.gate_proj:  34%|███▎      | 12269/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.93.up_proj:  34%|███▎      | 12270/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.93.down_proj:  34%|███▎      | 12271/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.94.gate_proj:  34%|███▎      | 12272/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.94.up_proj:  34%|███▎      | 12273/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.94.down_proj:  34%|███▎      | 12274/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.95.gate_proj:  34%|███▎      | 12275/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.95.up_proj:  34%|███▎      | 12276/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.95.down_proj:  34%|███▎      | 12277/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.96.gate_proj:  34%|███▎      | 12278/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.96.up_proj:  34%|███▎      | 12279/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.96.down_proj:  34%|███▎      | 12280/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.97.gate_proj:  34%|███▎      | 12281/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.97.up_proj:  34%|███▎      | 12282/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.97.down_proj:  34%|███▎      | 12283/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.98.gate_proj:  34%|███▎      | 12284/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.98.up_proj:  34%|███▎      | 12285/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.98.down_proj:  34%|███▎      | 12286/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.99.gate_proj:  34%|███▎      | 12287/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.99.up_proj:  34%|███▎      | 12288/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.99.down_proj:  34%|███▎      | 12289/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.100.gate_proj:  34%|███▎      | 12290/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.100.up_proj:  34%|███▎      | 12291/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.100.down_proj:  34%|███▎      | 12292/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.101.gate_proj:  34%|███▎      | 12293/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.101.up_proj:  34%|███▎      | 12294/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.101.down_proj:  34%|███▎      | 12295/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.102.gate_proj:  34%|███▎      | 12296/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.102.up_proj:  34%|███▎      | 12297/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.102.down_proj:  34%|███▎      | 12298/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.103.gate_proj:  34%|███▎      | 12299/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.103.up_proj:  34%|███▎      | 12300/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.103.down_proj:  34%|███▎      | 12301/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.104.gate_proj:  34%|███▎      | 12302/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.104.up_proj:  34%|███▎      | 12303/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.104.down_proj:  34%|███▎      | 12304/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.105.gate_proj:  34%|███▎      | 12305/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.105.up_proj:  34%|███▎      | 12306/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.105.down_proj:  34%|███▎      | 12307/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.106.gate_proj:  34%|███▎      | 12308/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.106.up_proj:  34%|███▎      | 12309/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.106.down_proj:  34%|███▎      | 12310/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.107.gate_proj:  34%|███▎      | 12311/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.107.up_proj:  34%|███▎      | 12312/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.107.down_proj:  34%|███▎      | 12313/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.108.gate_proj:  34%|███▎      | 12314/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.108.up_proj:  34%|███▎      | 12315/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.108.down_proj:  34%|███▎      | 12316/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.109.gate_proj:  34%|███▎      | 12317/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.109.up_proj:  34%|███▎      | 12318/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.109.down_proj:  34%|███▎      | 12319/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.110.gate_proj:  34%|███▎      | 12320/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.110.up_proj:  34%|███▎      | 12321/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.110.down_proj:  34%|███▎      | 12322/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.111.gate_proj:  34%|███▎      | 12323/36566 [00:11<00:21, 1128.00it/s]
packing model.layers.30.mlp.experts.111.up_proj:  34%|███▎      | 12324/36566 [00:11<00:21, 1128.00it/s]  
packing model.layers.30.mlp.experts.111.up_proj:  34%|███▎      | 12325/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.111.down_proj:  34%|███▎      | 12325/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.112.gate_proj:  34%|███▎      | 12326/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.112.up_proj:  34%|███▎      | 12327/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.112.down_proj:  34%|███▎      | 12328/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.113.gate_proj:  34%|███▎      | 12329/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.113.up_proj:  34%|███▎      | 12330/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.113.down_proj:  34%|███▎      | 12331/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.114.gate_proj:  34%|███▎      | 12332/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.114.up_proj:  34%|███▎      | 12333/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.114.down_proj:  34%|███▎      | 12334/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.115.gate_proj:  34%|███▎      | 12335/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.115.up_proj:  34%|███▎      | 12336/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.115.down_proj:  34%|███▎      | 12337/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.116.gate_proj:  34%|███▎      | 12338/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.116.up_proj:  34%|███▎      | 12339/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.116.down_proj:  34%|███▎      | 12340/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.117.gate_proj:  34%|███▎      | 12341/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.117.up_proj:  34%|███▍      | 12342/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.117.down_proj:  34%|███▍      | 12343/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.118.gate_proj:  34%|███▍      | 12344/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.118.up_proj:  34%|███▍      | 12345/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.118.down_proj:  34%|███▍      | 12346/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.119.gate_proj:  34%|███▍      | 12347/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.119.up_proj:  34%|███▍      | 12348/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.119.down_proj:  34%|███▍      | 12349/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.120.gate_proj:  34%|███▍      | 12350/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.120.up_proj:  34%|███▍      | 12351/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.120.down_proj:  34%|███▍      | 12352/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.121.gate_proj:  34%|███▍      | 12353/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.121.up_proj:  34%|███▍      | 12354/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.121.down_proj:  34%|███▍      | 12355/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.122.gate_proj:  34%|███▍      | 12356/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.122.up_proj:  34%|███▍      | 12357/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.122.down_proj:  34%|███▍      | 12358/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.123.gate_proj:  34%|███▍      | 12359/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.123.up_proj:  34%|███▍      | 12360/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.123.down_proj:  34%|███▍      | 12361/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.124.gate_proj:  34%|███▍      | 12362/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.124.up_proj:  34%|███▍      | 12363/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.124.down_proj:  34%|███▍      | 12364/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.125.gate_proj:  34%|███▍      | 12365/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.125.up_proj:  34%|███▍      | 12366/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.125.down_proj:  34%|███▍      | 12367/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.126.gate_proj:  34%|███▍      | 12368/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.126.up_proj:  34%|███▍      | 12369/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.126.down_proj:  34%|███▍      | 12370/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.127.gate_proj:  34%|███▍      | 12371/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.30.mlp.experts.127.up_proj:  34%|███▍      | 12372/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.30.mlp.experts.127.down_proj:  34%|███▍      | 12373/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.0.gate_proj:  34%|███▍      | 12374/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.0.up_proj:  34%|███▍      | 12375/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.0.down_proj:  34%|███▍      | 12376/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.1.gate_proj:  34%|███▍      | 12377/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.1.up_proj:  34%|███▍      | 12378/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.1.down_proj:  34%|███▍      | 12379/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.2.gate_proj:  34%|███▍      | 12380/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.2.up_proj:  34%|███▍      | 12381/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.2.down_proj:  34%|███▍      | 12382/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.3.gate_proj:  34%|███▍      | 12383/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.3.up_proj:  34%|███▍      | 12384/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.3.down_proj:  34%|███▍      | 12385/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.4.gate_proj:  34%|███▍      | 12386/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.4.up_proj:  34%|███▍      | 12387/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.4.down_proj:  34%|███▍      | 12388/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.5.gate_proj:  34%|███▍      | 12389/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.5.up_proj:  34%|███▍      | 12390/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.5.down_proj:  34%|███▍      | 12391/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.6.gate_proj:  34%|███▍      | 12392/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.6.up_proj:  34%|███▍      | 12393/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.6.down_proj:  34%|███▍      | 12394/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.7.gate_proj:  34%|███▍      | 12395/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.7.up_proj:  34%|███▍      | 12396/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.7.down_proj:  34%|███▍      | 12397/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.8.gate_proj:  34%|███▍      | 12398/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.8.up_proj:  34%|███▍      | 12399/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.8.down_proj:  34%|███▍      | 12400/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.9.gate_proj:  34%|███▍      | 12401/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.9.up_proj:  34%|███▍      | 12402/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.9.down_proj:  34%|███▍      | 12403/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.10.gate_proj:  34%|███▍      | 12404/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.10.up_proj:  34%|███▍      | 12405/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.10.down_proj:  34%|███▍      | 12406/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.11.gate_proj:  34%|███▍      | 12407/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.11.up_proj:  34%|███▍      | 12408/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.11.down_proj:  34%|███▍      | 12409/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.12.gate_proj:  34%|███▍      | 12410/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.12.up_proj:  34%|███▍      | 12411/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.12.down_proj:  34%|███▍      | 12412/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.13.gate_proj:  34%|███▍      | 12413/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.13.up_proj:  34%|███▍      | 12414/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.13.down_proj:  34%|███▍      | 12415/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.14.gate_proj:  34%|███▍      | 12416/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.14.up_proj:  34%|███▍      | 12417/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.14.down_proj:  34%|███▍      | 12418/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.15.gate_proj:  34%|███▍      | 12419/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.15.up_proj:  34%|███▍      | 12420/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.15.down_proj:  34%|███▍      | 12421/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.16.gate_proj:  34%|███▍      | 12422/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.16.up_proj:  34%|███▍      | 12423/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.16.down_proj:  34%|███▍      | 12424/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.17.gate_proj:  34%|███▍      | 12425/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.17.up_proj:  34%|███▍      | 12426/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.17.down_proj:  34%|███▍      | 12427/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.18.gate_proj:  34%|███▍      | 12428/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.18.up_proj:  34%|███▍      | 12429/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.18.down_proj:  34%|███▍      | 12430/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.19.gate_proj:  34%|███▍      | 12431/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.19.up_proj:  34%|███▍      | 12432/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.19.down_proj:  34%|███▍      | 12433/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.20.gate_proj:  34%|███▍      | 12434/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.20.up_proj:  34%|███▍      | 12435/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.20.down_proj:  34%|███▍      | 12436/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.21.gate_proj:  34%|███▍      | 12437/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.21.up_proj:  34%|███▍      | 12438/36566 [00:11<00:21, 1136.15it/s]  
packing model.layers.31.mlp.experts.21.down_proj:  34%|███▍      | 12439/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.22.gate_proj:  34%|███▍      | 12440/36566 [00:11<00:21, 1136.15it/s]
packing model.layers.31.mlp.experts.22.gate_proj:  34%|███▍      | 12441/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.22.up_proj:  34%|███▍      | 12441/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.22.down_proj:  34%|███▍      | 12442/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.23.gate_proj:  34%|███▍      | 12443/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.23.up_proj:  34%|███▍      | 12444/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.23.down_proj:  34%|███▍      | 12445/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.24.gate_proj:  34%|███▍      | 12446/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.24.up_proj:  34%|███▍      | 12447/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.24.down_proj:  34%|███▍      | 12448/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.25.gate_proj:  34%|███▍      | 12449/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.25.up_proj:  34%|███▍      | 12450/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.25.down_proj:  34%|███▍      | 12451/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.26.gate_proj:  34%|███▍      | 12452/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.26.up_proj:  34%|███▍      | 12453/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.26.down_proj:  34%|███▍      | 12454/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.27.gate_proj:  34%|███▍      | 12455/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.27.up_proj:  34%|███▍      | 12456/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.27.down_proj:  34%|███▍      | 12457/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.28.gate_proj:  34%|███▍      | 12458/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.28.up_proj:  34%|███▍      | 12459/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.28.down_proj:  34%|███▍      | 12460/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.29.gate_proj:  34%|███▍      | 12461/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.29.up_proj:  34%|███▍      | 12462/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.29.down_proj:  34%|███▍      | 12463/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.30.gate_proj:  34%|███▍      | 12464/36566 [00:11<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.30.up_proj:  34%|███▍      | 12465/36566 [00:11<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.30.down_proj:  34%|███▍      | 12466/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.31.gate_proj:  34%|███▍      | 12467/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.31.up_proj:  34%|███▍      | 12468/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.31.down_proj:  34%|███▍      | 12469/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.32.gate_proj:  34%|███▍      | 12470/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.32.up_proj:  34%|███▍      | 12471/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.32.down_proj:  34%|███▍      | 12472/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.33.gate_proj:  34%|███▍      | 12473/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.33.up_proj:  34%|███▍      | 12474/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.33.down_proj:  34%|███▍      | 12475/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.34.gate_proj:  34%|███▍      | 12476/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.34.up_proj:  34%|███▍      | 12477/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.34.down_proj:  34%|███▍      | 12478/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.35.gate_proj:  34%|███▍      | 12479/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.35.up_proj:  34%|███▍      | 12480/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.35.down_proj:  34%|███▍      | 12481/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.36.gate_proj:  34%|███▍      | 12482/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.36.up_proj:  34%|███▍      | 12483/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.36.down_proj:  34%|███▍      | 12484/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.37.gate_proj:  34%|███▍      | 12485/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.37.up_proj:  34%|███▍      | 12486/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.37.down_proj:  34%|███▍      | 12487/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.38.gate_proj:  34%|███▍      | 12488/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.38.up_proj:  34%|███▍      | 12489/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.38.down_proj:  34%|███▍      | 12490/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.39.gate_proj:  34%|███▍      | 12491/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.39.up_proj:  34%|███▍      | 12492/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.39.down_proj:  34%|███▍      | 12493/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.40.gate_proj:  34%|███▍      | 12494/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.40.up_proj:  34%|███▍      | 12495/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.40.down_proj:  34%|███▍      | 12496/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.41.gate_proj:  34%|███▍      | 12497/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.41.up_proj:  34%|███▍      | 12498/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.41.down_proj:  34%|███▍      | 12499/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.42.gate_proj:  34%|███▍      | 12500/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.42.up_proj:  34%|███▍      | 12501/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.42.down_proj:  34%|███▍      | 12502/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.43.gate_proj:  34%|███▍      | 12503/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.43.up_proj:  34%|███▍      | 12504/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.43.down_proj:  34%|███▍      | 12505/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.44.gate_proj:  34%|███▍      | 12506/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.44.up_proj:  34%|███▍      | 12507/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.44.down_proj:  34%|███▍      | 12508/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.45.gate_proj:  34%|███▍      | 12509/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.45.up_proj:  34%|███▍      | 12510/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.45.down_proj:  34%|███▍      | 12511/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.46.gate_proj:  34%|███▍      | 12512/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.46.up_proj:  34%|███▍      | 12513/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.46.down_proj:  34%|███▍      | 12514/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.47.gate_proj:  34%|███▍      | 12515/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.47.up_proj:  34%|███▍      | 12516/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.47.down_proj:  34%|███▍      | 12517/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.48.gate_proj:  34%|███▍      | 12518/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.48.up_proj:  34%|███▍      | 12519/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.48.down_proj:  34%|███▍      | 12520/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.49.gate_proj:  34%|███▍      | 12521/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.49.up_proj:  34%|███▍      | 12522/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.49.down_proj:  34%|███▍      | 12523/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.50.gate_proj:  34%|███▍      | 12524/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.50.up_proj:  34%|███▍      | 12525/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.50.down_proj:  34%|███▍      | 12526/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.51.gate_proj:  34%|███▍      | 12527/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.51.up_proj:  34%|███▍      | 12528/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.51.down_proj:  34%|███▍      | 12529/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.52.gate_proj:  34%|███▍      | 12530/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.52.up_proj:  34%|███▍      | 12531/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.52.down_proj:  34%|███▍      | 12532/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.53.gate_proj:  34%|███▍      | 12533/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.53.up_proj:  34%|███▍      | 12534/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.53.down_proj:  34%|███▍      | 12535/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.54.gate_proj:  34%|███▍      | 12536/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.54.up_proj:  34%|███▍      | 12537/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.54.down_proj:  34%|███▍      | 12538/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.55.gate_proj:  34%|███▍      | 12539/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.55.up_proj:  34%|███▍      | 12540/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.55.down_proj:  34%|███▍      | 12541/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.56.gate_proj:  34%|███▍      | 12542/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.56.up_proj:  34%|███▍      | 12543/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.56.down_proj:  34%|███▍      | 12544/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.57.gate_proj:  34%|███▍      | 12545/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.57.up_proj:  34%|███▍      | 12546/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.57.down_proj:  34%|███▍      | 12547/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.58.gate_proj:  34%|███▍      | 12548/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.58.up_proj:  34%|███▍      | 12549/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.58.down_proj:  34%|███▍      | 12550/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.59.gate_proj:  34%|███▍      | 12551/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.59.up_proj:  34%|███▍      | 12552/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.59.down_proj:  34%|███▍      | 12553/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.60.gate_proj:  34%|███▍      | 12554/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.60.up_proj:  34%|███▍      | 12555/36566 [00:12<00:21, 1141.22it/s]  
packing model.layers.31.mlp.experts.60.down_proj:  34%|███▍      | 12556/36566 [00:12<00:21, 1141.22it/s]
packing model.layers.31.mlp.experts.60.down_proj:  34%|███▍      | 12557/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.61.gate_proj:  34%|███▍      | 12557/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.61.up_proj:  34%|███▍      | 12558/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.61.down_proj:  34%|███▍      | 12559/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.62.gate_proj:  34%|███▍      | 12560/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.62.up_proj:  34%|███▍      | 12561/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.62.down_proj:  34%|███▍      | 12562/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.63.gate_proj:  34%|███▍      | 12563/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.63.up_proj:  34%|███▍      | 12564/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.63.down_proj:  34%|███▍      | 12565/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.64.gate_proj:  34%|███▍      | 12566/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.64.up_proj:  34%|███▍      | 12567/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.64.down_proj:  34%|███▍      | 12568/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.65.gate_proj:  34%|███▍      | 12569/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.65.up_proj:  34%|███▍      | 12570/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.65.down_proj:  34%|███▍      | 12571/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.66.gate_proj:  34%|███▍      | 12572/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.66.up_proj:  34%|███▍      | 12573/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.66.down_proj:  34%|███▍      | 12574/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.67.gate_proj:  34%|███▍      | 12575/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.67.up_proj:  34%|███▍      | 12576/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.67.down_proj:  34%|███▍      | 12577/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.68.gate_proj:  34%|███▍      | 12578/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.68.up_proj:  34%|███▍      | 12579/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.68.down_proj:  34%|███▍      | 12580/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.69.gate_proj:  34%|███▍      | 12581/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.69.up_proj:  34%|███▍      | 12582/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.69.down_proj:  34%|███▍      | 12583/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.70.gate_proj:  34%|███▍      | 12584/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.70.up_proj:  34%|███▍      | 12585/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.70.down_proj:  34%|███▍      | 12586/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.71.gate_proj:  34%|███▍      | 12587/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.71.up_proj:  34%|███▍      | 12588/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.71.down_proj:  34%|███▍      | 12589/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.72.gate_proj:  34%|███▍      | 12590/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.72.up_proj:  34%|███▍      | 12591/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.72.down_proj:  34%|███▍      | 12592/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.73.gate_proj:  34%|███▍      | 12593/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.73.up_proj:  34%|███▍      | 12594/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.73.down_proj:  34%|███▍      | 12595/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.74.gate_proj:  34%|███▍      | 12596/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.74.up_proj:  34%|███▍      | 12597/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.74.down_proj:  34%|███▍      | 12598/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.75.gate_proj:  34%|███▍      | 12599/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.75.up_proj:  34%|███▍      | 12600/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.75.down_proj:  34%|███▍      | 12601/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.76.gate_proj:  34%|███▍      | 12602/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.76.up_proj:  34%|███▍      | 12603/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.76.down_proj:  34%|███▍      | 12604/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.77.gate_proj:  34%|███▍      | 12605/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.77.up_proj:  34%|███▍      | 12606/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.77.down_proj:  34%|███▍      | 12607/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.78.gate_proj:  34%|███▍      | 12608/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.78.up_proj:  34%|███▍      | 12609/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.78.down_proj:  34%|███▍      | 12610/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.79.gate_proj:  34%|███▍      | 12611/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.79.up_proj:  34%|███▍      | 12612/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.79.down_proj:  34%|███▍      | 12613/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.80.gate_proj:  34%|███▍      | 12614/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.80.up_proj:  34%|███▍      | 12615/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.80.down_proj:  35%|███▍      | 12616/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.81.gate_proj:  35%|███▍      | 12617/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.81.up_proj:  35%|███▍      | 12618/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.81.down_proj:  35%|███▍      | 12619/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.82.gate_proj:  35%|███▍      | 12620/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.82.up_proj:  35%|███▍      | 12621/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.82.down_proj:  35%|███▍      | 12622/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.83.gate_proj:  35%|███▍      | 12623/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.83.up_proj:  35%|███▍      | 12624/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.83.down_proj:  35%|███▍      | 12625/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.84.gate_proj:  35%|███▍      | 12626/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.84.up_proj:  35%|███▍      | 12627/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.84.down_proj:  35%|███▍      | 12628/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.85.gate_proj:  35%|███▍      | 12629/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.85.up_proj:  35%|███▍      | 12630/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.85.down_proj:  35%|███▍      | 12631/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.86.gate_proj:  35%|███▍      | 12632/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.86.up_proj:  35%|███▍      | 12633/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.86.down_proj:  35%|███▍      | 12634/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.87.gate_proj:  35%|███▍      | 12635/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.87.up_proj:  35%|███▍      | 12636/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.87.down_proj:  35%|███▍      | 12637/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.88.gate_proj:  35%|███▍      | 12638/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.88.up_proj:  35%|███▍      | 12639/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.88.down_proj:  35%|███▍      | 12640/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.89.gate_proj:  35%|███▍      | 12641/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.89.up_proj:  35%|███▍      | 12642/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.89.down_proj:  35%|███▍      | 12643/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.90.gate_proj:  35%|███▍      | 12644/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.90.up_proj:  35%|███▍      | 12645/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.90.down_proj:  35%|███▍      | 12646/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.91.gate_proj:  35%|███▍      | 12647/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.91.up_proj:  35%|███▍      | 12648/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.91.down_proj:  35%|███▍      | 12649/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.92.gate_proj:  35%|███▍      | 12650/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.92.up_proj:  35%|███▍      | 12651/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.92.down_proj:  35%|███▍      | 12652/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.93.gate_proj:  35%|███▍      | 12653/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.93.up_proj:  35%|███▍      | 12654/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.93.down_proj:  35%|███▍      | 12655/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.94.gate_proj:  35%|███▍      | 12656/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.94.up_proj:  35%|███▍      | 12657/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.94.down_proj:  35%|███▍      | 12658/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.95.gate_proj:  35%|███▍      | 12659/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.95.up_proj:  35%|███▍      | 12660/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.95.down_proj:  35%|███▍      | 12661/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.96.gate_proj:  35%|███▍      | 12662/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.96.up_proj:  35%|███▍      | 12663/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.96.down_proj:  35%|███▍      | 12664/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.97.gate_proj:  35%|███▍      | 12665/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.97.up_proj:  35%|███▍      | 12666/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.97.down_proj:  35%|███▍      | 12667/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.98.gate_proj:  35%|███▍      | 12668/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.98.up_proj:  35%|███▍      | 12669/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.98.down_proj:  35%|███▍      | 12670/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.99.gate_proj:  35%|███▍      | 12671/36566 [00:12<00:20, 1145.42it/s]
packing model.layers.31.mlp.experts.99.up_proj:  35%|███▍      | 12672/36566 [00:12<00:20, 1145.42it/s]  
packing model.layers.31.mlp.experts.99.up_proj:  35%|███▍      | 12673/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.99.down_proj:  35%|███▍      | 12673/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.100.gate_proj:  35%|███▍      | 12674/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.100.up_proj:  35%|███▍      | 12675/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.100.down_proj:  35%|███▍      | 12676/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.101.gate_proj:  35%|███▍      | 12677/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.101.up_proj:  35%|███▍      | 12678/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.101.down_proj:  35%|███▍      | 12679/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.102.gate_proj:  35%|███▍      | 12680/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.102.up_proj:  35%|███▍      | 12681/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.102.down_proj:  35%|███▍      | 12682/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.103.gate_proj:  35%|███▍      | 12683/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.103.up_proj:  35%|███▍      | 12684/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.103.down_proj:  35%|███▍      | 12685/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.104.gate_proj:  35%|███▍      | 12686/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.104.up_proj:  35%|███▍      | 12687/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.104.down_proj:  35%|███▍      | 12688/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.105.gate_proj:  35%|███▍      | 12689/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.105.up_proj:  35%|███▍      | 12690/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.105.down_proj:  35%|███▍      | 12691/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.106.gate_proj:  35%|███▍      | 12692/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.106.up_proj:  35%|███▍      | 12693/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.106.down_proj:  35%|███▍      | 12694/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.107.gate_proj:  35%|███▍      | 12695/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.107.up_proj:  35%|███▍      | 12696/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.107.down_proj:  35%|███▍      | 12697/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.108.gate_proj:  35%|███▍      | 12698/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.108.up_proj:  35%|███▍      | 12699/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.108.down_proj:  35%|███▍      | 12700/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.109.gate_proj:  35%|███▍      | 12701/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.109.up_proj:  35%|███▍      | 12702/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.109.down_proj:  35%|███▍      | 12703/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.110.gate_proj:  35%|███▍      | 12704/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.110.up_proj:  35%|███▍      | 12705/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.110.down_proj:  35%|███▍      | 12706/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.111.gate_proj:  35%|███▍      | 12707/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.111.up_proj:  35%|███▍      | 12708/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.111.down_proj:  35%|███▍      | 12709/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.112.gate_proj:  35%|███▍      | 12710/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.112.up_proj:  35%|███▍      | 12711/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.112.down_proj:  35%|███▍      | 12712/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.113.gate_proj:  35%|███▍      | 12713/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.113.up_proj:  35%|███▍      | 12714/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.113.down_proj:  35%|███▍      | 12715/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.114.gate_proj:  35%|███▍      | 12716/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.114.up_proj:  35%|███▍      | 12717/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.114.down_proj:  35%|███▍      | 12718/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.115.gate_proj:  35%|███▍      | 12719/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.115.up_proj:  35%|███▍      | 12720/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.115.down_proj:  35%|███▍      | 12721/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.116.gate_proj:  35%|███▍      | 12722/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.116.up_proj:  35%|███▍      | 12723/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.116.down_proj:  35%|███▍      | 12724/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.117.gate_proj:  35%|███▍      | 12725/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.117.up_proj:  35%|███▍      | 12726/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.117.down_proj:  35%|███▍      | 12727/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.118.gate_proj:  35%|███▍      | 12728/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.118.up_proj:  35%|███▍      | 12729/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.118.down_proj:  35%|███▍      | 12730/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.119.gate_proj:  35%|███▍      | 12731/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.119.up_proj:  35%|███▍      | 12732/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.119.down_proj:  35%|███▍      | 12733/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.120.gate_proj:  35%|███▍      | 12734/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.120.up_proj:  35%|███▍      | 12735/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.120.down_proj:  35%|███▍      | 12736/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.121.gate_proj:  35%|███▍      | 12737/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.121.up_proj:  35%|███▍      | 12738/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.121.down_proj:  35%|███▍      | 12739/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.122.gate_proj:  35%|███▍      | 12740/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.122.up_proj:  35%|███▍      | 12741/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.122.down_proj:  35%|███▍      | 12742/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.123.gate_proj:  35%|███▍      | 12743/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.123.up_proj:  35%|███▍      | 12744/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.123.down_proj:  35%|███▍      | 12745/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.124.gate_proj:  35%|███▍      | 12746/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.124.up_proj:  35%|███▍      | 12747/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.124.down_proj:  35%|███▍      | 12748/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.125.gate_proj:  35%|███▍      | 12749/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.125.up_proj:  35%|███▍      | 12750/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.125.down_proj:  35%|███▍      | 12751/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.126.gate_proj:  35%|███▍      | 12752/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.126.up_proj:  35%|███▍      | 12753/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.126.down_proj:  35%|███▍      | 12754/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.127.gate_proj:  35%|███▍      | 12755/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.31.mlp.experts.127.up_proj:  35%|███▍      | 12756/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.31.mlp.experts.127.down_proj:  35%|███▍      | 12757/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.0.gate_proj:  35%|███▍      | 12758/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.0.up_proj:  35%|███▍      | 12759/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.0.down_proj:  35%|███▍      | 12760/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.1.gate_proj:  35%|███▍      | 12761/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.1.up_proj:  35%|███▍      | 12762/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.1.down_proj:  35%|███▍      | 12763/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.2.gate_proj:  35%|███▍      | 12764/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.2.up_proj:  35%|███▍      | 12765/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.2.down_proj:  35%|███▍      | 12766/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.3.gate_proj:  35%|███▍      | 12767/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.3.up_proj:  35%|███▍      | 12768/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.3.down_proj:  35%|███▍      | 12769/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.4.gate_proj:  35%|███▍      | 12770/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.4.up_proj:  35%|███▍      | 12771/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.4.down_proj:  35%|███▍      | 12772/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.5.gate_proj:  35%|███▍      | 12773/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.5.up_proj:  35%|███▍      | 12774/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.5.down_proj:  35%|███▍      | 12775/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.6.gate_proj:  35%|███▍      | 12776/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.6.up_proj:  35%|███▍      | 12777/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.6.down_proj:  35%|███▍      | 12778/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.7.gate_proj:  35%|███▍      | 12779/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.7.up_proj:  35%|███▍      | 12780/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.7.down_proj:  35%|███▍      | 12781/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.8.gate_proj:  35%|███▍      | 12782/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.8.up_proj:  35%|███▍      | 12783/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.8.down_proj:  35%|███▍      | 12784/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.9.gate_proj:  35%|███▍      | 12785/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.9.up_proj:  35%|███▍      | 12786/36566 [00:12<00:20, 1147.30it/s]  
packing model.layers.32.mlp.experts.9.down_proj:  35%|███▍      | 12787/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.10.gate_proj:  35%|███▍      | 12788/36566 [00:12<00:20, 1147.30it/s]
packing model.layers.32.mlp.experts.10.gate_proj:  35%|███▍      | 12789/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.10.up_proj:  35%|███▍      | 12789/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.10.down_proj:  35%|███▍      | 12790/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.11.gate_proj:  35%|███▍      | 12791/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.11.up_proj:  35%|███▍      | 12792/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.11.down_proj:  35%|███▍      | 12793/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.12.gate_proj:  35%|███▍      | 12794/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.12.up_proj:  35%|███▍      | 12795/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.12.down_proj:  35%|███▍      | 12796/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.13.gate_proj:  35%|███▍      | 12797/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.13.up_proj:  35%|███▍      | 12798/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.13.down_proj:  35%|███▌      | 12799/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.14.gate_proj:  35%|███▌      | 12800/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.14.up_proj:  35%|███▌      | 12801/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.14.down_proj:  35%|███▌      | 12802/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.15.gate_proj:  35%|███▌      | 12803/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.15.up_proj:  35%|███▌      | 12804/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.15.down_proj:  35%|███▌      | 12805/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.16.gate_proj:  35%|███▌      | 12806/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.16.up_proj:  35%|███▌      | 12807/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.16.down_proj:  35%|███▌      | 12808/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.17.gate_proj:  35%|███▌      | 12809/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.17.up_proj:  35%|███▌      | 12810/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.17.down_proj:  35%|███▌      | 12811/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.18.gate_proj:  35%|███▌      | 12812/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.18.up_proj:  35%|███▌      | 12813/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.18.down_proj:  35%|███▌      | 12814/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.19.gate_proj:  35%|███▌      | 12815/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.19.up_proj:  35%|███▌      | 12816/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.19.down_proj:  35%|███▌      | 12817/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.20.gate_proj:  35%|███▌      | 12818/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.20.up_proj:  35%|███▌      | 12819/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.20.down_proj:  35%|███▌      | 12820/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.21.gate_proj:  35%|███▌      | 12821/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.21.up_proj:  35%|███▌      | 12822/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.21.down_proj:  35%|███▌      | 12823/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.22.gate_proj:  35%|███▌      | 12824/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.22.up_proj:  35%|███▌      | 12825/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.22.down_proj:  35%|███▌      | 12826/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.23.gate_proj:  35%|███▌      | 12827/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.23.up_proj:  35%|███▌      | 12828/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.23.down_proj:  35%|███▌      | 12829/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.24.gate_proj:  35%|███▌      | 12830/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.24.up_proj:  35%|███▌      | 12831/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.24.down_proj:  35%|███▌      | 12832/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.25.gate_proj:  35%|███▌      | 12833/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.25.up_proj:  35%|███▌      | 12834/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.25.down_proj:  35%|███▌      | 12835/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.26.gate_proj:  35%|███▌      | 12836/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.26.up_proj:  35%|███▌      | 12837/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.26.down_proj:  35%|███▌      | 12838/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.27.gate_proj:  35%|███▌      | 12839/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.27.up_proj:  35%|███▌      | 12840/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.27.down_proj:  35%|███▌      | 12841/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.28.gate_proj:  35%|███▌      | 12842/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.28.up_proj:  35%|███▌      | 12843/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.28.down_proj:  35%|███▌      | 12844/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.29.gate_proj:  35%|███▌      | 12845/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.29.up_proj:  35%|███▌      | 12846/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.29.down_proj:  35%|███▌      | 12847/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.30.gate_proj:  35%|███▌      | 12848/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.30.up_proj:  35%|███▌      | 12849/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.30.down_proj:  35%|███▌      | 12850/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.31.gate_proj:  35%|███▌      | 12851/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.31.up_proj:  35%|███▌      | 12852/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.31.down_proj:  35%|███▌      | 12853/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.32.gate_proj:  35%|███▌      | 12854/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.32.up_proj:  35%|███▌      | 12855/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.32.down_proj:  35%|███▌      | 12856/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.33.gate_proj:  35%|███▌      | 12857/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.33.up_proj:  35%|███▌      | 12858/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.33.down_proj:  35%|███▌      | 12859/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.34.gate_proj:  35%|███▌      | 12860/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.34.up_proj:  35%|███▌      | 12861/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.34.down_proj:  35%|███▌      | 12862/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.35.gate_proj:  35%|███▌      | 12863/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.35.up_proj:  35%|███▌      | 12864/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.35.down_proj:  35%|███▌      | 12865/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.36.gate_proj:  35%|███▌      | 12866/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.36.up_proj:  35%|███▌      | 12867/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.36.down_proj:  35%|███▌      | 12868/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.37.gate_proj:  35%|███▌      | 12869/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.37.up_proj:  35%|███▌      | 12870/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.37.down_proj:  35%|███▌      | 12871/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.38.gate_proj:  35%|███▌      | 12872/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.38.up_proj:  35%|███▌      | 12873/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.38.down_proj:  35%|███▌      | 12874/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.39.gate_proj:  35%|███▌      | 12875/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.39.up_proj:  35%|███▌      | 12876/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.39.down_proj:  35%|███▌      | 12877/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.40.gate_proj:  35%|███▌      | 12878/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.40.up_proj:  35%|███▌      | 12879/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.40.down_proj:  35%|███▌      | 12880/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.41.gate_proj:  35%|███▌      | 12881/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.41.up_proj:  35%|███▌      | 12882/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.41.down_proj:  35%|███▌      | 12883/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.42.gate_proj:  35%|███▌      | 12884/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.42.up_proj:  35%|███▌      | 12885/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.42.down_proj:  35%|███▌      | 12886/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.43.gate_proj:  35%|███▌      | 12887/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.43.up_proj:  35%|███▌      | 12888/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.43.down_proj:  35%|███▌      | 12889/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.44.gate_proj:  35%|███▌      | 12890/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.44.up_proj:  35%|███▌      | 12891/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.44.down_proj:  35%|███▌      | 12892/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.45.gate_proj:  35%|███▌      | 12893/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.45.up_proj:  35%|███▌      | 12894/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.45.down_proj:  35%|███▌      | 12895/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.46.gate_proj:  35%|███▌      | 12896/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.46.up_proj:  35%|███▌      | 12897/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.46.down_proj:  35%|███▌      | 12898/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.47.gate_proj:  35%|███▌      | 12899/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.47.up_proj:  35%|███▌      | 12900/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.47.down_proj:  35%|███▌      | 12901/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.48.gate_proj:  35%|███▌      | 12902/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.48.up_proj:  35%|███▌      | 12903/36566 [00:12<00:20, 1150.21it/s]  
packing model.layers.32.mlp.experts.48.down_proj:  35%|███▌      | 12904/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.49.gate_proj:  35%|███▌      | 12905/36566 [00:12<00:20, 1150.21it/s]
packing model.layers.32.mlp.experts.49.gate_proj:  35%|███▌      | 12906/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.49.up_proj:  35%|███▌      | 12906/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.49.down_proj:  35%|███▌      | 12907/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.50.gate_proj:  35%|███▌      | 12908/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.50.up_proj:  35%|███▌      | 12909/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.50.down_proj:  35%|███▌      | 12910/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.51.gate_proj:  35%|███▌      | 12911/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.51.up_proj:  35%|███▌      | 12912/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.51.down_proj:  35%|███▌      | 12913/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.52.gate_proj:  35%|███▌      | 12914/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.52.up_proj:  35%|███▌      | 12915/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.52.down_proj:  35%|███▌      | 12916/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.53.gate_proj:  35%|███▌      | 12917/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.53.up_proj:  35%|███▌      | 12918/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.53.down_proj:  35%|███▌      | 12919/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.54.gate_proj:  35%|███▌      | 12920/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.54.up_proj:  35%|███▌      | 12921/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.54.down_proj:  35%|███▌      | 12922/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.55.gate_proj:  35%|███▌      | 12923/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.55.up_proj:  35%|███▌      | 12924/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.55.down_proj:  35%|███▌      | 12925/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.56.gate_proj:  35%|███▌      | 12926/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.56.up_proj:  35%|███▌      | 12927/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.56.down_proj:  35%|███▌      | 12928/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.57.gate_proj:  35%|███▌      | 12929/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.57.up_proj:  35%|███▌      | 12930/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.57.down_proj:  35%|███▌      | 12931/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.58.gate_proj:  35%|███▌      | 12932/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.58.up_proj:  35%|███▌      | 12933/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.58.down_proj:  35%|███▌      | 12934/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.59.gate_proj:  35%|███▌      | 12935/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.59.up_proj:  35%|███▌      | 12936/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.59.down_proj:  35%|███▌      | 12937/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.60.gate_proj:  35%|███▌      | 12938/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.60.up_proj:  35%|███▌      | 12939/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.60.down_proj:  35%|███▌      | 12940/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.61.gate_proj:  35%|███▌      | 12941/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.61.up_proj:  35%|███▌      | 12942/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.61.down_proj:  35%|███▌      | 12943/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.62.gate_proj:  35%|███▌      | 12944/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.62.up_proj:  35%|███▌      | 12945/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.62.down_proj:  35%|███▌      | 12946/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.63.gate_proj:  35%|███▌      | 12947/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.63.up_proj:  35%|███▌      | 12948/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.63.down_proj:  35%|███▌      | 12949/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.64.gate_proj:  35%|███▌      | 12950/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.64.up_proj:  35%|███▌      | 12951/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.64.down_proj:  35%|███▌      | 12952/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.65.gate_proj:  35%|███▌      | 12953/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.65.up_proj:  35%|███▌      | 12954/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.65.down_proj:  35%|███▌      | 12955/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.66.gate_proj:  35%|███▌      | 12956/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.66.up_proj:  35%|███▌      | 12957/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.66.down_proj:  35%|███▌      | 12958/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.67.gate_proj:  35%|███▌      | 12959/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.67.up_proj:  35%|███▌      | 12960/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.67.down_proj:  35%|███▌      | 12961/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.68.gate_proj:  35%|███▌      | 12962/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.68.up_proj:  35%|███▌      | 12963/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.68.down_proj:  35%|███▌      | 12964/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.69.gate_proj:  35%|███▌      | 12965/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.69.up_proj:  35%|███▌      | 12966/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.69.down_proj:  35%|███▌      | 12967/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.70.gate_proj:  35%|███▌      | 12968/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.70.up_proj:  35%|███▌      | 12969/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.70.down_proj:  35%|███▌      | 12970/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.71.gate_proj:  35%|███▌      | 12971/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.71.up_proj:  35%|███▌      | 12972/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.71.down_proj:  35%|███▌      | 12973/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.72.gate_proj:  35%|███▌      | 12974/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.72.up_proj:  35%|███▌      | 12975/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.72.down_proj:  35%|███▌      | 12976/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.73.gate_proj:  35%|███▌      | 12977/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.73.up_proj:  35%|███▌      | 12978/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.73.down_proj:  35%|███▌      | 12979/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.74.gate_proj:  35%|███▌      | 12980/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.74.up_proj:  36%|███▌      | 12981/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.74.down_proj:  36%|███▌      | 12982/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.75.gate_proj:  36%|███▌      | 12983/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.75.up_proj:  36%|███▌      | 12984/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.75.down_proj:  36%|███▌      | 12985/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.76.gate_proj:  36%|███▌      | 12986/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.76.up_proj:  36%|███▌      | 12987/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.76.down_proj:  36%|███▌      | 12988/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.77.gate_proj:  36%|███▌      | 12989/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.77.up_proj:  36%|███▌      | 12990/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.77.down_proj:  36%|███▌      | 12991/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.78.gate_proj:  36%|███▌      | 12992/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.78.up_proj:  36%|███▌      | 12993/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.78.down_proj:  36%|███▌      | 12994/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.79.gate_proj:  36%|███▌      | 12995/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.79.up_proj:  36%|███▌      | 12996/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.79.down_proj:  36%|███▌      | 12997/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.80.gate_proj:  36%|███▌      | 12998/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.80.up_proj:  36%|███▌      | 12999/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.80.down_proj:  36%|███▌      | 13000/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.81.gate_proj:  36%|███▌      | 13001/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.81.up_proj:  36%|███▌      | 13002/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.81.down_proj:  36%|███▌      | 13003/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.82.gate_proj:  36%|███▌      | 13004/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.82.up_proj:  36%|███▌      | 13005/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.82.down_proj:  36%|███▌      | 13006/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.83.gate_proj:  36%|███▌      | 13007/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.83.up_proj:  36%|███▌      | 13008/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.83.down_proj:  36%|███▌      | 13009/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.84.gate_proj:  36%|███▌      | 13010/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.84.up_proj:  36%|███▌      | 13011/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.84.down_proj:  36%|███▌      | 13012/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.85.gate_proj:  36%|███▌      | 13013/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.85.up_proj:  36%|███▌      | 13014/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.85.down_proj:  36%|███▌      | 13015/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.86.gate_proj:  36%|███▌      | 13016/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.86.up_proj:  36%|███▌      | 13017/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.86.down_proj:  36%|███▌      | 13018/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.87.gate_proj:  36%|███▌      | 13019/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.87.up_proj:  36%|███▌      | 13020/36566 [00:12<00:20, 1154.64it/s]  
packing model.layers.32.mlp.experts.87.down_proj:  36%|███▌      | 13021/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.88.gate_proj:  36%|███▌      | 13022/36566 [00:12<00:20, 1154.64it/s]
packing model.layers.32.mlp.experts.88.gate_proj:  36%|███▌      | 13023/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.88.up_proj:  36%|███▌      | 13023/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.88.down_proj:  36%|███▌      | 13024/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.89.gate_proj:  36%|███▌      | 13025/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.89.up_proj:  36%|███▌      | 13026/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.89.down_proj:  36%|███▌      | 13027/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.90.gate_proj:  36%|███▌      | 13028/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.90.up_proj:  36%|███▌      | 13029/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.90.down_proj:  36%|███▌      | 13030/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.91.gate_proj:  36%|███▌      | 13031/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.91.up_proj:  36%|███▌      | 13032/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.91.down_proj:  36%|███▌      | 13033/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.92.gate_proj:  36%|███▌      | 13034/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.92.up_proj:  36%|███▌      | 13035/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.92.down_proj:  36%|███▌      | 13036/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.93.gate_proj:  36%|███▌      | 13037/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.93.up_proj:  36%|███▌      | 13038/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.93.down_proj:  36%|███▌      | 13039/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.94.gate_proj:  36%|███▌      | 13040/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.94.up_proj:  36%|███▌      | 13041/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.94.down_proj:  36%|███▌      | 13042/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.95.gate_proj:  36%|███▌      | 13043/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.95.up_proj:  36%|███▌      | 13044/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.95.down_proj:  36%|███▌      | 13045/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.96.gate_proj:  36%|███▌      | 13046/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.96.up_proj:  36%|███▌      | 13047/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.96.down_proj:  36%|███▌      | 13048/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.97.gate_proj:  36%|███▌      | 13049/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.97.up_proj:  36%|███▌      | 13050/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.97.down_proj:  36%|███▌      | 13051/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.98.gate_proj:  36%|███▌      | 13052/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.98.up_proj:  36%|███▌      | 13053/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.98.down_proj:  36%|███▌      | 13054/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.99.gate_proj:  36%|███▌      | 13055/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.99.up_proj:  36%|███▌      | 13056/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.99.down_proj:  36%|███▌      | 13057/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.100.gate_proj:  36%|███▌      | 13058/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.100.up_proj:  36%|███▌      | 13059/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.100.down_proj:  36%|███▌      | 13060/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.101.gate_proj:  36%|███▌      | 13061/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.101.up_proj:  36%|███▌      | 13062/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.101.down_proj:  36%|███▌      | 13063/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.102.gate_proj:  36%|███▌      | 13064/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.102.up_proj:  36%|███▌      | 13065/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.102.down_proj:  36%|███▌      | 13066/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.103.gate_proj:  36%|███▌      | 13067/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.103.up_proj:  36%|███▌      | 13068/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.103.down_proj:  36%|███▌      | 13069/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.104.gate_proj:  36%|███▌      | 13070/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.104.up_proj:  36%|███▌      | 13071/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.104.down_proj:  36%|███▌      | 13072/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.105.gate_proj:  36%|███▌      | 13073/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.105.up_proj:  36%|███▌      | 13074/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.105.down_proj:  36%|███▌      | 13075/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.106.gate_proj:  36%|███▌      | 13076/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.106.up_proj:  36%|███▌      | 13077/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.106.down_proj:  36%|███▌      | 13078/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.107.gate_proj:  36%|███▌      | 13079/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.107.up_proj:  36%|███▌      | 13080/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.107.down_proj:  36%|███▌      | 13081/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.108.gate_proj:  36%|███▌      | 13082/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.108.up_proj:  36%|███▌      | 13083/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.108.down_proj:  36%|███▌      | 13084/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.109.gate_proj:  36%|███▌      | 13085/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.109.up_proj:  36%|███▌      | 13086/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.109.down_proj:  36%|███▌      | 13087/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.110.gate_proj:  36%|███▌      | 13088/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.110.up_proj:  36%|███▌      | 13089/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.110.down_proj:  36%|███▌      | 13090/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.111.gate_proj:  36%|███▌      | 13091/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.111.up_proj:  36%|███▌      | 13092/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.111.down_proj:  36%|███▌      | 13093/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.112.gate_proj:  36%|███▌      | 13094/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.112.up_proj:  36%|███▌      | 13095/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.112.down_proj:  36%|███▌      | 13096/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.113.gate_proj:  36%|███▌      | 13097/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.113.up_proj:  36%|███▌      | 13098/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.113.down_proj:  36%|███▌      | 13099/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.114.gate_proj:  36%|███▌      | 13100/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.114.up_proj:  36%|███▌      | 13101/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.114.down_proj:  36%|███▌      | 13102/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.115.gate_proj:  36%|███▌      | 13103/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.115.up_proj:  36%|███▌      | 13104/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.115.down_proj:  36%|███▌      | 13105/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.116.gate_proj:  36%|███▌      | 13106/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.116.up_proj:  36%|███▌      | 13107/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.116.down_proj:  36%|███▌      | 13108/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.117.gate_proj:  36%|███▌      | 13109/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.117.up_proj:  36%|███▌      | 13110/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.117.down_proj:  36%|███▌      | 13111/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.118.gate_proj:  36%|███▌      | 13112/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.118.up_proj:  36%|███▌      | 13113/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.118.down_proj:  36%|███▌      | 13114/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.119.gate_proj:  36%|███▌      | 13115/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.119.up_proj:  36%|███▌      | 13116/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.119.down_proj:  36%|███▌      | 13117/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.120.gate_proj:  36%|███▌      | 13118/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.120.up_proj:  36%|███▌      | 13119/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.120.down_proj:  36%|███▌      | 13120/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.121.gate_proj:  36%|███▌      | 13121/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.121.up_proj:  36%|███▌      | 13122/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.121.down_proj:  36%|███▌      | 13123/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.122.gate_proj:  36%|███▌      | 13124/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.122.up_proj:  36%|███▌      | 13125/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.122.down_proj:  36%|███▌      | 13126/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.123.gate_proj:  36%|███▌      | 13127/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.123.up_proj:  36%|███▌      | 13128/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.123.down_proj:  36%|███▌      | 13129/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.124.gate_proj:  36%|███▌      | 13130/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.124.up_proj:  36%|███▌      | 13131/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.124.down_proj:  36%|███▌      | 13132/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.125.gate_proj:  36%|███▌      | 13133/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.125.up_proj:  36%|███▌      | 13134/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.125.down_proj:  36%|███▌      | 13135/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.126.gate_proj:  36%|███▌      | 13136/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.126.up_proj:  36%|███▌      | 13137/36566 [00:12<00:20, 1156.45it/s]  
packing model.layers.32.mlp.experts.126.down_proj:  36%|███▌      | 13138/36566 [00:12<00:20, 1156.45it/s]
packing model.layers.32.mlp.experts.126.down_proj:  36%|███▌      | 13139/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.32.mlp.experts.127.gate_proj:  36%|███▌      | 13139/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.32.mlp.experts.127.up_proj:  36%|███▌      | 13140/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.32.mlp.experts.127.down_proj:  36%|███▌      | 13141/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.0.gate_proj:  36%|███▌      | 13142/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.0.up_proj:  36%|███▌      | 13143/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.0.down_proj:  36%|███▌      | 13144/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.1.gate_proj:  36%|███▌      | 13145/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.1.up_proj:  36%|███▌      | 13146/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.1.down_proj:  36%|███▌      | 13147/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.2.gate_proj:  36%|███▌      | 13148/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.2.up_proj:  36%|███▌      | 13149/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.2.down_proj:  36%|███▌      | 13150/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.3.gate_proj:  36%|███▌      | 13151/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.3.up_proj:  36%|███▌      | 13152/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.3.down_proj:  36%|███▌      | 13153/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.4.gate_proj:  36%|███▌      | 13154/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.4.up_proj:  36%|███▌      | 13155/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.4.down_proj:  36%|███▌      | 13156/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.5.gate_proj:  36%|███▌      | 13157/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.5.up_proj:  36%|███▌      | 13158/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.5.down_proj:  36%|███▌      | 13159/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.6.gate_proj:  36%|███▌      | 13160/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.6.up_proj:  36%|███▌      | 13161/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.6.down_proj:  36%|███▌      | 13162/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.7.gate_proj:  36%|███▌      | 13163/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.7.up_proj:  36%|███▌      | 13164/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.7.down_proj:  36%|███▌      | 13165/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.8.gate_proj:  36%|███▌      | 13166/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.8.up_proj:  36%|███▌      | 13167/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.8.down_proj:  36%|███▌      | 13168/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.9.gate_proj:  36%|███▌      | 13169/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.9.up_proj:  36%|███▌      | 13170/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.9.down_proj:  36%|███▌      | 13171/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.10.gate_proj:  36%|███▌      | 13172/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.10.up_proj:  36%|███▌      | 13173/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.10.down_proj:  36%|███▌      | 13174/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.11.gate_proj:  36%|███▌      | 13175/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.11.up_proj:  36%|███▌      | 13176/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.11.down_proj:  36%|███▌      | 13177/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.12.gate_proj:  36%|███▌      | 13178/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.12.up_proj:  36%|███▌      | 13179/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.12.down_proj:  36%|███▌      | 13180/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.13.gate_proj:  36%|███▌      | 13181/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.13.up_proj:  36%|███▌      | 13182/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.13.down_proj:  36%|███▌      | 13183/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.14.gate_proj:  36%|███▌      | 13184/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.14.up_proj:  36%|███▌      | 13185/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.14.down_proj:  36%|███▌      | 13186/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.15.gate_proj:  36%|███▌      | 13187/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.15.up_proj:  36%|███▌      | 13188/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.15.down_proj:  36%|███▌      | 13189/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.16.gate_proj:  36%|███▌      | 13190/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.16.up_proj:  36%|███▌      | 13191/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.16.down_proj:  36%|███▌      | 13192/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.17.gate_proj:  36%|███▌      | 13193/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.17.up_proj:  36%|███▌      | 13194/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.17.down_proj:  36%|███▌      | 13195/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.18.gate_proj:  36%|███▌      | 13196/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.18.up_proj:  36%|███▌      | 13197/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.18.down_proj:  36%|███▌      | 13198/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.19.gate_proj:  36%|███▌      | 13199/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.19.up_proj:  36%|███▌      | 13200/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.19.down_proj:  36%|███▌      | 13201/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.20.gate_proj:  36%|███▌      | 13202/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.20.up_proj:  36%|███▌      | 13203/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.20.down_proj:  36%|███▌      | 13204/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.21.gate_proj:  36%|███▌      | 13205/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.21.up_proj:  36%|███▌      | 13206/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.21.down_proj:  36%|███▌      | 13207/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.22.gate_proj:  36%|███▌      | 13208/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.22.up_proj:  36%|███▌      | 13209/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.22.down_proj:  36%|███▌      | 13210/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.23.gate_proj:  36%|███▌      | 13211/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.23.up_proj:  36%|███▌      | 13212/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.23.down_proj:  36%|███▌      | 13213/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.24.gate_proj:  36%|███▌      | 13214/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.24.up_proj:  36%|███▌      | 13215/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.24.down_proj:  36%|███▌      | 13216/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.25.gate_proj:  36%|███▌      | 13217/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.25.up_proj:  36%|███▌      | 13218/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.25.down_proj:  36%|███▌      | 13219/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.26.gate_proj:  36%|███▌      | 13220/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.26.up_proj:  36%|███▌      | 13221/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.26.down_proj:  36%|███▌      | 13222/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.27.gate_proj:  36%|███▌      | 13223/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.27.up_proj:  36%|███▌      | 13224/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.27.down_proj:  36%|███▌      | 13225/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.28.gate_proj:  36%|███▌      | 13226/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.28.up_proj:  36%|███▌      | 13227/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.28.down_proj:  36%|███▌      | 13228/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.29.gate_proj:  36%|███▌      | 13229/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.29.up_proj:  36%|███▌      | 13230/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.29.down_proj:  36%|███▌      | 13231/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.30.gate_proj:  36%|███▌      | 13232/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.30.up_proj:  36%|███▌      | 13233/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.30.down_proj:  36%|███▌      | 13234/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.31.gate_proj:  36%|███▌      | 13235/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.31.up_proj:  36%|███▌      | 13236/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.31.down_proj:  36%|███▌      | 13237/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.32.gate_proj:  36%|███▌      | 13238/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.32.up_proj:  36%|███▌      | 13239/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.32.down_proj:  36%|███▌      | 13240/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.33.gate_proj:  36%|███▌      | 13241/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.33.up_proj:  36%|███▌      | 13242/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.33.down_proj:  36%|███▌      | 13243/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.34.gate_proj:  36%|███▌      | 13244/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.34.up_proj:  36%|███▌      | 13245/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.34.down_proj:  36%|███▌      | 13246/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.35.gate_proj:  36%|███▌      | 13247/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.35.up_proj:  36%|███▌      | 13248/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.35.down_proj:  36%|███▌      | 13249/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.36.gate_proj:  36%|███▌      | 13250/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.36.up_proj:  36%|███▌      | 13251/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.36.down_proj:  36%|███▌      | 13252/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.37.gate_proj:  36%|███▌      | 13253/36566 [00:12<00:20, 1155.69it/s]
packing model.layers.33.mlp.experts.37.up_proj:  36%|███▌      | 13254/36566 [00:12<00:20, 1155.69it/s]  
packing model.layers.33.mlp.experts.37.up_proj:  36%|███▌      | 13255/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.37.down_proj:  36%|███▌      | 13255/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.38.gate_proj:  36%|███▋      | 13256/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.38.up_proj:  36%|███▋      | 13257/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.38.down_proj:  36%|███▋      | 13258/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.39.gate_proj:  36%|███▋      | 13259/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.39.up_proj:  36%|███▋      | 13260/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.39.down_proj:  36%|███▋      | 13261/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.40.gate_proj:  36%|███▋      | 13262/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.40.up_proj:  36%|███▋      | 13263/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.40.down_proj:  36%|███▋      | 13264/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.41.gate_proj:  36%|███▋      | 13265/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.41.up_proj:  36%|███▋      | 13266/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.41.down_proj:  36%|███▋      | 13267/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.42.gate_proj:  36%|███▋      | 13268/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.42.up_proj:  36%|███▋      | 13269/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.42.down_proj:  36%|███▋      | 13270/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.43.gate_proj:  36%|███▋      | 13271/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.43.up_proj:  36%|███▋      | 13272/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.43.down_proj:  36%|███▋      | 13273/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.44.gate_proj:  36%|███▋      | 13274/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.44.up_proj:  36%|███▋      | 13275/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.44.down_proj:  36%|███▋      | 13276/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.45.gate_proj:  36%|███▋      | 13277/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.45.up_proj:  36%|███▋      | 13278/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.45.down_proj:  36%|███▋      | 13279/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.46.gate_proj:  36%|███▋      | 13280/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.46.up_proj:  36%|███▋      | 13281/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.46.down_proj:  36%|███▋      | 13282/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.47.gate_proj:  36%|███▋      | 13283/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.47.up_proj:  36%|███▋      | 13284/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.47.down_proj:  36%|███▋      | 13285/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.48.gate_proj:  36%|███▋      | 13286/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.48.up_proj:  36%|███▋      | 13287/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.48.down_proj:  36%|███▋      | 13288/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.49.gate_proj:  36%|███▋      | 13289/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.49.up_proj:  36%|███▋      | 13290/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.49.down_proj:  36%|███▋      | 13291/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.50.gate_proj:  36%|███▋      | 13292/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.50.up_proj:  36%|███▋      | 13293/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.50.down_proj:  36%|███▋      | 13294/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.51.gate_proj:  36%|███▋      | 13295/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.51.up_proj:  36%|███▋      | 13296/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.51.down_proj:  36%|███▋      | 13297/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.52.gate_proj:  36%|███▋      | 13298/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.52.up_proj:  36%|███▋      | 13299/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.52.down_proj:  36%|███▋      | 13300/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.53.gate_proj:  36%|███▋      | 13301/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.53.up_proj:  36%|███▋      | 13302/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.53.down_proj:  36%|███▋      | 13303/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.54.gate_proj:  36%|███▋      | 13304/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.54.up_proj:  36%|███▋      | 13305/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.54.down_proj:  36%|███▋      | 13306/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.55.gate_proj:  36%|███▋      | 13307/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.55.up_proj:  36%|███▋      | 13308/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.55.down_proj:  36%|███▋      | 13309/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.56.gate_proj:  36%|███▋      | 13310/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.56.up_proj:  36%|███▋      | 13311/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.56.down_proj:  36%|███▋      | 13312/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.57.gate_proj:  36%|███▋      | 13313/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.57.up_proj:  36%|███▋      | 13314/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.57.down_proj:  36%|███▋      | 13315/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.58.gate_proj:  36%|███▋      | 13316/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.58.up_proj:  36%|███▋      | 13317/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.58.down_proj:  36%|███▋      | 13318/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.59.gate_proj:  36%|███▋      | 13319/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.59.up_proj:  36%|███▋      | 13320/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.59.down_proj:  36%|███▋      | 13321/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.60.gate_proj:  36%|███▋      | 13322/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.60.up_proj:  36%|███▋      | 13323/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.60.down_proj:  36%|███▋      | 13324/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.61.gate_proj:  36%|███▋      | 13325/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.61.up_proj:  36%|███▋      | 13326/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.61.down_proj:  36%|███▋      | 13327/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.62.gate_proj:  36%|███▋      | 13328/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.62.up_proj:  36%|███▋      | 13329/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.62.down_proj:  36%|███▋      | 13330/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.63.gate_proj:  36%|███▋      | 13331/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.63.up_proj:  36%|███▋      | 13332/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.63.down_proj:  36%|███▋      | 13333/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.64.gate_proj:  36%|███▋      | 13334/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.64.up_proj:  36%|███▋      | 13335/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.64.down_proj:  36%|███▋      | 13336/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.65.gate_proj:  36%|███▋      | 13337/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.65.up_proj:  36%|███▋      | 13338/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.65.down_proj:  36%|███▋      | 13339/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.66.gate_proj:  36%|███▋      | 13340/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.66.up_proj:  36%|███▋      | 13341/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.66.down_proj:  36%|███▋      | 13342/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.67.gate_proj:  36%|███▋      | 13343/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.67.up_proj:  36%|███▋      | 13344/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.67.down_proj:  36%|███▋      | 13345/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.68.gate_proj:  36%|███▋      | 13346/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.68.up_proj:  37%|███▋      | 13347/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.68.down_proj:  37%|███▋      | 13348/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.69.gate_proj:  37%|███▋      | 13349/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.69.up_proj:  37%|███▋      | 13350/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.69.down_proj:  37%|███▋      | 13351/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.70.gate_proj:  37%|███▋      | 13352/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.70.up_proj:  37%|███▋      | 13353/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.70.down_proj:  37%|███▋      | 13354/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.71.gate_proj:  37%|███▋      | 13355/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.71.up_proj:  37%|███▋      | 13356/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.71.down_proj:  37%|███▋      | 13357/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.72.gate_proj:  37%|███▋      | 13358/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.72.up_proj:  37%|███▋      | 13359/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.72.down_proj:  37%|███▋      | 13360/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.73.gate_proj:  37%|███▋      | 13361/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.73.up_proj:  37%|███▋      | 13362/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.73.down_proj:  37%|███▋      | 13363/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.74.gate_proj:  37%|███▋      | 13364/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.74.up_proj:  37%|███▋      | 13365/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.74.down_proj:  37%|███▋      | 13366/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.75.gate_proj:  37%|███▋      | 13367/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.75.up_proj:  37%|███▋      | 13368/36566 [00:12<00:20, 1155.58it/s]  
packing model.layers.33.mlp.experts.75.down_proj:  37%|███▋      | 13369/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.76.gate_proj:  37%|███▋      | 13370/36566 [00:12<00:20, 1155.58it/s]
packing model.layers.33.mlp.experts.76.gate_proj:  37%|███▋      | 13371/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.76.up_proj:  37%|███▋      | 13371/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.76.down_proj:  37%|███▋      | 13372/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.77.gate_proj:  37%|███▋      | 13373/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.77.up_proj:  37%|███▋      | 13374/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.77.down_proj:  37%|███▋      | 13375/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.78.gate_proj:  37%|███▋      | 13376/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.78.up_proj:  37%|███▋      | 13377/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.78.down_proj:  37%|███▋      | 13378/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.79.gate_proj:  37%|███▋      | 13379/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.79.up_proj:  37%|███▋      | 13380/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.79.down_proj:  37%|███▋      | 13381/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.80.gate_proj:  37%|███▋      | 13382/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.80.up_proj:  37%|███▋      | 13383/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.80.down_proj:  37%|███▋      | 13384/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.81.gate_proj:  37%|███▋      | 13385/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.81.up_proj:  37%|███▋      | 13386/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.81.down_proj:  37%|███▋      | 13387/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.82.gate_proj:  37%|███▋      | 13388/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.82.up_proj:  37%|███▋      | 13389/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.82.down_proj:  37%|███▋      | 13390/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.83.gate_proj:  37%|███▋      | 13391/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.83.up_proj:  37%|███▋      | 13392/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.83.down_proj:  37%|███▋      | 13393/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.84.gate_proj:  37%|███▋      | 13394/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.84.up_proj:  37%|███▋      | 13395/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.84.down_proj:  37%|███▋      | 13396/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.85.gate_proj:  37%|███▋      | 13397/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.85.up_proj:  37%|███▋      | 13398/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.85.down_proj:  37%|███▋      | 13399/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.86.gate_proj:  37%|███▋      | 13400/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.86.up_proj:  37%|███▋      | 13401/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.86.down_proj:  37%|███▋      | 13402/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.87.gate_proj:  37%|███▋      | 13403/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.87.up_proj:  37%|███▋      | 13404/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.87.down_proj:  37%|███▋      | 13405/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.88.gate_proj:  37%|███▋      | 13406/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.88.up_proj:  37%|███▋      | 13407/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.88.down_proj:  37%|███▋      | 13408/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.89.gate_proj:  37%|███▋      | 13409/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.89.up_proj:  37%|███▋      | 13410/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.89.down_proj:  37%|███▋      | 13411/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.90.gate_proj:  37%|███▋      | 13412/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.90.up_proj:  37%|███▋      | 13413/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.90.down_proj:  37%|███▋      | 13414/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.91.gate_proj:  37%|███▋      | 13415/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.91.up_proj:  37%|███▋      | 13416/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.91.down_proj:  37%|███▋      | 13417/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.92.gate_proj:  37%|███▋      | 13418/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.92.up_proj:  37%|███▋      | 13419/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.92.down_proj:  37%|███▋      | 13420/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.93.gate_proj:  37%|███▋      | 13421/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.93.up_proj:  37%|███▋      | 13422/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.93.down_proj:  37%|███▋      | 13423/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.94.gate_proj:  37%|███▋      | 13424/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.94.up_proj:  37%|███▋      | 13425/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.94.down_proj:  37%|███▋      | 13426/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.95.gate_proj:  37%|███▋      | 13427/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.95.up_proj:  37%|███▋      | 13428/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.95.down_proj:  37%|███▋      | 13429/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.96.gate_proj:  37%|███▋      | 13430/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.96.up_proj:  37%|███▋      | 13431/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.96.down_proj:  37%|███▋      | 13432/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.97.gate_proj:  37%|███▋      | 13433/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.97.up_proj:  37%|███▋      | 13434/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.97.down_proj:  37%|███▋      | 13435/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.98.gate_proj:  37%|███▋      | 13436/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.98.up_proj:  37%|███▋      | 13437/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.98.down_proj:  37%|███▋      | 13438/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.99.gate_proj:  37%|███▋      | 13439/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.99.up_proj:  37%|███▋      | 13440/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.99.down_proj:  37%|███▋      | 13441/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.100.gate_proj:  37%|███▋      | 13442/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.100.up_proj:  37%|███▋      | 13443/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.100.down_proj:  37%|███▋      | 13444/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.101.gate_proj:  37%|███▋      | 13445/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.101.up_proj:  37%|███▋      | 13446/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.101.down_proj:  37%|███▋      | 13447/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.102.gate_proj:  37%|███▋      | 13448/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.102.up_proj:  37%|███▋      | 13449/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.102.down_proj:  37%|███▋      | 13450/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.103.gate_proj:  37%|███▋      | 13451/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.103.up_proj:  37%|███▋      | 13452/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.103.down_proj:  37%|███▋      | 13453/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.104.gate_proj:  37%|███▋      | 13454/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.104.up_proj:  37%|███▋      | 13455/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.104.down_proj:  37%|███▋      | 13456/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.105.gate_proj:  37%|███▋      | 13457/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.105.up_proj:  37%|███▋      | 13458/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.105.down_proj:  37%|███▋      | 13459/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.106.gate_proj:  37%|███▋      | 13460/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.106.up_proj:  37%|███▋      | 13461/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.106.down_proj:  37%|███▋      | 13462/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.107.gate_proj:  37%|███▋      | 13463/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.107.up_proj:  37%|███▋      | 13464/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.107.down_proj:  37%|███▋      | 13465/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.108.gate_proj:  37%|███▋      | 13466/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.108.up_proj:  37%|███▋      | 13467/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.108.down_proj:  37%|███▋      | 13468/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.109.gate_proj:  37%|███▋      | 13469/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.109.up_proj:  37%|███▋      | 13470/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.109.down_proj:  37%|███▋      | 13471/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.110.gate_proj:  37%|███▋      | 13472/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.110.up_proj:  37%|███▋      | 13473/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.110.down_proj:  37%|███▋      | 13474/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.111.gate_proj:  37%|███▋      | 13475/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.111.up_proj:  37%|███▋      | 13476/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.111.down_proj:  37%|███▋      | 13477/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.112.gate_proj:  37%|███▋      | 13478/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.112.up_proj:  37%|███▋      | 13479/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.112.down_proj:  37%|███▋      | 13480/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.113.gate_proj:  37%|███▋      | 13481/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.113.up_proj:  37%|███▋      | 13482/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.113.down_proj:  37%|███▋      | 13483/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.114.gate_proj:  37%|███▋      | 13484/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.114.up_proj:  37%|███▋      | 13485/36566 [00:12<00:20, 1153.77it/s]  
packing model.layers.33.mlp.experts.114.down_proj:  37%|███▋      | 13486/36566 [00:12<00:20, 1153.77it/s]
packing model.layers.33.mlp.experts.114.down_proj:  37%|███▋      | 13487/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.115.gate_proj:  37%|███▋      | 13487/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.115.up_proj:  37%|███▋      | 13488/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.115.down_proj:  37%|███▋      | 13489/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.116.gate_proj:  37%|███▋      | 13490/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.116.up_proj:  37%|███▋      | 13491/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.116.down_proj:  37%|███▋      | 13492/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.117.gate_proj:  37%|███▋      | 13493/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.117.up_proj:  37%|███▋      | 13494/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.117.down_proj:  37%|███▋      | 13495/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.118.gate_proj:  37%|███▋      | 13496/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.118.up_proj:  37%|███▋      | 13497/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.118.down_proj:  37%|███▋      | 13498/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.119.gate_proj:  37%|███▋      | 13499/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.119.up_proj:  37%|███▋      | 13500/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.119.down_proj:  37%|███▋      | 13501/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.120.gate_proj:  37%|███▋      | 13502/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.120.up_proj:  37%|███▋      | 13503/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.120.down_proj:  37%|███▋      | 13504/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.121.gate_proj:  37%|███▋      | 13505/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.121.up_proj:  37%|███▋      | 13506/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.121.down_proj:  37%|███▋      | 13507/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.122.gate_proj:  37%|███▋      | 13508/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.122.up_proj:  37%|███▋      | 13509/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.122.down_proj:  37%|███▋      | 13510/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.123.gate_proj:  37%|███▋      | 13511/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.123.up_proj:  37%|███▋      | 13512/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.123.down_proj:  37%|███▋      | 13513/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.124.gate_proj:  37%|███▋      | 13514/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.124.up_proj:  37%|███▋      | 13515/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.124.down_proj:  37%|███▋      | 13516/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.125.gate_proj:  37%|███▋      | 13517/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.125.up_proj:  37%|███▋      | 13518/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.125.down_proj:  37%|███▋      | 13519/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.126.gate_proj:  37%|███▋      | 13520/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.126.up_proj:  37%|███▋      | 13521/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.126.down_proj:  37%|███▋      | 13522/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.127.gate_proj:  37%|███▋      | 13523/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.33.mlp.experts.127.up_proj:  37%|███▋      | 13524/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.33.mlp.experts.127.down_proj:  37%|███▋      | 13525/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.0.gate_proj:  37%|███▋      | 13526/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.0.up_proj:  37%|███▋      | 13527/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.0.down_proj:  37%|███▋      | 13528/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.1.gate_proj:  37%|███▋      | 13529/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.1.up_proj:  37%|███▋      | 13530/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.1.down_proj:  37%|███▋      | 13531/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.2.gate_proj:  37%|███▋      | 13532/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.2.up_proj:  37%|███▋      | 13533/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.2.down_proj:  37%|███▋      | 13534/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.3.gate_proj:  37%|███▋      | 13535/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.3.up_proj:  37%|███▋      | 13536/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.3.down_proj:  37%|███▋      | 13537/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.4.gate_proj:  37%|███▋      | 13538/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.4.up_proj:  37%|███▋      | 13539/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.4.down_proj:  37%|███▋      | 13540/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.5.gate_proj:  37%|███▋      | 13541/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.5.up_proj:  37%|███▋      | 13542/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.5.down_proj:  37%|███▋      | 13543/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.6.gate_proj:  37%|███▋      | 13544/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.6.up_proj:  37%|███▋      | 13545/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.6.down_proj:  37%|███▋      | 13546/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.7.gate_proj:  37%|███▋      | 13547/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.7.up_proj:  37%|███▋      | 13548/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.7.down_proj:  37%|███▋      | 13549/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.8.gate_proj:  37%|███▋      | 13550/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.8.up_proj:  37%|███▋      | 13551/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.8.down_proj:  37%|███▋      | 13552/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.9.gate_proj:  37%|███▋      | 13553/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.9.up_proj:  37%|███▋      | 13554/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.9.down_proj:  37%|███▋      | 13555/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.10.gate_proj:  37%|███▋      | 13556/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.10.up_proj:  37%|███▋      | 13557/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.10.down_proj:  37%|███▋      | 13558/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.11.gate_proj:  37%|███▋      | 13559/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.11.up_proj:  37%|███▋      | 13560/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.11.down_proj:  37%|███▋      | 13561/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.12.gate_proj:  37%|███▋      | 13562/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.12.up_proj:  37%|███▋      | 13563/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.12.down_proj:  37%|███▋      | 13564/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.13.gate_proj:  37%|███▋      | 13565/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.13.up_proj:  37%|███▋      | 13566/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.13.down_proj:  37%|███▋      | 13567/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.14.gate_proj:  37%|███▋      | 13568/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.14.up_proj:  37%|███▋      | 13569/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.14.down_proj:  37%|███▋      | 13570/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.15.gate_proj:  37%|███▋      | 13571/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.15.up_proj:  37%|███▋      | 13572/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.15.down_proj:  37%|███▋      | 13573/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.16.gate_proj:  37%|███▋      | 13574/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.16.up_proj:  37%|███▋      | 13575/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.16.down_proj:  37%|███▋      | 13576/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.17.gate_proj:  37%|███▋      | 13577/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.17.up_proj:  37%|███▋      | 13578/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.17.down_proj:  37%|███▋      | 13579/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.18.gate_proj:  37%|███▋      | 13580/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.18.up_proj:  37%|███▋      | 13581/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.18.down_proj:  37%|███▋      | 13582/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.19.gate_proj:  37%|███▋      | 13583/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.19.up_proj:  37%|███▋      | 13584/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.19.down_proj:  37%|███▋      | 13585/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.20.gate_proj:  37%|███▋      | 13586/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.20.up_proj:  37%|███▋      | 13587/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.20.down_proj:  37%|███▋      | 13588/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.21.gate_proj:  37%|███▋      | 13589/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.21.up_proj:  37%|███▋      | 13590/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.21.down_proj:  37%|███▋      | 13591/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.22.gate_proj:  37%|███▋      | 13592/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.22.up_proj:  37%|███▋      | 13593/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.22.down_proj:  37%|███▋      | 13594/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.23.gate_proj:  37%|███▋      | 13595/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.23.up_proj:  37%|███▋      | 13596/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.23.down_proj:  37%|███▋      | 13597/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.24.gate_proj:  37%|███▋      | 13598/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.24.up_proj:  37%|███▋      | 13599/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.24.down_proj:  37%|███▋      | 13600/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.25.gate_proj:  37%|███▋      | 13601/36566 [00:12<00:19, 1154.53it/s]
packing model.layers.34.mlp.experts.25.up_proj:  37%|███▋      | 13602/36566 [00:12<00:19, 1154.53it/s]  
packing model.layers.34.mlp.experts.25.up_proj:  37%|███▋      | 13603/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.25.down_proj:  37%|███▋      | 13603/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.26.gate_proj:  37%|███▋      | 13604/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.26.up_proj:  37%|███▋      | 13605/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.26.down_proj:  37%|███▋      | 13606/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.27.gate_proj:  37%|███▋      | 13607/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.27.up_proj:  37%|███▋      | 13608/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.27.down_proj:  37%|███▋      | 13609/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.28.gate_proj:  37%|███▋      | 13610/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.28.up_proj:  37%|███▋      | 13611/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.28.down_proj:  37%|███▋      | 13612/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.29.gate_proj:  37%|███▋      | 13613/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.29.up_proj:  37%|███▋      | 13614/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.29.down_proj:  37%|███▋      | 13615/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.30.gate_proj:  37%|███▋      | 13616/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.30.up_proj:  37%|███▋      | 13617/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.30.down_proj:  37%|███▋      | 13618/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.31.gate_proj:  37%|███▋      | 13619/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.31.up_proj:  37%|███▋      | 13620/36566 [00:12<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.31.down_proj:  37%|███▋      | 13621/36566 [00:12<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.32.gate_proj:  37%|███▋      | 13622/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.32.up_proj:  37%|███▋      | 13623/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.32.down_proj:  37%|███▋      | 13624/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.33.gate_proj:  37%|███▋      | 13625/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.33.up_proj:  37%|███▋      | 13626/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.33.down_proj:  37%|███▋      | 13627/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.34.gate_proj:  37%|███▋      | 13628/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.34.up_proj:  37%|███▋      | 13629/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.34.down_proj:  37%|███▋      | 13630/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.35.gate_proj:  37%|███▋      | 13631/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.35.up_proj:  37%|███▋      | 13632/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.35.down_proj:  37%|███▋      | 13633/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.36.gate_proj:  37%|███▋      | 13634/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.36.up_proj:  37%|███▋      | 13635/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.36.down_proj:  37%|███▋      | 13636/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.37.gate_proj:  37%|███▋      | 13637/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.37.up_proj:  37%|███▋      | 13638/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.37.down_proj:  37%|███▋      | 13639/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.38.gate_proj:  37%|███▋      | 13640/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.38.up_proj:  37%|███▋      | 13641/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.38.down_proj:  37%|███▋      | 13642/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.39.gate_proj:  37%|███▋      | 13643/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.39.up_proj:  37%|███▋      | 13644/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.39.down_proj:  37%|███▋      | 13645/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.40.gate_proj:  37%|███▋      | 13646/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.40.up_proj:  37%|███▋      | 13647/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.40.down_proj:  37%|███▋      | 13648/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.41.gate_proj:  37%|███▋      | 13649/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.41.up_proj:  37%|███▋      | 13650/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.41.down_proj:  37%|███▋      | 13651/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.42.gate_proj:  37%|███▋      | 13652/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.42.up_proj:  37%|███▋      | 13653/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.42.down_proj:  37%|███▋      | 13654/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.43.gate_proj:  37%|███▋      | 13655/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.43.up_proj:  37%|███▋      | 13656/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.43.down_proj:  37%|███▋      | 13657/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.44.gate_proj:  37%|███▋      | 13658/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.44.up_proj:  37%|███▋      | 13659/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.44.down_proj:  37%|███▋      | 13660/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.45.gate_proj:  37%|███▋      | 13661/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.45.up_proj:  37%|███▋      | 13662/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.45.down_proj:  37%|███▋      | 13663/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.46.gate_proj:  37%|███▋      | 13664/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.46.up_proj:  37%|███▋      | 13665/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.46.down_proj:  37%|███▋      | 13666/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.47.gate_proj:  37%|███▋      | 13667/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.47.up_proj:  37%|███▋      | 13668/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.47.down_proj:  37%|███▋      | 13669/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.48.gate_proj:  37%|███▋      | 13670/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.48.up_proj:  37%|███▋      | 13671/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.48.down_proj:  37%|███▋      | 13672/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.49.gate_proj:  37%|███▋      | 13673/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.49.up_proj:  37%|███▋      | 13674/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.49.down_proj:  37%|███▋      | 13675/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.50.gate_proj:  37%|███▋      | 13676/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.50.up_proj:  37%|███▋      | 13677/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.50.down_proj:  37%|███▋      | 13678/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.51.gate_proj:  37%|███▋      | 13679/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.51.up_proj:  37%|███▋      | 13680/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.51.down_proj:  37%|███▋      | 13681/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.52.gate_proj:  37%|███▋      | 13682/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.52.up_proj:  37%|███▋      | 13683/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.52.down_proj:  37%|███▋      | 13684/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.53.gate_proj:  37%|███▋      | 13685/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.53.up_proj:  37%|███▋      | 13686/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.53.down_proj:  37%|███▋      | 13687/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.54.gate_proj:  37%|███▋      | 13688/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.54.up_proj:  37%|███▋      | 13689/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.54.down_proj:  37%|███▋      | 13690/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.55.gate_proj:  37%|███▋      | 13691/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.55.up_proj:  37%|███▋      | 13692/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.55.down_proj:  37%|███▋      | 13693/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.56.gate_proj:  37%|███▋      | 13694/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.56.up_proj:  37%|███▋      | 13695/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.56.down_proj:  37%|███▋      | 13696/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.57.gate_proj:  37%|███▋      | 13697/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.57.up_proj:  37%|███▋      | 13698/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.57.down_proj:  37%|███▋      | 13699/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.58.gate_proj:  37%|███▋      | 13700/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.58.up_proj:  37%|███▋      | 13701/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.58.down_proj:  37%|███▋      | 13702/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.59.gate_proj:  37%|███▋      | 13703/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.59.up_proj:  37%|███▋      | 13704/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.59.down_proj:  37%|███▋      | 13705/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.60.gate_proj:  37%|███▋      | 13706/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.60.up_proj:  37%|███▋      | 13707/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.60.down_proj:  37%|███▋      | 13708/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.61.gate_proj:  37%|███▋      | 13709/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.61.up_proj:  37%|███▋      | 13710/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.61.down_proj:  37%|███▋      | 13711/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.62.gate_proj:  37%|███▋      | 13712/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.62.up_proj:  38%|███▊      | 13713/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.62.down_proj:  38%|███▊      | 13714/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.63.gate_proj:  38%|███▊      | 13715/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.63.up_proj:  38%|███▊      | 13716/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.63.down_proj:  38%|███▊      | 13717/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.64.gate_proj:  38%|███▊      | 13718/36566 [00:13<00:19, 1153.87it/s]
packing model.layers.34.mlp.experts.64.up_proj:  38%|███▊      | 13719/36566 [00:13<00:19, 1153.87it/s]  
packing model.layers.34.mlp.experts.64.up_proj:  38%|███▊      | 13720/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.64.down_proj:  38%|███▊      | 13720/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.65.gate_proj:  38%|███▊      | 13721/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.65.up_proj:  38%|███▊      | 13722/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.65.down_proj:  38%|███▊      | 13723/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.66.gate_proj:  38%|███▊      | 13724/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.66.up_proj:  38%|███▊      | 13725/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.66.down_proj:  38%|███▊      | 13726/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.67.gate_proj:  38%|███▊      | 13727/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.67.up_proj:  38%|███▊      | 13728/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.67.down_proj:  38%|███▊      | 13729/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.68.gate_proj:  38%|███▊      | 13730/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.68.up_proj:  38%|███▊      | 13731/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.68.down_proj:  38%|███▊      | 13732/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.69.gate_proj:  38%|███▊      | 13733/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.69.up_proj:  38%|███▊      | 13734/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.69.down_proj:  38%|███▊      | 13735/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.70.gate_proj:  38%|███▊      | 13736/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.70.up_proj:  38%|███▊      | 13737/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.70.down_proj:  38%|███▊      | 13738/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.71.gate_proj:  38%|███▊      | 13739/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.71.up_proj:  38%|███▊      | 13740/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.71.down_proj:  38%|███▊      | 13741/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.72.gate_proj:  38%|███▊      | 13742/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.72.up_proj:  38%|███▊      | 13743/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.72.down_proj:  38%|███▊      | 13744/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.73.gate_proj:  38%|███▊      | 13745/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.73.up_proj:  38%|███▊      | 13746/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.73.down_proj:  38%|███▊      | 13747/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.74.gate_proj:  38%|███▊      | 13748/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.74.up_proj:  38%|███▊      | 13749/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.74.down_proj:  38%|███▊      | 13750/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.75.gate_proj:  38%|███▊      | 13751/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.75.up_proj:  38%|███▊      | 13752/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.75.down_proj:  38%|███▊      | 13753/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.76.gate_proj:  38%|███▊      | 13754/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.76.up_proj:  38%|███▊      | 13755/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.76.down_proj:  38%|███▊      | 13756/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.77.gate_proj:  38%|███▊      | 13757/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.77.up_proj:  38%|███▊      | 13758/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.77.down_proj:  38%|███▊      | 13759/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.78.gate_proj:  38%|███▊      | 13760/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.78.up_proj:  38%|███▊      | 13761/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.78.down_proj:  38%|███▊      | 13762/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.79.gate_proj:  38%|███▊      | 13763/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.79.up_proj:  38%|███▊      | 13764/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.79.down_proj:  38%|███▊      | 13765/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.80.gate_proj:  38%|███▊      | 13766/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.80.up_proj:  38%|███▊      | 13767/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.80.down_proj:  38%|███▊      | 13768/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.81.gate_proj:  38%|███▊      | 13769/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.81.up_proj:  38%|███▊      | 13770/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.81.down_proj:  38%|███▊      | 13771/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.82.gate_proj:  38%|███▊      | 13772/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.82.up_proj:  38%|███▊      | 13773/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.82.down_proj:  38%|███▊      | 13774/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.83.gate_proj:  38%|███▊      | 13775/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.83.up_proj:  38%|███▊      | 13776/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.83.down_proj:  38%|███▊      | 13777/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.84.gate_proj:  38%|███▊      | 13778/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.84.up_proj:  38%|███▊      | 13779/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.84.down_proj:  38%|███▊      | 13780/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.85.gate_proj:  38%|███▊      | 13781/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.85.up_proj:  38%|███▊      | 13782/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.85.down_proj:  38%|███▊      | 13783/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.86.gate_proj:  38%|███▊      | 13784/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.86.up_proj:  38%|███▊      | 13785/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.86.down_proj:  38%|███▊      | 13786/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.87.gate_proj:  38%|███▊      | 13787/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.87.up_proj:  38%|███▊      | 13788/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.87.down_proj:  38%|███▊      | 13789/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.88.gate_proj:  38%|███▊      | 13790/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.88.up_proj:  38%|███▊      | 13791/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.88.down_proj:  38%|███▊      | 13792/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.89.gate_proj:  38%|███▊      | 13793/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.89.up_proj:  38%|███▊      | 13794/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.89.down_proj:  38%|███▊      | 13795/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.90.gate_proj:  38%|███▊      | 13796/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.90.up_proj:  38%|███▊      | 13797/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.90.down_proj:  38%|███▊      | 13798/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.91.gate_proj:  38%|███▊      | 13799/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.91.up_proj:  38%|███▊      | 13800/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.91.down_proj:  38%|███▊      | 13801/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.92.gate_proj:  38%|███▊      | 13802/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.92.up_proj:  38%|███▊      | 13803/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.92.down_proj:  38%|███▊      | 13804/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.93.gate_proj:  38%|███▊      | 13805/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.93.up_proj:  38%|███▊      | 13806/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.93.down_proj:  38%|███▊      | 13807/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.94.gate_proj:  38%|███▊      | 13808/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.94.up_proj:  38%|███▊      | 13809/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.94.down_proj:  38%|███▊      | 13810/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.95.gate_proj:  38%|███▊      | 13811/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.95.up_proj:  38%|███▊      | 13812/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.95.down_proj:  38%|███▊      | 13813/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.96.gate_proj:  38%|███▊      | 13814/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.96.up_proj:  38%|███▊      | 13815/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.96.down_proj:  38%|███▊      | 13816/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.97.gate_proj:  38%|███▊      | 13817/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.97.up_proj:  38%|███▊      | 13818/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.97.down_proj:  38%|███▊      | 13819/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.98.gate_proj:  38%|███▊      | 13820/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.98.up_proj:  38%|███▊      | 13821/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.98.down_proj:  38%|███▊      | 13822/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.99.gate_proj:  38%|███▊      | 13823/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.99.up_proj:  38%|███▊      | 13824/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.99.down_proj:  38%|███▊      | 13825/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.100.gate_proj:  38%|███▊      | 13826/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.100.up_proj:  38%|███▊      | 13827/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.100.down_proj:  38%|███▊      | 13828/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.101.gate_proj:  38%|███▊      | 13829/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.101.up_proj:  38%|███▊      | 13830/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.101.down_proj:  38%|███▊      | 13831/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.102.gate_proj:  38%|███▊      | 13832/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.102.up_proj:  38%|███▊      | 13833/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.102.down_proj:  38%|███▊      | 13834/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.103.gate_proj:  38%|███▊      | 13835/36566 [00:13<00:19, 1156.38it/s]
packing model.layers.34.mlp.experts.103.up_proj:  38%|███▊      | 13836/36566 [00:13<00:19, 1156.38it/s]  
packing model.layers.34.mlp.experts.103.up_proj:  38%|███▊      | 13837/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.103.down_proj:  38%|███▊      | 13837/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.104.gate_proj:  38%|███▊      | 13838/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.104.up_proj:  38%|███▊      | 13839/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.104.down_proj:  38%|███▊      | 13840/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.105.gate_proj:  38%|███▊      | 13841/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.105.up_proj:  38%|███▊      | 13842/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.105.down_proj:  38%|███▊      | 13843/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.106.gate_proj:  38%|███▊      | 13844/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.106.up_proj:  38%|███▊      | 13845/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.106.down_proj:  38%|███▊      | 13846/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.107.gate_proj:  38%|███▊      | 13847/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.107.up_proj:  38%|███▊      | 13848/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.107.down_proj:  38%|███▊      | 13849/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.108.gate_proj:  38%|███▊      | 13850/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.108.up_proj:  38%|███▊      | 13851/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.108.down_proj:  38%|███▊      | 13852/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.109.gate_proj:  38%|███▊      | 13853/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.109.up_proj:  38%|███▊      | 13854/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.109.down_proj:  38%|███▊      | 13855/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.110.gate_proj:  38%|███▊      | 13856/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.110.up_proj:  38%|███▊      | 13857/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.110.down_proj:  38%|███▊      | 13858/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.111.gate_proj:  38%|███▊      | 13859/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.111.up_proj:  38%|███▊      | 13860/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.111.down_proj:  38%|███▊      | 13861/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.112.gate_proj:  38%|███▊      | 13862/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.112.up_proj:  38%|███▊      | 13863/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.112.down_proj:  38%|███▊      | 13864/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.113.gate_proj:  38%|███▊      | 13865/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.113.up_proj:  38%|███▊      | 13866/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.113.down_proj:  38%|███▊      | 13867/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.114.gate_proj:  38%|███▊      | 13868/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.114.up_proj:  38%|███▊      | 13869/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.114.down_proj:  38%|███▊      | 13870/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.115.gate_proj:  38%|███▊      | 13871/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.115.up_proj:  38%|███▊      | 13872/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.115.down_proj:  38%|███▊      | 13873/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.116.gate_proj:  38%|███▊      | 13874/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.116.up_proj:  38%|███▊      | 13875/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.116.down_proj:  38%|███▊      | 13876/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.117.gate_proj:  38%|███▊      | 13877/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.117.up_proj:  38%|███▊      | 13878/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.117.down_proj:  38%|███▊      | 13879/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.118.gate_proj:  38%|███▊      | 13880/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.118.up_proj:  38%|███▊      | 13881/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.118.down_proj:  38%|███▊      | 13882/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.119.gate_proj:  38%|███▊      | 13883/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.119.up_proj:  38%|███▊      | 13884/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.119.down_proj:  38%|███▊      | 13885/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.120.gate_proj:  38%|███▊      | 13886/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.120.up_proj:  38%|███▊      | 13887/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.120.down_proj:  38%|███▊      | 13888/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.121.gate_proj:  38%|███▊      | 13889/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.121.up_proj:  38%|███▊      | 13890/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.121.down_proj:  38%|███▊      | 13891/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.122.gate_proj:  38%|███▊      | 13892/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.122.up_proj:  38%|███▊      | 13893/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.122.down_proj:  38%|███▊      | 13894/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.123.gate_proj:  38%|███▊      | 13895/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.123.up_proj:  38%|███▊      | 13896/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.123.down_proj:  38%|███▊      | 13897/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.124.gate_proj:  38%|███▊      | 13898/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.124.up_proj:  38%|███▊      | 13899/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.124.down_proj:  38%|███▊      | 13900/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.125.gate_proj:  38%|███▊      | 13901/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.125.up_proj:  38%|███▊      | 13902/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.125.down_proj:  38%|███▊      | 13903/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.126.gate_proj:  38%|███▊      | 13904/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.126.up_proj:  38%|███▊      | 13905/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.126.down_proj:  38%|███▊      | 13906/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.127.gate_proj:  38%|███▊      | 13907/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.34.mlp.experts.127.up_proj:  38%|███▊      | 13908/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.34.mlp.experts.127.down_proj:  38%|███▊      | 13909/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.0.gate_proj:  38%|███▊      | 13910/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.0.up_proj:  38%|███▊      | 13911/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.0.down_proj:  38%|███▊      | 13912/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.1.gate_proj:  38%|███▊      | 13913/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.1.up_proj:  38%|███▊      | 13914/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.1.down_proj:  38%|███▊      | 13915/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.2.gate_proj:  38%|███▊      | 13916/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.2.up_proj:  38%|███▊      | 13917/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.2.down_proj:  38%|███▊      | 13918/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.3.gate_proj:  38%|███▊      | 13919/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.3.up_proj:  38%|███▊      | 13920/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.3.down_proj:  38%|███▊      | 13921/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.4.gate_proj:  38%|███▊      | 13922/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.4.up_proj:  38%|███▊      | 13923/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.4.down_proj:  38%|███▊      | 13924/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.5.gate_proj:  38%|███▊      | 13925/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.5.up_proj:  38%|███▊      | 13926/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.5.down_proj:  38%|███▊      | 13927/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.6.gate_proj:  38%|███▊      | 13928/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.6.up_proj:  38%|███▊      | 13929/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.6.down_proj:  38%|███▊      | 13930/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.7.gate_proj:  38%|███▊      | 13931/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.7.up_proj:  38%|███▊      | 13932/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.7.down_proj:  38%|███▊      | 13933/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.8.gate_proj:  38%|███▊      | 13934/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.8.up_proj:  38%|███▊      | 13935/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.8.down_proj:  38%|███▊      | 13936/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.9.gate_proj:  38%|███▊      | 13937/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.9.up_proj:  38%|███▊      | 13938/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.9.down_proj:  38%|███▊      | 13939/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.10.gate_proj:  38%|███▊      | 13940/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.10.up_proj:  38%|███▊      | 13941/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.10.down_proj:  38%|███▊      | 13942/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.11.gate_proj:  38%|███▊      | 13943/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.11.up_proj:  38%|███▊      | 13944/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.11.down_proj:  38%|███▊      | 13945/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.12.gate_proj:  38%|███▊      | 13946/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.12.up_proj:  38%|███▊      | 13947/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.12.down_proj:  38%|███▊      | 13948/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.13.gate_proj:  38%|███▊      | 13949/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.13.up_proj:  38%|███▊      | 13950/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.13.down_proj:  38%|███▊      | 13951/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.14.gate_proj:  38%|███▊      | 13952/36566 [00:13<00:19, 1158.24it/s]
packing model.layers.35.mlp.experts.14.up_proj:  38%|███▊      | 13953/36566 [00:13<00:19, 1158.24it/s]  
packing model.layers.35.mlp.experts.14.up_proj:  38%|███▊      | 13954/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.14.down_proj:  38%|███▊      | 13954/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.15.gate_proj:  38%|███▊      | 13955/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.15.up_proj:  38%|███▊      | 13956/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.15.down_proj:  38%|███▊      | 13957/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.16.gate_proj:  38%|███▊      | 13958/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.16.up_proj:  38%|███▊      | 13959/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.16.down_proj:  38%|███▊      | 13960/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.17.gate_proj:  38%|███▊      | 13961/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.17.up_proj:  38%|███▊      | 13962/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.17.down_proj:  38%|███▊      | 13963/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.18.gate_proj:  38%|███▊      | 13964/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.18.up_proj:  38%|███▊      | 13965/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.18.down_proj:  38%|███▊      | 13966/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.19.gate_proj:  38%|███▊      | 13967/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.19.up_proj:  38%|███▊      | 13968/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.19.down_proj:  38%|███▊      | 13969/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.20.gate_proj:  38%|███▊      | 13970/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.20.up_proj:  38%|███▊      | 13971/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.20.down_proj:  38%|███▊      | 13972/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.21.gate_proj:  38%|███▊      | 13973/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.21.up_proj:  38%|███▊      | 13974/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.21.down_proj:  38%|███▊      | 13975/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.22.gate_proj:  38%|███▊      | 13976/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.22.up_proj:  38%|███▊      | 13977/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.22.down_proj:  38%|███▊      | 13978/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.23.gate_proj:  38%|███▊      | 13979/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.23.up_proj:  38%|███▊      | 13980/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.23.down_proj:  38%|███▊      | 13981/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.24.gate_proj:  38%|███▊      | 13982/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.24.up_proj:  38%|███▊      | 13983/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.24.down_proj:  38%|███▊      | 13984/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.25.gate_proj:  38%|███▊      | 13985/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.25.up_proj:  38%|███▊      | 13986/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.25.down_proj:  38%|███▊      | 13987/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.26.gate_proj:  38%|███▊      | 13988/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.26.up_proj:  38%|███▊      | 13989/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.26.down_proj:  38%|███▊      | 13990/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.27.gate_proj:  38%|███▊      | 13991/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.27.up_proj:  38%|███▊      | 13992/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.27.down_proj:  38%|███▊      | 13993/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.28.gate_proj:  38%|███▊      | 13994/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.28.up_proj:  38%|███▊      | 13995/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.28.down_proj:  38%|███▊      | 13996/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.29.gate_proj:  38%|███▊      | 13997/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.29.up_proj:  38%|███▊      | 13998/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.29.down_proj:  38%|███▊      | 13999/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.30.gate_proj:  38%|███▊      | 14000/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.30.up_proj:  38%|███▊      | 14001/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.30.down_proj:  38%|███▊      | 14002/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.31.gate_proj:  38%|███▊      | 14003/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.31.up_proj:  38%|███▊      | 14004/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.31.down_proj:  38%|███▊      | 14005/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.32.gate_proj:  38%|███▊      | 14006/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.32.up_proj:  38%|███▊      | 14007/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.32.down_proj:  38%|███▊      | 14008/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.33.gate_proj:  38%|███▊      | 14009/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.33.up_proj:  38%|███▊      | 14010/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.33.down_proj:  38%|███▊      | 14011/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.34.gate_proj:  38%|███▊      | 14012/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.34.up_proj:  38%|███▊      | 14013/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.34.down_proj:  38%|███▊      | 14014/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.35.gate_proj:  38%|███▊      | 14015/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.35.up_proj:  38%|███▊      | 14016/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.35.down_proj:  38%|███▊      | 14017/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.36.gate_proj:  38%|███▊      | 14018/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.36.up_proj:  38%|███▊      | 14019/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.36.down_proj:  38%|███▊      | 14020/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.37.gate_proj:  38%|███▊      | 14021/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.37.up_proj:  38%|███▊      | 14022/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.37.down_proj:  38%|███▊      | 14023/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.38.gate_proj:  38%|███▊      | 14024/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.38.up_proj:  38%|███▊      | 14025/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.38.down_proj:  38%|███▊      | 14026/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.39.gate_proj:  38%|███▊      | 14027/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.39.up_proj:  38%|███▊      | 14028/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.39.down_proj:  38%|███▊      | 14029/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.40.gate_proj:  38%|███▊      | 14030/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.40.up_proj:  38%|███▊      | 14031/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.40.down_proj:  38%|███▊      | 14032/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.41.gate_proj:  38%|███▊      | 14033/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.41.up_proj:  38%|███▊      | 14034/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.41.down_proj:  38%|███▊      | 14035/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.42.gate_proj:  38%|███▊      | 14036/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.42.up_proj:  38%|███▊      | 14037/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.42.down_proj:  38%|███▊      | 14038/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.43.gate_proj:  38%|███▊      | 14039/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.43.up_proj:  38%|███▊      | 14040/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.43.down_proj:  38%|███▊      | 14041/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.44.gate_proj:  38%|███▊      | 14042/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.44.up_proj:  38%|███▊      | 14043/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.44.down_proj:  38%|███▊      | 14044/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.45.gate_proj:  38%|███▊      | 14045/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.45.up_proj:  38%|███▊      | 14046/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.45.down_proj:  38%|███▊      | 14047/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.46.gate_proj:  38%|███▊      | 14048/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.46.up_proj:  38%|███▊      | 14049/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.46.down_proj:  38%|███▊      | 14050/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.47.gate_proj:  38%|███▊      | 14051/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.47.up_proj:  38%|███▊      | 14052/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.47.down_proj:  38%|███▊      | 14053/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.48.gate_proj:  38%|███▊      | 14054/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.48.up_proj:  38%|███▊      | 14055/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.48.down_proj:  38%|███▊      | 14056/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.49.gate_proj:  38%|███▊      | 14057/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.49.up_proj:  38%|███▊      | 14058/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.49.down_proj:  38%|███▊      | 14059/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.50.gate_proj:  38%|███▊      | 14060/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.50.up_proj:  38%|███▊      | 14061/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.50.down_proj:  38%|███▊      | 14062/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.51.gate_proj:  38%|███▊      | 14063/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.51.up_proj:  38%|███▊      | 14064/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.51.down_proj:  38%|███▊      | 14065/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.52.gate_proj:  38%|███▊      | 14066/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.52.up_proj:  38%|███▊      | 14067/36566 [00:13<00:19, 1158.95it/s]  
packing model.layers.35.mlp.experts.52.down_proj:  38%|███▊      | 14068/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.53.gate_proj:  38%|███▊      | 14069/36566 [00:13<00:19, 1158.95it/s]
packing model.layers.35.mlp.experts.53.gate_proj:  38%|███▊      | 14070/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.53.up_proj:  38%|███▊      | 14070/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.53.down_proj:  38%|███▊      | 14071/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.54.gate_proj:  38%|███▊      | 14072/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.54.up_proj:  38%|███▊      | 14073/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.54.down_proj:  38%|███▊      | 14074/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.55.gate_proj:  38%|███▊      | 14075/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.55.up_proj:  38%|███▊      | 14076/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.55.down_proj:  38%|███▊      | 14077/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.56.gate_proj:  39%|███▊      | 14078/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.56.up_proj:  39%|███▊      | 14079/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.56.down_proj:  39%|███▊      | 14080/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.57.gate_proj:  39%|███▊      | 14081/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.57.up_proj:  39%|███▊      | 14082/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.57.down_proj:  39%|███▊      | 14083/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.58.gate_proj:  39%|███▊      | 14084/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.58.up_proj:  39%|███▊      | 14085/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.58.down_proj:  39%|███▊      | 14086/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.59.gate_proj:  39%|███▊      | 14087/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.59.up_proj:  39%|███▊      | 14088/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.59.down_proj:  39%|███▊      | 14089/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.60.gate_proj:  39%|███▊      | 14090/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.60.up_proj:  39%|███▊      | 14091/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.60.down_proj:  39%|███▊      | 14092/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.61.gate_proj:  39%|███▊      | 14093/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.61.up_proj:  39%|███▊      | 14094/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.61.down_proj:  39%|███▊      | 14095/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.62.gate_proj:  39%|███▊      | 14096/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.62.up_proj:  39%|███▊      | 14097/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.62.down_proj:  39%|███▊      | 14098/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.63.gate_proj:  39%|███▊      | 14099/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.63.up_proj:  39%|███▊      | 14100/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.63.down_proj:  39%|███▊      | 14101/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.64.gate_proj:  39%|███▊      | 14102/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.64.up_proj:  39%|███▊      | 14103/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.64.down_proj:  39%|███▊      | 14104/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.65.gate_proj:  39%|███▊      | 14105/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.65.up_proj:  39%|███▊      | 14106/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.65.down_proj:  39%|███▊      | 14107/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.66.gate_proj:  39%|███▊      | 14108/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.66.up_proj:  39%|███▊      | 14109/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.66.down_proj:  39%|███▊      | 14110/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.67.gate_proj:  39%|███▊      | 14111/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.67.up_proj:  39%|███▊      | 14112/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.67.down_proj:  39%|███▊      | 14113/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.68.gate_proj:  39%|███▊      | 14114/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.68.up_proj:  39%|███▊      | 14115/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.68.down_proj:  39%|███▊      | 14116/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.69.gate_proj:  39%|███▊      | 14117/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.69.up_proj:  39%|███▊      | 14118/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.69.down_proj:  39%|███▊      | 14119/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.70.gate_proj:  39%|███▊      | 14120/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.70.up_proj:  39%|███▊      | 14121/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.70.down_proj:  39%|███▊      | 14122/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.71.gate_proj:  39%|███▊      | 14123/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.71.up_proj:  39%|███▊      | 14124/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.71.down_proj:  39%|███▊      | 14125/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.72.gate_proj:  39%|███▊      | 14126/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.72.up_proj:  39%|███▊      | 14127/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.72.down_proj:  39%|███▊      | 14128/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.73.gate_proj:  39%|███▊      | 14129/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.73.up_proj:  39%|███▊      | 14130/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.73.down_proj:  39%|███▊      | 14131/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.74.gate_proj:  39%|███▊      | 14132/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.74.up_proj:  39%|███▊      | 14133/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.74.down_proj:  39%|███▊      | 14134/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.75.gate_proj:  39%|███▊      | 14135/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.75.up_proj:  39%|███▊      | 14136/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.75.down_proj:  39%|███▊      | 14137/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.76.gate_proj:  39%|███▊      | 14138/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.76.up_proj:  39%|███▊      | 14139/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.76.down_proj:  39%|███▊      | 14140/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.77.gate_proj:  39%|███▊      | 14141/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.77.up_proj:  39%|███▊      | 14142/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.77.down_proj:  39%|███▊      | 14143/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.78.gate_proj:  39%|███▊      | 14144/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.78.up_proj:  39%|███▊      | 14145/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.78.down_proj:  39%|███▊      | 14146/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.79.gate_proj:  39%|███▊      | 14147/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.79.up_proj:  39%|███▊      | 14148/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.79.down_proj:  39%|███▊      | 14149/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.80.gate_proj:  39%|███▊      | 14150/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.80.up_proj:  39%|███▊      | 14151/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.80.down_proj:  39%|███▊      | 14152/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.81.gate_proj:  39%|███▊      | 14153/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.81.up_proj:  39%|███▊      | 14154/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.81.down_proj:  39%|███▊      | 14155/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.82.gate_proj:  39%|███▊      | 14156/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.82.up_proj:  39%|███▊      | 14157/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.82.down_proj:  39%|███▊      | 14158/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.83.gate_proj:  39%|███▊      | 14159/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.83.up_proj:  39%|███▊      | 14160/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.83.down_proj:  39%|███▊      | 14161/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.84.gate_proj:  39%|███▊      | 14162/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.84.up_proj:  39%|███▊      | 14163/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.84.down_proj:  39%|███▊      | 14164/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.85.gate_proj:  39%|███▊      | 14165/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.85.up_proj:  39%|███▊      | 14166/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.85.down_proj:  39%|███▊      | 14167/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.86.gate_proj:  39%|███▊      | 14168/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.86.up_proj:  39%|███▊      | 14169/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.86.down_proj:  39%|███▉      | 14170/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.87.gate_proj:  39%|███▉      | 14171/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.87.up_proj:  39%|███▉      | 14172/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.87.down_proj:  39%|███▉      | 14173/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.88.gate_proj:  39%|███▉      | 14174/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.88.up_proj:  39%|███▉      | 14175/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.88.down_proj:  39%|███▉      | 14176/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.89.gate_proj:  39%|███▉      | 14177/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.89.up_proj:  39%|███▉      | 14178/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.89.down_proj:  39%|███▉      | 14179/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.90.gate_proj:  39%|███▉      | 14180/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.90.up_proj:  39%|███▉      | 14181/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.90.down_proj:  39%|███▉      | 14182/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.91.gate_proj:  39%|███▉      | 14183/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.91.up_proj:  39%|███▉      | 14184/36566 [00:13<00:19, 1157.95it/s]  
packing model.layers.35.mlp.experts.91.down_proj:  39%|███▉      | 14185/36566 [00:13<00:19, 1157.95it/s]
packing model.layers.35.mlp.experts.91.down_proj:  39%|███▉      | 14186/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.92.gate_proj:  39%|███▉      | 14186/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.92.up_proj:  39%|███▉      | 14187/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.92.down_proj:  39%|███▉      | 14188/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.93.gate_proj:  39%|███▉      | 14189/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.93.up_proj:  39%|███▉      | 14190/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.93.down_proj:  39%|███▉      | 14191/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.94.gate_proj:  39%|███▉      | 14192/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.94.up_proj:  39%|███▉      | 14193/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.94.down_proj:  39%|███▉      | 14194/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.95.gate_proj:  39%|███▉      | 14195/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.95.up_proj:  39%|███▉      | 14196/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.95.down_proj:  39%|███▉      | 14197/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.96.gate_proj:  39%|███▉      | 14198/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.96.up_proj:  39%|███▉      | 14199/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.96.down_proj:  39%|███▉      | 14200/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.97.gate_proj:  39%|███▉      | 14201/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.97.up_proj:  39%|███▉      | 14202/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.97.down_proj:  39%|███▉      | 14203/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.98.gate_proj:  39%|███▉      | 14204/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.98.up_proj:  39%|███▉      | 14205/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.98.down_proj:  39%|███▉      | 14206/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.99.gate_proj:  39%|███▉      | 14207/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.99.up_proj:  39%|███▉      | 14208/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.99.down_proj:  39%|███▉      | 14209/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.100.gate_proj:  39%|███▉      | 14210/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.100.up_proj:  39%|███▉      | 14211/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.100.down_proj:  39%|███▉      | 14212/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.101.gate_proj:  39%|███▉      | 14213/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.101.up_proj:  39%|███▉      | 14214/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.101.down_proj:  39%|███▉      | 14215/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.102.gate_proj:  39%|███▉      | 14216/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.102.up_proj:  39%|███▉      | 14217/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.102.down_proj:  39%|███▉      | 14218/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.103.gate_proj:  39%|███▉      | 14219/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.103.up_proj:  39%|███▉      | 14220/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.103.down_proj:  39%|███▉      | 14221/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.104.gate_proj:  39%|███▉      | 14222/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.104.up_proj:  39%|███▉      | 14223/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.104.down_proj:  39%|███▉      | 14224/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.105.gate_proj:  39%|███▉      | 14225/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.105.up_proj:  39%|███▉      | 14226/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.105.down_proj:  39%|███▉      | 14227/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.106.gate_proj:  39%|███▉      | 14228/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.106.up_proj:  39%|███▉      | 14229/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.106.down_proj:  39%|███▉      | 14230/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.107.gate_proj:  39%|███▉      | 14231/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.107.up_proj:  39%|███▉      | 14232/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.107.down_proj:  39%|███▉      | 14233/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.108.gate_proj:  39%|███▉      | 14234/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.108.up_proj:  39%|███▉      | 14235/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.108.down_proj:  39%|███▉      | 14236/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.109.gate_proj:  39%|███▉      | 14237/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.109.up_proj:  39%|███▉      | 14238/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.109.down_proj:  39%|███▉      | 14239/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.110.gate_proj:  39%|███▉      | 14240/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.110.up_proj:  39%|███▉      | 14241/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.110.down_proj:  39%|███▉      | 14242/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.111.gate_proj:  39%|███▉      | 14243/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.111.up_proj:  39%|███▉      | 14244/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.111.down_proj:  39%|███▉      | 14245/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.112.gate_proj:  39%|███▉      | 14246/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.112.up_proj:  39%|███▉      | 14247/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.112.down_proj:  39%|███▉      | 14248/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.113.gate_proj:  39%|███▉      | 14249/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.113.up_proj:  39%|███▉      | 14250/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.113.down_proj:  39%|███▉      | 14251/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.114.gate_proj:  39%|███▉      | 14252/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.114.up_proj:  39%|███▉      | 14253/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.114.down_proj:  39%|███▉      | 14254/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.115.gate_proj:  39%|███▉      | 14255/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.115.up_proj:  39%|███▉      | 14256/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.115.down_proj:  39%|███▉      | 14257/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.116.gate_proj:  39%|███▉      | 14258/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.116.up_proj:  39%|███▉      | 14259/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.116.down_proj:  39%|███▉      | 14260/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.117.gate_proj:  39%|███▉      | 14261/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.117.up_proj:  39%|███▉      | 14262/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.117.down_proj:  39%|███▉      | 14263/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.118.gate_proj:  39%|███▉      | 14264/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.118.up_proj:  39%|███▉      | 14265/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.118.down_proj:  39%|███▉      | 14266/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.119.gate_proj:  39%|███▉      | 14267/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.119.up_proj:  39%|███▉      | 14268/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.119.down_proj:  39%|███▉      | 14269/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.120.gate_proj:  39%|███▉      | 14270/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.120.up_proj:  39%|███▉      | 14271/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.120.down_proj:  39%|███▉      | 14272/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.121.gate_proj:  39%|███▉      | 14273/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.121.up_proj:  39%|███▉      | 14274/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.121.down_proj:  39%|███▉      | 14275/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.122.gate_proj:  39%|███▉      | 14276/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.122.up_proj:  39%|███▉      | 14277/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.122.down_proj:  39%|███▉      | 14278/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.123.gate_proj:  39%|███▉      | 14279/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.123.up_proj:  39%|███▉      | 14280/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.123.down_proj:  39%|███▉      | 14281/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.124.gate_proj:  39%|███▉      | 14282/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.124.up_proj:  39%|███▉      | 14283/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.124.down_proj:  39%|███▉      | 14284/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.125.gate_proj:  39%|███▉      | 14285/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.125.up_proj:  39%|███▉      | 14286/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.125.down_proj:  39%|███▉      | 14287/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.126.gate_proj:  39%|███▉      | 14288/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.126.up_proj:  39%|███▉      | 14289/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.126.down_proj:  39%|███▉      | 14290/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.127.gate_proj:  39%|███▉      | 14291/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.35.mlp.experts.127.up_proj:  39%|███▉      | 14292/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.35.mlp.experts.127.down_proj:  39%|███▉      | 14293/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.36.mlp.experts.0.gate_proj:  39%|███▉      | 14294/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.36.mlp.experts.0.up_proj:  39%|███▉      | 14295/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.36.mlp.experts.0.down_proj:  39%|███▉      | 14296/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.36.mlp.experts.1.gate_proj:  39%|███▉      | 14297/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.36.mlp.experts.1.up_proj:  39%|███▉      | 14298/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.36.mlp.experts.1.down_proj:  39%|███▉      | 14299/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.36.mlp.experts.2.gate_proj:  39%|███▉      | 14300/36566 [00:13<00:19, 1158.30it/s]
packing model.layers.36.mlp.experts.2.up_proj:  39%|███▉      | 14301/36566 [00:13<00:19, 1158.30it/s]  
packing model.layers.36.mlp.experts.2.up_proj:  39%|███▉      | 14302/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.2.down_proj:  39%|███▉      | 14302/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.3.gate_proj:  39%|███▉      | 14303/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.3.up_proj:  39%|███▉      | 14304/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.3.down_proj:  39%|███▉      | 14305/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.4.gate_proj:  39%|███▉      | 14306/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.4.up_proj:  39%|███▉      | 14307/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.4.down_proj:  39%|███▉      | 14308/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.5.gate_proj:  39%|███▉      | 14309/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.5.up_proj:  39%|███▉      | 14310/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.5.down_proj:  39%|███▉      | 14311/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.6.gate_proj:  39%|███▉      | 14312/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.6.up_proj:  39%|███▉      | 14313/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.6.down_proj:  39%|███▉      | 14314/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.7.gate_proj:  39%|███▉      | 14315/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.7.up_proj:  39%|███▉      | 14316/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.7.down_proj:  39%|███▉      | 14317/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.8.gate_proj:  39%|███▉      | 14318/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.8.up_proj:  39%|███▉      | 14319/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.8.down_proj:  39%|███▉      | 14320/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.9.gate_proj:  39%|███▉      | 14321/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.9.up_proj:  39%|███▉      | 14322/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.9.down_proj:  39%|███▉      | 14323/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.10.gate_proj:  39%|███▉      | 14324/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.10.up_proj:  39%|███▉      | 14325/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.10.down_proj:  39%|███▉      | 14326/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.11.gate_proj:  39%|███▉      | 14327/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.11.up_proj:  39%|███▉      | 14328/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.11.down_proj:  39%|███▉      | 14329/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.12.gate_proj:  39%|███▉      | 14330/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.12.up_proj:  39%|███▉      | 14331/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.12.down_proj:  39%|███▉      | 14332/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.13.gate_proj:  39%|███▉      | 14333/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.13.up_proj:  39%|███▉      | 14334/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.13.down_proj:  39%|███▉      | 14335/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.14.gate_proj:  39%|███▉      | 14336/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.14.up_proj:  39%|███▉      | 14337/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.14.down_proj:  39%|███▉      | 14338/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.15.gate_proj:  39%|███▉      | 14339/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.15.up_proj:  39%|███▉      | 14340/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.15.down_proj:  39%|███▉      | 14341/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.16.gate_proj:  39%|███▉      | 14342/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.16.up_proj:  39%|███▉      | 14343/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.16.down_proj:  39%|███▉      | 14344/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.17.gate_proj:  39%|███▉      | 14345/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.17.up_proj:  39%|███▉      | 14346/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.17.down_proj:  39%|███▉      | 14347/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.18.gate_proj:  39%|███▉      | 14348/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.18.up_proj:  39%|███▉      | 14349/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.18.down_proj:  39%|███▉      | 14350/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.19.gate_proj:  39%|███▉      | 14351/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.19.up_proj:  39%|███▉      | 14352/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.19.down_proj:  39%|███▉      | 14353/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.20.gate_proj:  39%|███▉      | 14354/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.20.up_proj:  39%|███▉      | 14355/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.20.down_proj:  39%|███▉      | 14356/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.21.gate_proj:  39%|███▉      | 14357/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.21.up_proj:  39%|███▉      | 14358/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.21.down_proj:  39%|███▉      | 14359/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.22.gate_proj:  39%|███▉      | 14360/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.22.up_proj:  39%|███▉      | 14361/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.22.down_proj:  39%|███▉      | 14362/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.23.gate_proj:  39%|███▉      | 14363/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.23.up_proj:  39%|███▉      | 14364/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.23.down_proj:  39%|███▉      | 14365/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.24.gate_proj:  39%|███▉      | 14366/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.24.up_proj:  39%|███▉      | 14367/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.24.down_proj:  39%|███▉      | 14368/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.25.gate_proj:  39%|███▉      | 14369/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.25.up_proj:  39%|███▉      | 14370/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.25.down_proj:  39%|███▉      | 14371/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.26.gate_proj:  39%|███▉      | 14372/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.26.up_proj:  39%|███▉      | 14373/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.26.down_proj:  39%|███▉      | 14374/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.27.gate_proj:  39%|███▉      | 14375/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.27.up_proj:  39%|███▉      | 14376/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.27.down_proj:  39%|███▉      | 14377/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.28.gate_proj:  39%|███▉      | 14378/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.28.up_proj:  39%|███▉      | 14379/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.28.down_proj:  39%|███▉      | 14380/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.29.gate_proj:  39%|███▉      | 14381/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.29.up_proj:  39%|███▉      | 14382/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.29.down_proj:  39%|███▉      | 14383/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.30.gate_proj:  39%|███▉      | 14384/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.30.up_proj:  39%|███▉      | 14385/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.30.down_proj:  39%|███▉      | 14386/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.31.gate_proj:  39%|███▉      | 14387/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.31.up_proj:  39%|███▉      | 14388/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.31.down_proj:  39%|███▉      | 14389/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.32.gate_proj:  39%|███▉      | 14390/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.32.up_proj:  39%|███▉      | 14391/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.32.down_proj:  39%|███▉      | 14392/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.33.gate_proj:  39%|███▉      | 14393/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.33.up_proj:  39%|███▉      | 14394/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.33.down_proj:  39%|███▉      | 14395/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.34.gate_proj:  39%|███▉      | 14396/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.34.up_proj:  39%|███▉      | 14397/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.34.down_proj:  39%|███▉      | 14398/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.35.gate_proj:  39%|███▉      | 14399/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.35.up_proj:  39%|███▉      | 14400/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.35.down_proj:  39%|███▉      | 14401/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.36.gate_proj:  39%|███▉      | 14402/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.36.up_proj:  39%|███▉      | 14403/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.36.down_proj:  39%|███▉      | 14404/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.37.gate_proj:  39%|███▉      | 14405/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.37.up_proj:  39%|███▉      | 14406/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.37.down_proj:  39%|███▉      | 14407/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.38.gate_proj:  39%|███▉      | 14408/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.38.up_proj:  39%|███▉      | 14409/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.38.down_proj:  39%|███▉      | 14410/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.39.gate_proj:  39%|███▉      | 14411/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.39.up_proj:  39%|███▉      | 14412/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.39.down_proj:  39%|███▉      | 14413/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.40.gate_proj:  39%|███▉      | 14414/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.40.up_proj:  39%|███▉      | 14415/36566 [00:13<00:19, 1157.56it/s]  
packing model.layers.36.mlp.experts.40.down_proj:  39%|███▉      | 14416/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.41.gate_proj:  39%|███▉      | 14417/36566 [00:13<00:19, 1157.56it/s]
packing model.layers.36.mlp.experts.41.gate_proj:  39%|███▉      | 14418/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.41.up_proj:  39%|███▉      | 14418/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.41.down_proj:  39%|███▉      | 14419/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.42.gate_proj:  39%|███▉      | 14420/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.42.up_proj:  39%|███▉      | 14421/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.42.down_proj:  39%|███▉      | 14422/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.43.gate_proj:  39%|███▉      | 14423/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.43.up_proj:  39%|███▉      | 14424/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.43.down_proj:  39%|███▉      | 14425/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.44.gate_proj:  39%|███▉      | 14426/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.44.up_proj:  39%|███▉      | 14427/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.44.down_proj:  39%|███▉      | 14428/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.45.gate_proj:  39%|███▉      | 14429/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.45.up_proj:  39%|███▉      | 14430/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.45.down_proj:  39%|███▉      | 14431/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.46.gate_proj:  39%|███▉      | 14432/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.46.up_proj:  39%|███▉      | 14433/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.46.down_proj:  39%|███▉      | 14434/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.47.gate_proj:  39%|███▉      | 14435/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.47.up_proj:  39%|███▉      | 14436/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.47.down_proj:  39%|███▉      | 14437/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.48.gate_proj:  39%|███▉      | 14438/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.48.up_proj:  39%|███▉      | 14439/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.48.down_proj:  39%|███▉      | 14440/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.49.gate_proj:  39%|███▉      | 14441/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.49.up_proj:  39%|███▉      | 14442/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.49.down_proj:  39%|███▉      | 14443/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.50.gate_proj:  40%|███▉      | 14444/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.50.up_proj:  40%|███▉      | 14445/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.50.down_proj:  40%|███▉      | 14446/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.51.gate_proj:  40%|███▉      | 14447/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.51.up_proj:  40%|███▉      | 14448/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.51.down_proj:  40%|███▉      | 14449/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.52.gate_proj:  40%|███▉      | 14450/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.52.up_proj:  40%|███▉      | 14451/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.52.down_proj:  40%|███▉      | 14452/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.53.gate_proj:  40%|███▉      | 14453/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.53.up_proj:  40%|███▉      | 14454/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.53.down_proj:  40%|███▉      | 14455/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.54.gate_proj:  40%|███▉      | 14456/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.54.up_proj:  40%|███▉      | 14457/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.54.down_proj:  40%|███▉      | 14458/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.55.gate_proj:  40%|███▉      | 14459/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.55.up_proj:  40%|███▉      | 14460/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.55.down_proj:  40%|███▉      | 14461/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.56.gate_proj:  40%|███▉      | 14462/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.56.up_proj:  40%|███▉      | 14463/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.56.down_proj:  40%|███▉      | 14464/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.57.gate_proj:  40%|███▉      | 14465/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.57.up_proj:  40%|███▉      | 14466/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.57.down_proj:  40%|███▉      | 14467/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.58.gate_proj:  40%|███▉      | 14468/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.58.up_proj:  40%|███▉      | 14469/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.58.down_proj:  40%|███▉      | 14470/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.59.gate_proj:  40%|███▉      | 14471/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.59.up_proj:  40%|███▉      | 14472/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.59.down_proj:  40%|███▉      | 14473/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.60.gate_proj:  40%|███▉      | 14474/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.60.up_proj:  40%|███▉      | 14475/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.60.down_proj:  40%|███▉      | 14476/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.61.gate_proj:  40%|███▉      | 14477/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.61.up_proj:  40%|███▉      | 14478/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.61.down_proj:  40%|███▉      | 14479/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.62.gate_proj:  40%|███▉      | 14480/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.62.up_proj:  40%|███▉      | 14481/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.62.down_proj:  40%|███▉      | 14482/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.63.gate_proj:  40%|███▉      | 14483/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.63.up_proj:  40%|███▉      | 14484/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.63.down_proj:  40%|███▉      | 14485/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.64.gate_proj:  40%|███▉      | 14486/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.64.up_proj:  40%|███▉      | 14487/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.64.down_proj:  40%|███▉      | 14488/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.65.gate_proj:  40%|███▉      | 14489/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.65.up_proj:  40%|███▉      | 14490/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.65.down_proj:  40%|███▉      | 14491/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.66.gate_proj:  40%|███▉      | 14492/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.66.up_proj:  40%|███▉      | 14493/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.66.down_proj:  40%|███▉      | 14494/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.67.gate_proj:  40%|███▉      | 14495/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.67.up_proj:  40%|███▉      | 14496/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.67.down_proj:  40%|███▉      | 14497/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.68.gate_proj:  40%|███▉      | 14498/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.68.up_proj:  40%|███▉      | 14499/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.68.down_proj:  40%|███▉      | 14500/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.69.gate_proj:  40%|███▉      | 14501/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.69.up_proj:  40%|███▉      | 14502/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.69.down_proj:  40%|███▉      | 14503/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.70.gate_proj:  40%|███▉      | 14504/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.70.up_proj:  40%|███▉      | 14505/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.70.down_proj:  40%|███▉      | 14506/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.71.gate_proj:  40%|███▉      | 14507/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.71.up_proj:  40%|███▉      | 14508/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.71.down_proj:  40%|███▉      | 14509/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.72.gate_proj:  40%|███▉      | 14510/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.72.up_proj:  40%|███▉      | 14511/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.72.down_proj:  40%|███▉      | 14512/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.73.gate_proj:  40%|███▉      | 14513/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.73.up_proj:  40%|███▉      | 14514/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.73.down_proj:  40%|███▉      | 14515/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.74.gate_proj:  40%|███▉      | 14516/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.74.up_proj:  40%|███▉      | 14517/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.74.down_proj:  40%|███▉      | 14518/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.75.gate_proj:  40%|███▉      | 14519/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.75.up_proj:  40%|███▉      | 14520/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.75.down_proj:  40%|███▉      | 14521/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.76.gate_proj:  40%|███▉      | 14522/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.76.up_proj:  40%|███▉      | 14523/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.76.down_proj:  40%|███▉      | 14524/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.77.gate_proj:  40%|███▉      | 14525/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.77.up_proj:  40%|███▉      | 14526/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.77.down_proj:  40%|███▉      | 14527/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.78.gate_proj:  40%|███▉      | 14528/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.78.up_proj:  40%|███▉      | 14529/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.78.down_proj:  40%|███▉      | 14530/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.79.gate_proj:  40%|███▉      | 14531/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.79.up_proj:  40%|███▉      | 14532/36566 [00:13<00:19, 1157.49it/s]  
packing model.layers.36.mlp.experts.79.down_proj:  40%|███▉      | 14533/36566 [00:13<00:19, 1157.49it/s]
packing model.layers.36.mlp.experts.79.down_proj:  40%|███▉      | 14534/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.80.gate_proj:  40%|███▉      | 14534/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.80.up_proj:  40%|███▉      | 14535/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.80.down_proj:  40%|███▉      | 14536/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.81.gate_proj:  40%|███▉      | 14537/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.81.up_proj:  40%|███▉      | 14538/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.81.down_proj:  40%|███▉      | 14539/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.82.gate_proj:  40%|███▉      | 14540/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.82.up_proj:  40%|███▉      | 14541/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.82.down_proj:  40%|███▉      | 14542/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.83.gate_proj:  40%|███▉      | 14543/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.83.up_proj:  40%|███▉      | 14544/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.83.down_proj:  40%|███▉      | 14545/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.84.gate_proj:  40%|███▉      | 14546/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.84.up_proj:  40%|███▉      | 14547/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.84.down_proj:  40%|███▉      | 14548/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.85.gate_proj:  40%|███▉      | 14549/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.85.up_proj:  40%|███▉      | 14550/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.85.down_proj:  40%|███▉      | 14551/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.86.gate_proj:  40%|███▉      | 14552/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.86.up_proj:  40%|███▉      | 14553/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.86.down_proj:  40%|███▉      | 14554/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.87.gate_proj:  40%|███▉      | 14555/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.87.up_proj:  40%|███▉      | 14556/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.87.down_proj:  40%|███▉      | 14557/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.88.gate_proj:  40%|███▉      | 14558/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.88.up_proj:  40%|███▉      | 14559/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.88.down_proj:  40%|███▉      | 14560/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.89.gate_proj:  40%|███▉      | 14561/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.89.up_proj:  40%|███▉      | 14562/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.89.down_proj:  40%|███▉      | 14563/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.90.gate_proj:  40%|███▉      | 14564/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.90.up_proj:  40%|███▉      | 14565/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.90.down_proj:  40%|███▉      | 14566/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.91.gate_proj:  40%|███▉      | 14567/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.91.up_proj:  40%|███▉      | 14568/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.91.down_proj:  40%|███▉      | 14569/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.92.gate_proj:  40%|███▉      | 14570/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.92.up_proj:  40%|███▉      | 14571/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.92.down_proj:  40%|███▉      | 14572/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.93.gate_proj:  40%|███▉      | 14573/36566 [00:13<00:19, 1157.47it/s]
packing model.layers.36.mlp.experts.93.up_proj:  40%|███▉      | 14574/36566 [00:13<00:19, 1157.47it/s]  
packing model.layers.36.mlp.experts.93.down_proj:  40%|███▉      | 14575/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.94.gate_proj:  40%|███▉      | 14576/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.94.up_proj:  40%|███▉      | 14577/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.94.down_proj:  40%|███▉      | 14578/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.95.gate_proj:  40%|███▉      | 14579/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.95.up_proj:  40%|███▉      | 14580/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.95.down_proj:  40%|███▉      | 14581/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.96.gate_proj:  40%|███▉      | 14582/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.96.up_proj:  40%|███▉      | 14583/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.96.down_proj:  40%|███▉      | 14584/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.97.gate_proj:  40%|███▉      | 14585/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.97.up_proj:  40%|███▉      | 14586/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.97.down_proj:  40%|███▉      | 14587/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.98.gate_proj:  40%|███▉      | 14588/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.98.up_proj:  40%|███▉      | 14589/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.98.down_proj:  40%|███▉      | 14590/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.99.gate_proj:  40%|███▉      | 14591/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.99.up_proj:  40%|███▉      | 14592/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.99.down_proj:  40%|███▉      | 14593/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.100.gate_proj:  40%|███▉      | 14594/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.100.up_proj:  40%|███▉      | 14595/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.100.down_proj:  40%|███▉      | 14596/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.101.gate_proj:  40%|███▉      | 14597/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.101.up_proj:  40%|███▉      | 14598/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.101.down_proj:  40%|███▉      | 14599/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.102.gate_proj:  40%|███▉      | 14600/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.102.up_proj:  40%|███▉      | 14601/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.102.down_proj:  40%|███▉      | 14602/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.103.gate_proj:  40%|███▉      | 14603/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.103.up_proj:  40%|███▉      | 14604/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.103.down_proj:  40%|███▉      | 14605/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.104.gate_proj:  40%|███▉      | 14606/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.104.up_proj:  40%|███▉      | 14607/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.104.down_proj:  40%|███▉      | 14608/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.105.gate_proj:  40%|███▉      | 14609/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.105.up_proj:  40%|███▉      | 14610/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.105.down_proj:  40%|███▉      | 14611/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.106.gate_proj:  40%|███▉      | 14612/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.106.up_proj:  40%|███▉      | 14613/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.106.down_proj:  40%|███▉      | 14614/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.107.gate_proj:  40%|███▉      | 14615/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.107.up_proj:  40%|███▉      | 14616/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.107.down_proj:  40%|███▉      | 14617/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.108.gate_proj:  40%|███▉      | 14618/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.108.up_proj:  40%|███▉      | 14619/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.108.down_proj:  40%|███▉      | 14620/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.109.gate_proj:  40%|███▉      | 14621/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.109.up_proj:  40%|███▉      | 14622/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.109.down_proj:  40%|███▉      | 14623/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.110.gate_proj:  40%|███▉      | 14624/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.110.up_proj:  40%|███▉      | 14625/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.110.down_proj:  40%|███▉      | 14626/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.111.gate_proj:  40%|████      | 14627/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.111.up_proj:  40%|████      | 14628/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.111.down_proj:  40%|████      | 14629/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.112.gate_proj:  40%|████      | 14630/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.112.up_proj:  40%|████      | 14631/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.112.down_proj:  40%|████      | 14632/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.113.gate_proj:  40%|████      | 14633/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.113.up_proj:  40%|████      | 14634/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.113.down_proj:  40%|████      | 14635/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.114.gate_proj:  40%|████      | 14636/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.114.up_proj:  40%|████      | 14637/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.114.down_proj:  40%|████      | 14638/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.115.gate_proj:  40%|████      | 14639/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.115.up_proj:  40%|████      | 14640/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.115.down_proj:  40%|████      | 14641/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.116.gate_proj:  40%|████      | 14642/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.116.up_proj:  40%|████      | 14643/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.116.down_proj:  40%|████      | 14644/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.117.gate_proj:  40%|████      | 14645/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.117.up_proj:  40%|████      | 14646/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.117.down_proj:  40%|████      | 14647/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.118.gate_proj:  40%|████      | 14648/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.118.up_proj:  40%|████      | 14649/36566 [00:13<00:18, 1157.47it/s]  
packing model.layers.36.mlp.experts.118.down_proj:  40%|████      | 14650/36566 [00:13<00:18, 1157.47it/s]
packing model.layers.36.mlp.experts.118.down_proj:  40%|████      | 14651/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.119.gate_proj:  40%|████      | 14651/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.119.up_proj:  40%|████      | 14652/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.119.down_proj:  40%|████      | 14653/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.120.gate_proj:  40%|████      | 14654/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.120.up_proj:  40%|████      | 14655/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.120.down_proj:  40%|████      | 14656/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.121.gate_proj:  40%|████      | 14657/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.121.up_proj:  40%|████      | 14658/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.121.down_proj:  40%|████      | 14659/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.122.gate_proj:  40%|████      | 14660/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.122.up_proj:  40%|████      | 14661/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.122.down_proj:  40%|████      | 14662/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.123.gate_proj:  40%|████      | 14663/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.123.up_proj:  40%|████      | 14664/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.123.down_proj:  40%|████      | 14665/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.124.gate_proj:  40%|████      | 14666/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.124.up_proj:  40%|████      | 14667/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.124.down_proj:  40%|████      | 14668/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.125.gate_proj:  40%|████      | 14669/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.125.up_proj:  40%|████      | 14670/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.125.down_proj:  40%|████      | 14671/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.126.gate_proj:  40%|████      | 14672/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.126.up_proj:  40%|████      | 14673/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.126.down_proj:  40%|████      | 14674/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.127.gate_proj:  40%|████      | 14675/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.36.mlp.experts.127.up_proj:  40%|████      | 14676/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.36.mlp.experts.127.down_proj:  40%|████      | 14677/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.0.gate_proj:  40%|████      | 14678/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.0.up_proj:  40%|████      | 14679/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.0.down_proj:  40%|████      | 14680/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.1.gate_proj:  40%|████      | 14681/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.1.up_proj:  40%|████      | 14682/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.1.down_proj:  40%|████      | 14683/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.2.gate_proj:  40%|████      | 14684/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.2.up_proj:  40%|████      | 14685/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.2.down_proj:  40%|████      | 14686/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.3.gate_proj:  40%|████      | 14687/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.3.up_proj:  40%|████      | 14688/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.3.down_proj:  40%|████      | 14689/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.4.gate_proj:  40%|████      | 14690/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.4.up_proj:  40%|████      | 14691/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.4.down_proj:  40%|████      | 14692/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.5.gate_proj:  40%|████      | 14693/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.5.up_proj:  40%|████      | 14694/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.5.down_proj:  40%|████      | 14695/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.6.gate_proj:  40%|████      | 14696/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.6.up_proj:  40%|████      | 14697/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.6.down_proj:  40%|████      | 14698/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.7.gate_proj:  40%|████      | 14699/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.7.up_proj:  40%|████      | 14700/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.7.down_proj:  40%|████      | 14701/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.8.gate_proj:  40%|████      | 14702/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.8.up_proj:  40%|████      | 14703/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.8.down_proj:  40%|████      | 14704/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.9.gate_proj:  40%|████      | 14705/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.9.up_proj:  40%|████      | 14706/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.9.down_proj:  40%|████      | 14707/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.10.gate_proj:  40%|████      | 14708/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.10.up_proj:  40%|████      | 14709/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.10.down_proj:  40%|████      | 14710/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.11.gate_proj:  40%|████      | 14711/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.11.up_proj:  40%|████      | 14712/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.11.down_proj:  40%|████      | 14713/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.12.gate_proj:  40%|████      | 14714/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.12.up_proj:  40%|████      | 14715/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.12.down_proj:  40%|████      | 14716/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.13.gate_proj:  40%|████      | 14717/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.13.up_proj:  40%|████      | 14718/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.13.down_proj:  40%|████      | 14719/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.14.gate_proj:  40%|████      | 14720/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.14.up_proj:  40%|████      | 14721/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.14.down_proj:  40%|████      | 14722/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.15.gate_proj:  40%|████      | 14723/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.15.up_proj:  40%|████      | 14724/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.15.down_proj:  40%|████      | 14725/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.16.gate_proj:  40%|████      | 14726/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.16.up_proj:  40%|████      | 14727/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.16.down_proj:  40%|████      | 14728/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.17.gate_proj:  40%|████      | 14729/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.17.up_proj:  40%|████      | 14730/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.17.down_proj:  40%|████      | 14731/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.18.gate_proj:  40%|████      | 14732/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.18.up_proj:  40%|████      | 14733/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.18.down_proj:  40%|████      | 14734/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.19.gate_proj:  40%|████      | 14735/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.19.up_proj:  40%|████      | 14736/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.19.down_proj:  40%|████      | 14737/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.20.gate_proj:  40%|████      | 14738/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.20.up_proj:  40%|████      | 14739/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.20.down_proj:  40%|████      | 14740/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.21.gate_proj:  40%|████      | 14741/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.21.up_proj:  40%|████      | 14742/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.21.down_proj:  40%|████      | 14743/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.22.gate_proj:  40%|████      | 14744/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.22.up_proj:  40%|████      | 14745/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.22.down_proj:  40%|████      | 14746/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.23.gate_proj:  40%|████      | 14747/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.23.up_proj:  40%|████      | 14748/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.23.down_proj:  40%|████      | 14749/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.24.gate_proj:  40%|████      | 14750/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.24.up_proj:  40%|████      | 14751/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.24.down_proj:  40%|████      | 14752/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.25.gate_proj:  40%|████      | 14753/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.25.up_proj:  40%|████      | 14754/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.25.down_proj:  40%|████      | 14755/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.26.gate_proj:  40%|████      | 14756/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.26.up_proj:  40%|████      | 14757/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.26.down_proj:  40%|████      | 14758/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.27.gate_proj:  40%|████      | 14759/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.27.up_proj:  40%|████      | 14760/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.27.down_proj:  40%|████      | 14761/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.28.gate_proj:  40%|████      | 14762/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.28.up_proj:  40%|████      | 14763/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.28.down_proj:  40%|████      | 14764/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.29.gate_proj:  40%|████      | 14765/36566 [00:13<00:18, 1158.75it/s]
packing model.layers.37.mlp.experts.29.up_proj:  40%|████      | 14766/36566 [00:13<00:18, 1158.75it/s]  
packing model.layers.37.mlp.experts.29.up_proj:  40%|████      | 14767/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.29.down_proj:  40%|████      | 14767/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.30.gate_proj:  40%|████      | 14768/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.30.up_proj:  40%|████      | 14769/36566 [00:13<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.30.down_proj:  40%|████      | 14770/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.31.gate_proj:  40%|████      | 14771/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.31.up_proj:  40%|████      | 14772/36566 [00:13<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.31.down_proj:  40%|████      | 14773/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.32.gate_proj:  40%|████      | 14774/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.32.up_proj:  40%|████      | 14775/36566 [00:13<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.32.down_proj:  40%|████      | 14776/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.33.gate_proj:  40%|████      | 14777/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.33.up_proj:  40%|████      | 14778/36566 [00:13<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.33.down_proj:  40%|████      | 14779/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.34.gate_proj:  40%|████      | 14780/36566 [00:13<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.34.up_proj:  40%|████      | 14781/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.34.down_proj:  40%|████      | 14782/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.35.gate_proj:  40%|████      | 14783/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.35.up_proj:  40%|████      | 14784/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.35.down_proj:  40%|████      | 14785/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.36.gate_proj:  40%|████      | 14786/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.36.up_proj:  40%|████      | 14787/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.36.down_proj:  40%|████      | 14788/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.37.gate_proj:  40%|████      | 14789/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.37.up_proj:  40%|████      | 14790/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.37.down_proj:  40%|████      | 14791/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.38.gate_proj:  40%|████      | 14792/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.38.up_proj:  40%|████      | 14793/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.38.down_proj:  40%|████      | 14794/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.39.gate_proj:  40%|████      | 14795/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.39.up_proj:  40%|████      | 14796/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.39.down_proj:  40%|████      | 14797/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.40.gate_proj:  40%|████      | 14798/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.40.up_proj:  40%|████      | 14799/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.40.down_proj:  40%|████      | 14800/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.41.gate_proj:  40%|████      | 14801/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.41.up_proj:  40%|████      | 14802/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.41.down_proj:  40%|████      | 14803/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.42.gate_proj:  40%|████      | 14804/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.42.up_proj:  40%|████      | 14805/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.42.down_proj:  40%|████      | 14806/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.43.gate_proj:  40%|████      | 14807/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.43.up_proj:  40%|████      | 14808/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.43.down_proj:  40%|████      | 14809/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.44.gate_proj:  41%|████      | 14810/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.44.up_proj:  41%|████      | 14811/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.44.down_proj:  41%|████      | 14812/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.45.gate_proj:  41%|████      | 14813/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.45.up_proj:  41%|████      | 14814/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.45.down_proj:  41%|████      | 14815/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.46.gate_proj:  41%|████      | 14816/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.46.up_proj:  41%|████      | 14817/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.46.down_proj:  41%|████      | 14818/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.47.gate_proj:  41%|████      | 14819/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.47.up_proj:  41%|████      | 14820/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.47.down_proj:  41%|████      | 14821/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.48.gate_proj:  41%|████      | 14822/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.48.up_proj:  41%|████      | 14823/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.48.down_proj:  41%|████      | 14824/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.49.gate_proj:  41%|████      | 14825/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.49.up_proj:  41%|████      | 14826/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.49.down_proj:  41%|████      | 14827/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.50.gate_proj:  41%|████      | 14828/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.50.up_proj:  41%|████      | 14829/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.50.down_proj:  41%|████      | 14830/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.51.gate_proj:  41%|████      | 14831/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.51.up_proj:  41%|████      | 14832/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.51.down_proj:  41%|████      | 14833/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.52.gate_proj:  41%|████      | 14834/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.52.up_proj:  41%|████      | 14835/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.52.down_proj:  41%|████      | 14836/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.53.gate_proj:  41%|████      | 14837/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.53.up_proj:  41%|████      | 14838/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.53.down_proj:  41%|████      | 14839/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.54.gate_proj:  41%|████      | 14840/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.54.up_proj:  41%|████      | 14841/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.54.down_proj:  41%|████      | 14842/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.55.gate_proj:  41%|████      | 14843/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.55.up_proj:  41%|████      | 14844/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.55.down_proj:  41%|████      | 14845/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.56.gate_proj:  41%|████      | 14846/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.56.up_proj:  41%|████      | 14847/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.56.down_proj:  41%|████      | 14848/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.57.gate_proj:  41%|████      | 14849/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.57.up_proj:  41%|████      | 14850/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.57.down_proj:  41%|████      | 14851/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.58.gate_proj:  41%|████      | 14852/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.58.up_proj:  41%|████      | 14853/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.58.down_proj:  41%|████      | 14854/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.59.gate_proj:  41%|████      | 14855/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.59.up_proj:  41%|████      | 14856/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.59.down_proj:  41%|████      | 14857/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.60.gate_proj:  41%|████      | 14858/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.60.up_proj:  41%|████      | 14859/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.60.down_proj:  41%|████      | 14860/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.61.gate_proj:  41%|████      | 14861/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.61.up_proj:  41%|████      | 14862/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.61.down_proj:  41%|████      | 14863/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.62.gate_proj:  41%|████      | 14864/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.62.up_proj:  41%|████      | 14865/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.62.down_proj:  41%|████      | 14866/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.63.gate_proj:  41%|████      | 14867/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.63.up_proj:  41%|████      | 14868/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.63.down_proj:  41%|████      | 14869/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.64.gate_proj:  41%|████      | 14870/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.64.up_proj:  41%|████      | 14871/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.64.down_proj:  41%|████      | 14872/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.65.gate_proj:  41%|████      | 14873/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.65.up_proj:  41%|████      | 14874/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.65.down_proj:  41%|████      | 14875/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.66.gate_proj:  41%|████      | 14876/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.66.up_proj:  41%|████      | 14877/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.66.down_proj:  41%|████      | 14878/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.67.gate_proj:  41%|████      | 14879/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.67.up_proj:  41%|████      | 14880/36566 [00:14<00:18, 1157.49it/s]  
packing model.layers.37.mlp.experts.67.down_proj:  41%|████      | 14881/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.68.gate_proj:  41%|████      | 14882/36566 [00:14<00:18, 1157.49it/s]
packing model.layers.37.mlp.experts.68.gate_proj:  41%|████      | 14883/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.68.up_proj:  41%|████      | 14883/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.68.down_proj:  41%|████      | 14884/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.69.gate_proj:  41%|████      | 14885/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.69.up_proj:  41%|████      | 14886/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.69.down_proj:  41%|████      | 14887/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.70.gate_proj:  41%|████      | 14888/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.70.up_proj:  41%|████      | 14889/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.70.down_proj:  41%|████      | 14890/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.71.gate_proj:  41%|████      | 14891/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.71.up_proj:  41%|████      | 14892/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.71.down_proj:  41%|████      | 14893/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.72.gate_proj:  41%|████      | 14894/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.72.up_proj:  41%|████      | 14895/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.72.down_proj:  41%|████      | 14896/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.73.gate_proj:  41%|████      | 14897/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.73.up_proj:  41%|████      | 14898/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.73.down_proj:  41%|████      | 14899/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.74.gate_proj:  41%|████      | 14900/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.74.up_proj:  41%|████      | 14901/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.74.down_proj:  41%|████      | 14902/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.75.gate_proj:  41%|████      | 14903/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.75.up_proj:  41%|████      | 14904/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.75.down_proj:  41%|████      | 14905/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.76.gate_proj:  41%|████      | 14906/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.76.up_proj:  41%|████      | 14907/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.76.down_proj:  41%|████      | 14908/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.77.gate_proj:  41%|████      | 14909/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.77.up_proj:  41%|████      | 14910/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.77.down_proj:  41%|████      | 14911/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.78.gate_proj:  41%|████      | 14912/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.78.up_proj:  41%|████      | 14913/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.78.down_proj:  41%|████      | 14914/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.79.gate_proj:  41%|████      | 14915/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.79.up_proj:  41%|████      | 14916/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.79.down_proj:  41%|████      | 14917/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.80.gate_proj:  41%|████      | 14918/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.80.up_proj:  41%|████      | 14919/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.80.down_proj:  41%|████      | 14920/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.81.gate_proj:  41%|████      | 14921/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.81.up_proj:  41%|████      | 14922/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.81.down_proj:  41%|████      | 14923/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.82.gate_proj:  41%|████      | 14924/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.82.up_proj:  41%|████      | 14925/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.82.down_proj:  41%|████      | 14926/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.83.gate_proj:  41%|████      | 14927/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.83.up_proj:  41%|████      | 14928/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.83.down_proj:  41%|████      | 14929/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.84.gate_proj:  41%|████      | 14930/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.84.up_proj:  41%|████      | 14931/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.84.down_proj:  41%|████      | 14932/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.85.gate_proj:  41%|████      | 14933/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.85.up_proj:  41%|████      | 14934/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.85.down_proj:  41%|████      | 14935/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.86.gate_proj:  41%|████      | 14936/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.86.up_proj:  41%|████      | 14937/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.86.down_proj:  41%|████      | 14938/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.87.gate_proj:  41%|████      | 14939/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.87.up_proj:  41%|████      | 14940/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.87.down_proj:  41%|████      | 14941/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.88.gate_proj:  41%|████      | 14942/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.88.up_proj:  41%|████      | 14943/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.88.down_proj:  41%|████      | 14944/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.89.gate_proj:  41%|████      | 14945/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.89.up_proj:  41%|████      | 14946/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.89.down_proj:  41%|████      | 14947/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.90.gate_proj:  41%|████      | 14948/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.90.up_proj:  41%|████      | 14949/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.90.down_proj:  41%|████      | 14950/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.91.gate_proj:  41%|████      | 14951/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.91.up_proj:  41%|████      | 14952/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.91.down_proj:  41%|████      | 14953/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.92.gate_proj:  41%|████      | 14954/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.92.up_proj:  41%|████      | 14955/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.92.down_proj:  41%|████      | 14956/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.93.gate_proj:  41%|████      | 14957/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.93.up_proj:  41%|████      | 14958/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.93.down_proj:  41%|████      | 14959/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.94.gate_proj:  41%|████      | 14960/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.94.up_proj:  41%|████      | 14961/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.94.down_proj:  41%|████      | 14962/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.95.gate_proj:  41%|████      | 14963/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.95.up_proj:  41%|████      | 14964/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.95.down_proj:  41%|████      | 14965/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.96.gate_proj:  41%|████      | 14966/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.96.up_proj:  41%|████      | 14967/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.96.down_proj:  41%|████      | 14968/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.97.gate_proj:  41%|████      | 14969/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.97.up_proj:  41%|████      | 14970/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.97.down_proj:  41%|████      | 14971/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.98.gate_proj:  41%|████      | 14972/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.98.up_proj:  41%|████      | 14973/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.98.down_proj:  41%|████      | 14974/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.99.gate_proj:  41%|████      | 14975/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.99.up_proj:  41%|████      | 14976/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.99.down_proj:  41%|████      | 14977/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.100.gate_proj:  41%|████      | 14978/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.100.up_proj:  41%|████      | 14979/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.100.down_proj:  41%|████      | 14980/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.101.gate_proj:  41%|████      | 14981/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.101.up_proj:  41%|████      | 14982/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.101.down_proj:  41%|████      | 14983/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.102.gate_proj:  41%|████      | 14984/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.102.up_proj:  41%|████      | 14985/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.102.down_proj:  41%|████      | 14986/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.103.gate_proj:  41%|████      | 14987/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.103.up_proj:  41%|████      | 14988/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.103.down_proj:  41%|████      | 14989/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.104.gate_proj:  41%|████      | 14990/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.104.up_proj:  41%|████      | 14991/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.104.down_proj:  41%|████      | 14992/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.105.gate_proj:  41%|████      | 14993/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.105.up_proj:  41%|████      | 14994/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.105.down_proj:  41%|████      | 14995/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.106.gate_proj:  41%|████      | 14996/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.106.up_proj:  41%|████      | 14997/36566 [00:14<00:18, 1157.24it/s]  
packing model.layers.37.mlp.experts.106.down_proj:  41%|████      | 14998/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.107.gate_proj:  41%|████      | 14999/36566 [00:14<00:18, 1157.24it/s]
packing model.layers.37.mlp.experts.107.gate_proj:  41%|████      | 15000/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.107.up_proj:  41%|████      | 15000/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.107.down_proj:  41%|████      | 15001/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.108.gate_proj:  41%|████      | 15002/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.108.up_proj:  41%|████      | 15003/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.108.down_proj:  41%|████      | 15004/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.109.gate_proj:  41%|████      | 15005/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.109.up_proj:  41%|████      | 15006/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.109.down_proj:  41%|████      | 15007/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.110.gate_proj:  41%|████      | 15008/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.110.up_proj:  41%|████      | 15009/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.110.down_proj:  41%|████      | 15010/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.111.gate_proj:  41%|████      | 15011/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.111.up_proj:  41%|████      | 15012/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.111.down_proj:  41%|████      | 15013/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.112.gate_proj:  41%|████      | 15014/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.112.up_proj:  41%|████      | 15015/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.112.down_proj:  41%|████      | 15016/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.113.gate_proj:  41%|████      | 15017/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.113.up_proj:  41%|████      | 15018/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.113.down_proj:  41%|████      | 15019/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.114.gate_proj:  41%|████      | 15020/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.114.up_proj:  41%|████      | 15021/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.114.down_proj:  41%|████      | 15022/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.115.gate_proj:  41%|████      | 15023/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.115.up_proj:  41%|████      | 15024/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.115.down_proj:  41%|████      | 15025/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.116.gate_proj:  41%|████      | 15026/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.116.up_proj:  41%|████      | 15027/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.116.down_proj:  41%|████      | 15028/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.117.gate_proj:  41%|████      | 15029/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.117.up_proj:  41%|████      | 15030/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.117.down_proj:  41%|████      | 15031/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.118.gate_proj:  41%|████      | 15032/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.118.up_proj:  41%|████      | 15033/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.118.down_proj:  41%|████      | 15034/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.119.gate_proj:  41%|████      | 15035/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.119.up_proj:  41%|████      | 15036/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.119.down_proj:  41%|████      | 15037/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.120.gate_proj:  41%|████      | 15038/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.120.up_proj:  41%|████      | 15039/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.120.down_proj:  41%|████      | 15040/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.121.gate_proj:  41%|████      | 15041/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.121.up_proj:  41%|████      | 15042/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.121.down_proj:  41%|████      | 15043/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.122.gate_proj:  41%|████      | 15044/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.122.up_proj:  41%|████      | 15045/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.122.down_proj:  41%|████      | 15046/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.123.gate_proj:  41%|████      | 15047/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.123.up_proj:  41%|████      | 15048/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.123.down_proj:  41%|████      | 15049/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.124.gate_proj:  41%|████      | 15050/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.124.up_proj:  41%|████      | 15051/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.124.down_proj:  41%|████      | 15052/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.125.gate_proj:  41%|████      | 15053/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.125.up_proj:  41%|████      | 15054/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.125.down_proj:  41%|████      | 15055/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.126.gate_proj:  41%|████      | 15056/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.126.up_proj:  41%|████      | 15057/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.126.down_proj:  41%|████      | 15058/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.127.gate_proj:  41%|████      | 15059/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.37.mlp.experts.127.up_proj:  41%|████      | 15060/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.37.mlp.experts.127.down_proj:  41%|████      | 15061/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.0.gate_proj:  41%|████      | 15062/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.0.up_proj:  41%|████      | 15063/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.0.down_proj:  41%|████      | 15064/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.1.gate_proj:  41%|████      | 15065/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.1.up_proj:  41%|████      | 15066/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.1.down_proj:  41%|████      | 15067/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.2.gate_proj:  41%|████      | 15068/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.2.up_proj:  41%|████      | 15069/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.2.down_proj:  41%|████      | 15070/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.3.gate_proj:  41%|████      | 15071/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.3.up_proj:  41%|████      | 15072/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.3.down_proj:  41%|████      | 15073/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.4.gate_proj:  41%|████      | 15074/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.4.up_proj:  41%|████      | 15075/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.4.down_proj:  41%|████      | 15076/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.5.gate_proj:  41%|████      | 15077/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.5.up_proj:  41%|████      | 15078/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.5.down_proj:  41%|████      | 15079/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.6.gate_proj:  41%|████      | 15080/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.6.up_proj:  41%|████      | 15081/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.6.down_proj:  41%|████      | 15082/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.7.gate_proj:  41%|████      | 15083/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.7.up_proj:  41%|████▏     | 15084/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.7.down_proj:  41%|████▏     | 15085/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.8.gate_proj:  41%|████▏     | 15086/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.8.up_proj:  41%|████▏     | 15087/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.8.down_proj:  41%|████▏     | 15088/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.9.gate_proj:  41%|████▏     | 15089/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.9.up_proj:  41%|████▏     | 15090/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.9.down_proj:  41%|████▏     | 15091/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.10.gate_proj:  41%|████▏     | 15092/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.10.up_proj:  41%|████▏     | 15093/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.10.down_proj:  41%|████▏     | 15094/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.11.gate_proj:  41%|████▏     | 15095/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.11.up_proj:  41%|████▏     | 15096/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.11.down_proj:  41%|████▏     | 15097/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.12.gate_proj:  41%|████▏     | 15098/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.12.up_proj:  41%|████▏     | 15099/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.12.down_proj:  41%|████▏     | 15100/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.13.gate_proj:  41%|████▏     | 15101/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.13.up_proj:  41%|████▏     | 15102/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.13.down_proj:  41%|████▏     | 15103/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.14.gate_proj:  41%|████▏     | 15104/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.14.up_proj:  41%|████▏     | 15105/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.14.down_proj:  41%|████▏     | 15106/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.15.gate_proj:  41%|████▏     | 15107/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.15.up_proj:  41%|████▏     | 15108/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.15.down_proj:  41%|████▏     | 15109/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.16.gate_proj:  41%|████▏     | 15110/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.16.up_proj:  41%|████▏     | 15111/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.16.down_proj:  41%|████▏     | 15112/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.17.gate_proj:  41%|████▏     | 15113/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.17.up_proj:  41%|████▏     | 15114/36566 [00:14<00:18, 1158.29it/s]  
packing model.layers.38.mlp.experts.17.down_proj:  41%|████▏     | 15115/36566 [00:14<00:18, 1158.29it/s]
packing model.layers.38.mlp.experts.17.down_proj:  41%|████▏     | 15116/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.18.gate_proj:  41%|████▏     | 15116/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.18.up_proj:  41%|████▏     | 15117/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.18.down_proj:  41%|████▏     | 15118/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.19.gate_proj:  41%|████▏     | 15119/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.19.up_proj:  41%|████▏     | 15120/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.19.down_proj:  41%|████▏     | 15121/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.20.gate_proj:  41%|████▏     | 15122/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.20.up_proj:  41%|████▏     | 15123/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.20.down_proj:  41%|████▏     | 15124/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.21.gate_proj:  41%|████▏     | 15125/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.21.up_proj:  41%|████▏     | 15126/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.21.down_proj:  41%|████▏     | 15127/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.22.gate_proj:  41%|████▏     | 15128/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.22.up_proj:  41%|████▏     | 15129/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.22.down_proj:  41%|████▏     | 15130/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.23.gate_proj:  41%|████▏     | 15131/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.23.up_proj:  41%|████▏     | 15132/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.23.down_proj:  41%|████▏     | 15133/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.24.gate_proj:  41%|████▏     | 15134/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.24.up_proj:  41%|████▏     | 15135/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.24.down_proj:  41%|████▏     | 15136/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.25.gate_proj:  41%|████▏     | 15137/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.25.up_proj:  41%|████▏     | 15138/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.25.down_proj:  41%|████▏     | 15139/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.26.gate_proj:  41%|████▏     | 15140/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.26.up_proj:  41%|████▏     | 15141/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.26.down_proj:  41%|████▏     | 15142/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.27.gate_proj:  41%|████▏     | 15143/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.27.up_proj:  41%|████▏     | 15144/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.27.down_proj:  41%|████▏     | 15145/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.28.gate_proj:  41%|████▏     | 15146/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.28.up_proj:  41%|████▏     | 15147/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.28.down_proj:  41%|████▏     | 15148/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.29.gate_proj:  41%|████▏     | 15149/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.29.up_proj:  41%|████▏     | 15150/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.29.down_proj:  41%|████▏     | 15151/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.30.gate_proj:  41%|████▏     | 15152/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.30.up_proj:  41%|████▏     | 15153/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.30.down_proj:  41%|████▏     | 15154/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.31.gate_proj:  41%|████▏     | 15155/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.31.up_proj:  41%|████▏     | 15156/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.31.down_proj:  41%|████▏     | 15157/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.32.gate_proj:  41%|████▏     | 15158/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.32.up_proj:  41%|████▏     | 15159/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.32.down_proj:  41%|████▏     | 15160/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.33.gate_proj:  41%|████▏     | 15161/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.33.up_proj:  41%|████▏     | 15162/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.33.down_proj:  41%|████▏     | 15163/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.34.gate_proj:  41%|████▏     | 15164/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.34.up_proj:  41%|████▏     | 15165/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.34.down_proj:  41%|████▏     | 15166/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.35.gate_proj:  41%|████▏     | 15167/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.35.up_proj:  41%|████▏     | 15168/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.35.down_proj:  41%|████▏     | 15169/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.36.gate_proj:  41%|████▏     | 15170/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.36.up_proj:  41%|████▏     | 15171/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.36.down_proj:  41%|████▏     | 15172/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.37.gate_proj:  41%|████▏     | 15173/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.37.up_proj:  41%|████▏     | 15174/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.37.down_proj:  42%|████▏     | 15175/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.38.gate_proj:  42%|████▏     | 15176/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.38.up_proj:  42%|████▏     | 15177/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.38.down_proj:  42%|████▏     | 15178/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.39.gate_proj:  42%|████▏     | 15179/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.39.up_proj:  42%|████▏     | 15180/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.39.down_proj:  42%|████▏     | 15181/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.40.gate_proj:  42%|████▏     | 15182/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.40.up_proj:  42%|████▏     | 15183/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.40.down_proj:  42%|████▏     | 15184/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.41.gate_proj:  42%|████▏     | 15185/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.41.up_proj:  42%|████▏     | 15186/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.41.down_proj:  42%|████▏     | 15187/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.42.gate_proj:  42%|████▏     | 15188/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.42.up_proj:  42%|████▏     | 15189/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.42.down_proj:  42%|████▏     | 15190/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.43.gate_proj:  42%|████▏     | 15191/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.43.up_proj:  42%|████▏     | 15192/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.43.down_proj:  42%|████▏     | 15193/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.44.gate_proj:  42%|████▏     | 15194/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.44.up_proj:  42%|████▏     | 15195/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.44.down_proj:  42%|████▏     | 15196/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.45.gate_proj:  42%|████▏     | 15197/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.45.up_proj:  42%|████▏     | 15198/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.45.down_proj:  42%|████▏     | 15199/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.46.gate_proj:  42%|████▏     | 15200/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.46.up_proj:  42%|████▏     | 15201/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.46.down_proj:  42%|████▏     | 15202/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.47.gate_proj:  42%|████▏     | 15203/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.47.up_proj:  42%|████▏     | 15204/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.47.down_proj:  42%|████▏     | 15205/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.48.gate_proj:  42%|████▏     | 15206/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.48.up_proj:  42%|████▏     | 15207/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.48.down_proj:  42%|████▏     | 15208/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.49.gate_proj:  42%|████▏     | 15209/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.49.up_proj:  42%|████▏     | 15210/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.49.down_proj:  42%|████▏     | 15211/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.50.gate_proj:  42%|████▏     | 15212/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.50.up_proj:  42%|████▏     | 15213/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.50.down_proj:  42%|████▏     | 15214/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.51.gate_proj:  42%|████▏     | 15215/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.51.up_proj:  42%|████▏     | 15216/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.51.down_proj:  42%|████▏     | 15217/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.52.gate_proj:  42%|████▏     | 15218/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.52.up_proj:  42%|████▏     | 15219/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.52.down_proj:  42%|████▏     | 15220/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.53.gate_proj:  42%|████▏     | 15221/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.53.up_proj:  42%|████▏     | 15222/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.53.down_proj:  42%|████▏     | 15223/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.54.gate_proj:  42%|████▏     | 15224/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.54.up_proj:  42%|████▏     | 15225/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.54.down_proj:  42%|████▏     | 15226/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.55.gate_proj:  42%|████▏     | 15227/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.55.up_proj:  42%|████▏     | 15228/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.55.down_proj:  42%|████▏     | 15229/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.56.gate_proj:  42%|████▏     | 15230/36566 [00:14<00:18, 1157.58it/s]
packing model.layers.38.mlp.experts.56.up_proj:  42%|████▏     | 15231/36566 [00:14<00:18, 1157.58it/s]  
packing model.layers.38.mlp.experts.56.up_proj:  42%|████▏     | 15232/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.56.down_proj:  42%|████▏     | 15232/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.57.gate_proj:  42%|████▏     | 15233/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.57.up_proj:  42%|████▏     | 15234/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.57.down_proj:  42%|████▏     | 15235/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.58.gate_proj:  42%|████▏     | 15236/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.58.up_proj:  42%|████▏     | 15237/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.58.down_proj:  42%|████▏     | 15238/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.59.gate_proj:  42%|████▏     | 15239/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.59.up_proj:  42%|████▏     | 15240/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.59.down_proj:  42%|████▏     | 15241/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.60.gate_proj:  42%|████▏     | 15242/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.60.up_proj:  42%|████▏     | 15243/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.60.down_proj:  42%|████▏     | 15244/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.61.gate_proj:  42%|████▏     | 15245/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.61.up_proj:  42%|████▏     | 15246/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.61.down_proj:  42%|████▏     | 15247/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.62.gate_proj:  42%|████▏     | 15248/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.62.up_proj:  42%|████▏     | 15249/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.62.down_proj:  42%|████▏     | 15250/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.63.gate_proj:  42%|████▏     | 15251/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.63.up_proj:  42%|████▏     | 15252/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.63.down_proj:  42%|████▏     | 15253/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.64.gate_proj:  42%|████▏     | 15254/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.64.up_proj:  42%|████▏     | 15255/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.64.down_proj:  42%|████▏     | 15256/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.65.gate_proj:  42%|████▏     | 15257/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.65.up_proj:  42%|████▏     | 15258/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.65.down_proj:  42%|████▏     | 15259/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.66.gate_proj:  42%|████▏     | 15260/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.66.up_proj:  42%|████▏     | 15261/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.66.down_proj:  42%|████▏     | 15262/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.67.gate_proj:  42%|████▏     | 15263/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.67.up_proj:  42%|████▏     | 15264/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.67.down_proj:  42%|████▏     | 15265/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.68.gate_proj:  42%|████▏     | 15266/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.68.up_proj:  42%|████▏     | 15267/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.68.down_proj:  42%|████▏     | 15268/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.69.gate_proj:  42%|████▏     | 15269/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.69.up_proj:  42%|████▏     | 15270/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.69.down_proj:  42%|████▏     | 15271/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.70.gate_proj:  42%|████▏     | 15272/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.70.up_proj:  42%|████▏     | 15273/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.70.down_proj:  42%|████▏     | 15274/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.71.gate_proj:  42%|████▏     | 15275/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.71.up_proj:  42%|████▏     | 15276/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.71.down_proj:  42%|████▏     | 15277/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.72.gate_proj:  42%|████▏     | 15278/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.72.up_proj:  42%|████▏     | 15279/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.72.down_proj:  42%|████▏     | 15280/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.73.gate_proj:  42%|████▏     | 15281/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.73.up_proj:  42%|████▏     | 15282/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.73.down_proj:  42%|████▏     | 15283/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.74.gate_proj:  42%|████▏     | 15284/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.74.up_proj:  42%|████▏     | 15285/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.74.down_proj:  42%|████▏     | 15286/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.75.gate_proj:  42%|████▏     | 15287/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.75.up_proj:  42%|████▏     | 15288/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.75.down_proj:  42%|████▏     | 15289/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.76.gate_proj:  42%|████▏     | 15290/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.76.up_proj:  42%|████▏     | 15291/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.76.down_proj:  42%|████▏     | 15292/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.77.gate_proj:  42%|████▏     | 15293/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.77.up_proj:  42%|████▏     | 15294/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.77.down_proj:  42%|████▏     | 15295/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.78.gate_proj:  42%|████▏     | 15296/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.78.up_proj:  42%|████▏     | 15297/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.78.down_proj:  42%|████▏     | 15298/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.79.gate_proj:  42%|████▏     | 15299/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.79.up_proj:  42%|████▏     | 15300/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.79.down_proj:  42%|████▏     | 15301/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.80.gate_proj:  42%|████▏     | 15302/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.80.up_proj:  42%|████▏     | 15303/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.80.down_proj:  42%|████▏     | 15304/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.81.gate_proj:  42%|████▏     | 15305/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.81.up_proj:  42%|████▏     | 15306/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.81.down_proj:  42%|████▏     | 15307/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.82.gate_proj:  42%|████▏     | 15308/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.82.up_proj:  42%|████▏     | 15309/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.82.down_proj:  42%|████▏     | 15310/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.83.gate_proj:  42%|████▏     | 15311/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.83.up_proj:  42%|████▏     | 15312/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.83.down_proj:  42%|████▏     | 15313/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.84.gate_proj:  42%|████▏     | 15314/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.84.up_proj:  42%|████▏     | 15315/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.84.down_proj:  42%|████▏     | 15316/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.85.gate_proj:  42%|████▏     | 15317/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.85.up_proj:  42%|████▏     | 15318/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.85.down_proj:  42%|████▏     | 15319/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.86.gate_proj:  42%|████▏     | 15320/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.86.up_proj:  42%|████▏     | 15321/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.86.down_proj:  42%|████▏     | 15322/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.87.gate_proj:  42%|████▏     | 15323/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.87.up_proj:  42%|████▏     | 15324/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.87.down_proj:  42%|████▏     | 15325/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.88.gate_proj:  42%|████▏     | 15326/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.88.up_proj:  42%|████▏     | 15327/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.88.down_proj:  42%|████▏     | 15328/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.89.gate_proj:  42%|████▏     | 15329/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.89.up_proj:  42%|████▏     | 15330/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.89.down_proj:  42%|████▏     | 15331/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.90.gate_proj:  42%|████▏     | 15332/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.90.up_proj:  42%|████▏     | 15333/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.90.down_proj:  42%|████▏     | 15334/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.91.gate_proj:  42%|████▏     | 15335/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.91.up_proj:  42%|████▏     | 15336/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.91.down_proj:  42%|████▏     | 15337/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.92.gate_proj:  42%|████▏     | 15338/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.92.up_proj:  42%|████▏     | 15339/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.92.down_proj:  42%|████▏     | 15340/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.93.gate_proj:  42%|████▏     | 15341/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.93.up_proj:  42%|████▏     | 15342/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.93.down_proj:  42%|████▏     | 15343/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.94.gate_proj:  42%|████▏     | 15344/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.94.up_proj:  42%|████▏     | 15345/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.94.down_proj:  42%|████▏     | 15346/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.95.gate_proj:  42%|████▏     | 15347/36566 [00:14<00:18, 1155.75it/s]
packing model.layers.38.mlp.experts.95.up_proj:  42%|████▏     | 15348/36566 [00:14<00:18, 1155.75it/s]  
packing model.layers.38.mlp.experts.95.up_proj:  42%|████▏     | 15349/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.95.down_proj:  42%|████▏     | 15349/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.96.gate_proj:  42%|████▏     | 15350/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.96.up_proj:  42%|████▏     | 15351/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.96.down_proj:  42%|████▏     | 15352/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.97.gate_proj:  42%|████▏     | 15353/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.97.up_proj:  42%|████▏     | 15354/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.97.down_proj:  42%|████▏     | 15355/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.98.gate_proj:  42%|████▏     | 15356/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.98.up_proj:  42%|████▏     | 15357/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.98.down_proj:  42%|████▏     | 15358/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.99.gate_proj:  42%|████▏     | 15359/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.99.up_proj:  42%|████▏     | 15360/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.99.down_proj:  42%|████▏     | 15361/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.100.gate_proj:  42%|████▏     | 15362/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.100.up_proj:  42%|████▏     | 15363/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.100.down_proj:  42%|████▏     | 15364/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.101.gate_proj:  42%|████▏     | 15365/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.101.up_proj:  42%|████▏     | 15366/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.101.down_proj:  42%|████▏     | 15367/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.102.gate_proj:  42%|████▏     | 15368/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.102.up_proj:  42%|████▏     | 15369/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.102.down_proj:  42%|████▏     | 15370/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.103.gate_proj:  42%|████▏     | 15371/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.103.up_proj:  42%|████▏     | 15372/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.103.down_proj:  42%|████▏     | 15373/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.104.gate_proj:  42%|████▏     | 15374/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.104.up_proj:  42%|████▏     | 15375/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.104.down_proj:  42%|████▏     | 15376/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.105.gate_proj:  42%|████▏     | 15377/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.105.up_proj:  42%|████▏     | 15378/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.105.down_proj:  42%|████▏     | 15379/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.106.gate_proj:  42%|████▏     | 15380/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.106.up_proj:  42%|████▏     | 15381/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.106.down_proj:  42%|████▏     | 15382/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.107.gate_proj:  42%|████▏     | 15383/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.107.up_proj:  42%|████▏     | 15384/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.107.down_proj:  42%|████▏     | 15385/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.108.gate_proj:  42%|████▏     | 15386/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.108.up_proj:  42%|████▏     | 15387/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.108.down_proj:  42%|████▏     | 15388/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.109.gate_proj:  42%|████▏     | 15389/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.109.up_proj:  42%|████▏     | 15390/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.109.down_proj:  42%|████▏     | 15391/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.110.gate_proj:  42%|████▏     | 15392/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.110.up_proj:  42%|████▏     | 15393/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.110.down_proj:  42%|████▏     | 15394/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.111.gate_proj:  42%|████▏     | 15395/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.111.up_proj:  42%|████▏     | 15396/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.111.down_proj:  42%|████▏     | 15397/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.112.gate_proj:  42%|████▏     | 15398/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.112.up_proj:  42%|████▏     | 15399/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.112.down_proj:  42%|████▏     | 15400/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.113.gate_proj:  42%|████▏     | 15401/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.113.up_proj:  42%|████▏     | 15402/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.113.down_proj:  42%|████▏     | 15403/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.114.gate_proj:  42%|████▏     | 15404/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.114.up_proj:  42%|████▏     | 15405/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.114.down_proj:  42%|████▏     | 15406/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.115.gate_proj:  42%|████▏     | 15407/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.115.up_proj:  42%|████▏     | 15408/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.115.down_proj:  42%|████▏     | 15409/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.116.gate_proj:  42%|████▏     | 15410/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.116.up_proj:  42%|████▏     | 15411/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.116.down_proj:  42%|████▏     | 15412/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.117.gate_proj:  42%|████▏     | 15413/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.117.up_proj:  42%|████▏     | 15414/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.117.down_proj:  42%|████▏     | 15415/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.118.gate_proj:  42%|████▏     | 15416/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.118.up_proj:  42%|████▏     | 15417/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.118.down_proj:  42%|████▏     | 15418/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.119.gate_proj:  42%|████▏     | 15419/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.119.up_proj:  42%|████▏     | 15420/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.119.down_proj:  42%|████▏     | 15421/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.120.gate_proj:  42%|████▏     | 15422/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.120.up_proj:  42%|████▏     | 15423/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.120.down_proj:  42%|████▏     | 15424/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.121.gate_proj:  42%|████▏     | 15425/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.121.up_proj:  42%|████▏     | 15426/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.121.down_proj:  42%|████▏     | 15427/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.122.gate_proj:  42%|████▏     | 15428/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.122.up_proj:  42%|████▏     | 15429/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.122.down_proj:  42%|████▏     | 15430/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.123.gate_proj:  42%|████▏     | 15431/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.123.up_proj:  42%|████▏     | 15432/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.123.down_proj:  42%|████▏     | 15433/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.124.gate_proj:  42%|████▏     | 15434/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.124.up_proj:  42%|████▏     | 15435/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.124.down_proj:  42%|████▏     | 15436/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.125.gate_proj:  42%|████▏     | 15437/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.125.up_proj:  42%|████▏     | 15438/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.125.down_proj:  42%|████▏     | 15439/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.126.gate_proj:  42%|████▏     | 15440/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.126.up_proj:  42%|████▏     | 15441/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.126.down_proj:  42%|████▏     | 15442/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.127.gate_proj:  42%|████▏     | 15443/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.38.mlp.experts.127.up_proj:  42%|████▏     | 15444/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.38.mlp.experts.127.down_proj:  42%|████▏     | 15445/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.0.gate_proj:  42%|████▏     | 15446/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.0.up_proj:  42%|████▏     | 15447/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.0.down_proj:  42%|████▏     | 15448/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.1.gate_proj:  42%|████▏     | 15449/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.1.up_proj:  42%|████▏     | 15450/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.1.down_proj:  42%|████▏     | 15451/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.2.gate_proj:  42%|████▏     | 15452/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.2.up_proj:  42%|████▏     | 15453/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.2.down_proj:  42%|████▏     | 15454/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.3.gate_proj:  42%|████▏     | 15455/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.3.up_proj:  42%|████▏     | 15456/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.3.down_proj:  42%|████▏     | 15457/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.4.gate_proj:  42%|████▏     | 15458/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.4.up_proj:  42%|████▏     | 15459/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.4.down_proj:  42%|████▏     | 15460/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.5.gate_proj:  42%|████▏     | 15461/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.5.up_proj:  42%|████▏     | 15462/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.5.down_proj:  42%|████▏     | 15463/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.6.gate_proj:  42%|████▏     | 15464/36566 [00:14<00:18, 1157.46it/s]
packing model.layers.39.mlp.experts.6.up_proj:  42%|████▏     | 15465/36566 [00:14<00:18, 1157.46it/s]  
packing model.layers.39.mlp.experts.6.up_proj:  42%|████▏     | 15466/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.6.down_proj:  42%|████▏     | 15466/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.7.gate_proj:  42%|████▏     | 15467/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.7.up_proj:  42%|████▏     | 15468/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.7.down_proj:  42%|████▏     | 15469/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.8.gate_proj:  42%|████▏     | 15470/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.8.up_proj:  42%|████▏     | 15471/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.8.down_proj:  42%|████▏     | 15472/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.9.gate_proj:  42%|████▏     | 15473/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.9.up_proj:  42%|████▏     | 15474/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.9.down_proj:  42%|████▏     | 15475/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.10.gate_proj:  42%|████▏     | 15476/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.10.up_proj:  42%|████▏     | 15477/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.10.down_proj:  42%|████▏     | 15478/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.11.gate_proj:  42%|████▏     | 15479/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.11.up_proj:  42%|████▏     | 15480/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.11.down_proj:  42%|████▏     | 15481/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.12.gate_proj:  42%|████▏     | 15482/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.12.up_proj:  42%|████▏     | 15483/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.12.down_proj:  42%|████▏     | 15484/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.13.gate_proj:  42%|████▏     | 15485/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.13.up_proj:  42%|████▏     | 15486/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.13.down_proj:  42%|████▏     | 15487/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.14.gate_proj:  42%|████▏     | 15488/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.14.up_proj:  42%|████▏     | 15489/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.14.down_proj:  42%|████▏     | 15490/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.15.gate_proj:  42%|████▏     | 15491/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.15.up_proj:  42%|████▏     | 15492/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.15.down_proj:  42%|████▏     | 15493/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.16.gate_proj:  42%|████▏     | 15494/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.16.up_proj:  42%|████▏     | 15495/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.16.down_proj:  42%|████▏     | 15496/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.17.gate_proj:  42%|████▏     | 15497/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.17.up_proj:  42%|████▏     | 15498/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.17.down_proj:  42%|████▏     | 15499/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.18.gate_proj:  42%|████▏     | 15500/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.18.up_proj:  42%|████▏     | 15501/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.18.down_proj:  42%|████▏     | 15502/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.19.gate_proj:  42%|████▏     | 15503/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.19.up_proj:  42%|████▏     | 15504/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.19.down_proj:  42%|████▏     | 15505/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.20.gate_proj:  42%|████▏     | 15506/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.20.up_proj:  42%|████▏     | 15507/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.20.down_proj:  42%|████▏     | 15508/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.21.gate_proj:  42%|████▏     | 15509/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.21.up_proj:  42%|████▏     | 15510/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.21.down_proj:  42%|████▏     | 15511/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.22.gate_proj:  42%|████▏     | 15512/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.22.up_proj:  42%|████▏     | 15513/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.22.down_proj:  42%|████▏     | 15514/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.23.gate_proj:  42%|████▏     | 15515/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.23.up_proj:  42%|████▏     | 15516/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.23.down_proj:  42%|████▏     | 15517/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.24.gate_proj:  42%|████▏     | 15518/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.24.up_proj:  42%|████▏     | 15519/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.24.down_proj:  42%|████▏     | 15520/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.25.gate_proj:  42%|████▏     | 15521/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.25.up_proj:  42%|████▏     | 15522/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.25.down_proj:  42%|████▏     | 15523/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.26.gate_proj:  42%|████▏     | 15524/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.26.up_proj:  42%|████▏     | 15525/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.26.down_proj:  42%|████▏     | 15526/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.27.gate_proj:  42%|████▏     | 15527/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.27.up_proj:  42%|████▏     | 15528/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.27.down_proj:  42%|████▏     | 15529/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.28.gate_proj:  42%|████▏     | 15530/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.28.up_proj:  42%|████▏     | 15531/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.28.down_proj:  42%|████▏     | 15532/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.29.gate_proj:  42%|████▏     | 15533/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.29.up_proj:  42%|████▏     | 15534/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.29.down_proj:  42%|████▏     | 15535/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.30.gate_proj:  42%|████▏     | 15536/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.30.up_proj:  42%|████▏     | 15537/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.30.down_proj:  42%|████▏     | 15538/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.31.gate_proj:  42%|████▏     | 15539/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.31.up_proj:  42%|████▏     | 15540/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.31.down_proj:  43%|████▎     | 15541/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.32.gate_proj:  43%|████▎     | 15542/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.32.up_proj:  43%|████▎     | 15543/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.32.down_proj:  43%|████▎     | 15544/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.33.gate_proj:  43%|████▎     | 15545/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.33.up_proj:  43%|████▎     | 15546/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.33.down_proj:  43%|████▎     | 15547/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.34.gate_proj:  43%|████▎     | 15548/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.34.up_proj:  43%|████▎     | 15549/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.34.down_proj:  43%|████▎     | 15550/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.35.gate_proj:  43%|████▎     | 15551/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.35.up_proj:  43%|████▎     | 15552/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.35.down_proj:  43%|████▎     | 15553/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.36.gate_proj:  43%|████▎     | 15554/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.36.up_proj:  43%|████▎     | 15555/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.36.down_proj:  43%|████▎     | 15556/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.37.gate_proj:  43%|████▎     | 15557/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.37.up_proj:  43%|████▎     | 15558/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.37.down_proj:  43%|████▎     | 15559/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.38.gate_proj:  43%|████▎     | 15560/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.38.up_proj:  43%|████▎     | 15561/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.38.down_proj:  43%|████▎     | 15562/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.39.gate_proj:  43%|████▎     | 15563/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.39.up_proj:  43%|████▎     | 15564/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.39.down_proj:  43%|████▎     | 15565/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.40.gate_proj:  43%|████▎     | 15566/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.40.up_proj:  43%|████▎     | 15567/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.40.down_proj:  43%|████▎     | 15568/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.41.gate_proj:  43%|████▎     | 15569/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.41.up_proj:  43%|████▎     | 15570/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.41.down_proj:  43%|████▎     | 15571/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.42.gate_proj:  43%|████▎     | 15572/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.42.up_proj:  43%|████▎     | 15573/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.42.down_proj:  43%|████▎     | 15574/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.43.gate_proj:  43%|████▎     | 15575/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.43.up_proj:  43%|████▎     | 15576/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.43.down_proj:  43%|████▎     | 15577/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.44.gate_proj:  43%|████▎     | 15578/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.44.up_proj:  43%|████▎     | 15579/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.44.down_proj:  43%|████▎     | 15580/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.45.gate_proj:  43%|████▎     | 15581/36566 [00:14<00:18, 1158.45it/s]
packing model.layers.39.mlp.experts.45.up_proj:  43%|████▎     | 15582/36566 [00:14<00:18, 1158.45it/s]  
packing model.layers.39.mlp.experts.45.up_proj:  43%|████▎     | 15583/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.45.down_proj:  43%|████▎     | 15583/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.46.gate_proj:  43%|████▎     | 15584/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.46.up_proj:  43%|████▎     | 15585/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.46.down_proj:  43%|████▎     | 15586/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.47.gate_proj:  43%|████▎     | 15587/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.47.up_proj:  43%|████▎     | 15588/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.47.down_proj:  43%|████▎     | 15589/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.48.gate_proj:  43%|████▎     | 15590/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.48.up_proj:  43%|████▎     | 15591/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.48.down_proj:  43%|████▎     | 15592/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.49.gate_proj:  43%|████▎     | 15593/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.49.up_proj:  43%|████▎     | 15594/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.49.down_proj:  43%|████▎     | 15595/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.50.gate_proj:  43%|████▎     | 15596/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.50.up_proj:  43%|████▎     | 15597/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.50.down_proj:  43%|████▎     | 15598/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.51.gate_proj:  43%|████▎     | 15599/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.51.up_proj:  43%|████▎     | 15600/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.51.down_proj:  43%|████▎     | 15601/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.52.gate_proj:  43%|████▎     | 15602/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.52.up_proj:  43%|████▎     | 15603/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.52.down_proj:  43%|████▎     | 15604/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.53.gate_proj:  43%|████▎     | 15605/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.53.up_proj:  43%|████▎     | 15606/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.53.down_proj:  43%|████▎     | 15607/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.54.gate_proj:  43%|████▎     | 15608/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.54.up_proj:  43%|████▎     | 15609/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.54.down_proj:  43%|████▎     | 15610/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.55.gate_proj:  43%|████▎     | 15611/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.55.up_proj:  43%|████▎     | 15612/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.55.down_proj:  43%|████▎     | 15613/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.56.gate_proj:  43%|████▎     | 15614/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.56.up_proj:  43%|████▎     | 15615/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.56.down_proj:  43%|████▎     | 15616/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.57.gate_proj:  43%|████▎     | 15617/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.57.up_proj:  43%|████▎     | 15618/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.57.down_proj:  43%|████▎     | 15619/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.58.gate_proj:  43%|████▎     | 15620/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.58.up_proj:  43%|████▎     | 15621/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.58.down_proj:  43%|████▎     | 15622/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.59.gate_proj:  43%|████▎     | 15623/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.59.up_proj:  43%|████▎     | 15624/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.59.down_proj:  43%|████▎     | 15625/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.60.gate_proj:  43%|████▎     | 15626/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.60.up_proj:  43%|████▎     | 15627/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.60.down_proj:  43%|████▎     | 15628/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.61.gate_proj:  43%|████▎     | 15629/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.61.up_proj:  43%|████▎     | 15630/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.61.down_proj:  43%|████▎     | 15631/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.62.gate_proj:  43%|████▎     | 15632/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.62.up_proj:  43%|████▎     | 15633/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.62.down_proj:  43%|████▎     | 15634/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.63.gate_proj:  43%|████▎     | 15635/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.63.up_proj:  43%|████▎     | 15636/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.63.down_proj:  43%|████▎     | 15637/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.64.gate_proj:  43%|████▎     | 15638/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.64.up_proj:  43%|████▎     | 15639/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.64.down_proj:  43%|████▎     | 15640/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.65.gate_proj:  43%|████▎     | 15641/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.65.up_proj:  43%|████▎     | 15642/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.65.down_proj:  43%|████▎     | 15643/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.66.gate_proj:  43%|████▎     | 15644/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.66.up_proj:  43%|████▎     | 15645/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.66.down_proj:  43%|████▎     | 15646/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.67.gate_proj:  43%|████▎     | 15647/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.67.up_proj:  43%|████▎     | 15648/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.67.down_proj:  43%|████▎     | 15649/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.68.gate_proj:  43%|████▎     | 15650/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.68.up_proj:  43%|████▎     | 15651/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.68.down_proj:  43%|████▎     | 15652/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.69.gate_proj:  43%|████▎     | 15653/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.69.up_proj:  43%|████▎     | 15654/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.69.down_proj:  43%|████▎     | 15655/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.70.gate_proj:  43%|████▎     | 15656/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.70.up_proj:  43%|████▎     | 15657/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.70.down_proj:  43%|████▎     | 15658/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.71.gate_proj:  43%|████▎     | 15659/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.71.up_proj:  43%|████▎     | 15660/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.71.down_proj:  43%|████▎     | 15661/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.72.gate_proj:  43%|████▎     | 15662/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.72.up_proj:  43%|████▎     | 15663/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.72.down_proj:  43%|████▎     | 15664/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.73.gate_proj:  43%|████▎     | 15665/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.73.up_proj:  43%|████▎     | 15666/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.73.down_proj:  43%|████▎     | 15667/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.74.gate_proj:  43%|████▎     | 15668/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.74.up_proj:  43%|████▎     | 15669/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.74.down_proj:  43%|████▎     | 15670/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.75.gate_proj:  43%|████▎     | 15671/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.75.up_proj:  43%|████▎     | 15672/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.75.down_proj:  43%|████▎     | 15673/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.76.gate_proj:  43%|████▎     | 15674/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.76.up_proj:  43%|████▎     | 15675/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.76.down_proj:  43%|████▎     | 15676/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.77.gate_proj:  43%|████▎     | 15677/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.77.up_proj:  43%|████▎     | 15678/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.77.down_proj:  43%|████▎     | 15679/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.78.gate_proj:  43%|████▎     | 15680/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.78.up_proj:  43%|████▎     | 15681/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.78.down_proj:  43%|████▎     | 15682/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.79.gate_proj:  43%|████▎     | 15683/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.79.up_proj:  43%|████▎     | 15684/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.79.down_proj:  43%|████▎     | 15685/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.80.gate_proj:  43%|████▎     | 15686/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.80.up_proj:  43%|████▎     | 15687/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.80.down_proj:  43%|████▎     | 15688/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.81.gate_proj:  43%|████▎     | 15689/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.81.up_proj:  43%|████▎     | 15690/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.81.down_proj:  43%|████▎     | 15691/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.82.gate_proj:  43%|████▎     | 15692/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.82.up_proj:  43%|████▎     | 15693/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.82.down_proj:  43%|████▎     | 15694/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.83.gate_proj:  43%|████▎     | 15695/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.83.up_proj:  43%|████▎     | 15696/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.83.down_proj:  43%|████▎     | 15697/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.84.gate_proj:  43%|████▎     | 15698/36566 [00:14<00:18, 1159.25it/s]
packing model.layers.39.mlp.experts.84.up_proj:  43%|████▎     | 15699/36566 [00:14<00:18, 1159.25it/s]  
packing model.layers.39.mlp.experts.84.up_proj:  43%|████▎     | 15700/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.84.down_proj:  43%|████▎     | 15700/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.85.gate_proj:  43%|████▎     | 15701/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.85.up_proj:  43%|████▎     | 15702/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.85.down_proj:  43%|████▎     | 15703/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.86.gate_proj:  43%|████▎     | 15704/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.86.up_proj:  43%|████▎     | 15705/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.86.down_proj:  43%|████▎     | 15706/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.87.gate_proj:  43%|████▎     | 15707/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.87.up_proj:  43%|████▎     | 15708/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.87.down_proj:  43%|████▎     | 15709/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.88.gate_proj:  43%|████▎     | 15710/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.88.up_proj:  43%|████▎     | 15711/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.88.down_proj:  43%|████▎     | 15712/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.89.gate_proj:  43%|████▎     | 15713/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.89.up_proj:  43%|████▎     | 15714/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.89.down_proj:  43%|████▎     | 15715/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.90.gate_proj:  43%|████▎     | 15716/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.90.up_proj:  43%|████▎     | 15717/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.90.down_proj:  43%|████▎     | 15718/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.91.gate_proj:  43%|████▎     | 15719/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.91.up_proj:  43%|████▎     | 15720/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.91.down_proj:  43%|████▎     | 15721/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.92.gate_proj:  43%|████▎     | 15722/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.92.up_proj:  43%|████▎     | 15723/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.92.down_proj:  43%|████▎     | 15724/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.93.gate_proj:  43%|████▎     | 15725/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.93.up_proj:  43%|████▎     | 15726/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.93.down_proj:  43%|████▎     | 15727/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.94.gate_proj:  43%|████▎     | 15728/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.94.up_proj:  43%|████▎     | 15729/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.94.down_proj:  43%|████▎     | 15730/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.95.gate_proj:  43%|████▎     | 15731/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.95.up_proj:  43%|████▎     | 15732/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.95.down_proj:  43%|████▎     | 15733/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.96.gate_proj:  43%|████▎     | 15734/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.96.up_proj:  43%|████▎     | 15735/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.96.down_proj:  43%|████▎     | 15736/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.97.gate_proj:  43%|████▎     | 15737/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.97.up_proj:  43%|████▎     | 15738/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.97.down_proj:  43%|████▎     | 15739/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.98.gate_proj:  43%|████▎     | 15740/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.98.up_proj:  43%|████▎     | 15741/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.98.down_proj:  43%|████▎     | 15742/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.99.gate_proj:  43%|████▎     | 15743/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.99.up_proj:  43%|████▎     | 15744/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.99.down_proj:  43%|████▎     | 15745/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.100.gate_proj:  43%|████▎     | 15746/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.100.up_proj:  43%|████▎     | 15747/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.100.down_proj:  43%|████▎     | 15748/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.101.gate_proj:  43%|████▎     | 15749/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.101.up_proj:  43%|████▎     | 15750/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.101.down_proj:  43%|████▎     | 15751/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.102.gate_proj:  43%|████▎     | 15752/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.102.up_proj:  43%|████▎     | 15753/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.102.down_proj:  43%|████▎     | 15754/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.103.gate_proj:  43%|████▎     | 15755/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.103.up_proj:  43%|████▎     | 15756/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.103.down_proj:  43%|████▎     | 15757/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.104.gate_proj:  43%|████▎     | 15758/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.104.up_proj:  43%|████▎     | 15759/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.104.down_proj:  43%|████▎     | 15760/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.105.gate_proj:  43%|████▎     | 15761/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.105.up_proj:  43%|████▎     | 15762/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.105.down_proj:  43%|████▎     | 15763/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.106.gate_proj:  43%|████▎     | 15764/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.106.up_proj:  43%|████▎     | 15765/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.106.down_proj:  43%|████▎     | 15766/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.107.gate_proj:  43%|████▎     | 15767/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.107.up_proj:  43%|████▎     | 15768/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.107.down_proj:  43%|████▎     | 15769/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.108.gate_proj:  43%|████▎     | 15770/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.108.up_proj:  43%|████▎     | 15771/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.108.down_proj:  43%|████▎     | 15772/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.109.gate_proj:  43%|████▎     | 15773/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.109.up_proj:  43%|████▎     | 15774/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.109.down_proj:  43%|████▎     | 15775/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.110.gate_proj:  43%|████▎     | 15776/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.110.up_proj:  43%|████▎     | 15777/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.110.down_proj:  43%|████▎     | 15778/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.111.gate_proj:  43%|████▎     | 15779/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.111.up_proj:  43%|████▎     | 15780/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.111.down_proj:  43%|████▎     | 15781/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.112.gate_proj:  43%|████▎     | 15782/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.112.up_proj:  43%|████▎     | 15783/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.112.down_proj:  43%|████▎     | 15784/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.113.gate_proj:  43%|████▎     | 15785/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.113.up_proj:  43%|████▎     | 15786/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.113.down_proj:  43%|████▎     | 15787/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.114.gate_proj:  43%|████▎     | 15788/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.114.up_proj:  43%|████▎     | 15789/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.114.down_proj:  43%|████▎     | 15790/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.115.gate_proj:  43%|████▎     | 15791/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.115.up_proj:  43%|████▎     | 15792/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.115.down_proj:  43%|████▎     | 15793/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.116.gate_proj:  43%|████▎     | 15794/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.116.up_proj:  43%|████▎     | 15795/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.116.down_proj:  43%|████▎     | 15796/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.117.gate_proj:  43%|████▎     | 15797/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.117.up_proj:  43%|████▎     | 15798/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.117.down_proj:  43%|████▎     | 15799/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.118.gate_proj:  43%|████▎     | 15800/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.118.up_proj:  43%|████▎     | 15801/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.118.down_proj:  43%|████▎     | 15802/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.119.gate_proj:  43%|████▎     | 15803/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.119.up_proj:  43%|████▎     | 15804/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.119.down_proj:  43%|████▎     | 15805/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.120.gate_proj:  43%|████▎     | 15806/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.120.up_proj:  43%|████▎     | 15807/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.120.down_proj:  43%|████▎     | 15808/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.121.gate_proj:  43%|████▎     | 15809/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.121.up_proj:  43%|████▎     | 15810/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.121.down_proj:  43%|████▎     | 15811/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.122.gate_proj:  43%|████▎     | 15812/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.122.up_proj:  43%|████▎     | 15813/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.122.down_proj:  43%|████▎     | 15814/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.123.gate_proj:  43%|████▎     | 15815/36566 [00:14<00:17, 1159.83it/s]
packing model.layers.39.mlp.experts.123.up_proj:  43%|████▎     | 15816/36566 [00:14<00:17, 1159.83it/s]  
packing model.layers.39.mlp.experts.123.up_proj:  43%|████▎     | 15817/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.123.down_proj:  43%|████▎     | 15817/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.124.gate_proj:  43%|████▎     | 15818/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.124.up_proj:  43%|████▎     | 15819/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.39.mlp.experts.124.down_proj:  43%|████▎     | 15820/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.125.gate_proj:  43%|████▎     | 15821/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.125.up_proj:  43%|████▎     | 15822/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.39.mlp.experts.125.down_proj:  43%|████▎     | 15823/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.126.gate_proj:  43%|████▎     | 15824/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.126.up_proj:  43%|████▎     | 15825/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.39.mlp.experts.126.down_proj:  43%|████▎     | 15826/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.127.gate_proj:  43%|████▎     | 15827/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.39.mlp.experts.127.up_proj:  43%|████▎     | 15828/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.39.mlp.experts.127.down_proj:  43%|████▎     | 15829/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.0.gate_proj:  43%|████▎     | 15830/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.0.up_proj:  43%|████▎     | 15831/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.0.down_proj:  43%|████▎     | 15832/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.1.gate_proj:  43%|████▎     | 15833/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.1.up_proj:  43%|████▎     | 15834/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.1.down_proj:  43%|████▎     | 15835/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.2.gate_proj:  43%|████▎     | 15836/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.2.up_proj:  43%|████▎     | 15837/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.2.down_proj:  43%|████▎     | 15838/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.3.gate_proj:  43%|████▎     | 15839/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.3.up_proj:  43%|████▎     | 15840/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.3.down_proj:  43%|████▎     | 15841/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.4.gate_proj:  43%|████▎     | 15842/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.4.up_proj:  43%|████▎     | 15843/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.4.down_proj:  43%|████▎     | 15844/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.5.gate_proj:  43%|████▎     | 15845/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.5.up_proj:  43%|████▎     | 15846/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.5.down_proj:  43%|████▎     | 15847/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.6.gate_proj:  43%|████▎     | 15848/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.6.up_proj:  43%|████▎     | 15849/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.6.down_proj:  43%|████▎     | 15850/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.7.gate_proj:  43%|████▎     | 15851/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.7.up_proj:  43%|████▎     | 15852/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.7.down_proj:  43%|████▎     | 15853/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.8.gate_proj:  43%|████▎     | 15854/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.8.up_proj:  43%|████▎     | 15855/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.8.down_proj:  43%|████▎     | 15856/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.9.gate_proj:  43%|████▎     | 15857/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.9.up_proj:  43%|████▎     | 15858/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.9.down_proj:  43%|████▎     | 15859/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.10.gate_proj:  43%|████▎     | 15860/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.10.up_proj:  43%|████▎     | 15861/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.10.down_proj:  43%|████▎     | 15862/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.11.gate_proj:  43%|████▎     | 15863/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.11.up_proj:  43%|████▎     | 15864/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.11.down_proj:  43%|████▎     | 15865/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.12.gate_proj:  43%|████▎     | 15866/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.12.up_proj:  43%|████▎     | 15867/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.12.down_proj:  43%|████▎     | 15868/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.13.gate_proj:  43%|████▎     | 15869/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.13.up_proj:  43%|████▎     | 15870/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.13.down_proj:  43%|████▎     | 15871/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.14.gate_proj:  43%|████▎     | 15872/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.14.up_proj:  43%|████▎     | 15873/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.14.down_proj:  43%|████▎     | 15874/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.15.gate_proj:  43%|████▎     | 15875/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.15.up_proj:  43%|████▎     | 15876/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.15.down_proj:  43%|████▎     | 15877/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.16.gate_proj:  43%|████▎     | 15878/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.16.up_proj:  43%|████▎     | 15879/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.16.down_proj:  43%|████▎     | 15880/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.17.gate_proj:  43%|████▎     | 15881/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.17.up_proj:  43%|████▎     | 15882/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.17.down_proj:  43%|████▎     | 15883/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.18.gate_proj:  43%|████▎     | 15884/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.18.up_proj:  43%|████▎     | 15885/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.18.down_proj:  43%|████▎     | 15886/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.19.gate_proj:  43%|████▎     | 15887/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.19.up_proj:  43%|████▎     | 15888/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.19.down_proj:  43%|████▎     | 15889/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.20.gate_proj:  43%|████▎     | 15890/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.20.up_proj:  43%|████▎     | 15891/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.20.down_proj:  43%|████▎     | 15892/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.21.gate_proj:  43%|████▎     | 15893/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.21.up_proj:  43%|████▎     | 15894/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.21.down_proj:  43%|████▎     | 15895/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.22.gate_proj:  43%|████▎     | 15896/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.22.up_proj:  43%|████▎     | 15897/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.22.down_proj:  43%|████▎     | 15898/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.23.gate_proj:  43%|████▎     | 15899/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.23.up_proj:  43%|████▎     | 15900/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.23.down_proj:  43%|████▎     | 15901/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.24.gate_proj:  43%|████▎     | 15902/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.24.up_proj:  43%|████▎     | 15903/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.24.down_proj:  43%|████▎     | 15904/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.25.gate_proj:  43%|████▎     | 15905/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.25.up_proj:  43%|████▎     | 15906/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.25.down_proj:  44%|████▎     | 15907/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.26.gate_proj:  44%|████▎     | 15908/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.26.up_proj:  44%|████▎     | 15909/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.26.down_proj:  44%|████▎     | 15910/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.27.gate_proj:  44%|████▎     | 15911/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.27.up_proj:  44%|████▎     | 15912/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.27.down_proj:  44%|████▎     | 15913/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.28.gate_proj:  44%|████▎     | 15914/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.28.up_proj:  44%|████▎     | 15915/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.28.down_proj:  44%|████▎     | 15916/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.29.gate_proj:  44%|████▎     | 15917/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.29.up_proj:  44%|████▎     | 15918/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.29.down_proj:  44%|████▎     | 15919/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.30.gate_proj:  44%|████▎     | 15920/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.30.up_proj:  44%|████▎     | 15921/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.30.down_proj:  44%|████▎     | 15922/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.31.gate_proj:  44%|████▎     | 15923/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.31.up_proj:  44%|████▎     | 15924/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.31.down_proj:  44%|████▎     | 15925/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.32.gate_proj:  44%|████▎     | 15926/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.32.up_proj:  44%|████▎     | 15927/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.32.down_proj:  44%|████▎     | 15928/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.33.gate_proj:  44%|████▎     | 15929/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.33.up_proj:  44%|████▎     | 15930/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.33.down_proj:  44%|████▎     | 15931/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.34.gate_proj:  44%|████▎     | 15932/36566 [00:14<00:17, 1160.17it/s]
packing model.layers.40.mlp.experts.34.up_proj:  44%|████▎     | 15933/36566 [00:14<00:17, 1160.17it/s]  
packing model.layers.40.mlp.experts.34.up_proj:  44%|████▎     | 15934/36566 [00:14<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.34.down_proj:  44%|████▎     | 15934/36566 [00:14<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.35.gate_proj:  44%|████▎     | 15935/36566 [00:14<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.35.up_proj:  44%|████▎     | 15936/36566 [00:14<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.35.down_proj:  44%|████▎     | 15937/36566 [00:14<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.36.gate_proj:  44%|████▎     | 15938/36566 [00:14<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.36.up_proj:  44%|████▎     | 15939/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.36.down_proj:  44%|████▎     | 15940/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.37.gate_proj:  44%|████▎     | 15941/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.37.up_proj:  44%|████▎     | 15942/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.37.down_proj:  44%|████▎     | 15943/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.38.gate_proj:  44%|████▎     | 15944/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.38.up_proj:  44%|████▎     | 15945/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.38.down_proj:  44%|████▎     | 15946/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.39.gate_proj:  44%|████▎     | 15947/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.39.up_proj:  44%|████▎     | 15948/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.39.down_proj:  44%|████▎     | 15949/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.40.gate_proj:  44%|████▎     | 15950/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.40.up_proj:  44%|████▎     | 15951/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.40.down_proj:  44%|████▎     | 15952/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.41.gate_proj:  44%|████▎     | 15953/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.41.up_proj:  44%|████▎     | 15954/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.41.down_proj:  44%|████▎     | 15955/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.42.gate_proj:  44%|████▎     | 15956/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.42.up_proj:  44%|████▎     | 15957/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.42.down_proj:  44%|████▎     | 15958/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.43.gate_proj:  44%|████▎     | 15959/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.43.up_proj:  44%|████▎     | 15960/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.43.down_proj:  44%|████▎     | 15961/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.44.gate_proj:  44%|████▎     | 15962/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.44.up_proj:  44%|████▎     | 15963/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.44.down_proj:  44%|████▎     | 15964/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.45.gate_proj:  44%|████▎     | 15965/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.45.up_proj:  44%|████▎     | 15966/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.45.down_proj:  44%|████▎     | 15967/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.46.gate_proj:  44%|████▎     | 15968/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.46.up_proj:  44%|████▎     | 15969/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.46.down_proj:  44%|████▎     | 15970/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.47.gate_proj:  44%|████▎     | 15971/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.47.up_proj:  44%|████▎     | 15972/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.47.down_proj:  44%|████▎     | 15973/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.48.gate_proj:  44%|████▎     | 15974/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.48.up_proj:  44%|████▎     | 15975/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.48.down_proj:  44%|████▎     | 15976/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.49.gate_proj:  44%|████▎     | 15977/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.49.up_proj:  44%|████▎     | 15978/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.49.down_proj:  44%|████▎     | 15979/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.50.gate_proj:  44%|████▎     | 15980/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.50.up_proj:  44%|████▎     | 15981/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.50.down_proj:  44%|████▎     | 15982/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.51.gate_proj:  44%|████▎     | 15983/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.51.up_proj:  44%|████▎     | 15984/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.51.down_proj:  44%|████▎     | 15985/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.52.gate_proj:  44%|████▎     | 15986/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.52.up_proj:  44%|████▎     | 15987/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.52.down_proj:  44%|████▎     | 15988/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.53.gate_proj:  44%|████▎     | 15989/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.53.up_proj:  44%|████▎     | 15990/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.53.down_proj:  44%|████▎     | 15991/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.54.gate_proj:  44%|████▎     | 15992/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.54.up_proj:  44%|████▎     | 15993/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.54.down_proj:  44%|████▎     | 15994/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.55.gate_proj:  44%|████▎     | 15995/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.55.up_proj:  44%|████▎     | 15996/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.55.down_proj:  44%|████▎     | 15997/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.56.gate_proj:  44%|████▍     | 15998/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.56.up_proj:  44%|████▍     | 15999/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.56.down_proj:  44%|████▍     | 16000/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.57.gate_proj:  44%|████▍     | 16001/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.57.up_proj:  44%|████▍     | 16002/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.57.down_proj:  44%|████▍     | 16003/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.58.gate_proj:  44%|████▍     | 16004/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.58.up_proj:  44%|████▍     | 16005/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.58.down_proj:  44%|████▍     | 16006/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.59.gate_proj:  44%|████▍     | 16007/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.59.up_proj:  44%|████▍     | 16008/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.59.down_proj:  44%|████▍     | 16009/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.60.gate_proj:  44%|████▍     | 16010/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.60.up_proj:  44%|████▍     | 16011/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.60.down_proj:  44%|████▍     | 16012/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.61.gate_proj:  44%|████▍     | 16013/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.61.up_proj:  44%|████▍     | 16014/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.61.down_proj:  44%|████▍     | 16015/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.62.gate_proj:  44%|████▍     | 16016/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.62.up_proj:  44%|████▍     | 16017/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.62.down_proj:  44%|████▍     | 16018/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.63.gate_proj:  44%|████▍     | 16019/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.63.up_proj:  44%|████▍     | 16020/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.63.down_proj:  44%|████▍     | 16021/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.64.gate_proj:  44%|████▍     | 16022/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.64.up_proj:  44%|████▍     | 16023/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.64.down_proj:  44%|████▍     | 16024/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.65.gate_proj:  44%|████▍     | 16025/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.65.up_proj:  44%|████▍     | 16026/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.65.down_proj:  44%|████▍     | 16027/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.66.gate_proj:  44%|████▍     | 16028/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.66.up_proj:  44%|████▍     | 16029/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.66.down_proj:  44%|████▍     | 16030/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.67.gate_proj:  44%|████▍     | 16031/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.67.up_proj:  44%|████▍     | 16032/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.67.down_proj:  44%|████▍     | 16033/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.68.gate_proj:  44%|████▍     | 16034/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.68.up_proj:  44%|████▍     | 16035/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.68.down_proj:  44%|████▍     | 16036/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.69.gate_proj:  44%|████▍     | 16037/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.69.up_proj:  44%|████▍     | 16038/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.69.down_proj:  44%|████▍     | 16039/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.70.gate_proj:  44%|████▍     | 16040/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.70.up_proj:  44%|████▍     | 16041/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.70.down_proj:  44%|████▍     | 16042/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.71.gate_proj:  44%|████▍     | 16043/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.71.up_proj:  44%|████▍     | 16044/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.71.down_proj:  44%|████▍     | 16045/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.72.gate_proj:  44%|████▍     | 16046/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.72.up_proj:  44%|████▍     | 16047/36566 [00:15<00:17, 1156.64it/s]  
packing model.layers.40.mlp.experts.72.down_proj:  44%|████▍     | 16048/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.73.gate_proj:  44%|████▍     | 16049/36566 [00:15<00:17, 1156.64it/s]
packing model.layers.40.mlp.experts.73.gate_proj:  44%|████▍     | 16050/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.73.up_proj:  44%|████▍     | 16050/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.73.down_proj:  44%|████▍     | 16051/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.74.gate_proj:  44%|████▍     | 16052/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.74.up_proj:  44%|████▍     | 16053/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.74.down_proj:  44%|████▍     | 16054/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.75.gate_proj:  44%|████▍     | 16055/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.75.up_proj:  44%|████▍     | 16056/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.75.down_proj:  44%|████▍     | 16057/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.76.gate_proj:  44%|████▍     | 16058/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.76.up_proj:  44%|████▍     | 16059/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.76.down_proj:  44%|████▍     | 16060/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.77.gate_proj:  44%|████▍     | 16061/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.77.up_proj:  44%|████▍     | 16062/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.77.down_proj:  44%|████▍     | 16063/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.78.gate_proj:  44%|████▍     | 16064/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.78.up_proj:  44%|████▍     | 16065/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.78.down_proj:  44%|████▍     | 16066/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.79.gate_proj:  44%|████▍     | 16067/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.79.up_proj:  44%|████▍     | 16068/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.79.down_proj:  44%|████▍     | 16069/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.80.gate_proj:  44%|████▍     | 16070/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.80.up_proj:  44%|████▍     | 16071/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.80.down_proj:  44%|████▍     | 16072/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.81.gate_proj:  44%|████▍     | 16073/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.81.up_proj:  44%|████▍     | 16074/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.81.down_proj:  44%|████▍     | 16075/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.82.gate_proj:  44%|████▍     | 16076/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.82.up_proj:  44%|████▍     | 16077/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.82.down_proj:  44%|████▍     | 16078/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.83.gate_proj:  44%|████▍     | 16079/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.83.up_proj:  44%|████▍     | 16080/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.83.down_proj:  44%|████▍     | 16081/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.84.gate_proj:  44%|████▍     | 16082/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.84.up_proj:  44%|████▍     | 16083/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.84.down_proj:  44%|████▍     | 16084/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.85.gate_proj:  44%|████▍     | 16085/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.85.up_proj:  44%|████▍     | 16086/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.85.down_proj:  44%|████▍     | 16087/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.86.gate_proj:  44%|████▍     | 16088/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.86.up_proj:  44%|████▍     | 16089/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.86.down_proj:  44%|████▍     | 16090/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.87.gate_proj:  44%|████▍     | 16091/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.87.up_proj:  44%|████▍     | 16092/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.87.down_proj:  44%|████▍     | 16093/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.88.gate_proj:  44%|████▍     | 16094/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.88.up_proj:  44%|████▍     | 16095/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.88.down_proj:  44%|████▍     | 16096/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.89.gate_proj:  44%|████▍     | 16097/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.89.up_proj:  44%|████▍     | 16098/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.89.down_proj:  44%|████▍     | 16099/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.90.gate_proj:  44%|████▍     | 16100/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.90.up_proj:  44%|████▍     | 16101/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.90.down_proj:  44%|████▍     | 16102/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.91.gate_proj:  44%|████▍     | 16103/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.91.up_proj:  44%|████▍     | 16104/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.91.down_proj:  44%|████▍     | 16105/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.92.gate_proj:  44%|████▍     | 16106/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.92.up_proj:  44%|████▍     | 16107/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.92.down_proj:  44%|████▍     | 16108/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.93.gate_proj:  44%|████▍     | 16109/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.93.up_proj:  44%|████▍     | 16110/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.93.down_proj:  44%|████▍     | 16111/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.94.gate_proj:  44%|████▍     | 16112/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.94.up_proj:  44%|████▍     | 16113/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.94.down_proj:  44%|████▍     | 16114/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.95.gate_proj:  44%|████▍     | 16115/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.95.up_proj:  44%|████▍     | 16116/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.95.down_proj:  44%|████▍     | 16117/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.96.gate_proj:  44%|████▍     | 16118/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.96.up_proj:  44%|████▍     | 16119/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.96.down_proj:  44%|████▍     | 16120/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.97.gate_proj:  44%|████▍     | 16121/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.97.up_proj:  44%|████▍     | 16122/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.97.down_proj:  44%|████▍     | 16123/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.98.gate_proj:  44%|████▍     | 16124/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.98.up_proj:  44%|████▍     | 16125/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.98.down_proj:  44%|████▍     | 16126/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.99.gate_proj:  44%|████▍     | 16127/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.99.up_proj:  44%|████▍     | 16128/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.99.down_proj:  44%|████▍     | 16129/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.100.gate_proj:  44%|████▍     | 16130/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.100.up_proj:  44%|████▍     | 16131/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.100.down_proj:  44%|████▍     | 16132/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.101.gate_proj:  44%|████▍     | 16133/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.101.up_proj:  44%|████▍     | 16134/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.101.down_proj:  44%|████▍     | 16135/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.102.gate_proj:  44%|████▍     | 16136/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.102.up_proj:  44%|████▍     | 16137/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.102.down_proj:  44%|████▍     | 16138/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.103.gate_proj:  44%|████▍     | 16139/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.103.up_proj:  44%|████▍     | 16140/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.103.down_proj:  44%|████▍     | 16141/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.104.gate_proj:  44%|████▍     | 16142/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.104.up_proj:  44%|████▍     | 16143/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.104.down_proj:  44%|████▍     | 16144/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.105.gate_proj:  44%|████▍     | 16145/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.105.up_proj:  44%|████▍     | 16146/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.105.down_proj:  44%|████▍     | 16147/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.106.gate_proj:  44%|████▍     | 16148/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.106.up_proj:  44%|████▍     | 16149/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.106.down_proj:  44%|████▍     | 16150/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.107.gate_proj:  44%|████▍     | 16151/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.107.up_proj:  44%|████▍     | 16152/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.107.down_proj:  44%|████▍     | 16153/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.108.gate_proj:  44%|████▍     | 16154/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.108.up_proj:  44%|████▍     | 16155/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.108.down_proj:  44%|████▍     | 16156/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.109.gate_proj:  44%|████▍     | 16157/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.109.up_proj:  44%|████▍     | 16158/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.109.down_proj:  44%|████▍     | 16159/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.110.gate_proj:  44%|████▍     | 16160/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.110.up_proj:  44%|████▍     | 16161/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.110.down_proj:  44%|████▍     | 16162/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.111.gate_proj:  44%|████▍     | 16163/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.111.up_proj:  44%|████▍     | 16164/36566 [00:15<00:17, 1156.10it/s]  
packing model.layers.40.mlp.experts.111.down_proj:  44%|████▍     | 16165/36566 [00:15<00:17, 1156.10it/s]
packing model.layers.40.mlp.experts.111.down_proj:  44%|████▍     | 16166/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.112.gate_proj:  44%|████▍     | 16166/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.112.up_proj:  44%|████▍     | 16167/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.112.down_proj:  44%|████▍     | 16168/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.113.gate_proj:  44%|████▍     | 16169/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.113.up_proj:  44%|████▍     | 16170/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.113.down_proj:  44%|████▍     | 16171/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.114.gate_proj:  44%|████▍     | 16172/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.114.up_proj:  44%|████▍     | 16173/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.114.down_proj:  44%|████▍     | 16174/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.115.gate_proj:  44%|████▍     | 16175/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.115.up_proj:  44%|████▍     | 16176/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.115.down_proj:  44%|████▍     | 16177/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.116.gate_proj:  44%|████▍     | 16178/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.116.up_proj:  44%|████▍     | 16179/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.116.down_proj:  44%|████▍     | 16180/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.117.gate_proj:  44%|████▍     | 16181/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.117.up_proj:  44%|████▍     | 16182/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.117.down_proj:  44%|████▍     | 16183/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.118.gate_proj:  44%|████▍     | 16184/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.118.up_proj:  44%|████▍     | 16185/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.118.down_proj:  44%|████▍     | 16186/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.119.gate_proj:  44%|████▍     | 16187/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.119.up_proj:  44%|████▍     | 16188/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.119.down_proj:  44%|████▍     | 16189/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.120.gate_proj:  44%|████▍     | 16190/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.120.up_proj:  44%|████▍     | 16191/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.120.down_proj:  44%|████▍     | 16192/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.121.gate_proj:  44%|████▍     | 16193/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.121.up_proj:  44%|████▍     | 16194/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.121.down_proj:  44%|████▍     | 16195/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.122.gate_proj:  44%|████▍     | 16196/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.122.up_proj:  44%|████▍     | 16197/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.122.down_proj:  44%|████▍     | 16198/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.123.gate_proj:  44%|████▍     | 16199/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.123.up_proj:  44%|████▍     | 16200/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.123.down_proj:  44%|████▍     | 16201/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.124.gate_proj:  44%|████▍     | 16202/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.124.up_proj:  44%|████▍     | 16203/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.124.down_proj:  44%|████▍     | 16204/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.125.gate_proj:  44%|████▍     | 16205/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.125.up_proj:  44%|████▍     | 16206/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.125.down_proj:  44%|████▍     | 16207/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.126.gate_proj:  44%|████▍     | 16208/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.126.up_proj:  44%|████▍     | 16209/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.126.down_proj:  44%|████▍     | 16210/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.127.gate_proj:  44%|████▍     | 16211/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.40.mlp.experts.127.up_proj:  44%|████▍     | 16212/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.40.mlp.experts.127.down_proj:  44%|████▍     | 16213/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.0.gate_proj:  44%|████▍     | 16214/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.0.up_proj:  44%|████▍     | 16215/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.0.down_proj:  44%|████▍     | 16216/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.1.gate_proj:  44%|████▍     | 16217/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.1.up_proj:  44%|████▍     | 16218/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.1.down_proj:  44%|████▍     | 16219/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.2.gate_proj:  44%|████▍     | 16220/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.2.up_proj:  44%|████▍     | 16221/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.2.down_proj:  44%|████▍     | 16222/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.3.gate_proj:  44%|████▍     | 16223/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.3.up_proj:  44%|████▍     | 16224/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.3.down_proj:  44%|████▍     | 16225/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.4.gate_proj:  44%|████▍     | 16226/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.4.up_proj:  44%|████▍     | 16227/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.4.down_proj:  44%|████▍     | 16228/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.5.gate_proj:  44%|████▍     | 16229/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.5.up_proj:  44%|████▍     | 16230/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.5.down_proj:  44%|████▍     | 16231/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.6.gate_proj:  44%|████▍     | 16232/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.6.up_proj:  44%|████▍     | 16233/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.6.down_proj:  44%|████▍     | 16234/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.7.gate_proj:  44%|████▍     | 16235/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.7.up_proj:  44%|████▍     | 16236/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.7.down_proj:  44%|████▍     | 16237/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.8.gate_proj:  44%|████▍     | 16238/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.8.up_proj:  44%|████▍     | 16239/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.8.down_proj:  44%|████▍     | 16240/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.9.gate_proj:  44%|████▍     | 16241/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.9.up_proj:  44%|████▍     | 16242/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.9.down_proj:  44%|████▍     | 16243/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.10.gate_proj:  44%|████▍     | 16244/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.10.up_proj:  44%|████▍     | 16245/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.10.down_proj:  44%|████▍     | 16246/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.11.gate_proj:  44%|████▍     | 16247/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.11.up_proj:  44%|████▍     | 16248/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.11.down_proj:  44%|████▍     | 16249/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.12.gate_proj:  44%|████▍     | 16250/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.12.up_proj:  44%|████▍     | 16251/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.12.down_proj:  44%|████▍     | 16252/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.13.gate_proj:  44%|████▍     | 16253/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.13.up_proj:  44%|████▍     | 16254/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.13.down_proj:  44%|████▍     | 16255/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.14.gate_proj:  44%|████▍     | 16256/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.14.up_proj:  44%|████▍     | 16257/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.14.down_proj:  44%|████▍     | 16258/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.15.gate_proj:  44%|████▍     | 16259/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.15.up_proj:  44%|████▍     | 16260/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.15.down_proj:  44%|████▍     | 16261/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.16.gate_proj:  44%|████▍     | 16262/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.16.up_proj:  44%|████▍     | 16263/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.16.down_proj:  44%|████▍     | 16264/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.17.gate_proj:  44%|████▍     | 16265/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.17.up_proj:  44%|████▍     | 16266/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.17.down_proj:  44%|████▍     | 16267/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.18.gate_proj:  44%|████▍     | 16268/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.18.up_proj:  44%|████▍     | 16269/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.18.down_proj:  44%|████▍     | 16270/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.19.gate_proj:  44%|████▍     | 16271/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.19.up_proj:  45%|████▍     | 16272/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.19.down_proj:  45%|████▍     | 16273/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.20.gate_proj:  45%|████▍     | 16274/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.20.up_proj:  45%|████▍     | 16275/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.20.down_proj:  45%|████▍     | 16276/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.21.gate_proj:  45%|████▍     | 16277/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.21.up_proj:  45%|████▍     | 16278/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.21.down_proj:  45%|████▍     | 16279/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.22.gate_proj:  45%|████▍     | 16280/36566 [00:15<00:17, 1157.06it/s]
packing model.layers.41.mlp.experts.22.up_proj:  45%|████▍     | 16281/36566 [00:15<00:17, 1157.06it/s]  
packing model.layers.41.mlp.experts.22.up_proj:  45%|████▍     | 16282/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.22.down_proj:  45%|████▍     | 16282/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.23.gate_proj:  45%|████▍     | 16283/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.23.up_proj:  45%|████▍     | 16284/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.23.down_proj:  45%|████▍     | 16285/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.24.gate_proj:  45%|████▍     | 16286/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.24.up_proj:  45%|████▍     | 16287/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.24.down_proj:  45%|████▍     | 16288/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.25.gate_proj:  45%|████▍     | 16289/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.25.up_proj:  45%|████▍     | 16290/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.25.down_proj:  45%|████▍     | 16291/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.26.gate_proj:  45%|████▍     | 16292/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.26.up_proj:  45%|████▍     | 16293/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.26.down_proj:  45%|████▍     | 16294/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.27.gate_proj:  45%|████▍     | 16295/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.27.up_proj:  45%|████▍     | 16296/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.27.down_proj:  45%|████▍     | 16297/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.28.gate_proj:  45%|████▍     | 16298/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.28.up_proj:  45%|████▍     | 16299/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.28.down_proj:  45%|████▍     | 16300/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.29.gate_proj:  45%|████▍     | 16301/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.29.up_proj:  45%|████▍     | 16302/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.29.down_proj:  45%|████▍     | 16303/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.30.gate_proj:  45%|████▍     | 16304/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.30.up_proj:  45%|████▍     | 16305/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.30.down_proj:  45%|████▍     | 16306/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.31.gate_proj:  45%|████▍     | 16307/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.31.up_proj:  45%|████▍     | 16308/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.31.down_proj:  45%|████▍     | 16309/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.32.gate_proj:  45%|████▍     | 16310/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.32.up_proj:  45%|████▍     | 16311/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.32.down_proj:  45%|████▍     | 16312/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.33.gate_proj:  45%|████▍     | 16313/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.33.up_proj:  45%|████▍     | 16314/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.33.down_proj:  45%|████▍     | 16315/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.34.gate_proj:  45%|████▍     | 16316/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.34.up_proj:  45%|████▍     | 16317/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.34.down_proj:  45%|████▍     | 16318/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.35.gate_proj:  45%|████▍     | 16319/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.35.up_proj:  45%|████▍     | 16320/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.35.down_proj:  45%|████▍     | 16321/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.36.gate_proj:  45%|████▍     | 16322/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.36.up_proj:  45%|████▍     | 16323/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.36.down_proj:  45%|████▍     | 16324/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.37.gate_proj:  45%|████▍     | 16325/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.37.up_proj:  45%|████▍     | 16326/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.37.down_proj:  45%|████▍     | 16327/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.38.gate_proj:  45%|████▍     | 16328/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.38.up_proj:  45%|████▍     | 16329/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.38.down_proj:  45%|████▍     | 16330/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.39.gate_proj:  45%|████▍     | 16331/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.39.up_proj:  45%|████▍     | 16332/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.39.down_proj:  45%|████▍     | 16333/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.40.gate_proj:  45%|████▍     | 16334/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.40.up_proj:  45%|████▍     | 16335/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.40.down_proj:  45%|████▍     | 16336/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.41.gate_proj:  45%|████▍     | 16337/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.41.up_proj:  45%|████▍     | 16338/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.41.down_proj:  45%|████▍     | 16339/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.42.gate_proj:  45%|████▍     | 16340/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.42.up_proj:  45%|████▍     | 16341/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.42.down_proj:  45%|████▍     | 16342/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.43.gate_proj:  45%|████▍     | 16343/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.43.up_proj:  45%|████▍     | 16344/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.43.down_proj:  45%|████▍     | 16345/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.44.gate_proj:  45%|████▍     | 16346/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.44.up_proj:  45%|████▍     | 16347/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.44.down_proj:  45%|████▍     | 16348/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.45.gate_proj:  45%|████▍     | 16349/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.45.up_proj:  45%|████▍     | 16350/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.45.down_proj:  45%|████▍     | 16351/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.46.gate_proj:  45%|████▍     | 16352/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.46.up_proj:  45%|████▍     | 16353/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.46.down_proj:  45%|████▍     | 16354/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.47.gate_proj:  45%|████▍     | 16355/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.47.up_proj:  45%|████▍     | 16356/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.47.down_proj:  45%|████▍     | 16357/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.48.gate_proj:  45%|████▍     | 16358/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.48.up_proj:  45%|████▍     | 16359/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.48.down_proj:  45%|████▍     | 16360/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.49.gate_proj:  45%|████▍     | 16361/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.49.up_proj:  45%|████▍     | 16362/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.49.down_proj:  45%|████▍     | 16363/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.50.gate_proj:  45%|████▍     | 16364/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.50.up_proj:  45%|████▍     | 16365/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.50.down_proj:  45%|████▍     | 16366/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.51.gate_proj:  45%|████▍     | 16367/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.51.up_proj:  45%|████▍     | 16368/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.51.down_proj:  45%|████▍     | 16369/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.52.gate_proj:  45%|████▍     | 16370/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.52.up_proj:  45%|████▍     | 16371/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.52.down_proj:  45%|████▍     | 16372/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.53.gate_proj:  45%|████▍     | 16373/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.53.up_proj:  45%|████▍     | 16374/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.53.down_proj:  45%|████▍     | 16375/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.54.gate_proj:  45%|████▍     | 16376/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.54.up_proj:  45%|████▍     | 16377/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.54.down_proj:  45%|████▍     | 16378/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.55.gate_proj:  45%|████▍     | 16379/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.55.up_proj:  45%|████▍     | 16380/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.55.down_proj:  45%|████▍     | 16381/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.56.gate_proj:  45%|████▍     | 16382/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.56.up_proj:  45%|████▍     | 16383/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.56.down_proj:  45%|████▍     | 16384/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.57.gate_proj:  45%|████▍     | 16385/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.57.up_proj:  45%|████▍     | 16386/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.57.down_proj:  45%|████▍     | 16387/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.58.gate_proj:  45%|████▍     | 16388/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.58.up_proj:  45%|████▍     | 16389/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.58.down_proj:  45%|████▍     | 16390/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.59.gate_proj:  45%|████▍     | 16391/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.59.up_proj:  45%|████▍     | 16392/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.59.down_proj:  45%|████▍     | 16393/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.60.gate_proj:  45%|████▍     | 16394/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.60.up_proj:  45%|████▍     | 16395/36566 [00:15<00:17, 1155.57it/s]  
packing model.layers.41.mlp.experts.60.down_proj:  45%|████▍     | 16396/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.61.gate_proj:  45%|████▍     | 16397/36566 [00:15<00:17, 1155.57it/s]
packing model.layers.41.mlp.experts.61.gate_proj:  45%|████▍     | 16398/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.61.up_proj:  45%|████▍     | 16398/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.61.down_proj:  45%|████▍     | 16399/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.62.gate_proj:  45%|████▍     | 16400/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.62.up_proj:  45%|████▍     | 16401/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.62.down_proj:  45%|████▍     | 16402/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.63.gate_proj:  45%|████▍     | 16403/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.63.up_proj:  45%|████▍     | 16404/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.63.down_proj:  45%|████▍     | 16405/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.64.gate_proj:  45%|████▍     | 16406/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.64.up_proj:  45%|████▍     | 16407/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.64.down_proj:  45%|████▍     | 16408/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.65.gate_proj:  45%|████▍     | 16409/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.65.up_proj:  45%|████▍     | 16410/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.65.down_proj:  45%|████▍     | 16411/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.66.gate_proj:  45%|████▍     | 16412/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.66.up_proj:  45%|████▍     | 16413/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.66.down_proj:  45%|████▍     | 16414/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.67.gate_proj:  45%|████▍     | 16415/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.67.up_proj:  45%|████▍     | 16416/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.67.down_proj:  45%|████▍     | 16417/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.68.gate_proj:  45%|████▍     | 16418/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.68.up_proj:  45%|████▍     | 16419/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.68.down_proj:  45%|████▍     | 16420/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.69.gate_proj:  45%|████▍     | 16421/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.69.up_proj:  45%|████▍     | 16422/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.69.down_proj:  45%|████▍     | 16423/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.70.gate_proj:  45%|████▍     | 16424/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.70.up_proj:  45%|████▍     | 16425/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.70.down_proj:  45%|████▍     | 16426/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.71.gate_proj:  45%|████▍     | 16427/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.71.up_proj:  45%|████▍     | 16428/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.71.down_proj:  45%|████▍     | 16429/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.72.gate_proj:  45%|████▍     | 16430/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.72.up_proj:  45%|████▍     | 16431/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.72.down_proj:  45%|████▍     | 16432/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.73.gate_proj:  45%|████▍     | 16433/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.73.up_proj:  45%|████▍     | 16434/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.73.down_proj:  45%|████▍     | 16435/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.74.gate_proj:  45%|████▍     | 16436/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.74.up_proj:  45%|████▍     | 16437/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.74.down_proj:  45%|████▍     | 16438/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.75.gate_proj:  45%|████▍     | 16439/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.75.up_proj:  45%|████▍     | 16440/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.75.down_proj:  45%|████▍     | 16441/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.76.gate_proj:  45%|████▍     | 16442/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.76.up_proj:  45%|████▍     | 16443/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.76.down_proj:  45%|████▍     | 16444/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.77.gate_proj:  45%|████▍     | 16445/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.77.up_proj:  45%|████▍     | 16446/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.77.down_proj:  45%|████▍     | 16447/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.78.gate_proj:  45%|████▍     | 16448/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.78.up_proj:  45%|████▍     | 16449/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.78.down_proj:  45%|████▍     | 16450/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.79.gate_proj:  45%|████▍     | 16451/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.79.up_proj:  45%|████▍     | 16452/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.79.down_proj:  45%|████▍     | 16453/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.80.gate_proj:  45%|████▍     | 16454/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.80.up_proj:  45%|████▌     | 16455/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.80.down_proj:  45%|████▌     | 16456/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.81.gate_proj:  45%|████▌     | 16457/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.81.up_proj:  45%|████▌     | 16458/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.81.down_proj:  45%|████▌     | 16459/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.82.gate_proj:  45%|████▌     | 16460/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.82.up_proj:  45%|████▌     | 16461/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.82.down_proj:  45%|████▌     | 16462/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.83.gate_proj:  45%|████▌     | 16463/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.83.up_proj:  45%|████▌     | 16464/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.83.down_proj:  45%|████▌     | 16465/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.84.gate_proj:  45%|████▌     | 16466/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.84.up_proj:  45%|████▌     | 16467/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.84.down_proj:  45%|████▌     | 16468/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.85.gate_proj:  45%|████▌     | 16469/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.85.up_proj:  45%|████▌     | 16470/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.85.down_proj:  45%|████▌     | 16471/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.86.gate_proj:  45%|████▌     | 16472/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.86.up_proj:  45%|████▌     | 16473/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.86.down_proj:  45%|████▌     | 16474/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.87.gate_proj:  45%|████▌     | 16475/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.87.up_proj:  45%|████▌     | 16476/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.87.down_proj:  45%|████▌     | 16477/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.88.gate_proj:  45%|████▌     | 16478/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.88.up_proj:  45%|████▌     | 16479/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.88.down_proj:  45%|████▌     | 16480/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.89.gate_proj:  45%|████▌     | 16481/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.89.up_proj:  45%|████▌     | 16482/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.89.down_proj:  45%|████▌     | 16483/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.90.gate_proj:  45%|████▌     | 16484/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.90.up_proj:  45%|████▌     | 16485/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.90.down_proj:  45%|████▌     | 16486/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.91.gate_proj:  45%|████▌     | 16487/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.91.up_proj:  45%|████▌     | 16488/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.91.down_proj:  45%|████▌     | 16489/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.92.gate_proj:  45%|████▌     | 16490/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.92.up_proj:  45%|████▌     | 16491/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.92.down_proj:  45%|████▌     | 16492/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.93.gate_proj:  45%|████▌     | 16493/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.93.up_proj:  45%|████▌     | 16494/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.93.down_proj:  45%|████▌     | 16495/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.94.gate_proj:  45%|████▌     | 16496/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.94.up_proj:  45%|████▌     | 16497/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.94.down_proj:  45%|████▌     | 16498/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.95.gate_proj:  45%|████▌     | 16499/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.95.up_proj:  45%|████▌     | 16500/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.95.down_proj:  45%|████▌     | 16501/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.96.gate_proj:  45%|████▌     | 16502/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.96.up_proj:  45%|████▌     | 16503/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.96.down_proj:  45%|████▌     | 16504/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.97.gate_proj:  45%|████▌     | 16505/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.97.up_proj:  45%|████▌     | 16506/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.97.down_proj:  45%|████▌     | 16507/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.98.gate_proj:  45%|████▌     | 16508/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.98.up_proj:  45%|████▌     | 16509/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.98.down_proj:  45%|████▌     | 16510/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.99.gate_proj:  45%|████▌     | 16511/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.99.up_proj:  45%|████▌     | 16512/36566 [00:15<00:17, 1155.97it/s]  
packing model.layers.41.mlp.experts.99.down_proj:  45%|████▌     | 16513/36566 [00:15<00:17, 1155.97it/s]
packing model.layers.41.mlp.experts.99.down_proj:  45%|████▌     | 16514/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.100.gate_proj:  45%|████▌     | 16514/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.100.up_proj:  45%|████▌     | 16515/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.100.down_proj:  45%|████▌     | 16516/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.101.gate_proj:  45%|████▌     | 16517/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.101.up_proj:  45%|████▌     | 16518/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.101.down_proj:  45%|████▌     | 16519/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.102.gate_proj:  45%|████▌     | 16520/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.102.up_proj:  45%|████▌     | 16521/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.102.down_proj:  45%|████▌     | 16522/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.103.gate_proj:  45%|████▌     | 16523/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.103.up_proj:  45%|████▌     | 16524/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.103.down_proj:  45%|████▌     | 16525/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.104.gate_proj:  45%|████▌     | 16526/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.104.up_proj:  45%|████▌     | 16527/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.104.down_proj:  45%|████▌     | 16528/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.105.gate_proj:  45%|████▌     | 16529/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.105.up_proj:  45%|████▌     | 16530/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.105.down_proj:  45%|████▌     | 16531/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.106.gate_proj:  45%|████▌     | 16532/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.106.up_proj:  45%|████▌     | 16533/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.106.down_proj:  45%|████▌     | 16534/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.107.gate_proj:  45%|████▌     | 16535/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.107.up_proj:  45%|████▌     | 16536/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.107.down_proj:  45%|████▌     | 16537/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.108.gate_proj:  45%|████▌     | 16538/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.108.up_proj:  45%|████▌     | 16539/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.108.down_proj:  45%|████▌     | 16540/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.109.gate_proj:  45%|████▌     | 16541/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.109.up_proj:  45%|████▌     | 16542/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.109.down_proj:  45%|████▌     | 16543/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.110.gate_proj:  45%|████▌     | 16544/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.110.up_proj:  45%|████▌     | 16545/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.110.down_proj:  45%|████▌     | 16546/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.111.gate_proj:  45%|████▌     | 16547/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.111.up_proj:  45%|████▌     | 16548/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.111.down_proj:  45%|████▌     | 16549/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.112.gate_proj:  45%|████▌     | 16550/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.112.up_proj:  45%|████▌     | 16551/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.112.down_proj:  45%|████▌     | 16552/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.113.gate_proj:  45%|████▌     | 16553/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.113.up_proj:  45%|████▌     | 16554/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.113.down_proj:  45%|████▌     | 16555/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.114.gate_proj:  45%|████▌     | 16556/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.114.up_proj:  45%|████▌     | 16557/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.114.down_proj:  45%|████▌     | 16558/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.115.gate_proj:  45%|████▌     | 16559/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.115.up_proj:  45%|████▌     | 16560/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.115.down_proj:  45%|████▌     | 16561/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.116.gate_proj:  45%|████▌     | 16562/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.116.up_proj:  45%|████▌     | 16563/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.116.down_proj:  45%|████▌     | 16564/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.117.gate_proj:  45%|████▌     | 16565/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.117.up_proj:  45%|████▌     | 16566/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.117.down_proj:  45%|████▌     | 16567/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.118.gate_proj:  45%|████▌     | 16568/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.118.up_proj:  45%|████▌     | 16569/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.118.down_proj:  45%|████▌     | 16570/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.119.gate_proj:  45%|████▌     | 16571/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.119.up_proj:  45%|████▌     | 16572/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.119.down_proj:  45%|████▌     | 16573/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.120.gate_proj:  45%|████▌     | 16574/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.120.up_proj:  45%|████▌     | 16575/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.120.down_proj:  45%|████▌     | 16576/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.121.gate_proj:  45%|████▌     | 16577/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.121.up_proj:  45%|████▌     | 16578/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.121.down_proj:  45%|████▌     | 16579/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.122.gate_proj:  45%|████▌     | 16580/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.122.up_proj:  45%|████▌     | 16581/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.122.down_proj:  45%|████▌     | 16582/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.123.gate_proj:  45%|████▌     | 16583/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.123.up_proj:  45%|████▌     | 16584/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.123.down_proj:  45%|████▌     | 16585/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.124.gate_proj:  45%|████▌     | 16586/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.124.up_proj:  45%|████▌     | 16587/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.124.down_proj:  45%|████▌     | 16588/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.125.gate_proj:  45%|████▌     | 16589/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.125.up_proj:  45%|████▌     | 16590/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.125.down_proj:  45%|████▌     | 16591/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.126.gate_proj:  45%|████▌     | 16592/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.126.up_proj:  45%|████▌     | 16593/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.126.down_proj:  45%|████▌     | 16594/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.127.gate_proj:  45%|████▌     | 16595/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.41.mlp.experts.127.up_proj:  45%|████▌     | 16596/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.41.mlp.experts.127.down_proj:  45%|████▌     | 16597/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.0.gate_proj:  45%|████▌     | 16598/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.0.up_proj:  45%|████▌     | 16599/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.0.down_proj:  45%|████▌     | 16600/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.1.gate_proj:  45%|████▌     | 16601/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.1.up_proj:  45%|████▌     | 16602/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.1.down_proj:  45%|████▌     | 16603/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.2.gate_proj:  45%|████▌     | 16604/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.2.up_proj:  45%|████▌     | 16605/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.2.down_proj:  45%|████▌     | 16606/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.3.gate_proj:  45%|████▌     | 16607/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.3.up_proj:  45%|████▌     | 16608/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.3.down_proj:  45%|████▌     | 16609/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.4.gate_proj:  45%|████▌     | 16610/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.4.up_proj:  45%|████▌     | 16611/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.4.down_proj:  45%|████▌     | 16612/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.5.gate_proj:  45%|████▌     | 16613/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.5.up_proj:  45%|████▌     | 16614/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.5.down_proj:  45%|████▌     | 16615/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.6.gate_proj:  45%|████▌     | 16616/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.6.up_proj:  45%|████▌     | 16617/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.6.down_proj:  45%|████▌     | 16618/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.7.gate_proj:  45%|████▌     | 16619/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.7.up_proj:  45%|████▌     | 16620/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.7.down_proj:  45%|████▌     | 16621/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.8.gate_proj:  45%|████▌     | 16622/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.8.up_proj:  45%|████▌     | 16623/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.8.down_proj:  45%|████▌     | 16624/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.9.gate_proj:  45%|████▌     | 16625/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.9.up_proj:  45%|████▌     | 16626/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.9.down_proj:  45%|████▌     | 16627/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.10.gate_proj:  45%|████▌     | 16628/36566 [00:15<00:17, 1156.04it/s]
packing model.layers.42.mlp.experts.10.up_proj:  45%|████▌     | 16629/36566 [00:15<00:17, 1156.04it/s]  
packing model.layers.42.mlp.experts.10.up_proj:  45%|████▌     | 16630/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.10.down_proj:  45%|████▌     | 16630/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.11.gate_proj:  45%|████▌     | 16631/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.11.up_proj:  45%|████▌     | 16632/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.11.down_proj:  45%|████▌     | 16633/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.12.gate_proj:  45%|████▌     | 16634/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.12.up_proj:  45%|████▌     | 16635/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.12.down_proj:  45%|████▌     | 16636/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.13.gate_proj:  45%|████▌     | 16637/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.13.up_proj:  46%|████▌     | 16638/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.13.down_proj:  46%|████▌     | 16639/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.14.gate_proj:  46%|████▌     | 16640/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.14.up_proj:  46%|████▌     | 16641/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.14.down_proj:  46%|████▌     | 16642/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.15.gate_proj:  46%|████▌     | 16643/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.15.up_proj:  46%|████▌     | 16644/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.15.down_proj:  46%|████▌     | 16645/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.16.gate_proj:  46%|████▌     | 16646/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.16.up_proj:  46%|████▌     | 16647/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.16.down_proj:  46%|████▌     | 16648/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.17.gate_proj:  46%|████▌     | 16649/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.17.up_proj:  46%|████▌     | 16650/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.17.down_proj:  46%|████▌     | 16651/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.18.gate_proj:  46%|████▌     | 16652/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.18.up_proj:  46%|████▌     | 16653/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.18.down_proj:  46%|████▌     | 16654/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.19.gate_proj:  46%|████▌     | 16655/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.19.up_proj:  46%|████▌     | 16656/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.19.down_proj:  46%|████▌     | 16657/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.20.gate_proj:  46%|████▌     | 16658/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.20.up_proj:  46%|████▌     | 16659/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.20.down_proj:  46%|████▌     | 16660/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.21.gate_proj:  46%|████▌     | 16661/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.21.up_proj:  46%|████▌     | 16662/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.21.down_proj:  46%|████▌     | 16663/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.22.gate_proj:  46%|████▌     | 16664/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.22.up_proj:  46%|████▌     | 16665/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.22.down_proj:  46%|████▌     | 16666/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.23.gate_proj:  46%|████▌     | 16667/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.23.up_proj:  46%|████▌     | 16668/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.23.down_proj:  46%|████▌     | 16669/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.24.gate_proj:  46%|████▌     | 16670/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.24.up_proj:  46%|████▌     | 16671/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.24.down_proj:  46%|████▌     | 16672/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.25.gate_proj:  46%|████▌     | 16673/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.25.up_proj:  46%|████▌     | 16674/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.25.down_proj:  46%|████▌     | 16675/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.26.gate_proj:  46%|████▌     | 16676/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.26.up_proj:  46%|████▌     | 16677/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.26.down_proj:  46%|████▌     | 16678/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.27.gate_proj:  46%|████▌     | 16679/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.27.up_proj:  46%|████▌     | 16680/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.27.down_proj:  46%|████▌     | 16681/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.28.gate_proj:  46%|████▌     | 16682/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.28.up_proj:  46%|████▌     | 16683/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.28.down_proj:  46%|████▌     | 16684/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.29.gate_proj:  46%|████▌     | 16685/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.29.up_proj:  46%|████▌     | 16686/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.29.down_proj:  46%|████▌     | 16687/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.30.gate_proj:  46%|████▌     | 16688/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.30.up_proj:  46%|████▌     | 16689/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.30.down_proj:  46%|████▌     | 16690/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.31.gate_proj:  46%|████▌     | 16691/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.31.up_proj:  46%|████▌     | 16692/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.31.down_proj:  46%|████▌     | 16693/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.32.gate_proj:  46%|████▌     | 16694/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.32.up_proj:  46%|████▌     | 16695/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.32.down_proj:  46%|████▌     | 16696/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.33.gate_proj:  46%|████▌     | 16697/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.33.up_proj:  46%|████▌     | 16698/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.33.down_proj:  46%|████▌     | 16699/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.34.gate_proj:  46%|████▌     | 16700/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.34.up_proj:  46%|████▌     | 16701/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.34.down_proj:  46%|████▌     | 16702/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.35.gate_proj:  46%|████▌     | 16703/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.35.up_proj:  46%|████▌     | 16704/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.35.down_proj:  46%|████▌     | 16705/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.36.gate_proj:  46%|████▌     | 16706/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.36.up_proj:  46%|████▌     | 16707/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.36.down_proj:  46%|████▌     | 16708/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.37.gate_proj:  46%|████▌     | 16709/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.37.up_proj:  46%|████▌     | 16710/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.37.down_proj:  46%|████▌     | 16711/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.38.gate_proj:  46%|████▌     | 16712/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.38.up_proj:  46%|████▌     | 16713/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.38.down_proj:  46%|████▌     | 16714/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.39.gate_proj:  46%|████▌     | 16715/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.39.up_proj:  46%|████▌     | 16716/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.39.down_proj:  46%|████▌     | 16717/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.40.gate_proj:  46%|████▌     | 16718/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.40.up_proj:  46%|████▌     | 16719/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.40.down_proj:  46%|████▌     | 16720/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.41.gate_proj:  46%|████▌     | 16721/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.41.up_proj:  46%|████▌     | 16722/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.41.down_proj:  46%|████▌     | 16723/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.42.gate_proj:  46%|████▌     | 16724/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.42.up_proj:  46%|████▌     | 16725/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.42.down_proj:  46%|████▌     | 16726/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.43.gate_proj:  46%|████▌     | 16727/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.43.up_proj:  46%|████▌     | 16728/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.43.down_proj:  46%|████▌     | 16729/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.44.gate_proj:  46%|████▌     | 16730/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.44.up_proj:  46%|████▌     | 16731/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.44.down_proj:  46%|████▌     | 16732/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.45.gate_proj:  46%|████▌     | 16733/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.45.up_proj:  46%|████▌     | 16734/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.45.down_proj:  46%|████▌     | 16735/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.46.gate_proj:  46%|████▌     | 16736/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.46.up_proj:  46%|████▌     | 16737/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.46.down_proj:  46%|████▌     | 16738/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.47.gate_proj:  46%|████▌     | 16739/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.47.up_proj:  46%|████▌     | 16740/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.47.down_proj:  46%|████▌     | 16741/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.48.gate_proj:  46%|████▌     | 16742/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.48.up_proj:  46%|████▌     | 16743/36566 [00:15<00:17, 1150.87it/s]  
packing model.layers.42.mlp.experts.48.down_proj:  46%|████▌     | 16744/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.49.gate_proj:  46%|████▌     | 16745/36566 [00:15<00:17, 1150.87it/s]
packing model.layers.42.mlp.experts.49.gate_proj:  46%|████▌     | 16746/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.49.up_proj:  46%|████▌     | 16746/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.49.down_proj:  46%|████▌     | 16747/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.50.gate_proj:  46%|████▌     | 16748/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.50.up_proj:  46%|████▌     | 16749/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.50.down_proj:  46%|████▌     | 16750/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.51.gate_proj:  46%|████▌     | 16751/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.51.up_proj:  46%|████▌     | 16752/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.51.down_proj:  46%|████▌     | 16753/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.52.gate_proj:  46%|████▌     | 16754/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.52.up_proj:  46%|████▌     | 16755/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.52.down_proj:  46%|████▌     | 16756/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.53.gate_proj:  46%|████▌     | 16757/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.53.up_proj:  46%|████▌     | 16758/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.53.down_proj:  46%|████▌     | 16759/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.54.gate_proj:  46%|████▌     | 16760/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.54.up_proj:  46%|████▌     | 16761/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.54.down_proj:  46%|████▌     | 16762/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.55.gate_proj:  46%|████▌     | 16763/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.55.up_proj:  46%|████▌     | 16764/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.55.down_proj:  46%|████▌     | 16765/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.56.gate_proj:  46%|████▌     | 16766/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.56.up_proj:  46%|████▌     | 16767/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.56.down_proj:  46%|████▌     | 16768/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.57.gate_proj:  46%|████▌     | 16769/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.57.up_proj:  46%|████▌     | 16770/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.57.down_proj:  46%|████▌     | 16771/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.58.gate_proj:  46%|████▌     | 16772/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.58.up_proj:  46%|████▌     | 16773/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.58.down_proj:  46%|████▌     | 16774/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.59.gate_proj:  46%|████▌     | 16775/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.59.up_proj:  46%|████▌     | 16776/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.59.down_proj:  46%|████▌     | 16777/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.60.gate_proj:  46%|████▌     | 16778/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.60.up_proj:  46%|████▌     | 16779/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.60.down_proj:  46%|████▌     | 16780/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.61.gate_proj:  46%|████▌     | 16781/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.61.up_proj:  46%|████▌     | 16782/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.61.down_proj:  46%|████▌     | 16783/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.62.gate_proj:  46%|████▌     | 16784/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.62.up_proj:  46%|████▌     | 16785/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.62.down_proj:  46%|████▌     | 16786/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.63.gate_proj:  46%|████▌     | 16787/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.63.up_proj:  46%|████▌     | 16788/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.63.down_proj:  46%|████▌     | 16789/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.64.gate_proj:  46%|████▌     | 16790/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.64.up_proj:  46%|████▌     | 16791/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.64.down_proj:  46%|████▌     | 16792/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.65.gate_proj:  46%|████▌     | 16793/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.65.up_proj:  46%|████▌     | 16794/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.65.down_proj:  46%|████▌     | 16795/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.66.gate_proj:  46%|████▌     | 16796/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.66.up_proj:  46%|████▌     | 16797/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.66.down_proj:  46%|████▌     | 16798/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.67.gate_proj:  46%|████▌     | 16799/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.67.up_proj:  46%|████▌     | 16800/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.67.down_proj:  46%|████▌     | 16801/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.68.gate_proj:  46%|████▌     | 16802/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.68.up_proj:  46%|████▌     | 16803/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.68.down_proj:  46%|████▌     | 16804/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.69.gate_proj:  46%|████▌     | 16805/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.69.up_proj:  46%|████▌     | 16806/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.69.down_proj:  46%|████▌     | 16807/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.70.gate_proj:  46%|████▌     | 16808/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.70.up_proj:  46%|████▌     | 16809/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.70.down_proj:  46%|████▌     | 16810/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.71.gate_proj:  46%|████▌     | 16811/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.71.up_proj:  46%|████▌     | 16812/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.71.down_proj:  46%|████▌     | 16813/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.72.gate_proj:  46%|████▌     | 16814/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.72.up_proj:  46%|████▌     | 16815/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.72.down_proj:  46%|████▌     | 16816/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.73.gate_proj:  46%|████▌     | 16817/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.73.up_proj:  46%|████▌     | 16818/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.73.down_proj:  46%|████▌     | 16819/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.74.gate_proj:  46%|████▌     | 16820/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.74.up_proj:  46%|████▌     | 16821/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.74.down_proj:  46%|████▌     | 16822/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.75.gate_proj:  46%|████▌     | 16823/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.75.up_proj:  46%|████▌     | 16824/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.75.down_proj:  46%|████▌     | 16825/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.76.gate_proj:  46%|████▌     | 16826/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.76.up_proj:  46%|████▌     | 16827/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.76.down_proj:  46%|████▌     | 16828/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.77.gate_proj:  46%|████▌     | 16829/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.77.up_proj:  46%|████▌     | 16830/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.77.down_proj:  46%|████▌     | 16831/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.78.gate_proj:  46%|████▌     | 16832/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.78.up_proj:  46%|████▌     | 16833/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.78.down_proj:  46%|████▌     | 16834/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.79.gate_proj:  46%|████▌     | 16835/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.79.up_proj:  46%|████▌     | 16836/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.79.down_proj:  46%|████▌     | 16837/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.80.gate_proj:  46%|████▌     | 16838/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.80.up_proj:  46%|████▌     | 16839/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.80.down_proj:  46%|████▌     | 16840/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.81.gate_proj:  46%|████▌     | 16841/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.81.up_proj:  46%|████▌     | 16842/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.81.down_proj:  46%|████▌     | 16843/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.82.gate_proj:  46%|████▌     | 16844/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.82.up_proj:  46%|████▌     | 16845/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.82.down_proj:  46%|████▌     | 16846/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.83.gate_proj:  46%|████▌     | 16847/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.83.up_proj:  46%|████▌     | 16848/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.83.down_proj:  46%|████▌     | 16849/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.84.gate_proj:  46%|████▌     | 16850/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.84.up_proj:  46%|████▌     | 16851/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.84.down_proj:  46%|████▌     | 16852/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.85.gate_proj:  46%|████▌     | 16853/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.85.up_proj:  46%|████▌     | 16854/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.85.down_proj:  46%|████▌     | 16855/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.86.gate_proj:  46%|████▌     | 16856/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.86.up_proj:  46%|████▌     | 16857/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.86.down_proj:  46%|████▌     | 16858/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.87.gate_proj:  46%|████▌     | 16859/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.87.up_proj:  46%|████▌     | 16860/36566 [00:15<00:17, 1151.94it/s]  
packing model.layers.42.mlp.experts.87.down_proj:  46%|████▌     | 16861/36566 [00:15<00:17, 1151.94it/s]
packing model.layers.42.mlp.experts.87.down_proj:  46%|████▌     | 16862/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.88.gate_proj:  46%|████▌     | 16862/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.88.up_proj:  46%|████▌     | 16863/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.88.down_proj:  46%|████▌     | 16864/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.89.gate_proj:  46%|████▌     | 16865/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.89.up_proj:  46%|████▌     | 16866/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.89.down_proj:  46%|████▌     | 16867/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.90.gate_proj:  46%|████▌     | 16868/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.90.up_proj:  46%|████▌     | 16869/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.90.down_proj:  46%|████▌     | 16870/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.91.gate_proj:  46%|████▌     | 16871/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.91.up_proj:  46%|████▌     | 16872/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.91.down_proj:  46%|████▌     | 16873/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.92.gate_proj:  46%|████▌     | 16874/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.92.up_proj:  46%|████▌     | 16875/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.92.down_proj:  46%|████▌     | 16876/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.93.gate_proj:  46%|████▌     | 16877/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.93.up_proj:  46%|████▌     | 16878/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.93.down_proj:  46%|████▌     | 16879/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.94.gate_proj:  46%|████▌     | 16880/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.94.up_proj:  46%|████▌     | 16881/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.94.down_proj:  46%|████▌     | 16882/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.95.gate_proj:  46%|████▌     | 16883/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.95.up_proj:  46%|████▌     | 16884/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.95.down_proj:  46%|████▌     | 16885/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.96.gate_proj:  46%|████▌     | 16886/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.96.up_proj:  46%|████▌     | 16887/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.96.down_proj:  46%|████▌     | 16888/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.97.gate_proj:  46%|████▌     | 16889/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.97.up_proj:  46%|████▌     | 16890/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.97.down_proj:  46%|████▌     | 16891/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.98.gate_proj:  46%|████▌     | 16892/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.98.up_proj:  46%|████▌     | 16893/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.98.down_proj:  46%|████▌     | 16894/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.99.gate_proj:  46%|████▌     | 16895/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.99.up_proj:  46%|████▌     | 16896/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.99.down_proj:  46%|████▌     | 16897/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.100.gate_proj:  46%|████▌     | 16898/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.100.up_proj:  46%|████▌     | 16899/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.100.down_proj:  46%|████▌     | 16900/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.101.gate_proj:  46%|████▌     | 16901/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.101.up_proj:  46%|████▌     | 16902/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.101.down_proj:  46%|████▌     | 16903/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.102.gate_proj:  46%|████▌     | 16904/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.102.up_proj:  46%|████▌     | 16905/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.102.down_proj:  46%|████▌     | 16906/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.103.gate_proj:  46%|████▌     | 16907/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.103.up_proj:  46%|████▌     | 16908/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.103.down_proj:  46%|████▌     | 16909/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.104.gate_proj:  46%|████▌     | 16910/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.104.up_proj:  46%|████▌     | 16911/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.104.down_proj:  46%|████▋     | 16912/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.105.gate_proj:  46%|████▋     | 16913/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.105.up_proj:  46%|████▋     | 16914/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.105.down_proj:  46%|████▋     | 16915/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.106.gate_proj:  46%|████▋     | 16916/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.106.up_proj:  46%|████▋     | 16917/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.106.down_proj:  46%|████▋     | 16918/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.107.gate_proj:  46%|████▋     | 16919/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.107.up_proj:  46%|████▋     | 16920/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.107.down_proj:  46%|████▋     | 16921/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.108.gate_proj:  46%|████▋     | 16922/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.108.up_proj:  46%|████▋     | 16923/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.108.down_proj:  46%|████▋     | 16924/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.109.gate_proj:  46%|████▋     | 16925/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.109.up_proj:  46%|████▋     | 16926/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.109.down_proj:  46%|████▋     | 16927/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.110.gate_proj:  46%|████▋     | 16928/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.110.up_proj:  46%|████▋     | 16929/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.110.down_proj:  46%|████▋     | 16930/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.111.gate_proj:  46%|████▋     | 16931/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.111.up_proj:  46%|████▋     | 16932/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.111.down_proj:  46%|████▋     | 16933/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.112.gate_proj:  46%|████▋     | 16934/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.112.up_proj:  46%|████▋     | 16935/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.112.down_proj:  46%|████▋     | 16936/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.113.gate_proj:  46%|████▋     | 16937/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.113.up_proj:  46%|████▋     | 16938/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.113.down_proj:  46%|████▋     | 16939/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.114.gate_proj:  46%|████▋     | 16940/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.114.up_proj:  46%|████▋     | 16941/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.114.down_proj:  46%|████▋     | 16942/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.115.gate_proj:  46%|████▋     | 16943/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.115.up_proj:  46%|████▋     | 16944/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.115.down_proj:  46%|████▋     | 16945/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.116.gate_proj:  46%|████▋     | 16946/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.116.up_proj:  46%|████▋     | 16947/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.116.down_proj:  46%|████▋     | 16948/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.117.gate_proj:  46%|████▋     | 16949/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.117.up_proj:  46%|████▋     | 16950/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.117.down_proj:  46%|████▋     | 16951/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.118.gate_proj:  46%|████▋     | 16952/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.118.up_proj:  46%|████▋     | 16953/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.118.down_proj:  46%|████▋     | 16954/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.119.gate_proj:  46%|████▋     | 16955/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.119.up_proj:  46%|████▋     | 16956/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.119.down_proj:  46%|████▋     | 16957/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.120.gate_proj:  46%|████▋     | 16958/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.120.up_proj:  46%|████▋     | 16959/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.120.down_proj:  46%|████▋     | 16960/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.121.gate_proj:  46%|████▋     | 16961/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.121.up_proj:  46%|████▋     | 16962/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.121.down_proj:  46%|████▋     | 16963/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.122.gate_proj:  46%|████▋     | 16964/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.122.up_proj:  46%|████▋     | 16965/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.122.down_proj:  46%|████▋     | 16966/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.123.gate_proj:  46%|████▋     | 16967/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.123.up_proj:  46%|████▋     | 16968/36566 [00:15<00:17, 1152.67it/s]  
packing model.layers.42.mlp.experts.123.down_proj:  46%|████▋     | 16969/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.124.gate_proj:  46%|████▋     | 16970/36566 [00:15<00:17, 1152.67it/s]
packing model.layers.42.mlp.experts.124.up_proj:  46%|████▋     | 16971/36566 [00:15<00:16, 1152.67it/s]  
packing model.layers.42.mlp.experts.124.down_proj:  46%|████▋     | 16972/36566 [00:15<00:16, 1152.67it/s]
packing model.layers.42.mlp.experts.125.gate_proj:  46%|████▋     | 16973/36566 [00:15<00:16, 1152.67it/s]
packing model.layers.42.mlp.experts.125.up_proj:  46%|████▋     | 16974/36566 [00:15<00:16, 1152.67it/s]  
packing model.layers.42.mlp.experts.125.down_proj:  46%|████▋     | 16975/36566 [00:15<00:16, 1152.67it/s]
packing model.layers.42.mlp.experts.126.gate_proj:  46%|████▋     | 16976/36566 [00:15<00:16, 1152.67it/s]
packing model.layers.42.mlp.experts.126.up_proj:  46%|████▋     | 16977/36566 [00:15<00:16, 1152.67it/s]  
packing model.layers.42.mlp.experts.126.up_proj:  46%|████▋     | 16978/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.42.mlp.experts.126.down_proj:  46%|████▋     | 16978/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.42.mlp.experts.127.gate_proj:  46%|████▋     | 16979/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.42.mlp.experts.127.up_proj:  46%|████▋     | 16980/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.42.mlp.experts.127.down_proj:  46%|████▋     | 16981/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.0.gate_proj:  46%|████▋     | 16982/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.0.up_proj:  46%|████▋     | 16983/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.0.down_proj:  46%|████▋     | 16984/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.1.gate_proj:  46%|████▋     | 16985/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.1.up_proj:  46%|████▋     | 16986/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.1.down_proj:  46%|████▋     | 16987/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.2.gate_proj:  46%|████▋     | 16988/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.2.up_proj:  46%|████▋     | 16989/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.2.down_proj:  46%|████▋     | 16990/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.3.gate_proj:  46%|████▋     | 16991/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.3.up_proj:  46%|████▋     | 16992/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.3.down_proj:  46%|████▋     | 16993/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.4.gate_proj:  46%|████▋     | 16994/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.4.up_proj:  46%|████▋     | 16995/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.4.down_proj:  46%|████▋     | 16996/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.5.gate_proj:  46%|████▋     | 16997/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.5.up_proj:  46%|████▋     | 16998/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.5.down_proj:  46%|████▋     | 16999/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.6.gate_proj:  46%|████▋     | 17000/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.6.up_proj:  46%|████▋     | 17001/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.6.down_proj:  46%|████▋     | 17002/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.7.gate_proj:  46%|████▋     | 17003/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.7.up_proj:  47%|████▋     | 17004/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.7.down_proj:  47%|████▋     | 17005/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.8.gate_proj:  47%|████▋     | 17006/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.8.up_proj:  47%|████▋     | 17007/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.8.down_proj:  47%|████▋     | 17008/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.9.gate_proj:  47%|████▋     | 17009/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.9.up_proj:  47%|████▋     | 17010/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.9.down_proj:  47%|████▋     | 17011/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.10.gate_proj:  47%|████▋     | 17012/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.10.up_proj:  47%|████▋     | 17013/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.10.down_proj:  47%|████▋     | 17014/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.11.gate_proj:  47%|████▋     | 17015/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.11.up_proj:  47%|████▋     | 17016/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.11.down_proj:  47%|████▋     | 17017/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.12.gate_proj:  47%|████▋     | 17018/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.12.up_proj:  47%|████▋     | 17019/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.12.down_proj:  47%|████▋     | 17020/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.13.gate_proj:  47%|████▋     | 17021/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.13.up_proj:  47%|████▋     | 17022/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.13.down_proj:  47%|████▋     | 17023/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.14.gate_proj:  47%|████▋     | 17024/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.14.up_proj:  47%|████▋     | 17025/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.14.down_proj:  47%|████▋     | 17026/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.15.gate_proj:  47%|████▋     | 17027/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.15.up_proj:  47%|████▋     | 17028/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.15.down_proj:  47%|████▋     | 17029/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.16.gate_proj:  47%|████▋     | 17030/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.16.up_proj:  47%|████▋     | 17031/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.16.down_proj:  47%|████▋     | 17032/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.17.gate_proj:  47%|████▋     | 17033/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.17.up_proj:  47%|████▋     | 17034/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.17.down_proj:  47%|████▋     | 17035/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.18.gate_proj:  47%|████▋     | 17036/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.18.up_proj:  47%|████▋     | 17037/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.18.down_proj:  47%|████▋     | 17038/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.19.gate_proj:  47%|████▋     | 17039/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.19.up_proj:  47%|████▋     | 17040/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.19.down_proj:  47%|████▋     | 17041/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.20.gate_proj:  47%|████▋     | 17042/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.20.up_proj:  47%|████▋     | 17043/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.20.down_proj:  47%|████▋     | 17044/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.21.gate_proj:  47%|████▋     | 17045/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.21.up_proj:  47%|████▋     | 17046/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.21.down_proj:  47%|████▋     | 17047/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.22.gate_proj:  47%|████▋     | 17048/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.22.up_proj:  47%|████▋     | 17049/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.22.down_proj:  47%|████▋     | 17050/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.23.gate_proj:  47%|████▋     | 17051/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.23.up_proj:  47%|████▋     | 17052/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.23.down_proj:  47%|████▋     | 17053/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.24.gate_proj:  47%|████▋     | 17054/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.24.up_proj:  47%|████▋     | 17055/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.24.down_proj:  47%|████▋     | 17056/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.25.gate_proj:  47%|████▋     | 17057/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.25.up_proj:  47%|████▋     | 17058/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.25.down_proj:  47%|████▋     | 17059/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.26.gate_proj:  47%|████▋     | 17060/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.26.up_proj:  47%|████▋     | 17061/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.26.down_proj:  47%|████▋     | 17062/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.27.gate_proj:  47%|████▋     | 17063/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.27.up_proj:  47%|████▋     | 17064/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.27.down_proj:  47%|████▋     | 17065/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.28.gate_proj:  47%|████▋     | 17066/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.28.up_proj:  47%|████▋     | 17067/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.28.down_proj:  47%|████▋     | 17068/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.29.gate_proj:  47%|████▋     | 17069/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.29.up_proj:  47%|████▋     | 17070/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.29.down_proj:  47%|████▋     | 17071/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.30.gate_proj:  47%|████▋     | 17072/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.30.up_proj:  47%|████▋     | 17073/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.30.down_proj:  47%|████▋     | 17074/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.31.gate_proj:  47%|████▋     | 17075/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.31.up_proj:  47%|████▋     | 17076/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.31.down_proj:  47%|████▋     | 17077/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.32.gate_proj:  47%|████▋     | 17078/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.32.up_proj:  47%|████▋     | 17079/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.32.down_proj:  47%|████▋     | 17080/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.33.gate_proj:  47%|████▋     | 17081/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.33.up_proj:  47%|████▋     | 17082/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.33.down_proj:  47%|████▋     | 17083/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.34.gate_proj:  47%|████▋     | 17084/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.34.up_proj:  47%|████▋     | 17085/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.34.down_proj:  47%|████▋     | 17086/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.35.gate_proj:  47%|████▋     | 17087/36566 [00:15<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.35.up_proj:  47%|████▋     | 17088/36566 [00:15<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.35.down_proj:  47%|████▋     | 17089/36566 [00:16<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.36.gate_proj:  47%|████▋     | 17090/36566 [00:16<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.36.up_proj:  47%|████▋     | 17091/36566 [00:16<00:16, 1152.32it/s]  
packing model.layers.43.mlp.experts.36.down_proj:  47%|████▋     | 17092/36566 [00:16<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.37.gate_proj:  47%|████▋     | 17093/36566 [00:16<00:16, 1152.32it/s]
packing model.layers.43.mlp.experts.37.gate_proj:  47%|████▋     | 17094/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.37.up_proj:  47%|████▋     | 17094/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.37.down_proj:  47%|████▋     | 17095/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.38.gate_proj:  47%|████▋     | 17096/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.38.up_proj:  47%|████▋     | 17097/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.38.down_proj:  47%|████▋     | 17098/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.39.gate_proj:  47%|████▋     | 17099/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.39.up_proj:  47%|████▋     | 17100/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.39.down_proj:  47%|████▋     | 17101/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.40.gate_proj:  47%|████▋     | 17102/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.40.up_proj:  47%|████▋     | 17103/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.40.down_proj:  47%|████▋     | 17104/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.41.gate_proj:  47%|████▋     | 17105/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.41.up_proj:  47%|████▋     | 17106/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.41.down_proj:  47%|████▋     | 17107/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.42.gate_proj:  47%|████▋     | 17108/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.42.up_proj:  47%|████▋     | 17109/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.42.down_proj:  47%|████▋     | 17110/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.43.gate_proj:  47%|████▋     | 17111/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.43.up_proj:  47%|████▋     | 17112/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.43.down_proj:  47%|████▋     | 17113/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.44.gate_proj:  47%|████▋     | 17114/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.44.up_proj:  47%|████▋     | 17115/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.44.down_proj:  47%|████▋     | 17116/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.45.gate_proj:  47%|████▋     | 17117/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.45.up_proj:  47%|████▋     | 17118/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.45.down_proj:  47%|████▋     | 17119/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.46.gate_proj:  47%|████▋     | 17120/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.46.up_proj:  47%|████▋     | 17121/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.46.down_proj:  47%|████▋     | 17122/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.47.gate_proj:  47%|████▋     | 17123/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.47.up_proj:  47%|████▋     | 17124/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.47.down_proj:  47%|████▋     | 17125/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.48.gate_proj:  47%|████▋     | 17126/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.48.up_proj:  47%|████▋     | 17127/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.48.down_proj:  47%|████▋     | 17128/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.49.gate_proj:  47%|████▋     | 17129/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.49.up_proj:  47%|████▋     | 17130/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.49.down_proj:  47%|████▋     | 17131/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.50.gate_proj:  47%|████▋     | 17132/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.50.up_proj:  47%|████▋     | 17133/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.50.down_proj:  47%|████▋     | 17134/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.51.gate_proj:  47%|████▋     | 17135/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.51.up_proj:  47%|████▋     | 17136/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.51.down_proj:  47%|████▋     | 17137/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.52.gate_proj:  47%|████▋     | 17138/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.52.up_proj:  47%|████▋     | 17139/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.52.down_proj:  47%|████▋     | 17140/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.53.gate_proj:  47%|████▋     | 17141/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.53.up_proj:  47%|████▋     | 17142/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.53.down_proj:  47%|████▋     | 17143/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.54.gate_proj:  47%|████▋     | 17144/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.54.up_proj:  47%|████▋     | 17145/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.54.down_proj:  47%|████▋     | 17146/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.55.gate_proj:  47%|████▋     | 17147/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.55.up_proj:  47%|████▋     | 17148/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.55.down_proj:  47%|████▋     | 17149/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.56.gate_proj:  47%|████▋     | 17150/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.56.up_proj:  47%|████▋     | 17151/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.56.down_proj:  47%|████▋     | 17152/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.57.gate_proj:  47%|████▋     | 17153/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.57.up_proj:  47%|████▋     | 17154/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.57.down_proj:  47%|████▋     | 17155/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.58.gate_proj:  47%|████▋     | 17156/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.58.up_proj:  47%|████▋     | 17157/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.58.down_proj:  47%|████▋     | 17158/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.59.gate_proj:  47%|████▋     | 17159/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.59.up_proj:  47%|████▋     | 17160/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.59.down_proj:  47%|████▋     | 17161/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.60.gate_proj:  47%|████▋     | 17162/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.60.up_proj:  47%|████▋     | 17163/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.60.down_proj:  47%|████▋     | 17164/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.61.gate_proj:  47%|████▋     | 17165/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.61.up_proj:  47%|████▋     | 17166/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.61.down_proj:  47%|████▋     | 17167/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.62.gate_proj:  47%|████▋     | 17168/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.62.up_proj:  47%|████▋     | 17169/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.62.down_proj:  47%|████▋     | 17170/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.63.gate_proj:  47%|████▋     | 17171/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.63.up_proj:  47%|████▋     | 17172/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.63.down_proj:  47%|████▋     | 17173/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.64.gate_proj:  47%|████▋     | 17174/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.64.up_proj:  47%|████▋     | 17175/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.64.down_proj:  47%|████▋     | 17176/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.65.gate_proj:  47%|████▋     | 17177/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.65.up_proj:  47%|████▋     | 17178/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.65.down_proj:  47%|████▋     | 17179/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.66.gate_proj:  47%|████▋     | 17180/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.66.up_proj:  47%|████▋     | 17181/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.66.down_proj:  47%|████▋     | 17182/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.67.gate_proj:  47%|████▋     | 17183/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.67.up_proj:  47%|████▋     | 17184/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.67.down_proj:  47%|████▋     | 17185/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.68.gate_proj:  47%|████▋     | 17186/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.68.up_proj:  47%|████▋     | 17187/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.68.down_proj:  47%|████▋     | 17188/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.69.gate_proj:  47%|████▋     | 17189/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.69.up_proj:  47%|████▋     | 17190/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.69.down_proj:  47%|████▋     | 17191/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.70.gate_proj:  47%|████▋     | 17192/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.70.up_proj:  47%|████▋     | 17193/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.70.down_proj:  47%|████▋     | 17194/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.71.gate_proj:  47%|████▋     | 17195/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.71.up_proj:  47%|████▋     | 17196/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.71.down_proj:  47%|████▋     | 17197/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.72.gate_proj:  47%|████▋     | 17198/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.72.up_proj:  47%|████▋     | 17199/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.72.down_proj:  47%|████▋     | 17200/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.73.gate_proj:  47%|████▋     | 17201/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.73.up_proj:  47%|████▋     | 17202/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.73.down_proj:  47%|████▋     | 17203/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.74.gate_proj:  47%|████▋     | 17204/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.74.up_proj:  47%|████▋     | 17205/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.74.down_proj:  47%|████▋     | 17206/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.75.gate_proj:  47%|████▋     | 17207/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.75.up_proj:  47%|████▋     | 17208/36566 [00:16<00:16, 1145.66it/s]  
packing model.layers.43.mlp.experts.75.down_proj:  47%|████▋     | 17209/36566 [00:16<00:16, 1145.66it/s]
packing model.layers.43.mlp.experts.75.down_proj:  47%|████▋     | 17210/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.76.gate_proj:  47%|████▋     | 17210/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.76.up_proj:  47%|████▋     | 17211/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.76.down_proj:  47%|████▋     | 17212/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.77.gate_proj:  47%|████▋     | 17213/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.77.up_proj:  47%|████▋     | 17214/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.77.down_proj:  47%|████▋     | 17215/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.78.gate_proj:  47%|████▋     | 17216/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.78.up_proj:  47%|████▋     | 17217/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.78.down_proj:  47%|████▋     | 17218/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.79.gate_proj:  47%|████▋     | 17219/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.79.up_proj:  47%|████▋     | 17220/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.79.down_proj:  47%|████▋     | 17221/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.80.gate_proj:  47%|████▋     | 17222/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.80.up_proj:  47%|████▋     | 17223/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.80.down_proj:  47%|████▋     | 17224/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.81.gate_proj:  47%|████▋     | 17225/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.81.up_proj:  47%|████▋     | 17226/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.81.down_proj:  47%|████▋     | 17227/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.82.gate_proj:  47%|████▋     | 17228/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.82.up_proj:  47%|████▋     | 17229/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.82.down_proj:  47%|████▋     | 17230/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.83.gate_proj:  47%|████▋     | 17231/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.83.up_proj:  47%|████▋     | 17232/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.83.down_proj:  47%|████▋     | 17233/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.84.gate_proj:  47%|████▋     | 17234/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.84.up_proj:  47%|████▋     | 17235/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.84.down_proj:  47%|████▋     | 17236/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.85.gate_proj:  47%|████▋     | 17237/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.85.up_proj:  47%|████▋     | 17238/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.85.down_proj:  47%|████▋     | 17239/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.86.gate_proj:  47%|████▋     | 17240/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.86.up_proj:  47%|████▋     | 17241/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.86.down_proj:  47%|████▋     | 17242/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.87.gate_proj:  47%|████▋     | 17243/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.87.up_proj:  47%|████▋     | 17244/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.87.down_proj:  47%|████▋     | 17245/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.88.gate_proj:  47%|████▋     | 17246/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.88.up_proj:  47%|████▋     | 17247/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.88.down_proj:  47%|████▋     | 17248/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.89.gate_proj:  47%|████▋     | 17249/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.89.up_proj:  47%|████▋     | 17250/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.89.down_proj:  47%|████▋     | 17251/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.90.gate_proj:  47%|████▋     | 17252/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.90.up_proj:  47%|████▋     | 17253/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.90.down_proj:  47%|████▋     | 17254/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.91.gate_proj:  47%|████▋     | 17255/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.91.up_proj:  47%|████▋     | 17256/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.91.down_proj:  47%|████▋     | 17257/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.92.gate_proj:  47%|████▋     | 17258/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.92.up_proj:  47%|████▋     | 17259/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.92.down_proj:  47%|████▋     | 17260/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.93.gate_proj:  47%|████▋     | 17261/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.93.up_proj:  47%|████▋     | 17262/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.93.down_proj:  47%|████▋     | 17263/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.94.gate_proj:  47%|████▋     | 17264/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.94.up_proj:  47%|████▋     | 17265/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.94.down_proj:  47%|████▋     | 17266/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.95.gate_proj:  47%|████▋     | 17267/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.95.up_proj:  47%|████▋     | 17268/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.95.down_proj:  47%|████▋     | 17269/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.96.gate_proj:  47%|████▋     | 17270/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.96.up_proj:  47%|████▋     | 17271/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.96.down_proj:  47%|████▋     | 17272/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.97.gate_proj:  47%|████▋     | 17273/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.97.up_proj:  47%|████▋     | 17274/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.97.down_proj:  47%|████▋     | 17275/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.98.gate_proj:  47%|████▋     | 17276/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.98.up_proj:  47%|████▋     | 17277/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.98.down_proj:  47%|████▋     | 17278/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.99.gate_proj:  47%|████▋     | 17279/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.99.up_proj:  47%|████▋     | 17280/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.99.down_proj:  47%|████▋     | 17281/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.100.gate_proj:  47%|████▋     | 17282/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.100.up_proj:  47%|████▋     | 17283/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.100.down_proj:  47%|████▋     | 17284/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.101.gate_proj:  47%|████▋     | 17285/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.101.up_proj:  47%|████▋     | 17286/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.101.down_proj:  47%|████▋     | 17287/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.102.gate_proj:  47%|████▋     | 17288/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.102.up_proj:  47%|████▋     | 17289/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.102.down_proj:  47%|████▋     | 17290/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.103.gate_proj:  47%|████▋     | 17291/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.103.up_proj:  47%|████▋     | 17292/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.103.down_proj:  47%|████▋     | 17293/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.104.gate_proj:  47%|████▋     | 17294/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.104.up_proj:  47%|████▋     | 17295/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.104.down_proj:  47%|████▋     | 17296/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.105.gate_proj:  47%|████▋     | 17297/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.105.up_proj:  47%|████▋     | 17298/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.105.down_proj:  47%|████▋     | 17299/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.106.gate_proj:  47%|████▋     | 17300/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.106.up_proj:  47%|████▋     | 17301/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.106.down_proj:  47%|████▋     | 17302/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.107.gate_proj:  47%|████▋     | 17303/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.107.up_proj:  47%|████▋     | 17304/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.107.down_proj:  47%|████▋     | 17305/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.108.gate_proj:  47%|████▋     | 17306/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.108.up_proj:  47%|████▋     | 17307/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.108.down_proj:  47%|████▋     | 17308/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.109.gate_proj:  47%|████▋     | 17309/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.109.up_proj:  47%|████▋     | 17310/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.109.down_proj:  47%|████▋     | 17311/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.110.gate_proj:  47%|████▋     | 17312/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.110.up_proj:  47%|████▋     | 17313/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.110.down_proj:  47%|████▋     | 17314/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.111.gate_proj:  47%|████▋     | 17315/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.111.up_proj:  47%|████▋     | 17316/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.111.down_proj:  47%|████▋     | 17317/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.112.gate_proj:  47%|████▋     | 17318/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.112.up_proj:  47%|████▋     | 17319/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.112.down_proj:  47%|████▋     | 17320/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.113.gate_proj:  47%|████▋     | 17321/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.113.up_proj:  47%|████▋     | 17322/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.113.down_proj:  47%|████▋     | 17323/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.114.gate_proj:  47%|████▋     | 17324/36566 [00:16<00:16, 1148.90it/s]
packing model.layers.43.mlp.experts.114.up_proj:  47%|████▋     | 17325/36566 [00:16<00:16, 1148.90it/s]  
packing model.layers.43.mlp.experts.114.up_proj:  47%|████▋     | 17326/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.114.down_proj:  47%|████▋     | 17326/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.115.gate_proj:  47%|████▋     | 17327/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.115.up_proj:  47%|████▋     | 17328/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.115.down_proj:  47%|████▋     | 17329/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.116.gate_proj:  47%|████▋     | 17330/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.116.up_proj:  47%|████▋     | 17331/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.116.down_proj:  47%|████▋     | 17332/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.117.gate_proj:  47%|████▋     | 17333/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.117.up_proj:  47%|████▋     | 17334/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.117.down_proj:  47%|████▋     | 17335/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.118.gate_proj:  47%|████▋     | 17336/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.118.up_proj:  47%|████▋     | 17337/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.118.down_proj:  47%|████▋     | 17338/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.119.gate_proj:  47%|████▋     | 17339/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.119.up_proj:  47%|████▋     | 17340/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.119.down_proj:  47%|████▋     | 17341/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.120.gate_proj:  47%|████▋     | 17342/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.120.up_proj:  47%|████▋     | 17343/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.120.down_proj:  47%|████▋     | 17344/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.121.gate_proj:  47%|████▋     | 17345/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.121.up_proj:  47%|████▋     | 17346/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.121.down_proj:  47%|████▋     | 17347/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.122.gate_proj:  47%|████▋     | 17348/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.122.up_proj:  47%|████▋     | 17349/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.122.down_proj:  47%|████▋     | 17350/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.123.gate_proj:  47%|████▋     | 17351/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.123.up_proj:  47%|████▋     | 17352/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.123.down_proj:  47%|████▋     | 17353/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.124.gate_proj:  47%|████▋     | 17354/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.124.up_proj:  47%|████▋     | 17355/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.124.down_proj:  47%|████▋     | 17356/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.125.gate_proj:  47%|████▋     | 17357/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.125.up_proj:  47%|████▋     | 17358/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.125.down_proj:  47%|████▋     | 17359/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.126.gate_proj:  47%|████▋     | 17360/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.126.up_proj:  47%|████▋     | 17361/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.126.down_proj:  47%|████▋     | 17362/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.127.gate_proj:  47%|████▋     | 17363/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.43.mlp.experts.127.up_proj:  47%|████▋     | 17364/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.43.mlp.experts.127.down_proj:  47%|████▋     | 17365/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.0.gate_proj:  47%|████▋     | 17366/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.0.up_proj:  47%|████▋     | 17367/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.0.down_proj:  47%|████▋     | 17368/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.1.gate_proj:  48%|████▊     | 17369/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.1.up_proj:  48%|████▊     | 17370/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.1.down_proj:  48%|████▊     | 17371/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.2.gate_proj:  48%|████▊     | 17372/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.2.up_proj:  48%|████▊     | 17373/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.2.down_proj:  48%|████▊     | 17374/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.3.gate_proj:  48%|████▊     | 17375/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.3.up_proj:  48%|████▊     | 17376/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.3.down_proj:  48%|████▊     | 17377/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.4.gate_proj:  48%|████▊     | 17378/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.4.up_proj:  48%|████▊     | 17379/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.4.down_proj:  48%|████▊     | 17380/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.5.gate_proj:  48%|████▊     | 17381/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.5.up_proj:  48%|████▊     | 17382/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.5.down_proj:  48%|████▊     | 17383/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.6.gate_proj:  48%|████▊     | 17384/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.6.up_proj:  48%|████▊     | 17385/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.6.down_proj:  48%|████▊     | 17386/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.7.gate_proj:  48%|████▊     | 17387/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.7.up_proj:  48%|████▊     | 17388/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.7.down_proj:  48%|████▊     | 17389/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.8.gate_proj:  48%|████▊     | 17390/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.8.up_proj:  48%|████▊     | 17391/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.8.down_proj:  48%|████▊     | 17392/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.9.gate_proj:  48%|████▊     | 17393/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.9.up_proj:  48%|████▊     | 17394/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.9.down_proj:  48%|████▊     | 17395/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.10.gate_proj:  48%|████▊     | 17396/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.10.up_proj:  48%|████▊     | 17397/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.10.down_proj:  48%|████▊     | 17398/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.11.gate_proj:  48%|████▊     | 17399/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.11.up_proj:  48%|████▊     | 17400/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.11.down_proj:  48%|████▊     | 17401/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.12.gate_proj:  48%|████▊     | 17402/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.12.up_proj:  48%|████▊     | 17403/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.12.down_proj:  48%|████▊     | 17404/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.13.gate_proj:  48%|████▊     | 17405/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.13.up_proj:  48%|████▊     | 17406/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.13.down_proj:  48%|████▊     | 17407/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.14.gate_proj:  48%|████▊     | 17408/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.14.up_proj:  48%|████▊     | 17409/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.14.down_proj:  48%|████▊     | 17410/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.15.gate_proj:  48%|████▊     | 17411/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.15.up_proj:  48%|████▊     | 17412/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.15.down_proj:  48%|████▊     | 17413/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.16.gate_proj:  48%|████▊     | 17414/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.16.up_proj:  48%|████▊     | 17415/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.16.down_proj:  48%|████▊     | 17416/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.17.gate_proj:  48%|████▊     | 17417/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.17.up_proj:  48%|████▊     | 17418/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.17.down_proj:  48%|████▊     | 17419/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.18.gate_proj:  48%|████▊     | 17420/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.18.up_proj:  48%|████▊     | 17421/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.18.down_proj:  48%|████▊     | 17422/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.19.gate_proj:  48%|████▊     | 17423/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.19.up_proj:  48%|████▊     | 17424/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.19.down_proj:  48%|████▊     | 17425/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.20.gate_proj:  48%|████▊     | 17426/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.20.up_proj:  48%|████▊     | 17427/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.20.down_proj:  48%|████▊     | 17428/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.21.gate_proj:  48%|████▊     | 17429/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.21.up_proj:  48%|████▊     | 17430/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.21.down_proj:  48%|████▊     | 17431/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.22.gate_proj:  48%|████▊     | 17432/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.22.up_proj:  48%|████▊     | 17433/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.22.down_proj:  48%|████▊     | 17434/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.23.gate_proj:  48%|████▊     | 17435/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.23.up_proj:  48%|████▊     | 17436/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.23.down_proj:  48%|████▊     | 17437/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.24.gate_proj:  48%|████▊     | 17438/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.24.up_proj:  48%|████▊     | 17439/36566 [00:16<00:16, 1151.06it/s]  
packing model.layers.44.mlp.experts.24.down_proj:  48%|████▊     | 17440/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.25.gate_proj:  48%|████▊     | 17441/36566 [00:16<00:16, 1151.06it/s]
packing model.layers.44.mlp.experts.25.gate_proj:  48%|████▊     | 17442/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.25.up_proj:  48%|████▊     | 17442/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.25.down_proj:  48%|████▊     | 17443/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.26.gate_proj:  48%|████▊     | 17444/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.26.up_proj:  48%|████▊     | 17445/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.26.down_proj:  48%|████▊     | 17446/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.27.gate_proj:  48%|████▊     | 17447/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.27.up_proj:  48%|████▊     | 17448/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.27.down_proj:  48%|████▊     | 17449/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.28.gate_proj:  48%|████▊     | 17450/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.28.up_proj:  48%|████▊     | 17451/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.28.down_proj:  48%|████▊     | 17452/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.29.gate_proj:  48%|████▊     | 17453/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.29.up_proj:  48%|████▊     | 17454/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.29.down_proj:  48%|████▊     | 17455/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.30.gate_proj:  48%|████▊     | 17456/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.30.up_proj:  48%|████▊     | 17457/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.30.down_proj:  48%|████▊     | 17458/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.31.gate_proj:  48%|████▊     | 17459/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.31.up_proj:  48%|████▊     | 17460/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.31.down_proj:  48%|████▊     | 17461/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.32.gate_proj:  48%|████▊     | 17462/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.32.up_proj:  48%|████▊     | 17463/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.32.down_proj:  48%|████▊     | 17464/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.33.gate_proj:  48%|████▊     | 17465/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.33.up_proj:  48%|████▊     | 17466/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.33.down_proj:  48%|████▊     | 17467/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.34.gate_proj:  48%|████▊     | 17468/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.34.up_proj:  48%|████▊     | 17469/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.34.down_proj:  48%|████▊     | 17470/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.35.gate_proj:  48%|████▊     | 17471/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.35.up_proj:  48%|████▊     | 17472/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.35.down_proj:  48%|████▊     | 17473/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.36.gate_proj:  48%|████▊     | 17474/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.36.up_proj:  48%|████▊     | 17475/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.36.down_proj:  48%|████▊     | 17476/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.37.gate_proj:  48%|████▊     | 17477/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.37.up_proj:  48%|████▊     | 17478/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.37.down_proj:  48%|████▊     | 17479/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.38.gate_proj:  48%|████▊     | 17480/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.38.up_proj:  48%|████▊     | 17481/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.38.down_proj:  48%|████▊     | 17482/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.39.gate_proj:  48%|████▊     | 17483/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.39.up_proj:  48%|████▊     | 17484/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.39.down_proj:  48%|████▊     | 17485/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.40.gate_proj:  48%|████▊     | 17486/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.40.up_proj:  48%|████▊     | 17487/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.40.down_proj:  48%|████▊     | 17488/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.41.gate_proj:  48%|████▊     | 17489/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.41.up_proj:  48%|████▊     | 17490/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.41.down_proj:  48%|████▊     | 17491/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.42.gate_proj:  48%|████▊     | 17492/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.42.up_proj:  48%|████▊     | 17493/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.42.down_proj:  48%|████▊     | 17494/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.43.gate_proj:  48%|████▊     | 17495/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.43.up_proj:  48%|████▊     | 17496/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.43.down_proj:  48%|████▊     | 17497/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.44.gate_proj:  48%|████▊     | 17498/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.44.up_proj:  48%|████▊     | 17499/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.44.down_proj:  48%|████▊     | 17500/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.45.gate_proj:  48%|████▊     | 17501/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.45.up_proj:  48%|████▊     | 17502/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.45.down_proj:  48%|████▊     | 17503/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.46.gate_proj:  48%|████▊     | 17504/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.46.up_proj:  48%|████▊     | 17505/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.46.down_proj:  48%|████▊     | 17506/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.47.gate_proj:  48%|████▊     | 17507/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.47.up_proj:  48%|████▊     | 17508/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.47.down_proj:  48%|████▊     | 17509/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.48.gate_proj:  48%|████▊     | 17510/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.48.up_proj:  48%|████▊     | 17511/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.48.down_proj:  48%|████▊     | 17512/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.49.gate_proj:  48%|████▊     | 17513/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.49.up_proj:  48%|████▊     | 17514/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.49.down_proj:  48%|████▊     | 17515/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.50.gate_proj:  48%|████▊     | 17516/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.50.up_proj:  48%|████▊     | 17517/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.50.down_proj:  48%|████▊     | 17518/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.51.gate_proj:  48%|████▊     | 17519/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.51.up_proj:  48%|████▊     | 17520/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.51.down_proj:  48%|████▊     | 17521/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.52.gate_proj:  48%|████▊     | 17522/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.52.up_proj:  48%|████▊     | 17523/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.52.down_proj:  48%|████▊     | 17524/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.53.gate_proj:  48%|████▊     | 17525/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.53.up_proj:  48%|████▊     | 17526/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.53.down_proj:  48%|████▊     | 17527/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.54.gate_proj:  48%|████▊     | 17528/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.54.up_proj:  48%|████▊     | 17529/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.54.down_proj:  48%|████▊     | 17530/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.55.gate_proj:  48%|████▊     | 17531/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.55.up_proj:  48%|████▊     | 17532/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.55.down_proj:  48%|████▊     | 17533/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.56.gate_proj:  48%|████▊     | 17534/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.56.up_proj:  48%|████▊     | 17535/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.56.down_proj:  48%|████▊     | 17536/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.57.gate_proj:  48%|████▊     | 17537/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.57.up_proj:  48%|████▊     | 17538/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.57.down_proj:  48%|████▊     | 17539/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.58.gate_proj:  48%|████▊     | 17540/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.58.up_proj:  48%|████▊     | 17541/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.58.down_proj:  48%|████▊     | 17542/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.59.gate_proj:  48%|████▊     | 17543/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.59.up_proj:  48%|████▊     | 17544/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.59.down_proj:  48%|████▊     | 17545/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.60.gate_proj:  48%|████▊     | 17546/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.60.up_proj:  48%|████▊     | 17547/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.60.down_proj:  48%|████▊     | 17548/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.61.gate_proj:  48%|████▊     | 17549/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.61.up_proj:  48%|████▊     | 17550/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.61.down_proj:  48%|████▊     | 17551/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.62.gate_proj:  48%|████▊     | 17552/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.62.up_proj:  48%|████▊     | 17553/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.62.down_proj:  48%|████▊     | 17554/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.63.gate_proj:  48%|████▊     | 17555/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.63.up_proj:  48%|████▊     | 17556/36566 [00:16<00:16, 1152.20it/s]  
packing model.layers.44.mlp.experts.63.down_proj:  48%|████▊     | 17557/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.64.gate_proj:  48%|████▊     | 17558/36566 [00:16<00:16, 1152.20it/s]
packing model.layers.44.mlp.experts.64.gate_proj:  48%|████▊     | 17559/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.64.up_proj:  48%|████▊     | 17559/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.64.down_proj:  48%|████▊     | 17560/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.65.gate_proj:  48%|████▊     | 17561/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.65.up_proj:  48%|████▊     | 17562/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.65.down_proj:  48%|████▊     | 17563/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.66.gate_proj:  48%|████▊     | 17564/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.66.up_proj:  48%|████▊     | 17565/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.66.down_proj:  48%|████▊     | 17566/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.67.gate_proj:  48%|████▊     | 17567/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.67.up_proj:  48%|████▊     | 17568/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.67.down_proj:  48%|████▊     | 17569/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.68.gate_proj:  48%|████▊     | 17570/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.68.up_proj:  48%|████▊     | 17571/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.68.down_proj:  48%|████▊     | 17572/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.69.gate_proj:  48%|████▊     | 17573/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.69.up_proj:  48%|████▊     | 17574/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.69.down_proj:  48%|████▊     | 17575/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.70.gate_proj:  48%|████▊     | 17576/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.70.up_proj:  48%|████▊     | 17577/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.70.down_proj:  48%|████▊     | 17578/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.71.gate_proj:  48%|████▊     | 17579/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.71.up_proj:  48%|████▊     | 17580/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.71.down_proj:  48%|████▊     | 17581/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.72.gate_proj:  48%|████▊     | 17582/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.72.up_proj:  48%|████▊     | 17583/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.72.down_proj:  48%|████▊     | 17584/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.73.gate_proj:  48%|████▊     | 17585/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.73.up_proj:  48%|████▊     | 17586/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.73.down_proj:  48%|████▊     | 17587/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.74.gate_proj:  48%|████▊     | 17588/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.74.up_proj:  48%|████▊     | 17589/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.74.down_proj:  48%|████▊     | 17590/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.75.gate_proj:  48%|████▊     | 17591/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.75.up_proj:  48%|████▊     | 17592/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.75.down_proj:  48%|████▊     | 17593/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.76.gate_proj:  48%|████▊     | 17594/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.76.up_proj:  48%|████▊     | 17595/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.76.down_proj:  48%|████▊     | 17596/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.77.gate_proj:  48%|████▊     | 17597/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.77.up_proj:  48%|████▊     | 17598/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.77.down_proj:  48%|████▊     | 17599/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.78.gate_proj:  48%|████▊     | 17600/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.78.up_proj:  48%|████▊     | 17601/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.78.down_proj:  48%|████▊     | 17602/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.79.gate_proj:  48%|████▊     | 17603/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.79.up_proj:  48%|████▊     | 17604/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.79.down_proj:  48%|████▊     | 17605/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.80.gate_proj:  48%|████▊     | 17606/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.80.up_proj:  48%|████▊     | 17607/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.80.down_proj:  48%|████▊     | 17608/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.81.gate_proj:  48%|████▊     | 17609/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.81.up_proj:  48%|████▊     | 17610/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.81.down_proj:  48%|████▊     | 17611/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.82.gate_proj:  48%|████▊     | 17612/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.82.up_proj:  48%|████▊     | 17613/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.82.down_proj:  48%|████▊     | 17614/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.83.gate_proj:  48%|████▊     | 17615/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.83.up_proj:  48%|████▊     | 17616/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.83.down_proj:  48%|████▊     | 17617/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.84.gate_proj:  48%|████▊     | 17618/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.84.up_proj:  48%|████▊     | 17619/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.84.down_proj:  48%|████▊     | 17620/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.85.gate_proj:  48%|████▊     | 17621/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.85.up_proj:  48%|████▊     | 17622/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.85.down_proj:  48%|████▊     | 17623/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.86.gate_proj:  48%|████▊     | 17624/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.86.up_proj:  48%|████▊     | 17625/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.86.down_proj:  48%|████▊     | 17626/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.87.gate_proj:  48%|████▊     | 17627/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.87.up_proj:  48%|████▊     | 17628/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.87.down_proj:  48%|████▊     | 17629/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.88.gate_proj:  48%|████▊     | 17630/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.88.up_proj:  48%|████▊     | 17631/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.88.down_proj:  48%|████▊     | 17632/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.89.gate_proj:  48%|████▊     | 17633/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.89.up_proj:  48%|████▊     | 17634/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.89.down_proj:  48%|████▊     | 17635/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.90.gate_proj:  48%|████▊     | 17636/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.90.up_proj:  48%|████▊     | 17637/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.90.down_proj:  48%|████▊     | 17638/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.91.gate_proj:  48%|████▊     | 17639/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.91.up_proj:  48%|████▊     | 17640/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.91.down_proj:  48%|████▊     | 17641/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.92.gate_proj:  48%|████▊     | 17642/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.92.up_proj:  48%|████▊     | 17643/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.92.down_proj:  48%|████▊     | 17644/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.93.gate_proj:  48%|████▊     | 17645/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.93.up_proj:  48%|████▊     | 17646/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.93.down_proj:  48%|████▊     | 17647/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.94.gate_proj:  48%|████▊     | 17648/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.94.up_proj:  48%|████▊     | 17649/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.94.down_proj:  48%|████▊     | 17650/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.95.gate_proj:  48%|████▊     | 17651/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.95.up_proj:  48%|████▊     | 17652/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.95.down_proj:  48%|████▊     | 17653/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.96.gate_proj:  48%|████▊     | 17654/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.96.up_proj:  48%|████▊     | 17655/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.96.down_proj:  48%|████▊     | 17656/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.97.gate_proj:  48%|████▊     | 17657/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.97.up_proj:  48%|████▊     | 17658/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.97.down_proj:  48%|████▊     | 17659/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.98.gate_proj:  48%|████▊     | 17660/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.98.up_proj:  48%|████▊     | 17661/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.98.down_proj:  48%|████▊     | 17662/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.99.gate_proj:  48%|████▊     | 17663/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.99.up_proj:  48%|████▊     | 17664/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.99.down_proj:  48%|████▊     | 17665/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.100.gate_proj:  48%|████▊     | 17666/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.100.up_proj:  48%|████▊     | 17667/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.100.down_proj:  48%|████▊     | 17668/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.101.gate_proj:  48%|████▊     | 17669/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.101.up_proj:  48%|████▊     | 17670/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.101.down_proj:  48%|████▊     | 17671/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.102.gate_proj:  48%|████▊     | 17672/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.102.up_proj:  48%|████▊     | 17673/36566 [00:16<00:16, 1154.82it/s]  
packing model.layers.44.mlp.experts.102.down_proj:  48%|████▊     | 17674/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.103.gate_proj:  48%|████▊     | 17675/36566 [00:16<00:16, 1154.82it/s]
packing model.layers.44.mlp.experts.103.gate_proj:  48%|████▊     | 17676/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.103.up_proj:  48%|████▊     | 17676/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.103.down_proj:  48%|████▊     | 17677/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.104.gate_proj:  48%|████▊     | 17678/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.104.up_proj:  48%|████▊     | 17679/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.104.down_proj:  48%|████▊     | 17680/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.105.gate_proj:  48%|████▊     | 17681/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.105.up_proj:  48%|████▊     | 17682/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.105.down_proj:  48%|████▊     | 17683/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.106.gate_proj:  48%|████▊     | 17684/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.106.up_proj:  48%|████▊     | 17685/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.106.down_proj:  48%|████▊     | 17686/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.107.gate_proj:  48%|████▊     | 17687/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.107.up_proj:  48%|████▊     | 17688/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.107.down_proj:  48%|████▊     | 17689/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.108.gate_proj:  48%|████▊     | 17690/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.108.up_proj:  48%|████▊     | 17691/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.108.down_proj:  48%|████▊     | 17692/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.109.gate_proj:  48%|████▊     | 17693/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.109.up_proj:  48%|████▊     | 17694/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.109.down_proj:  48%|████▊     | 17695/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.110.gate_proj:  48%|████▊     | 17696/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.110.up_proj:  48%|████▊     | 17697/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.110.down_proj:  48%|████▊     | 17698/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.111.gate_proj:  48%|████▊     | 17699/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.111.up_proj:  48%|████▊     | 17700/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.111.down_proj:  48%|████▊     | 17701/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.112.gate_proj:  48%|████▊     | 17702/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.112.up_proj:  48%|████▊     | 17703/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.112.down_proj:  48%|████▊     | 17704/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.113.gate_proj:  48%|████▊     | 17705/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.113.up_proj:  48%|████▊     | 17706/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.113.down_proj:  48%|████▊     | 17707/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.114.gate_proj:  48%|████▊     | 17708/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.114.up_proj:  48%|████▊     | 17709/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.114.down_proj:  48%|████▊     | 17710/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.115.gate_proj:  48%|████▊     | 17711/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.115.up_proj:  48%|████▊     | 17712/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.115.down_proj:  48%|████▊     | 17713/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.116.gate_proj:  48%|████▊     | 17714/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.116.up_proj:  48%|████▊     | 17715/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.116.down_proj:  48%|████▊     | 17716/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.117.gate_proj:  48%|████▊     | 17717/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.117.up_proj:  48%|████▊     | 17718/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.117.down_proj:  48%|████▊     | 17719/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.118.gate_proj:  48%|████▊     | 17720/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.118.up_proj:  48%|████▊     | 17721/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.118.down_proj:  48%|████▊     | 17722/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.119.gate_proj:  48%|████▊     | 17723/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.119.up_proj:  48%|████▊     | 17724/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.119.down_proj:  48%|████▊     | 17725/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.120.gate_proj:  48%|████▊     | 17726/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.120.up_proj:  48%|████▊     | 17727/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.120.down_proj:  48%|████▊     | 17728/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.121.gate_proj:  48%|████▊     | 17729/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.121.up_proj:  48%|████▊     | 17730/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.121.down_proj:  48%|████▊     | 17731/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.122.gate_proj:  48%|████▊     | 17732/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.122.up_proj:  48%|████▊     | 17733/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.122.down_proj:  48%|████▊     | 17734/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.123.gate_proj:  49%|████▊     | 17735/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.123.up_proj:  49%|████▊     | 17736/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.123.down_proj:  49%|████▊     | 17737/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.124.gate_proj:  49%|████▊     | 17738/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.124.up_proj:  49%|████▊     | 17739/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.124.down_proj:  49%|████▊     | 17740/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.125.gate_proj:  49%|████▊     | 17741/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.125.up_proj:  49%|████▊     | 17742/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.125.down_proj:  49%|████▊     | 17743/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.126.gate_proj:  49%|████▊     | 17744/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.126.up_proj:  49%|████▊     | 17745/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.126.down_proj:  49%|████▊     | 17746/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.127.gate_proj:  49%|████▊     | 17747/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.44.mlp.experts.127.up_proj:  49%|████▊     | 17748/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.44.mlp.experts.127.down_proj:  49%|████▊     | 17749/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.0.gate_proj:  49%|████▊     | 17750/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.0.up_proj:  49%|████▊     | 17751/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.0.down_proj:  49%|████▊     | 17752/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.1.gate_proj:  49%|████▊     | 17753/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.1.up_proj:  49%|████▊     | 17754/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.1.down_proj:  49%|████▊     | 17755/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.2.gate_proj:  49%|████▊     | 17756/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.2.up_proj:  49%|████▊     | 17757/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.2.down_proj:  49%|████▊     | 17758/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.3.gate_proj:  49%|████▊     | 17759/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.3.up_proj:  49%|████▊     | 17760/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.3.down_proj:  49%|████▊     | 17761/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.4.gate_proj:  49%|████▊     | 17762/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.4.up_proj:  49%|████▊     | 17763/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.4.down_proj:  49%|████▊     | 17764/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.5.gate_proj:  49%|████▊     | 17765/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.5.up_proj:  49%|████▊     | 17766/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.5.down_proj:  49%|████▊     | 17767/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.6.gate_proj:  49%|████▊     | 17768/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.6.up_proj:  49%|████▊     | 17769/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.6.down_proj:  49%|████▊     | 17770/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.7.gate_proj:  49%|████▊     | 17771/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.7.up_proj:  49%|████▊     | 17772/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.7.down_proj:  49%|████▊     | 17773/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.8.gate_proj:  49%|████▊     | 17774/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.8.up_proj:  49%|████▊     | 17775/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.8.down_proj:  49%|████▊     | 17776/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.9.gate_proj:  49%|████▊     | 17777/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.9.up_proj:  49%|████▊     | 17778/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.9.down_proj:  49%|████▊     | 17779/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.10.gate_proj:  49%|████▊     | 17780/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.10.up_proj:  49%|████▊     | 17781/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.10.down_proj:  49%|████▊     | 17782/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.11.gate_proj:  49%|████▊     | 17783/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.11.up_proj:  49%|████▊     | 17784/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.11.down_proj:  49%|████▊     | 17785/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.12.gate_proj:  49%|████▊     | 17786/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.12.up_proj:  49%|████▊     | 17787/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.12.down_proj:  49%|████▊     | 17788/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.13.gate_proj:  49%|████▊     | 17789/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.13.up_proj:  49%|████▊     | 17790/36566 [00:16<00:16, 1157.77it/s]  
packing model.layers.45.mlp.experts.13.down_proj:  49%|████▊     | 17791/36566 [00:16<00:16, 1157.77it/s]
packing model.layers.45.mlp.experts.13.down_proj:  49%|████▊     | 17792/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.14.gate_proj:  49%|████▊     | 17792/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.14.up_proj:  49%|████▊     | 17793/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.14.down_proj:  49%|████▊     | 17794/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.15.gate_proj:  49%|████▊     | 17795/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.15.up_proj:  49%|████▊     | 17796/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.15.down_proj:  49%|████▊     | 17797/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.16.gate_proj:  49%|████▊     | 17798/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.16.up_proj:  49%|████▊     | 17799/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.16.down_proj:  49%|████▊     | 17800/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.17.gate_proj:  49%|████▊     | 17801/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.17.up_proj:  49%|████▊     | 17802/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.17.down_proj:  49%|████▊     | 17803/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.18.gate_proj:  49%|████▊     | 17804/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.18.up_proj:  49%|████▊     | 17805/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.18.down_proj:  49%|████▊     | 17806/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.19.gate_proj:  49%|████▊     | 17807/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.19.up_proj:  49%|████▊     | 17808/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.19.down_proj:  49%|████▊     | 17809/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.20.gate_proj:  49%|████▊     | 17810/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.20.up_proj:  49%|████▊     | 17811/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.20.down_proj:  49%|████▊     | 17812/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.21.gate_proj:  49%|████▊     | 17813/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.21.up_proj:  49%|████▊     | 17814/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.21.down_proj:  49%|████▊     | 17815/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.22.gate_proj:  49%|████▊     | 17816/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.22.up_proj:  49%|████▊     | 17817/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.22.down_proj:  49%|████▊     | 17818/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.23.gate_proj:  49%|████▊     | 17819/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.23.up_proj:  49%|████▊     | 17820/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.23.down_proj:  49%|████▊     | 17821/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.24.gate_proj:  49%|████▊     | 17822/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.24.up_proj:  49%|████▊     | 17823/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.24.down_proj:  49%|████▊     | 17824/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.25.gate_proj:  49%|████▊     | 17825/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.25.up_proj:  49%|████▉     | 17826/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.25.down_proj:  49%|████▉     | 17827/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.26.gate_proj:  49%|████▉     | 17828/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.26.up_proj:  49%|████▉     | 17829/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.26.down_proj:  49%|████▉     | 17830/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.27.gate_proj:  49%|████▉     | 17831/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.27.up_proj:  49%|████▉     | 17832/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.27.down_proj:  49%|████▉     | 17833/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.28.gate_proj:  49%|████▉     | 17834/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.28.up_proj:  49%|████▉     | 17835/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.28.down_proj:  49%|████▉     | 17836/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.29.gate_proj:  49%|████▉     | 17837/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.29.up_proj:  49%|████▉     | 17838/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.29.down_proj:  49%|████▉     | 17839/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.30.gate_proj:  49%|████▉     | 17840/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.30.up_proj:  49%|████▉     | 17841/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.30.down_proj:  49%|████▉     | 17842/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.31.gate_proj:  49%|████▉     | 17843/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.31.up_proj:  49%|████▉     | 17844/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.31.down_proj:  49%|████▉     | 17845/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.32.gate_proj:  49%|████▉     | 17846/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.32.up_proj:  49%|████▉     | 17847/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.32.down_proj:  49%|████▉     | 17848/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.33.gate_proj:  49%|████▉     | 17849/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.33.up_proj:  49%|████▉     | 17850/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.33.down_proj:  49%|████▉     | 17851/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.34.gate_proj:  49%|████▉     | 17852/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.34.up_proj:  49%|████▉     | 17853/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.34.down_proj:  49%|████▉     | 17854/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.35.gate_proj:  49%|████▉     | 17855/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.35.up_proj:  49%|████▉     | 17856/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.35.down_proj:  49%|████▉     | 17857/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.36.gate_proj:  49%|████▉     | 17858/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.36.up_proj:  49%|████▉     | 17859/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.36.down_proj:  49%|████▉     | 17860/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.37.gate_proj:  49%|████▉     | 17861/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.37.up_proj:  49%|████▉     | 17862/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.37.down_proj:  49%|████▉     | 17863/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.38.gate_proj:  49%|████▉     | 17864/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.38.up_proj:  49%|████▉     | 17865/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.38.down_proj:  49%|████▉     | 17866/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.39.gate_proj:  49%|████▉     | 17867/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.39.up_proj:  49%|████▉     | 17868/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.39.down_proj:  49%|████▉     | 17869/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.40.gate_proj:  49%|████▉     | 17870/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.40.up_proj:  49%|████▉     | 17871/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.40.down_proj:  49%|████▉     | 17872/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.41.gate_proj:  49%|████▉     | 17873/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.41.up_proj:  49%|████▉     | 17874/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.41.down_proj:  49%|████▉     | 17875/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.42.gate_proj:  49%|████▉     | 17876/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.42.up_proj:  49%|████▉     | 17877/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.42.down_proj:  49%|████▉     | 17878/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.43.gate_proj:  49%|████▉     | 17879/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.43.up_proj:  49%|████▉     | 17880/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.43.down_proj:  49%|████▉     | 17881/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.44.gate_proj:  49%|████▉     | 17882/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.44.up_proj:  49%|████▉     | 17883/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.44.down_proj:  49%|████▉     | 17884/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.45.gate_proj:  49%|████▉     | 17885/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.45.up_proj:  49%|████▉     | 17886/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.45.down_proj:  49%|████▉     | 17887/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.46.gate_proj:  49%|████▉     | 17888/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.46.up_proj:  49%|████▉     | 17889/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.46.down_proj:  49%|████▉     | 17890/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.47.gate_proj:  49%|████▉     | 17891/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.47.up_proj:  49%|████▉     | 17892/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.47.down_proj:  49%|████▉     | 17893/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.48.gate_proj:  49%|████▉     | 17894/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.48.up_proj:  49%|████▉     | 17895/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.48.down_proj:  49%|████▉     | 17896/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.49.gate_proj:  49%|████▉     | 17897/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.49.up_proj:  49%|████▉     | 17898/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.49.down_proj:  49%|████▉     | 17899/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.50.gate_proj:  49%|████▉     | 17900/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.50.up_proj:  49%|████▉     | 17901/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.50.down_proj:  49%|████▉     | 17902/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.51.gate_proj:  49%|████▉     | 17903/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.51.up_proj:  49%|████▉     | 17904/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.51.down_proj:  49%|████▉     | 17905/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.52.gate_proj:  49%|████▉     | 17906/36566 [00:16<00:16, 1157.53it/s]
packing model.layers.45.mlp.experts.52.up_proj:  49%|████▉     | 17907/36566 [00:16<00:16, 1157.53it/s]  
packing model.layers.45.mlp.experts.52.up_proj:  49%|████▉     | 17908/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.52.down_proj:  49%|████▉     | 17908/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.53.gate_proj:  49%|████▉     | 17909/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.53.up_proj:  49%|████▉     | 17910/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.53.down_proj:  49%|████▉     | 17911/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.54.gate_proj:  49%|████▉     | 17912/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.54.up_proj:  49%|████▉     | 17913/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.54.down_proj:  49%|████▉     | 17914/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.55.gate_proj:  49%|████▉     | 17915/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.55.up_proj:  49%|████▉     | 17916/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.55.down_proj:  49%|████▉     | 17917/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.56.gate_proj:  49%|████▉     | 17918/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.56.up_proj:  49%|████▉     | 17919/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.56.down_proj:  49%|████▉     | 17920/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.57.gate_proj:  49%|████▉     | 17921/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.57.up_proj:  49%|████▉     | 17922/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.57.down_proj:  49%|████▉     | 17923/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.58.gate_proj:  49%|████▉     | 17924/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.58.up_proj:  49%|████▉     | 17925/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.58.down_proj:  49%|████▉     | 17926/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.59.gate_proj:  49%|████▉     | 17927/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.59.up_proj:  49%|████▉     | 17928/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.59.down_proj:  49%|████▉     | 17929/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.60.gate_proj:  49%|████▉     | 17930/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.60.up_proj:  49%|████▉     | 17931/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.60.down_proj:  49%|████▉     | 17932/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.61.gate_proj:  49%|████▉     | 17933/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.61.up_proj:  49%|████▉     | 17934/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.61.down_proj:  49%|████▉     | 17935/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.62.gate_proj:  49%|████▉     | 17936/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.62.up_proj:  49%|████▉     | 17937/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.62.down_proj:  49%|████▉     | 17938/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.63.gate_proj:  49%|████▉     | 17939/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.63.up_proj:  49%|████▉     | 17940/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.63.down_proj:  49%|████▉     | 17941/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.64.gate_proj:  49%|████▉     | 17942/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.64.up_proj:  49%|████▉     | 17943/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.64.down_proj:  49%|████▉     | 17944/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.65.gate_proj:  49%|████▉     | 17945/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.65.up_proj:  49%|████▉     | 17946/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.65.down_proj:  49%|████▉     | 17947/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.66.gate_proj:  49%|████▉     | 17948/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.66.up_proj:  49%|████▉     | 17949/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.66.down_proj:  49%|████▉     | 17950/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.67.gate_proj:  49%|████▉     | 17951/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.67.up_proj:  49%|████▉     | 17952/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.67.down_proj:  49%|████▉     | 17953/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.68.gate_proj:  49%|████▉     | 17954/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.68.up_proj:  49%|████▉     | 17955/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.68.down_proj:  49%|████▉     | 17956/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.69.gate_proj:  49%|████▉     | 17957/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.69.up_proj:  49%|████▉     | 17958/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.69.down_proj:  49%|████▉     | 17959/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.70.gate_proj:  49%|████▉     | 17960/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.70.up_proj:  49%|████▉     | 17961/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.70.down_proj:  49%|████▉     | 17962/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.71.gate_proj:  49%|████▉     | 17963/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.71.up_proj:  49%|████▉     | 17964/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.71.down_proj:  49%|████▉     | 17965/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.72.gate_proj:  49%|████▉     | 17966/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.72.up_proj:  49%|████▉     | 17967/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.72.down_proj:  49%|████▉     | 17968/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.73.gate_proj:  49%|████▉     | 17969/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.73.up_proj:  49%|████▉     | 17970/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.73.down_proj:  49%|████▉     | 17971/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.74.gate_proj:  49%|████▉     | 17972/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.74.up_proj:  49%|████▉     | 17973/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.74.down_proj:  49%|████▉     | 17974/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.75.gate_proj:  49%|████▉     | 17975/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.75.up_proj:  49%|████▉     | 17976/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.75.down_proj:  49%|████▉     | 17977/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.76.gate_proj:  49%|████▉     | 17978/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.76.up_proj:  49%|████▉     | 17979/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.76.down_proj:  49%|████▉     | 17980/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.77.gate_proj:  49%|████▉     | 17981/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.77.up_proj:  49%|████▉     | 17982/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.77.down_proj:  49%|████▉     | 17983/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.78.gate_proj:  49%|████▉     | 17984/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.78.up_proj:  49%|████▉     | 17985/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.78.down_proj:  49%|████▉     | 17986/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.79.gate_proj:  49%|████▉     | 17987/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.79.up_proj:  49%|████▉     | 17988/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.79.down_proj:  49%|████▉     | 17989/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.80.gate_proj:  49%|████▉     | 17990/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.80.up_proj:  49%|████▉     | 17991/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.80.down_proj:  49%|████▉     | 17992/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.81.gate_proj:  49%|████▉     | 17993/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.81.up_proj:  49%|████▉     | 17994/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.81.down_proj:  49%|████▉     | 17995/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.82.gate_proj:  49%|████▉     | 17996/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.82.up_proj:  49%|████▉     | 17997/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.82.down_proj:  49%|████▉     | 17998/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.83.gate_proj:  49%|████▉     | 17999/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.83.up_proj:  49%|████▉     | 18000/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.83.down_proj:  49%|████▉     | 18001/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.84.gate_proj:  49%|████▉     | 18002/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.84.up_proj:  49%|████▉     | 18003/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.84.down_proj:  49%|████▉     | 18004/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.85.gate_proj:  49%|████▉     | 18005/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.85.up_proj:  49%|████▉     | 18006/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.85.down_proj:  49%|████▉     | 18007/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.86.gate_proj:  49%|████▉     | 18008/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.86.up_proj:  49%|████▉     | 18009/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.86.down_proj:  49%|████▉     | 18010/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.87.gate_proj:  49%|████▉     | 18011/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.87.up_proj:  49%|████▉     | 18012/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.87.down_proj:  49%|████▉     | 18013/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.88.gate_proj:  49%|████▉     | 18014/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.88.up_proj:  49%|████▉     | 18015/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.88.down_proj:  49%|████▉     | 18016/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.89.gate_proj:  49%|████▉     | 18017/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.89.up_proj:  49%|████▉     | 18018/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.89.down_proj:  49%|████▉     | 18019/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.90.gate_proj:  49%|████▉     | 18020/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.90.up_proj:  49%|████▉     | 18021/36566 [00:16<00:16, 1158.20it/s]  
packing model.layers.45.mlp.experts.90.down_proj:  49%|████▉     | 18022/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.91.gate_proj:  49%|████▉     | 18023/36566 [00:16<00:16, 1158.20it/s]
packing model.layers.45.mlp.experts.91.gate_proj:  49%|████▉     | 18024/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.91.up_proj:  49%|████▉     | 18024/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.91.down_proj:  49%|████▉     | 18025/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.92.gate_proj:  49%|████▉     | 18026/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.92.up_proj:  49%|████▉     | 18027/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.92.down_proj:  49%|████▉     | 18028/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.93.gate_proj:  49%|████▉     | 18029/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.93.up_proj:  49%|████▉     | 18030/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.93.down_proj:  49%|████▉     | 18031/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.94.gate_proj:  49%|████▉     | 18032/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.94.up_proj:  49%|████▉     | 18033/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.94.down_proj:  49%|████▉     | 18034/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.95.gate_proj:  49%|████▉     | 18035/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.95.up_proj:  49%|████▉     | 18036/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.95.down_proj:  49%|████▉     | 18037/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.96.gate_proj:  49%|████▉     | 18038/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.96.up_proj:  49%|████▉     | 18039/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.96.down_proj:  49%|████▉     | 18040/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.97.gate_proj:  49%|████▉     | 18041/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.97.up_proj:  49%|████▉     | 18042/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.97.down_proj:  49%|████▉     | 18043/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.98.gate_proj:  49%|████▉     | 18044/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.98.up_proj:  49%|████▉     | 18045/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.98.down_proj:  49%|████▉     | 18046/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.99.gate_proj:  49%|████▉     | 18047/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.99.up_proj:  49%|████▉     | 18048/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.99.down_proj:  49%|████▉     | 18049/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.100.gate_proj:  49%|████▉     | 18050/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.100.up_proj:  49%|████▉     | 18051/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.100.down_proj:  49%|████▉     | 18052/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.101.gate_proj:  49%|████▉     | 18053/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.101.up_proj:  49%|████▉     | 18054/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.101.down_proj:  49%|████▉     | 18055/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.102.gate_proj:  49%|████▉     | 18056/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.102.up_proj:  49%|████▉     | 18057/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.102.down_proj:  49%|████▉     | 18058/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.103.gate_proj:  49%|████▉     | 18059/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.103.up_proj:  49%|████▉     | 18060/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.103.down_proj:  49%|████▉     | 18061/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.104.gate_proj:  49%|████▉     | 18062/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.104.up_proj:  49%|████▉     | 18063/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.104.down_proj:  49%|████▉     | 18064/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.105.gate_proj:  49%|████▉     | 18065/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.105.up_proj:  49%|████▉     | 18066/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.105.down_proj:  49%|████▉     | 18067/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.106.gate_proj:  49%|████▉     | 18068/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.106.up_proj:  49%|████▉     | 18069/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.106.down_proj:  49%|████▉     | 18070/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.107.gate_proj:  49%|████▉     | 18071/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.107.up_proj:  49%|████▉     | 18072/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.107.down_proj:  49%|████▉     | 18073/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.108.gate_proj:  49%|████▉     | 18074/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.108.up_proj:  49%|████▉     | 18075/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.108.down_proj:  49%|████▉     | 18076/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.109.gate_proj:  49%|████▉     | 18077/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.109.up_proj:  49%|████▉     | 18078/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.109.down_proj:  49%|████▉     | 18079/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.110.gate_proj:  49%|████▉     | 18080/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.110.up_proj:  49%|████▉     | 18081/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.110.down_proj:  49%|████▉     | 18082/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.111.gate_proj:  49%|████▉     | 18083/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.111.up_proj:  49%|████▉     | 18084/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.111.down_proj:  49%|████▉     | 18085/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.112.gate_proj:  49%|████▉     | 18086/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.112.up_proj:  49%|████▉     | 18087/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.112.down_proj:  49%|████▉     | 18088/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.113.gate_proj:  49%|████▉     | 18089/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.113.up_proj:  49%|████▉     | 18090/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.113.down_proj:  49%|████▉     | 18091/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.114.gate_proj:  49%|████▉     | 18092/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.114.up_proj:  49%|████▉     | 18093/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.114.down_proj:  49%|████▉     | 18094/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.115.gate_proj:  49%|████▉     | 18095/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.115.up_proj:  49%|████▉     | 18096/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.115.down_proj:  49%|████▉     | 18097/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.116.gate_proj:  49%|████▉     | 18098/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.116.up_proj:  49%|████▉     | 18099/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.116.down_proj:  49%|████▉     | 18100/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.117.gate_proj:  50%|████▉     | 18101/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.117.up_proj:  50%|████▉     | 18102/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.117.down_proj:  50%|████▉     | 18103/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.118.gate_proj:  50%|████▉     | 18104/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.118.up_proj:  50%|████▉     | 18105/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.118.down_proj:  50%|████▉     | 18106/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.119.gate_proj:  50%|████▉     | 18107/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.119.up_proj:  50%|████▉     | 18108/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.119.down_proj:  50%|████▉     | 18109/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.120.gate_proj:  50%|████▉     | 18110/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.120.up_proj:  50%|████▉     | 18111/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.120.down_proj:  50%|████▉     | 18112/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.121.gate_proj:  50%|████▉     | 18113/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.121.up_proj:  50%|████▉     | 18114/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.121.down_proj:  50%|████▉     | 18115/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.122.gate_proj:  50%|████▉     | 18116/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.122.up_proj:  50%|████▉     | 18117/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.122.down_proj:  50%|████▉     | 18118/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.123.gate_proj:  50%|████▉     | 18119/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.123.up_proj:  50%|████▉     | 18120/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.123.down_proj:  50%|████▉     | 18121/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.124.gate_proj:  50%|████▉     | 18122/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.124.up_proj:  50%|████▉     | 18123/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.124.down_proj:  50%|████▉     | 18124/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.125.gate_proj:  50%|████▉     | 18125/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.125.up_proj:  50%|████▉     | 18126/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.125.down_proj:  50%|████▉     | 18127/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.126.gate_proj:  50%|████▉     | 18128/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.126.up_proj:  50%|████▉     | 18129/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.126.down_proj:  50%|████▉     | 18130/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.127.gate_proj:  50%|████▉     | 18131/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.45.mlp.experts.127.up_proj:  50%|████▉     | 18132/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.45.mlp.experts.127.down_proj:  50%|████▉     | 18133/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.46.mlp.experts.0.gate_proj:  50%|████▉     | 18134/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.46.mlp.experts.0.up_proj:  50%|████▉     | 18135/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.46.mlp.experts.0.down_proj:  50%|████▉     | 18136/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.46.mlp.experts.1.gate_proj:  50%|████▉     | 18137/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.46.mlp.experts.1.up_proj:  50%|████▉     | 18138/36566 [00:16<00:16, 1150.67it/s]  
packing model.layers.46.mlp.experts.1.down_proj:  50%|████▉     | 18139/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.46.mlp.experts.2.gate_proj:  50%|████▉     | 18140/36566 [00:16<00:16, 1150.67it/s]
packing model.layers.46.mlp.experts.2.gate_proj:  50%|████▉     | 18141/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.2.up_proj:  50%|████▉     | 18141/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.2.down_proj:  50%|████▉     | 18142/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.3.gate_proj:  50%|████▉     | 18143/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.3.up_proj:  50%|████▉     | 18144/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.3.down_proj:  50%|████▉     | 18145/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.4.gate_proj:  50%|████▉     | 18146/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.4.up_proj:  50%|████▉     | 18147/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.4.down_proj:  50%|████▉     | 18148/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.5.gate_proj:  50%|████▉     | 18149/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.5.up_proj:  50%|████▉     | 18150/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.5.down_proj:  50%|████▉     | 18151/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.6.gate_proj:  50%|████▉     | 18152/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.6.up_proj:  50%|████▉     | 18153/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.6.down_proj:  50%|████▉     | 18154/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.7.gate_proj:  50%|████▉     | 18155/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.7.up_proj:  50%|████▉     | 18156/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.7.down_proj:  50%|████▉     | 18157/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.8.gate_proj:  50%|████▉     | 18158/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.8.up_proj:  50%|████▉     | 18159/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.8.down_proj:  50%|████▉     | 18160/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.9.gate_proj:  50%|████▉     | 18161/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.9.up_proj:  50%|████▉     | 18162/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.9.down_proj:  50%|████▉     | 18163/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.10.gate_proj:  50%|████▉     | 18164/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.10.up_proj:  50%|████▉     | 18165/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.10.down_proj:  50%|████▉     | 18166/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.11.gate_proj:  50%|████▉     | 18167/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.11.up_proj:  50%|████▉     | 18168/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.11.down_proj:  50%|████▉     | 18169/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.12.gate_proj:  50%|████▉     | 18170/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.12.up_proj:  50%|████▉     | 18171/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.12.down_proj:  50%|████▉     | 18172/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.13.gate_proj:  50%|████▉     | 18173/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.13.up_proj:  50%|████▉     | 18174/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.13.down_proj:  50%|████▉     | 18175/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.14.gate_proj:  50%|████▉     | 18176/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.14.up_proj:  50%|████▉     | 18177/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.14.down_proj:  50%|████▉     | 18178/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.15.gate_proj:  50%|████▉     | 18179/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.15.up_proj:  50%|████▉     | 18180/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.15.down_proj:  50%|████▉     | 18181/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.16.gate_proj:  50%|████▉     | 18182/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.16.up_proj:  50%|████▉     | 18183/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.16.down_proj:  50%|████▉     | 18184/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.17.gate_proj:  50%|████▉     | 18185/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.17.up_proj:  50%|████▉     | 18186/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.17.down_proj:  50%|████▉     | 18187/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.18.gate_proj:  50%|████▉     | 18188/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.18.up_proj:  50%|████▉     | 18189/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.18.down_proj:  50%|████▉     | 18190/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.19.gate_proj:  50%|████▉     | 18191/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.19.up_proj:  50%|████▉     | 18192/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.19.down_proj:  50%|████▉     | 18193/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.20.gate_proj:  50%|████▉     | 18194/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.20.up_proj:  50%|████▉     | 18195/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.20.down_proj:  50%|████▉     | 18196/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.21.gate_proj:  50%|████▉     | 18197/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.21.up_proj:  50%|████▉     | 18198/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.21.down_proj:  50%|████▉     | 18199/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.22.gate_proj:  50%|████▉     | 18200/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.22.up_proj:  50%|████▉     | 18201/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.22.down_proj:  50%|████▉     | 18202/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.23.gate_proj:  50%|████▉     | 18203/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.23.up_proj:  50%|████▉     | 18204/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.23.down_proj:  50%|████▉     | 18205/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.24.gate_proj:  50%|████▉     | 18206/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.24.up_proj:  50%|████▉     | 18207/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.24.down_proj:  50%|████▉     | 18208/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.25.gate_proj:  50%|████▉     | 18209/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.25.up_proj:  50%|████▉     | 18210/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.25.down_proj:  50%|████▉     | 18211/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.26.gate_proj:  50%|████▉     | 18212/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.26.up_proj:  50%|████▉     | 18213/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.26.down_proj:  50%|████▉     | 18214/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.27.gate_proj:  50%|████▉     | 18215/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.27.up_proj:  50%|████▉     | 18216/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.27.down_proj:  50%|████▉     | 18217/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.28.gate_proj:  50%|████▉     | 18218/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.28.up_proj:  50%|████▉     | 18219/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.28.down_proj:  50%|████▉     | 18220/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.29.gate_proj:  50%|████▉     | 18221/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.29.up_proj:  50%|████▉     | 18222/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.29.down_proj:  50%|████▉     | 18223/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.30.gate_proj:  50%|████▉     | 18224/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.30.up_proj:  50%|████▉     | 18225/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.30.down_proj:  50%|████▉     | 18226/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.31.gate_proj:  50%|████▉     | 18227/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.31.up_proj:  50%|████▉     | 18228/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.31.down_proj:  50%|████▉     | 18229/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.32.gate_proj:  50%|████▉     | 18230/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.32.up_proj:  50%|████▉     | 18231/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.32.down_proj:  50%|████▉     | 18232/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.33.gate_proj:  50%|████▉     | 18233/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.33.up_proj:  50%|████▉     | 18234/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.33.down_proj:  50%|████▉     | 18235/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.34.gate_proj:  50%|████▉     | 18236/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.34.up_proj:  50%|████▉     | 18237/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.34.down_proj:  50%|████▉     | 18238/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.35.gate_proj:  50%|████▉     | 18239/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.35.up_proj:  50%|████▉     | 18240/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.35.down_proj:  50%|████▉     | 18241/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.36.gate_proj:  50%|████▉     | 18242/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.36.up_proj:  50%|████▉     | 18243/36566 [00:16<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.36.down_proj:  50%|████▉     | 18244/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.37.gate_proj:  50%|████▉     | 18245/36566 [00:16<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.37.up_proj:  50%|████▉     | 18246/36566 [00:17<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.37.down_proj:  50%|████▉     | 18247/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.38.gate_proj:  50%|████▉     | 18248/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.38.up_proj:  50%|████▉     | 18249/36566 [00:17<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.38.down_proj:  50%|████▉     | 18250/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.39.gate_proj:  50%|████▉     | 18251/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.39.up_proj:  50%|████▉     | 18252/36566 [00:17<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.39.down_proj:  50%|████▉     | 18253/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.40.gate_proj:  50%|████▉     | 18254/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.40.up_proj:  50%|████▉     | 18255/36566 [00:17<00:15, 1153.65it/s]  
packing model.layers.46.mlp.experts.40.down_proj:  50%|████▉     | 18256/36566 [00:17<00:15, 1153.65it/s]
packing model.layers.46.mlp.experts.40.down_proj:  50%|████▉     | 18257/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.41.gate_proj:  50%|████▉     | 18257/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.41.up_proj:  50%|████▉     | 18258/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.41.down_proj:  50%|████▉     | 18259/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.42.gate_proj:  50%|████▉     | 18260/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.42.up_proj:  50%|████▉     | 18261/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.42.down_proj:  50%|████▉     | 18262/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.43.gate_proj:  50%|████▉     | 18263/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.43.up_proj:  50%|████▉     | 18264/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.43.down_proj:  50%|████▉     | 18265/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.44.gate_proj:  50%|████▉     | 18266/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.44.up_proj:  50%|████▉     | 18267/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.44.down_proj:  50%|████▉     | 18268/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.45.gate_proj:  50%|████▉     | 18269/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.45.up_proj:  50%|████▉     | 18270/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.45.down_proj:  50%|████▉     | 18271/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.46.gate_proj:  50%|████▉     | 18272/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.46.up_proj:  50%|████▉     | 18273/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.46.down_proj:  50%|████▉     | 18274/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.47.gate_proj:  50%|████▉     | 18275/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.47.up_proj:  50%|████▉     | 18276/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.47.down_proj:  50%|████▉     | 18277/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.48.gate_proj:  50%|████▉     | 18278/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.48.up_proj:  50%|████▉     | 18279/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.48.down_proj:  50%|████▉     | 18280/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.49.gate_proj:  50%|████▉     | 18281/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.49.up_proj:  50%|████▉     | 18282/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.49.down_proj:  50%|█████     | 18283/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.50.gate_proj:  50%|█████     | 18284/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.50.up_proj:  50%|█████     | 18285/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.50.down_proj:  50%|█████     | 18286/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.51.gate_proj:  50%|█████     | 18287/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.51.up_proj:  50%|█████     | 18288/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.51.down_proj:  50%|█████     | 18289/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.52.gate_proj:  50%|█████     | 18290/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.52.up_proj:  50%|█████     | 18291/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.52.down_proj:  50%|█████     | 18292/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.53.gate_proj:  50%|█████     | 18293/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.53.up_proj:  50%|█████     | 18294/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.53.down_proj:  50%|█████     | 18295/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.54.gate_proj:  50%|█████     | 18296/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.54.up_proj:  50%|█████     | 18297/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.54.down_proj:  50%|█████     | 18298/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.55.gate_proj:  50%|█████     | 18299/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.55.up_proj:  50%|█████     | 18300/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.55.down_proj:  50%|█████     | 18301/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.56.gate_proj:  50%|█████     | 18302/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.56.up_proj:  50%|█████     | 18303/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.56.down_proj:  50%|█████     | 18304/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.57.gate_proj:  50%|█████     | 18305/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.57.up_proj:  50%|█████     | 18306/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.57.down_proj:  50%|█████     | 18307/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.58.gate_proj:  50%|█████     | 18308/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.58.up_proj:  50%|█████     | 18309/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.58.down_proj:  50%|█████     | 18310/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.59.gate_proj:  50%|█████     | 18311/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.59.up_proj:  50%|█████     | 18312/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.59.down_proj:  50%|█████     | 18313/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.60.gate_proj:  50%|█████     | 18314/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.60.up_proj:  50%|█████     | 18315/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.60.down_proj:  50%|█████     | 18316/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.61.gate_proj:  50%|█████     | 18317/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.61.up_proj:  50%|█████     | 18318/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.61.down_proj:  50%|█████     | 18319/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.62.gate_proj:  50%|█████     | 18320/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.62.up_proj:  50%|█████     | 18321/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.62.down_proj:  50%|█████     | 18322/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.63.gate_proj:  50%|█████     | 18323/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.63.up_proj:  50%|█████     | 18324/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.63.down_proj:  50%|█████     | 18325/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.64.gate_proj:  50%|█████     | 18326/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.64.up_proj:  50%|█████     | 18327/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.64.down_proj:  50%|█████     | 18328/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.65.gate_proj:  50%|█████     | 18329/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.65.up_proj:  50%|█████     | 18330/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.65.down_proj:  50%|█████     | 18331/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.66.gate_proj:  50%|█████     | 18332/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.66.up_proj:  50%|█████     | 18333/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.66.down_proj:  50%|█████     | 18334/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.67.gate_proj:  50%|█████     | 18335/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.67.up_proj:  50%|█████     | 18336/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.67.down_proj:  50%|█████     | 18337/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.68.gate_proj:  50%|█████     | 18338/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.68.up_proj:  50%|█████     | 18339/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.68.down_proj:  50%|█████     | 18340/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.69.gate_proj:  50%|█████     | 18341/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.69.up_proj:  50%|█████     | 18342/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.69.down_proj:  50%|█████     | 18343/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.70.gate_proj:  50%|█████     | 18344/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.70.up_proj:  50%|█████     | 18345/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.70.down_proj:  50%|█████     | 18346/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.71.gate_proj:  50%|█████     | 18347/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.71.up_proj:  50%|█████     | 18348/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.71.down_proj:  50%|█████     | 18349/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.72.gate_proj:  50%|█████     | 18350/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.72.up_proj:  50%|█████     | 18351/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.72.down_proj:  50%|█████     | 18352/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.73.gate_proj:  50%|█████     | 18353/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.73.up_proj:  50%|█████     | 18354/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.73.down_proj:  50%|█████     | 18355/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.74.gate_proj:  50%|█████     | 18356/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.74.up_proj:  50%|█████     | 18357/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.74.down_proj:  50%|█████     | 18358/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.75.gate_proj:  50%|█████     | 18359/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.75.up_proj:  50%|█████     | 18360/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.75.down_proj:  50%|█████     | 18361/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.76.gate_proj:  50%|█████     | 18362/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.76.up_proj:  50%|█████     | 18363/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.76.down_proj:  50%|█████     | 18364/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.77.gate_proj:  50%|█████     | 18365/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.77.up_proj:  50%|█████     | 18366/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.77.down_proj:  50%|█████     | 18367/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.78.gate_proj:  50%|█████     | 18368/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.78.up_proj:  50%|█████     | 18369/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.78.down_proj:  50%|█████     | 18370/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.79.gate_proj:  50%|█████     | 18371/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.79.up_proj:  50%|█████     | 18372/36566 [00:17<00:15, 1155.12it/s]  
packing model.layers.46.mlp.experts.79.down_proj:  50%|█████     | 18373/36566 [00:17<00:15, 1155.12it/s]
packing model.layers.46.mlp.experts.79.down_proj:  50%|█████     | 18374/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.80.gate_proj:  50%|█████     | 18374/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.80.up_proj:  50%|█████     | 18375/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.80.down_proj:  50%|█████     | 18376/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.81.gate_proj:  50%|█████     | 18377/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.81.up_proj:  50%|█████     | 18378/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.81.down_proj:  50%|█████     | 18379/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.82.gate_proj:  50%|█████     | 18380/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.82.up_proj:  50%|█████     | 18381/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.82.down_proj:  50%|█████     | 18382/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.83.gate_proj:  50%|█████     | 18383/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.83.up_proj:  50%|█████     | 18384/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.83.down_proj:  50%|█████     | 18385/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.84.gate_proj:  50%|█████     | 18386/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.84.up_proj:  50%|█████     | 18387/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.84.down_proj:  50%|█████     | 18388/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.85.gate_proj:  50%|█████     | 18389/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.85.up_proj:  50%|█████     | 18390/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.85.down_proj:  50%|█████     | 18391/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.86.gate_proj:  50%|█████     | 18392/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.86.up_proj:  50%|█████     | 18393/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.86.down_proj:  50%|█████     | 18394/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.87.gate_proj:  50%|█████     | 18395/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.87.up_proj:  50%|█████     | 18396/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.87.down_proj:  50%|█████     | 18397/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.88.gate_proj:  50%|█████     | 18398/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.88.up_proj:  50%|█████     | 18399/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.88.down_proj:  50%|█████     | 18400/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.89.gate_proj:  50%|█████     | 18401/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.89.up_proj:  50%|█████     | 18402/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.89.down_proj:  50%|█████     | 18403/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.90.gate_proj:  50%|█████     | 18404/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.90.up_proj:  50%|█████     | 18405/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.90.down_proj:  50%|█████     | 18406/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.91.gate_proj:  50%|█████     | 18407/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.91.up_proj:  50%|█████     | 18408/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.91.down_proj:  50%|█████     | 18409/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.92.gate_proj:  50%|█████     | 18410/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.92.up_proj:  50%|█████     | 18411/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.92.down_proj:  50%|█████     | 18412/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.93.gate_proj:  50%|█████     | 18413/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.93.up_proj:  50%|█████     | 18414/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.93.down_proj:  50%|█████     | 18415/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.94.gate_proj:  50%|█████     | 18416/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.94.up_proj:  50%|█████     | 18417/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.94.down_proj:  50%|█████     | 18418/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.95.gate_proj:  50%|█████     | 18419/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.95.up_proj:  50%|█████     | 18420/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.95.down_proj:  50%|█████     | 18421/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.96.gate_proj:  50%|█████     | 18422/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.96.up_proj:  50%|█████     | 18423/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.96.down_proj:  50%|█████     | 18424/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.97.gate_proj:  50%|█████     | 18425/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.97.up_proj:  50%|█████     | 18426/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.97.down_proj:  50%|█████     | 18427/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.98.gate_proj:  50%|█████     | 18428/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.98.up_proj:  50%|█████     | 18429/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.98.down_proj:  50%|█████     | 18430/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.99.gate_proj:  50%|█████     | 18431/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.99.up_proj:  50%|█████     | 18432/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.99.down_proj:  50%|█████     | 18433/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.100.gate_proj:  50%|█████     | 18434/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.100.up_proj:  50%|█████     | 18435/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.100.down_proj:  50%|█████     | 18436/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.101.gate_proj:  50%|█████     | 18437/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.101.up_proj:  50%|█████     | 18438/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.101.down_proj:  50%|█████     | 18439/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.102.gate_proj:  50%|█████     | 18440/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.102.up_proj:  50%|█████     | 18441/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.102.down_proj:  50%|█████     | 18442/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.103.gate_proj:  50%|█████     | 18443/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.103.up_proj:  50%|█████     | 18444/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.103.down_proj:  50%|█████     | 18445/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.104.gate_proj:  50%|█████     | 18446/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.104.up_proj:  50%|█████     | 18447/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.104.down_proj:  50%|█████     | 18448/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.105.gate_proj:  50%|█████     | 18449/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.105.up_proj:  50%|█████     | 18450/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.105.down_proj:  50%|█████     | 18451/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.106.gate_proj:  50%|█████     | 18452/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.106.up_proj:  50%|█████     | 18453/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.106.down_proj:  50%|█████     | 18454/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.107.gate_proj:  50%|█████     | 18455/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.107.up_proj:  50%|█████     | 18456/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.107.down_proj:  50%|█████     | 18457/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.108.gate_proj:  50%|█████     | 18458/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.108.up_proj:  50%|█████     | 18459/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.108.down_proj:  50%|█████     | 18460/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.109.gate_proj:  50%|█████     | 18461/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.109.up_proj:  50%|█████     | 18462/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.109.down_proj:  50%|█████     | 18463/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.110.gate_proj:  50%|█████     | 18464/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.110.up_proj:  50%|█████     | 18465/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.110.down_proj:  51%|█████     | 18466/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.111.gate_proj:  51%|█████     | 18467/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.111.up_proj:  51%|█████     | 18468/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.111.down_proj:  51%|█████     | 18469/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.112.gate_proj:  51%|█████     | 18470/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.112.up_proj:  51%|█████     | 18471/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.112.down_proj:  51%|█████     | 18472/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.113.gate_proj:  51%|█████     | 18473/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.113.up_proj:  51%|█████     | 18474/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.113.down_proj:  51%|█████     | 18475/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.114.gate_proj:  51%|█████     | 18476/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.114.up_proj:  51%|█████     | 18477/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.114.down_proj:  51%|█████     | 18478/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.115.gate_proj:  51%|█████     | 18479/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.115.up_proj:  51%|█████     | 18480/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.115.down_proj:  51%|█████     | 18481/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.116.gate_proj:  51%|█████     | 18482/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.116.up_proj:  51%|█████     | 18483/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.116.down_proj:  51%|█████     | 18484/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.117.gate_proj:  51%|█████     | 18485/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.117.up_proj:  51%|█████     | 18486/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.117.down_proj:  51%|█████     | 18487/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.118.gate_proj:  51%|█████     | 18488/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.118.up_proj:  51%|█████     | 18489/36566 [00:17<00:15, 1156.38it/s]  
packing model.layers.46.mlp.experts.118.down_proj:  51%|█████     | 18490/36566 [00:17<00:15, 1156.38it/s]
packing model.layers.46.mlp.experts.118.down_proj:  51%|█████     | 18491/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.119.gate_proj:  51%|█████     | 18491/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.119.up_proj:  51%|█████     | 18492/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.119.down_proj:  51%|█████     | 18493/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.120.gate_proj:  51%|█████     | 18494/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.120.up_proj:  51%|█████     | 18495/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.120.down_proj:  51%|█████     | 18496/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.121.gate_proj:  51%|█████     | 18497/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.121.up_proj:  51%|█████     | 18498/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.121.down_proj:  51%|█████     | 18499/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.122.gate_proj:  51%|█████     | 18500/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.122.up_proj:  51%|█████     | 18501/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.122.down_proj:  51%|█████     | 18502/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.123.gate_proj:  51%|█████     | 18503/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.123.up_proj:  51%|█████     | 18504/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.123.down_proj:  51%|█████     | 18505/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.124.gate_proj:  51%|█████     | 18506/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.124.up_proj:  51%|█████     | 18507/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.124.down_proj:  51%|█████     | 18508/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.125.gate_proj:  51%|█████     | 18509/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.125.up_proj:  51%|█████     | 18510/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.125.down_proj:  51%|█████     | 18511/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.126.gate_proj:  51%|█████     | 18512/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.126.up_proj:  51%|█████     | 18513/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.126.down_proj:  51%|█████     | 18514/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.127.gate_proj:  51%|█████     | 18515/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.46.mlp.experts.127.up_proj:  51%|█████     | 18516/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.46.mlp.experts.127.down_proj:  51%|█████     | 18517/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.0.gate_proj:  51%|█████     | 18518/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.0.up_proj:  51%|█████     | 18519/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.0.down_proj:  51%|█████     | 18520/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.1.gate_proj:  51%|█████     | 18521/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.1.up_proj:  51%|█████     | 18522/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.1.down_proj:  51%|█████     | 18523/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.2.gate_proj:  51%|█████     | 18524/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.2.up_proj:  51%|█████     | 18525/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.2.down_proj:  51%|█████     | 18526/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.3.gate_proj:  51%|█████     | 18527/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.3.up_proj:  51%|█████     | 18528/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.3.down_proj:  51%|█████     | 18529/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.4.gate_proj:  51%|█████     | 18530/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.4.up_proj:  51%|█████     | 18531/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.4.down_proj:  51%|█████     | 18532/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.5.gate_proj:  51%|█████     | 18533/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.5.up_proj:  51%|█████     | 18534/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.5.down_proj:  51%|█████     | 18535/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.6.gate_proj:  51%|█████     | 18536/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.6.up_proj:  51%|█████     | 18537/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.6.down_proj:  51%|█████     | 18538/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.7.gate_proj:  51%|█████     | 18539/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.7.up_proj:  51%|█████     | 18540/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.7.down_proj:  51%|█████     | 18541/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.8.gate_proj:  51%|█████     | 18542/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.8.up_proj:  51%|█████     | 18543/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.8.down_proj:  51%|█████     | 18544/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.9.gate_proj:  51%|█████     | 18545/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.9.up_proj:  51%|█████     | 18546/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.9.down_proj:  51%|█████     | 18547/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.10.gate_proj:  51%|█████     | 18548/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.10.up_proj:  51%|█████     | 18549/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.10.down_proj:  51%|█████     | 18550/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.11.gate_proj:  51%|█████     | 18551/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.11.up_proj:  51%|█████     | 18552/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.11.down_proj:  51%|█████     | 18553/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.12.gate_proj:  51%|█████     | 18554/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.12.up_proj:  51%|█████     | 18555/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.12.down_proj:  51%|█████     | 18556/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.13.gate_proj:  51%|█████     | 18557/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.13.up_proj:  51%|█████     | 18558/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.13.down_proj:  51%|█████     | 18559/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.14.gate_proj:  51%|█████     | 18560/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.14.up_proj:  51%|█████     | 18561/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.14.down_proj:  51%|█████     | 18562/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.15.gate_proj:  51%|█████     | 18563/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.15.up_proj:  51%|█████     | 18564/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.15.down_proj:  51%|█████     | 18565/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.16.gate_proj:  51%|█████     | 18566/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.16.up_proj:  51%|█████     | 18567/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.16.down_proj:  51%|█████     | 18568/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.17.gate_proj:  51%|█████     | 18569/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.17.up_proj:  51%|█████     | 18570/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.17.down_proj:  51%|█████     | 18571/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.18.gate_proj:  51%|█████     | 18572/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.18.up_proj:  51%|█████     | 18573/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.18.down_proj:  51%|█████     | 18574/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.19.gate_proj:  51%|█████     | 18575/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.19.up_proj:  51%|█████     | 18576/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.19.down_proj:  51%|█████     | 18577/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.20.gate_proj:  51%|█████     | 18578/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.20.up_proj:  51%|█████     | 18579/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.20.down_proj:  51%|█████     | 18580/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.21.gate_proj:  51%|█████     | 18581/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.21.up_proj:  51%|█████     | 18582/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.21.down_proj:  51%|█████     | 18583/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.22.gate_proj:  51%|█████     | 18584/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.22.up_proj:  51%|█████     | 18585/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.22.down_proj:  51%|█████     | 18586/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.23.gate_proj:  51%|█████     | 18587/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.23.up_proj:  51%|█████     | 18588/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.23.down_proj:  51%|█████     | 18589/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.24.gate_proj:  51%|█████     | 18590/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.24.up_proj:  51%|█████     | 18591/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.24.down_proj:  51%|█████     | 18592/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.25.gate_proj:  51%|█████     | 18593/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.25.up_proj:  51%|█████     | 18594/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.25.down_proj:  51%|█████     | 18595/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.26.gate_proj:  51%|█████     | 18596/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.26.up_proj:  51%|█████     | 18597/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.26.down_proj:  51%|█████     | 18598/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.27.gate_proj:  51%|█████     | 18599/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.27.up_proj:  51%|█████     | 18600/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.27.down_proj:  51%|█████     | 18601/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.28.gate_proj:  51%|█████     | 18602/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.28.up_proj:  51%|█████     | 18603/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.28.down_proj:  51%|█████     | 18604/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.29.gate_proj:  51%|█████     | 18605/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.29.up_proj:  51%|█████     | 18606/36566 [00:17<00:15, 1160.24it/s]  
packing model.layers.47.mlp.experts.29.down_proj:  51%|█████     | 18607/36566 [00:17<00:15, 1160.24it/s]
packing model.layers.47.mlp.experts.29.down_proj:  51%|█████     | 18608/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.30.gate_proj:  51%|█████     | 18608/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.30.up_proj:  51%|█████     | 18609/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.30.down_proj:  51%|█████     | 18610/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.31.gate_proj:  51%|█████     | 18611/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.31.up_proj:  51%|█████     | 18612/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.31.down_proj:  51%|█████     | 18613/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.32.gate_proj:  51%|█████     | 18614/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.32.up_proj:  51%|█████     | 18615/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.32.down_proj:  51%|█████     | 18616/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.33.gate_proj:  51%|█████     | 18617/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.33.up_proj:  51%|█████     | 18618/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.33.down_proj:  51%|█████     | 18619/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.34.gate_proj:  51%|█████     | 18620/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.34.up_proj:  51%|█████     | 18621/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.34.down_proj:  51%|█████     | 18622/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.35.gate_proj:  51%|█████     | 18623/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.35.up_proj:  51%|█████     | 18624/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.35.down_proj:  51%|█████     | 18625/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.36.gate_proj:  51%|█████     | 18626/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.36.up_proj:  51%|█████     | 18627/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.36.down_proj:  51%|█████     | 18628/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.37.gate_proj:  51%|█████     | 18629/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.37.up_proj:  51%|█████     | 18630/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.37.down_proj:  51%|█████     | 18631/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.38.gate_proj:  51%|█████     | 18632/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.38.up_proj:  51%|█████     | 18633/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.38.down_proj:  51%|█████     | 18634/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.39.gate_proj:  51%|█████     | 18635/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.39.up_proj:  51%|█████     | 18636/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.39.down_proj:  51%|█████     | 18637/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.40.gate_proj:  51%|█████     | 18638/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.40.up_proj:  51%|█████     | 18639/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.40.down_proj:  51%|█████     | 18640/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.41.gate_proj:  51%|█████     | 18641/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.41.up_proj:  51%|█████     | 18642/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.41.down_proj:  51%|█████     | 18643/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.42.gate_proj:  51%|█████     | 18644/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.42.up_proj:  51%|█████     | 18645/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.42.down_proj:  51%|█████     | 18646/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.43.gate_proj:  51%|█████     | 18647/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.43.up_proj:  51%|█████     | 18648/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.43.down_proj:  51%|█████     | 18649/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.44.gate_proj:  51%|█████     | 18650/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.44.up_proj:  51%|█████     | 18651/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.44.down_proj:  51%|█████     | 18652/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.45.gate_proj:  51%|█████     | 18653/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.45.up_proj:  51%|█████     | 18654/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.45.down_proj:  51%|█████     | 18655/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.46.gate_proj:  51%|█████     | 18656/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.46.up_proj:  51%|█████     | 18657/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.46.down_proj:  51%|█████     | 18658/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.47.gate_proj:  51%|█████     | 18659/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.47.up_proj:  51%|█████     | 18660/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.47.down_proj:  51%|█████     | 18661/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.48.gate_proj:  51%|█████     | 18662/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.48.up_proj:  51%|█████     | 18663/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.48.down_proj:  51%|█████     | 18664/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.49.gate_proj:  51%|█████     | 18665/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.49.up_proj:  51%|█████     | 18666/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.49.down_proj:  51%|█████     | 18667/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.50.gate_proj:  51%|█████     | 18668/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.50.up_proj:  51%|█████     | 18669/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.50.down_proj:  51%|█████     | 18670/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.51.gate_proj:  51%|█████     | 18671/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.51.up_proj:  51%|█████     | 18672/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.51.down_proj:  51%|█████     | 18673/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.52.gate_proj:  51%|█████     | 18674/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.52.up_proj:  51%|█████     | 18675/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.52.down_proj:  51%|█████     | 18676/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.53.gate_proj:  51%|█████     | 18677/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.53.up_proj:  51%|█████     | 18678/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.53.down_proj:  51%|█████     | 18679/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.54.gate_proj:  51%|█████     | 18680/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.54.up_proj:  51%|█████     | 18681/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.54.down_proj:  51%|█████     | 18682/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.55.gate_proj:  51%|█████     | 18683/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.55.up_proj:  51%|█████     | 18684/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.55.down_proj:  51%|█████     | 18685/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.56.gate_proj:  51%|█████     | 18686/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.56.up_proj:  51%|█████     | 18687/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.56.down_proj:  51%|█████     | 18688/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.57.gate_proj:  51%|█████     | 18689/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.57.up_proj:  51%|█████     | 18690/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.57.down_proj:  51%|█████     | 18691/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.58.gate_proj:  51%|█████     | 18692/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.58.up_proj:  51%|█████     | 18693/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.58.down_proj:  51%|█████     | 18694/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.59.gate_proj:  51%|█████     | 18695/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.59.up_proj:  51%|█████     | 18696/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.59.down_proj:  51%|█████     | 18697/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.60.gate_proj:  51%|█████     | 18698/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.60.up_proj:  51%|█████     | 18699/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.60.down_proj:  51%|█████     | 18700/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.61.gate_proj:  51%|█████     | 18701/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.61.up_proj:  51%|█████     | 18702/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.61.down_proj:  51%|█████     | 18703/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.62.gate_proj:  51%|█████     | 18704/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.62.up_proj:  51%|█████     | 18705/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.62.down_proj:  51%|█████     | 18706/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.63.gate_proj:  51%|█████     | 18707/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.63.up_proj:  51%|█████     | 18708/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.63.down_proj:  51%|█████     | 18709/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.64.gate_proj:  51%|█████     | 18710/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.64.up_proj:  51%|█████     | 18711/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.64.down_proj:  51%|█████     | 18712/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.65.gate_proj:  51%|█████     | 18713/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.65.up_proj:  51%|█████     | 18714/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.65.down_proj:  51%|█████     | 18715/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.66.gate_proj:  51%|█████     | 18716/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.66.up_proj:  51%|█████     | 18717/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.66.down_proj:  51%|█████     | 18718/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.67.gate_proj:  51%|█████     | 18719/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.67.up_proj:  51%|█████     | 18720/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.67.down_proj:  51%|█████     | 18721/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.68.gate_proj:  51%|█████     | 18722/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.68.up_proj:  51%|█████     | 18723/36566 [00:17<00:15, 1162.67it/s]  
packing model.layers.47.mlp.experts.68.down_proj:  51%|█████     | 18724/36566 [00:17<00:15, 1162.67it/s]
packing model.layers.47.mlp.experts.68.down_proj:  51%|█████     | 18725/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.69.gate_proj:  51%|█████     | 18725/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.69.up_proj:  51%|█████     | 18726/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.69.down_proj:  51%|█████     | 18727/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.70.gate_proj:  51%|█████     | 18728/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.70.up_proj:  51%|█████     | 18729/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.70.down_proj:  51%|█████     | 18730/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.71.gate_proj:  51%|█████     | 18731/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.71.up_proj:  51%|█████     | 18732/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.71.down_proj:  51%|█████     | 18733/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.72.gate_proj:  51%|█████     | 18734/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.72.up_proj:  51%|█████     | 18735/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.72.down_proj:  51%|█████     | 18736/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.73.gate_proj:  51%|█████     | 18737/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.73.up_proj:  51%|█████     | 18738/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.73.down_proj:  51%|█████     | 18739/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.74.gate_proj:  51%|█████     | 18740/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.74.up_proj:  51%|█████▏    | 18741/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.74.down_proj:  51%|█████▏    | 18742/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.75.gate_proj:  51%|█████▏    | 18743/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.75.up_proj:  51%|█████▏    | 18744/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.75.down_proj:  51%|█████▏    | 18745/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.76.gate_proj:  51%|█████▏    | 18746/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.76.up_proj:  51%|█████▏    | 18747/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.76.down_proj:  51%|█████▏    | 18748/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.77.gate_proj:  51%|█████▏    | 18749/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.77.up_proj:  51%|█████▏    | 18750/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.77.down_proj:  51%|█████▏    | 18751/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.78.gate_proj:  51%|█████▏    | 18752/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.78.up_proj:  51%|█████▏    | 18753/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.78.down_proj:  51%|█████▏    | 18754/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.79.gate_proj:  51%|█████▏    | 18755/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.79.up_proj:  51%|█████▏    | 18756/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.79.down_proj:  51%|█████▏    | 18757/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.80.gate_proj:  51%|█████▏    | 18758/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.80.up_proj:  51%|█████▏    | 18759/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.80.down_proj:  51%|█████▏    | 18760/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.81.gate_proj:  51%|█████▏    | 18761/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.81.up_proj:  51%|█████▏    | 18762/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.81.down_proj:  51%|█████▏    | 18763/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.82.gate_proj:  51%|█████▏    | 18764/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.82.up_proj:  51%|█████▏    | 18765/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.82.down_proj:  51%|█████▏    | 18766/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.83.gate_proj:  51%|█████▏    | 18767/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.83.up_proj:  51%|█████▏    | 18768/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.83.down_proj:  51%|█████▏    | 18769/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.84.gate_proj:  51%|█████▏    | 18770/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.84.up_proj:  51%|█████▏    | 18771/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.84.down_proj:  51%|█████▏    | 18772/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.85.gate_proj:  51%|█████▏    | 18773/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.85.up_proj:  51%|█████▏    | 18774/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.85.down_proj:  51%|█████▏    | 18775/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.86.gate_proj:  51%|█████▏    | 18776/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.86.up_proj:  51%|█████▏    | 18777/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.86.down_proj:  51%|█████▏    | 18778/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.87.gate_proj:  51%|█████▏    | 18779/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.87.up_proj:  51%|█████▏    | 18780/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.87.down_proj:  51%|█████▏    | 18781/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.88.gate_proj:  51%|█████▏    | 18782/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.88.up_proj:  51%|█████▏    | 18783/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.88.down_proj:  51%|█████▏    | 18784/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.89.gate_proj:  51%|█████▏    | 18785/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.89.up_proj:  51%|█████▏    | 18786/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.89.down_proj:  51%|█████▏    | 18787/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.90.gate_proj:  51%|█████▏    | 18788/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.90.up_proj:  51%|█████▏    | 18789/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.90.down_proj:  51%|█████▏    | 18790/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.91.gate_proj:  51%|█████▏    | 18791/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.91.up_proj:  51%|█████▏    | 18792/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.91.down_proj:  51%|█████▏    | 18793/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.92.gate_proj:  51%|█████▏    | 18794/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.92.up_proj:  51%|█████▏    | 18795/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.92.down_proj:  51%|█████▏    | 18796/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.93.gate_proj:  51%|█████▏    | 18797/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.93.up_proj:  51%|█████▏    | 18798/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.93.down_proj:  51%|█████▏    | 18799/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.94.gate_proj:  51%|█████▏    | 18800/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.94.up_proj:  51%|█████▏    | 18801/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.94.down_proj:  51%|█████▏    | 18802/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.95.gate_proj:  51%|█████▏    | 18803/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.95.up_proj:  51%|█████▏    | 18804/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.95.down_proj:  51%|█████▏    | 18805/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.96.gate_proj:  51%|█████▏    | 18806/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.96.up_proj:  51%|█████▏    | 18807/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.96.down_proj:  51%|█████▏    | 18808/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.97.gate_proj:  51%|█████▏    | 18809/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.97.up_proj:  51%|█████▏    | 18810/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.97.down_proj:  51%|█████▏    | 18811/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.98.gate_proj:  51%|█████▏    | 18812/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.98.up_proj:  51%|█████▏    | 18813/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.98.down_proj:  51%|█████▏    | 18814/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.99.gate_proj:  51%|█████▏    | 18815/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.99.up_proj:  51%|█████▏    | 18816/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.99.down_proj:  51%|█████▏    | 18817/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.100.gate_proj:  51%|█████▏    | 18818/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.100.up_proj:  51%|█████▏    | 18819/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.100.down_proj:  51%|█████▏    | 18820/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.101.gate_proj:  51%|█████▏    | 18821/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.101.up_proj:  51%|█████▏    | 18822/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.101.down_proj:  51%|█████▏    | 18823/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.102.gate_proj:  51%|█████▏    | 18824/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.102.up_proj:  51%|█████▏    | 18825/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.102.down_proj:  51%|█████▏    | 18826/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.103.gate_proj:  51%|█████▏    | 18827/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.103.up_proj:  51%|█████▏    | 18828/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.103.down_proj:  51%|█████▏    | 18829/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.104.gate_proj:  51%|█████▏    | 18830/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.104.up_proj:  51%|█████▏    | 18831/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.104.down_proj:  52%|█████▏    | 18832/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.105.gate_proj:  52%|█████▏    | 18833/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.105.up_proj:  52%|█████▏    | 18834/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.105.down_proj:  52%|█████▏    | 18835/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.106.gate_proj:  52%|█████▏    | 18836/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.106.up_proj:  52%|█████▏    | 18837/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.106.down_proj:  52%|█████▏    | 18838/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.107.gate_proj:  52%|█████▏    | 18839/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.107.up_proj:  52%|█████▏    | 18840/36566 [00:17<00:15, 1160.81it/s]  
packing model.layers.47.mlp.experts.107.down_proj:  52%|█████▏    | 18841/36566 [00:17<00:15, 1160.81it/s]
packing model.layers.47.mlp.experts.107.down_proj:  52%|█████▏    | 18842/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.108.gate_proj:  52%|█████▏    | 18842/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.108.up_proj:  52%|█████▏    | 18843/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.108.down_proj:  52%|█████▏    | 18844/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.109.gate_proj:  52%|█████▏    | 18845/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.109.up_proj:  52%|█████▏    | 18846/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.109.down_proj:  52%|█████▏    | 18847/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.110.gate_proj:  52%|█████▏    | 18848/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.110.up_proj:  52%|█████▏    | 18849/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.110.down_proj:  52%|█████▏    | 18850/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.111.gate_proj:  52%|█████▏    | 18851/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.111.up_proj:  52%|█████▏    | 18852/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.111.down_proj:  52%|█████▏    | 18853/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.112.gate_proj:  52%|█████▏    | 18854/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.112.up_proj:  52%|█████▏    | 18855/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.112.down_proj:  52%|█████▏    | 18856/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.113.gate_proj:  52%|█████▏    | 18857/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.113.up_proj:  52%|█████▏    | 18858/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.113.down_proj:  52%|█████▏    | 18859/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.114.gate_proj:  52%|█████▏    | 18860/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.114.up_proj:  52%|█████▏    | 18861/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.114.down_proj:  52%|█████▏    | 18862/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.115.gate_proj:  52%|█████▏    | 18863/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.115.up_proj:  52%|█████▏    | 18864/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.115.down_proj:  52%|█████▏    | 18865/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.116.gate_proj:  52%|█████▏    | 18866/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.116.up_proj:  52%|█████▏    | 18867/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.116.down_proj:  52%|█████▏    | 18868/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.117.gate_proj:  52%|█████▏    | 18869/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.117.up_proj:  52%|█████▏    | 18870/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.117.down_proj:  52%|█████▏    | 18871/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.118.gate_proj:  52%|█████▏    | 18872/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.118.up_proj:  52%|█████▏    | 18873/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.118.down_proj:  52%|█████▏    | 18874/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.119.gate_proj:  52%|█████▏    | 18875/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.119.up_proj:  52%|█████▏    | 18876/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.119.down_proj:  52%|█████▏    | 18877/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.120.gate_proj:  52%|█████▏    | 18878/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.120.up_proj:  52%|█████▏    | 18879/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.120.down_proj:  52%|█████▏    | 18880/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.121.gate_proj:  52%|█████▏    | 18881/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.121.up_proj:  52%|█████▏    | 18882/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.121.down_proj:  52%|█████▏    | 18883/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.122.gate_proj:  52%|█████▏    | 18884/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.122.up_proj:  52%|█████▏    | 18885/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.122.down_proj:  52%|█████▏    | 18886/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.123.gate_proj:  52%|█████▏    | 18887/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.123.up_proj:  52%|█████▏    | 18888/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.123.down_proj:  52%|█████▏    | 18889/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.124.gate_proj:  52%|█████▏    | 18890/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.124.up_proj:  52%|█████▏    | 18891/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.124.down_proj:  52%|█████▏    | 18892/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.125.gate_proj:  52%|█████▏    | 18893/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.125.up_proj:  52%|█████▏    | 18894/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.125.down_proj:  52%|█████▏    | 18895/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.126.gate_proj:  52%|█████▏    | 18896/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.126.up_proj:  52%|█████▏    | 18897/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.126.down_proj:  52%|█████▏    | 18898/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.127.gate_proj:  52%|█████▏    | 18899/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.47.mlp.experts.127.up_proj:  52%|█████▏    | 18900/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.47.mlp.experts.127.down_proj:  52%|█████▏    | 18901/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.0.gate_proj:  52%|█████▏    | 18902/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.0.up_proj:  52%|█████▏    | 18903/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.0.down_proj:  52%|█████▏    | 18904/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.1.gate_proj:  52%|█████▏    | 18905/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.1.up_proj:  52%|█████▏    | 18906/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.1.down_proj:  52%|█████▏    | 18907/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.2.gate_proj:  52%|█████▏    | 18908/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.2.up_proj:  52%|█████▏    | 18909/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.2.down_proj:  52%|█████▏    | 18910/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.3.gate_proj:  52%|█████▏    | 18911/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.3.up_proj:  52%|█████▏    | 18912/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.3.down_proj:  52%|█████▏    | 18913/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.4.gate_proj:  52%|█████▏    | 18914/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.4.up_proj:  52%|█████▏    | 18915/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.4.down_proj:  52%|█████▏    | 18916/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.5.gate_proj:  52%|█████▏    | 18917/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.5.up_proj:  52%|█████▏    | 18918/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.5.down_proj:  52%|█████▏    | 18919/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.6.gate_proj:  52%|█████▏    | 18920/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.6.up_proj:  52%|█████▏    | 18921/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.6.down_proj:  52%|█████▏    | 18922/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.7.gate_proj:  52%|█████▏    | 18923/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.7.up_proj:  52%|█████▏    | 18924/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.7.down_proj:  52%|█████▏    | 18925/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.8.gate_proj:  52%|█████▏    | 18926/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.8.up_proj:  52%|█████▏    | 18927/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.8.down_proj:  52%|█████▏    | 18928/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.9.gate_proj:  52%|█████▏    | 18929/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.9.up_proj:  52%|█████▏    | 18930/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.9.down_proj:  52%|█████▏    | 18931/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.10.gate_proj:  52%|█████▏    | 18932/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.10.up_proj:  52%|█████▏    | 18933/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.10.down_proj:  52%|█████▏    | 18934/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.11.gate_proj:  52%|█████▏    | 18935/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.11.up_proj:  52%|█████▏    | 18936/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.11.down_proj:  52%|█████▏    | 18937/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.12.gate_proj:  52%|█████▏    | 18938/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.12.up_proj:  52%|█████▏    | 18939/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.12.down_proj:  52%|█████▏    | 18940/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.13.gate_proj:  52%|█████▏    | 18941/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.13.up_proj:  52%|█████▏    | 18942/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.13.down_proj:  52%|█████▏    | 18943/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.14.gate_proj:  52%|█████▏    | 18944/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.14.up_proj:  52%|█████▏    | 18945/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.14.down_proj:  52%|█████▏    | 18946/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.15.gate_proj:  52%|█████▏    | 18947/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.15.up_proj:  52%|█████▏    | 18948/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.15.down_proj:  52%|█████▏    | 18949/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.16.gate_proj:  52%|█████▏    | 18950/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.16.up_proj:  52%|█████▏    | 18951/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.16.down_proj:  52%|█████▏    | 18952/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.17.gate_proj:  52%|█████▏    | 18953/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.17.up_proj:  52%|█████▏    | 18954/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.17.down_proj:  52%|█████▏    | 18955/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.18.gate_proj:  52%|█████▏    | 18956/36566 [00:17<00:15, 1157.14it/s]
packing model.layers.48.mlp.experts.18.up_proj:  52%|█████▏    | 18957/36566 [00:17<00:15, 1157.14it/s]  
packing model.layers.48.mlp.experts.18.up_proj:  52%|█████▏    | 18958/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.18.down_proj:  52%|█████▏    | 18958/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.19.gate_proj:  52%|█████▏    | 18959/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.19.up_proj:  52%|█████▏    | 18960/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.19.down_proj:  52%|█████▏    | 18961/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.20.gate_proj:  52%|█████▏    | 18962/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.20.up_proj:  52%|█████▏    | 18963/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.20.down_proj:  52%|█████▏    | 18964/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.21.gate_proj:  52%|█████▏    | 18965/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.21.up_proj:  52%|█████▏    | 18966/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.21.down_proj:  52%|█████▏    | 18967/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.22.gate_proj:  52%|█████▏    | 18968/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.22.up_proj:  52%|█████▏    | 18969/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.22.down_proj:  52%|█████▏    | 18970/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.23.gate_proj:  52%|█████▏    | 18971/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.23.up_proj:  52%|█████▏    | 18972/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.23.down_proj:  52%|█████▏    | 18973/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.24.gate_proj:  52%|█████▏    | 18974/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.24.up_proj:  52%|█████▏    | 18975/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.24.down_proj:  52%|█████▏    | 18976/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.25.gate_proj:  52%|█████▏    | 18977/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.25.up_proj:  52%|█████▏    | 18978/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.25.down_proj:  52%|█████▏    | 18979/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.26.gate_proj:  52%|█████▏    | 18980/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.26.up_proj:  52%|█████▏    | 18981/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.26.down_proj:  52%|█████▏    | 18982/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.27.gate_proj:  52%|█████▏    | 18983/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.27.up_proj:  52%|█████▏    | 18984/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.27.down_proj:  52%|█████▏    | 18985/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.28.gate_proj:  52%|█████▏    | 18986/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.28.up_proj:  52%|█████▏    | 18987/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.28.down_proj:  52%|█████▏    | 18988/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.29.gate_proj:  52%|█████▏    | 18989/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.29.up_proj:  52%|█████▏    | 18990/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.29.down_proj:  52%|█████▏    | 18991/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.30.gate_proj:  52%|█████▏    | 18992/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.30.up_proj:  52%|█████▏    | 18993/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.30.down_proj:  52%|█████▏    | 18994/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.31.gate_proj:  52%|█████▏    | 18995/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.31.up_proj:  52%|█████▏    | 18996/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.31.down_proj:  52%|█████▏    | 18997/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.32.gate_proj:  52%|█████▏    | 18998/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.32.up_proj:  52%|█████▏    | 18999/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.32.down_proj:  52%|█████▏    | 19000/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.33.gate_proj:  52%|█████▏    | 19001/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.33.up_proj:  52%|█████▏    | 19002/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.33.down_proj:  52%|█████▏    | 19003/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.34.gate_proj:  52%|█████▏    | 19004/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.34.up_proj:  52%|█████▏    | 19005/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.34.down_proj:  52%|█████▏    | 19006/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.35.gate_proj:  52%|█████▏    | 19007/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.35.up_proj:  52%|█████▏    | 19008/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.35.down_proj:  52%|█████▏    | 19009/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.36.gate_proj:  52%|█████▏    | 19010/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.36.up_proj:  52%|█████▏    | 19011/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.36.down_proj:  52%|█████▏    | 19012/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.37.gate_proj:  52%|█████▏    | 19013/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.37.up_proj:  52%|█████▏    | 19014/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.37.down_proj:  52%|█████▏    | 19015/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.38.gate_proj:  52%|█████▏    | 19016/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.38.up_proj:  52%|█████▏    | 19017/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.38.down_proj:  52%|█████▏    | 19018/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.39.gate_proj:  52%|█████▏    | 19019/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.39.up_proj:  52%|█████▏    | 19020/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.39.down_proj:  52%|█████▏    | 19021/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.40.gate_proj:  52%|█████▏    | 19022/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.40.up_proj:  52%|█████▏    | 19023/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.40.down_proj:  52%|█████▏    | 19024/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.41.gate_proj:  52%|█████▏    | 19025/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.41.up_proj:  52%|█████▏    | 19026/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.41.down_proj:  52%|█████▏    | 19027/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.42.gate_proj:  52%|█████▏    | 19028/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.42.up_proj:  52%|█████▏    | 19029/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.42.down_proj:  52%|█████▏    | 19030/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.43.gate_proj:  52%|█████▏    | 19031/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.43.up_proj:  52%|█████▏    | 19032/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.43.down_proj:  52%|█████▏    | 19033/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.44.gate_proj:  52%|█████▏    | 19034/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.44.up_proj:  52%|█████▏    | 19035/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.44.down_proj:  52%|█████▏    | 19036/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.45.gate_proj:  52%|█████▏    | 19037/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.45.up_proj:  52%|█████▏    | 19038/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.45.down_proj:  52%|█████▏    | 19039/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.46.gate_proj:  52%|█████▏    | 19040/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.46.up_proj:  52%|█████▏    | 19041/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.46.down_proj:  52%|█████▏    | 19042/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.47.gate_proj:  52%|█████▏    | 19043/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.47.up_proj:  52%|█████▏    | 19044/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.47.down_proj:  52%|█████▏    | 19045/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.48.gate_proj:  52%|█████▏    | 19046/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.48.up_proj:  52%|█████▏    | 19047/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.48.down_proj:  52%|█████▏    | 19048/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.49.gate_proj:  52%|█████▏    | 19049/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.49.up_proj:  52%|█████▏    | 19050/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.49.down_proj:  52%|█████▏    | 19051/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.50.gate_proj:  52%|█████▏    | 19052/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.50.up_proj:  52%|█████▏    | 19053/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.50.down_proj:  52%|█████▏    | 19054/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.51.gate_proj:  52%|█████▏    | 19055/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.51.up_proj:  52%|█████▏    | 19056/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.51.down_proj:  52%|█████▏    | 19057/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.52.gate_proj:  52%|█████▏    | 19058/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.52.up_proj:  52%|█████▏    | 19059/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.52.down_proj:  52%|█████▏    | 19060/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.53.gate_proj:  52%|█████▏    | 19061/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.53.up_proj:  52%|█████▏    | 19062/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.53.down_proj:  52%|█████▏    | 19063/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.54.gate_proj:  52%|█████▏    | 19064/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.54.up_proj:  52%|█████▏    | 19065/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.54.down_proj:  52%|█████▏    | 19066/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.55.gate_proj:  52%|█████▏    | 19067/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.55.up_proj:  52%|█████▏    | 19068/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.55.down_proj:  52%|█████▏    | 19069/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.56.gate_proj:  52%|█████▏    | 19070/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.56.up_proj:  52%|█████▏    | 19071/36566 [00:17<00:15, 1156.02it/s]  
packing model.layers.48.mlp.experts.56.down_proj:  52%|█████▏    | 19072/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.57.gate_proj:  52%|█████▏    | 19073/36566 [00:17<00:15, 1156.02it/s]
packing model.layers.48.mlp.experts.57.gate_proj:  52%|█████▏    | 19074/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.57.up_proj:  52%|█████▏    | 19074/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.57.down_proj:  52%|█████▏    | 19075/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.58.gate_proj:  52%|█████▏    | 19076/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.58.up_proj:  52%|█████▏    | 19077/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.58.down_proj:  52%|█████▏    | 19078/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.59.gate_proj:  52%|█████▏    | 19079/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.59.up_proj:  52%|█████▏    | 19080/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.59.down_proj:  52%|█████▏    | 19081/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.60.gate_proj:  52%|█████▏    | 19082/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.60.up_proj:  52%|█████▏    | 19083/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.60.down_proj:  52%|█████▏    | 19084/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.61.gate_proj:  52%|█████▏    | 19085/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.61.up_proj:  52%|█████▏    | 19086/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.61.down_proj:  52%|█████▏    | 19087/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.62.gate_proj:  52%|█████▏    | 19088/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.62.up_proj:  52%|█████▏    | 19089/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.62.down_proj:  52%|█████▏    | 19090/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.63.gate_proj:  52%|█████▏    | 19091/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.63.up_proj:  52%|█████▏    | 19092/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.63.down_proj:  52%|█████▏    | 19093/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.64.gate_proj:  52%|█████▏    | 19094/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.64.up_proj:  52%|█████▏    | 19095/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.64.down_proj:  52%|█████▏    | 19096/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.65.gate_proj:  52%|█████▏    | 19097/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.65.up_proj:  52%|█████▏    | 19098/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.65.down_proj:  52%|█████▏    | 19099/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.66.gate_proj:  52%|█████▏    | 19100/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.66.up_proj:  52%|█████▏    | 19101/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.66.down_proj:  52%|█████▏    | 19102/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.67.gate_proj:  52%|█████▏    | 19103/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.67.up_proj:  52%|█████▏    | 19104/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.67.down_proj:  52%|█████▏    | 19105/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.68.gate_proj:  52%|█████▏    | 19106/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.68.up_proj:  52%|█████▏    | 19107/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.68.down_proj:  52%|█████▏    | 19108/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.69.gate_proj:  52%|█████▏    | 19109/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.69.up_proj:  52%|█████▏    | 19110/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.69.down_proj:  52%|█████▏    | 19111/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.70.gate_proj:  52%|█████▏    | 19112/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.70.up_proj:  52%|█████▏    | 19113/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.70.down_proj:  52%|█████▏    | 19114/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.71.gate_proj:  52%|█████▏    | 19115/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.71.up_proj:  52%|█████▏    | 19116/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.71.down_proj:  52%|█████▏    | 19117/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.72.gate_proj:  52%|█████▏    | 19118/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.72.up_proj:  52%|█████▏    | 19119/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.72.down_proj:  52%|█████▏    | 19120/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.73.gate_proj:  52%|█████▏    | 19121/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.73.up_proj:  52%|█████▏    | 19122/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.73.down_proj:  52%|█████▏    | 19123/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.74.gate_proj:  52%|█████▏    | 19124/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.74.up_proj:  52%|█████▏    | 19125/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.74.down_proj:  52%|█████▏    | 19126/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.75.gate_proj:  52%|█████▏    | 19127/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.75.up_proj:  52%|█████▏    | 19128/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.75.down_proj:  52%|█████▏    | 19129/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.76.gate_proj:  52%|█████▏    | 19130/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.76.up_proj:  52%|█████▏    | 19131/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.76.down_proj:  52%|█████▏    | 19132/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.77.gate_proj:  52%|█████▏    | 19133/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.77.up_proj:  52%|█████▏    | 19134/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.77.down_proj:  52%|█████▏    | 19135/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.78.gate_proj:  52%|█████▏    | 19136/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.78.up_proj:  52%|█████▏    | 19137/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.78.down_proj:  52%|█████▏    | 19138/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.79.gate_proj:  52%|█████▏    | 19139/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.79.up_proj:  52%|█████▏    | 19140/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.79.down_proj:  52%|█████▏    | 19141/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.80.gate_proj:  52%|█████▏    | 19142/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.80.up_proj:  52%|█████▏    | 19143/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.80.down_proj:  52%|█████▏    | 19144/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.81.gate_proj:  52%|█████▏    | 19145/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.81.up_proj:  52%|█████▏    | 19146/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.81.down_proj:  52%|█████▏    | 19147/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.82.gate_proj:  52%|█████▏    | 19148/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.82.up_proj:  52%|█████▏    | 19149/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.82.down_proj:  52%|█████▏    | 19150/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.83.gate_proj:  52%|█████▏    | 19151/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.83.up_proj:  52%|█████▏    | 19152/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.83.down_proj:  52%|█████▏    | 19153/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.84.gate_proj:  52%|█████▏    | 19154/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.84.up_proj:  52%|█████▏    | 19155/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.84.down_proj:  52%|█████▏    | 19156/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.85.gate_proj:  52%|█████▏    | 19157/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.85.up_proj:  52%|█████▏    | 19158/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.85.down_proj:  52%|█████▏    | 19159/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.86.gate_proj:  52%|█████▏    | 19160/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.86.up_proj:  52%|█████▏    | 19161/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.86.down_proj:  52%|█████▏    | 19162/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.87.gate_proj:  52%|█████▏    | 19163/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.87.up_proj:  52%|█████▏    | 19164/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.87.down_proj:  52%|█████▏    | 19165/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.88.gate_proj:  52%|█████▏    | 19166/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.88.up_proj:  52%|█████▏    | 19167/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.88.down_proj:  52%|█████▏    | 19168/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.89.gate_proj:  52%|█████▏    | 19169/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.89.up_proj:  52%|█████▏    | 19170/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.89.down_proj:  52%|█████▏    | 19171/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.90.gate_proj:  52%|█████▏    | 19172/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.90.up_proj:  52%|█████▏    | 19173/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.90.down_proj:  52%|█████▏    | 19174/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.91.gate_proj:  52%|█████▏    | 19175/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.91.up_proj:  52%|█████▏    | 19176/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.91.down_proj:  52%|█████▏    | 19177/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.92.gate_proj:  52%|█████▏    | 19178/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.92.up_proj:  52%|█████▏    | 19179/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.92.down_proj:  52%|█████▏    | 19180/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.93.gate_proj:  52%|█████▏    | 19181/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.93.up_proj:  52%|█████▏    | 19182/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.93.down_proj:  52%|█████▏    | 19183/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.94.gate_proj:  52%|█████▏    | 19184/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.94.up_proj:  52%|█████▏    | 19185/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.94.down_proj:  52%|█████▏    | 19186/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.95.gate_proj:  52%|█████▏    | 19187/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.95.up_proj:  52%|█████▏    | 19188/36566 [00:17<00:15, 1156.79it/s]  
packing model.layers.48.mlp.experts.95.down_proj:  52%|█████▏    | 19189/36566 [00:17<00:15, 1156.79it/s]
packing model.layers.48.mlp.experts.95.down_proj:  52%|█████▏    | 19190/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.96.gate_proj:  52%|█████▏    | 19190/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.96.up_proj:  52%|█████▏    | 19191/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.96.down_proj:  52%|█████▏    | 19192/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.97.gate_proj:  52%|█████▏    | 19193/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.97.up_proj:  52%|█████▏    | 19194/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.97.down_proj:  52%|█████▏    | 19195/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.98.gate_proj:  52%|█████▏    | 19196/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.98.up_proj:  52%|█████▏    | 19197/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.98.down_proj:  53%|█████▎    | 19198/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.99.gate_proj:  53%|█████▎    | 19199/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.99.up_proj:  53%|█████▎    | 19200/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.99.down_proj:  53%|█████▎    | 19201/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.100.gate_proj:  53%|█████▎    | 19202/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.100.up_proj:  53%|█████▎    | 19203/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.100.down_proj:  53%|█████▎    | 19204/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.101.gate_proj:  53%|█████▎    | 19205/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.101.up_proj:  53%|█████▎    | 19206/36566 [00:17<00:15, 1157.21it/s]  
packing model.layers.48.mlp.experts.101.down_proj:  53%|█████▎    | 19207/36566 [00:17<00:15, 1157.21it/s]
packing model.layers.48.mlp.experts.102.gate_proj:  53%|█████▎    | 19208/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.102.up_proj:  53%|█████▎    | 19209/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.102.down_proj:  53%|█████▎    | 19210/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.103.gate_proj:  53%|█████▎    | 19211/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.103.up_proj:  53%|█████▎    | 19212/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.103.down_proj:  53%|█████▎    | 19213/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.104.gate_proj:  53%|█████▎    | 19214/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.104.up_proj:  53%|█████▎    | 19215/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.104.down_proj:  53%|█████▎    | 19216/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.105.gate_proj:  53%|█████▎    | 19217/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.105.up_proj:  53%|█████▎    | 19218/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.105.down_proj:  53%|█████▎    | 19219/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.106.gate_proj:  53%|█████▎    | 19220/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.106.up_proj:  53%|█████▎    | 19221/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.106.down_proj:  53%|█████▎    | 19222/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.107.gate_proj:  53%|█████▎    | 19223/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.107.up_proj:  53%|█████▎    | 19224/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.107.down_proj:  53%|█████▎    | 19225/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.108.gate_proj:  53%|█████▎    | 19226/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.108.up_proj:  53%|█████▎    | 19227/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.108.down_proj:  53%|█████▎    | 19228/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.109.gate_proj:  53%|█████▎    | 19229/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.109.up_proj:  53%|█████▎    | 19230/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.109.down_proj:  53%|█████▎    | 19231/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.110.gate_proj:  53%|█████▎    | 19232/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.110.up_proj:  53%|█████▎    | 19233/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.110.down_proj:  53%|█████▎    | 19234/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.111.gate_proj:  53%|█████▎    | 19235/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.111.up_proj:  53%|█████▎    | 19236/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.111.down_proj:  53%|█████▎    | 19237/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.112.gate_proj:  53%|█████▎    | 19238/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.112.up_proj:  53%|█████▎    | 19239/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.112.down_proj:  53%|█████▎    | 19240/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.113.gate_proj:  53%|█████▎    | 19241/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.113.up_proj:  53%|█████▎    | 19242/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.113.down_proj:  53%|█████▎    | 19243/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.114.gate_proj:  53%|█████▎    | 19244/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.114.up_proj:  53%|█████▎    | 19245/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.114.down_proj:  53%|█████▎    | 19246/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.115.gate_proj:  53%|█████▎    | 19247/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.115.up_proj:  53%|█████▎    | 19248/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.115.down_proj:  53%|█████▎    | 19249/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.116.gate_proj:  53%|█████▎    | 19250/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.116.up_proj:  53%|█████▎    | 19251/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.116.down_proj:  53%|█████▎    | 19252/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.117.gate_proj:  53%|█████▎    | 19253/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.117.up_proj:  53%|█████▎    | 19254/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.117.down_proj:  53%|█████▎    | 19255/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.118.gate_proj:  53%|█████▎    | 19256/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.118.up_proj:  53%|█████▎    | 19257/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.118.down_proj:  53%|█████▎    | 19258/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.119.gate_proj:  53%|█████▎    | 19259/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.119.up_proj:  53%|█████▎    | 19260/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.119.down_proj:  53%|█████▎    | 19261/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.120.gate_proj:  53%|█████▎    | 19262/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.120.up_proj:  53%|█████▎    | 19263/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.120.down_proj:  53%|█████▎    | 19264/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.121.gate_proj:  53%|█████▎    | 19265/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.121.up_proj:  53%|█████▎    | 19266/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.121.down_proj:  53%|█████▎    | 19267/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.122.gate_proj:  53%|█████▎    | 19268/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.122.up_proj:  53%|█████▎    | 19269/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.122.down_proj:  53%|█████▎    | 19270/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.123.gate_proj:  53%|█████▎    | 19271/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.123.up_proj:  53%|█████▎    | 19272/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.123.down_proj:  53%|█████▎    | 19273/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.124.gate_proj:  53%|█████▎    | 19274/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.124.up_proj:  53%|█████▎    | 19275/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.124.down_proj:  53%|█████▎    | 19276/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.125.gate_proj:  53%|█████▎    | 19277/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.125.up_proj:  53%|█████▎    | 19278/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.125.down_proj:  53%|█████▎    | 19279/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.126.gate_proj:  53%|█████▎    | 19280/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.126.up_proj:  53%|█████▎    | 19281/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.126.down_proj:  53%|█████▎    | 19282/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.127.gate_proj:  53%|█████▎    | 19283/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.48.mlp.experts.127.up_proj:  53%|█████▎    | 19284/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.48.mlp.experts.127.down_proj:  53%|█████▎    | 19285/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.0.gate_proj:  53%|█████▎    | 19286/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.0.up_proj:  53%|█████▎    | 19287/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.0.down_proj:  53%|█████▎    | 19288/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.1.gate_proj:  53%|█████▎    | 19289/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.1.up_proj:  53%|█████▎    | 19290/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.1.down_proj:  53%|█████▎    | 19291/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.2.gate_proj:  53%|█████▎    | 19292/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.2.up_proj:  53%|█████▎    | 19293/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.2.down_proj:  53%|█████▎    | 19294/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.3.gate_proj:  53%|█████▎    | 19295/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.3.up_proj:  53%|█████▎    | 19296/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.3.down_proj:  53%|█████▎    | 19297/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.4.gate_proj:  53%|█████▎    | 19298/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.4.up_proj:  53%|█████▎    | 19299/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.4.down_proj:  53%|█████▎    | 19300/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.5.gate_proj:  53%|█████▎    | 19301/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.5.up_proj:  53%|█████▎    | 19302/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.5.down_proj:  53%|█████▎    | 19303/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.6.gate_proj:  53%|█████▎    | 19304/36566 [00:17<00:14, 1157.21it/s]
packing model.layers.49.mlp.experts.6.up_proj:  53%|█████▎    | 19305/36566 [00:17<00:14, 1157.21it/s]  
packing model.layers.49.mlp.experts.6.up_proj:  53%|█████▎    | 19306/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.6.down_proj:  53%|█████▎    | 19306/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.7.gate_proj:  53%|█████▎    | 19307/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.7.up_proj:  53%|█████▎    | 19308/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.7.down_proj:  53%|█████▎    | 19309/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.8.gate_proj:  53%|█████▎    | 19310/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.8.up_proj:  53%|█████▎    | 19311/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.8.down_proj:  53%|█████▎    | 19312/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.9.gate_proj:  53%|█████▎    | 19313/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.9.up_proj:  53%|█████▎    | 19314/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.9.down_proj:  53%|█████▎    | 19315/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.10.gate_proj:  53%|█████▎    | 19316/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.10.up_proj:  53%|█████▎    | 19317/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.10.down_proj:  53%|█████▎    | 19318/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.11.gate_proj:  53%|█████▎    | 19319/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.11.up_proj:  53%|█████▎    | 19320/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.11.down_proj:  53%|█████▎    | 19321/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.12.gate_proj:  53%|█████▎    | 19322/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.12.up_proj:  53%|█████▎    | 19323/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.12.down_proj:  53%|█████▎    | 19324/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.13.gate_proj:  53%|█████▎    | 19325/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.13.up_proj:  53%|█████▎    | 19326/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.13.down_proj:  53%|█████▎    | 19327/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.14.gate_proj:  53%|█████▎    | 19328/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.14.up_proj:  53%|█████▎    | 19329/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.14.down_proj:  53%|█████▎    | 19330/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.15.gate_proj:  53%|█████▎    | 19331/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.15.up_proj:  53%|█████▎    | 19332/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.15.down_proj:  53%|█████▎    | 19333/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.16.gate_proj:  53%|█████▎    | 19334/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.16.up_proj:  53%|█████▎    | 19335/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.16.down_proj:  53%|█████▎    | 19336/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.17.gate_proj:  53%|█████▎    | 19337/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.17.up_proj:  53%|█████▎    | 19338/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.17.down_proj:  53%|█████▎    | 19339/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.18.gate_proj:  53%|█████▎    | 19340/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.18.up_proj:  53%|█████▎    | 19341/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.18.down_proj:  53%|█████▎    | 19342/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.19.gate_proj:  53%|█████▎    | 19343/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.19.up_proj:  53%|█████▎    | 19344/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.19.down_proj:  53%|█████▎    | 19345/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.20.gate_proj:  53%|█████▎    | 19346/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.20.up_proj:  53%|█████▎    | 19347/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.20.down_proj:  53%|█████▎    | 19348/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.21.gate_proj:  53%|█████▎    | 19349/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.21.up_proj:  53%|█████▎    | 19350/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.21.down_proj:  53%|█████▎    | 19351/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.22.gate_proj:  53%|█████▎    | 19352/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.22.up_proj:  53%|█████▎    | 19353/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.22.down_proj:  53%|█████▎    | 19354/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.23.gate_proj:  53%|█████▎    | 19355/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.23.up_proj:  53%|█████▎    | 19356/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.23.down_proj:  53%|█████▎    | 19357/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.24.gate_proj:  53%|█████▎    | 19358/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.24.up_proj:  53%|█████▎    | 19359/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.24.down_proj:  53%|█████▎    | 19360/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.25.gate_proj:  53%|█████▎    | 19361/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.25.up_proj:  53%|█████▎    | 19362/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.25.down_proj:  53%|█████▎    | 19363/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.26.gate_proj:  53%|█████▎    | 19364/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.26.up_proj:  53%|█████▎    | 19365/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.26.down_proj:  53%|█████▎    | 19366/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.27.gate_proj:  53%|█████▎    | 19367/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.27.up_proj:  53%|█████▎    | 19368/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.27.down_proj:  53%|█████▎    | 19369/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.28.gate_proj:  53%|█████▎    | 19370/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.28.up_proj:  53%|█████▎    | 19371/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.28.down_proj:  53%|█████▎    | 19372/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.29.gate_proj:  53%|█████▎    | 19373/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.29.up_proj:  53%|█████▎    | 19374/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.29.down_proj:  53%|█████▎    | 19375/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.30.gate_proj:  53%|█████▎    | 19376/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.30.up_proj:  53%|█████▎    | 19377/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.30.down_proj:  53%|█████▎    | 19378/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.31.gate_proj:  53%|█████▎    | 19379/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.31.up_proj:  53%|█████▎    | 19380/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.31.down_proj:  53%|█████▎    | 19381/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.32.gate_proj:  53%|█████▎    | 19382/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.32.up_proj:  53%|█████▎    | 19383/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.32.down_proj:  53%|█████▎    | 19384/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.33.gate_proj:  53%|█████▎    | 19385/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.33.up_proj:  53%|█████▎    | 19386/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.33.down_proj:  53%|█████▎    | 19387/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.34.gate_proj:  53%|█████▎    | 19388/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.34.up_proj:  53%|█████▎    | 19389/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.34.down_proj:  53%|█████▎    | 19390/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.35.gate_proj:  53%|█████▎    | 19391/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.35.up_proj:  53%|█████▎    | 19392/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.35.down_proj:  53%|█████▎    | 19393/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.36.gate_proj:  53%|█████▎    | 19394/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.36.up_proj:  53%|█████▎    | 19395/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.36.down_proj:  53%|█████▎    | 19396/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.37.gate_proj:  53%|█████▎    | 19397/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.37.up_proj:  53%|█████▎    | 19398/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.37.down_proj:  53%|█████▎    | 19399/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.38.gate_proj:  53%|█████▎    | 19400/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.38.up_proj:  53%|█████▎    | 19401/36566 [00:17<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.38.down_proj:  53%|█████▎    | 19402/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.39.gate_proj:  53%|█████▎    | 19403/36566 [00:17<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.39.up_proj:  53%|█████▎    | 19404/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.39.down_proj:  53%|█████▎    | 19405/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.40.gate_proj:  53%|█████▎    | 19406/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.40.up_proj:  53%|█████▎    | 19407/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.40.down_proj:  53%|█████▎    | 19408/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.41.gate_proj:  53%|█████▎    | 19409/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.41.up_proj:  53%|█████▎    | 19410/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.41.down_proj:  53%|█████▎    | 19411/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.42.gate_proj:  53%|█████▎    | 19412/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.42.up_proj:  53%|█████▎    | 19413/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.42.down_proj:  53%|█████▎    | 19414/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.43.gate_proj:  53%|█████▎    | 19415/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.43.up_proj:  53%|█████▎    | 19416/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.43.down_proj:  53%|█████▎    | 19417/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.44.gate_proj:  53%|█████▎    | 19418/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.44.up_proj:  53%|█████▎    | 19419/36566 [00:18<00:14, 1157.92it/s]  
packing model.layers.49.mlp.experts.44.down_proj:  53%|█████▎    | 19420/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.45.gate_proj:  53%|█████▎    | 19421/36566 [00:18<00:14, 1157.92it/s]
packing model.layers.49.mlp.experts.45.gate_proj:  53%|█████▎    | 19422/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.45.up_proj:  53%|█████▎    | 19422/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.45.down_proj:  53%|█████▎    | 19423/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.46.gate_proj:  53%|█████▎    | 19424/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.46.up_proj:  53%|█████▎    | 19425/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.46.down_proj:  53%|█████▎    | 19426/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.47.gate_proj:  53%|█████▎    | 19427/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.47.up_proj:  53%|█████▎    | 19428/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.47.down_proj:  53%|█████▎    | 19429/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.48.gate_proj:  53%|█████▎    | 19430/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.48.up_proj:  53%|█████▎    | 19431/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.48.down_proj:  53%|█████▎    | 19432/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.49.gate_proj:  53%|█████▎    | 19433/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.49.up_proj:  53%|█████▎    | 19434/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.49.down_proj:  53%|█████▎    | 19435/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.50.gate_proj:  53%|█████▎    | 19436/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.50.up_proj:  53%|█████▎    | 19437/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.50.down_proj:  53%|█████▎    | 19438/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.51.gate_proj:  53%|█████▎    | 19439/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.51.up_proj:  53%|█████▎    | 19440/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.51.down_proj:  53%|█████▎    | 19441/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.52.gate_proj:  53%|█████▎    | 19442/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.52.up_proj:  53%|█████▎    | 19443/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.52.down_proj:  53%|█████▎    | 19444/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.53.gate_proj:  53%|█████▎    | 19445/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.53.up_proj:  53%|█████▎    | 19446/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.53.down_proj:  53%|█████▎    | 19447/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.54.gate_proj:  53%|█████▎    | 19448/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.54.up_proj:  53%|█████▎    | 19449/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.54.down_proj:  53%|█████▎    | 19450/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.55.gate_proj:  53%|█████▎    | 19451/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.55.up_proj:  53%|█████▎    | 19452/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.55.down_proj:  53%|█████▎    | 19453/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.56.gate_proj:  53%|█████▎    | 19454/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.56.up_proj:  53%|█████▎    | 19455/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.56.down_proj:  53%|█████▎    | 19456/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.57.gate_proj:  53%|█████▎    | 19457/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.57.up_proj:  53%|█████▎    | 19458/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.57.down_proj:  53%|█████▎    | 19459/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.58.gate_proj:  53%|█████▎    | 19460/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.58.up_proj:  53%|█████▎    | 19461/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.58.down_proj:  53%|█████▎    | 19462/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.59.gate_proj:  53%|█████▎    | 19463/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.59.up_proj:  53%|█████▎    | 19464/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.59.down_proj:  53%|█████▎    | 19465/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.60.gate_proj:  53%|█████▎    | 19466/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.60.up_proj:  53%|█████▎    | 19467/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.60.down_proj:  53%|█████▎    | 19468/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.61.gate_proj:  53%|█████▎    | 19469/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.61.up_proj:  53%|█████▎    | 19470/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.61.down_proj:  53%|█████▎    | 19471/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.62.gate_proj:  53%|█████▎    | 19472/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.62.up_proj:  53%|█████▎    | 19473/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.62.down_proj:  53%|█████▎    | 19474/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.63.gate_proj:  53%|█████▎    | 19475/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.63.up_proj:  53%|█████▎    | 19476/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.63.down_proj:  53%|█████▎    | 19477/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.64.gate_proj:  53%|█████▎    | 19478/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.64.up_proj:  53%|█████▎    | 19479/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.64.down_proj:  53%|█████▎    | 19480/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.65.gate_proj:  53%|█████▎    | 19481/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.65.up_proj:  53%|█████▎    | 19482/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.65.down_proj:  53%|█████▎    | 19483/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.66.gate_proj:  53%|█████▎    | 19484/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.66.up_proj:  53%|█████▎    | 19485/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.66.down_proj:  53%|█████▎    | 19486/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.67.gate_proj:  53%|█████▎    | 19487/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.67.up_proj:  53%|█████▎    | 19488/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.67.down_proj:  53%|█████▎    | 19489/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.68.gate_proj:  53%|█████▎    | 19490/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.68.up_proj:  53%|█████▎    | 19491/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.68.down_proj:  53%|█████▎    | 19492/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.69.gate_proj:  53%|█████▎    | 19493/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.69.up_proj:  53%|█████▎    | 19494/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.69.down_proj:  53%|█████▎    | 19495/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.70.gate_proj:  53%|█████▎    | 19496/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.70.up_proj:  53%|█████▎    | 19497/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.70.down_proj:  53%|█████▎    | 19498/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.71.gate_proj:  53%|█████▎    | 19499/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.71.up_proj:  53%|█████▎    | 19500/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.71.down_proj:  53%|█████▎    | 19501/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.72.gate_proj:  53%|█████▎    | 19502/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.72.up_proj:  53%|█████▎    | 19503/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.72.down_proj:  53%|█████▎    | 19504/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.73.gate_proj:  53%|█████▎    | 19505/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.73.up_proj:  53%|█████▎    | 19506/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.73.down_proj:  53%|█████▎    | 19507/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.74.gate_proj:  53%|█████▎    | 19508/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.74.up_proj:  53%|█████▎    | 19509/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.74.down_proj:  53%|█████▎    | 19510/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.75.gate_proj:  53%|█████▎    | 19511/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.75.up_proj:  53%|█████▎    | 19512/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.75.down_proj:  53%|█████▎    | 19513/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.76.gate_proj:  53%|█████▎    | 19514/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.76.up_proj:  53%|█████▎    | 19515/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.76.down_proj:  53%|█████▎    | 19516/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.77.gate_proj:  53%|█████▎    | 19517/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.77.up_proj:  53%|█████▎    | 19518/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.77.down_proj:  53%|█████▎    | 19519/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.78.gate_proj:  53%|█████▎    | 19520/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.78.up_proj:  53%|█████▎    | 19521/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.78.down_proj:  53%|█████▎    | 19522/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.79.gate_proj:  53%|█████▎    | 19523/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.79.up_proj:  53%|█████▎    | 19524/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.79.down_proj:  53%|█████▎    | 19525/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.80.gate_proj:  53%|█████▎    | 19526/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.80.up_proj:  53%|█████▎    | 19527/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.80.down_proj:  53%|█████▎    | 19528/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.81.gate_proj:  53%|█████▎    | 19529/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.81.up_proj:  53%|█████▎    | 19530/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.81.down_proj:  53%|█████▎    | 19531/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.82.gate_proj:  53%|█████▎    | 19532/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.82.up_proj:  53%|█████▎    | 19533/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.82.down_proj:  53%|█████▎    | 19534/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.83.gate_proj:  53%|█████▎    | 19535/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.83.up_proj:  53%|█████▎    | 19536/36566 [00:18<00:14, 1157.10it/s]  
packing model.layers.49.mlp.experts.83.down_proj:  53%|█████▎    | 19537/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.84.gate_proj:  53%|█████▎    | 19538/36566 [00:18<00:14, 1157.10it/s]
packing model.layers.49.mlp.experts.84.gate_proj:  53%|█████▎    | 19539/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.84.up_proj:  53%|█████▎    | 19539/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.84.down_proj:  53%|█████▎    | 19540/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.85.gate_proj:  53%|█████▎    | 19541/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.85.up_proj:  53%|█████▎    | 19542/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.85.down_proj:  53%|█████▎    | 19543/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.86.gate_proj:  53%|█████▎    | 19544/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.86.up_proj:  53%|█████▎    | 19545/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.86.down_proj:  53%|█████▎    | 19546/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.87.gate_proj:  53%|█████▎    | 19547/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.87.up_proj:  53%|█████▎    | 19548/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.87.down_proj:  53%|█████▎    | 19549/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.88.gate_proj:  53%|█████▎    | 19550/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.88.up_proj:  53%|█████▎    | 19551/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.88.down_proj:  53%|█████▎    | 19552/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.89.gate_proj:  53%|█████▎    | 19553/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.89.up_proj:  53%|█████▎    | 19554/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.89.down_proj:  53%|█████▎    | 19555/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.90.gate_proj:  53%|█████▎    | 19556/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.90.up_proj:  53%|█████▎    | 19557/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.90.down_proj:  53%|█████▎    | 19558/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.91.gate_proj:  53%|█████▎    | 19559/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.91.up_proj:  53%|█████▎    | 19560/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.91.down_proj:  53%|█████▎    | 19561/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.92.gate_proj:  53%|█████▎    | 19562/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.92.up_proj:  54%|█████▎    | 19563/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.92.down_proj:  54%|█████▎    | 19564/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.93.gate_proj:  54%|█████▎    | 19565/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.93.up_proj:  54%|█████▎    | 19566/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.93.down_proj:  54%|█████▎    | 19567/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.94.gate_proj:  54%|█████▎    | 19568/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.94.up_proj:  54%|█████▎    | 19569/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.94.down_proj:  54%|█████▎    | 19570/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.95.gate_proj:  54%|█████▎    | 19571/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.95.up_proj:  54%|█████▎    | 19572/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.95.down_proj:  54%|█████▎    | 19573/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.96.gate_proj:  54%|█████▎    | 19574/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.96.up_proj:  54%|█████▎    | 19575/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.96.down_proj:  54%|█████▎    | 19576/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.97.gate_proj:  54%|█████▎    | 19577/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.97.up_proj:  54%|█████▎    | 19578/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.97.down_proj:  54%|█████▎    | 19579/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.98.gate_proj:  54%|█████▎    | 19580/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.98.up_proj:  54%|█████▎    | 19581/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.98.down_proj:  54%|█████▎    | 19582/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.99.gate_proj:  54%|█████▎    | 19583/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.99.up_proj:  54%|█████▎    | 19584/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.99.down_proj:  54%|█████▎    | 19585/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.100.gate_proj:  54%|█████▎    | 19586/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.100.up_proj:  54%|█████▎    | 19587/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.100.down_proj:  54%|█████▎    | 19588/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.101.gate_proj:  54%|█████▎    | 19589/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.101.up_proj:  54%|█████▎    | 19590/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.101.down_proj:  54%|█████▎    | 19591/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.102.gate_proj:  54%|█████▎    | 19592/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.102.up_proj:  54%|█████▎    | 19593/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.102.down_proj:  54%|█████▎    | 19594/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.103.gate_proj:  54%|█████▎    | 19595/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.103.up_proj:  54%|█████▎    | 19596/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.103.down_proj:  54%|█████▎    | 19597/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.104.gate_proj:  54%|█████▎    | 19598/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.104.up_proj:  54%|█████▎    | 19599/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.104.down_proj:  54%|█████▎    | 19600/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.105.gate_proj:  54%|█████▎    | 19601/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.105.up_proj:  54%|█████▎    | 19602/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.105.down_proj:  54%|█████▎    | 19603/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.106.gate_proj:  54%|█████▎    | 19604/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.106.up_proj:  54%|█████▎    | 19605/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.106.down_proj:  54%|█████▎    | 19606/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.107.gate_proj:  54%|█████▎    | 19607/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.107.up_proj:  54%|█████▎    | 19608/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.107.down_proj:  54%|█████▎    | 19609/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.108.gate_proj:  54%|█████▎    | 19610/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.108.up_proj:  54%|█████▎    | 19611/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.108.down_proj:  54%|█████▎    | 19612/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.109.gate_proj:  54%|█████▎    | 19613/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.109.up_proj:  54%|█████▎    | 19614/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.109.down_proj:  54%|█████▎    | 19615/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.110.gate_proj:  54%|█████▎    | 19616/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.110.up_proj:  54%|█████▎    | 19617/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.110.down_proj:  54%|█████▎    | 19618/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.111.gate_proj:  54%|█████▎    | 19619/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.111.up_proj:  54%|█████▎    | 19620/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.111.down_proj:  54%|█████▎    | 19621/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.112.gate_proj:  54%|█████▎    | 19622/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.112.up_proj:  54%|█████▎    | 19623/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.112.down_proj:  54%|█████▎    | 19624/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.113.gate_proj:  54%|█████▎    | 19625/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.113.up_proj:  54%|█████▎    | 19626/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.113.down_proj:  54%|█████▎    | 19627/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.114.gate_proj:  54%|█████▎    | 19628/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.114.up_proj:  54%|█████▎    | 19629/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.114.down_proj:  54%|█████▎    | 19630/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.115.gate_proj:  54%|█████▎    | 19631/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.115.up_proj:  54%|█████▎    | 19632/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.115.down_proj:  54%|█████▎    | 19633/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.116.gate_proj:  54%|█████▎    | 19634/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.116.up_proj:  54%|█████▎    | 19635/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.116.down_proj:  54%|█████▎    | 19636/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.117.gate_proj:  54%|█████▎    | 19637/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.117.up_proj:  54%|█████▎    | 19638/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.117.down_proj:  54%|█████▎    | 19639/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.118.gate_proj:  54%|█████▎    | 19640/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.118.up_proj:  54%|█████▎    | 19641/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.118.down_proj:  54%|█████▎    | 19642/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.119.gate_proj:  54%|█████▎    | 19643/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.119.up_proj:  54%|█████▎    | 19644/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.119.down_proj:  54%|█████▎    | 19645/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.120.gate_proj:  54%|█████▎    | 19646/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.120.up_proj:  54%|█████▎    | 19647/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.120.down_proj:  54%|█████▎    | 19648/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.121.gate_proj:  54%|█████▎    | 19649/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.121.up_proj:  54%|█████▎    | 19650/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.121.down_proj:  54%|█████▎    | 19651/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.122.gate_proj:  54%|█████▎    | 19652/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.122.up_proj:  54%|█████▎    | 19653/36566 [00:18<00:14, 1158.88it/s]  
packing model.layers.49.mlp.experts.122.down_proj:  54%|█████▎    | 19654/36566 [00:18<00:14, 1158.88it/s]
packing model.layers.49.mlp.experts.122.down_proj:  54%|█████▍    | 19655/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.123.gate_proj:  54%|█████▍    | 19655/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.123.up_proj:  54%|█████▍    | 19656/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.49.mlp.experts.123.down_proj:  54%|█████▍    | 19657/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.124.gate_proj:  54%|█████▍    | 19658/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.124.up_proj:  54%|█████▍    | 19659/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.49.mlp.experts.124.down_proj:  54%|█████▍    | 19660/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.125.gate_proj:  54%|█████▍    | 19661/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.125.up_proj:  54%|█████▍    | 19662/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.49.mlp.experts.125.down_proj:  54%|█████▍    | 19663/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.126.gate_proj:  54%|█████▍    | 19664/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.126.up_proj:  54%|█████▍    | 19665/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.49.mlp.experts.126.down_proj:  54%|█████▍    | 19666/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.127.gate_proj:  54%|█████▍    | 19667/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.49.mlp.experts.127.up_proj:  54%|█████▍    | 19668/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.49.mlp.experts.127.down_proj:  54%|█████▍    | 19669/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.0.gate_proj:  54%|█████▍    | 19670/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.0.up_proj:  54%|█████▍    | 19671/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.0.down_proj:  54%|█████▍    | 19672/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.1.gate_proj:  54%|█████▍    | 19673/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.1.up_proj:  54%|█████▍    | 19674/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.1.down_proj:  54%|█████▍    | 19675/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.2.gate_proj:  54%|█████▍    | 19676/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.2.up_proj:  54%|█████▍    | 19677/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.2.down_proj:  54%|█████▍    | 19678/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.3.gate_proj:  54%|█████▍    | 19679/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.3.up_proj:  54%|█████▍    | 19680/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.3.down_proj:  54%|█████▍    | 19681/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.4.gate_proj:  54%|█████▍    | 19682/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.4.up_proj:  54%|█████▍    | 19683/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.4.down_proj:  54%|█████▍    | 19684/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.5.gate_proj:  54%|█████▍    | 19685/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.5.up_proj:  54%|█████▍    | 19686/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.5.down_proj:  54%|█████▍    | 19687/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.6.gate_proj:  54%|█████▍    | 19688/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.6.up_proj:  54%|█████▍    | 19689/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.6.down_proj:  54%|█████▍    | 19690/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.7.gate_proj:  54%|█████▍    | 19691/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.7.up_proj:  54%|█████▍    | 19692/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.7.down_proj:  54%|█████▍    | 19693/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.8.gate_proj:  54%|█████▍    | 19694/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.8.up_proj:  54%|█████▍    | 19695/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.8.down_proj:  54%|█████▍    | 19696/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.9.gate_proj:  54%|█████▍    | 19697/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.9.up_proj:  54%|█████▍    | 19698/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.9.down_proj:  54%|█████▍    | 19699/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.10.gate_proj:  54%|█████▍    | 19700/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.10.up_proj:  54%|█████▍    | 19701/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.10.down_proj:  54%|█████▍    | 19702/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.11.gate_proj:  54%|█████▍    | 19703/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.11.up_proj:  54%|█████▍    | 19704/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.11.down_proj:  54%|█████▍    | 19705/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.12.gate_proj:  54%|█████▍    | 19706/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.12.up_proj:  54%|█████▍    | 19707/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.12.down_proj:  54%|█████▍    | 19708/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.13.gate_proj:  54%|█████▍    | 19709/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.13.up_proj:  54%|█████▍    | 19710/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.13.down_proj:  54%|█████▍    | 19711/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.14.gate_proj:  54%|█████▍    | 19712/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.14.up_proj:  54%|█████▍    | 19713/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.14.down_proj:  54%|█████▍    | 19714/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.15.gate_proj:  54%|█████▍    | 19715/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.15.up_proj:  54%|█████▍    | 19716/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.15.down_proj:  54%|█████▍    | 19717/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.16.gate_proj:  54%|█████▍    | 19718/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.16.up_proj:  54%|█████▍    | 19719/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.16.down_proj:  54%|█████▍    | 19720/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.17.gate_proj:  54%|█████▍    | 19721/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.17.up_proj:  54%|█████▍    | 19722/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.17.down_proj:  54%|█████▍    | 19723/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.18.gate_proj:  54%|█████▍    | 19724/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.18.up_proj:  54%|█████▍    | 19725/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.18.down_proj:  54%|█████▍    | 19726/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.19.gate_proj:  54%|█████▍    | 19727/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.19.up_proj:  54%|█████▍    | 19728/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.19.down_proj:  54%|█████▍    | 19729/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.20.gate_proj:  54%|█████▍    | 19730/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.20.up_proj:  54%|█████▍    | 19731/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.20.down_proj:  54%|█████▍    | 19732/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.21.gate_proj:  54%|█████▍    | 19733/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.21.up_proj:  54%|█████▍    | 19734/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.21.down_proj:  54%|█████▍    | 19735/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.22.gate_proj:  54%|█████▍    | 19736/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.22.up_proj:  54%|█████▍    | 19737/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.22.down_proj:  54%|█████▍    | 19738/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.23.gate_proj:  54%|█████▍    | 19739/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.23.up_proj:  54%|█████▍    | 19740/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.23.down_proj:  54%|█████▍    | 19741/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.24.gate_proj:  54%|█████▍    | 19742/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.24.up_proj:  54%|█████▍    | 19743/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.24.down_proj:  54%|█████▍    | 19744/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.25.gate_proj:  54%|█████▍    | 19745/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.25.up_proj:  54%|█████▍    | 19746/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.25.down_proj:  54%|█████▍    | 19747/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.26.gate_proj:  54%|█████▍    | 19748/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.26.up_proj:  54%|█████▍    | 19749/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.26.down_proj:  54%|█████▍    | 19750/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.27.gate_proj:  54%|█████▍    | 19751/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.27.up_proj:  54%|█████▍    | 19752/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.27.down_proj:  54%|█████▍    | 19753/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.28.gate_proj:  54%|█████▍    | 19754/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.28.up_proj:  54%|█████▍    | 19755/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.28.down_proj:  54%|█████▍    | 19756/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.29.gate_proj:  54%|█████▍    | 19757/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.29.up_proj:  54%|█████▍    | 19758/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.29.down_proj:  54%|█████▍    | 19759/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.30.gate_proj:  54%|█████▍    | 19760/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.30.up_proj:  54%|█████▍    | 19761/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.30.down_proj:  54%|█████▍    | 19762/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.31.gate_proj:  54%|█████▍    | 19763/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.31.up_proj:  54%|█████▍    | 19764/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.31.down_proj:  54%|█████▍    | 19765/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.32.gate_proj:  54%|█████▍    | 19766/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.32.up_proj:  54%|█████▍    | 19767/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.32.down_proj:  54%|█████▍    | 19768/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.33.gate_proj:  54%|█████▍    | 19769/36566 [00:18<00:14, 1159.05it/s]
packing model.layers.50.mlp.experts.33.up_proj:  54%|█████▍    | 19770/36566 [00:18<00:14, 1159.05it/s]  
packing model.layers.50.mlp.experts.33.up_proj:  54%|█████▍    | 19771/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.33.down_proj:  54%|█████▍    | 19771/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.34.gate_proj:  54%|█████▍    | 19772/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.34.up_proj:  54%|█████▍    | 19773/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.34.down_proj:  54%|█████▍    | 19774/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.35.gate_proj:  54%|█████▍    | 19775/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.35.up_proj:  54%|█████▍    | 19776/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.35.down_proj:  54%|█████▍    | 19777/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.36.gate_proj:  54%|█████▍    | 19778/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.36.up_proj:  54%|█████▍    | 19779/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.36.down_proj:  54%|█████▍    | 19780/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.37.gate_proj:  54%|█████▍    | 19781/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.37.up_proj:  54%|█████▍    | 19782/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.37.down_proj:  54%|█████▍    | 19783/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.38.gate_proj:  54%|█████▍    | 19784/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.38.up_proj:  54%|█████▍    | 19785/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.38.down_proj:  54%|█████▍    | 19786/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.39.gate_proj:  54%|█████▍    | 19787/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.39.up_proj:  54%|█████▍    | 19788/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.39.down_proj:  54%|█████▍    | 19789/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.40.gate_proj:  54%|█████▍    | 19790/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.40.up_proj:  54%|█████▍    | 19791/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.40.down_proj:  54%|█████▍    | 19792/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.41.gate_proj:  54%|█████▍    | 19793/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.41.up_proj:  54%|█████▍    | 19794/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.41.down_proj:  54%|█████▍    | 19795/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.42.gate_proj:  54%|█████▍    | 19796/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.42.up_proj:  54%|█████▍    | 19797/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.42.down_proj:  54%|█████▍    | 19798/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.43.gate_proj:  54%|█████▍    | 19799/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.43.up_proj:  54%|█████▍    | 19800/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.43.down_proj:  54%|█████▍    | 19801/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.44.gate_proj:  54%|█████▍    | 19802/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.44.up_proj:  54%|█████▍    | 19803/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.44.down_proj:  54%|█████▍    | 19804/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.45.gate_proj:  54%|█████▍    | 19805/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.45.up_proj:  54%|█████▍    | 19806/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.45.down_proj:  54%|█████▍    | 19807/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.46.gate_proj:  54%|█████▍    | 19808/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.46.up_proj:  54%|█████▍    | 19809/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.46.down_proj:  54%|█████▍    | 19810/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.47.gate_proj:  54%|█████▍    | 19811/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.47.up_proj:  54%|█████▍    | 19812/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.47.down_proj:  54%|█████▍    | 19813/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.48.gate_proj:  54%|█████▍    | 19814/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.48.up_proj:  54%|█████▍    | 19815/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.48.down_proj:  54%|█████▍    | 19816/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.49.gate_proj:  54%|█████▍    | 19817/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.49.up_proj:  54%|█████▍    | 19818/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.49.down_proj:  54%|█████▍    | 19819/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.50.gate_proj:  54%|█████▍    | 19820/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.50.up_proj:  54%|█████▍    | 19821/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.50.down_proj:  54%|█████▍    | 19822/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.51.gate_proj:  54%|█████▍    | 19823/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.51.up_proj:  54%|█████▍    | 19824/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.51.down_proj:  54%|█████▍    | 19825/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.52.gate_proj:  54%|█████▍    | 19826/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.52.up_proj:  54%|█████▍    | 19827/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.52.down_proj:  54%|█████▍    | 19828/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.53.gate_proj:  54%|█████▍    | 19829/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.53.up_proj:  54%|█████▍    | 19830/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.53.down_proj:  54%|█████▍    | 19831/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.54.gate_proj:  54%|█████▍    | 19832/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.54.up_proj:  54%|█████▍    | 19833/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.54.down_proj:  54%|█████▍    | 19834/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.55.gate_proj:  54%|█████▍    | 19835/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.55.up_proj:  54%|█████▍    | 19836/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.55.down_proj:  54%|█████▍    | 19837/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.56.gate_proj:  54%|█████▍    | 19838/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.56.up_proj:  54%|█████▍    | 19839/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.56.down_proj:  54%|█████▍    | 19840/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.57.gate_proj:  54%|█████▍    | 19841/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.57.up_proj:  54%|█████▍    | 19842/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.57.down_proj:  54%|█████▍    | 19843/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.58.gate_proj:  54%|█████▍    | 19844/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.58.up_proj:  54%|█████▍    | 19845/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.58.down_proj:  54%|█████▍    | 19846/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.59.gate_proj:  54%|█████▍    | 19847/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.59.up_proj:  54%|█████▍    | 19848/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.59.down_proj:  54%|█████▍    | 19849/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.60.gate_proj:  54%|█████▍    | 19850/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.60.up_proj:  54%|█████▍    | 19851/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.60.down_proj:  54%|█████▍    | 19852/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.61.gate_proj:  54%|█████▍    | 19853/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.61.up_proj:  54%|█████▍    | 19854/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.61.down_proj:  54%|█████▍    | 19855/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.62.gate_proj:  54%|█████▍    | 19856/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.62.up_proj:  54%|█████▍    | 19857/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.62.down_proj:  54%|█████▍    | 19858/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.63.gate_proj:  54%|█████▍    | 19859/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.63.up_proj:  54%|█████▍    | 19860/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.63.down_proj:  54%|█████▍    | 19861/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.64.gate_proj:  54%|█████▍    | 19862/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.64.up_proj:  54%|█████▍    | 19863/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.64.down_proj:  54%|█████▍    | 19864/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.65.gate_proj:  54%|█████▍    | 19865/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.65.up_proj:  54%|█████▍    | 19866/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.65.down_proj:  54%|█████▍    | 19867/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.66.gate_proj:  54%|█████▍    | 19868/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.66.up_proj:  54%|█████▍    | 19869/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.66.down_proj:  54%|█████▍    | 19870/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.67.gate_proj:  54%|█████▍    | 19871/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.67.up_proj:  54%|█████▍    | 19872/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.67.down_proj:  54%|█████▍    | 19873/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.68.gate_proj:  54%|█████▍    | 19874/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.68.up_proj:  54%|█████▍    | 19875/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.68.down_proj:  54%|█████▍    | 19876/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.69.gate_proj:  54%|█████▍    | 19877/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.69.up_proj:  54%|█████▍    | 19878/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.69.down_proj:  54%|█████▍    | 19879/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.70.gate_proj:  54%|█████▍    | 19880/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.70.up_proj:  54%|█████▍    | 19881/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.70.down_proj:  54%|█████▍    | 19882/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.71.gate_proj:  54%|█████▍    | 19883/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.71.up_proj:  54%|█████▍    | 19884/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.71.down_proj:  54%|█████▍    | 19885/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.72.gate_proj:  54%|█████▍    | 19886/36566 [00:18<00:14, 1157.70it/s]
packing model.layers.50.mlp.experts.72.up_proj:  54%|█████▍    | 19887/36566 [00:18<00:14, 1157.70it/s]  
packing model.layers.50.mlp.experts.72.up_proj:  54%|█████▍    | 19888/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.72.down_proj:  54%|█████▍    | 19888/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.73.gate_proj:  54%|█████▍    | 19889/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.73.up_proj:  54%|█████▍    | 19890/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.73.down_proj:  54%|█████▍    | 19891/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.74.gate_proj:  54%|█████▍    | 19892/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.74.up_proj:  54%|█████▍    | 19893/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.74.down_proj:  54%|█████▍    | 19894/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.75.gate_proj:  54%|█████▍    | 19895/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.75.up_proj:  54%|█████▍    | 19896/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.75.down_proj:  54%|█████▍    | 19897/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.76.gate_proj:  54%|█████▍    | 19898/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.76.up_proj:  54%|█████▍    | 19899/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.76.down_proj:  54%|█████▍    | 19900/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.77.gate_proj:  54%|█████▍    | 19901/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.77.up_proj:  54%|█████▍    | 19902/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.77.down_proj:  54%|█████▍    | 19903/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.78.gate_proj:  54%|█████▍    | 19904/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.78.up_proj:  54%|█████▍    | 19905/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.78.down_proj:  54%|█████▍    | 19906/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.79.gate_proj:  54%|█████▍    | 19907/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.79.up_proj:  54%|█████▍    | 19908/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.79.down_proj:  54%|█████▍    | 19909/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.80.gate_proj:  54%|█████▍    | 19910/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.80.up_proj:  54%|█████▍    | 19911/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.80.down_proj:  54%|█████▍    | 19912/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.81.gate_proj:  54%|█████▍    | 19913/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.81.up_proj:  54%|█████▍    | 19914/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.81.down_proj:  54%|█████▍    | 19915/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.82.gate_proj:  54%|█████▍    | 19916/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.82.up_proj:  54%|█████▍    | 19917/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.82.down_proj:  54%|█████▍    | 19918/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.83.gate_proj:  54%|█████▍    | 19919/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.83.up_proj:  54%|█████▍    | 19920/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.83.down_proj:  54%|█████▍    | 19921/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.84.gate_proj:  54%|█████▍    | 19922/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.84.up_proj:  54%|█████▍    | 19923/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.84.down_proj:  54%|█████▍    | 19924/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.85.gate_proj:  54%|█████▍    | 19925/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.85.up_proj:  54%|█████▍    | 19926/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.85.down_proj:  54%|█████▍    | 19927/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.86.gate_proj:  54%|█████▍    | 19928/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.86.up_proj:  55%|█████▍    | 19929/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.86.down_proj:  55%|█████▍    | 19930/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.87.gate_proj:  55%|█████▍    | 19931/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.87.up_proj:  55%|█████▍    | 19932/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.87.down_proj:  55%|█████▍    | 19933/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.88.gate_proj:  55%|█████▍    | 19934/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.88.up_proj:  55%|█████▍    | 19935/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.88.down_proj:  55%|█████▍    | 19936/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.89.gate_proj:  55%|█████▍    | 19937/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.89.up_proj:  55%|█████▍    | 19938/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.89.down_proj:  55%|█████▍    | 19939/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.90.gate_proj:  55%|█████▍    | 19940/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.90.up_proj:  55%|█████▍    | 19941/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.90.down_proj:  55%|█████▍    | 19942/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.91.gate_proj:  55%|█████▍    | 19943/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.91.up_proj:  55%|█████▍    | 19944/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.91.down_proj:  55%|█████▍    | 19945/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.92.gate_proj:  55%|█████▍    | 19946/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.92.up_proj:  55%|█████▍    | 19947/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.92.down_proj:  55%|█████▍    | 19948/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.93.gate_proj:  55%|█████▍    | 19949/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.93.up_proj:  55%|█████▍    | 19950/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.93.down_proj:  55%|█████▍    | 19951/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.94.gate_proj:  55%|█████▍    | 19952/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.94.up_proj:  55%|█████▍    | 19953/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.94.down_proj:  55%|█████▍    | 19954/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.95.gate_proj:  55%|█████▍    | 19955/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.95.up_proj:  55%|█████▍    | 19956/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.95.down_proj:  55%|█████▍    | 19957/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.96.gate_proj:  55%|█████▍    | 19958/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.96.up_proj:  55%|█████▍    | 19959/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.96.down_proj:  55%|█████▍    | 19960/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.97.gate_proj:  55%|█████▍    | 19961/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.97.up_proj:  55%|█████▍    | 19962/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.97.down_proj:  55%|█████▍    | 19963/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.98.gate_proj:  55%|█████▍    | 19964/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.98.up_proj:  55%|█████▍    | 19965/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.98.down_proj:  55%|█████▍    | 19966/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.99.gate_proj:  55%|█████▍    | 19967/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.99.up_proj:  55%|█████▍    | 19968/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.99.down_proj:  55%|█████▍    | 19969/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.100.gate_proj:  55%|█████▍    | 19970/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.100.up_proj:  55%|█████▍    | 19971/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.100.down_proj:  55%|█████▍    | 19972/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.101.gate_proj:  55%|█████▍    | 19973/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.101.up_proj:  55%|█████▍    | 19974/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.101.down_proj:  55%|█████▍    | 19975/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.102.gate_proj:  55%|█████▍    | 19976/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.102.up_proj:  55%|█████▍    | 19977/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.102.down_proj:  55%|█████▍    | 19978/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.103.gate_proj:  55%|█████▍    | 19979/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.103.up_proj:  55%|█████▍    | 19980/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.103.down_proj:  55%|█████▍    | 19981/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.104.gate_proj:  55%|█████▍    | 19982/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.104.up_proj:  55%|█████▍    | 19983/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.104.down_proj:  55%|█████▍    | 19984/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.105.gate_proj:  55%|█████▍    | 19985/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.105.up_proj:  55%|█████▍    | 19986/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.105.down_proj:  55%|█████▍    | 19987/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.106.gate_proj:  55%|█████▍    | 19988/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.106.up_proj:  55%|█████▍    | 19989/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.106.down_proj:  55%|█████▍    | 19990/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.107.gate_proj:  55%|█████▍    | 19991/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.107.up_proj:  55%|█████▍    | 19992/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.107.down_proj:  55%|█████▍    | 19993/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.108.gate_proj:  55%|█████▍    | 19994/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.108.up_proj:  55%|█████▍    | 19995/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.108.down_proj:  55%|█████▍    | 19996/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.109.gate_proj:  55%|█████▍    | 19997/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.109.up_proj:  55%|█████▍    | 19998/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.109.down_proj:  55%|█████▍    | 19999/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.110.gate_proj:  55%|█████▍    | 20000/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.110.up_proj:  55%|█████▍    | 20001/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.110.down_proj:  55%|█████▍    | 20002/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.111.gate_proj:  55%|█████▍    | 20003/36566 [00:18<00:14, 1158.98it/s]
packing model.layers.50.mlp.experts.111.up_proj:  55%|█████▍    | 20004/36566 [00:18<00:14, 1158.98it/s]  
packing model.layers.50.mlp.experts.111.up_proj:  55%|█████▍    | 20005/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.111.down_proj:  55%|█████▍    | 20005/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.112.gate_proj:  55%|█████▍    | 20006/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.112.up_proj:  55%|█████▍    | 20007/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.112.down_proj:  55%|█████▍    | 20008/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.113.gate_proj:  55%|█████▍    | 20009/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.113.up_proj:  55%|█████▍    | 20010/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.113.down_proj:  55%|█████▍    | 20011/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.114.gate_proj:  55%|█████▍    | 20012/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.114.up_proj:  55%|█████▍    | 20013/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.114.down_proj:  55%|█████▍    | 20014/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.115.gate_proj:  55%|█████▍    | 20015/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.115.up_proj:  55%|█████▍    | 20016/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.115.down_proj:  55%|█████▍    | 20017/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.116.gate_proj:  55%|█████▍    | 20018/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.116.up_proj:  55%|█████▍    | 20019/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.116.down_proj:  55%|█████▍    | 20020/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.117.gate_proj:  55%|█████▍    | 20021/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.117.up_proj:  55%|█████▍    | 20022/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.117.down_proj:  55%|█████▍    | 20023/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.118.gate_proj:  55%|█████▍    | 20024/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.118.up_proj:  55%|█████▍    | 20025/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.118.down_proj:  55%|█████▍    | 20026/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.119.gate_proj:  55%|█████▍    | 20027/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.119.up_proj:  55%|█████▍    | 20028/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.119.down_proj:  55%|█████▍    | 20029/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.120.gate_proj:  55%|█████▍    | 20030/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.120.up_proj:  55%|█████▍    | 20031/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.120.down_proj:  55%|█████▍    | 20032/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.121.gate_proj:  55%|█████▍    | 20033/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.121.up_proj:  55%|█████▍    | 20034/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.121.down_proj:  55%|█████▍    | 20035/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.122.gate_proj:  55%|█████▍    | 20036/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.122.up_proj:  55%|█████▍    | 20037/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.122.down_proj:  55%|█████▍    | 20038/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.123.gate_proj:  55%|█████▍    | 20039/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.123.up_proj:  55%|█████▍    | 20040/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.123.down_proj:  55%|█████▍    | 20041/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.124.gate_proj:  55%|█████▍    | 20042/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.124.up_proj:  55%|█████▍    | 20043/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.124.down_proj:  55%|█████▍    | 20044/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.125.gate_proj:  55%|█████▍    | 20045/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.125.up_proj:  55%|█████▍    | 20046/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.125.down_proj:  55%|█████▍    | 20047/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.126.gate_proj:  55%|█████▍    | 20048/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.126.up_proj:  55%|█████▍    | 20049/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.126.down_proj:  55%|█████▍    | 20050/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.127.gate_proj:  55%|█████▍    | 20051/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.50.mlp.experts.127.up_proj:  55%|█████▍    | 20052/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.50.mlp.experts.127.down_proj:  55%|█████▍    | 20053/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.0.gate_proj:  55%|█████▍    | 20054/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.0.up_proj:  55%|█████▍    | 20055/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.0.down_proj:  55%|█████▍    | 20056/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.1.gate_proj:  55%|█████▍    | 20057/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.1.up_proj:  55%|█████▍    | 20058/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.1.down_proj:  55%|█████▍    | 20059/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.2.gate_proj:  55%|█████▍    | 20060/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.2.up_proj:  55%|█████▍    | 20061/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.2.down_proj:  55%|█████▍    | 20062/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.3.gate_proj:  55%|█████▍    | 20063/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.3.up_proj:  55%|█████▍    | 20064/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.3.down_proj:  55%|█████▍    | 20065/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.4.gate_proj:  55%|█████▍    | 20066/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.4.up_proj:  55%|█████▍    | 20067/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.4.down_proj:  55%|█████▍    | 20068/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.5.gate_proj:  55%|█████▍    | 20069/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.5.up_proj:  55%|█████▍    | 20070/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.5.down_proj:  55%|█████▍    | 20071/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.6.gate_proj:  55%|█████▍    | 20072/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.6.up_proj:  55%|█████▍    | 20073/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.6.down_proj:  55%|█████▍    | 20074/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.7.gate_proj:  55%|█████▍    | 20075/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.7.up_proj:  55%|█████▍    | 20076/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.7.down_proj:  55%|█████▍    | 20077/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.8.gate_proj:  55%|█████▍    | 20078/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.8.up_proj:  55%|█████▍    | 20079/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.8.down_proj:  55%|█████▍    | 20080/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.9.gate_proj:  55%|█████▍    | 20081/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.9.up_proj:  55%|█████▍    | 20082/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.9.down_proj:  55%|█████▍    | 20083/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.10.gate_proj:  55%|█████▍    | 20084/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.10.up_proj:  55%|█████▍    | 20085/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.10.down_proj:  55%|█████▍    | 20086/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.11.gate_proj:  55%|█████▍    | 20087/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.11.up_proj:  55%|█████▍    | 20088/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.11.down_proj:  55%|█████▍    | 20089/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.12.gate_proj:  55%|█████▍    | 20090/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.12.up_proj:  55%|█████▍    | 20091/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.12.down_proj:  55%|█████▍    | 20092/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.13.gate_proj:  55%|█████▍    | 20093/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.13.up_proj:  55%|█████▍    | 20094/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.13.down_proj:  55%|█████▍    | 20095/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.14.gate_proj:  55%|█████▍    | 20096/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.14.up_proj:  55%|█████▍    | 20097/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.14.down_proj:  55%|█████▍    | 20098/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.15.gate_proj:  55%|█████▍    | 20099/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.15.up_proj:  55%|█████▍    | 20100/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.15.down_proj:  55%|█████▍    | 20101/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.16.gate_proj:  55%|█████▍    | 20102/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.16.up_proj:  55%|█████▍    | 20103/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.16.down_proj:  55%|█████▍    | 20104/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.17.gate_proj:  55%|█████▍    | 20105/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.17.up_proj:  55%|█████▍    | 20106/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.17.down_proj:  55%|█████▍    | 20107/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.18.gate_proj:  55%|█████▍    | 20108/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.18.up_proj:  55%|█████▍    | 20109/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.18.down_proj:  55%|█████▍    | 20110/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.19.gate_proj:  55%|█████▍    | 20111/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.19.up_proj:  55%|█████▌    | 20112/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.19.down_proj:  55%|█████▌    | 20113/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.20.gate_proj:  55%|█████▌    | 20114/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.20.up_proj:  55%|█████▌    | 20115/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.20.down_proj:  55%|█████▌    | 20116/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.21.gate_proj:  55%|█████▌    | 20117/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.21.up_proj:  55%|█████▌    | 20118/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.21.down_proj:  55%|█████▌    | 20119/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.22.gate_proj:  55%|█████▌    | 20120/36566 [00:18<00:14, 1161.02it/s]
packing model.layers.51.mlp.experts.22.up_proj:  55%|█████▌    | 20121/36566 [00:18<00:14, 1161.02it/s]  
packing model.layers.51.mlp.experts.22.up_proj:  55%|█████▌    | 20122/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.22.down_proj:  55%|█████▌    | 20122/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.23.gate_proj:  55%|█████▌    | 20123/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.23.up_proj:  55%|█████▌    | 20124/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.23.down_proj:  55%|█████▌    | 20125/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.24.gate_proj:  55%|█████▌    | 20126/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.24.up_proj:  55%|█████▌    | 20127/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.24.down_proj:  55%|█████▌    | 20128/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.25.gate_proj:  55%|█████▌    | 20129/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.25.up_proj:  55%|█████▌    | 20130/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.25.down_proj:  55%|█████▌    | 20131/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.26.gate_proj:  55%|█████▌    | 20132/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.26.up_proj:  55%|█████▌    | 20133/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.26.down_proj:  55%|█████▌    | 20134/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.27.gate_proj:  55%|█████▌    | 20135/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.27.up_proj:  55%|█████▌    | 20136/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.27.down_proj:  55%|█████▌    | 20137/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.28.gate_proj:  55%|█████▌    | 20138/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.28.up_proj:  55%|█████▌    | 20139/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.28.down_proj:  55%|█████▌    | 20140/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.29.gate_proj:  55%|█████▌    | 20141/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.29.up_proj:  55%|█████▌    | 20142/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.29.down_proj:  55%|█████▌    | 20143/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.30.gate_proj:  55%|█████▌    | 20144/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.30.up_proj:  55%|█████▌    | 20145/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.30.down_proj:  55%|█████▌    | 20146/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.31.gate_proj:  55%|█████▌    | 20147/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.31.up_proj:  55%|█████▌    | 20148/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.31.down_proj:  55%|█████▌    | 20149/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.32.gate_proj:  55%|█████▌    | 20150/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.32.up_proj:  55%|█████▌    | 20151/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.32.down_proj:  55%|█████▌    | 20152/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.33.gate_proj:  55%|█████▌    | 20153/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.33.up_proj:  55%|█████▌    | 20154/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.33.down_proj:  55%|█████▌    | 20155/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.34.gate_proj:  55%|█████▌    | 20156/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.34.up_proj:  55%|█████▌    | 20157/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.34.down_proj:  55%|█████▌    | 20158/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.35.gate_proj:  55%|█████▌    | 20159/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.35.up_proj:  55%|█████▌    | 20160/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.35.down_proj:  55%|█████▌    | 20161/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.36.gate_proj:  55%|█████▌    | 20162/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.36.up_proj:  55%|█████▌    | 20163/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.36.down_proj:  55%|█████▌    | 20164/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.37.gate_proj:  55%|█████▌    | 20165/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.37.up_proj:  55%|█████▌    | 20166/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.37.down_proj:  55%|█████▌    | 20167/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.38.gate_proj:  55%|█████▌    | 20168/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.38.up_proj:  55%|█████▌    | 20169/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.38.down_proj:  55%|█████▌    | 20170/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.39.gate_proj:  55%|█████▌    | 20171/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.39.up_proj:  55%|█████▌    | 20172/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.39.down_proj:  55%|█████▌    | 20173/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.40.gate_proj:  55%|█████▌    | 20174/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.40.up_proj:  55%|█████▌    | 20175/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.40.down_proj:  55%|█████▌    | 20176/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.41.gate_proj:  55%|█████▌    | 20177/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.41.up_proj:  55%|█████▌    | 20178/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.41.down_proj:  55%|█████▌    | 20179/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.42.gate_proj:  55%|█████▌    | 20180/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.42.up_proj:  55%|█████▌    | 20181/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.42.down_proj:  55%|█████▌    | 20182/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.43.gate_proj:  55%|█████▌    | 20183/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.43.up_proj:  55%|█████▌    | 20184/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.43.down_proj:  55%|█████▌    | 20185/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.44.gate_proj:  55%|█████▌    | 20186/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.44.up_proj:  55%|█████▌    | 20187/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.44.down_proj:  55%|█████▌    | 20188/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.45.gate_proj:  55%|█████▌    | 20189/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.45.up_proj:  55%|█████▌    | 20190/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.45.down_proj:  55%|█████▌    | 20191/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.46.gate_proj:  55%|█████▌    | 20192/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.46.up_proj:  55%|█████▌    | 20193/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.46.down_proj:  55%|█████▌    | 20194/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.47.gate_proj:  55%|█████▌    | 20195/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.47.up_proj:  55%|█████▌    | 20196/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.47.down_proj:  55%|█████▌    | 20197/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.48.gate_proj:  55%|█████▌    | 20198/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.48.up_proj:  55%|█████▌    | 20199/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.48.down_proj:  55%|█████▌    | 20200/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.49.gate_proj:  55%|█████▌    | 20201/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.49.up_proj:  55%|█████▌    | 20202/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.49.down_proj:  55%|█████▌    | 20203/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.50.gate_proj:  55%|█████▌    | 20204/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.50.up_proj:  55%|█████▌    | 20205/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.50.down_proj:  55%|█████▌    | 20206/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.51.gate_proj:  55%|█████▌    | 20207/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.51.up_proj:  55%|█████▌    | 20208/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.51.down_proj:  55%|█████▌    | 20209/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.52.gate_proj:  55%|█████▌    | 20210/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.52.up_proj:  55%|█████▌    | 20211/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.52.down_proj:  55%|█████▌    | 20212/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.53.gate_proj:  55%|█████▌    | 20213/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.53.up_proj:  55%|█████▌    | 20214/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.53.down_proj:  55%|█████▌    | 20215/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.54.gate_proj:  55%|█████▌    | 20216/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.54.up_proj:  55%|█████▌    | 20217/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.54.down_proj:  55%|█████▌    | 20218/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.55.gate_proj:  55%|█████▌    | 20219/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.55.up_proj:  55%|█████▌    | 20220/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.55.down_proj:  55%|█████▌    | 20221/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.56.gate_proj:  55%|█████▌    | 20222/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.56.up_proj:  55%|█████▌    | 20223/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.56.down_proj:  55%|█████▌    | 20224/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.57.gate_proj:  55%|█████▌    | 20225/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.57.up_proj:  55%|█████▌    | 20226/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.57.down_proj:  55%|█████▌    | 20227/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.58.gate_proj:  55%|█████▌    | 20228/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.58.up_proj:  55%|█████▌    | 20229/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.58.down_proj:  55%|█████▌    | 20230/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.59.gate_proj:  55%|█████▌    | 20231/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.59.up_proj:  55%|█████▌    | 20232/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.59.down_proj:  55%|█████▌    | 20233/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.60.gate_proj:  55%|█████▌    | 20234/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.60.up_proj:  55%|█████▌    | 20235/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.60.down_proj:  55%|█████▌    | 20236/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.61.gate_proj:  55%|█████▌    | 20237/36566 [00:18<00:14, 1160.36it/s]
packing model.layers.51.mlp.experts.61.up_proj:  55%|█████▌    | 20238/36566 [00:18<00:14, 1160.36it/s]  
packing model.layers.51.mlp.experts.61.up_proj:  55%|█████▌    | 20239/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.61.down_proj:  55%|█████▌    | 20239/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.62.gate_proj:  55%|█████▌    | 20240/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.62.up_proj:  55%|█████▌    | 20241/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.62.down_proj:  55%|█████▌    | 20242/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.63.gate_proj:  55%|█████▌    | 20243/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.63.up_proj:  55%|█████▌    | 20244/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.63.down_proj:  55%|█████▌    | 20245/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.64.gate_proj:  55%|█████▌    | 20246/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.64.up_proj:  55%|█████▌    | 20247/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.64.down_proj:  55%|█████▌    | 20248/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.65.gate_proj:  55%|█████▌    | 20249/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.65.up_proj:  55%|█████▌    | 20250/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.65.down_proj:  55%|█████▌    | 20251/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.66.gate_proj:  55%|█████▌    | 20252/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.66.up_proj:  55%|█████▌    | 20253/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.66.down_proj:  55%|█████▌    | 20254/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.67.gate_proj:  55%|█████▌    | 20255/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.67.up_proj:  55%|█████▌    | 20256/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.67.down_proj:  55%|█████▌    | 20257/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.68.gate_proj:  55%|█████▌    | 20258/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.68.up_proj:  55%|█████▌    | 20259/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.68.down_proj:  55%|█████▌    | 20260/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.69.gate_proj:  55%|█████▌    | 20261/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.69.up_proj:  55%|█████▌    | 20262/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.69.down_proj:  55%|█████▌    | 20263/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.70.gate_proj:  55%|█████▌    | 20264/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.70.up_proj:  55%|█████▌    | 20265/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.70.down_proj:  55%|█████▌    | 20266/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.71.gate_proj:  55%|█████▌    | 20267/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.71.up_proj:  55%|█████▌    | 20268/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.71.down_proj:  55%|█████▌    | 20269/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.72.gate_proj:  55%|█████▌    | 20270/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.72.up_proj:  55%|█████▌    | 20271/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.72.down_proj:  55%|█████▌    | 20272/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.73.gate_proj:  55%|█████▌    | 20273/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.73.up_proj:  55%|█████▌    | 20274/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.73.down_proj:  55%|█████▌    | 20275/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.74.gate_proj:  55%|█████▌    | 20276/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.74.up_proj:  55%|█████▌    | 20277/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.74.down_proj:  55%|█████▌    | 20278/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.75.gate_proj:  55%|█████▌    | 20279/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.75.up_proj:  55%|█████▌    | 20280/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.75.down_proj:  55%|█████▌    | 20281/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.76.gate_proj:  55%|█████▌    | 20282/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.76.up_proj:  55%|█████▌    | 20283/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.76.down_proj:  55%|█████▌    | 20284/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.77.gate_proj:  55%|█████▌    | 20285/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.77.up_proj:  55%|█████▌    | 20286/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.77.down_proj:  55%|█████▌    | 20287/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.78.gate_proj:  55%|█████▌    | 20288/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.78.up_proj:  55%|█████▌    | 20289/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.78.down_proj:  55%|█████▌    | 20290/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.79.gate_proj:  55%|█████▌    | 20291/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.79.up_proj:  55%|█████▌    | 20292/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.79.down_proj:  55%|█████▌    | 20293/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.80.gate_proj:  55%|█████▌    | 20294/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.80.up_proj:  56%|█████▌    | 20295/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.80.down_proj:  56%|█████▌    | 20296/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.81.gate_proj:  56%|█████▌    | 20297/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.81.up_proj:  56%|█████▌    | 20298/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.81.down_proj:  56%|█████▌    | 20299/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.82.gate_proj:  56%|█████▌    | 20300/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.82.up_proj:  56%|█████▌    | 20301/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.82.down_proj:  56%|█████▌    | 20302/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.83.gate_proj:  56%|█████▌    | 20303/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.83.up_proj:  56%|█████▌    | 20304/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.83.down_proj:  56%|█████▌    | 20305/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.84.gate_proj:  56%|█████▌    | 20306/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.84.up_proj:  56%|█████▌    | 20307/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.84.down_proj:  56%|█████▌    | 20308/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.85.gate_proj:  56%|█████▌    | 20309/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.85.up_proj:  56%|█████▌    | 20310/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.85.down_proj:  56%|█████▌    | 20311/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.86.gate_proj:  56%|█████▌    | 20312/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.86.up_proj:  56%|█████▌    | 20313/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.86.down_proj:  56%|█████▌    | 20314/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.87.gate_proj:  56%|█████▌    | 20315/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.87.up_proj:  56%|█████▌    | 20316/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.87.down_proj:  56%|█████▌    | 20317/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.88.gate_proj:  56%|█████▌    | 20318/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.88.up_proj:  56%|█████▌    | 20319/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.88.down_proj:  56%|█████▌    | 20320/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.89.gate_proj:  56%|█████▌    | 20321/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.89.up_proj:  56%|█████▌    | 20322/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.89.down_proj:  56%|█████▌    | 20323/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.90.gate_proj:  56%|█████▌    | 20324/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.90.up_proj:  56%|█████▌    | 20325/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.90.down_proj:  56%|█████▌    | 20326/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.91.gate_proj:  56%|█████▌    | 20327/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.91.up_proj:  56%|█████▌    | 20328/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.91.down_proj:  56%|█████▌    | 20329/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.92.gate_proj:  56%|█████▌    | 20330/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.92.up_proj:  56%|█████▌    | 20331/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.92.down_proj:  56%|█████▌    | 20332/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.93.gate_proj:  56%|█████▌    | 20333/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.93.up_proj:  56%|█████▌    | 20334/36566 [00:18<00:14, 1159.29it/s]  
packing model.layers.51.mlp.experts.93.down_proj:  56%|█████▌    | 20335/36566 [00:18<00:14, 1159.29it/s]
packing model.layers.51.mlp.experts.94.gate_proj:  56%|█████▌    | 20336/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.94.up_proj:  56%|█████▌    | 20337/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.94.down_proj:  56%|█████▌    | 20338/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.95.gate_proj:  56%|█████▌    | 20339/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.95.up_proj:  56%|█████▌    | 20340/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.95.down_proj:  56%|█████▌    | 20341/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.96.gate_proj:  56%|█████▌    | 20342/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.96.up_proj:  56%|█████▌    | 20343/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.96.down_proj:  56%|█████▌    | 20344/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.97.gate_proj:  56%|█████▌    | 20345/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.97.up_proj:  56%|█████▌    | 20346/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.97.down_proj:  56%|█████▌    | 20347/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.98.gate_proj:  56%|█████▌    | 20348/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.98.up_proj:  56%|█████▌    | 20349/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.98.down_proj:  56%|█████▌    | 20350/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.99.gate_proj:  56%|█████▌    | 20351/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.99.up_proj:  56%|█████▌    | 20352/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.99.down_proj:  56%|█████▌    | 20353/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.100.gate_proj:  56%|█████▌    | 20354/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.100.up_proj:  56%|█████▌    | 20355/36566 [00:18<00:13, 1159.29it/s]  
packing model.layers.51.mlp.experts.100.down_proj:  56%|█████▌    | 20356/36566 [00:18<00:13, 1159.29it/s]
packing model.layers.51.mlp.experts.100.down_proj:  56%|█████▌    | 20357/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.101.gate_proj:  56%|█████▌    | 20357/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.101.up_proj:  56%|█████▌    | 20358/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.101.down_proj:  56%|█████▌    | 20359/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.102.gate_proj:  56%|█████▌    | 20360/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.102.up_proj:  56%|█████▌    | 20361/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.102.down_proj:  56%|█████▌    | 20362/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.103.gate_proj:  56%|█████▌    | 20363/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.103.up_proj:  56%|█████▌    | 20364/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.103.down_proj:  56%|█████▌    | 20365/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.104.gate_proj:  56%|█████▌    | 20366/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.104.up_proj:  56%|█████▌    | 20367/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.104.down_proj:  56%|█████▌    | 20368/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.105.gate_proj:  56%|█████▌    | 20369/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.105.up_proj:  56%|█████▌    | 20370/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.105.down_proj:  56%|█████▌    | 20371/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.106.gate_proj:  56%|█████▌    | 20372/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.106.up_proj:  56%|█████▌    | 20373/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.106.down_proj:  56%|█████▌    | 20374/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.107.gate_proj:  56%|█████▌    | 20375/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.107.up_proj:  56%|█████▌    | 20376/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.107.down_proj:  56%|█████▌    | 20377/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.108.gate_proj:  56%|█████▌    | 20378/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.108.up_proj:  56%|█████▌    | 20379/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.108.down_proj:  56%|█████▌    | 20380/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.109.gate_proj:  56%|█████▌    | 20381/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.109.up_proj:  56%|█████▌    | 20382/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.109.down_proj:  56%|█████▌    | 20383/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.110.gate_proj:  56%|█████▌    | 20384/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.110.up_proj:  56%|█████▌    | 20385/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.110.down_proj:  56%|█████▌    | 20386/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.111.gate_proj:  56%|█████▌    | 20387/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.111.up_proj:  56%|█████▌    | 20388/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.111.down_proj:  56%|█████▌    | 20389/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.112.gate_proj:  56%|█████▌    | 20390/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.112.up_proj:  56%|█████▌    | 20391/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.112.down_proj:  56%|█████▌    | 20392/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.113.gate_proj:  56%|█████▌    | 20393/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.113.up_proj:  56%|█████▌    | 20394/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.113.down_proj:  56%|█████▌    | 20395/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.114.gate_proj:  56%|█████▌    | 20396/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.114.up_proj:  56%|█████▌    | 20397/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.114.down_proj:  56%|█████▌    | 20398/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.115.gate_proj:  56%|█████▌    | 20399/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.115.up_proj:  56%|█████▌    | 20400/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.115.down_proj:  56%|█████▌    | 20401/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.116.gate_proj:  56%|█████▌    | 20402/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.116.up_proj:  56%|█████▌    | 20403/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.116.down_proj:  56%|█████▌    | 20404/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.117.gate_proj:  56%|█████▌    | 20405/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.117.up_proj:  56%|█████▌    | 20406/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.117.down_proj:  56%|█████▌    | 20407/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.118.gate_proj:  56%|█████▌    | 20408/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.118.up_proj:  56%|█████▌    | 20409/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.118.down_proj:  56%|█████▌    | 20410/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.119.gate_proj:  56%|█████▌    | 20411/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.119.up_proj:  56%|█████▌    | 20412/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.119.down_proj:  56%|█████▌    | 20413/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.120.gate_proj:  56%|█████▌    | 20414/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.120.up_proj:  56%|█████▌    | 20415/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.120.down_proj:  56%|█████▌    | 20416/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.121.gate_proj:  56%|█████▌    | 20417/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.121.up_proj:  56%|█████▌    | 20418/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.121.down_proj:  56%|█████▌    | 20419/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.122.gate_proj:  56%|█████▌    | 20420/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.122.up_proj:  56%|█████▌    | 20421/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.122.down_proj:  56%|█████▌    | 20422/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.123.gate_proj:  56%|█████▌    | 20423/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.123.up_proj:  56%|█████▌    | 20424/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.123.down_proj:  56%|█████▌    | 20425/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.124.gate_proj:  56%|█████▌    | 20426/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.124.up_proj:  56%|█████▌    | 20427/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.124.down_proj:  56%|█████▌    | 20428/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.125.gate_proj:  56%|█████▌    | 20429/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.125.up_proj:  56%|█████▌    | 20430/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.125.down_proj:  56%|█████▌    | 20431/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.126.gate_proj:  56%|█████▌    | 20432/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.126.up_proj:  56%|█████▌    | 20433/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.126.down_proj:  56%|█████▌    | 20434/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.127.gate_proj:  56%|█████▌    | 20435/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.51.mlp.experts.127.up_proj:  56%|█████▌    | 20436/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.51.mlp.experts.127.down_proj:  56%|█████▌    | 20437/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.0.gate_proj:  56%|█████▌    | 20438/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.0.up_proj:  56%|█████▌    | 20439/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.0.down_proj:  56%|█████▌    | 20440/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.1.gate_proj:  56%|█████▌    | 20441/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.1.up_proj:  56%|█████▌    | 20442/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.1.down_proj:  56%|█████▌    | 20443/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.2.gate_proj:  56%|█████▌    | 20444/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.2.up_proj:  56%|█████▌    | 20445/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.2.down_proj:  56%|█████▌    | 20446/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.3.gate_proj:  56%|█████▌    | 20447/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.3.up_proj:  56%|█████▌    | 20448/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.3.down_proj:  56%|█████▌    | 20449/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.4.gate_proj:  56%|█████▌    | 20450/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.4.up_proj:  56%|█████▌    | 20451/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.4.down_proj:  56%|█████▌    | 20452/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.5.gate_proj:  56%|█████▌    | 20453/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.5.up_proj:  56%|█████▌    | 20454/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.5.down_proj:  56%|█████▌    | 20455/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.6.gate_proj:  56%|█████▌    | 20456/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.6.up_proj:  56%|█████▌    | 20457/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.6.down_proj:  56%|█████▌    | 20458/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.7.gate_proj:  56%|█████▌    | 20459/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.7.up_proj:  56%|█████▌    | 20460/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.7.down_proj:  56%|█████▌    | 20461/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.8.gate_proj:  56%|█████▌    | 20462/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.8.up_proj:  56%|█████▌    | 20463/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.8.down_proj:  56%|█████▌    | 20464/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.9.gate_proj:  56%|█████▌    | 20465/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.9.up_proj:  56%|█████▌    | 20466/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.9.down_proj:  56%|█████▌    | 20467/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.10.gate_proj:  56%|█████▌    | 20468/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.10.up_proj:  56%|█████▌    | 20469/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.10.down_proj:  56%|█████▌    | 20470/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.11.gate_proj:  56%|█████▌    | 20471/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.11.up_proj:  56%|█████▌    | 20472/36566 [00:18<00:13, 1162.58it/s]  
packing model.layers.52.mlp.experts.11.down_proj:  56%|█████▌    | 20473/36566 [00:18<00:13, 1162.58it/s]
packing model.layers.52.mlp.experts.11.down_proj:  56%|█████▌    | 20474/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.12.gate_proj:  56%|█████▌    | 20474/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.12.up_proj:  56%|█████▌    | 20475/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.12.down_proj:  56%|█████▌    | 20476/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.13.gate_proj:  56%|█████▌    | 20477/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.13.up_proj:  56%|█████▌    | 20478/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.13.down_proj:  56%|█████▌    | 20479/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.14.gate_proj:  56%|█████▌    | 20480/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.14.up_proj:  56%|█████▌    | 20481/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.14.down_proj:  56%|█████▌    | 20482/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.15.gate_proj:  56%|█████▌    | 20483/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.15.up_proj:  56%|█████▌    | 20484/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.15.down_proj:  56%|█████▌    | 20485/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.16.gate_proj:  56%|█████▌    | 20486/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.16.up_proj:  56%|█████▌    | 20487/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.16.down_proj:  56%|█████▌    | 20488/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.17.gate_proj:  56%|█████▌    | 20489/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.17.up_proj:  56%|█████▌    | 20490/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.17.down_proj:  56%|█████▌    | 20491/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.18.gate_proj:  56%|█████▌    | 20492/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.18.up_proj:  56%|█████▌    | 20493/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.18.down_proj:  56%|█████▌    | 20494/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.19.gate_proj:  56%|█████▌    | 20495/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.19.up_proj:  56%|█████▌    | 20496/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.19.down_proj:  56%|█████▌    | 20497/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.20.gate_proj:  56%|█████▌    | 20498/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.20.up_proj:  56%|█████▌    | 20499/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.20.down_proj:  56%|█████▌    | 20500/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.21.gate_proj:  56%|█████▌    | 20501/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.21.up_proj:  56%|█████▌    | 20502/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.21.down_proj:  56%|█████▌    | 20503/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.22.gate_proj:  56%|█████▌    | 20504/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.22.up_proj:  56%|█████▌    | 20505/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.22.down_proj:  56%|█████▌    | 20506/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.23.gate_proj:  56%|█████▌    | 20507/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.23.up_proj:  56%|█████▌    | 20508/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.23.down_proj:  56%|█████▌    | 20509/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.24.gate_proj:  56%|█████▌    | 20510/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.24.up_proj:  56%|█████▌    | 20511/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.24.down_proj:  56%|█████▌    | 20512/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.25.gate_proj:  56%|█████▌    | 20513/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.25.up_proj:  56%|█████▌    | 20514/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.25.down_proj:  56%|█████▌    | 20515/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.26.gate_proj:  56%|█████▌    | 20516/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.26.up_proj:  56%|█████▌    | 20517/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.26.down_proj:  56%|█████▌    | 20518/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.27.gate_proj:  56%|█████▌    | 20519/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.27.up_proj:  56%|█████▌    | 20520/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.27.down_proj:  56%|█████▌    | 20521/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.28.gate_proj:  56%|█████▌    | 20522/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.28.up_proj:  56%|█████▌    | 20523/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.28.down_proj:  56%|█████▌    | 20524/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.29.gate_proj:  56%|█████▌    | 20525/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.29.up_proj:  56%|█████▌    | 20526/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.29.down_proj:  56%|█████▌    | 20527/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.30.gate_proj:  56%|█████▌    | 20528/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.30.up_proj:  56%|█████▌    | 20529/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.30.down_proj:  56%|█████▌    | 20530/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.31.gate_proj:  56%|█████▌    | 20531/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.31.up_proj:  56%|█████▌    | 20532/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.31.down_proj:  56%|█████▌    | 20533/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.32.gate_proj:  56%|█████▌    | 20534/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.32.up_proj:  56%|█████▌    | 20535/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.32.down_proj:  56%|█████▌    | 20536/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.33.gate_proj:  56%|█████▌    | 20537/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.33.up_proj:  56%|█████▌    | 20538/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.33.down_proj:  56%|█████▌    | 20539/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.34.gate_proj:  56%|█████▌    | 20540/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.34.up_proj:  56%|█████▌    | 20541/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.34.down_proj:  56%|█████▌    | 20542/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.35.gate_proj:  56%|█████▌    | 20543/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.35.up_proj:  56%|█████▌    | 20544/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.35.down_proj:  56%|█████▌    | 20545/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.36.gate_proj:  56%|█████▌    | 20546/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.36.up_proj:  56%|█████▌    | 20547/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.36.down_proj:  56%|█████▌    | 20548/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.37.gate_proj:  56%|█████▌    | 20549/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.37.up_proj:  56%|█████▌    | 20550/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.37.down_proj:  56%|█████▌    | 20551/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.38.gate_proj:  56%|█████▌    | 20552/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.38.up_proj:  56%|█████▌    | 20553/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.38.down_proj:  56%|█████▌    | 20554/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.39.gate_proj:  56%|█████▌    | 20555/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.39.up_proj:  56%|█████▌    | 20556/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.39.down_proj:  56%|█████▌    | 20557/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.40.gate_proj:  56%|█████▌    | 20558/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.40.up_proj:  56%|█████▌    | 20559/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.40.down_proj:  56%|█████▌    | 20560/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.41.gate_proj:  56%|█████▌    | 20561/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.41.up_proj:  56%|█████▌    | 20562/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.41.down_proj:  56%|█████▌    | 20563/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.42.gate_proj:  56%|█████▌    | 20564/36566 [00:18<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.42.up_proj:  56%|█████▌    | 20565/36566 [00:18<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.42.down_proj:  56%|█████▌    | 20566/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.43.gate_proj:  56%|█████▌    | 20567/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.43.up_proj:  56%|█████▌    | 20568/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.43.down_proj:  56%|█████▋    | 20569/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.44.gate_proj:  56%|█████▋    | 20570/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.44.up_proj:  56%|█████▋    | 20571/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.44.down_proj:  56%|█████▋    | 20572/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.45.gate_proj:  56%|█████▋    | 20573/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.45.up_proj:  56%|█████▋    | 20574/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.45.down_proj:  56%|█████▋    | 20575/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.46.gate_proj:  56%|█████▋    | 20576/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.46.up_proj:  56%|█████▋    | 20577/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.46.down_proj:  56%|█████▋    | 20578/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.47.gate_proj:  56%|█████▋    | 20579/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.47.up_proj:  56%|█████▋    | 20580/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.47.down_proj:  56%|█████▋    | 20581/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.48.gate_proj:  56%|█████▋    | 20582/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.48.up_proj:  56%|█████▋    | 20583/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.48.down_proj:  56%|█████▋    | 20584/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.49.gate_proj:  56%|█████▋    | 20585/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.49.up_proj:  56%|█████▋    | 20586/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.49.down_proj:  56%|█████▋    | 20587/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.50.gate_proj:  56%|█████▋    | 20588/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.50.up_proj:  56%|█████▋    | 20589/36566 [00:19<00:13, 1162.06it/s]  
packing model.layers.52.mlp.experts.50.down_proj:  56%|█████▋    | 20590/36566 [00:19<00:13, 1162.06it/s]
packing model.layers.52.mlp.experts.50.down_proj:  56%|█████▋    | 20591/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.51.gate_proj:  56%|█████▋    | 20591/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.51.up_proj:  56%|█████▋    | 20592/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.51.down_proj:  56%|█████▋    | 20593/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.52.gate_proj:  56%|█████▋    | 20594/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.52.up_proj:  56%|█████▋    | 20595/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.52.down_proj:  56%|█████▋    | 20596/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.53.gate_proj:  56%|█████▋    | 20597/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.53.up_proj:  56%|█████▋    | 20598/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.53.down_proj:  56%|█████▋    | 20599/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.54.gate_proj:  56%|█████▋    | 20600/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.54.up_proj:  56%|█████▋    | 20601/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.54.down_proj:  56%|█████▋    | 20602/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.55.gate_proj:  56%|█████▋    | 20603/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.55.up_proj:  56%|█████▋    | 20604/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.55.down_proj:  56%|█████▋    | 20605/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.56.gate_proj:  56%|█████▋    | 20606/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.56.up_proj:  56%|█████▋    | 20607/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.56.down_proj:  56%|█████▋    | 20608/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.57.gate_proj:  56%|█████▋    | 20609/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.57.up_proj:  56%|█████▋    | 20610/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.57.down_proj:  56%|█████▋    | 20611/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.58.gate_proj:  56%|█████▋    | 20612/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.58.up_proj:  56%|█████▋    | 20613/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.58.down_proj:  56%|█████▋    | 20614/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.59.gate_proj:  56%|█████▋    | 20615/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.59.up_proj:  56%|█████▋    | 20616/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.59.down_proj:  56%|█████▋    | 20617/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.60.gate_proj:  56%|█████▋    | 20618/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.60.up_proj:  56%|█████▋    | 20619/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.60.down_proj:  56%|█████▋    | 20620/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.61.gate_proj:  56%|█████▋    | 20621/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.61.up_proj:  56%|█████▋    | 20622/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.61.down_proj:  56%|█████▋    | 20623/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.62.gate_proj:  56%|█████▋    | 20624/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.62.up_proj:  56%|█████▋    | 20625/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.62.down_proj:  56%|█████▋    | 20626/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.63.gate_proj:  56%|█████▋    | 20627/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.63.up_proj:  56%|█████▋    | 20628/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.63.down_proj:  56%|█████▋    | 20629/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.64.gate_proj:  56%|█████▋    | 20630/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.64.up_proj:  56%|█████▋    | 20631/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.64.down_proj:  56%|█████▋    | 20632/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.65.gate_proj:  56%|█████▋    | 20633/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.65.up_proj:  56%|█████▋    | 20634/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.65.down_proj:  56%|█████▋    | 20635/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.66.gate_proj:  56%|█████▋    | 20636/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.66.up_proj:  56%|█████▋    | 20637/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.66.down_proj:  56%|█████▋    | 20638/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.67.gate_proj:  56%|█████▋    | 20639/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.67.up_proj:  56%|█████▋    | 20640/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.67.down_proj:  56%|█████▋    | 20641/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.68.gate_proj:  56%|█████▋    | 20642/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.68.up_proj:  56%|█████▋    | 20643/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.68.down_proj:  56%|█████▋    | 20644/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.69.gate_proj:  56%|█████▋    | 20645/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.69.up_proj:  56%|█████▋    | 20646/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.69.down_proj:  56%|█████▋    | 20647/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.70.gate_proj:  56%|█████▋    | 20648/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.70.up_proj:  56%|█████▋    | 20649/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.70.down_proj:  56%|█████▋    | 20650/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.71.gate_proj:  56%|█████▋    | 20651/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.71.up_proj:  56%|█████▋    | 20652/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.71.down_proj:  56%|█████▋    | 20653/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.72.gate_proj:  56%|█████▋    | 20654/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.72.up_proj:  56%|█████▋    | 20655/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.72.down_proj:  56%|█████▋    | 20656/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.73.gate_proj:  56%|█████▋    | 20657/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.73.up_proj:  56%|█████▋    | 20658/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.73.down_proj:  56%|█████▋    | 20659/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.74.gate_proj:  57%|█████▋    | 20660/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.74.up_proj:  57%|█████▋    | 20661/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.74.down_proj:  57%|█████▋    | 20662/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.75.gate_proj:  57%|█████▋    | 20663/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.75.up_proj:  57%|█████▋    | 20664/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.75.down_proj:  57%|█████▋    | 20665/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.76.gate_proj:  57%|█████▋    | 20666/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.76.up_proj:  57%|█████▋    | 20667/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.76.down_proj:  57%|█████▋    | 20668/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.77.gate_proj:  57%|█████▋    | 20669/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.77.up_proj:  57%|█████▋    | 20670/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.77.down_proj:  57%|█████▋    | 20671/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.78.gate_proj:  57%|█████▋    | 20672/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.78.up_proj:  57%|█████▋    | 20673/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.78.down_proj:  57%|█████▋    | 20674/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.79.gate_proj:  57%|█████▋    | 20675/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.79.up_proj:  57%|█████▋    | 20676/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.79.down_proj:  57%|█████▋    | 20677/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.80.gate_proj:  57%|█████▋    | 20678/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.80.up_proj:  57%|█████▋    | 20679/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.80.down_proj:  57%|█████▋    | 20680/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.81.gate_proj:  57%|█████▋    | 20681/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.81.up_proj:  57%|█████▋    | 20682/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.81.down_proj:  57%|█████▋    | 20683/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.82.gate_proj:  57%|█████▋    | 20684/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.82.up_proj:  57%|█████▋    | 20685/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.82.down_proj:  57%|█████▋    | 20686/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.83.gate_proj:  57%|█████▋    | 20687/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.83.up_proj:  57%|█████▋    | 20688/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.83.down_proj:  57%|█████▋    | 20689/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.84.gate_proj:  57%|█████▋    | 20690/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.84.up_proj:  57%|█████▋    | 20691/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.84.down_proj:  57%|█████▋    | 20692/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.85.gate_proj:  57%|█████▋    | 20693/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.85.up_proj:  57%|█████▋    | 20694/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.85.down_proj:  57%|█████▋    | 20695/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.86.gate_proj:  57%|█████▋    | 20696/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.86.up_proj:  57%|█████▋    | 20697/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.86.down_proj:  57%|█████▋    | 20698/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.87.gate_proj:  57%|█████▋    | 20699/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.87.up_proj:  57%|█████▋    | 20700/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.87.down_proj:  57%|█████▋    | 20701/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.88.gate_proj:  57%|█████▋    | 20702/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.88.up_proj:  57%|█████▋    | 20703/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.88.down_proj:  57%|█████▋    | 20704/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.89.gate_proj:  57%|█████▋    | 20705/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.89.up_proj:  57%|█████▋    | 20706/36566 [00:19<00:13, 1164.08it/s]  
packing model.layers.52.mlp.experts.89.down_proj:  57%|█████▋    | 20707/36566 [00:19<00:13, 1164.08it/s]
packing model.layers.52.mlp.experts.89.down_proj:  57%|█████▋    | 20708/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.90.gate_proj:  57%|█████▋    | 20708/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.90.up_proj:  57%|█████▋    | 20709/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.90.down_proj:  57%|█████▋    | 20710/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.91.gate_proj:  57%|█████▋    | 20711/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.91.up_proj:  57%|█████▋    | 20712/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.91.down_proj:  57%|█████▋    | 20713/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.92.gate_proj:  57%|█████▋    | 20714/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.92.up_proj:  57%|█████▋    | 20715/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.92.down_proj:  57%|█████▋    | 20716/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.93.gate_proj:  57%|█████▋    | 20717/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.93.up_proj:  57%|█████▋    | 20718/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.93.down_proj:  57%|█████▋    | 20719/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.94.gate_proj:  57%|█████▋    | 20720/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.94.up_proj:  57%|█████▋    | 20721/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.94.down_proj:  57%|█████▋    | 20722/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.95.gate_proj:  57%|█████▋    | 20723/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.95.up_proj:  57%|█████▋    | 20724/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.95.down_proj:  57%|█████▋    | 20725/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.96.gate_proj:  57%|█████▋    | 20726/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.96.up_proj:  57%|█████▋    | 20727/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.96.down_proj:  57%|█████▋    | 20728/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.97.gate_proj:  57%|█████▋    | 20729/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.97.up_proj:  57%|█████▋    | 20730/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.97.down_proj:  57%|█████▋    | 20731/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.98.gate_proj:  57%|█████▋    | 20732/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.98.up_proj:  57%|█████▋    | 20733/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.98.down_proj:  57%|█████▋    | 20734/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.99.gate_proj:  57%|█████▋    | 20735/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.99.up_proj:  57%|█████▋    | 20736/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.99.down_proj:  57%|█████▋    | 20737/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.100.gate_proj:  57%|█████▋    | 20738/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.100.up_proj:  57%|█████▋    | 20739/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.100.down_proj:  57%|█████▋    | 20740/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.101.gate_proj:  57%|█████▋    | 20741/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.101.up_proj:  57%|█████▋    | 20742/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.101.down_proj:  57%|█████▋    | 20743/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.102.gate_proj:  57%|█████▋    | 20744/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.102.up_proj:  57%|█████▋    | 20745/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.102.down_proj:  57%|█████▋    | 20746/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.103.gate_proj:  57%|█████▋    | 20747/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.103.up_proj:  57%|█████▋    | 20748/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.103.down_proj:  57%|█████▋    | 20749/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.104.gate_proj:  57%|█████▋    | 20750/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.104.up_proj:  57%|█████▋    | 20751/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.104.down_proj:  57%|█████▋    | 20752/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.105.gate_proj:  57%|█████▋    | 20753/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.105.up_proj:  57%|█████▋    | 20754/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.105.down_proj:  57%|█████▋    | 20755/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.106.gate_proj:  57%|█████▋    | 20756/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.106.up_proj:  57%|█████▋    | 20757/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.106.down_proj:  57%|█████▋    | 20758/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.107.gate_proj:  57%|█████▋    | 20759/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.107.up_proj:  57%|█████▋    | 20760/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.107.down_proj:  57%|█████▋    | 20761/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.108.gate_proj:  57%|█████▋    | 20762/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.108.up_proj:  57%|█████▋    | 20763/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.108.down_proj:  57%|█████▋    | 20764/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.109.gate_proj:  57%|█████▋    | 20765/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.109.up_proj:  57%|█████▋    | 20766/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.109.down_proj:  57%|█████▋    | 20767/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.110.gate_proj:  57%|█████▋    | 20768/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.110.up_proj:  57%|█████▋    | 20769/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.110.down_proj:  57%|█████▋    | 20770/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.111.gate_proj:  57%|█████▋    | 20771/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.111.up_proj:  57%|█████▋    | 20772/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.111.down_proj:  57%|█████▋    | 20773/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.112.gate_proj:  57%|█████▋    | 20774/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.112.up_proj:  57%|█████▋    | 20775/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.112.down_proj:  57%|█████▋    | 20776/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.113.gate_proj:  57%|█████▋    | 20777/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.113.up_proj:  57%|█████▋    | 20778/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.113.down_proj:  57%|█████▋    | 20779/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.114.gate_proj:  57%|█████▋    | 20780/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.114.up_proj:  57%|█████▋    | 20781/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.114.down_proj:  57%|█████▋    | 20782/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.115.gate_proj:  57%|█████▋    | 20783/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.115.up_proj:  57%|█████▋    | 20784/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.115.down_proj:  57%|█████▋    | 20785/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.116.gate_proj:  57%|█████▋    | 20786/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.116.up_proj:  57%|█████▋    | 20787/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.116.down_proj:  57%|█████▋    | 20788/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.117.gate_proj:  57%|█████▋    | 20789/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.117.up_proj:  57%|█████▋    | 20790/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.117.down_proj:  57%|█████▋    | 20791/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.118.gate_proj:  57%|█████▋    | 20792/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.118.up_proj:  57%|█████▋    | 20793/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.118.down_proj:  57%|█████▋    | 20794/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.119.gate_proj:  57%|█████▋    | 20795/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.119.up_proj:  57%|█████▋    | 20796/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.119.down_proj:  57%|█████▋    | 20797/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.120.gate_proj:  57%|█████▋    | 20798/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.120.up_proj:  57%|█████▋    | 20799/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.120.down_proj:  57%|█████▋    | 20800/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.121.gate_proj:  57%|█████▋    | 20801/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.121.up_proj:  57%|█████▋    | 20802/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.121.down_proj:  57%|█████▋    | 20803/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.122.gate_proj:  57%|█████▋    | 20804/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.122.up_proj:  57%|█████▋    | 20805/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.122.down_proj:  57%|█████▋    | 20806/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.123.gate_proj:  57%|█████▋    | 20807/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.123.up_proj:  57%|█████▋    | 20808/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.123.down_proj:  57%|█████▋    | 20809/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.124.gate_proj:  57%|█████▋    | 20810/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.124.up_proj:  57%|█████▋    | 20811/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.124.down_proj:  57%|█████▋    | 20812/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.125.gate_proj:  57%|█████▋    | 20813/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.125.up_proj:  57%|█████▋    | 20814/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.125.down_proj:  57%|█████▋    | 20815/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.126.gate_proj:  57%|█████▋    | 20816/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.126.up_proj:  57%|█████▋    | 20817/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.126.down_proj:  57%|█████▋    | 20818/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.127.gate_proj:  57%|█████▋    | 20819/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.52.mlp.experts.127.up_proj:  57%|█████▋    | 20820/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.52.mlp.experts.127.down_proj:  57%|█████▋    | 20821/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.53.mlp.experts.0.gate_proj:  57%|█████▋    | 20822/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.53.mlp.experts.0.up_proj:  57%|█████▋    | 20823/36566 [00:19<00:13, 1164.63it/s]  
packing model.layers.53.mlp.experts.0.down_proj:  57%|█████▋    | 20824/36566 [00:19<00:13, 1164.63it/s]
packing model.layers.53.mlp.experts.0.down_proj:  57%|█████▋    | 20825/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.1.gate_proj:  57%|█████▋    | 20825/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.1.up_proj:  57%|█████▋    | 20826/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.1.down_proj:  57%|█████▋    | 20827/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.2.gate_proj:  57%|█████▋    | 20828/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.2.up_proj:  57%|█████▋    | 20829/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.2.down_proj:  57%|█████▋    | 20830/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.3.gate_proj:  57%|█████▋    | 20831/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.3.up_proj:  57%|█████▋    | 20832/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.3.down_proj:  57%|█████▋    | 20833/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.4.gate_proj:  57%|█████▋    | 20834/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.4.up_proj:  57%|█████▋    | 20835/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.4.down_proj:  57%|█████▋    | 20836/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.5.gate_proj:  57%|█████▋    | 20837/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.5.up_proj:  57%|█████▋    | 20838/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.5.down_proj:  57%|█████▋    | 20839/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.6.gate_proj:  57%|█████▋    | 20840/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.6.up_proj:  57%|█████▋    | 20841/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.6.down_proj:  57%|█████▋    | 20842/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.7.gate_proj:  57%|█████▋    | 20843/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.7.up_proj:  57%|█████▋    | 20844/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.7.down_proj:  57%|█████▋    | 20845/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.8.gate_proj:  57%|█████▋    | 20846/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.8.up_proj:  57%|█████▋    | 20847/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.8.down_proj:  57%|█████▋    | 20848/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.9.gate_proj:  57%|█████▋    | 20849/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.9.up_proj:  57%|█████▋    | 20850/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.9.down_proj:  57%|█████▋    | 20851/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.10.gate_proj:  57%|█████▋    | 20852/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.10.up_proj:  57%|█████▋    | 20853/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.10.down_proj:  57%|█████▋    | 20854/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.11.gate_proj:  57%|█████▋    | 20855/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.11.up_proj:  57%|█████▋    | 20856/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.11.down_proj:  57%|█████▋    | 20857/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.12.gate_proj:  57%|█████▋    | 20858/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.12.up_proj:  57%|█████▋    | 20859/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.12.down_proj:  57%|█████▋    | 20860/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.13.gate_proj:  57%|█████▋    | 20861/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.13.up_proj:  57%|█████▋    | 20862/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.13.down_proj:  57%|█████▋    | 20863/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.14.gate_proj:  57%|█████▋    | 20864/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.14.up_proj:  57%|█████▋    | 20865/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.14.down_proj:  57%|█████▋    | 20866/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.15.gate_proj:  57%|█████▋    | 20867/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.15.up_proj:  57%|█████▋    | 20868/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.15.down_proj:  57%|█████▋    | 20869/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.16.gate_proj:  57%|█████▋    | 20870/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.16.up_proj:  57%|█████▋    | 20871/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.16.down_proj:  57%|█████▋    | 20872/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.17.gate_proj:  57%|█████▋    | 20873/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.17.up_proj:  57%|█████▋    | 20874/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.17.down_proj:  57%|█████▋    | 20875/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.18.gate_proj:  57%|█████▋    | 20876/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.18.up_proj:  57%|█████▋    | 20877/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.18.down_proj:  57%|█████▋    | 20878/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.19.gate_proj:  57%|█████▋    | 20879/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.19.up_proj:  57%|█████▋    | 20880/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.19.down_proj:  57%|█████▋    | 20881/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.20.gate_proj:  57%|█████▋    | 20882/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.20.up_proj:  57%|█████▋    | 20883/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.20.down_proj:  57%|█████▋    | 20884/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.21.gate_proj:  57%|█████▋    | 20885/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.21.up_proj:  57%|█████▋    | 20886/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.21.down_proj:  57%|█████▋    | 20887/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.22.gate_proj:  57%|█████▋    | 20888/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.22.up_proj:  57%|█████▋    | 20889/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.22.down_proj:  57%|█████▋    | 20890/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.23.gate_proj:  57%|█████▋    | 20891/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.23.up_proj:  57%|█████▋    | 20892/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.23.down_proj:  57%|█████▋    | 20893/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.24.gate_proj:  57%|█████▋    | 20894/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.24.up_proj:  57%|█████▋    | 20895/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.24.down_proj:  57%|█████▋    | 20896/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.25.gate_proj:  57%|█████▋    | 20897/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.25.up_proj:  57%|█████▋    | 20898/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.25.down_proj:  57%|█████▋    | 20899/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.26.gate_proj:  57%|█████▋    | 20900/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.26.up_proj:  57%|█████▋    | 20901/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.26.down_proj:  57%|█████▋    | 20902/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.27.gate_proj:  57%|█████▋    | 20903/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.27.up_proj:  57%|█████▋    | 20904/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.27.down_proj:  57%|█████▋    | 20905/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.28.gate_proj:  57%|█████▋    | 20906/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.28.up_proj:  57%|█████▋    | 20907/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.28.down_proj:  57%|█████▋    | 20908/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.29.gate_proj:  57%|█████▋    | 20909/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.29.up_proj:  57%|█████▋    | 20910/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.29.down_proj:  57%|█████▋    | 20911/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.30.gate_proj:  57%|█████▋    | 20912/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.30.up_proj:  57%|█████▋    | 20913/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.30.down_proj:  57%|█████▋    | 20914/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.31.gate_proj:  57%|█████▋    | 20915/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.31.up_proj:  57%|█████▋    | 20916/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.31.down_proj:  57%|█████▋    | 20917/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.32.gate_proj:  57%|█████▋    | 20918/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.32.up_proj:  57%|█████▋    | 20919/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.32.down_proj:  57%|█████▋    | 20920/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.33.gate_proj:  57%|█████▋    | 20921/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.33.up_proj:  57%|█████▋    | 20922/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.33.down_proj:  57%|█████▋    | 20923/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.34.gate_proj:  57%|█████▋    | 20924/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.34.up_proj:  57%|█████▋    | 20925/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.34.down_proj:  57%|█████▋    | 20926/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.35.gate_proj:  57%|█████▋    | 20927/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.35.up_proj:  57%|█████▋    | 20928/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.35.down_proj:  57%|█████▋    | 20929/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.36.gate_proj:  57%|█████▋    | 20930/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.36.up_proj:  57%|█████▋    | 20931/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.36.down_proj:  57%|█████▋    | 20932/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.37.gate_proj:  57%|█████▋    | 20933/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.37.up_proj:  57%|█████▋    | 20934/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.37.down_proj:  57%|█████▋    | 20935/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.38.gate_proj:  57%|█████▋    | 20936/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.38.up_proj:  57%|█████▋    | 20937/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.38.down_proj:  57%|█████▋    | 20938/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.39.gate_proj:  57%|█████▋    | 20939/36566 [00:19<00:13, 1157.66it/s]
packing model.layers.53.mlp.experts.39.up_proj:  57%|█████▋    | 20940/36566 [00:19<00:13, 1157.66it/s]  
packing model.layers.53.mlp.experts.39.up_proj:  57%|█████▋    | 20941/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.39.down_proj:  57%|█████▋    | 20941/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.40.gate_proj:  57%|█████▋    | 20942/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.40.up_proj:  57%|█████▋    | 20943/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.40.down_proj:  57%|█████▋    | 20944/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.41.gate_proj:  57%|█████▋    | 20945/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.41.up_proj:  57%|█████▋    | 20946/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.41.down_proj:  57%|█████▋    | 20947/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.42.gate_proj:  57%|█████▋    | 20948/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.42.up_proj:  57%|█████▋    | 20949/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.42.down_proj:  57%|█████▋    | 20950/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.43.gate_proj:  57%|█████▋    | 20951/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.43.up_proj:  57%|█████▋    | 20952/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.43.down_proj:  57%|█████▋    | 20953/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.44.gate_proj:  57%|█████▋    | 20954/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.44.up_proj:  57%|█████▋    | 20955/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.44.down_proj:  57%|█████▋    | 20956/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.45.gate_proj:  57%|█████▋    | 20957/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.45.up_proj:  57%|█████▋    | 20958/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.45.down_proj:  57%|█████▋    | 20959/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.46.gate_proj:  57%|█████▋    | 20960/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.46.up_proj:  57%|█████▋    | 20961/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.46.down_proj:  57%|█████▋    | 20962/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.47.gate_proj:  57%|█████▋    | 20963/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.47.up_proj:  57%|█████▋    | 20964/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.47.down_proj:  57%|█████▋    | 20965/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.48.gate_proj:  57%|█████▋    | 20966/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.48.up_proj:  57%|█████▋    | 20967/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.48.down_proj:  57%|█████▋    | 20968/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.49.gate_proj:  57%|█████▋    | 20969/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.49.up_proj:  57%|█████▋    | 20970/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.49.down_proj:  57%|█████▋    | 20971/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.50.gate_proj:  57%|█████▋    | 20972/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.50.up_proj:  57%|█████▋    | 20973/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.50.down_proj:  57%|█████▋    | 20974/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.51.gate_proj:  57%|█████▋    | 20975/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.51.up_proj:  57%|█████▋    | 20976/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.51.down_proj:  57%|█████▋    | 20977/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.52.gate_proj:  57%|█████▋    | 20978/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.52.up_proj:  57%|█████▋    | 20979/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.52.down_proj:  57%|█████▋    | 20980/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.53.gate_proj:  57%|█████▋    | 20981/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.53.up_proj:  57%|█████▋    | 20982/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.53.down_proj:  57%|█████▋    | 20983/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.54.gate_proj:  57%|█████▋    | 20984/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.54.up_proj:  57%|█████▋    | 20985/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.54.down_proj:  57%|█████▋    | 20986/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.55.gate_proj:  57%|█████▋    | 20987/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.55.up_proj:  57%|█████▋    | 20988/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.55.down_proj:  57%|█████▋    | 20989/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.56.gate_proj:  57%|█████▋    | 20990/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.56.up_proj:  57%|█████▋    | 20991/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.56.down_proj:  57%|█████▋    | 20992/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.57.gate_proj:  57%|█████▋    | 20993/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.57.up_proj:  57%|█████▋    | 20994/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.57.down_proj:  57%|█████▋    | 20995/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.58.gate_proj:  57%|█████▋    | 20996/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.58.up_proj:  57%|█████▋    | 20997/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.58.down_proj:  57%|█████▋    | 20998/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.59.gate_proj:  57%|█████▋    | 20999/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.59.up_proj:  57%|█████▋    | 21000/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.59.down_proj:  57%|█████▋    | 21001/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.60.gate_proj:  57%|█████▋    | 21002/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.60.up_proj:  57%|█████▋    | 21003/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.60.down_proj:  57%|█████▋    | 21004/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.61.gate_proj:  57%|█████▋    | 21005/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.61.up_proj:  57%|█████▋    | 21006/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.61.down_proj:  57%|█████▋    | 21007/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.62.gate_proj:  57%|█████▋    | 21008/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.62.up_proj:  57%|█████▋    | 21009/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.62.down_proj:  57%|█████▋    | 21010/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.63.gate_proj:  57%|█████▋    | 21011/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.63.up_proj:  57%|█████▋    | 21012/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.63.down_proj:  57%|█████▋    | 21013/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.64.gate_proj:  57%|█████▋    | 21014/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.64.up_proj:  57%|█████▋    | 21015/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.64.down_proj:  57%|█████▋    | 21016/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.65.gate_proj:  57%|█████▋    | 21017/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.65.up_proj:  57%|█████▋    | 21018/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.65.down_proj:  57%|█████▋    | 21019/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.66.gate_proj:  57%|█████▋    | 21020/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.66.up_proj:  57%|█████▋    | 21021/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.66.down_proj:  57%|█████▋    | 21022/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.67.gate_proj:  57%|█████▋    | 21023/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.67.up_proj:  57%|█████▋    | 21024/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.67.down_proj:  57%|█████▋    | 21025/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.68.gate_proj:  58%|█████▊    | 21026/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.68.up_proj:  58%|█████▊    | 21027/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.68.down_proj:  58%|█████▊    | 21028/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.69.gate_proj:  58%|█████▊    | 21029/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.69.up_proj:  58%|█████▊    | 21030/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.69.down_proj:  58%|█████▊    | 21031/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.70.gate_proj:  58%|█████▊    | 21032/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.70.up_proj:  58%|█████▊    | 21033/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.70.down_proj:  58%|█████▊    | 21034/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.71.gate_proj:  58%|█████▊    | 21035/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.71.up_proj:  58%|█████▊    | 21036/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.71.down_proj:  58%|█████▊    | 21037/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.72.gate_proj:  58%|█████▊    | 21038/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.72.up_proj:  58%|█████▊    | 21039/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.72.down_proj:  58%|█████▊    | 21040/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.73.gate_proj:  58%|█████▊    | 21041/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.73.up_proj:  58%|█████▊    | 21042/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.73.down_proj:  58%|█████▊    | 21043/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.74.gate_proj:  58%|█████▊    | 21044/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.74.up_proj:  58%|█████▊    | 21045/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.74.down_proj:  58%|█████▊    | 21046/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.75.gate_proj:  58%|█████▊    | 21047/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.75.up_proj:  58%|█████▊    | 21048/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.75.down_proj:  58%|█████▊    | 21049/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.76.gate_proj:  58%|█████▊    | 21050/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.76.up_proj:  58%|█████▊    | 21051/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.76.down_proj:  58%|█████▊    | 21052/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.77.gate_proj:  58%|█████▊    | 21053/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.77.up_proj:  58%|█████▊    | 21054/36566 [00:19<00:13, 1158.31it/s]  
packing model.layers.53.mlp.experts.77.down_proj:  58%|█████▊    | 21055/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.78.gate_proj:  58%|█████▊    | 21056/36566 [00:19<00:13, 1158.31it/s]
packing model.layers.53.mlp.experts.78.gate_proj:  58%|█████▊    | 21057/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.78.up_proj:  58%|█████▊    | 21057/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.78.down_proj:  58%|█████▊    | 21058/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.79.gate_proj:  58%|█████▊    | 21059/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.79.up_proj:  58%|█████▊    | 21060/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.79.down_proj:  58%|█████▊    | 21061/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.80.gate_proj:  58%|█████▊    | 21062/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.80.up_proj:  58%|█████▊    | 21063/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.80.down_proj:  58%|█████▊    | 21064/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.81.gate_proj:  58%|█████▊    | 21065/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.81.up_proj:  58%|█████▊    | 21066/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.81.down_proj:  58%|█████▊    | 21067/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.82.gate_proj:  58%|█████▊    | 21068/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.82.up_proj:  58%|█████▊    | 21069/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.82.down_proj:  58%|█████▊    | 21070/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.83.gate_proj:  58%|█████▊    | 21071/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.83.up_proj:  58%|█████▊    | 21072/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.83.down_proj:  58%|█████▊    | 21073/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.84.gate_proj:  58%|█████▊    | 21074/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.84.up_proj:  58%|█████▊    | 21075/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.84.down_proj:  58%|█████▊    | 21076/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.85.gate_proj:  58%|█████▊    | 21077/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.85.up_proj:  58%|█████▊    | 21078/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.85.down_proj:  58%|█████▊    | 21079/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.86.gate_proj:  58%|█████▊    | 21080/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.86.up_proj:  58%|█████▊    | 21081/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.86.down_proj:  58%|█████▊    | 21082/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.87.gate_proj:  58%|█████▊    | 21083/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.87.up_proj:  58%|█████▊    | 21084/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.87.down_proj:  58%|█████▊    | 21085/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.88.gate_proj:  58%|█████▊    | 21086/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.88.up_proj:  58%|█████▊    | 21087/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.88.down_proj:  58%|█████▊    | 21088/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.89.gate_proj:  58%|█████▊    | 21089/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.89.up_proj:  58%|█████▊    | 21090/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.89.down_proj:  58%|█████▊    | 21091/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.90.gate_proj:  58%|█████▊    | 21092/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.90.up_proj:  58%|█████▊    | 21093/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.90.down_proj:  58%|█████▊    | 21094/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.91.gate_proj:  58%|█████▊    | 21095/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.91.up_proj:  58%|█████▊    | 21096/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.91.down_proj:  58%|█████▊    | 21097/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.92.gate_proj:  58%|█████▊    | 21098/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.92.up_proj:  58%|█████▊    | 21099/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.92.down_proj:  58%|█████▊    | 21100/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.93.gate_proj:  58%|█████▊    | 21101/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.93.up_proj:  58%|█████▊    | 21102/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.93.down_proj:  58%|█████▊    | 21103/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.94.gate_proj:  58%|█████▊    | 21104/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.94.up_proj:  58%|█████▊    | 21105/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.94.down_proj:  58%|█████▊    | 21106/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.95.gate_proj:  58%|█████▊    | 21107/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.95.up_proj:  58%|█████▊    | 21108/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.95.down_proj:  58%|█████▊    | 21109/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.96.gate_proj:  58%|█████▊    | 21110/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.96.up_proj:  58%|█████▊    | 21111/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.96.down_proj:  58%|█████▊    | 21112/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.97.gate_proj:  58%|█████▊    | 21113/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.97.up_proj:  58%|█████▊    | 21114/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.97.down_proj:  58%|█████▊    | 21115/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.98.gate_proj:  58%|█████▊    | 21116/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.98.up_proj:  58%|█████▊    | 21117/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.98.down_proj:  58%|█████▊    | 21118/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.99.gate_proj:  58%|█████▊    | 21119/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.99.up_proj:  58%|█████▊    | 21120/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.99.down_proj:  58%|█████▊    | 21121/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.100.gate_proj:  58%|█████▊    | 21122/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.100.up_proj:  58%|█████▊    | 21123/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.100.down_proj:  58%|█████▊    | 21124/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.101.gate_proj:  58%|█████▊    | 21125/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.101.up_proj:  58%|█████▊    | 21126/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.101.down_proj:  58%|█████▊    | 21127/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.102.gate_proj:  58%|█████▊    | 21128/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.102.up_proj:  58%|█████▊    | 21129/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.102.down_proj:  58%|█████▊    | 21130/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.103.gate_proj:  58%|█████▊    | 21131/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.103.up_proj:  58%|█████▊    | 21132/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.103.down_proj:  58%|█████▊    | 21133/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.104.gate_proj:  58%|█████▊    | 21134/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.104.up_proj:  58%|█████▊    | 21135/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.104.down_proj:  58%|█████▊    | 21136/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.105.gate_proj:  58%|█████▊    | 21137/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.105.up_proj:  58%|█████▊    | 21138/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.105.down_proj:  58%|█████▊    | 21139/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.106.gate_proj:  58%|█████▊    | 21140/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.106.up_proj:  58%|█████▊    | 21141/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.106.down_proj:  58%|█████▊    | 21142/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.107.gate_proj:  58%|█████▊    | 21143/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.107.up_proj:  58%|█████▊    | 21144/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.107.down_proj:  58%|█████▊    | 21145/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.108.gate_proj:  58%|█████▊    | 21146/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.108.up_proj:  58%|█████▊    | 21147/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.108.down_proj:  58%|█████▊    | 21148/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.109.gate_proj:  58%|█████▊    | 21149/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.109.up_proj:  58%|█████▊    | 21150/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.109.down_proj:  58%|█████▊    | 21151/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.110.gate_proj:  58%|█████▊    | 21152/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.110.up_proj:  58%|█████▊    | 21153/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.110.down_proj:  58%|█████▊    | 21154/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.111.gate_proj:  58%|█████▊    | 21155/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.111.up_proj:  58%|█████▊    | 21156/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.111.down_proj:  58%|█████▊    | 21157/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.112.gate_proj:  58%|█████▊    | 21158/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.112.up_proj:  58%|█████▊    | 21159/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.112.down_proj:  58%|█████▊    | 21160/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.113.gate_proj:  58%|█████▊    | 21161/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.113.up_proj:  58%|█████▊    | 21162/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.113.down_proj:  58%|█████▊    | 21163/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.114.gate_proj:  58%|█████▊    | 21164/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.114.up_proj:  58%|█████▊    | 21165/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.114.down_proj:  58%|█████▊    | 21166/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.115.gate_proj:  58%|█████▊    | 21167/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.115.up_proj:  58%|█████▊    | 21168/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.115.down_proj:  58%|█████▊    | 21169/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.116.gate_proj:  58%|█████▊    | 21170/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.116.up_proj:  58%|█████▊    | 21171/36566 [00:19<00:13, 1158.23it/s]  
packing model.layers.53.mlp.experts.116.down_proj:  58%|█████▊    | 21172/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.117.gate_proj:  58%|█████▊    | 21173/36566 [00:19<00:13, 1158.23it/s]
packing model.layers.53.mlp.experts.117.gate_proj:  58%|█████▊    | 21174/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.117.up_proj:  58%|█████▊    | 21174/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.117.down_proj:  58%|█████▊    | 21175/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.118.gate_proj:  58%|█████▊    | 21176/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.118.up_proj:  58%|█████▊    | 21177/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.118.down_proj:  58%|█████▊    | 21178/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.119.gate_proj:  58%|█████▊    | 21179/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.119.up_proj:  58%|█████▊    | 21180/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.119.down_proj:  58%|█████▊    | 21181/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.120.gate_proj:  58%|█████▊    | 21182/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.120.up_proj:  58%|█████▊    | 21183/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.120.down_proj:  58%|█████▊    | 21184/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.121.gate_proj:  58%|█████▊    | 21185/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.121.up_proj:  58%|█████▊    | 21186/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.121.down_proj:  58%|█████▊    | 21187/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.122.gate_proj:  58%|█████▊    | 21188/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.122.up_proj:  58%|█████▊    | 21189/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.122.down_proj:  58%|█████▊    | 21190/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.123.gate_proj:  58%|█████▊    | 21191/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.123.up_proj:  58%|█████▊    | 21192/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.123.down_proj:  58%|█████▊    | 21193/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.124.gate_proj:  58%|█████▊    | 21194/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.124.up_proj:  58%|█████▊    | 21195/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.124.down_proj:  58%|█████▊    | 21196/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.125.gate_proj:  58%|█████▊    | 21197/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.125.up_proj:  58%|█████▊    | 21198/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.125.down_proj:  58%|█████▊    | 21199/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.126.gate_proj:  58%|█████▊    | 21200/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.126.up_proj:  58%|█████▊    | 21201/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.126.down_proj:  58%|█████▊    | 21202/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.127.gate_proj:  58%|█████▊    | 21203/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.53.mlp.experts.127.up_proj:  58%|█████▊    | 21204/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.53.mlp.experts.127.down_proj:  58%|█████▊    | 21205/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.0.gate_proj:  58%|█████▊    | 21206/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.0.up_proj:  58%|█████▊    | 21207/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.0.down_proj:  58%|█████▊    | 21208/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.1.gate_proj:  58%|█████▊    | 21209/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.1.up_proj:  58%|█████▊    | 21210/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.1.down_proj:  58%|█████▊    | 21211/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.2.gate_proj:  58%|█████▊    | 21212/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.2.up_proj:  58%|█████▊    | 21213/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.2.down_proj:  58%|█████▊    | 21214/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.3.gate_proj:  58%|█████▊    | 21215/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.3.up_proj:  58%|█████▊    | 21216/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.3.down_proj:  58%|█████▊    | 21217/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.4.gate_proj:  58%|█████▊    | 21218/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.experts.4.up_proj:  58%|█████▊    | 21219/36566 [00:19<00:13, 1159.27it/s]  
packing model.layers.54.mlp.experts.4.down_proj:  58%|█████▊    | 21220/36566 [00:19<00:13, 1159.27it/s]
packing model.layers.54.mlp.exp
chaiml-muster-v2-q235b-77862-v1-uploader: 0.up_proj:  60%|█████▉    | 21771/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.60.down_proj:  60%|█████▉    | 21772/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.61.gate_proj:  60%|█████▉    | 21773/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.61.up_proj:  60%|█████▉    | 21774/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.61.down_proj:  60%|█████▉    | 21775/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.62.gate_proj:  60%|█████▉    | 21776/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.62.up_proj:  60%|█████▉    | 21777/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.62.down_proj:  60%|█████▉    | 21778/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.63.gate_proj:  60%|█████▉    | 21779/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.63.up_proj:  60%|█████▉    | 21780/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.63.down_proj:  60%|█████▉    | 21781/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.64.gate_proj:  60%|█████▉    | 21782/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.64.up_proj:  60%|█████▉    | 21783/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.64.down_proj:  60%|█████▉    | 21784/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.65.gate_proj:  60%|█████▉    | 21785/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.65.up_proj:  60%|█████▉    | 21786/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.65.down_proj:  60%|█████▉    | 21787/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.66.gate_proj:  60%|█████▉    | 21788/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.66.up_proj:  60%|█████▉    | 21789/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.66.down_proj:  60%|█████▉    | 21790/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.67.gate_proj:  60%|█████▉    | 21791/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.67.up_proj:  60%|█████▉    | 21792/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.67.down_proj:  60%|█████▉    | 21793/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.68.gate_proj:  60%|█████▉    | 21794/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.68.up_proj:  60%|█████▉    | 21795/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.68.down_proj:  60%|█████▉    | 21796/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.69.gate_proj:  60%|█████▉    | 21797/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.69.up_proj:  60%|█████▉    | 21798/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.69.down_proj:  60%|█████▉    | 21799/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.70.gate_proj:  60%|█████▉    | 21800/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.70.up_proj:  60%|█████▉    | 21801/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.70.down_proj:  60%|█████▉    | 21802/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.71.gate_proj:  60%|█████▉    | 21803/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.71.up_proj:  60%|█████▉    | 21804/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.71.down_proj:  60%|█████▉    | 21805/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.72.gate_proj:  60%|█████▉    | 21806/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.72.up_proj:  60%|█████▉    | 21807/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.72.down_proj:  60%|█████▉    | 21808/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.73.gate_proj:  60%|█████▉    | 21809/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.73.up_proj:  60%|█████▉    | 21810/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.73.down_proj:  60%|█████▉    | 21811/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.74.gate_proj:  60%|█████▉    | 21812/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.74.up_proj:  60%|█████▉    | 21813/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.74.down_proj:  60%|█████▉    | 21814/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.75.gate_proj:  60%|█████▉    | 21815/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.75.up_proj:  60%|█████▉    | 21816/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.75.down_proj:  60%|█████▉    | 21817/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.76.gate_proj:  60%|█████▉    | 21818/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.76.up_proj:  60%|█████▉    | 21819/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.76.down_proj:  60%|█████▉    | 21820/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.77.gate_proj:  60%|█████▉    | 21821/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.77.up_proj:  60%|█████▉    | 21822/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.77.down_proj:  60%|█████▉    | 21823/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.78.gate_proj:  60%|█████▉    | 21824/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.78.up_proj:  60%|█████▉    | 21825/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.78.down_proj:  60%|█████▉    | 21826/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.79.gate_proj:  60%|█████▉    | 21827/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.79.up_proj:  60%|█████▉    | 21828/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.79.down_proj:  60%|█████▉    | 21829/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.80.gate_proj:  60%|█████▉    | 21830/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.80.up_proj:  60%|█████▉    | 21831/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.80.down_proj:  60%|█████▉    | 21832/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.81.gate_proj:  60%|█████▉    | 21833/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.81.up_proj:  60%|█████▉    | 21834/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.81.down_proj:  60%|█████▉    | 21835/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.82.gate_proj:  60%|█████▉    | 21836/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.82.up_proj:  60%|█████▉    | 21837/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.82.down_proj:  60%|█████▉    | 21838/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.83.gate_proj:  60%|█████▉    | 21839/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.83.up_proj:  60%|█████▉    | 21840/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.83.down_proj:  60%|█████▉    | 21841/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.84.gate_proj:  60%|█████▉    | 21842/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.84.up_proj:  60%|█████▉    | 21843/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.84.down_proj:  60%|█████▉    | 21844/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.85.gate_proj:  60%|█████▉    | 21845/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.85.up_proj:  60%|█████▉    | 21846/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.85.down_proj:  60%|█████▉    | 21847/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.86.gate_proj:  60%|█████▉    | 21848/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.86.up_proj:  60%|█████▉    | 21849/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.86.down_proj:  60%|█████▉    | 21850/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.87.gate_proj:  60%|█████▉    | 21851/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.87.up_proj:  60%|█████▉    | 21852/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.87.down_proj:  60%|█████▉    | 21853/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.88.gate_proj:  60%|█████▉    | 21854/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.88.up_proj:  60%|█████▉    | 21855/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.88.down_proj:  60%|█████▉    | 21856/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.89.gate_proj:  60%|█████▉    | 21857/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.89.up_proj:  60%|█████▉    | 21858/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.89.down_proj:  60%|█████▉    | 21859/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.90.gate_proj:  60%|█████▉    | 21860/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.90.up_proj:  60%|█████▉    | 21861/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.90.down_proj:  60%|█████▉    | 21862/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.91.gate_proj:  60%|█████▉    | 21863/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.91.up_proj:  60%|█████▉    | 21864/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.91.down_proj:  60%|█████▉    | 21865/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.92.gate_proj:  60%|█████▉    | 21866/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.92.up_proj:  60%|█████▉    | 21867/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.92.down_proj:  60%|█████▉    | 21868/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.93.gate_proj:  60%|█████▉    | 21869/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.93.up_proj:  60%|█████▉    | 21870/36566 [00:20<00:12, 1148.38it/s]  
packing model.layers.55.mlp.experts.93.down_proj:  60%|█████▉    | 21871/36566 [00:20<00:12, 1148.38it/s]
packing model.layers.55.mlp.experts.93.down_proj:  60%|█████▉    | 21872/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.94.gate_proj:  60%|█████▉    | 21872/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.94.up_proj:  60%|█████▉    | 21873/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.94.down_proj:  60%|█████▉    | 21874/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.95.gate_proj:  60%|█████▉    | 21875/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.95.up_proj:  60%|█████▉    | 21876/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.95.down_proj:  60%|█████▉    | 21877/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.96.gate_proj:  60%|█████▉    | 21878/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.96.up_proj:  60%|█████▉    | 21879/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.96.down_proj:  60%|█████▉    | 21880/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.97.gate_proj:  60%|█████▉    | 21881/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.97.up_proj:  60%|█████▉    | 21882/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.97.down_proj:  60%|█████▉    | 21883/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.98.gate_proj:  60%|█████▉    | 21884/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.98.up_proj:  60%|█████▉    | 21885/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.98.down_proj:  60%|█████▉    | 21886/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.99.gate_proj:  60%|█████▉    | 21887/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.99.up_proj:  60%|█████▉    | 21888/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.99.down_proj:  60%|█████▉    | 21889/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.100.gate_proj:  60%|█████▉    | 21890/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.100.up_proj:  60%|█████▉    | 21891/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.100.down_proj:  60%|█████▉    | 21892/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.101.gate_proj:  60%|█████▉    | 21893/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.101.up_proj:  60%|█████▉    | 21894/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.101.down_proj:  60%|█████▉    | 21895/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.102.gate_proj:  60%|█████▉    | 21896/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.102.up_proj:  60%|█████▉    | 21897/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.102.down_proj:  60%|█████▉    | 21898/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.103.gate_proj:  60%|█████▉    | 21899/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.103.up_proj:  60%|█████▉    | 21900/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.103.down_proj:  60%|█████▉    | 21901/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.104.gate_proj:  60%|█████▉    | 21902/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.104.up_proj:  60%|█████▉    | 21903/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.104.down_proj:  60%|█████▉    | 21904/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.105.gate_proj:  60%|█████▉    | 21905/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.105.up_proj:  60%|█████▉    | 21906/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.105.down_proj:  60%|█████▉    | 21907/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.106.gate_proj:  60%|█████▉    | 21908/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.106.up_proj:  60%|█████▉    | 21909/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.106.down_proj:  60%|█████▉    | 21910/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.107.gate_proj:  60%|█████▉    | 21911/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.107.up_proj:  60%|█████▉    | 21912/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.107.down_proj:  60%|█████▉    | 21913/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.108.gate_proj:  60%|█████▉    | 21914/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.108.up_proj:  60%|█████▉    | 21915/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.108.down_proj:  60%|█████▉    | 21916/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.109.gate_proj:  60%|█████▉    | 21917/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.109.up_proj:  60%|█████▉    | 21918/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.109.down_proj:  60%|█████▉    | 21919/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.110.gate_proj:  60%|█████▉    | 21920/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.110.up_proj:  60%|█████▉    | 21921/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.110.down_proj:  60%|█████▉    | 21922/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.111.gate_proj:  60%|█████▉    | 21923/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.111.up_proj:  60%|█████▉    | 21924/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.111.down_proj:  60%|█████▉    | 21925/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.112.gate_proj:  60%|█████▉    | 21926/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.112.up_proj:  60%|█████▉    | 21927/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.112.down_proj:  60%|█████▉    | 21928/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.113.gate_proj:  60%|█████▉    | 21929/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.113.up_proj:  60%|█████▉    | 21930/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.113.down_proj:  60%|█████▉    | 21931/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.114.gate_proj:  60%|█████▉    | 21932/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.114.up_proj:  60%|█████▉    | 21933/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.114.down_proj:  60%|█████▉    | 21934/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.115.gate_proj:  60%|█████▉    | 21935/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.115.up_proj:  60%|█████▉    | 21936/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.115.down_proj:  60%|█████▉    | 21937/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.116.gate_proj:  60%|█████▉    | 21938/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.116.up_proj:  60%|█████▉    | 21939/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.116.down_proj:  60%|██████    | 21940/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.117.gate_proj:  60%|██████    | 21941/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.117.up_proj:  60%|██████    | 21942/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.117.down_proj:  60%|██████    | 21943/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.118.gate_proj:  60%|██████    | 21944/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.118.up_proj:  60%|██████    | 21945/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.118.down_proj:  60%|██████    | 21946/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.119.gate_proj:  60%|██████    | 21947/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.119.up_proj:  60%|██████    | 21948/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.119.down_proj:  60%|██████    | 21949/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.120.gate_proj:  60%|██████    | 21950/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.120.up_proj:  60%|██████    | 21951/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.120.down_proj:  60%|██████    | 21952/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.121.gate_proj:  60%|██████    | 21953/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.121.up_proj:  60%|██████    | 21954/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.121.down_proj:  60%|██████    | 21955/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.122.gate_proj:  60%|██████    | 21956/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.122.up_proj:  60%|██████    | 21957/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.122.down_proj:  60%|██████    | 21958/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.123.gate_proj:  60%|██████    | 21959/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.123.up_proj:  60%|██████    | 21960/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.123.down_proj:  60%|██████    | 21961/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.124.gate_proj:  60%|██████    | 21962/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.124.up_proj:  60%|██████    | 21963/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.124.down_proj:  60%|██████    | 21964/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.125.gate_proj:  60%|██████    | 21965/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.125.up_proj:  60%|██████    | 21966/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.125.down_proj:  60%|██████    | 21967/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.126.gate_proj:  60%|██████    | 21968/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.126.up_proj:  60%|██████    | 21969/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.126.down_proj:  60%|██████    | 21970/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.127.gate_proj:  60%|██████    | 21971/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.55.mlp.experts.127.up_proj:  60%|██████    | 21972/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.55.mlp.experts.127.down_proj:  60%|██████    | 21973/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.0.gate_proj:  60%|██████    | 21974/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.56.mlp.experts.0.up_proj:  60%|██████    | 21975/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.56.mlp.experts.0.down_proj:  60%|██████    | 21976/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.1.gate_proj:  60%|██████    | 21977/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.1.up_proj:  60%|██████    | 21978/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.56.mlp.experts.1.down_proj:  60%|██████    | 21979/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.2.gate_proj:  60%|██████    | 21980/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.2.up_proj:  60%|██████    | 21981/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.56.mlp.experts.2.down_proj:  60%|██████    | 21982/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.3.gate_proj:  60%|██████    | 21983/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.3.up_proj:  60%|██████    | 21984/36566 [00:20<00:12, 1141.93it/s]  
packing model.layers.56.mlp.experts.3.down_proj:  60%|██████    | 21985/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.4.gate_proj:  60%|██████    | 21986/36566 [00:20<00:12, 1141.93it/s]
packing model.layers.56.mlp.experts.4.gate_proj:  60%|██████    | 21987/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.4.up_proj:  60%|██████    | 21987/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.4.down_proj:  60%|██████    | 21988/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.5.gate_proj:  60%|██████    | 21989/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.5.up_proj:  60%|██████    | 21990/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.5.down_proj:  60%|██████    | 21991/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.6.gate_proj:  60%|██████    | 21992/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.6.up_proj:  60%|██████    | 21993/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.6.down_proj:  60%|██████    | 21994/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.7.gate_proj:  60%|██████    | 21995/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.7.up_proj:  60%|██████    | 21996/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.7.down_proj:  60%|██████    | 21997/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.8.gate_proj:  60%|██████    | 21998/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.8.up_proj:  60%|██████    | 21999/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.8.down_proj:  60%|██████    | 22000/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.9.gate_proj:  60%|██████    | 22001/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.9.up_proj:  60%|██████    | 22002/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.9.down_proj:  60%|██████    | 22003/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.10.gate_proj:  60%|██████    | 22004/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.10.up_proj:  60%|██████    | 22005/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.10.down_proj:  60%|██████    | 22006/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.11.gate_proj:  60%|██████    | 22007/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.11.up_proj:  60%|██████    | 22008/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.11.down_proj:  60%|██████    | 22009/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.12.gate_proj:  60%|██████    | 22010/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.12.up_proj:  60%|██████    | 22011/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.12.down_proj:  60%|██████    | 22012/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.13.gate_proj:  60%|██████    | 22013/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.13.up_proj:  60%|██████    | 22014/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.13.down_proj:  60%|██████    | 22015/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.14.gate_proj:  60%|██████    | 22016/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.14.up_proj:  60%|██████    | 22017/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.14.down_proj:  60%|██████    | 22018/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.15.gate_proj:  60%|██████    | 22019/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.15.up_proj:  60%|██████    | 22020/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.15.down_proj:  60%|██████    | 22021/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.16.gate_proj:  60%|██████    | 22022/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.16.up_proj:  60%|██████    | 22023/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.16.down_proj:  60%|██████    | 22024/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.17.gate_proj:  60%|██████    | 22025/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.17.up_proj:  60%|██████    | 22026/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.17.down_proj:  60%|██████    | 22027/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.18.gate_proj:  60%|██████    | 22028/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.18.up_proj:  60%|██████    | 22029/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.18.down_proj:  60%|██████    | 22030/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.19.gate_proj:  60%|██████    | 22031/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.19.up_proj:  60%|██████    | 22032/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.19.down_proj:  60%|██████    | 22033/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.20.gate_proj:  60%|██████    | 22034/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.20.up_proj:  60%|██████    | 22035/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.20.down_proj:  60%|██████    | 22036/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.21.gate_proj:  60%|██████    | 22037/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.21.up_proj:  60%|██████    | 22038/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.21.down_proj:  60%|██████    | 22039/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.22.gate_proj:  60%|██████    | 22040/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.22.up_proj:  60%|██████    | 22041/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.22.down_proj:  60%|██████    | 22042/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.23.gate_proj:  60%|██████    | 22043/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.23.up_proj:  60%|██████    | 22044/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.23.down_proj:  60%|██████    | 22045/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.24.gate_proj:  60%|██████    | 22046/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.24.up_proj:  60%|██████    | 22047/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.24.down_proj:  60%|██████    | 22048/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.25.gate_proj:  60%|██████    | 22049/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.25.up_proj:  60%|██████    | 22050/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.25.down_proj:  60%|██████    | 22051/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.26.gate_proj:  60%|██████    | 22052/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.26.up_proj:  60%|██████    | 22053/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.26.down_proj:  60%|██████    | 22054/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.27.gate_proj:  60%|██████    | 22055/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.27.up_proj:  60%|██████    | 22056/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.27.down_proj:  60%|██████    | 22057/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.28.gate_proj:  60%|██████    | 22058/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.28.up_proj:  60%|██████    | 22059/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.28.down_proj:  60%|██████    | 22060/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.29.gate_proj:  60%|██████    | 22061/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.29.up_proj:  60%|██████    | 22062/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.29.down_proj:  60%|██████    | 22063/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.30.gate_proj:  60%|██████    | 22064/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.30.up_proj:  60%|██████    | 22065/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.30.down_proj:  60%|██████    | 22066/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.31.gate_proj:  60%|██████    | 22067/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.31.up_proj:  60%|██████    | 22068/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.31.down_proj:  60%|██████    | 22069/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.32.gate_proj:  60%|██████    | 22070/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.32.up_proj:  60%|██████    | 22071/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.32.down_proj:  60%|██████    | 22072/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.33.gate_proj:  60%|██████    | 22073/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.33.up_proj:  60%|██████    | 22074/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.33.down_proj:  60%|██████    | 22075/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.34.gate_proj:  60%|██████    | 22076/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.34.up_proj:  60%|██████    | 22077/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.34.down_proj:  60%|██████    | 22078/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.35.gate_proj:  60%|██████    | 22079/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.35.up_proj:  60%|██████    | 22080/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.35.down_proj:  60%|██████    | 22081/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.36.gate_proj:  60%|██████    | 22082/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.36.up_proj:  60%|██████    | 22083/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.36.down_proj:  60%|██████    | 22084/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.37.gate_proj:  60%|██████    | 22085/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.37.up_proj:  60%|██████    | 22086/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.37.down_proj:  60%|██████    | 22087/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.38.gate_proj:  60%|██████    | 22088/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.38.up_proj:  60%|██████    | 22089/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.38.down_proj:  60%|██████    | 22090/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.39.gate_proj:  60%|██████    | 22091/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.39.up_proj:  60%|██████    | 22092/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.39.down_proj:  60%|██████    | 22093/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.40.gate_proj:  60%|██████    | 22094/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.40.up_proj:  60%|██████    | 22095/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.40.down_proj:  60%|██████    | 22096/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.41.gate_proj:  60%|██████    | 22097/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.41.up_proj:  60%|██████    | 22098/36566 [00:20<00:12, 1138.42it/s]  
packing model.layers.56.mlp.experts.41.down_proj:  60%|██████    | 22099/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.42.gate_proj:  60%|██████    | 22100/36566 [00:20<00:12, 1138.42it/s]
packing model.layers.56.mlp.experts.42.gate_proj:  60%|██████    | 22101/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.42.up_proj:  60%|██████    | 22101/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.42.down_proj:  60%|██████    | 22102/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.43.gate_proj:  60%|██████    | 22103/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.43.up_proj:  60%|██████    | 22104/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.43.down_proj:  60%|██████    | 22105/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.44.gate_proj:  60%|██████    | 22106/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.44.up_proj:  60%|██████    | 22107/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.44.down_proj:  60%|██████    | 22108/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.45.gate_proj:  60%|██████    | 22109/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.45.up_proj:  60%|██████    | 22110/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.45.down_proj:  60%|██████    | 22111/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.46.gate_proj:  60%|██████    | 22112/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.46.up_proj:  60%|██████    | 22113/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.46.down_proj:  60%|██████    | 22114/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.47.gate_proj:  60%|██████    | 22115/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.47.up_proj:  60%|██████    | 22116/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.47.down_proj:  60%|██████    | 22117/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.48.gate_proj:  60%|██████    | 22118/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.48.up_proj:  60%|██████    | 22119/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.48.down_proj:  60%|██████    | 22120/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.49.gate_proj:  60%|██████    | 22121/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.49.up_proj:  60%|██████    | 22122/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.49.down_proj:  61%|██████    | 22123/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.50.gate_proj:  61%|██████    | 22124/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.50.up_proj:  61%|██████    | 22125/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.50.down_proj:  61%|██████    | 22126/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.51.gate_proj:  61%|██████    | 22127/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.51.up_proj:  61%|██████    | 22128/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.51.down_proj:  61%|██████    | 22129/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.52.gate_proj:  61%|██████    | 22130/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.52.up_proj:  61%|██████    | 22131/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.52.down_proj:  61%|██████    | 22132/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.53.gate_proj:  61%|██████    | 22133/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.53.up_proj:  61%|██████    | 22134/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.53.down_proj:  61%|██████    | 22135/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.54.gate_proj:  61%|██████    | 22136/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.54.up_proj:  61%|██████    | 22137/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.54.down_proj:  61%|██████    | 22138/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.55.gate_proj:  61%|██████    | 22139/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.55.up_proj:  61%|██████    | 22140/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.55.down_proj:  61%|██████    | 22141/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.56.gate_proj:  61%|██████    | 22142/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.56.up_proj:  61%|██████    | 22143/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.56.down_proj:  61%|██████    | 22144/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.57.gate_proj:  61%|██████    | 22145/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.57.up_proj:  61%|██████    | 22146/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.57.down_proj:  61%|██████    | 22147/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.58.gate_proj:  61%|██████    | 22148/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.58.up_proj:  61%|██████    | 22149/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.58.down_proj:  61%|██████    | 22150/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.59.gate_proj:  61%|██████    | 22151/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.59.up_proj:  61%|██████    | 22152/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.59.down_proj:  61%|██████    | 22153/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.60.gate_proj:  61%|██████    | 22154/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.60.up_proj:  61%|██████    | 22155/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.60.down_proj:  61%|██████    | 22156/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.61.gate_proj:  61%|██████    | 22157/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.61.up_proj:  61%|██████    | 22158/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.61.down_proj:  61%|██████    | 22159/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.62.gate_proj:  61%|██████    | 22160/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.62.up_proj:  61%|██████    | 22161/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.62.down_proj:  61%|██████    | 22162/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.63.gate_proj:  61%|██████    | 22163/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.63.up_proj:  61%|██████    | 22164/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.63.down_proj:  61%|██████    | 22165/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.64.gate_proj:  61%|██████    | 22166/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.64.up_proj:  61%|██████    | 22167/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.64.down_proj:  61%|██████    | 22168/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.65.gate_proj:  61%|██████    | 22169/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.65.up_proj:  61%|██████    | 22170/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.65.down_proj:  61%|██████    | 22171/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.66.gate_proj:  61%|██████    | 22172/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.66.up_proj:  61%|██████    | 22173/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.66.down_proj:  61%|██████    | 22174/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.67.gate_proj:  61%|██████    | 22175/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.67.up_proj:  61%|██████    | 22176/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.67.down_proj:  61%|██████    | 22177/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.68.gate_proj:  61%|██████    | 22178/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.68.up_proj:  61%|██████    | 22179/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.68.down_proj:  61%|██████    | 22180/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.69.gate_proj:  61%|██████    | 22181/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.69.up_proj:  61%|██████    | 22182/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.69.down_proj:  61%|██████    | 22183/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.70.gate_proj:  61%|██████    | 22184/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.70.up_proj:  61%|██████    | 22185/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.70.down_proj:  61%|██████    | 22186/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.71.gate_proj:  61%|██████    | 22187/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.71.up_proj:  61%|██████    | 22188/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.71.down_proj:  61%|██████    | 22189/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.72.gate_proj:  61%|██████    | 22190/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.72.up_proj:  61%|██████    | 22191/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.72.down_proj:  61%|██████    | 22192/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.73.gate_proj:  61%|██████    | 22193/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.73.up_proj:  61%|██████    | 22194/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.73.down_proj:  61%|██████    | 22195/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.74.gate_proj:  61%|██████    | 22196/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.74.up_proj:  61%|██████    | 22197/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.74.down_proj:  61%|██████    | 22198/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.75.gate_proj:  61%|██████    | 22199/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.75.up_proj:  61%|██████    | 22200/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.75.down_proj:  61%|██████    | 22201/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.76.gate_proj:  61%|██████    | 22202/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.76.up_proj:  61%|██████    | 22203/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.76.down_proj:  61%|██████    | 22204/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.77.gate_proj:  61%|██████    | 22205/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.77.up_proj:  61%|██████    | 22206/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.77.down_proj:  61%|██████    | 22207/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.78.gate_proj:  61%|██████    | 22208/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.78.up_proj:  61%|██████    | 22209/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.78.down_proj:  61%|██████    | 22210/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.79.gate_proj:  61%|██████    | 22211/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.79.up_proj:  61%|██████    | 22212/36566 [00:20<00:12, 1136.34it/s]  
packing model.layers.56.mlp.experts.79.down_proj:  61%|██████    | 22213/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.80.gate_proj:  61%|██████    | 22214/36566 [00:20<00:12, 1136.34it/s]
packing model.layers.56.mlp.experts.80.gate_proj:  61%|██████    | 22215/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.80.up_proj:  61%|██████    | 22215/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.80.down_proj:  61%|██████    | 22216/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.81.gate_proj:  61%|██████    | 22217/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.81.up_proj:  61%|██████    | 22218/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.81.down_proj:  61%|██████    | 22219/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.82.gate_proj:  61%|██████    | 22220/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.82.up_proj:  61%|██████    | 22221/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.82.down_proj:  61%|██████    | 22222/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.83.gate_proj:  61%|██████    | 22223/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.83.up_proj:  61%|██████    | 22224/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.83.down_proj:  61%|██████    | 22225/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.84.gate_proj:  61%|██████    | 22226/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.84.up_proj:  61%|██████    | 22227/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.84.down_proj:  61%|██████    | 22228/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.85.gate_proj:  61%|██████    | 22229/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.85.up_proj:  61%|██████    | 22230/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.85.down_proj:  61%|██████    | 22231/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.86.gate_proj:  61%|██████    | 22232/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.86.up_proj:  61%|██████    | 22233/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.86.down_proj:  61%|██████    | 22234/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.87.gate_proj:  61%|██████    | 22235/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.87.up_proj:  61%|██████    | 22236/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.87.down_proj:  61%|██████    | 22237/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.88.gate_proj:  61%|██████    | 22238/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.88.up_proj:  61%|██████    | 22239/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.88.down_proj:  61%|██████    | 22240/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.89.gate_proj:  61%|██████    | 22241/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.89.up_proj:  61%|██████    | 22242/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.89.down_proj:  61%|██████    | 22243/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.90.gate_proj:  61%|██████    | 22244/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.90.up_proj:  61%|██████    | 22245/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.90.down_proj:  61%|██████    | 22246/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.91.gate_proj:  61%|██████    | 22247/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.91.up_proj:  61%|██████    | 22248/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.91.down_proj:  61%|██████    | 22249/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.92.gate_proj:  61%|██████    | 22250/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.92.up_proj:  61%|██████    | 22251/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.92.down_proj:  61%|██████    | 22252/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.93.gate_proj:  61%|██████    | 22253/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.93.up_proj:  61%|██████    | 22254/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.93.down_proj:  61%|██████    | 22255/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.94.gate_proj:  61%|██████    | 22256/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.94.up_proj:  61%|██████    | 22257/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.94.down_proj:  61%|██████    | 22258/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.95.gate_proj:  61%|██████    | 22259/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.95.up_proj:  61%|██████    | 22260/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.95.down_proj:  61%|██████    | 22261/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.96.gate_proj:  61%|██████    | 22262/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.96.up_proj:  61%|██████    | 22263/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.96.down_proj:  61%|██████    | 22264/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.97.gate_proj:  61%|██████    | 22265/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.97.up_proj:  61%|██████    | 22266/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.97.down_proj:  61%|██████    | 22267/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.98.gate_proj:  61%|██████    | 22268/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.98.up_proj:  61%|██████    | 22269/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.98.down_proj:  61%|██████    | 22270/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.99.gate_proj:  61%|██████    | 22271/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.99.up_proj:  61%|██████    | 22272/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.99.down_proj:  61%|██████    | 22273/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.100.gate_proj:  61%|██████    | 22274/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.100.up_proj:  61%|██████    | 22275/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.100.down_proj:  61%|██████    | 22276/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.101.gate_proj:  61%|██████    | 22277/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.101.up_proj:  61%|██████    | 22278/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.101.down_proj:  61%|██████    | 22279/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.102.gate_proj:  61%|██████    | 22280/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.102.up_proj:  61%|██████    | 22281/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.102.down_proj:  61%|██████    | 22282/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.103.gate_proj:  61%|██████    | 22283/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.103.up_proj:  61%|██████    | 22284/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.103.down_proj:  61%|██████    | 22285/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.104.gate_proj:  61%|██████    | 22286/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.104.up_proj:  61%|██████    | 22287/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.104.down_proj:  61%|██████    | 22288/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.105.gate_proj:  61%|██████    | 22289/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.105.up_proj:  61%|██████    | 22290/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.105.down_proj:  61%|██████    | 22291/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.106.gate_proj:  61%|██████    | 22292/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.106.up_proj:  61%|██████    | 22293/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.106.down_proj:  61%|██████    | 22294/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.107.gate_proj:  61%|██████    | 22295/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.107.up_proj:  61%|██████    | 22296/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.107.down_proj:  61%|██████    | 22297/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.108.gate_proj:  61%|██████    | 22298/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.108.up_proj:  61%|██████    | 22299/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.108.down_proj:  61%|██████    | 22300/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.109.gate_proj:  61%|██████    | 22301/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.109.up_proj:  61%|██████    | 22302/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.109.down_proj:  61%|██████    | 22303/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.110.gate_proj:  61%|██████    | 22304/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.110.up_proj:  61%|██████    | 22305/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.110.down_proj:  61%|██████    | 22306/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.111.gate_proj:  61%|██████    | 22307/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.111.up_proj:  61%|██████    | 22308/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.111.down_proj:  61%|██████    | 22309/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.112.gate_proj:  61%|██████    | 22310/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.112.up_proj:  61%|██████    | 22311/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.112.down_proj:  61%|██████    | 22312/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.113.gate_proj:  61%|██████    | 22313/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.113.up_proj:  61%|██████    | 22314/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.113.down_proj:  61%|██████    | 22315/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.114.gate_proj:  61%|██████    | 22316/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.114.up_proj:  61%|██████    | 22317/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.114.down_proj:  61%|██████    | 22318/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.115.gate_proj:  61%|██████    | 22319/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.115.up_proj:  61%|██████    | 22320/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.115.down_proj:  61%|██████    | 22321/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.116.gate_proj:  61%|██████    | 22322/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.116.up_proj:  61%|██████    | 22323/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.116.down_proj:  61%|██████    | 22324/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.117.gate_proj:  61%|██████    | 22325/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.117.up_proj:  61%|██████    | 22326/36566 [00:20<00:12, 1137.23it/s]  
packing model.layers.56.mlp.experts.117.down_proj:  61%|██████    | 22327/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.118.gate_proj:  61%|██████    | 22328/36566 [00:20<00:12, 1137.23it/s]
packing model.layers.56.mlp.experts.118.gate_proj:  61%|██████    | 22329/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.118.up_proj:  61%|██████    | 22329/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.118.down_proj:  61%|██████    | 22330/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.119.gate_proj:  61%|██████    | 22331/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.119.up_proj:  61%|██████    | 22332/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.119.down_proj:  61%|██████    | 22333/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.120.gate_proj:  61%|██████    | 22334/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.120.up_proj:  61%|██████    | 22335/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.120.down_proj:  61%|██████    | 22336/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.121.gate_proj:  61%|██████    | 22337/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.121.up_proj:  61%|██████    | 22338/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.121.down_proj:  61%|██████    | 22339/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.122.gate_proj:  61%|██████    | 22340/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.122.up_proj:  61%|██████    | 22341/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.122.down_proj:  61%|██████    | 22342/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.123.gate_proj:  61%|██████    | 22343/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.123.up_proj:  61%|██████    | 22344/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.123.down_proj:  61%|██████    | 22345/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.124.gate_proj:  61%|██████    | 22346/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.124.up_proj:  61%|██████    | 22347/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.124.down_proj:  61%|██████    | 22348/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.125.gate_proj:  61%|██████    | 22349/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.125.up_proj:  61%|██████    | 22350/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.125.down_proj:  61%|██████    | 22351/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.126.gate_proj:  61%|██████    | 22352/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.126.up_proj:  61%|██████    | 22353/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.126.down_proj:  61%|██████    | 22354/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.127.gate_proj:  61%|██████    | 22355/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.56.mlp.experts.127.up_proj:  61%|██████    | 22356/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.56.mlp.experts.127.down_proj:  61%|██████    | 22357/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.0.gate_proj:  61%|██████    | 22358/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.0.up_proj:  61%|██████    | 22359/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.0.down_proj:  61%|██████    | 22360/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.1.gate_proj:  61%|██████    | 22361/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.1.up_proj:  61%|██████    | 22362/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.1.down_proj:  61%|██████    | 22363/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.2.gate_proj:  61%|██████    | 22364/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.2.up_proj:  61%|██████    | 22365/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.2.down_proj:  61%|██████    | 22366/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.3.gate_proj:  61%|██████    | 22367/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.3.up_proj:  61%|██████    | 22368/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.3.down_proj:  61%|██████    | 22369/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.4.gate_proj:  61%|██████    | 22370/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.4.up_proj:  61%|██████    | 22371/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.4.down_proj:  61%|██████    | 22372/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.5.gate_proj:  61%|██████    | 22373/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.5.up_proj:  61%|██████    | 22374/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.5.down_proj:  61%|██████    | 22375/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.6.gate_proj:  61%|██████    | 22376/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.6.up_proj:  61%|██████    | 22377/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.6.down_proj:  61%|██████    | 22378/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.7.gate_proj:  61%|██████    | 22379/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.7.up_proj:  61%|██████    | 22380/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.7.down_proj:  61%|██████    | 22381/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.8.gate_proj:  61%|██████    | 22382/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.8.up_proj:  61%|██████    | 22383/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.8.down_proj:  61%|██████    | 22384/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.9.gate_proj:  61%|██████    | 22385/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.9.up_proj:  61%|██████    | 22386/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.9.down_proj:  61%|██████    | 22387/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.10.gate_proj:  61%|██████    | 22388/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.10.up_proj:  61%|██████    | 22389/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.10.down_proj:  61%|██████    | 22390/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.11.gate_proj:  61%|██████    | 22391/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.11.up_proj:  61%|██████    | 22392/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.11.down_proj:  61%|██████    | 22393/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.12.gate_proj:  61%|██████    | 22394/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.12.up_proj:  61%|██████    | 22395/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.12.down_proj:  61%|██████    | 22396/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.13.gate_proj:  61%|██████▏   | 22397/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.13.up_proj:  61%|██████▏   | 22398/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.13.down_proj:  61%|██████▏   | 22399/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.14.gate_proj:  61%|██████▏   | 22400/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.14.up_proj:  61%|██████▏   | 22401/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.14.down_proj:  61%|██████▏   | 22402/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.15.gate_proj:  61%|██████▏   | 22403/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.15.up_proj:  61%|██████▏   | 22404/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.15.down_proj:  61%|██████▏   | 22405/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.16.gate_proj:  61%|██████▏   | 22406/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.16.up_proj:  61%|██████▏   | 22407/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.16.down_proj:  61%|██████▏   | 22408/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.17.gate_proj:  61%|██████▏   | 22409/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.17.up_proj:  61%|██████▏   | 22410/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.17.down_proj:  61%|██████▏   | 22411/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.18.gate_proj:  61%|██████▏   | 22412/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.18.up_proj:  61%|██████▏   | 22413/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.18.down_proj:  61%|██████▏   | 22414/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.19.gate_proj:  61%|██████▏   | 22415/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.19.up_proj:  61%|██████▏   | 22416/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.19.down_proj:  61%|██████▏   | 22417/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.20.gate_proj:  61%|██████▏   | 22418/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.20.up_proj:  61%|██████▏   | 22419/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.20.down_proj:  61%|██████▏   | 22420/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.21.gate_proj:  61%|██████▏   | 22421/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.21.up_proj:  61%|██████▏   | 22422/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.21.down_proj:  61%|██████▏   | 22423/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.22.gate_proj:  61%|██████▏   | 22424/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.22.up_proj:  61%|██████▏   | 22425/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.22.down_proj:  61%|██████▏   | 22426/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.23.gate_proj:  61%|██████▏   | 22427/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.23.up_proj:  61%|██████▏   | 22428/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.23.down_proj:  61%|██████▏   | 22429/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.24.gate_proj:  61%|██████▏   | 22430/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.24.up_proj:  61%|██████▏   | 22431/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.24.down_proj:  61%|██████▏   | 22432/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.25.gate_proj:  61%|██████▏   | 22433/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.25.up_proj:  61%|██████▏   | 22434/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.25.down_proj:  61%|██████▏   | 22435/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.26.gate_proj:  61%|██████▏   | 22436/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.26.up_proj:  61%|██████▏   | 22437/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.26.down_proj:  61%|██████▏   | 22438/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.27.gate_proj:  61%|██████▏   | 22439/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.27.up_proj:  61%|██████▏   | 22440/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.27.down_proj:  61%|██████▏   | 22441/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.28.gate_proj:  61%|██████▏   | 22442/36566 [00:20<00:12, 1135.83it/s]
packing model.layers.57.mlp.experts.28.up_proj:  61%|██████▏   | 22443/36566 [00:20<00:12, 1135.83it/s]  
packing model.layers.57.mlp.experts.28.up_proj:  61%|██████▏   | 22444/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.28.down_proj:  61%|██████▏   | 22444/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.29.gate_proj:  61%|██████▏   | 22445/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.29.up_proj:  61%|██████▏   | 22446/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.29.down_proj:  61%|██████▏   | 22447/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.30.gate_proj:  61%|██████▏   | 22448/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.30.up_proj:  61%|██████▏   | 22449/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.30.down_proj:  61%|██████▏   | 22450/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.31.gate_proj:  61%|██████▏   | 22451/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.31.up_proj:  61%|██████▏   | 22452/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.31.down_proj:  61%|██████▏   | 22453/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.32.gate_proj:  61%|██████▏   | 22454/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.32.up_proj:  61%|██████▏   | 22455/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.32.down_proj:  61%|██████▏   | 22456/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.33.gate_proj:  61%|██████▏   | 22457/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.33.up_proj:  61%|██████▏   | 22458/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.33.down_proj:  61%|██████▏   | 22459/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.34.gate_proj:  61%|██████▏   | 22460/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.34.up_proj:  61%|██████▏   | 22461/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.34.down_proj:  61%|██████▏   | 22462/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.35.gate_proj:  61%|██████▏   | 22463/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.35.up_proj:  61%|██████▏   | 22464/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.35.down_proj:  61%|██████▏   | 22465/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.36.gate_proj:  61%|██████▏   | 22466/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.36.up_proj:  61%|██████▏   | 22467/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.36.down_proj:  61%|██████▏   | 22468/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.37.gate_proj:  61%|██████▏   | 22469/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.37.up_proj:  61%|██████▏   | 22470/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.37.down_proj:  61%|██████▏   | 22471/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.38.gate_proj:  61%|██████▏   | 22472/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.38.up_proj:  61%|██████▏   | 22473/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.38.down_proj:  61%|██████▏   | 22474/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.39.gate_proj:  61%|██████▏   | 22475/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.39.up_proj:  61%|██████▏   | 22476/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.39.down_proj:  61%|██████▏   | 22477/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.40.gate_proj:  61%|██████▏   | 22478/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.40.up_proj:  61%|██████▏   | 22479/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.40.down_proj:  61%|██████▏   | 22480/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.41.gate_proj:  61%|██████▏   | 22481/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.41.up_proj:  61%|██████▏   | 22482/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.41.down_proj:  61%|██████▏   | 22483/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.42.gate_proj:  61%|██████▏   | 22484/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.42.up_proj:  61%|██████▏   | 22485/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.42.down_proj:  61%|██████▏   | 22486/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.43.gate_proj:  61%|██████▏   | 22487/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.43.up_proj:  61%|██████▏   | 22488/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.43.down_proj:  62%|██████▏   | 22489/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.44.gate_proj:  62%|██████▏   | 22490/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.44.up_proj:  62%|██████▏   | 22491/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.44.down_proj:  62%|██████▏   | 22492/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.45.gate_proj:  62%|██████▏   | 22493/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.45.up_proj:  62%|██████▏   | 22494/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.45.down_proj:  62%|██████▏   | 22495/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.46.gate_proj:  62%|██████▏   | 22496/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.46.up_proj:  62%|██████▏   | 22497/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.46.down_proj:  62%|██████▏   | 22498/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.47.gate_proj:  62%|██████▏   | 22499/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.47.up_proj:  62%|██████▏   | 22500/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.47.down_proj:  62%|██████▏   | 22501/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.48.gate_proj:  62%|██████▏   | 22502/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.48.up_proj:  62%|██████▏   | 22503/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.48.down_proj:  62%|██████▏   | 22504/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.49.gate_proj:  62%|██████▏   | 22505/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.49.up_proj:  62%|██████▏   | 22506/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.49.down_proj:  62%|██████▏   | 22507/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.50.gate_proj:  62%|██████▏   | 22508/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.50.up_proj:  62%|██████▏   | 22509/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.50.down_proj:  62%|██████▏   | 22510/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.51.gate_proj:  62%|██████▏   | 22511/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.51.up_proj:  62%|██████▏   | 22512/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.51.down_proj:  62%|██████▏   | 22513/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.52.gate_proj:  62%|██████▏   | 22514/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.52.up_proj:  62%|██████▏   | 22515/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.52.down_proj:  62%|██████▏   | 22516/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.53.gate_proj:  62%|██████▏   | 22517/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.53.up_proj:  62%|██████▏   | 22518/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.53.down_proj:  62%|██████▏   | 22519/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.54.gate_proj:  62%|██████▏   | 22520/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.54.up_proj:  62%|██████▏   | 22521/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.54.down_proj:  62%|██████▏   | 22522/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.55.gate_proj:  62%|██████▏   | 22523/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.55.up_proj:  62%|██████▏   | 22524/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.55.down_proj:  62%|██████▏   | 22525/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.56.gate_proj:  62%|██████▏   | 22526/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.56.up_proj:  62%|██████▏   | 22527/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.56.down_proj:  62%|██████▏   | 22528/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.57.gate_proj:  62%|██████▏   | 22529/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.57.up_proj:  62%|██████▏   | 22530/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.57.down_proj:  62%|██████▏   | 22531/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.58.gate_proj:  62%|██████▏   | 22532/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.58.up_proj:  62%|██████▏   | 22533/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.58.down_proj:  62%|██████▏   | 22534/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.59.gate_proj:  62%|██████▏   | 22535/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.59.up_proj:  62%|██████▏   | 22536/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.59.down_proj:  62%|██████▏   | 22537/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.60.gate_proj:  62%|██████▏   | 22538/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.60.up_proj:  62%|██████▏   | 22539/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.60.down_proj:  62%|██████▏   | 22540/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.61.gate_proj:  62%|██████▏   | 22541/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.61.up_proj:  62%|██████▏   | 22542/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.61.down_proj:  62%|██████▏   | 22543/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.62.gate_proj:  62%|██████▏   | 22544/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.62.up_proj:  62%|██████▏   | 22545/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.62.down_proj:  62%|██████▏   | 22546/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.63.gate_proj:  62%|██████▏   | 22547/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.63.up_proj:  62%|██████▏   | 22548/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.63.down_proj:  62%|██████▏   | 22549/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.64.gate_proj:  62%|██████▏   | 22550/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.64.up_proj:  62%|██████▏   | 22551/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.64.down_proj:  62%|██████▏   | 22552/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.65.gate_proj:  62%|██████▏   | 22553/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.65.up_proj:  62%|██████▏   | 22554/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.65.down_proj:  62%|██████▏   | 22555/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.66.gate_proj:  62%|██████▏   | 22556/36566 [00:20<00:12, 1138.26it/s]
packing model.layers.57.mlp.experts.66.up_proj:  62%|██████▏   | 22557/36566 [00:20<00:12, 1138.26it/s]  
packing model.layers.57.mlp.experts.66.up_proj:  62%|██████▏   | 22558/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.66.down_proj:  62%|██████▏   | 22558/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.67.gate_proj:  62%|██████▏   | 22559/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.67.up_proj:  62%|██████▏   | 22560/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.67.down_proj:  62%|██████▏   | 22561/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.68.gate_proj:  62%|██████▏   | 22562/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.68.up_proj:  62%|██████▏   | 22563/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.68.down_proj:  62%|██████▏   | 22564/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.69.gate_proj:  62%|██████▏   | 22565/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.69.up_proj:  62%|██████▏   | 22566/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.69.down_proj:  62%|██████▏   | 22567/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.70.gate_proj:  62%|██████▏   | 22568/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.70.up_proj:  62%|██████▏   | 22569/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.70.down_proj:  62%|██████▏   | 22570/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.71.gate_proj:  62%|██████▏   | 22571/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.71.up_proj:  62%|██████▏   | 22572/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.71.down_proj:  62%|██████▏   | 22573/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.72.gate_proj:  62%|██████▏   | 22574/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.72.up_proj:  62%|██████▏   | 22575/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.72.down_proj:  62%|██████▏   | 22576/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.73.gate_proj:  62%|██████▏   | 22577/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.73.up_proj:  62%|██████▏   | 22578/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.73.down_proj:  62%|██████▏   | 22579/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.74.gate_proj:  62%|██████▏   | 22580/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.74.up_proj:  62%|██████▏   | 22581/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.74.down_proj:  62%|██████▏   | 22582/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.75.gate_proj:  62%|██████▏   | 22583/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.75.up_proj:  62%|██████▏   | 22584/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.75.down_proj:  62%|██████▏   | 22585/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.76.gate_proj:  62%|██████▏   | 22586/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.76.up_proj:  62%|██████▏   | 22587/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.76.down_proj:  62%|██████▏   | 22588/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.77.gate_proj:  62%|██████▏   | 22589/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.77.up_proj:  62%|██████▏   | 22590/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.77.down_proj:  62%|██████▏   | 22591/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.78.gate_proj:  62%|██████▏   | 22592/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.78.up_proj:  62%|██████▏   | 22593/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.78.down_proj:  62%|██████▏   | 22594/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.79.gate_proj:  62%|██████▏   | 22595/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.79.up_proj:  62%|██████▏   | 22596/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.79.down_proj:  62%|██████▏   | 22597/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.80.gate_proj:  62%|██████▏   | 22598/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.80.up_proj:  62%|██████▏   | 22599/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.80.down_proj:  62%|██████▏   | 22600/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.81.gate_proj:  62%|██████▏   | 22601/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.81.up_proj:  62%|██████▏   | 22602/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.81.down_proj:  62%|██████▏   | 22603/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.82.gate_proj:  62%|██████▏   | 22604/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.82.up_proj:  62%|██████▏   | 22605/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.82.down_proj:  62%|██████▏   | 22606/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.83.gate_proj:  62%|██████▏   | 22607/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.83.up_proj:  62%|██████▏   | 22608/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.83.down_proj:  62%|██████▏   | 22609/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.84.gate_proj:  62%|██████▏   | 22610/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.84.up_proj:  62%|██████▏   | 22611/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.84.down_proj:  62%|██████▏   | 22612/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.85.gate_proj:  62%|██████▏   | 22613/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.85.up_proj:  62%|██████▏   | 22614/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.85.down_proj:  62%|██████▏   | 22615/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.86.gate_proj:  62%|██████▏   | 22616/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.86.up_proj:  62%|██████▏   | 22617/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.86.down_proj:  62%|██████▏   | 22618/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.87.gate_proj:  62%|██████▏   | 22619/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.87.up_proj:  62%|██████▏   | 22620/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.87.down_proj:  62%|██████▏   | 22621/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.88.gate_proj:  62%|██████▏   | 22622/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.88.up_proj:  62%|██████▏   | 22623/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.88.down_proj:  62%|██████▏   | 22624/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.89.gate_proj:  62%|██████▏   | 22625/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.89.up_proj:  62%|██████▏   | 22626/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.89.down_proj:  62%|██████▏   | 22627/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.90.gate_proj:  62%|██████▏   | 22628/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.90.up_proj:  62%|██████▏   | 22629/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.90.down_proj:  62%|██████▏   | 22630/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.91.gate_proj:  62%|██████▏   | 22631/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.91.up_proj:  62%|██████▏   | 22632/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.91.down_proj:  62%|██████▏   | 22633/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.92.gate_proj:  62%|██████▏   | 22634/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.92.up_proj:  62%|██████▏   | 22635/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.92.down_proj:  62%|██████▏   | 22636/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.93.gate_proj:  62%|██████▏   | 22637/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.93.up_proj:  62%|██████▏   | 22638/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.93.down_proj:  62%|██████▏   | 22639/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.94.gate_proj:  62%|██████▏   | 22640/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.94.up_proj:  62%|██████▏   | 22641/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.94.down_proj:  62%|██████▏   | 22642/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.95.gate_proj:  62%|██████▏   | 22643/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.95.up_proj:  62%|██████▏   | 22644/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.95.down_proj:  62%|██████▏   | 22645/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.96.gate_proj:  62%|██████▏   | 22646/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.96.up_proj:  62%|██████▏   | 22647/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.96.down_proj:  62%|██████▏   | 22648/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.97.gate_proj:  62%|██████▏   | 22649/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.97.up_proj:  62%|██████▏   | 22650/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.97.down_proj:  62%|██████▏   | 22651/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.98.gate_proj:  62%|██████▏   | 22652/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.98.up_proj:  62%|██████▏   | 22653/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.98.down_proj:  62%|██████▏   | 22654/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.99.gate_proj:  62%|██████▏   | 22655/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.99.up_proj:  62%|██████▏   | 22656/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.99.down_proj:  62%|██████▏   | 22657/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.100.gate_proj:  62%|██████▏   | 22658/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.100.up_proj:  62%|██████▏   | 22659/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.100.down_proj:  62%|██████▏   | 22660/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.101.gate_proj:  62%|██████▏   | 22661/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.101.up_proj:  62%|██████▏   | 22662/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.101.down_proj:  62%|██████▏   | 22663/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.102.gate_proj:  62%|██████▏   | 22664/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.102.up_proj:  62%|██████▏   | 22665/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.102.down_proj:  62%|██████▏   | 22666/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.103.gate_proj:  62%|██████▏   | 22667/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.103.up_proj:  62%|██████▏   | 22668/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.103.down_proj:  62%|██████▏   | 22669/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.104.gate_proj:  62%|██████▏   | 22670/36566 [00:20<00:12, 1137.74it/s]
packing model.layers.57.mlp.experts.104.up_proj:  62%|██████▏   | 22671/36566 [00:20<00:12, 1137.74it/s]  
packing model.layers.57.mlp.experts.104.up_proj:  62%|██████▏   | 22672/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.104.down_proj:  62%|██████▏   | 22672/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.105.gate_proj:  62%|██████▏   | 22673/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.105.up_proj:  62%|██████▏   | 22674/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.105.down_proj:  62%|██████▏   | 22675/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.106.gate_proj:  62%|██████▏   | 22676/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.106.up_proj:  62%|██████▏   | 22677/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.106.down_proj:  62%|██████▏   | 22678/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.107.gate_proj:  62%|██████▏   | 22679/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.107.up_proj:  62%|██████▏   | 22680/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.107.down_proj:  62%|██████▏   | 22681/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.108.gate_proj:  62%|██████▏   | 22682/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.108.up_proj:  62%|██████▏   | 22683/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.108.down_proj:  62%|██████▏   | 22684/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.109.gate_proj:  62%|██████▏   | 22685/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.109.up_proj:  62%|██████▏   | 22686/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.109.down_proj:  62%|██████▏   | 22687/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.110.gate_proj:  62%|██████▏   | 22688/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.110.up_proj:  62%|██████▏   | 22689/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.110.down_proj:  62%|██████▏   | 22690/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.111.gate_proj:  62%|██████▏   | 22691/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.111.up_proj:  62%|██████▏   | 22692/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.111.down_proj:  62%|██████▏   | 22693/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.112.gate_proj:  62%|██████▏   | 22694/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.112.up_proj:  62%|██████▏   | 22695/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.112.down_proj:  62%|██████▏   | 22696/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.113.gate_proj:  62%|██████▏   | 22697/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.113.up_proj:  62%|██████▏   | 22698/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.113.down_proj:  62%|██████▏   | 22699/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.114.gate_proj:  62%|██████▏   | 22700/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.114.up_proj:  62%|██████▏   | 22701/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.114.down_proj:  62%|██████▏   | 22702/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.115.gate_proj:  62%|██████▏   | 22703/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.115.up_proj:  62%|██████▏   | 22704/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.115.down_proj:  62%|██████▏   | 22705/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.116.gate_proj:  62%|██████▏   | 22706/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.116.up_proj:  62%|██████▏   | 22707/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.116.down_proj:  62%|██████▏   | 22708/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.117.gate_proj:  62%|██████▏   | 22709/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.117.up_proj:  62%|██████▏   | 22710/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.117.down_proj:  62%|██████▏   | 22711/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.118.gate_proj:  62%|██████▏   | 22712/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.118.up_proj:  62%|██████▏   | 22713/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.118.down_proj:  62%|██████▏   | 22714/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.119.gate_proj:  62%|██████▏   | 22715/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.119.up_proj:  62%|██████▏   | 22716/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.119.down_proj:  62%|██████▏   | 22717/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.120.gate_proj:  62%|██████▏   | 22718/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.120.up_proj:  62%|██████▏   | 22719/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.120.down_proj:  62%|██████▏   | 22720/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.121.gate_proj:  62%|██████▏   | 22721/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.121.up_proj:  62%|██████▏   | 22722/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.121.down_proj:  62%|██████▏   | 22723/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.122.gate_proj:  62%|██████▏   | 22724/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.122.up_proj:  62%|██████▏   | 22725/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.122.down_proj:  62%|██████▏   | 22726/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.123.gate_proj:  62%|██████▏   | 22727/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.123.up_proj:  62%|██████▏   | 22728/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.123.down_proj:  62%|██████▏   | 22729/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.124.gate_proj:  62%|██████▏   | 22730/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.124.up_proj:  62%|██████▏   | 22731/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.124.down_proj:  62%|██████▏   | 22732/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.125.gate_proj:  62%|██████▏   | 22733/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.125.up_proj:  62%|██████▏   | 22734/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.125.down_proj:  62%|██████▏   | 22735/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.126.gate_proj:  62%|██████▏   | 22736/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.126.up_proj:  62%|██████▏   | 22737/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.126.down_proj:  62%|██████▏   | 22738/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.127.gate_proj:  62%|██████▏   | 22739/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.57.mlp.experts.127.up_proj:  62%|██████▏   | 22740/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.57.mlp.experts.127.down_proj:  62%|██████▏   | 22741/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.0.gate_proj:  62%|██████▏   | 22742/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.0.up_proj:  62%|██████▏   | 22743/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.0.down_proj:  62%|██████▏   | 22744/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.1.gate_proj:  62%|██████▏   | 22745/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.1.up_proj:  62%|██████▏   | 22746/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.1.down_proj:  62%|██████▏   | 22747/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.2.gate_proj:  62%|██████▏   | 22748/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.2.up_proj:  62%|██████▏   | 22749/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.2.down_proj:  62%|██████▏   | 22750/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.3.gate_proj:  62%|██████▏   | 22751/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.3.up_proj:  62%|██████▏   | 22752/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.3.down_proj:  62%|██████▏   | 22753/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.4.gate_proj:  62%|██████▏   | 22754/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.4.up_proj:  62%|██████▏   | 22755/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.4.down_proj:  62%|██████▏   | 22756/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.5.gate_proj:  62%|██████▏   | 22757/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.5.up_proj:  62%|██████▏   | 22758/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.5.down_proj:  62%|██████▏   | 22759/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.6.gate_proj:  62%|██████▏   | 22760/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.6.up_proj:  62%|██████▏   | 22761/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.6.down_proj:  62%|██████▏   | 22762/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.7.gate_proj:  62%|██████▏   | 22763/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.7.up_proj:  62%|██████▏   | 22764/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.7.down_proj:  62%|██████▏   | 22765/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.8.gate_proj:  62%|██████▏   | 22766/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.8.up_proj:  62%|██████▏   | 22767/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.8.down_proj:  62%|██████▏   | 22768/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.9.gate_proj:  62%|██████▏   | 22769/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.9.up_proj:  62%|██████▏   | 22770/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.9.down_proj:  62%|██████▏   | 22771/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.10.gate_proj:  62%|██████▏   | 22772/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.10.up_proj:  62%|██████▏   | 22773/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.10.down_proj:  62%|██████▏   | 22774/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.11.gate_proj:  62%|██████▏   | 22775/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.11.up_proj:  62%|██████▏   | 22776/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.11.down_proj:  62%|██████▏   | 22777/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.12.gate_proj:  62%|██████▏   | 22778/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.12.up_proj:  62%|██████▏   | 22779/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.12.down_proj:  62%|██████▏   | 22780/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.13.gate_proj:  62%|██████▏   | 22781/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.13.up_proj:  62%|██████▏   | 22782/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.13.down_proj:  62%|██████▏   | 22783/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.14.gate_proj:  62%|██████▏   | 22784/36566 [00:20<00:12, 1137.24it/s]
packing model.layers.58.mlp.experts.14.up_proj:  62%|██████▏   | 22785/36566 [00:20<00:12, 1137.24it/s]  
packing model.layers.58.mlp.experts.14.up_proj:  62%|██████▏   | 22786/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.14.down_proj:  62%|██████▏   | 22786/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.15.gate_proj:  62%|██████▏   | 22787/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.15.up_proj:  62%|██████▏   | 22788/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.15.down_proj:  62%|██████▏   | 22789/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.16.gate_proj:  62%|██████▏   | 22790/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.16.up_proj:  62%|██████▏   | 22791/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.16.down_proj:  62%|██████▏   | 22792/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.17.gate_proj:  62%|██████▏   | 22793/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.17.up_proj:  62%|██████▏   | 22794/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.17.down_proj:  62%|██████▏   | 22795/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.18.gate_proj:  62%|██████▏   | 22796/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.18.up_proj:  62%|██████▏   | 22797/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.18.down_proj:  62%|██████▏   | 22798/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.19.gate_proj:  62%|██████▏   | 22799/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.19.up_proj:  62%|██████▏   | 22800/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.19.down_proj:  62%|██████▏   | 22801/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.20.gate_proj:  62%|██████▏   | 22802/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.20.up_proj:  62%|██████▏   | 22803/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.20.down_proj:  62%|██████▏   | 22804/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.21.gate_proj:  62%|██████▏   | 22805/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.21.up_proj:  62%|██████▏   | 22806/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.21.down_proj:  62%|██████▏   | 22807/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.22.gate_proj:  62%|██████▏   | 22808/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.22.up_proj:  62%|██████▏   | 22809/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.22.down_proj:  62%|██████▏   | 22810/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.23.gate_proj:  62%|██████▏   | 22811/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.23.up_proj:  62%|██████▏   | 22812/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.23.down_proj:  62%|██████▏   | 22813/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.24.gate_proj:  62%|██████▏   | 22814/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.24.up_proj:  62%|██████▏   | 22815/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.24.down_proj:  62%|██████▏   | 22816/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.25.gate_proj:  62%|██████▏   | 22817/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.25.up_proj:  62%|██████▏   | 22818/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.25.down_proj:  62%|██████▏   | 22819/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.26.gate_proj:  62%|██████▏   | 22820/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.26.up_proj:  62%|██████▏   | 22821/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.26.down_proj:  62%|██████▏   | 22822/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.27.gate_proj:  62%|██████▏   | 22823/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.27.up_proj:  62%|██████▏   | 22824/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.27.down_proj:  62%|██████▏   | 22825/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.28.gate_proj:  62%|██████▏   | 22826/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.28.up_proj:  62%|██████▏   | 22827/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.28.down_proj:  62%|██████▏   | 22828/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.29.gate_proj:  62%|██████▏   | 22829/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.29.up_proj:  62%|██████▏   | 22830/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.29.down_proj:  62%|██████▏   | 22831/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.30.gate_proj:  62%|██████▏   | 22832/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.30.up_proj:  62%|██████▏   | 22833/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.30.down_proj:  62%|██████▏   | 22834/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.31.gate_proj:  62%|██████▏   | 22835/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.31.up_proj:  62%|██████▏   | 22836/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.31.down_proj:  62%|██████▏   | 22837/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.32.gate_proj:  62%|██████▏   | 22838/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.32.up_proj:  62%|██████▏   | 22839/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.32.down_proj:  62%|██████▏   | 22840/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.33.gate_proj:  62%|██████▏   | 22841/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.33.up_proj:  62%|██████▏   | 22842/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.33.down_proj:  62%|██████▏   | 22843/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.34.gate_proj:  62%|██████▏   | 22844/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.34.up_proj:  62%|██████▏   | 22845/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.34.down_proj:  62%|██████▏   | 22846/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.35.gate_proj:  62%|██████▏   | 22847/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.35.up_proj:  62%|██████▏   | 22848/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.35.down_proj:  62%|██████▏   | 22849/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.36.gate_proj:  62%|██████▏   | 22850/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.36.up_proj:  62%|██████▏   | 22851/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.36.down_proj:  62%|██████▏   | 22852/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.37.gate_proj:  62%|██████▏   | 22853/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.37.up_proj:  63%|██████▎   | 22854/36566 [00:20<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.37.down_proj:  63%|██████▎   | 22855/36566 [00:20<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.38.gate_proj:  63%|██████▎   | 22856/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.38.up_proj:  63%|██████▎   | 22857/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.38.down_proj:  63%|██████▎   | 22858/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.39.gate_proj:  63%|██████▎   | 22859/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.39.up_proj:  63%|██████▎   | 22860/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.39.down_proj:  63%|██████▎   | 22861/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.40.gate_proj:  63%|██████▎   | 22862/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.40.up_proj:  63%|██████▎   | 22863/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.40.down_proj:  63%|██████▎   | 22864/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.41.gate_proj:  63%|██████▎   | 22865/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.41.up_proj:  63%|██████▎   | 22866/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.41.down_proj:  63%|██████▎   | 22867/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.42.gate_proj:  63%|██████▎   | 22868/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.42.up_proj:  63%|██████▎   | 22869/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.42.down_proj:  63%|██████▎   | 22870/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.43.gate_proj:  63%|██████▎   | 22871/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.43.up_proj:  63%|██████▎   | 22872/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.43.down_proj:  63%|██████▎   | 22873/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.44.gate_proj:  63%|██████▎   | 22874/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.44.up_proj:  63%|██████▎   | 22875/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.44.down_proj:  63%|██████▎   | 22876/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.45.gate_proj:  63%|██████▎   | 22877/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.45.up_proj:  63%|██████▎   | 22878/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.45.down_proj:  63%|██████▎   | 22879/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.46.gate_proj:  63%|██████▎   | 22880/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.46.up_proj:  63%|██████▎   | 22881/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.46.down_proj:  63%|██████▎   | 22882/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.47.gate_proj:  63%|██████▎   | 22883/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.47.up_proj:  63%|██████▎   | 22884/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.47.down_proj:  63%|██████▎   | 22885/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.48.gate_proj:  63%|██████▎   | 22886/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.48.up_proj:  63%|██████▎   | 22887/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.48.down_proj:  63%|██████▎   | 22888/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.49.gate_proj:  63%|██████▎   | 22889/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.49.up_proj:  63%|██████▎   | 22890/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.49.down_proj:  63%|██████▎   | 22891/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.50.gate_proj:  63%|██████▎   | 22892/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.50.up_proj:  63%|██████▎   | 22893/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.50.down_proj:  63%|██████▎   | 22894/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.51.gate_proj:  63%|██████▎   | 22895/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.51.up_proj:  63%|██████▎   | 22896/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.51.down_proj:  63%|██████▎   | 22897/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.52.gate_proj:  63%|██████▎   | 22898/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.52.up_proj:  63%|██████▎   | 22899/36566 [00:21<00:12, 1137.04it/s]  
packing model.layers.58.mlp.experts.52.down_proj:  63%|██████▎   | 22900/36566 [00:21<00:12, 1137.04it/s]
packing model.layers.58.mlp.experts.52.down_proj:  63%|██████▎   | 22901/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.53.gate_proj:  63%|██████▎   | 22901/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.53.up_proj:  63%|██████▎   | 22902/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.53.down_proj:  63%|██████▎   | 22903/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.54.gate_proj:  63%|██████▎   | 22904/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.54.up_proj:  63%|██████▎   | 22905/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.54.down_proj:  63%|██████▎   | 22906/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.55.gate_proj:  63%|██████▎   | 22907/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.55.up_proj:  63%|██████▎   | 22908/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.55.down_proj:  63%|██████▎   | 22909/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.56.gate_proj:  63%|██████▎   | 22910/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.56.up_proj:  63%|██████▎   | 22911/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.56.down_proj:  63%|██████▎   | 22912/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.57.gate_proj:  63%|██████▎   | 22913/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.57.up_proj:  63%|██████▎   | 22914/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.57.down_proj:  63%|██████▎   | 22915/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.58.gate_proj:  63%|██████▎   | 22916/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.58.up_proj:  63%|██████▎   | 22917/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.58.down_proj:  63%|██████▎   | 22918/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.59.gate_proj:  63%|██████▎   | 22919/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.59.up_proj:  63%|██████▎   | 22920/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.59.down_proj:  63%|██████▎   | 22921/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.60.gate_proj:  63%|██████▎   | 22922/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.60.up_proj:  63%|██████▎   | 22923/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.60.down_proj:  63%|██████▎   | 22924/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.61.gate_proj:  63%|██████▎   | 22925/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.61.up_proj:  63%|██████▎   | 22926/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.61.down_proj:  63%|██████▎   | 22927/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.62.gate_proj:  63%|██████▎   | 22928/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.62.up_proj:  63%|██████▎   | 22929/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.62.down_proj:  63%|██████▎   | 22930/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.63.gate_proj:  63%|██████▎   | 22931/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.63.up_proj:  63%|██████▎   | 22932/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.63.down_proj:  63%|██████▎   | 22933/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.64.gate_proj:  63%|██████▎   | 22934/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.64.up_proj:  63%|██████▎   | 22935/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.64.down_proj:  63%|██████▎   | 22936/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.65.gate_proj:  63%|██████▎   | 22937/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.65.up_proj:  63%|██████▎   | 22938/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.65.down_proj:  63%|██████▎   | 22939/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.66.gate_proj:  63%|██████▎   | 22940/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.66.up_proj:  63%|██████▎   | 22941/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.66.down_proj:  63%|██████▎   | 22942/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.67.gate_proj:  63%|██████▎   | 22943/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.67.up_proj:  63%|██████▎   | 22944/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.67.down_proj:  63%|██████▎   | 22945/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.68.gate_proj:  63%|██████▎   | 22946/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.68.up_proj:  63%|██████▎   | 22947/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.68.down_proj:  63%|██████▎   | 22948/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.69.gate_proj:  63%|██████▎   | 22949/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.69.up_proj:  63%|██████▎   | 22950/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.69.down_proj:  63%|██████▎   | 22951/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.70.gate_proj:  63%|██████▎   | 22952/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.70.up_proj:  63%|██████▎   | 22953/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.70.down_proj:  63%|██████▎   | 22954/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.71.gate_proj:  63%|██████▎   | 22955/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.71.up_proj:  63%|██████▎   | 22956/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.71.down_proj:  63%|██████▎   | 22957/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.72.gate_proj:  63%|██████▎   | 22958/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.72.up_proj:  63%|██████▎   | 22959/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.72.down_proj:  63%|██████▎   | 22960/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.73.gate_proj:  63%|██████▎   | 22961/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.73.up_proj:  63%|██████▎   | 22962/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.73.down_proj:  63%|██████▎   | 22963/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.74.gate_proj:  63%|██████▎   | 22964/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.74.up_proj:  63%|██████▎   | 22965/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.74.down_proj:  63%|██████▎   | 22966/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.75.gate_proj:  63%|██████▎   | 22967/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.75.up_proj:  63%|██████▎   | 22968/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.75.down_proj:  63%|██████▎   | 22969/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.76.gate_proj:  63%|██████▎   | 22970/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.76.up_proj:  63%|██████▎   | 22971/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.76.down_proj:  63%|██████▎   | 22972/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.77.gate_proj:  63%|██████▎   | 22973/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.77.up_proj:  63%|██████▎   | 22974/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.77.down_proj:  63%|██████▎   | 22975/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.78.gate_proj:  63%|██████▎   | 22976/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.78.up_proj:  63%|██████▎   | 22977/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.78.down_proj:  63%|██████▎   | 22978/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.79.gate_proj:  63%|██████▎   | 22979/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.79.up_proj:  63%|██████▎   | 22980/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.79.down_proj:  63%|██████▎   | 22981/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.80.gate_proj:  63%|██████▎   | 22982/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.80.up_proj:  63%|██████▎   | 22983/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.80.down_proj:  63%|██████▎   | 22984/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.81.gate_proj:  63%|██████▎   | 22985/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.81.up_proj:  63%|██████▎   | 22986/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.81.down_proj:  63%|██████▎   | 22987/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.82.gate_proj:  63%|██████▎   | 22988/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.82.up_proj:  63%|██████▎   | 22989/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.82.down_proj:  63%|██████▎   | 22990/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.83.gate_proj:  63%|██████▎   | 22991/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.83.up_proj:  63%|██████▎   | 22992/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.83.down_proj:  63%|██████▎   | 22993/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.84.gate_proj:  63%|██████▎   | 22994/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.84.up_proj:  63%|██████▎   | 22995/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.84.down_proj:  63%|██████▎   | 22996/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.85.gate_proj:  63%|██████▎   | 22997/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.85.up_proj:  63%|██████▎   | 22998/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.85.down_proj:  63%|██████▎   | 22999/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.86.gate_proj:  63%|██████▎   | 23000/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.86.up_proj:  63%|██████▎   | 23001/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.86.down_proj:  63%|██████▎   | 23002/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.87.gate_proj:  63%|██████▎   | 23003/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.87.up_proj:  63%|██████▎   | 23004/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.87.down_proj:  63%|██████▎   | 23005/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.88.gate_proj:  63%|██████▎   | 23006/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.88.up_proj:  63%|██████▎   | 23007/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.88.down_proj:  63%|██████▎   | 23008/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.89.gate_proj:  63%|██████▎   | 23009/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.89.up_proj:  63%|██████▎   | 23010/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.89.down_proj:  63%|██████▎   | 23011/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.90.gate_proj:  63%|██████▎   | 23012/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.90.up_proj:  63%|██████▎   | 23013/36566 [00:21<00:11, 1139.18it/s]  
packing model.layers.58.mlp.experts.90.down_proj:  63%|██████▎   | 23014/36566 [00:21<00:11, 1139.18it/s]
packing model.layers.58.mlp.experts.90.down_proj:  63%|██████▎   | 23015/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.91.gate_proj:  63%|██████▎   | 23015/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.91.up_proj:  63%|██████▎   | 23016/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.91.down_proj:  63%|██████▎   | 23017/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.92.gate_proj:  63%|██████▎   | 23018/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.92.up_proj:  63%|██████▎   | 23019/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.92.down_proj:  63%|██████▎   | 23020/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.93.gate_proj:  63%|██████▎   | 23021/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.93.up_proj:  63%|██████▎   | 23022/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.93.down_proj:  63%|██████▎   | 23023/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.94.gate_proj:  63%|██████▎   | 23024/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.94.up_proj:  63%|██████▎   | 23025/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.94.down_proj:  63%|██████▎   | 23026/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.95.gate_proj:  63%|██████▎   | 23027/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.95.up_proj:  63%|██████▎   | 23028/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.95.down_proj:  63%|██████▎   | 23029/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.96.gate_proj:  63%|██████▎   | 23030/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.96.up_proj:  63%|██████▎   | 23031/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.96.down_proj:  63%|██████▎   | 23032/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.97.gate_proj:  63%|██████▎   | 23033/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.97.up_proj:  63%|██████▎   | 23034/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.97.down_proj:  63%|██████▎   | 23035/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.98.gate_proj:  63%|██████▎   | 23036/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.98.up_proj:  63%|██████▎   | 23037/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.98.down_proj:  63%|██████▎   | 23038/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.99.gate_proj:  63%|██████▎   | 23039/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.99.up_proj:  63%|██████▎   | 23040/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.99.down_proj:  63%|██████▎   | 23041/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.100.gate_proj:  63%|██████▎   | 23042/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.100.up_proj:  63%|██████▎   | 23043/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.100.down_proj:  63%|██████▎   | 23044/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.101.gate_proj:  63%|██████▎   | 23045/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.101.up_proj:  63%|██████▎   | 23046/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.101.down_proj:  63%|██████▎   | 23047/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.102.gate_proj:  63%|██████▎   | 23048/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.102.up_proj:  63%|██████▎   | 23049/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.102.down_proj:  63%|██████▎   | 23050/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.103.gate_proj:  63%|██████▎   | 23051/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.103.up_proj:  63%|██████▎   | 23052/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.103.down_proj:  63%|██████▎   | 23053/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.104.gate_proj:  63%|██████▎   | 23054/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.104.up_proj:  63%|██████▎   | 23055/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.104.down_proj:  63%|██████▎   | 23056/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.105.gate_proj:  63%|██████▎   | 23057/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.105.up_proj:  63%|██████▎   | 23058/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.105.down_proj:  63%|██████▎   | 23059/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.106.gate_proj:  63%|██████▎   | 23060/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.106.up_proj:  63%|██████▎   | 23061/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.106.down_proj:  63%|██████▎   | 23062/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.107.gate_proj:  63%|██████▎   | 23063/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.107.up_proj:  63%|██████▎   | 23064/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.107.down_proj:  63%|██████▎   | 23065/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.108.gate_proj:  63%|██████▎   | 23066/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.108.up_proj:  63%|██████▎   | 23067/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.108.down_proj:  63%|██████▎   | 23068/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.109.gate_proj:  63%|██████▎   | 23069/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.109.up_proj:  63%|██████▎   | 23070/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.109.down_proj:  63%|██████▎   | 23071/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.110.gate_proj:  63%|██████▎   | 23072/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.110.up_proj:  63%|██████▎   | 23073/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.110.down_proj:  63%|██████▎   | 23074/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.111.gate_proj:  63%|██████▎   | 23075/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.111.up_proj:  63%|██████▎   | 23076/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.111.down_proj:  63%|██████▎   | 23077/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.112.gate_proj:  63%|██████▎   | 23078/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.112.up_proj:  63%|██████▎   | 23079/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.112.down_proj:  63%|██████▎   | 23080/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.113.gate_proj:  63%|██████▎   | 23081/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.113.up_proj:  63%|██████▎   | 23082/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.113.down_proj:  63%|██████▎   | 23083/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.114.gate_proj:  63%|██████▎   | 23084/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.114.up_proj:  63%|██████▎   | 23085/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.114.down_proj:  63%|██████▎   | 23086/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.115.gate_proj:  63%|██████▎   | 23087/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.115.up_proj:  63%|██████▎   | 23088/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.115.down_proj:  63%|██████▎   | 23089/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.116.gate_proj:  63%|██████▎   | 23090/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.116.up_proj:  63%|██████▎   | 23091/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.116.down_proj:  63%|██████▎   | 23092/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.117.gate_proj:  63%|██████▎   | 23093/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.117.up_proj:  63%|██████▎   | 23094/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.117.down_proj:  63%|██████▎   | 23095/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.118.gate_proj:  63%|██████▎   | 23096/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.118.up_proj:  63%|██████▎   | 23097/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.118.down_proj:  63%|██████▎   | 23098/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.119.gate_proj:  63%|██████▎   | 23099/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.119.up_proj:  63%|██████▎   | 23100/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.119.down_proj:  63%|██████▎   | 23101/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.120.gate_proj:  63%|██████▎   | 23102/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.120.up_proj:  63%|██████▎   | 23103/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.120.down_proj:  63%|██████▎   | 23104/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.121.gate_proj:  63%|██████▎   | 23105/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.121.up_proj:  63%|██████▎   | 23106/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.121.down_proj:  63%|██████▎   | 23107/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.122.gate_proj:  63%|██████▎   | 23108/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.122.up_proj:  63%|██████▎   | 23109/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.122.down_proj:  63%|██████▎   | 23110/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.123.gate_proj:  63%|██████▎   | 23111/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.123.up_proj:  63%|██████▎   | 23112/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.123.down_proj:  63%|██████▎   | 23113/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.124.gate_proj:  63%|██████▎   | 23114/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.124.up_proj:  63%|██████▎   | 23115/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.124.down_proj:  63%|██████▎   | 23116/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.125.gate_proj:  63%|██████▎   | 23117/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.125.up_proj:  63%|██████▎   | 23118/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.125.down_proj:  63%|██████▎   | 23119/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.126.gate_proj:  63%|██████▎   | 23120/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.126.up_proj:  63%|██████▎   | 23121/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.126.down_proj:  63%|██████▎   | 23122/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.127.gate_proj:  63%|██████▎   | 23123/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.58.mlp.experts.127.up_proj:  63%|██████▎   | 23124/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.58.mlp.experts.127.down_proj:  63%|██████▎   | 23125/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.59.mlp.experts.0.gate_proj:  63%|██████▎   | 23126/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.59.mlp.experts.0.up_proj:  63%|██████▎   | 23127/36566 [00:21<00:11, 1137.41it/s]  
packing model.layers.59.mlp.experts.0.down_proj:  63%|██████▎   | 23128/36566 [00:21<00:11, 1137.41it/s]
packing model.layers.59.mlp.experts.0.down_proj:  63%|██████▎   | 23129/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.1.gate_proj:  63%|██████▎   | 23129/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.1.up_proj:  63%|██████▎   | 23130/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.1.down_proj:  63%|██████▎   | 23131/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.2.gate_proj:  63%|██████▎   | 23132/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.2.up_proj:  63%|██████▎   | 23133/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.2.down_proj:  63%|██████▎   | 23134/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.3.gate_proj:  63%|██████▎   | 23135/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.3.up_proj:  63%|██████▎   | 23136/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.3.down_proj:  63%|██████▎   | 23137/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.4.gate_proj:  63%|██████▎   | 23138/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.4.up_proj:  63%|██████▎   | 23139/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.4.down_proj:  63%|██████▎   | 23140/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.5.gate_proj:  63%|██████▎   | 23141/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.5.up_proj:  63%|██████▎   | 23142/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.5.down_proj:  63%|██████▎   | 23143/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.6.gate_proj:  63%|██████▎   | 23144/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.6.up_proj:  63%|██████▎   | 23145/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.6.down_proj:  63%|██████▎   | 23146/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.7.gate_proj:  63%|██████▎   | 23147/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.7.up_proj:  63%|██████▎   | 23148/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.7.down_proj:  63%|██████▎   | 23149/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.8.gate_proj:  63%|██████▎   | 23150/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.8.up_proj:  63%|██████▎   | 23151/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.8.down_proj:  63%|██████▎   | 23152/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.9.gate_proj:  63%|██████▎   | 23153/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.9.up_proj:  63%|██████▎   | 23154/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.9.down_proj:  63%|██████▎   | 23155/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.10.gate_proj:  63%|██████▎   | 23156/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.10.up_proj:  63%|██████▎   | 23157/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.10.down_proj:  63%|██████▎   | 23158/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.11.gate_proj:  63%|██████▎   | 23159/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.11.up_proj:  63%|██████▎   | 23160/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.11.down_proj:  63%|██████▎   | 23161/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.12.gate_proj:  63%|██████▎   | 23162/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.12.up_proj:  63%|██████▎   | 23163/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.12.down_proj:  63%|██████▎   | 23164/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.13.gate_proj:  63%|██████▎   | 23165/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.13.up_proj:  63%|██████▎   | 23166/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.13.down_proj:  63%|██████▎   | 23167/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.14.gate_proj:  63%|██████▎   | 23168/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.14.up_proj:  63%|██████▎   | 23169/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.14.down_proj:  63%|██████▎   | 23170/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.15.gate_proj:  63%|██████▎   | 23171/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.15.up_proj:  63%|██████▎   | 23172/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.15.down_proj:  63%|██████▎   | 23173/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.16.gate_proj:  63%|██████▎   | 23174/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.16.up_proj:  63%|██████▎   | 23175/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.16.down_proj:  63%|██████▎   | 23176/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.17.gate_proj:  63%|██████▎   | 23177/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.17.up_proj:  63%|██████▎   | 23178/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.17.down_proj:  63%|██████▎   | 23179/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.18.gate_proj:  63%|██████▎   | 23180/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.18.up_proj:  63%|██████▎   | 23181/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.18.down_proj:  63%|██████▎   | 23182/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.19.gate_proj:  63%|██████▎   | 23183/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.19.up_proj:  63%|██████▎   | 23184/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.19.down_proj:  63%|██████▎   | 23185/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.20.gate_proj:  63%|██████▎   | 23186/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.20.up_proj:  63%|██████▎   | 23187/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.20.down_proj:  63%|██████▎   | 23188/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.21.gate_proj:  63%|██████▎   | 23189/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.21.up_proj:  63%|██████▎   | 23190/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.21.down_proj:  63%|██████▎   | 23191/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.22.gate_proj:  63%|██████▎   | 23192/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.22.up_proj:  63%|██████▎   | 23193/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.22.down_proj:  63%|██████▎   | 23194/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.23.gate_proj:  63%|██████▎   | 23195/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.23.up_proj:  63%|██████▎   | 23196/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.23.down_proj:  63%|██████▎   | 23197/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.24.gate_proj:  63%|██████▎   | 23198/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.24.up_proj:  63%|██████▎   | 23199/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.24.down_proj:  63%|██████▎   | 23200/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.25.gate_proj:  63%|██████▎   | 23201/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.25.up_proj:  63%|██████▎   | 23202/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.25.down_proj:  63%|██████▎   | 23203/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.26.gate_proj:  63%|██████▎   | 23204/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.26.up_proj:  63%|██████▎   | 23205/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.26.down_proj:  63%|██████▎   | 23206/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.27.gate_proj:  63%|██████▎   | 23207/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.27.up_proj:  63%|██████▎   | 23208/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.27.down_proj:  63%|██████▎   | 23209/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.28.gate_proj:  63%|██████▎   | 23210/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.28.up_proj:  63%|██████▎   | 23211/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.28.down_proj:  63%|██████▎   | 23212/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.29.gate_proj:  63%|██████▎   | 23213/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.29.up_proj:  63%|██████▎   | 23214/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.29.down_proj:  63%|██████▎   | 23215/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.30.gate_proj:  63%|██████▎   | 23216/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.30.up_proj:  63%|██████▎   | 23217/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.30.down_proj:  63%|██████▎   | 23218/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.31.gate_proj:  63%|██████▎   | 23219/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.31.up_proj:  64%|██████▎   | 23220/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.31.down_proj:  64%|██████▎   | 23221/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.32.gate_proj:  64%|██████▎   | 23222/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.32.up_proj:  64%|██████▎   | 23223/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.32.down_proj:  64%|██████▎   | 23224/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.33.gate_proj:  64%|██████▎   | 23225/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.33.up_proj:  64%|██████▎   | 23226/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.33.down_proj:  64%|██████▎   | 23227/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.34.gate_proj:  64%|██████▎   | 23228/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.34.up_proj:  64%|██████▎   | 23229/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.34.down_proj:  64%|██████▎   | 23230/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.35.gate_proj:  64%|██████▎   | 23231/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.35.up_proj:  64%|██████▎   | 23232/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.35.down_proj:  64%|██████▎   | 23233/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.36.gate_proj:  64%|██████▎   | 23234/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.36.up_proj:  64%|██████▎   | 23235/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.36.down_proj:  64%|██████▎   | 23236/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.37.gate_proj:  64%|██████▎   | 23237/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.37.up_proj:  64%|██████▎   | 23238/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.37.down_proj:  64%|██████▎   | 23239/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.38.gate_proj:  64%|██████▎   | 23240/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.38.up_proj:  64%|██████▎   | 23241/36566 [00:21<00:11, 1136.31it/s]  
packing model.layers.59.mlp.experts.38.down_proj:  64%|██████▎   | 23242/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.39.gate_proj:  64%|██████▎   | 23243/36566 [00:21<00:11, 1136.31it/s]
packing model.layers.59.mlp.experts.39.gate_proj:  64%|██████▎   | 23244/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.39.up_proj:  64%|██████▎   | 23244/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.39.down_proj:  64%|██████▎   | 23245/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.40.gate_proj:  64%|██████▎   | 23246/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.40.up_proj:  64%|██████▎   | 23247/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.40.down_proj:  64%|██████▎   | 23248/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.41.gate_proj:  64%|██████▎   | 23249/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.41.up_proj:  64%|██████▎   | 23250/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.41.down_proj:  64%|██████▎   | 23251/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.42.gate_proj:  64%|██████▎   | 23252/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.42.up_proj:  64%|██████▎   | 23253/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.42.down_proj:  64%|██████▎   | 23254/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.43.gate_proj:  64%|██████▎   | 23255/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.43.up_proj:  64%|██████▎   | 23256/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.43.down_proj:  64%|██████▎   | 23257/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.44.gate_proj:  64%|██████▎   | 23258/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.44.up_proj:  64%|██████▎   | 23259/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.44.down_proj:  64%|██████▎   | 23260/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.45.gate_proj:  64%|██████▎   | 23261/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.45.up_proj:  64%|██████▎   | 23262/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.45.down_proj:  64%|██████▎   | 23263/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.46.gate_proj:  64%|██████▎   | 23264/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.46.up_proj:  64%|██████▎   | 23265/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.46.down_proj:  64%|██████▎   | 23266/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.47.gate_proj:  64%|██████▎   | 23267/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.47.up_proj:  64%|██████▎   | 23268/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.47.down_proj:  64%|██████▎   | 23269/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.48.gate_proj:  64%|██████▎   | 23270/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.48.up_proj:  64%|██████▎   | 23271/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.48.down_proj:  64%|██████▎   | 23272/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.49.gate_proj:  64%|██████▎   | 23273/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.49.up_proj:  64%|██████▎   | 23274/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.49.down_proj:  64%|██████▎   | 23275/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.50.gate_proj:  64%|██████▎   | 23276/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.50.up_proj:  64%|██████▎   | 23277/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.50.down_proj:  64%|██████▎   | 23278/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.51.gate_proj:  64%|██████▎   | 23279/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.51.up_proj:  64%|██████▎   | 23280/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.51.down_proj:  64%|██████▎   | 23281/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.52.gate_proj:  64%|██████▎   | 23282/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.52.up_proj:  64%|██████▎   | 23283/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.52.down_proj:  64%|██████▎   | 23284/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.53.gate_proj:  64%|██████▎   | 23285/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.53.up_proj:  64%|██████▎   | 23286/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.53.down_proj:  64%|██████▎   | 23287/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.54.gate_proj:  64%|██████▎   | 23288/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.54.up_proj:  64%|██████▎   | 23289/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.54.down_proj:  64%|██████▎   | 23290/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.55.gate_proj:  64%|██████▎   | 23291/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.55.up_proj:  64%|██████▎   | 23292/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.55.down_proj:  64%|██████▎   | 23293/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.56.gate_proj:  64%|██████▎   | 23294/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.56.up_proj:  64%|██████▎   | 23295/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.56.down_proj:  64%|██████▎   | 23296/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.57.gate_proj:  64%|██████▎   | 23297/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.57.up_proj:  64%|██████▎   | 23298/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.57.down_proj:  64%|██████▎   | 23299/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.58.gate_proj:  64%|██████▎   | 23300/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.58.up_proj:  64%|██████▎   | 23301/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.58.down_proj:  64%|██████▎   | 23302/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.59.gate_proj:  64%|██████▎   | 23303/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.59.up_proj:  64%|██████▎   | 23304/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.59.down_proj:  64%|██████▎   | 23305/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.60.gate_proj:  64%|██████▎   | 23306/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.60.up_proj:  64%|██████▎   | 23307/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.60.down_proj:  64%|██████▎   | 23308/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.61.gate_proj:  64%|██████▎   | 23309/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.61.up_proj:  64%|██████▎   | 23310/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.61.down_proj:  64%|██████▍   | 23311/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.62.gate_proj:  64%|██████▍   | 23312/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.62.up_proj:  64%|██████▍   | 23313/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.62.down_proj:  64%|██████▍   | 23314/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.63.gate_proj:  64%|██████▍   | 23315/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.63.up_proj:  64%|██████▍   | 23316/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.63.down_proj:  64%|██████▍   | 23317/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.64.gate_proj:  64%|██████▍   | 23318/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.64.up_proj:  64%|██████▍   | 23319/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.64.down_proj:  64%|██████▍   | 23320/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.65.gate_proj:  64%|██████▍   | 23321/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.65.up_proj:  64%|██████▍   | 23322/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.65.down_proj:  64%|██████▍   | 23323/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.66.gate_proj:  64%|██████▍   | 23324/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.66.up_proj:  64%|██████▍   | 23325/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.66.down_proj:  64%|██████▍   | 23326/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.67.gate_proj:  64%|██████▍   | 23327/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.67.up_proj:  64%|██████▍   | 23328/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.67.down_proj:  64%|██████▍   | 23329/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.68.gate_proj:  64%|██████▍   | 23330/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.68.up_proj:  64%|██████▍   | 23331/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.68.down_proj:  64%|██████▍   | 23332/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.69.gate_proj:  64%|██████▍   | 23333/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.69.up_proj:  64%|██████▍   | 23334/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.69.down_proj:  64%|██████▍   | 23335/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.70.gate_proj:  64%|██████▍   | 23336/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.70.up_proj:  64%|██████▍   | 23337/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.70.down_proj:  64%|██████▍   | 23338/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.71.gate_proj:  64%|██████▍   | 23339/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.71.up_proj:  64%|██████▍   | 23340/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.71.down_proj:  64%|██████▍   | 23341/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.72.gate_proj:  64%|██████▍   | 23342/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.72.up_proj:  64%|██████▍   | 23343/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.72.down_proj:  64%|██████▍   | 23344/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.73.gate_proj:  64%|██████▍   | 23345/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.73.up_proj:  64%|██████▍   | 23346/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.73.down_proj:  64%|██████▍   | 23347/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.74.gate_proj:  64%|██████▍   | 23348/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.74.up_proj:  64%|██████▍   | 23349/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.74.down_proj:  64%|██████▍   | 23350/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.75.gate_proj:  64%|██████▍   | 23351/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.75.up_proj:  64%|██████▍   | 23352/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.75.down_proj:  64%|██████▍   | 23353/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.76.gate_proj:  64%|██████▍   | 23354/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.76.up_proj:  64%|██████▍   | 23355/36566 [00:21<00:11, 1137.62it/s]  
packing model.layers.59.mlp.experts.76.down_proj:  64%|██████▍   | 23356/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.77.gate_proj:  64%|██████▍   | 23357/36566 [00:21<00:11, 1137.62it/s]
packing model.layers.59.mlp.experts.77.gate_proj:  64%|██████▍   | 23358/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.77.up_proj:  64%|██████▍   | 23358/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.77.down_proj:  64%|██████▍   | 23359/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.78.gate_proj:  64%|██████▍   | 23360/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.78.up_proj:  64%|██████▍   | 23361/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.78.down_proj:  64%|██████▍   | 23362/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.79.gate_proj:  64%|██████▍   | 23363/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.79.up_proj:  64%|██████▍   | 23364/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.79.down_proj:  64%|██████▍   | 23365/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.80.gate_proj:  64%|██████▍   | 23366/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.80.up_proj:  64%|██████▍   | 23367/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.80.down_proj:  64%|██████▍   | 23368/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.81.gate_proj:  64%|██████▍   | 23369/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.81.up_proj:  64%|██████▍   | 23370/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.81.down_proj:  64%|██████▍   | 23371/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.82.gate_proj:  64%|██████▍   | 23372/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.82.up_proj:  64%|██████▍   | 23373/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.82.down_proj:  64%|██████▍   | 23374/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.83.gate_proj:  64%|██████▍   | 23375/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.83.up_proj:  64%|██████▍   | 23376/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.83.down_proj:  64%|██████▍   | 23377/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.84.gate_proj:  64%|██████▍   | 23378/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.84.up_proj:  64%|██████▍   | 23379/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.84.down_proj:  64%|██████▍   | 23380/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.85.gate_proj:  64%|██████▍   | 23381/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.85.up_proj:  64%|██████▍   | 23382/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.85.down_proj:  64%|██████▍   | 23383/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.86.gate_proj:  64%|██████▍   | 23384/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.86.up_proj:  64%|██████▍   | 23385/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.86.down_proj:  64%|██████▍   | 23386/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.87.gate_proj:  64%|██████▍   | 23387/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.87.up_proj:  64%|██████▍   | 23388/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.87.down_proj:  64%|██████▍   | 23389/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.88.gate_proj:  64%|██████▍   | 23390/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.88.up_proj:  64%|██████▍   | 23391/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.88.down_proj:  64%|██████▍   | 23392/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.89.gate_proj:  64%|██████▍   | 23393/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.89.up_proj:  64%|██████▍   | 23394/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.89.down_proj:  64%|██████▍   | 23395/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.90.gate_proj:  64%|██████▍   | 23396/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.90.up_proj:  64%|██████▍   | 23397/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.90.down_proj:  64%|██████▍   | 23398/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.91.gate_proj:  64%|██████▍   | 23399/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.91.up_proj:  64%|██████▍   | 23400/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.91.down_proj:  64%|██████▍   | 23401/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.92.gate_proj:  64%|██████▍   | 23402/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.92.up_proj:  64%|██████▍   | 23403/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.92.down_proj:  64%|██████▍   | 23404/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.93.gate_proj:  64%|██████▍   | 23405/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.93.up_proj:  64%|██████▍   | 23406/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.93.down_proj:  64%|██████▍   | 23407/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.94.gate_proj:  64%|██████▍   | 23408/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.94.up_proj:  64%|██████▍   | 23409/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.94.down_proj:  64%|██████▍   | 23410/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.95.gate_proj:  64%|██████▍   | 23411/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.95.up_proj:  64%|██████▍   | 23412/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.95.down_proj:  64%|██████▍   | 23413/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.96.gate_proj:  64%|██████▍   | 23414/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.96.up_proj:  64%|██████▍   | 23415/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.96.down_proj:  64%|██████▍   | 23416/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.97.gate_proj:  64%|██████▍   | 23417/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.97.up_proj:  64%|██████▍   | 23418/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.97.down_proj:  64%|██████▍   | 23419/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.98.gate_proj:  64%|██████▍   | 23420/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.98.up_proj:  64%|██████▍   | 23421/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.98.down_proj:  64%|██████▍   | 23422/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.99.gate_proj:  64%|██████▍   | 23423/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.99.up_proj:  64%|██████▍   | 23424/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.99.down_proj:  64%|██████▍   | 23425/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.100.gate_proj:  64%|██████▍   | 23426/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.100.up_proj:  64%|██████▍   | 23427/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.100.down_proj:  64%|██████▍   | 23428/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.101.gate_proj:  64%|██████▍   | 23429/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.101.up_proj:  64%|██████▍   | 23430/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.101.down_proj:  64%|██████▍   | 23431/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.102.gate_proj:  64%|██████▍   | 23432/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.102.up_proj:  64%|██████▍   | 23433/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.102.down_proj:  64%|██████▍   | 23434/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.103.gate_proj:  64%|██████▍   | 23435/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.103.up_proj:  64%|██████▍   | 23436/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.103.down_proj:  64%|██████▍   | 23437/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.104.gate_proj:  64%|██████▍   | 23438/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.104.up_proj:  64%|██████▍   | 23439/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.104.down_proj:  64%|██████▍   | 23440/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.105.gate_proj:  64%|██████▍   | 23441/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.105.up_proj:  64%|██████▍   | 23442/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.105.down_proj:  64%|██████▍   | 23443/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.106.gate_proj:  64%|██████▍   | 23444/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.106.up_proj:  64%|██████▍   | 23445/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.106.down_proj:  64%|██████▍   | 23446/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.107.gate_proj:  64%|██████▍   | 23447/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.107.up_proj:  64%|██████▍   | 23448/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.107.down_proj:  64%|██████▍   | 23449/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.108.gate_proj:  64%|██████▍   | 23450/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.108.up_proj:  64%|██████▍   | 23451/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.108.down_proj:  64%|██████▍   | 23452/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.109.gate_proj:  64%|██████▍   | 23453/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.109.up_proj:  64%|██████▍   | 23454/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.109.down_proj:  64%|██████▍   | 23455/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.110.gate_proj:  64%|██████▍   | 23456/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.110.up_proj:  64%|██████▍   | 23457/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.110.down_proj:  64%|██████▍   | 23458/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.111.gate_proj:  64%|██████▍   | 23459/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.111.up_proj:  64%|██████▍   | 23460/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.111.down_proj:  64%|██████▍   | 23461/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.112.gate_proj:  64%|██████▍   | 23462/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.112.up_proj:  64%|██████▍   | 23463/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.112.down_proj:  64%|██████▍   | 23464/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.113.gate_proj:  64%|██████▍   | 23465/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.113.up_proj:  64%|██████▍   | 23466/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.113.down_proj:  64%|██████▍   | 23467/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.114.gate_proj:  64%|██████▍   | 23468/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.114.up_proj:  64%|██████▍   | 23469/36566 [00:21<00:11, 1132.88it/s]  
packing model.layers.59.mlp.experts.114.down_proj:  64%|██████▍   | 23470/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.115.gate_proj:  64%|██████▍   | 23471/36566 [00:21<00:11, 1132.88it/s]
packing model.layers.59.mlp.experts.115.gate_proj:  64%|██████▍   | 23472/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.115.up_proj:  64%|██████▍   | 23472/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.115.down_proj:  64%|██████▍   | 23473/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.116.gate_proj:  64%|██████▍   | 23474/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.116.up_proj:  64%|██████▍   | 23475/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.116.down_proj:  64%|██████▍   | 23476/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.117.gate_proj:  64%|██████▍   | 23477/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.117.up_proj:  64%|██████▍   | 23478/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.117.down_proj:  64%|██████▍   | 23479/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.118.gate_proj:  64%|██████▍   | 23480/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.118.up_proj:  64%|██████▍   | 23481/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.118.down_proj:  64%|██████▍   | 23482/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.119.gate_proj:  64%|██████▍   | 23483/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.119.up_proj:  64%|██████▍   | 23484/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.119.down_proj:  64%|██████▍   | 23485/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.120.gate_proj:  64%|██████▍   | 23486/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.120.up_proj:  64%|██████▍   | 23487/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.120.down_proj:  64%|██████▍   | 23488/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.121.gate_proj:  64%|██████▍   | 23489/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.121.up_proj:  64%|██████▍   | 23490/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.121.down_proj:  64%|██████▍   | 23491/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.122.gate_proj:  64%|██████▍   | 23492/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.122.up_proj:  64%|██████▍   | 23493/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.122.down_proj:  64%|██████▍   | 23494/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.123.gate_proj:  64%|██████▍   | 23495/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.123.up_proj:  64%|██████▍   | 23496/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.123.down_proj:  64%|██████▍   | 23497/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.124.gate_proj:  64%|██████▍   | 23498/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.124.up_proj:  64%|██████▍   | 23499/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.124.down_proj:  64%|██████▍   | 23500/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.125.gate_proj:  64%|██████▍   | 23501/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.125.up_proj:  64%|██████▍   | 23502/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.125.down_proj:  64%|██████▍   | 23503/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.126.gate_proj:  64%|██████▍   | 23504/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.126.up_proj:  64%|██████▍   | 23505/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.126.down_proj:  64%|██████▍   | 23506/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.127.gate_proj:  64%|██████▍   | 23507/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.59.mlp.experts.127.up_proj:  64%|██████▍   | 23508/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.59.mlp.experts.127.down_proj:  64%|██████▍   | 23509/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.0.gate_proj:  64%|██████▍   | 23510/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.0.up_proj:  64%|██████▍   | 23511/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.0.down_proj:  64%|██████▍   | 23512/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.1.gate_proj:  64%|██████▍   | 23513/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.1.up_proj:  64%|██████▍   | 23514/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.1.down_proj:  64%|██████▍   | 23515/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.2.gate_proj:  64%|██████▍   | 23516/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.2.up_proj:  64%|██████▍   | 23517/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.2.down_proj:  64%|██████▍   | 23518/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.3.gate_proj:  64%|██████▍   | 23519/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.3.up_proj:  64%|██████▍   | 23520/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.3.down_proj:  64%|██████▍   | 23521/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.4.gate_proj:  64%|██████▍   | 23522/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.4.up_proj:  64%|██████▍   | 23523/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.4.down_proj:  64%|██████▍   | 23524/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.5.gate_proj:  64%|██████▍   | 23525/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.5.up_proj:  64%|██████▍   | 23526/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.5.down_proj:  64%|██████▍   | 23527/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.6.gate_proj:  64%|██████▍   | 23528/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.6.up_proj:  64%|██████▍   | 23529/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.6.down_proj:  64%|██████▍   | 23530/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.7.gate_proj:  64%|██████▍   | 23531/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.7.up_proj:  64%|██████▍   | 23532/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.7.down_proj:  64%|██████▍   | 23533/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.8.gate_proj:  64%|██████▍   | 23534/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.8.up_proj:  64%|██████▍   | 23535/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.8.down_proj:  64%|██████▍   | 23536/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.9.gate_proj:  64%|██████▍   | 23537/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.9.up_proj:  64%|██████▍   | 23538/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.9.down_proj:  64%|██████▍   | 23539/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.10.gate_proj:  64%|██████▍   | 23540/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.10.up_proj:  64%|██████▍   | 23541/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.10.down_proj:  64%|██████▍   | 23542/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.11.gate_proj:  64%|██████▍   | 23543/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.11.up_proj:  64%|██████▍   | 23544/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.11.down_proj:  64%|██████▍   | 23545/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.12.gate_proj:  64%|██████▍   | 23546/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.12.up_proj:  64%|██████▍   | 23547/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.12.down_proj:  64%|██████▍   | 23548/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.13.gate_proj:  64%|██████▍   | 23549/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.13.up_proj:  64%|██████▍   | 23550/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.13.down_proj:  64%|██████▍   | 23551/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.14.gate_proj:  64%|██████▍   | 23552/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.14.up_proj:  64%|██████▍   | 23553/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.14.down_proj:  64%|██████▍   | 23554/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.15.gate_proj:  64%|██████▍   | 23555/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.15.up_proj:  64%|██████▍   | 23556/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.15.down_proj:  64%|██████▍   | 23557/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.16.gate_proj:  64%|██████▍   | 23558/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.16.up_proj:  64%|██████▍   | 23559/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.16.down_proj:  64%|██████▍   | 23560/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.17.gate_proj:  64%|██████▍   | 23561/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.17.up_proj:  64%|██████▍   | 23562/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.17.down_proj:  64%|██████▍   | 23563/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.18.gate_proj:  64%|██████▍   | 23564/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.18.up_proj:  64%|██████▍   | 23565/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.18.down_proj:  64%|██████▍   | 23566/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.19.gate_proj:  64%|██████▍   | 23567/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.19.up_proj:  64%|██████▍   | 23568/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.19.down_proj:  64%|██████▍   | 23569/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.20.gate_proj:  64%|██████▍   | 23570/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.20.up_proj:  64%|██████▍   | 23571/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.20.down_proj:  64%|██████▍   | 23572/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.21.gate_proj:  64%|██████▍   | 23573/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.21.up_proj:  64%|██████▍   | 23574/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.21.down_proj:  64%|██████▍   | 23575/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.22.gate_proj:  64%|██████▍   | 23576/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.22.up_proj:  64%|██████▍   | 23577/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.22.down_proj:  64%|██████▍   | 23578/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.23.gate_proj:  64%|██████▍   | 23579/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.23.up_proj:  64%|██████▍   | 23580/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.23.down_proj:  64%|██████▍   | 23581/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.24.gate_proj:  64%|██████▍   | 23582/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.24.up_proj:  64%|██████▍   | 23583/36566 [00:21<00:11, 1123.98it/s]  
packing model.layers.60.mlp.experts.24.down_proj:  64%|██████▍   | 23584/36566 [00:21<00:11, 1123.98it/s]
packing model.layers.60.mlp.experts.24.down_proj:  64%|██████▍   | 23585/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.25.gate_proj:  64%|██████▍   | 23585/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.25.up_proj:  65%|██████▍   | 23586/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.25.down_proj:  65%|██████▍   | 23587/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.26.gate_proj:  65%|██████▍   | 23588/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.26.up_proj:  65%|██████▍   | 23589/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.26.down_proj:  65%|██████▍   | 23590/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.27.gate_proj:  65%|██████▍   | 23591/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.27.up_proj:  65%|██████▍   | 23592/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.27.down_proj:  65%|██████▍   | 23593/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.28.gate_proj:  65%|██████▍   | 23594/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.28.up_proj:  65%|██████▍   | 23595/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.28.down_proj:  65%|██████▍   | 23596/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.29.gate_proj:  65%|██████▍   | 23597/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.29.up_proj:  65%|██████▍   | 23598/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.29.down_proj:  65%|██████▍   | 23599/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.30.gate_proj:  65%|██████▍   | 23600/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.30.up_proj:  65%|██████▍   | 23601/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.30.down_proj:  65%|██████▍   | 23602/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.31.gate_proj:  65%|██████▍   | 23603/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.31.up_proj:  65%|██████▍   | 23604/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.31.down_proj:  65%|██████▍   | 23605/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.32.gate_proj:  65%|██████▍   | 23606/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.32.up_proj:  65%|██████▍   | 23607/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.32.down_proj:  65%|██████▍   | 23608/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.33.gate_proj:  65%|██████▍   | 23609/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.33.up_proj:  65%|██████▍   | 23610/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.33.down_proj:  65%|██████▍   | 23611/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.34.gate_proj:  65%|██████▍   | 23612/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.34.up_proj:  65%|██████▍   | 23613/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.34.down_proj:  65%|██████▍   | 23614/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.35.gate_proj:  65%|██████▍   | 23615/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.35.up_proj:  65%|██████▍   | 23616/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.35.down_proj:  65%|██████▍   | 23617/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.36.gate_proj:  65%|██████▍   | 23618/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.36.up_proj:  65%|██████▍   | 23619/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.36.down_proj:  65%|██████▍   | 23620/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.37.gate_proj:  65%|██████▍   | 23621/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.37.up_proj:  65%|██████▍   | 23622/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.37.down_proj:  65%|██████▍   | 23623/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.38.gate_proj:  65%|██████▍   | 23624/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.38.up_proj:  65%|██████▍   | 23625/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.38.down_proj:  65%|██████▍   | 23626/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.39.gate_proj:  65%|██████▍   | 23627/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.39.up_proj:  65%|██████▍   | 23628/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.39.down_proj:  65%|██████▍   | 23629/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.40.gate_proj:  65%|██████▍   | 23630/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.40.up_proj:  65%|██████▍   | 23631/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.40.down_proj:  65%|██████▍   | 23632/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.41.gate_proj:  65%|██████▍   | 23633/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.41.up_proj:  65%|██████▍   | 23634/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.41.down_proj:  65%|██████▍   | 23635/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.42.gate_proj:  65%|██████▍   | 23636/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.42.up_proj:  65%|██████▍   | 23637/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.42.down_proj:  65%|██████▍   | 23638/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.43.gate_proj:  65%|██████▍   | 23639/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.43.up_proj:  65%|██████▍   | 23640/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.43.down_proj:  65%|██████▍   | 23641/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.44.gate_proj:  65%|██████▍   | 23642/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.44.up_proj:  65%|██████▍   | 23643/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.44.down_proj:  65%|██████▍   | 23644/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.45.gate_proj:  65%|██████▍   | 23645/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.45.up_proj:  65%|██████▍   | 23646/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.45.down_proj:  65%|██████▍   | 23647/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.46.gate_proj:  65%|██████▍   | 23648/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.46.up_proj:  65%|██████▍   | 23649/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.46.down_proj:  65%|██████▍   | 23650/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.47.gate_proj:  65%|██████▍   | 23651/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.47.up_proj:  65%|██████▍   | 23652/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.47.down_proj:  65%|██████▍   | 23653/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.48.gate_proj:  65%|██████▍   | 23654/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.48.up_proj:  65%|██████▍   | 23655/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.48.down_proj:  65%|██████▍   | 23656/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.49.gate_proj:  65%|██████▍   | 23657/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.49.up_proj:  65%|██████▍   | 23658/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.49.down_proj:  65%|██████▍   | 23659/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.50.gate_proj:  65%|██████▍   | 23660/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.50.up_proj:  65%|██████▍   | 23661/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.50.down_proj:  65%|██████▍   | 23662/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.51.gate_proj:  65%|██████▍   | 23663/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.51.up_proj:  65%|██████▍   | 23664/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.51.down_proj:  65%|██████▍   | 23665/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.52.gate_proj:  65%|██████▍   | 23666/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.52.up_proj:  65%|██████▍   | 23667/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.52.down_proj:  65%|██████▍   | 23668/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.53.gate_proj:  65%|██████▍   | 23669/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.53.up_proj:  65%|██████▍   | 23670/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.53.down_proj:  65%|██████▍   | 23671/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.54.gate_proj:  65%|██████▍   | 23672/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.54.up_proj:  65%|██████▍   | 23673/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.54.down_proj:  65%|██████▍   | 23674/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.55.gate_proj:  65%|██████▍   | 23675/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.55.up_proj:  65%|██████▍   | 23676/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.55.down_proj:  65%|██████▍   | 23677/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.56.gate_proj:  65%|██████▍   | 23678/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.56.up_proj:  65%|██████▍   | 23679/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.56.down_proj:  65%|██████▍   | 23680/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.57.gate_proj:  65%|██████▍   | 23681/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.57.up_proj:  65%|██████▍   | 23682/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.57.down_proj:  65%|██████▍   | 23683/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.58.gate_proj:  65%|██████▍   | 23684/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.58.up_proj:  65%|██████▍   | 23685/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.58.down_proj:  65%|██████▍   | 23686/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.59.gate_proj:  65%|██████▍   | 23687/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.59.up_proj:  65%|██████▍   | 23688/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.59.down_proj:  65%|██████▍   | 23689/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.60.gate_proj:  65%|██████▍   | 23690/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.60.up_proj:  65%|██████▍   | 23691/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.60.down_proj:  65%|██████▍   | 23692/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.61.gate_proj:  65%|██████▍   | 23693/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.61.up_proj:  65%|██████▍   | 23694/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.61.down_proj:  65%|██████▍   | 23695/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.62.gate_proj:  65%|██████▍   | 23696/36566 [00:21<00:11, 1113.72it/s]
packing model.layers.60.mlp.experts.62.up_proj:  65%|██████▍   | 23697/36566 [00:21<00:11, 1113.72it/s]  
packing model.layers.60.mlp.experts.62.up_proj:  65%|██████▍   | 23698/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.62.down_proj:  65%|██████▍   | 23698/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.63.gate_proj:  65%|██████▍   | 23699/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.63.up_proj:  65%|██████▍   | 23700/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.63.down_proj:  65%|██████▍   | 23701/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.64.gate_proj:  65%|██████▍   | 23702/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.64.up_proj:  65%|██████▍   | 23703/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.64.down_proj:  65%|██████▍   | 23704/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.65.gate_proj:  65%|██████▍   | 23705/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.65.up_proj:  65%|██████▍   | 23706/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.65.down_proj:  65%|██████▍   | 23707/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.66.gate_proj:  65%|██████▍   | 23708/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.66.up_proj:  65%|██████▍   | 23709/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.66.down_proj:  65%|██████▍   | 23710/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.67.gate_proj:  65%|██████▍   | 23711/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.67.up_proj:  65%|██████▍   | 23712/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.67.down_proj:  65%|██████▍   | 23713/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.68.gate_proj:  65%|██████▍   | 23714/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.68.up_proj:  65%|██████▍   | 23715/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.68.down_proj:  65%|██████▍   | 23716/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.69.gate_proj:  65%|██████▍   | 23717/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.69.up_proj:  65%|██████▍   | 23718/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.69.down_proj:  65%|██████▍   | 23719/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.70.gate_proj:  65%|██████▍   | 23720/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.70.up_proj:  65%|██████▍   | 23721/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.70.down_proj:  65%|██████▍   | 23722/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.71.gate_proj:  65%|██████▍   | 23723/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.71.up_proj:  65%|██████▍   | 23724/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.71.down_proj:  65%|██████▍   | 23725/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.72.gate_proj:  65%|██████▍   | 23726/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.72.up_proj:  65%|██████▍   | 23727/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.72.down_proj:  65%|██████▍   | 23728/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.73.gate_proj:  65%|██████▍   | 23729/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.73.up_proj:  65%|██████▍   | 23730/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.73.down_proj:  65%|██████▍   | 23731/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.74.gate_proj:  65%|██████▍   | 23732/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.74.up_proj:  65%|██████▍   | 23733/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.74.down_proj:  65%|██████▍   | 23734/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.75.gate_proj:  65%|██████▍   | 23735/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.75.up_proj:  65%|██████▍   | 23736/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.75.down_proj:  65%|██████▍   | 23737/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.76.gate_proj:  65%|██████▍   | 23738/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.76.up_proj:  65%|██████▍   | 23739/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.76.down_proj:  65%|██████▍   | 23740/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.77.gate_proj:  65%|██████▍   | 23741/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.77.up_proj:  65%|██████▍   | 23742/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.77.down_proj:  65%|██████▍   | 23743/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.78.gate_proj:  65%|██████▍   | 23744/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.78.up_proj:  65%|██████▍   | 23745/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.78.down_proj:  65%|██████▍   | 23746/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.79.gate_proj:  65%|██████▍   | 23747/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.79.up_proj:  65%|██████▍   | 23748/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.79.down_proj:  65%|██████▍   | 23749/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.80.gate_proj:  65%|██████▍   | 23750/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.80.up_proj:  65%|██████▍   | 23751/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.80.down_proj:  65%|██████▍   | 23752/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.81.gate_proj:  65%|██████▍   | 23753/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.81.up_proj:  65%|██████▍   | 23754/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.81.down_proj:  65%|██████▍   | 23755/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.82.gate_proj:  65%|██████▍   | 23756/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.82.up_proj:  65%|██████▍   | 23757/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.82.down_proj:  65%|██████▍   | 23758/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.83.gate_proj:  65%|██████▍   | 23759/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.83.up_proj:  65%|██████▍   | 23760/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.83.down_proj:  65%|██████▍   | 23761/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.84.gate_proj:  65%|██████▍   | 23762/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.84.up_proj:  65%|██████▍   | 23763/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.84.down_proj:  65%|██████▍   | 23764/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.85.gate_proj:  65%|██████▍   | 23765/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.85.up_proj:  65%|██████▍   | 23766/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.85.down_proj:  65%|██████▍   | 23767/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.86.gate_proj:  65%|██████▌   | 23768/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.86.up_proj:  65%|██████▌   | 23769/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.86.down_proj:  65%|██████▌   | 23770/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.87.gate_proj:  65%|██████▌   | 23771/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.87.up_proj:  65%|██████▌   | 23772/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.87.down_proj:  65%|██████▌   | 23773/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.88.gate_proj:  65%|██████▌   | 23774/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.88.up_proj:  65%|██████▌   | 23775/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.88.down_proj:  65%|██████▌   | 23776/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.89.gate_proj:  65%|██████▌   | 23777/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.89.up_proj:  65%|██████▌   | 23778/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.89.down_proj:  65%|██████▌   | 23779/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.90.gate_proj:  65%|██████▌   | 23780/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.90.up_proj:  65%|██████▌   | 23781/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.90.down_proj:  65%|██████▌   | 23782/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.91.gate_proj:  65%|██████▌   | 23783/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.91.up_proj:  65%|██████▌   | 23784/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.91.down_proj:  65%|██████▌   | 23785/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.92.gate_proj:  65%|██████▌   | 23786/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.92.up_proj:  65%|██████▌   | 23787/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.92.down_proj:  65%|██████▌   | 23788/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.93.gate_proj:  65%|██████▌   | 23789/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.93.up_proj:  65%|██████▌   | 23790/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.93.down_proj:  65%|██████▌   | 23791/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.94.gate_proj:  65%|██████▌   | 23792/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.94.up_proj:  65%|██████▌   | 23793/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.94.down_proj:  65%|██████▌   | 23794/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.95.gate_proj:  65%|██████▌   | 23795/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.95.up_proj:  65%|██████▌   | 23796/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.95.down_proj:  65%|██████▌   | 23797/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.96.gate_proj:  65%|██████▌   | 23798/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.96.up_proj:  65%|██████▌   | 23799/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.96.down_proj:  65%|██████▌   | 23800/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.97.gate_proj:  65%|██████▌   | 23801/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.97.up_proj:  65%|██████▌   | 23802/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.97.down_proj:  65%|██████▌   | 23803/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.98.gate_proj:  65%|██████▌   | 23804/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.98.up_proj:  65%|██████▌   | 23805/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.98.down_proj:  65%|██████▌   | 23806/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.99.gate_proj:  65%|██████▌   | 23807/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.99.up_proj:  65%|██████▌   | 23808/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.99.down_proj:  65%|██████▌   | 23809/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.100.gate_proj:  65%|██████▌   | 23810/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.100.up_proj:  65%|██████▌   | 23811/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.100.down_proj:  65%|██████▌   | 23812/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.101.gate_proj:  65%|██████▌   | 23813/36566 [00:21<00:11, 1118.27it/s]
packing model.layers.60.mlp.experts.101.up_proj:  65%|██████▌   | 23814/36566 [00:21<00:11, 1118.27it/s]  
packing model.layers.60.mlp.experts.101.up_proj:  65%|██████▌   | 23815/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.101.down_proj:  65%|██████▌   | 23815/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.102.gate_proj:  65%|██████▌   | 23816/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.102.up_proj:  65%|██████▌   | 23817/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.102.down_proj:  65%|██████▌   | 23818/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.103.gate_proj:  65%|██████▌   | 23819/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.103.up_proj:  65%|██████▌   | 23820/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.103.down_proj:  65%|██████▌   | 23821/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.104.gate_proj:  65%|██████▌   | 23822/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.104.up_proj:  65%|██████▌   | 23823/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.104.down_proj:  65%|██████▌   | 23824/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.105.gate_proj:  65%|██████▌   | 23825/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.105.up_proj:  65%|██████▌   | 23826/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.105.down_proj:  65%|██████▌   | 23827/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.106.gate_proj:  65%|██████▌   | 23828/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.106.up_proj:  65%|██████▌   | 23829/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.106.down_proj:  65%|██████▌   | 23830/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.107.gate_proj:  65%|██████▌   | 23831/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.107.up_proj:  65%|██████▌   | 23832/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.107.down_proj:  65%|██████▌   | 23833/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.108.gate_proj:  65%|██████▌   | 23834/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.108.up_proj:  65%|██████▌   | 23835/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.108.down_proj:  65%|██████▌   | 23836/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.109.gate_proj:  65%|██████▌   | 23837/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.109.up_proj:  65%|██████▌   | 23838/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.109.down_proj:  65%|██████▌   | 23839/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.110.gate_proj:  65%|██████▌   | 23840/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.110.up_proj:  65%|██████▌   | 23841/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.110.down_proj:  65%|██████▌   | 23842/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.111.gate_proj:  65%|██████▌   | 23843/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.111.up_proj:  65%|██████▌   | 23844/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.111.down_proj:  65%|██████▌   | 23845/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.112.gate_proj:  65%|██████▌   | 23846/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.112.up_proj:  65%|██████▌   | 23847/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.112.down_proj:  65%|██████▌   | 23848/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.113.gate_proj:  65%|██████▌   | 23849/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.113.up_proj:  65%|██████▌   | 23850/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.113.down_proj:  65%|██████▌   | 23851/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.114.gate_proj:  65%|██████▌   | 23852/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.114.up_proj:  65%|██████▌   | 23853/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.114.down_proj:  65%|██████▌   | 23854/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.115.gate_proj:  65%|██████▌   | 23855/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.115.up_proj:  65%|██████▌   | 23856/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.115.down_proj:  65%|██████▌   | 23857/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.116.gate_proj:  65%|██████▌   | 23858/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.116.up_proj:  65%|██████▌   | 23859/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.116.down_proj:  65%|██████▌   | 23860/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.117.gate_proj:  65%|██████▌   | 23861/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.117.up_proj:  65%|██████▌   | 23862/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.117.down_proj:  65%|██████▌   | 23863/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.118.gate_proj:  65%|██████▌   | 23864/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.118.up_proj:  65%|██████▌   | 23865/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.118.down_proj:  65%|██████▌   | 23866/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.119.gate_proj:  65%|██████▌   | 23867/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.119.up_proj:  65%|██████▌   | 23868/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.119.down_proj:  65%|██████▌   | 23869/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.120.gate_proj:  65%|██████▌   | 23870/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.120.up_proj:  65%|██████▌   | 23871/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.120.down_proj:  65%|██████▌   | 23872/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.121.gate_proj:  65%|██████▌   | 23873/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.121.up_proj:  65%|██████▌   | 23874/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.121.down_proj:  65%|██████▌   | 23875/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.122.gate_proj:  65%|██████▌   | 23876/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.122.up_proj:  65%|██████▌   | 23877/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.122.down_proj:  65%|██████▌   | 23878/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.123.gate_proj:  65%|██████▌   | 23879/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.123.up_proj:  65%|██████▌   | 23880/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.123.down_proj:  65%|██████▌   | 23881/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.124.gate_proj:  65%|██████▌   | 23882/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.124.up_proj:  65%|██████▌   | 23883/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.124.down_proj:  65%|██████▌   | 23884/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.125.gate_proj:  65%|██████▌   | 23885/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.125.up_proj:  65%|██████▌   | 23886/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.125.down_proj:  65%|██████▌   | 23887/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.126.gate_proj:  65%|██████▌   | 23888/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.126.up_proj:  65%|██████▌   | 23889/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.126.down_proj:  65%|██████▌   | 23890/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.127.gate_proj:  65%|██████▌   | 23891/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.60.mlp.experts.127.up_proj:  65%|██████▌   | 23892/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.60.mlp.experts.127.down_proj:  65%|██████▌   | 23893/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.0.gate_proj:  65%|██████▌   | 23894/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.0.up_proj:  65%|██████▌   | 23895/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.0.down_proj:  65%|██████▌   | 23896/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.1.gate_proj:  65%|██████▌   | 23897/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.1.up_proj:  65%|██████▌   | 23898/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.1.down_proj:  65%|██████▌   | 23899/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.2.gate_proj:  65%|██████▌   | 23900/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.2.up_proj:  65%|██████▌   | 23901/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.2.down_proj:  65%|██████▌   | 23902/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.3.gate_proj:  65%|██████▌   | 23903/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.3.up_proj:  65%|██████▌   | 23904/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.3.down_proj:  65%|██████▌   | 23905/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.4.gate_proj:  65%|██████▌   | 23906/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.4.up_proj:  65%|██████▌   | 23907/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.4.down_proj:  65%|██████▌   | 23908/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.5.gate_proj:  65%|██████▌   | 23909/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.5.up_proj:  65%|██████▌   | 23910/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.5.down_proj:  65%|██████▌   | 23911/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.6.gate_proj:  65%|██████▌   | 23912/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.6.up_proj:  65%|██████▌   | 23913/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.6.down_proj:  65%|██████▌   | 23914/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.7.gate_proj:  65%|██████▌   | 23915/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.7.up_proj:  65%|██████▌   | 23916/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.7.down_proj:  65%|██████▌   | 23917/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.8.gate_proj:  65%|██████▌   | 23918/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.8.up_proj:  65%|██████▌   | 23919/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.8.down_proj:  65%|██████▌   | 23920/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.9.gate_proj:  65%|██████▌   | 23921/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.9.up_proj:  65%|██████▌   | 23922/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.9.down_proj:  65%|██████▌   | 23923/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.10.gate_proj:  65%|██████▌   | 23924/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.10.up_proj:  65%|██████▌   | 23925/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.10.down_proj:  65%|██████▌   | 23926/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.11.gate_proj:  65%|██████▌   | 23927/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.11.up_proj:  65%|██████▌   | 23928/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.11.down_proj:  65%|██████▌   | 23929/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.12.gate_proj:  65%|██████▌   | 23930/36566 [00:21<00:11, 1131.55it/s]
packing model.layers.61.mlp.experts.12.up_proj:  65%|██████▌   | 23931/36566 [00:21<00:11, 1131.55it/s]  
packing model.layers.61.mlp.experts.12.up_proj:  65%|██████▌   | 23932/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.12.down_proj:  65%|██████▌   | 23932/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.13.gate_proj:  65%|██████▌   | 23933/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.13.up_proj:  65%|██████▌   | 23934/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.13.down_proj:  65%|██████▌   | 23935/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.14.gate_proj:  65%|██████▌   | 23936/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.14.up_proj:  65%|██████▌   | 23937/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.14.down_proj:  65%|██████▌   | 23938/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.15.gate_proj:  65%|██████▌   | 23939/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.15.up_proj:  65%|██████▌   | 23940/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.15.down_proj:  65%|██████▌   | 23941/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.16.gate_proj:  65%|██████▌   | 23942/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.16.up_proj:  65%|██████▌   | 23943/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.16.down_proj:  65%|██████▌   | 23944/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.17.gate_proj:  65%|██████▌   | 23945/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.17.up_proj:  65%|██████▌   | 23946/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.17.down_proj:  65%|██████▌   | 23947/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.18.gate_proj:  65%|██████▌   | 23948/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.18.up_proj:  65%|██████▌   | 23949/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.18.down_proj:  65%|██████▌   | 23950/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.19.gate_proj:  66%|██████▌   | 23951/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.19.up_proj:  66%|██████▌   | 23952/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.19.down_proj:  66%|██████▌   | 23953/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.20.gate_proj:  66%|██████▌   | 23954/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.20.up_proj:  66%|██████▌   | 23955/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.20.down_proj:  66%|██████▌   | 23956/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.21.gate_proj:  66%|██████▌   | 23957/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.21.up_proj:  66%|██████▌   | 23958/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.21.down_proj:  66%|██████▌   | 23959/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.22.gate_proj:  66%|██████▌   | 23960/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.22.up_proj:  66%|██████▌   | 23961/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.22.down_proj:  66%|██████▌   | 23962/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.23.gate_proj:  66%|██████▌   | 23963/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.23.up_proj:  66%|██████▌   | 23964/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.23.down_proj:  66%|██████▌   | 23965/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.24.gate_proj:  66%|██████▌   | 23966/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.24.up_proj:  66%|██████▌   | 23967/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.24.down_proj:  66%|██████▌   | 23968/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.25.gate_proj:  66%|██████▌   | 23969/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.25.up_proj:  66%|██████▌   | 23970/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.25.down_proj:  66%|██████▌   | 23971/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.26.gate_proj:  66%|██████▌   | 23972/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.26.up_proj:  66%|██████▌   | 23973/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.26.down_proj:  66%|██████▌   | 23974/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.27.gate_proj:  66%|██████▌   | 23975/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.27.up_proj:  66%|██████▌   | 23976/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.27.down_proj:  66%|██████▌   | 23977/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.28.gate_proj:  66%|██████▌   | 23978/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.28.up_proj:  66%|██████▌   | 23979/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.28.down_proj:  66%|██████▌   | 23980/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.29.gate_proj:  66%|██████▌   | 23981/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.29.up_proj:  66%|██████▌   | 23982/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.29.down_proj:  66%|██████▌   | 23983/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.30.gate_proj:  66%|██████▌   | 23984/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.30.up_proj:  66%|██████▌   | 23985/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.30.down_proj:  66%|██████▌   | 23986/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.31.gate_proj:  66%|██████▌   | 23987/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.31.up_proj:  66%|██████▌   | 23988/36566 [00:21<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.31.down_proj:  66%|██████▌   | 23989/36566 [00:21<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.32.gate_proj:  66%|██████▌   | 23990/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.32.up_proj:  66%|██████▌   | 23991/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.32.down_proj:  66%|██████▌   | 23992/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.33.gate_proj:  66%|██████▌   | 23993/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.33.up_proj:  66%|██████▌   | 23994/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.33.down_proj:  66%|██████▌   | 23995/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.34.gate_proj:  66%|██████▌   | 23996/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.34.up_proj:  66%|██████▌   | 23997/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.34.down_proj:  66%|██████▌   | 23998/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.35.gate_proj:  66%|██████▌   | 23999/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.35.up_proj:  66%|██████▌   | 24000/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.35.down_proj:  66%|██████▌   | 24001/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.36.gate_proj:  66%|██████▌   | 24002/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.36.up_proj:  66%|██████▌   | 24003/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.36.down_proj:  66%|██████▌   | 24004/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.37.gate_proj:  66%|██████▌   | 24005/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.37.up_proj:  66%|██████▌   | 24006/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.37.down_proj:  66%|██████▌   | 24007/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.38.gate_proj:  66%|██████▌   | 24008/36566 [00:22<00:11, 1141.47it/s]
packing model.layers.61.mlp.experts.38.up_proj:  66%|██████▌   | 24009/36566 [00:22<00:11, 1141.47it/s]  
packing model.layers.61.mlp.experts.38.down_proj:  66%|██████▌   | 24010/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.39.gate_proj:  66%|██████▌   | 24011/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.39.up_proj:  66%|██████▌   | 24012/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.39.down_proj:  66%|██████▌   | 24013/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.40.gate_proj:  66%|██████▌   | 24014/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.40.up_proj:  66%|██████▌   | 24015/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.40.down_proj:  66%|██████▌   | 24016/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.41.gate_proj:  66%|██████▌   | 24017/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.41.up_proj:  66%|██████▌   | 24018/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.41.down_proj:  66%|██████▌   | 24019/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.42.gate_proj:  66%|██████▌   | 24020/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.42.up_proj:  66%|██████▌   | 24021/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.42.down_proj:  66%|██████▌   | 24022/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.43.gate_proj:  66%|██████▌   | 24023/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.43.up_proj:  66%|██████▌   | 24024/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.43.down_proj:  66%|██████▌   | 24025/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.44.gate_proj:  66%|██████▌   | 24026/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.44.up_proj:  66%|██████▌   | 24027/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.44.down_proj:  66%|██████▌   | 24028/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.45.gate_proj:  66%|██████▌   | 24029/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.45.up_proj:  66%|██████▌   | 24030/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.45.down_proj:  66%|██████▌   | 24031/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.46.gate_proj:  66%|██████▌   | 24032/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.46.up_proj:  66%|██████▌   | 24033/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.46.down_proj:  66%|██████▌   | 24034/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.47.gate_proj:  66%|██████▌   | 24035/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.47.up_proj:  66%|██████▌   | 24036/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.47.down_proj:  66%|██████▌   | 24037/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.48.gate_proj:  66%|██████▌   | 24038/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.48.up_proj:  66%|██████▌   | 24039/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.48.down_proj:  66%|██████▌   | 24040/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.49.gate_proj:  66%|██████▌   | 24041/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.49.up_proj:  66%|██████▌   | 24042/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.49.down_proj:  66%|██████▌   | 24043/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.50.gate_proj:  66%|██████▌   | 24044/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.50.up_proj:  66%|██████▌   | 24045/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.61.mlp.experts.50.down_proj:  66%|██████▌   | 24046/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.51.gate_proj:  66%|██████▌   | 24047/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.61.mlp.experts.51.gate_proj:  66%|██████▌   | 24048/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.51.up_proj:  66%|██████▌   | 24048/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.51.down_proj:  66%|██████▌   | 24049/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.52.gate_proj:  66%|██████▌   | 24050/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.52.up_proj:  66%|██████▌   | 24051/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.52.down_proj:  66%|██████▌   | 24052/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.53.gate_proj:  66%|██████▌   | 24053/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.53.up_proj:  66%|██████▌   | 24054/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.53.down_proj:  66%|██████▌   | 24055/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.54.gate_proj:  66%|██████▌   | 24056/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.54.up_proj:  66%|██████▌   | 24057/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.54.down_proj:  66%|██████▌   | 24058/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.55.gate_proj:  66%|██████▌   | 24059/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.55.up_proj:  66%|██████▌   | 24060/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.55.down_proj:  66%|██████▌   | 24061/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.56.gate_proj:  66%|██████▌   | 24062/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.56.up_proj:  66%|██████▌   | 24063/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.56.down_proj:  66%|██████▌   | 24064/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.57.gate_proj:  66%|██████▌   | 24065/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.57.up_proj:  66%|██████▌   | 24066/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.57.down_proj:  66%|██████▌   | 24067/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.58.gate_proj:  66%|██████▌   | 24068/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.58.up_proj:  66%|██████▌   | 24069/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.58.down_proj:  66%|██████▌   | 24070/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.59.gate_proj:  66%|██████▌   | 24071/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.59.up_proj:  66%|██████▌   | 24072/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.59.down_proj:  66%|██████▌   | 24073/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.60.gate_proj:  66%|██████▌   | 24074/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.60.up_proj:  66%|██████▌   | 24075/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.60.down_proj:  66%|██████▌   | 24076/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.61.gate_proj:  66%|██████▌   | 24077/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.61.up_proj:  66%|██████▌   | 24078/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.61.down_proj:  66%|██████▌   | 24079/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.62.gate_proj:  66%|██████▌   | 24080/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.62.up_proj:  66%|██████▌   | 24081/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.62.down_proj:  66%|██████▌   | 24082/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.63.gate_proj:  66%|██████▌   | 24083/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.63.up_proj:  66%|██████▌   | 24084/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.63.down_proj:  66%|██████▌   | 24085/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.64.gate_proj:  66%|██████▌   | 24086/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.64.up_proj:  66%|██████▌   | 24087/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.64.down_proj:  66%|██████▌   | 24088/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.65.gate_proj:  66%|██████▌   | 24089/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.65.up_proj:  66%|██████▌   | 24090/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.65.down_proj:  66%|██████▌   | 24091/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.66.gate_proj:  66%|██████▌   | 24092/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.66.up_proj:  66%|██████▌   | 24093/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.66.down_proj:  66%|██████▌   | 24094/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.67.gate_proj:  66%|██████▌   | 24095/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.67.up_proj:  66%|██████▌   | 24096/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.67.down_proj:  66%|██████▌   | 24097/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.68.gate_proj:  66%|██████▌   | 24098/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.68.up_proj:  66%|██████▌   | 24099/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.68.down_proj:  66%|██████▌   | 24100/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.69.gate_proj:  66%|██████▌   | 24101/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.69.up_proj:  66%|██████▌   | 24102/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.69.down_proj:  66%|██████▌   | 24103/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.70.gate_proj:  66%|██████▌   | 24104/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.70.up_proj:  66%|██████▌   | 24105/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.70.down_proj:  66%|██████▌   | 24106/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.71.gate_proj:  66%|██████▌   | 24107/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.71.up_proj:  66%|██████▌   | 24108/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.71.down_proj:  66%|██████▌   | 24109/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.72.gate_proj:  66%|██████▌   | 24110/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.72.up_proj:  66%|██████▌   | 24111/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.72.down_proj:  66%|██████▌   | 24112/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.73.gate_proj:  66%|██████▌   | 24113/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.73.up_proj:  66%|██████▌   | 24114/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.73.down_proj:  66%|██████▌   | 24115/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.74.gate_proj:  66%|██████▌   | 24116/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.74.up_proj:  66%|██████▌   | 24117/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.74.down_proj:  66%|██████▌   | 24118/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.75.gate_proj:  66%|██████▌   | 24119/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.75.up_proj:  66%|██████▌   | 24120/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.75.down_proj:  66%|██████▌   | 24121/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.76.gate_proj:  66%|██████▌   | 24122/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.76.up_proj:  66%|██████▌   | 24123/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.76.down_proj:  66%|██████▌   | 24124/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.77.gate_proj:  66%|██████▌   | 24125/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.77.up_proj:  66%|██████▌   | 24126/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.77.down_proj:  66%|██████▌   | 24127/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.78.gate_proj:  66%|██████▌   | 24128/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.78.up_proj:  66%|██████▌   | 24129/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.78.down_proj:  66%|██████▌   | 24130/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.79.gate_proj:  66%|██████▌   | 24131/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.79.up_proj:  66%|██████▌   | 24132/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.79.down_proj:  66%|██████▌   | 24133/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.80.gate_proj:  66%|██████▌   | 24134/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.80.up_proj:  66%|██████▌   | 24135/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.80.down_proj:  66%|██████▌   | 24136/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.81.gate_proj:  66%|██████▌   | 24137/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.81.up_proj:  66%|██████▌   | 24138/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.81.down_proj:  66%|██████▌   | 24139/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.82.gate_proj:  66%|██████▌   | 24140/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.82.up_proj:  66%|██████▌   | 24141/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.82.down_proj:  66%|██████▌   | 24142/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.83.gate_proj:  66%|██████▌   | 24143/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.83.up_proj:  66%|██████▌   | 24144/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.83.down_proj:  66%|██████▌   | 24145/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.84.gate_proj:  66%|██████▌   | 24146/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.84.up_proj:  66%|██████▌   | 24147/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.84.down_proj:  66%|██████▌   | 24148/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.85.gate_proj:  66%|██████▌   | 24149/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.85.up_proj:  66%|██████▌   | 24150/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.85.down_proj:  66%|██████▌   | 24151/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.86.gate_proj:  66%|██████▌   | 24152/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.86.up_proj:  66%|██████▌   | 24153/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.86.down_proj:  66%|██████▌   | 24154/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.87.gate_proj:  66%|██████▌   | 24155/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.87.up_proj:  66%|██████▌   | 24156/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.87.down_proj:  66%|██████▌   | 24157/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.88.gate_proj:  66%|██████▌   | 24158/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.88.up_proj:  66%|██████▌   | 24159/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.88.down_proj:  66%|██████▌   | 24160/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.89.gate_proj:  66%|██████▌   | 24161/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.89.up_proj:  66%|██████▌   | 24162/36566 [00:22<00:10, 1146.83it/s]  
packing model.layers.61.mlp.experts.89.down_proj:  66%|██████▌   | 24163/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.90.gate_proj:  66%|██████▌   | 24164/36566 [00:22<00:10, 1146.83it/s]
packing model.layers.61.mlp.experts.90.gate_proj:  66%|██████▌   | 24165/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.90.up_proj:  66%|██████▌   | 24165/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.90.down_proj:  66%|██████▌   | 24166/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.91.gate_proj:  66%|██████▌   | 24167/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.91.up_proj:  66%|██████▌   | 24168/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.91.down_proj:  66%|██████▌   | 24169/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.92.gate_proj:  66%|██████▌   | 24170/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.92.up_proj:  66%|██████▌   | 24171/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.92.down_proj:  66%|██████▌   | 24172/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.93.gate_proj:  66%|██████▌   | 24173/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.93.up_proj:  66%|██████▌   | 24174/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.93.down_proj:  66%|██████▌   | 24175/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.94.gate_proj:  66%|██████▌   | 24176/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.94.up_proj:  66%|██████▌   | 24177/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.94.down_proj:  66%|██████▌   | 24178/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.95.gate_proj:  66%|██████▌   | 24179/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.95.up_proj:  66%|██████▌   | 24180/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.95.down_proj:  66%|██████▌   | 24181/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.96.gate_proj:  66%|██████▌   | 24182/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.96.up_proj:  66%|██████▌   | 24183/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.96.down_proj:  66%|██████▌   | 24184/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.97.gate_proj:  66%|██████▌   | 24185/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.97.up_proj:  66%|██████▌   | 24186/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.97.down_proj:  66%|██████▌   | 24187/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.98.gate_proj:  66%|██████▌   | 24188/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.98.up_proj:  66%|██████▌   | 24189/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.98.down_proj:  66%|██████▌   | 24190/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.99.gate_proj:  66%|██████▌   | 24191/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.99.up_proj:  66%|██████▌   | 24192/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.99.down_proj:  66%|██████▌   | 24193/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.100.gate_proj:  66%|██████▌   | 24194/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.100.up_proj:  66%|██████▌   | 24195/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.100.down_proj:  66%|██████▌   | 24196/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.101.gate_proj:  66%|██████▌   | 24197/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.101.up_proj:  66%|██████▌   | 24198/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.101.down_proj:  66%|██████▌   | 24199/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.102.gate_proj:  66%|██████▌   | 24200/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.102.up_proj:  66%|██████▌   | 24201/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.102.down_proj:  66%|██████▌   | 24202/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.103.gate_proj:  66%|██████▌   | 24203/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.103.up_proj:  66%|██████▌   | 24204/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.103.down_proj:  66%|██████▌   | 24205/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.104.gate_proj:  66%|██████▌   | 24206/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.104.up_proj:  66%|██████▌   | 24207/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.104.down_proj:  66%|██████▌   | 24208/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.105.gate_proj:  66%|██████▌   | 24209/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.105.up_proj:  66%|██████▌   | 24210/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.105.down_proj:  66%|██████▌   | 24211/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.106.gate_proj:  66%|██████▌   | 24212/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.106.up_proj:  66%|██████▌   | 24213/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.106.down_proj:  66%|██████▌   | 24214/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.107.gate_proj:  66%|██████▌   | 24215/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.107.up_proj:  66%|██████▌   | 24216/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.107.down_proj:  66%|██████▌   | 24217/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.108.gate_proj:  66%|██████▌   | 24218/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.108.up_proj:  66%|██████▌   | 24219/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.108.down_proj:  66%|██████▌   | 24220/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.109.gate_proj:  66%|██████▌   | 24221/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.109.up_proj:  66%|██████▌   | 24222/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.109.down_proj:  66%|██████▌   | 24223/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.110.gate_proj:  66%|██████▌   | 24224/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.110.up_proj:  66%|██████▋   | 24225/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.110.down_proj:  66%|██████▋   | 24226/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.111.gate_proj:  66%|██████▋   | 24227/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.111.up_proj:  66%|██████▋   | 24228/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.111.down_proj:  66%|██████▋   | 24229/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.112.gate_proj:  66%|██████▋   | 24230/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.112.up_proj:  66%|██████▋   | 24231/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.112.down_proj:  66%|██████▋   | 24232/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.113.gate_proj:  66%|██████▋   | 24233/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.113.up_proj:  66%|██████▋   | 24234/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.113.down_proj:  66%|██████▋   | 24235/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.114.gate_proj:  66%|██████▋   | 24236/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.114.up_proj:  66%|██████▋   | 24237/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.114.down_proj:  66%|██████▋   | 24238/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.115.gate_proj:  66%|██████▋   | 24239/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.115.up_proj:  66%|██████▋   | 24240/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.115.down_proj:  66%|██████▋   | 24241/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.116.gate_proj:  66%|██████▋   | 24242/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.116.up_proj:  66%|██████▋   | 24243/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.116.down_proj:  66%|██████▋   | 24244/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.117.gate_proj:  66%|██████▋   | 24245/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.117.up_proj:  66%|██████▋   | 24246/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.117.down_proj:  66%|██████▋   | 24247/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.118.gate_proj:  66%|██████▋   | 24248/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.118.up_proj:  66%|██████▋   | 24249/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.118.down_proj:  66%|██████▋   | 24250/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.119.gate_proj:  66%|██████▋   | 24251/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.119.up_proj:  66%|██████▋   | 24252/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.119.down_proj:  66%|██████▋   | 24253/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.120.gate_proj:  66%|██████▋   | 24254/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.120.up_proj:  66%|██████▋   | 24255/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.120.down_proj:  66%|██████▋   | 24256/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.121.gate_proj:  66%|██████▋   | 24257/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.121.up_proj:  66%|██████▋   | 24258/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.121.down_proj:  66%|██████▋   | 24259/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.122.gate_proj:  66%|██████▋   | 24260/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.122.up_proj:  66%|██████▋   | 24261/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.122.down_proj:  66%|██████▋   | 24262/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.123.gate_proj:  66%|██████▋   | 24263/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.123.up_proj:  66%|██████▋   | 24264/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.123.down_proj:  66%|██████▋   | 24265/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.124.gate_proj:  66%|██████▋   | 24266/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.124.up_proj:  66%|██████▋   | 24267/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.124.down_proj:  66%|██████▋   | 24268/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.125.gate_proj:  66%|██████▋   | 24269/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.125.up_proj:  66%|██████▋   | 24270/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.125.down_proj:  66%|██████▋   | 24271/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.126.gate_proj:  66%|██████▋   | 24272/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.126.up_proj:  66%|██████▋   | 24273/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.126.down_proj:  66%|██████▋   | 24274/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.127.gate_proj:  66%|██████▋   | 24275/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.61.mlp.experts.127.up_proj:  66%|██████▋   | 24276/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.61.mlp.experts.127.down_proj:  66%|██████▋   | 24277/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.62.mlp.experts.0.gate_proj:  66%|██████▋   | 24278/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.62.mlp.experts.0.up_proj:  66%|██████▋   | 24279/36566 [00:22<00:10, 1151.02it/s]  
packing model.layers.62.mlp.experts.0.down_proj:  66%|██████▋   | 24280/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.62.mlp.experts.1.gate_proj:  66%|██████▋   | 24281/36566 [00:22<00:10, 1151.02it/s]
packing model.layers.62.mlp.experts.1.gate_proj:  66%|██████▋   | 24282/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.1.up_proj:  66%|██████▋   | 24282/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.1.down_proj:  66%|██████▋   | 24283/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.2.gate_proj:  66%|██████▋   | 24284/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.2.up_proj:  66%|██████▋   | 24285/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.2.down_proj:  66%|██████▋   | 24286/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.3.gate_proj:  66%|██████▋   | 24287/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.3.up_proj:  66%|██████▋   | 24288/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.3.down_proj:  66%|██████▋   | 24289/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.4.gate_proj:  66%|██████▋   | 24290/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.4.up_proj:  66%|██████▋   | 24291/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.4.down_proj:  66%|██████▋   | 24292/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.5.gate_proj:  66%|██████▋   | 24293/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.5.up_proj:  66%|██████▋   | 24294/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.5.down_proj:  66%|██████▋   | 24295/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.6.gate_proj:  66%|██████▋   | 24296/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.6.up_proj:  66%|██████▋   | 24297/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.6.down_proj:  66%|██████▋   | 24298/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.7.gate_proj:  66%|██████▋   | 24299/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.7.up_proj:  66%|██████▋   | 24300/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.7.down_proj:  66%|██████▋   | 24301/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.8.gate_proj:  66%|██████▋   | 24302/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.8.up_proj:  66%|██████▋   | 24303/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.8.down_proj:  66%|██████▋   | 24304/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.9.gate_proj:  66%|██████▋   | 24305/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.9.up_proj:  66%|██████▋   | 24306/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.9.down_proj:  66%|██████▋   | 24307/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.10.gate_proj:  66%|██████▋   | 24308/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.10.up_proj:  66%|██████▋   | 24309/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.10.down_proj:  66%|██████▋   | 24310/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.11.gate_proj:  66%|██████▋   | 24311/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.11.up_proj:  66%|██████▋   | 24312/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.11.down_proj:  66%|██████▋   | 24313/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.12.gate_proj:  66%|██████▋   | 24314/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.12.up_proj:  66%|██████▋   | 24315/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.12.down_proj:  66%|██████▋   | 24316/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.13.gate_proj:  67%|██████▋   | 24317/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.13.up_proj:  67%|██████▋   | 24318/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.13.down_proj:  67%|██████▋   | 24319/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.14.gate_proj:  67%|██████▋   | 24320/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.14.up_proj:  67%|██████▋   | 24321/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.14.down_proj:  67%|██████▋   | 24322/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.15.gate_proj:  67%|██████▋   | 24323/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.15.up_proj:  67%|██████▋   | 24324/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.15.down_proj:  67%|██████▋   | 24325/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.16.gate_proj:  67%|██████▋   | 24326/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.16.up_proj:  67%|██████▋   | 24327/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.16.down_proj:  67%|██████▋   | 24328/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.17.gate_proj:  67%|██████▋   | 24329/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.17.up_proj:  67%|██████▋   | 24330/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.17.down_proj:  67%|██████▋   | 24331/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.18.gate_proj:  67%|██████▋   | 24332/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.18.up_proj:  67%|██████▋   | 24333/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.18.down_proj:  67%|██████▋   | 24334/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.19.gate_proj:  67%|██████▋   | 24335/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.19.up_proj:  67%|██████▋   | 24336/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.19.down_proj:  67%|██████▋   | 24337/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.20.gate_proj:  67%|██████▋   | 24338/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.20.up_proj:  67%|██████▋   | 24339/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.20.down_proj:  67%|██████▋   | 24340/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.21.gate_proj:  67%|██████▋   | 24341/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.21.up_proj:  67%|██████▋   | 24342/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.21.down_proj:  67%|██████▋   | 24343/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.22.gate_proj:  67%|██████▋   | 24344/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.22.up_proj:  67%|██████▋   | 24345/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.22.down_proj:  67%|██████▋   | 24346/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.23.gate_proj:  67%|██████▋   | 24347/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.23.up_proj:  67%|██████▋   | 24348/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.23.down_proj:  67%|██████▋   | 24349/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.24.gate_proj:  67%|██████▋   | 24350/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.24.up_proj:  67%|██████▋   | 24351/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.24.down_proj:  67%|██████▋   | 24352/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.25.gate_proj:  67%|██████▋   | 24353/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.25.up_proj:  67%|██████▋   | 24354/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.25.down_proj:  67%|██████▋   | 24355/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.26.gate_proj:  67%|██████▋   | 24356/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.26.up_proj:  67%|██████▋   | 24357/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.26.down_proj:  67%|██████▋   | 24358/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.27.gate_proj:  67%|██████▋   | 24359/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.27.up_proj:  67%|██████▋   | 24360/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.27.down_proj:  67%|██████▋   | 24361/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.28.gate_proj:  67%|██████▋   | 24362/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.28.up_proj:  67%|██████▋   | 24363/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.28.down_proj:  67%|██████▋   | 24364/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.29.gate_proj:  67%|██████▋   | 24365/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.29.up_proj:  67%|██████▋   | 24366/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.29.down_proj:  67%|██████▋   | 24367/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.30.gate_proj:  67%|██████▋   | 24368/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.30.up_proj:  67%|██████▋   | 24369/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.30.down_proj:  67%|██████▋   | 24370/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.31.gate_proj:  67%|██████▋   | 24371/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.31.up_proj:  67%|██████▋   | 24372/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.31.down_proj:  67%|██████▋   | 24373/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.32.gate_proj:  67%|██████▋   | 24374/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.32.up_proj:  67%|██████▋   | 24375/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.32.down_proj:  67%|██████▋   | 24376/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.33.gate_proj:  67%|██████▋   | 24377/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.33.up_proj:  67%|██████▋   | 24378/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.33.down_proj:  67%|██████▋   | 24379/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.34.gate_proj:  67%|██████▋   | 24380/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.34.up_proj:  67%|██████▋   | 24381/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.34.down_proj:  67%|██████▋   | 24382/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.35.gate_proj:  67%|██████▋   | 24383/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.35.up_proj:  67%|██████▋   | 24384/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.35.down_proj:  67%|██████▋   | 24385/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.36.gate_proj:  67%|██████▋   | 24386/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.36.up_proj:  67%|██████▋   | 24387/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.36.down_proj:  67%|██████▋   | 24388/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.37.gate_proj:  67%|██████▋   | 24389/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.37.up_proj:  67%|██████▋   | 24390/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.37.down_proj:  67%|██████▋   | 24391/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.38.gate_proj:  67%|██████▋   | 24392/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.38.up_proj:  67%|██████▋   | 24393/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.38.down_proj:  67%|██████▋   | 24394/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.39.gate_proj:  67%|██████▋   | 24395/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.39.up_proj:  67%|██████▋   | 24396/36566 [00:22<00:10, 1155.17it/s]  
packing model.layers.62.mlp.experts.39.down_proj:  67%|██████▋   | 24397/36566 [00:22<00:10, 1155.17it/s]
packing model.layers.62.mlp.experts.39.down_proj:  67%|██████▋   | 24398/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.40.gate_proj:  67%|██████▋   | 24398/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.40.up_proj:  67%|██████▋   | 24399/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.40.down_proj:  67%|██████▋   | 24400/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.41.gate_proj:  67%|██████▋   | 24401/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.41.up_proj:  67%|██████▋   | 24402/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.41.down_proj:  67%|██████▋   | 24403/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.42.gate_proj:  67%|██████▋   | 24404/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.42.up_proj:  67%|██████▋   | 24405/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.42.down_proj:  67%|██████▋   | 24406/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.43.gate_proj:  67%|██████▋   | 24407/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.43.up_proj:  67%|██████▋   | 24408/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.43.down_proj:  67%|██████▋   | 24409/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.44.gate_proj:  67%|██████▋   | 24410/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.44.up_proj:  67%|██████▋   | 24411/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.44.down_proj:  67%|██████▋   | 24412/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.45.gate_proj:  67%|██████▋   | 24413/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.45.up_proj:  67%|██████▋   | 24414/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.45.down_proj:  67%|██████▋   | 24415/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.46.gate_proj:  67%|██████▋   | 24416/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.46.up_proj:  67%|██████▋   | 24417/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.46.down_proj:  67%|██████▋   | 24418/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.47.gate_proj:  67%|██████▋   | 24419/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.47.up_proj:  67%|██████▋   | 24420/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.47.down_proj:  67%|██████▋   | 24421/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.48.gate_proj:  67%|██████▋   | 24422/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.48.up_proj:  67%|██████▋   | 24423/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.48.down_proj:  67%|██████▋   | 24424/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.49.gate_proj:  67%|██████▋   | 24425/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.49.up_proj:  67%|██████▋   | 24426/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.49.down_proj:  67%|██████▋   | 24427/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.50.gate_proj:  67%|██████▋   | 24428/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.50.up_proj:  67%|██████▋   | 24429/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.50.down_proj:  67%|██████▋   | 24430/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.51.gate_proj:  67%|██████▋   | 24431/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.51.up_proj:  67%|██████▋   | 24432/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.51.down_proj:  67%|██████▋   | 24433/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.52.gate_proj:  67%|██████▋   | 24434/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.52.up_proj:  67%|██████▋   | 24435/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.52.down_proj:  67%|██████▋   | 24436/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.53.gate_proj:  67%|██████▋   | 24437/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.53.up_proj:  67%|██████▋   | 24438/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.53.down_proj:  67%|██████▋   | 24439/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.54.gate_proj:  67%|██████▋   | 24440/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.54.up_proj:  67%|██████▋   | 24441/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.54.down_proj:  67%|██████▋   | 24442/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.55.gate_proj:  67%|██████▋   | 24443/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.55.up_proj:  67%|██████▋   | 24444/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.55.down_proj:  67%|██████▋   | 24445/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.56.gate_proj:  67%|██████▋   | 24446/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.56.up_proj:  67%|██████▋   | 24447/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.56.down_proj:  67%|██████▋   | 24448/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.57.gate_proj:  67%|██████▋   | 24449/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.57.up_proj:  67%|██████▋   | 24450/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.57.down_proj:  67%|██████▋   | 24451/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.58.gate_proj:  67%|██████▋   | 24452/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.58.up_proj:  67%|██████▋   | 24453/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.58.down_proj:  67%|██████▋   | 24454/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.59.gate_proj:  67%|██████▋   | 24455/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.59.up_proj:  67%|██████▋   | 24456/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.59.down_proj:  67%|██████▋   | 24457/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.60.gate_proj:  67%|██████▋   | 24458/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.60.up_proj:  67%|██████▋   | 24459/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.60.down_proj:  67%|██████▋   | 24460/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.61.gate_proj:  67%|██████▋   | 24461/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.61.up_proj:  67%|██████▋   | 24462/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.61.down_proj:  67%|██████▋   | 24463/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.62.gate_proj:  67%|██████▋   | 24464/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.62.up_proj:  67%|██████▋   | 24465/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.62.down_proj:  67%|██████▋   | 24466/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.63.gate_proj:  67%|██████▋   | 24467/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.63.up_proj:  67%|██████▋   | 24468/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.63.down_proj:  67%|██████▋   | 24469/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.64.gate_proj:  67%|██████▋   | 24470/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.64.up_proj:  67%|██████▋   | 24471/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.64.down_proj:  67%|██████▋   | 24472/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.65.gate_proj:  67%|██████▋   | 24473/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.65.up_proj:  67%|██████▋   | 24474/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.65.down_proj:  67%|██████▋   | 24475/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.66.gate_proj:  67%|██████▋   | 24476/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.66.up_proj:  67%|██████▋   | 24477/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.66.down_proj:  67%|██████▋   | 24478/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.67.gate_proj:  67%|██████▋   | 24479/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.67.up_proj:  67%|██████▋   | 24480/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.67.down_proj:  67%|██████▋   | 24481/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.68.gate_proj:  67%|██████▋   | 24482/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.68.up_proj:  67%|██████▋   | 24483/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.68.down_proj:  67%|██████▋   | 24484/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.69.gate_proj:  67%|██████▋   | 24485/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.69.up_proj:  67%|██████▋   | 24486/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.69.down_proj:  67%|██████▋   | 24487/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.70.gate_proj:  67%|██████▋   | 24488/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.70.up_proj:  67%|██████▋   | 24489/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.70.down_proj:  67%|██████▋   | 24490/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.71.gate_proj:  67%|██████▋   | 24491/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.71.up_proj:  67%|██████▋   | 24492/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.71.down_proj:  67%|██████▋   | 24493/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.72.gate_proj:  67%|██████▋   | 24494/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.72.up_proj:  67%|██████▋   | 24495/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.72.down_proj:  67%|██████▋   | 24496/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.73.gate_proj:  67%|██████▋   | 24497/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.73.up_proj:  67%|██████▋   | 24498/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.73.down_proj:  67%|██████▋   | 24499/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.74.gate_proj:  67%|██████▋   | 24500/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.74.up_proj:  67%|██████▋   | 24501/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.74.down_proj:  67%|██████▋   | 24502/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.75.gate_proj:  67%|██████▋   | 24503/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.75.up_proj:  67%|██████▋   | 24504/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.75.down_proj:  67%|██████▋   | 24505/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.76.gate_proj:  67%|██████▋   | 24506/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.76.up_proj:  67%|██████▋   | 24507/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.76.down_proj:  67%|██████▋   | 24508/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.77.gate_proj:  67%|██████▋   | 24509/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.77.up_proj:  67%|██████▋   | 24510/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.77.down_proj:  67%|██████▋   | 24511/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.78.gate_proj:  67%|██████▋   | 24512/36566 [00:22<00:10, 1152.62it/s]
packing model.layers.62.mlp.experts.78.up_proj:  67%|██████▋   | 24513/36566 [00:22<00:10, 1152.62it/s]  
packing model.layers.62.mlp.experts.78.up_proj:  67%|██████▋   | 24514/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.78.down_proj:  67%|██████▋   | 24514/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.79.gate_proj:  67%|██████▋   | 24515/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.79.up_proj:  67%|██████▋   | 24516/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.79.down_proj:  67%|██████▋   | 24517/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.80.gate_proj:  67%|██████▋   | 24518/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.80.up_proj:  67%|██████▋   | 24519/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.80.down_proj:  67%|██████▋   | 24520/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.81.gate_proj:  67%|██████▋   | 24521/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.81.up_proj:  67%|██████▋   | 24522/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.81.down_proj:  67%|██████▋   | 24523/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.82.gate_proj:  67%|██████▋   | 24524/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.82.up_proj:  67%|██████▋   | 24525/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.82.down_proj:  67%|██████▋   | 24526/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.83.gate_proj:  67%|██████▋   | 24527/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.83.up_proj:  67%|██████▋   | 24528/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.83.down_proj:  67%|██████▋   | 24529/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.84.gate_proj:  67%|██████▋   | 24530/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.84.up_proj:  67%|██████▋   | 24531/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.84.down_proj:  67%|██████▋   | 24532/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.85.gate_proj:  67%|██████▋   | 24533/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.85.up_proj:  67%|██████▋   | 24534/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.85.down_proj:  67%|██████▋   | 24535/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.86.gate_proj:  67%|██████▋   | 24536/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.86.up_proj:  67%|██████▋   | 24537/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.86.down_proj:  67%|██████▋   | 24538/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.87.gate_proj:  67%|██████▋   | 24539/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.87.up_proj:  67%|██████▋   | 24540/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.87.down_proj:  67%|██████▋   | 24541/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.88.gate_proj:  67%|██████▋   | 24542/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.88.up_proj:  67%|██████▋   | 24543/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.88.down_proj:  67%|██████▋   | 24544/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.89.gate_proj:  67%|██████▋   | 24545/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.89.up_proj:  67%|██████▋   | 24546/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.89.down_proj:  67%|██████▋   | 24547/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.90.gate_proj:  67%|██████▋   | 24548/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.90.up_proj:  67%|██████▋   | 24549/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.90.down_proj:  67%|██████▋   | 24550/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.91.gate_proj:  67%|██████▋   | 24551/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.91.up_proj:  67%|██████▋   | 24552/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.91.down_proj:  67%|██████▋   | 24553/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.92.gate_proj:  67%|██████▋   | 24554/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.92.up_proj:  67%|██████▋   | 24555/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.92.down_proj:  67%|██████▋   | 24556/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.93.gate_proj:  67%|██████▋   | 24557/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.93.up_proj:  67%|██████▋   | 24558/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.93.down_proj:  67%|██████▋   | 24559/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.94.gate_proj:  67%|██████▋   | 24560/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.94.up_proj:  67%|██████▋   | 24561/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.94.down_proj:  67%|██████▋   | 24562/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.95.gate_proj:  67%|██████▋   | 24563/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.95.up_proj:  67%|██████▋   | 24564/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.95.down_proj:  67%|██████▋   | 24565/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.96.gate_proj:  67%|██████▋   | 24566/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.96.up_proj:  67%|██████▋   | 24567/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.96.down_proj:  67%|██████▋   | 24568/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.97.gate_proj:  67%|██████▋   | 24569/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.97.up_proj:  67%|██████▋   | 24570/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.97.down_proj:  67%|██████▋   | 24571/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.98.gate_proj:  67%|██████▋   | 24572/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.98.up_proj:  67%|██████▋   | 24573/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.98.down_proj:  67%|██████▋   | 24574/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.99.gate_proj:  67%|██████▋   | 24575/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.99.up_proj:  67%|██████▋   | 24576/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.99.down_proj:  67%|██████▋   | 24577/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.100.gate_proj:  67%|██████▋   | 24578/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.100.up_proj:  67%|██████▋   | 24579/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.100.down_proj:  67%|██████▋   | 24580/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.101.gate_proj:  67%|██████▋   | 24581/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.101.up_proj:  67%|██████▋   | 24582/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.101.down_proj:  67%|██████▋   | 24583/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.102.gate_proj:  67%|██████▋   | 24584/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.102.up_proj:  67%|██████▋   | 24585/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.102.down_proj:  67%|██████▋   | 24586/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.103.gate_proj:  67%|██████▋   | 24587/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.103.up_proj:  67%|██████▋   | 24588/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.103.down_proj:  67%|██████▋   | 24589/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.104.gate_proj:  67%|██████▋   | 24590/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.104.up_proj:  67%|██████▋   | 24591/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.104.down_proj:  67%|██████▋   | 24592/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.105.gate_proj:  67%|██████▋   | 24593/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.105.up_proj:  67%|██████▋   | 24594/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.105.down_proj:  67%|██████▋   | 24595/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.106.gate_proj:  67%|██████▋   | 24596/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.106.up_proj:  67%|██████▋   | 24597/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.106.down_proj:  67%|██████▋   | 24598/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.107.gate_proj:  67%|██████▋   | 24599/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.107.up_proj:  67%|██████▋   | 24600/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.107.down_proj:  67%|██████▋   | 24601/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.108.gate_proj:  67%|██████▋   | 24602/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.108.up_proj:  67%|██████▋   | 24603/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.108.down_proj:  67%|██████▋   | 24604/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.109.gate_proj:  67%|██████▋   | 24605/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.109.up_proj:  67%|██████▋   | 24606/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.109.down_proj:  67%|██████▋   | 24607/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.110.gate_proj:  67%|██████▋   | 24608/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.110.up_proj:  67%|██████▋   | 24609/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.110.down_proj:  67%|██████▋   | 24610/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.111.gate_proj:  67%|██████▋   | 24611/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.111.up_proj:  67%|██████▋   | 24612/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.111.down_proj:  67%|██████▋   | 24613/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.112.gate_proj:  67%|██████▋   | 24614/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.112.up_proj:  67%|██████▋   | 24615/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.112.down_proj:  67%|██████▋   | 24616/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.113.gate_proj:  67%|██████▋   | 24617/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.113.up_proj:  67%|██████▋   | 24618/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.113.down_proj:  67%|██████▋   | 24619/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.114.gate_proj:  67%|██████▋   | 24620/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.114.up_proj:  67%|██████▋   | 24621/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.114.down_proj:  67%|██████▋   | 24622/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.115.gate_proj:  67%|██████▋   | 24623/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.115.up_proj:  67%|██████▋   | 24624/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.115.down_proj:  67%|██████▋   | 24625/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.116.gate_proj:  67%|██████▋   | 24626/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.116.up_proj:  67%|██████▋   | 24627/36566 [00:22<00:10, 1150.01it/s]  
packing model.layers.62.mlp.experts.116.down_proj:  67%|██████▋   | 24628/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.117.gate_proj:  67%|██████▋   | 24629/36566 [00:22<00:10, 1150.01it/s]
packing model.layers.62.mlp.experts.117.gate_proj:  67%|██████▋   | 24630/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.117.up_proj:  67%|██████▋   | 24630/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.117.down_proj:  67%|██████▋   | 24631/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.118.gate_proj:  67%|██████▋   | 24632/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.118.up_proj:  67%|██████▋   | 24633/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.118.down_proj:  67%|██████▋   | 24634/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.119.gate_proj:  67%|██████▋   | 24635/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.119.up_proj:  67%|██████▋   | 24636/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.119.down_proj:  67%|██████▋   | 24637/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.120.gate_proj:  67%|██████▋   | 24638/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.120.up_proj:  67%|██████▋   | 24639/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.120.down_proj:  67%|██████▋   | 24640/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.121.gate_proj:  67%|██████▋   | 24641/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.121.up_proj:  67%|██████▋   | 24642/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.121.down_proj:  67%|██████▋   | 24643/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.122.gate_proj:  67%|██████▋   | 24644/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.122.up_proj:  67%|██████▋   | 24645/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.122.down_proj:  67%|██████▋   | 24646/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.123.gate_proj:  67%|██████▋   | 24647/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.123.up_proj:  67%|██████▋   | 24648/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.123.down_proj:  67%|██████▋   | 24649/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.124.gate_proj:  67%|██████▋   | 24650/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.124.up_proj:  67%|██████▋   | 24651/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.124.down_proj:  67%|██████▋   | 24652/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.125.gate_proj:  67%|██████▋   | 24653/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.125.up_proj:  67%|██████▋   | 24654/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.125.down_proj:  67%|██████▋   | 24655/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.126.gate_proj:  67%|██████▋   | 24656/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.126.up_proj:  67%|██████▋   | 24657/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.126.down_proj:  67%|██████▋   | 24658/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.127.gate_proj:  67%|██████▋   | 24659/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.62.mlp.experts.127.up_proj:  67%|██████▋   | 24660/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.62.mlp.experts.127.down_proj:  67%|██████▋   | 24661/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.0.gate_proj:  67%|██████▋   | 24662/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.0.up_proj:  67%|██████▋   | 24663/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.0.down_proj:  67%|██████▋   | 24664/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.1.gate_proj:  67%|██████▋   | 24665/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.1.up_proj:  67%|██████▋   | 24666/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.1.down_proj:  67%|██████▋   | 24667/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.2.gate_proj:  67%|██████▋   | 24668/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.2.up_proj:  67%|██████▋   | 24669/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.2.down_proj:  67%|██████▋   | 24670/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.3.gate_proj:  67%|██████▋   | 24671/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.3.up_proj:  67%|██████▋   | 24672/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.3.down_proj:  67%|██████▋   | 24673/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.4.gate_proj:  67%|██████▋   | 24674/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.4.up_proj:  67%|██████▋   | 24675/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.4.down_proj:  67%|██████▋   | 24676/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.5.gate_proj:  67%|██████▋   | 24677/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.5.up_proj:  67%|██████▋   | 24678/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.5.down_proj:  67%|██████▋   | 24679/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.6.gate_proj:  67%|██████▋   | 24680/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.6.up_proj:  67%|██████▋   | 24681/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.6.down_proj:  67%|██████▋   | 24682/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.7.gate_proj:  68%|██████▊   | 24683/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.7.up_proj:  68%|██████▊   | 24684/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.7.down_proj:  68%|██████▊   | 24685/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.8.gate_proj:  68%|██████▊   | 24686/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.8.up_proj:  68%|██████▊   | 24687/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.8.down_proj:  68%|██████▊   | 24688/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.9.gate_proj:  68%|██████▊   | 24689/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.9.up_proj:  68%|██████▊   | 24690/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.9.down_proj:  68%|██████▊   | 24691/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.10.gate_proj:  68%|██████▊   | 24692/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.10.up_proj:  68%|██████▊   | 24693/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.10.down_proj:  68%|██████▊   | 24694/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.11.gate_proj:  68%|██████▊   | 24695/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.11.up_proj:  68%|██████▊   | 24696/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.11.down_proj:  68%|██████▊   | 24697/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.12.gate_proj:  68%|██████▊   | 24698/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.12.up_proj:  68%|██████▊   | 24699/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.12.down_proj:  68%|██████▊   | 24700/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.13.gate_proj:  68%|██████▊   | 24701/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.13.up_proj:  68%|██████▊   | 24702/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.13.down_proj:  68%|██████▊   | 24703/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.14.gate_proj:  68%|██████▊   | 24704/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.14.up_proj:  68%|██████▊   | 24705/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.14.down_proj:  68%|██████▊   | 24706/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.15.gate_proj:  68%|██████▊   | 24707/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.15.up_proj:  68%|██████▊   | 24708/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.15.down_proj:  68%|██████▊   | 24709/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.16.gate_proj:  68%|██████▊   | 24710/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.16.up_proj:  68%|██████▊   | 24711/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.16.down_proj:  68%|██████▊   | 24712/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.17.gate_proj:  68%|██████▊   | 24713/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.17.up_proj:  68%|██████▊   | 24714/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.17.down_proj:  68%|██████▊   | 24715/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.18.gate_proj:  68%|██████▊   | 24716/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.18.up_proj:  68%|██████▊   | 24717/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.18.down_proj:  68%|██████▊   | 24718/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.19.gate_proj:  68%|██████▊   | 24719/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.19.up_proj:  68%|██████▊   | 24720/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.19.down_proj:  68%|██████▊   | 24721/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.20.gate_proj:  68%|██████▊   | 24722/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.20.up_proj:  68%|██████▊   | 24723/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.20.down_proj:  68%|██████▊   | 24724/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.21.gate_proj:  68%|██████▊   | 24725/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.21.up_proj:  68%|██████▊   | 24726/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.21.down_proj:  68%|██████▊   | 24727/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.22.gate_proj:  68%|██████▊   | 24728/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.22.up_proj:  68%|██████▊   | 24729/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.22.down_proj:  68%|██████▊   | 24730/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.23.gate_proj:  68%|██████▊   | 24731/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.23.up_proj:  68%|██████▊   | 24732/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.23.down_proj:  68%|██████▊   | 24733/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.24.gate_proj:  68%|██████▊   | 24734/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.24.up_proj:  68%|██████▊   | 24735/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.24.down_proj:  68%|██████▊   | 24736/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.25.gate_proj:  68%|██████▊   | 24737/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.25.up_proj:  68%|██████▊   | 24738/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.25.down_proj:  68%|██████▊   | 24739/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.26.gate_proj:  68%|██████▊   | 24740/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.26.up_proj:  68%|██████▊   | 24741/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.26.down_proj:  68%|██████▊   | 24742/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.27.gate_proj:  68%|██████▊   | 24743/36566 [00:22<00:10, 1139.48it/s]
packing model.layers.63.mlp.experts.27.up_proj:  68%|██████▊   | 24744/36566 [00:22<00:10, 1139.48it/s]  
packing model.layers.63.mlp.experts.27.up_proj:  68%|██████▊   | 24745/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.27.down_proj:  68%|██████▊   | 24745/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.28.gate_proj:  68%|██████▊   | 24746/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.28.up_proj:  68%|██████▊   | 24747/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.28.down_proj:  68%|██████▊   | 24748/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.29.gate_proj:  68%|██████▊   | 24749/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.29.up_proj:  68%|██████▊   | 24750/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.29.down_proj:  68%|██████▊   | 24751/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.30.gate_proj:  68%|██████▊   | 24752/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.30.up_proj:  68%|██████▊   | 24753/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.30.down_proj:  68%|██████▊   | 24754/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.31.gate_proj:  68%|██████▊   | 24755/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.31.up_proj:  68%|██████▊   | 24756/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.31.down_proj:  68%|██████▊   | 24757/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.32.gate_proj:  68%|██████▊   | 24758/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.32.up_proj:  68%|██████▊   | 24759/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.32.down_proj:  68%|██████▊   | 24760/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.33.gate_proj:  68%|██████▊   | 24761/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.33.up_proj:  68%|██████▊   | 24762/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.33.down_proj:  68%|██████▊   | 24763/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.34.gate_proj:  68%|██████▊   | 24764/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.34.up_proj:  68%|██████▊   | 24765/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.34.down_proj:  68%|██████▊   | 24766/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.35.gate_proj:  68%|██████▊   | 24767/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.35.up_proj:  68%|██████▊   | 24768/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.35.down_proj:  68%|██████▊   | 24769/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.36.gate_proj:  68%|██████▊   | 24770/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.36.up_proj:  68%|██████▊   | 24771/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.36.down_proj:  68%|██████▊   | 24772/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.37.gate_proj:  68%|██████▊   | 24773/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.37.up_proj:  68%|██████▊   | 24774/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.37.down_proj:  68%|██████▊   | 24775/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.38.gate_proj:  68%|██████▊   | 24776/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.38.up_proj:  68%|██████▊   | 24777/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.38.down_proj:  68%|██████▊   | 24778/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.39.gate_proj:  68%|██████▊   | 24779/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.39.up_proj:  68%|██████▊   | 24780/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.39.down_proj:  68%|██████▊   | 24781/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.40.gate_proj:  68%|██████▊   | 24782/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.40.up_proj:  68%|██████▊   | 24783/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.40.down_proj:  68%|██████▊   | 24784/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.41.gate_proj:  68%|██████▊   | 24785/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.41.up_proj:  68%|██████▊   | 24786/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.41.down_proj:  68%|██████▊   | 24787/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.42.gate_proj:  68%|██████▊   | 24788/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.42.up_proj:  68%|██████▊   | 24789/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.42.down_proj:  68%|██████▊   | 24790/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.43.gate_proj:  68%|██████▊   | 24791/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.43.up_proj:  68%|██████▊   | 24792/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.43.down_proj:  68%|██████▊   | 24793/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.44.gate_proj:  68%|██████▊   | 24794/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.44.up_proj:  68%|██████▊   | 24795/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.44.down_proj:  68%|██████▊   | 24796/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.45.gate_proj:  68%|██████▊   | 24797/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.45.up_proj:  68%|██████▊   | 24798/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.45.down_proj:  68%|██████▊   | 24799/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.46.gate_proj:  68%|██████▊   | 24800/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.46.up_proj:  68%|██████▊   | 24801/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.46.down_proj:  68%|██████▊   | 24802/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.47.gate_proj:  68%|██████▊   | 24803/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.47.up_proj:  68%|██████▊   | 24804/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.47.down_proj:  68%|██████▊   | 24805/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.48.gate_proj:  68%|██████▊   | 24806/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.48.up_proj:  68%|██████▊   | 24807/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.48.down_proj:  68%|██████▊   | 24808/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.49.gate_proj:  68%|██████▊   | 24809/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.49.up_proj:  68%|██████▊   | 24810/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.49.down_proj:  68%|██████▊   | 24811/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.50.gate_proj:  68%|██████▊   | 24812/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.50.up_proj:  68%|██████▊   | 24813/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.50.down_proj:  68%|██████▊   | 24814/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.51.gate_proj:  68%|██████▊   | 24815/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.51.up_proj:  68%|██████▊   | 24816/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.51.down_proj:  68%|██████▊   | 24817/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.52.gate_proj:  68%|██████▊   | 24818/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.52.up_proj:  68%|██████▊   | 24819/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.52.down_proj:  68%|██████▊   | 24820/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.53.gate_proj:  68%|██████▊   | 24821/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.53.up_proj:  68%|██████▊   | 24822/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.53.down_proj:  68%|██████▊   | 24823/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.54.gate_proj:  68%|██████▊   | 24824/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.54.up_proj:  68%|██████▊   | 24825/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.54.down_proj:  68%|██████▊   | 24826/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.55.gate_proj:  68%|██████▊   | 24827/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.55.up_proj:  68%|██████▊   | 24828/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.55.down_proj:  68%|██████▊   | 24829/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.56.gate_proj:  68%|██████▊   | 24830/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.56.up_proj:  68%|██████▊   | 24831/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.56.down_proj:  68%|██████▊   | 24832/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.57.gate_proj:  68%|██████▊   | 24833/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.57.up_proj:  68%|██████▊   | 24834/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.57.down_proj:  68%|██████▊   | 24835/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.58.gate_proj:  68%|██████▊   | 24836/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.58.up_proj:  68%|██████▊   | 24837/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.58.down_proj:  68%|██████▊   | 24838/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.59.gate_proj:  68%|██████▊   | 24839/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.59.up_proj:  68%|██████▊   | 24840/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.59.down_proj:  68%|██████▊   | 24841/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.60.gate_proj:  68%|██████▊   | 24842/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.60.up_proj:  68%|██████▊   | 24843/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.60.down_proj:  68%|██████▊   | 24844/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.61.gate_proj:  68%|██████▊   | 24845/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.61.up_proj:  68%|██████▊   | 24846/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.61.down_proj:  68%|██████▊   | 24847/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.62.gate_proj:  68%|██████▊   | 24848/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.62.up_proj:  68%|██████▊   | 24849/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.62.down_proj:  68%|██████▊   | 24850/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.63.gate_proj:  68%|██████▊   | 24851/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.63.up_proj:  68%|██████▊   | 24852/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.63.down_proj:  68%|██████▊   | 24853/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.64.gate_proj:  68%|██████▊   | 24854/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.64.up_proj:  68%|██████▊   | 24855/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.64.down_proj:  68%|██████▊   | 24856/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.65.gate_proj:  68%|██████▊   | 24857/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.65.up_proj:  68%|██████▊   | 24858/36566 [00:22<00:10, 1141.47it/s]  
packing model.layers.63.mlp.experts.65.down_proj:  68%|██████▊   | 24859/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.66.gate_proj:  68%|██████▊   | 24860/36566 [00:22<00:10, 1141.47it/s]
packing model.layers.63.mlp.experts.66.gate_proj:  68%|██████▊   | 24861/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.66.up_proj:  68%|██████▊   | 24861/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.66.down_proj:  68%|██████▊   | 24862/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.67.gate_proj:  68%|██████▊   | 24863/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.67.up_proj:  68%|██████▊   | 24864/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.67.down_proj:  68%|██████▊   | 24865/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.68.gate_proj:  68%|██████▊   | 24866/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.68.up_proj:  68%|██████▊   | 24867/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.68.down_proj:  68%|██████▊   | 24868/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.69.gate_proj:  68%|██████▊   | 24869/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.69.up_proj:  68%|██████▊   | 24870/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.69.down_proj:  68%|██████▊   | 24871/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.70.gate_proj:  68%|██████▊   | 24872/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.70.up_proj:  68%|██████▊   | 24873/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.70.down_proj:  68%|██████▊   | 24874/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.71.gate_proj:  68%|██████▊   | 24875/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.71.up_proj:  68%|██████▊   | 24876/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.71.down_proj:  68%|██████▊   | 24877/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.72.gate_proj:  68%|██████▊   | 24878/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.72.up_proj:  68%|██████▊   | 24879/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.72.down_proj:  68%|██████▊   | 24880/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.73.gate_proj:  68%|██████▊   | 24881/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.73.up_proj:  68%|██████▊   | 24882/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.73.down_proj:  68%|██████▊   | 24883/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.74.gate_proj:  68%|██████▊   | 24884/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.74.up_proj:  68%|██████▊   | 24885/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.74.down_proj:  68%|██████▊   | 24886/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.75.gate_proj:  68%|██████▊   | 24887/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.75.up_proj:  68%|██████▊   | 24888/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.75.down_proj:  68%|██████▊   | 24889/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.76.gate_proj:  68%|██████▊   | 24890/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.76.up_proj:  68%|██████▊   | 24891/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.76.down_proj:  68%|██████▊   | 24892/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.77.gate_proj:  68%|██████▊   | 24893/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.77.up_proj:  68%|██████▊   | 24894/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.77.down_proj:  68%|██████▊   | 24895/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.78.gate_proj:  68%|██████▊   | 24896/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.78.up_proj:  68%|██████▊   | 24897/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.78.down_proj:  68%|██████▊   | 24898/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.79.gate_proj:  68%|██████▊   | 24899/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.79.up_proj:  68%|██████▊   | 24900/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.79.down_proj:  68%|██████▊   | 24901/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.80.gate_proj:  68%|██████▊   | 24902/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.80.up_proj:  68%|██████▊   | 24903/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.80.down_proj:  68%|██████▊   | 24904/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.81.gate_proj:  68%|██████▊   | 24905/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.81.up_proj:  68%|██████▊   | 24906/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.81.down_proj:  68%|██████▊   | 24907/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.82.gate_proj:  68%|██████▊   | 24908/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.82.up_proj:  68%|██████▊   | 24909/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.82.down_proj:  68%|██████▊   | 24910/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.83.gate_proj:  68%|██████▊   | 24911/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.83.up_proj:  68%|██████▊   | 24912/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.83.down_proj:  68%|██████▊   | 24913/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.84.gate_proj:  68%|██████▊   | 24914/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.84.up_proj:  68%|██████▊   | 24915/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.84.down_proj:  68%|██████▊   | 24916/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.85.gate_proj:  68%|██████▊   | 24917/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.85.up_proj:  68%|██████▊   | 24918/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.85.down_proj:  68%|██████▊   | 24919/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.86.gate_proj:  68%|██████▊   | 24920/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.86.up_proj:  68%|██████▊   | 24921/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.86.down_proj:  68%|██████▊   | 24922/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.87.gate_proj:  68%|██████▊   | 24923/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.87.up_proj:  68%|██████▊   | 24924/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.87.down_proj:  68%|██████▊   | 24925/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.88.gate_proj:  68%|██████▊   | 24926/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.88.up_proj:  68%|██████▊   | 24927/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.88.down_proj:  68%|██████▊   | 24928/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.89.gate_proj:  68%|██████▊   | 24929/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.89.up_proj:  68%|██████▊   | 24930/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.89.down_proj:  68%|██████▊   | 24931/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.90.gate_proj:  68%|██████▊   | 24932/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.90.up_proj:  68%|██████▊   | 24933/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.90.down_proj:  68%|██████▊   | 24934/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.91.gate_proj:  68%|██████▊   | 24935/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.91.up_proj:  68%|██████▊   | 24936/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.91.down_proj:  68%|██████▊   | 24937/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.92.gate_proj:  68%|██████▊   | 24938/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.92.up_proj:  68%|██████▊   | 24939/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.92.down_proj:  68%|██████▊   | 24940/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.93.gate_proj:  68%|██████▊   | 24941/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.93.up_proj:  68%|██████▊   | 24942/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.93.down_proj:  68%|██████▊   | 24943/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.94.gate_proj:  68%|██████▊   | 24944/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.94.up_proj:  68%|██████▊   | 24945/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.94.down_proj:  68%|██████▊   | 24946/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.95.gate_proj:  68%|██████▊   | 24947/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.95.up_proj:  68%|██████▊   | 24948/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.95.down_proj:  68%|██████▊   | 24949/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.96.gate_proj:  68%|██████▊   | 24950/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.96.up_proj:  68%|██████▊   | 24951/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.96.down_proj:  68%|██████▊   | 24952/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.97.gate_proj:  68%|██████▊   | 24953/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.97.up_proj:  68%|██████▊   | 24954/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.97.down_proj:  68%|██████▊   | 24955/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.98.gate_proj:  68%|██████▊   | 24956/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.98.up_proj:  68%|██████▊   | 24957/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.98.down_proj:  68%|██████▊   | 24958/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.99.gate_proj:  68%|██████▊   | 24959/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.99.up_proj:  68%|██████▊   | 24960/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.99.down_proj:  68%|██████▊   | 24961/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.100.gate_proj:  68%|██████▊   | 24962/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.100.up_proj:  68%|██████▊   | 24963/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.100.down_proj:  68%|██████▊   | 24964/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.101.gate_proj:  68%|██████▊   | 24965/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.101.up_proj:  68%|██████▊   | 24966/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.101.down_proj:  68%|██████▊   | 24967/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.102.gate_proj:  68%|██████▊   | 24968/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.102.up_proj:  68%|██████▊   | 24969/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.102.down_proj:  68%|██████▊   | 24970/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.103.gate_proj:  68%|██████▊   | 24971/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.103.up_proj:  68%|██████▊   | 24972/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.103.down_proj:  68%|██████▊   | 24973/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.104.gate_proj:  68%|██████▊   | 24974/36566 [00:22<00:10, 1144.92it/s]
packing model.layers.63.mlp.experts.104.up_proj:  68%|██████▊   | 24975/36566 [00:22<00:10, 1144.92it/s]  
packing model.layers.63.mlp.experts.104.up_proj:  68%|██████▊   | 24976/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.104.down_proj:  68%|██████▊   | 24976/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.105.gate_proj:  68%|██████▊   | 24977/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.105.up_proj:  68%|██████▊   | 24978/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.105.down_proj:  68%|██████▊   | 24979/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.106.gate_proj:  68%|██████▊   | 24980/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.106.up_proj:  68%|██████▊   | 24981/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.106.down_proj:  68%|██████▊   | 24982/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.107.gate_proj:  68%|██████▊   | 24983/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.107.up_proj:  68%|██████▊   | 24984/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.107.down_proj:  68%|██████▊   | 24985/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.108.gate_proj:  68%|██████▊   | 24986/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.108.up_proj:  68%|██████▊   | 24987/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.108.down_proj:  68%|██████▊   | 24988/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.109.gate_proj:  68%|██████▊   | 24989/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.109.up_proj:  68%|██████▊   | 24990/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.109.down_proj:  68%|██████▊   | 24991/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.110.gate_proj:  68%|██████▊   | 24992/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.110.up_proj:  68%|██████▊   | 24993/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.110.down_proj:  68%|██████▊   | 24994/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.111.gate_proj:  68%|██████▊   | 24995/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.111.up_proj:  68%|██████▊   | 24996/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.111.down_proj:  68%|██████▊   | 24997/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.112.gate_proj:  68%|██████▊   | 24998/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.112.up_proj:  68%|██████▊   | 24999/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.112.down_proj:  68%|██████▊   | 25000/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.113.gate_proj:  68%|██████▊   | 25001/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.113.up_proj:  68%|██████▊   | 25002/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.113.down_proj:  68%|██████▊   | 25003/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.114.gate_proj:  68%|██████▊   | 25004/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.114.up_proj:  68%|██████▊   | 25005/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.114.down_proj:  68%|██████▊   | 25006/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.115.gate_proj:  68%|██████▊   | 25007/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.115.up_proj:  68%|██████▊   | 25008/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.115.down_proj:  68%|██████▊   | 25009/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.116.gate_proj:  68%|██████▊   | 25010/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.116.up_proj:  68%|██████▊   | 25011/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.116.down_proj:  68%|██████▊   | 25012/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.117.gate_proj:  68%|██████▊   | 25013/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.117.up_proj:  68%|██████▊   | 25014/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.117.down_proj:  68%|██████▊   | 25015/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.118.gate_proj:  68%|██████▊   | 25016/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.118.up_proj:  68%|██████▊   | 25017/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.118.down_proj:  68%|██████▊   | 25018/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.119.gate_proj:  68%|██████▊   | 25019/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.119.up_proj:  68%|██████▊   | 25020/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.119.down_proj:  68%|██████▊   | 25021/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.120.gate_proj:  68%|██████▊   | 25022/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.120.up_proj:  68%|██████▊   | 25023/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.120.down_proj:  68%|██████▊   | 25024/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.121.gate_proj:  68%|██████▊   | 25025/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.121.up_proj:  68%|██████▊   | 25026/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.121.down_proj:  68%|██████▊   | 25027/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.122.gate_proj:  68%|██████▊   | 25028/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.122.up_proj:  68%|██████▊   | 25029/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.122.down_proj:  68%|██████▊   | 25030/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.123.gate_proj:  68%|██████▊   | 25031/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.123.up_proj:  68%|██████▊   | 25032/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.123.down_proj:  68%|██████▊   | 25033/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.124.gate_proj:  68%|██████▊   | 25034/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.124.up_proj:  68%|██████▊   | 25035/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.124.down_proj:  68%|██████▊   | 25036/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.125.gate_proj:  68%|██████▊   | 25037/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.125.up_proj:  68%|██████▊   | 25038/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.125.down_proj:  68%|██████▊   | 25039/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.126.gate_proj:  68%|██████▊   | 25040/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.126.up_proj:  68%|██████▊   | 25041/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.126.down_proj:  68%|██████▊   | 25042/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.127.gate_proj:  68%|██████▊   | 25043/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.63.mlp.experts.127.up_proj:  68%|██████▊   | 25044/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.63.mlp.experts.127.down_proj:  68%|██████▊   | 25045/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.0.gate_proj:  68%|██████▊   | 25046/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.0.up_proj:  68%|██████▊   | 25047/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.0.down_proj:  69%|██████▊   | 25048/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.1.gate_proj:  69%|██████▊   | 25049/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.1.up_proj:  69%|██████▊   | 25050/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.1.down_proj:  69%|██████▊   | 25051/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.2.gate_proj:  69%|██████▊   | 25052/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.2.up_proj:  69%|██████▊   | 25053/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.2.down_proj:  69%|██████▊   | 25054/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.3.gate_proj:  69%|██████▊   | 25055/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.3.up_proj:  69%|██████▊   | 25056/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.3.down_proj:  69%|██████▊   | 25057/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.4.gate_proj:  69%|██████▊   | 25058/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.4.up_proj:  69%|██████▊   | 25059/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.4.down_proj:  69%|██████▊   | 25060/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.5.gate_proj:  69%|██████▊   | 25061/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.5.up_proj:  69%|██████▊   | 25062/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.5.down_proj:  69%|██████▊   | 25063/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.6.gate_proj:  69%|██████▊   | 25064/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.6.up_proj:  69%|██████▊   | 25065/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.6.down_proj:  69%|██████▊   | 25066/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.7.gate_proj:  69%|██████▊   | 25067/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.7.up_proj:  69%|██████▊   | 25068/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.7.down_proj:  69%|██████▊   | 25069/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.8.gate_proj:  69%|██████▊   | 25070/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.8.up_proj:  69%|██████▊   | 25071/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.8.down_proj:  69%|██████▊   | 25072/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.9.gate_proj:  69%|██████▊   | 25073/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.9.up_proj:  69%|██████▊   | 25074/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.9.down_proj:  69%|██████▊   | 25075/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.10.gate_proj:  69%|██████▊   | 25076/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.10.up_proj:  69%|██████▊   | 25077/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.10.down_proj:  69%|██████▊   | 25078/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.11.gate_proj:  69%|██████▊   | 25079/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.11.up_proj:  69%|██████▊   | 25080/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.11.down_proj:  69%|██████▊   | 25081/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.12.gate_proj:  69%|██████▊   | 25082/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.12.up_proj:  69%|██████▊   | 25083/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.12.down_proj:  69%|██████▊   | 25084/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.13.gate_proj:  69%|██████▊   | 25085/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.13.up_proj:  69%|██████▊   | 25086/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.13.down_proj:  69%|██████▊   | 25087/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.14.gate_proj:  69%|██████▊   | 25088/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.14.up_proj:  69%|██████▊   | 25089/36566 [00:22<00:10, 1146.41it/s]  
packing model.layers.64.mlp.experts.14.down_proj:  69%|██████▊   | 25090/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.15.gate_proj:  69%|██████▊   | 25091/36566 [00:22<00:10, 1146.41it/s]
packing model.layers.64.mlp.experts.15.gate_proj:  69%|██████▊   | 25092/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.15.up_proj:  69%|██████▊   | 25092/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.15.down_proj:  69%|██████▊   | 25093/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.16.gate_proj:  69%|██████▊   | 25094/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.16.up_proj:  69%|██████▊   | 25095/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.16.down_proj:  69%|██████▊   | 25096/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.17.gate_proj:  69%|██████▊   | 25097/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.17.up_proj:  69%|██████▊   | 25098/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.17.down_proj:  69%|██████▊   | 25099/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.18.gate_proj:  69%|██████▊   | 25100/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.18.up_proj:  69%|██████▊   | 25101/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.18.down_proj:  69%|██████▊   | 25102/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.19.gate_proj:  69%|██████▊   | 25103/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.19.up_proj:  69%|██████▊   | 25104/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.19.down_proj:  69%|██████▊   | 25105/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.20.gate_proj:  69%|██████▊   | 25106/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.20.up_proj:  69%|██████▊   | 25107/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.20.down_proj:  69%|██████▊   | 25108/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.21.gate_proj:  69%|██████▊   | 25109/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.21.up_proj:  69%|██████▊   | 25110/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.21.down_proj:  69%|██████▊   | 25111/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.22.gate_proj:  69%|██████▊   | 25112/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.22.up_proj:  69%|██████▊   | 25113/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.22.down_proj:  69%|██████▊   | 25114/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.23.gate_proj:  69%|██████▊   | 25115/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.23.up_proj:  69%|██████▊   | 25116/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.23.down_proj:  69%|██████▊   | 25117/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.24.gate_proj:  69%|██████▊   | 25118/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.24.up_proj:  69%|██████▊   | 25119/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.24.down_proj:  69%|██████▊   | 25120/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.25.gate_proj:  69%|██████▊   | 25121/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.25.up_proj:  69%|██████▊   | 25122/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.25.down_proj:  69%|██████▊   | 25123/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.26.gate_proj:  69%|██████▊   | 25124/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.26.up_proj:  69%|██████▊   | 25125/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.26.down_proj:  69%|██████▊   | 25126/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.27.gate_proj:  69%|██████▊   | 25127/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.27.up_proj:  69%|██████▊   | 25128/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.27.down_proj:  69%|██████▊   | 25129/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.28.gate_proj:  69%|██████▊   | 25130/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.28.up_proj:  69%|██████▊   | 25131/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.28.down_proj:  69%|██████▊   | 25132/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.29.gate_proj:  69%|██████▊   | 25133/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.29.up_proj:  69%|██████▊   | 25134/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.29.down_proj:  69%|██████▊   | 25135/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.30.gate_proj:  69%|██████▊   | 25136/36566 [00:22<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.30.up_proj:  69%|██████▊   | 25137/36566 [00:22<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.30.down_proj:  69%|██████▊   | 25138/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.31.gate_proj:  69%|██████▊   | 25139/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.31.up_proj:  69%|██████▉   | 25140/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.31.down_proj:  69%|██████▉   | 25141/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.32.gate_proj:  69%|██████▉   | 25142/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.32.up_proj:  69%|██████▉   | 25143/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.32.down_proj:  69%|██████▉   | 25144/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.33.gate_proj:  69%|██████▉   | 25145/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.33.up_proj:  69%|██████▉   | 25146/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.33.down_proj:  69%|██████▉   | 25147/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.34.gate_proj:  69%|██████▉   | 25148/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.34.up_proj:  69%|██████▉   | 25149/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.34.down_proj:  69%|██████▉   | 25150/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.35.gate_proj:  69%|██████▉   | 25151/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.35.up_proj:  69%|██████▉   | 25152/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.35.down_proj:  69%|██████▉   | 25153/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.36.gate_proj:  69%|██████▉   | 25154/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.36.up_proj:  69%|██████▉   | 25155/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.36.down_proj:  69%|██████▉   | 25156/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.37.gate_proj:  69%|██████▉   | 25157/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.37.up_proj:  69%|██████▉   | 25158/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.37.down_proj:  69%|██████▉   | 25159/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.38.gate_proj:  69%|██████▉   | 25160/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.38.up_proj:  69%|██████▉   | 25161/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.38.down_proj:  69%|██████▉   | 25162/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.39.gate_proj:  69%|██████▉   | 25163/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.39.up_proj:  69%|██████▉   | 25164/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.39.down_proj:  69%|██████▉   | 25165/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.40.gate_proj:  69%|██████▉   | 25166/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.40.up_proj:  69%|██████▉   | 25167/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.40.down_proj:  69%|██████▉   | 25168/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.41.gate_proj:  69%|██████▉   | 25169/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.41.up_proj:  69%|██████▉   | 25170/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.41.down_proj:  69%|██████▉   | 25171/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.42.gate_proj:  69%|██████▉   | 25172/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.42.up_proj:  69%|██████▉   | 25173/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.42.down_proj:  69%|██████▉   | 25174/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.43.gate_proj:  69%|██████▉   | 25175/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.43.up_proj:  69%|██████▉   | 25176/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.43.down_proj:  69%|██████▉   | 25177/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.44.gate_proj:  69%|██████▉   | 25178/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.44.up_proj:  69%|██████▉   | 25179/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.44.down_proj:  69%|██████▉   | 25180/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.45.gate_proj:  69%|██████▉   | 25181/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.45.up_proj:  69%|██████▉   | 25182/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.45.down_proj:  69%|██████▉   | 25183/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.46.gate_proj:  69%|██████▉   | 25184/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.46.up_proj:  69%|██████▉   | 25185/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.46.down_proj:  69%|██████▉   | 25186/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.47.gate_proj:  69%|██████▉   | 25187/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.47.up_proj:  69%|██████▉   | 25188/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.47.down_proj:  69%|██████▉   | 25189/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.48.gate_proj:  69%|██████▉   | 25190/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.48.up_proj:  69%|██████▉   | 25191/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.48.down_proj:  69%|██████▉   | 25192/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.49.gate_proj:  69%|██████▉   | 25193/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.49.up_proj:  69%|██████▉   | 25194/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.49.down_proj:  69%|██████▉   | 25195/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.50.gate_proj:  69%|██████▉   | 25196/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.50.up_proj:  69%|██████▉   | 25197/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.50.down_proj:  69%|██████▉   | 25198/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.51.gate_proj:  69%|██████▉   | 25199/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.51.up_proj:  69%|██████▉   | 25200/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.51.down_proj:  69%|██████▉   | 25201/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.52.gate_proj:  69%|██████▉   | 25202/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.52.up_proj:  69%|██████▉   | 25203/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.52.down_proj:  69%|██████▉   | 25204/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.53.gate_proj:  69%|██████▉   | 25205/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.53.up_proj:  69%|██████▉   | 25206/36566 [00:23<00:09, 1147.74it/s]  
packing model.layers.64.mlp.experts.53.down_proj:  69%|██████▉   | 25207/36566 [00:23<00:09, 1147.74it/s]
packing model.layers.64.mlp.experts.53.down_proj:  69%|██████▉   | 25208/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.54.gate_proj:  69%|██████▉   | 25208/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.54.up_proj:  69%|██████▉   | 25209/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.54.down_proj:  69%|██████▉   | 25210/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.55.gate_proj:  69%|██████▉   | 25211/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.55.up_proj:  69%|██████▉   | 25212/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.55.down_proj:  69%|██████▉   | 25213/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.56.gate_proj:  69%|██████▉   | 25214/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.56.up_proj:  69%|██████▉   | 25215/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.56.down_proj:  69%|██████▉   | 25216/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.57.gate_proj:  69%|██████▉   | 25217/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.57.up_proj:  69%|██████▉   | 25218/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.57.down_proj:  69%|██████▉   | 25219/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.58.gate_proj:  69%|██████▉   | 25220/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.58.up_proj:  69%|██████▉   | 25221/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.58.down_proj:  69%|██████▉   | 25222/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.59.gate_proj:  69%|██████▉   | 25223/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.59.up_proj:  69%|██████▉   | 25224/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.59.down_proj:  69%|██████▉   | 25225/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.60.gate_proj:  69%|██████▉   | 25226/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.60.up_proj:  69%|██████▉   | 25227/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.60.down_proj:  69%|██████▉   | 25228/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.61.gate_proj:  69%|██████▉   | 25229/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.61.up_proj:  69%|██████▉   | 25230/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.61.down_proj:  69%|██████▉   | 25231/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.62.gate_proj:  69%|██████▉   | 25232/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.62.up_proj:  69%|██████▉   | 25233/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.62.down_proj:  69%|██████▉   | 25234/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.63.gate_proj:  69%|██████▉   | 25235/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.63.up_proj:  69%|██████▉   | 25236/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.63.down_proj:  69%|██████▉   | 25237/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.64.gate_proj:  69%|██████▉   | 25238/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.64.up_proj:  69%|██████▉   | 25239/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.64.down_proj:  69%|██████▉   | 25240/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.65.gate_proj:  69%|██████▉   | 25241/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.65.up_proj:  69%|██████▉   | 25242/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.65.down_proj:  69%|██████▉   | 25243/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.66.gate_proj:  69%|██████▉   | 25244/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.66.up_proj:  69%|██████▉   | 25245/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.66.down_proj:  69%|██████▉   | 25246/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.67.gate_proj:  69%|██████▉   | 25247/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.67.up_proj:  69%|██████▉   | 25248/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.67.down_proj:  69%|██████▉   | 25249/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.68.gate_proj:  69%|██████▉   | 25250/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.68.up_proj:  69%|██████▉   | 25251/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.68.down_proj:  69%|██████▉   | 25252/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.69.gate_proj:  69%|██████▉   | 25253/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.69.up_proj:  69%|██████▉   | 25254/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.69.down_proj:  69%|██████▉   | 25255/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.70.gate_proj:  69%|██████▉   | 25256/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.70.up_proj:  69%|██████▉   | 25257/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.70.down_proj:  69%|██████▉   | 25258/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.71.gate_proj:  69%|██████▉   | 25259/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.71.up_proj:  69%|██████▉   | 25260/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.71.down_proj:  69%|██████▉   | 25261/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.72.gate_proj:  69%|██████▉   | 25262/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.72.up_proj:  69%|██████▉   | 25263/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.72.down_proj:  69%|██████▉   | 25264/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.73.gate_proj:  69%|██████▉   | 25265/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.73.up_proj:  69%|██████▉   | 25266/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.73.down_proj:  69%|██████▉   | 25267/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.74.gate_proj:  69%|██████▉   | 25268/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.74.up_proj:  69%|██████▉   | 25269/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.74.down_proj:  69%|██████▉   | 25270/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.75.gate_proj:  69%|██████▉   | 25271/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.75.up_proj:  69%|██████▉   | 25272/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.75.down_proj:  69%|██████▉   | 25273/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.76.gate_proj:  69%|██████▉   | 25274/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.76.up_proj:  69%|██████▉   | 25275/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.76.down_proj:  69%|██████▉   | 25276/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.77.gate_proj:  69%|██████▉   | 25277/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.77.up_proj:  69%|██████▉   | 25278/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.77.down_proj:  69%|██████▉   | 25279/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.78.gate_proj:  69%|██████▉   | 25280/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.78.up_proj:  69%|██████▉   | 25281/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.78.down_proj:  69%|██████▉   | 25282/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.79.gate_proj:  69%|██████▉   | 25283/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.79.up_proj:  69%|██████▉   | 25284/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.79.down_proj:  69%|██████▉   | 25285/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.80.gate_proj:  69%|██████▉   | 25286/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.80.up_proj:  69%|██████▉   | 25287/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.80.down_proj:  69%|██████▉   | 25288/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.81.gate_proj:  69%|██████▉   | 25289/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.81.up_proj:  69%|██████▉   | 25290/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.81.down_proj:  69%|██████▉   | 25291/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.82.gate_proj:  69%|██████▉   | 25292/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.82.up_proj:  69%|██████▉   | 25293/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.82.down_proj:  69%|██████▉   | 25294/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.83.gate_proj:  69%|██████▉   | 25295/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.83.up_proj:  69%|██████▉   | 25296/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.83.down_proj:  69%|██████▉   | 25297/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.84.gate_proj:  69%|██████▉   | 25298/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.84.up_proj:  69%|██████▉   | 25299/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.84.down_proj:  69%|██████▉   | 25300/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.85.gate_proj:  69%|██████▉   | 25301/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.85.up_proj:  69%|██████▉   | 25302/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.85.down_proj:  69%|██████▉   | 25303/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.86.gate_proj:  69%|██████▉   | 25304/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.86.up_proj:  69%|██████▉   | 25305/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.86.down_proj:  69%|██████▉   | 25306/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.87.gate_proj:  69%|██████▉   | 25307/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.87.up_proj:  69%|██████▉   | 25308/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.87.down_proj:  69%|██████▉   | 25309/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.88.gate_proj:  69%|██████▉   | 25310/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.88.up_proj:  69%|██████▉   | 25311/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.88.down_proj:  69%|██████▉   | 25312/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.89.gate_proj:  69%|██████▉   | 25313/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.89.up_proj:  69%|██████▉   | 25314/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.89.down_proj:  69%|██████▉   | 25315/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.90.gate_proj:  69%|██████▉   | 25316/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.90.up_proj:  69%|██████▉   | 25317/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.90.down_proj:  69%|██████▉   | 25318/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.91.gate_proj:  69%|██████▉   | 25319/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.91.up_proj:  69%|██████▉   | 25320/36566 [00:23<00:09, 1149.00it/s]  
packing model.layers.64.mlp.experts.91.down_proj:  69%|██████▉   | 25321/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.92.gate_proj:  69%|██████▉   | 25322/36566 [00:23<00:09, 1149.00it/s]
packing model.layers.64.mlp.experts.92.gate_proj:  69%|██████▉   | 25323/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.92.up_proj:  69%|██████▉   | 25323/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.92.down_proj:  69%|██████▉   | 25324/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.93.gate_proj:  69%|██████▉   | 25325/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.93.up_proj:  69%|██████▉   | 25326/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.93.down_proj:  69%|██████▉   | 25327/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.94.gate_proj:  69%|██████▉   | 25328/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.94.up_proj:  69%|██████▉   | 25329/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.94.down_proj:  69%|██████▉   | 25330/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.95.gate_proj:  69%|██████▉   | 25331/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.95.up_proj:  69%|██████▉   | 25332/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.95.down_proj:  69%|██████▉   | 25333/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.96.gate_proj:  69%|██████▉   | 25334/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.96.up_proj:  69%|██████▉   | 25335/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.96.down_proj:  69%|██████▉   | 25336/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.97.gate_proj:  69%|██████▉   | 25337/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.97.up_proj:  69%|██████▉   | 25338/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.97.down_proj:  69%|██████▉   | 25339/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.98.gate_proj:  69%|██████▉   | 25340/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.98.up_proj:  69%|██████▉   | 25341/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.98.down_proj:  69%|██████▉   | 25342/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.99.gate_proj:  69%|██████▉   | 25343/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.99.up_proj:  69%|██████▉   | 25344/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.99.down_proj:  69%|██████▉   | 25345/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.100.gate_proj:  69%|██████▉   | 25346/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.100.up_proj:  69%|██████▉   | 25347/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.100.down_proj:  69%|██████▉   | 25348/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.101.gate_proj:  69%|██████▉   | 25349/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.101.up_proj:  69%|██████▉   | 25350/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.101.down_proj:  69%|██████▉   | 25351/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.102.gate_proj:  69%|██████▉   | 25352/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.102.up_proj:  69%|██████▉   | 25353/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.102.down_proj:  69%|██████▉   | 25354/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.103.gate_proj:  69%|██████▉   | 25355/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.103.up_proj:  69%|██████▉   | 25356/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.103.down_proj:  69%|██████▉   | 25357/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.104.gate_proj:  69%|██████▉   | 25358/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.104.up_proj:  69%|██████▉   | 25359/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.104.down_proj:  69%|██████▉   | 25360/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.105.gate_proj:  69%|██████▉   | 25361/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.105.up_proj:  69%|██████▉   | 25362/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.105.down_proj:  69%|██████▉   | 25363/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.106.gate_proj:  69%|██████▉   | 25364/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.106.up_proj:  69%|██████▉   | 25365/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.106.down_proj:  69%|██████▉   | 25366/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.107.gate_proj:  69%|██████▉   | 25367/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.107.up_proj:  69%|██████▉   | 25368/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.107.down_proj:  69%|██████▉   | 25369/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.108.gate_proj:  69%|██████▉   | 25370/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.108.up_proj:  69%|██████▉   | 25371/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.108.down_proj:  69%|██████▉   | 25372/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.109.gate_proj:  69%|██████▉   | 25373/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.109.up_proj:  69%|██████▉   | 25374/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.109.down_proj:  69%|██████▉   | 25375/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.110.gate_proj:  69%|██████▉   | 25376/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.110.up_proj:  69%|██████▉   | 25377/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.110.down_proj:  69%|██████▉   | 25378/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.111.gate_proj:  69%|██████▉   | 25379/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.111.up_proj:  69%|██████▉   | 25380/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.111.down_proj:  69%|██████▉   | 25381/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.112.gate_proj:  69%|██████▉   | 25382/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.112.up_proj:  69%|██████▉   | 25383/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.112.down_proj:  69%|██████▉   | 25384/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.113.gate_proj:  69%|██████▉   | 25385/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.113.up_proj:  69%|██████▉   | 25386/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.113.down_proj:  69%|██████▉   | 25387/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.114.gate_proj:  69%|██████▉   | 25388/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.114.up_proj:  69%|██████▉   | 25389/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.114.down_proj:  69%|██████▉   | 25390/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.115.gate_proj:  69%|██████▉   | 25391/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.115.up_proj:  69%|██████▉   | 25392/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.115.down_proj:  69%|██████▉   | 25393/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.116.gate_proj:  69%|██████▉   | 25394/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.116.up_proj:  69%|██████▉   | 25395/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.116.down_proj:  69%|██████▉   | 25396/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.117.gate_proj:  69%|██████▉   | 25397/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.117.up_proj:  69%|██████▉   | 25398/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.117.down_proj:  69%|██████▉   | 25399/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.118.gate_proj:  69%|██████▉   | 25400/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.118.up_proj:  69%|██████▉   | 25401/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.118.down_proj:  69%|██████▉   | 25402/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.119.gate_proj:  69%|██████▉   | 25403/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.119.up_proj:  69%|██████▉   | 25404/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.119.down_proj:  69%|██████▉   | 25405/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.120.gate_proj:  69%|██████▉   | 25406/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.120.up_proj:  69%|██████▉   | 25407/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.120.down_proj:  69%|██████▉   | 25408/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.121.gate_proj:  69%|██████▉   | 25409/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.121.up_proj:  69%|██████▉   | 25410/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.121.down_proj:  69%|██████▉   | 25411/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.122.gate_proj:  69%|██████▉   | 25412/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.122.up_proj:  69%|██████▉   | 25413/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.122.down_proj:  70%|██████▉   | 25414/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.123.gate_proj:  70%|██████▉   | 25415/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.123.up_proj:  70%|██████▉   | 25416/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.123.down_proj:  70%|██████▉   | 25417/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.124.gate_proj:  70%|██████▉   | 25418/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.124.up_proj:  70%|██████▉   | 25419/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.124.down_proj:  70%|██████▉   | 25420/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.125.gate_proj:  70%|██████▉   | 25421/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.125.up_proj:  70%|██████▉   | 25422/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.125.down_proj:  70%|██████▉   | 25423/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.126.gate_proj:  70%|██████▉   | 25424/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.126.up_proj:  70%|██████▉   | 25425/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.126.down_proj:  70%|██████▉   | 25426/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.127.gate_proj:  70%|██████▉   | 25427/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.64.mlp.experts.127.up_proj:  70%|██████▉   | 25428/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.64.mlp.experts.127.down_proj:  70%|██████▉   | 25429/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.0.gate_proj:  70%|██████▉   | 25430/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.0.up_proj:  70%|██████▉   | 25431/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.0.down_proj:  70%|██████▉   | 25432/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.1.gate_proj:  70%|██████▉   | 25433/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.1.up_proj:  70%|██████▉   | 25434/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.1.down_proj:  70%|██████▉   | 25435/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.2.gate_proj:  70%|██████▉   | 25436/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.2.up_proj:  70%|██████▉   | 25437/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.2.up_proj:  70%|██████▉   | 25438/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.2.down_proj:  70%|██████▉   | 25438/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.3.gate_proj:  70%|██████▉   | 25439/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.3.up_proj:  70%|██████▉   | 25440/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.3.down_proj:  70%|██████▉   | 25441/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.4.gate_proj:  70%|██████▉   | 25442/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.4.up_proj:  70%|██████▉   | 25443/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.4.down_proj:  70%|██████▉   | 25444/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.5.gate_proj:  70%|██████▉   | 25445/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.5.up_proj:  70%|██████▉   | 25446/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.5.down_proj:  70%|██████▉   | 25447/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.6.gate_proj:  70%|██████▉   | 25448/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.6.up_proj:  70%|██████▉   | 25449/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.6.down_proj:  70%|██████▉   | 25450/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.7.gate_proj:  70%|██████▉   | 25451/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.7.up_proj:  70%|██████▉   | 25452/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.7.down_proj:  70%|██████▉   | 25453/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.8.gate_proj:  70%|██████▉   | 25454/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.8.up_proj:  70%|██████▉   | 25455/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.8.down_proj:  70%|██████▉   | 25456/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.9.gate_proj:  70%|██████▉   | 25457/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.9.up_proj:  70%|██████▉   | 25458/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.9.down_proj:  70%|██████▉   | 25459/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.10.gate_proj:  70%|██████▉   | 25460/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.10.up_proj:  70%|██████▉   | 25461/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.10.down_proj:  70%|██████▉   | 25462/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.11.gate_proj:  70%|██████▉   | 25463/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.11.up_proj:  70%|██████▉   | 25464/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.11.down_proj:  70%|██████▉   | 25465/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.12.gate_proj:  70%|██████▉   | 25466/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.12.up_proj:  70%|██████▉   | 25467/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.12.down_proj:  70%|██████▉   | 25468/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.13.gate_proj:  70%|██████▉   | 25469/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.13.up_proj:  70%|██████▉   | 25470/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.13.down_proj:  70%|██████▉   | 25471/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.14.gate_proj:  70%|██████▉   | 25472/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.14.up_proj:  70%|██████▉   | 25473/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.14.down_proj:  70%|██████▉   | 25474/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.15.gate_proj:  70%|██████▉   | 25475/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.15.up_proj:  70%|██████▉   | 25476/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.15.down_proj:  70%|██████▉   | 25477/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.16.gate_proj:  70%|██████▉   | 25478/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.16.up_proj:  70%|██████▉   | 25479/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.16.down_proj:  70%|██████▉   | 25480/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.17.gate_proj:  70%|██████▉   | 25481/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.17.up_proj:  70%|██████▉   | 25482/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.17.down_proj:  70%|██████▉   | 25483/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.18.gate_proj:  70%|██████▉   | 25484/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.18.up_proj:  70%|██████▉   | 25485/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.18.down_proj:  70%|██████▉   | 25486/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.19.gate_proj:  70%|██████▉   | 25487/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.19.up_proj:  70%|██████▉   | 25488/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.19.down_proj:  70%|██████▉   | 25489/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.20.gate_proj:  70%|██████▉   | 25490/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.20.up_proj:  70%|██████▉   | 25491/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.20.down_proj:  70%|██████▉   | 25492/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.21.gate_proj:  70%|██████▉   | 25493/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.21.up_proj:  70%|██████▉   | 25494/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.21.down_proj:  70%|██████▉   | 25495/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.22.gate_proj:  70%|██████▉   | 25496/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.22.up_proj:  70%|██████▉   | 25497/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.22.down_proj:  70%|██████▉   | 25498/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.23.gate_proj:  70%|██████▉   | 25499/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.23.up_proj:  70%|██████▉   | 25500/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.23.down_proj:  70%|██████▉   | 25501/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.24.gate_proj:  70%|██████▉   | 25502/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.24.up_proj:  70%|██████▉   | 25503/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.24.down_proj:  70%|██████▉   | 25504/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.25.gate_proj:  70%|██████▉   | 25505/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.25.up_proj:  70%|██████▉   | 25506/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.25.down_proj:  70%|██████▉   | 25507/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.26.gate_proj:  70%|██████▉   | 25508/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.26.up_proj:  70%|██████▉   | 25509/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.26.down_proj:  70%|██████▉   | 25510/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.27.gate_proj:  70%|██████▉   | 25511/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.27.up_proj:  70%|██████▉   | 25512/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.27.down_proj:  70%|██████▉   | 25513/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.28.gate_proj:  70%|██████▉   | 25514/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.28.up_proj:  70%|██████▉   | 25515/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.28.down_proj:  70%|██████▉   | 25516/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.29.gate_proj:  70%|██████▉   | 25517/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.29.up_proj:  70%|██████▉   | 25518/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.29.down_proj:  70%|██████▉   | 25519/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.30.gate_proj:  70%|██████▉   | 25520/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.30.up_proj:  70%|██████▉   | 25521/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.30.down_proj:  70%|██████▉   | 25522/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.31.gate_proj:  70%|██████▉   | 25523/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.31.up_proj:  70%|██████▉   | 25524/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.31.down_proj:  70%|██████▉   | 25525/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.32.gate_proj:  70%|██████▉   | 25526/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.32.up_proj:  70%|██████▉   | 25527/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.32.down_proj:  70%|██████▉   | 25528/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.33.gate_proj:  70%|██████▉   | 25529/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.33.up_proj:  70%|██████▉   | 25530/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.33.down_proj:  70%|██████▉   | 25531/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.34.gate_proj:  70%|██████▉   | 25532/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.34.up_proj:  70%|██████▉   | 25533/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.34.down_proj:  70%|██████▉   | 25534/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.35.gate_proj:  70%|██████▉   | 25535/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.35.up_proj:  70%|██████▉   | 25536/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.35.down_proj:  70%|██████▉   | 25537/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.36.gate_proj:  70%|██████▉   | 25538/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.36.up_proj:  70%|██████▉   | 25539/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.36.down_proj:  70%|██████▉   | 25540/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.37.gate_proj:  70%|██████▉   | 25541/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.37.up_proj:  70%|██████▉   | 25542/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.37.down_proj:  70%|██████▉   | 25543/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.38.gate_proj:  70%|██████▉   | 25544/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.38.up_proj:  70%|██████▉   | 25545/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.38.down_proj:  70%|██████▉   | 25546/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.39.gate_proj:  70%|██████▉   | 25547/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.39.up_proj:  70%|██████▉   | 25548/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.39.down_proj:  70%|██████▉   | 25549/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.40.gate_proj:  70%|██████▉   | 25550/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.40.up_proj:  70%|██████▉   | 25551/36566 [00:23<00:09, 1144.98it/s]  
packing model.layers.65.mlp.experts.40.down_proj:  70%|██████▉   | 25552/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.41.gate_proj:  70%|██████▉   | 25553/36566 [00:23<00:09, 1144.98it/s]
packing model.layers.65.mlp.experts.41.gate_proj:  70%|██████▉   | 25554/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.41.up_proj:  70%|██████▉   | 25554/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.41.down_proj:  70%|██████▉   | 25555/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.42.gate_proj:  70%|██████▉   | 25556/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.42.up_proj:  70%|██████▉   | 25557/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.42.down_proj:  70%|██████▉   | 25558/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.43.gate_proj:  70%|██████▉   | 25559/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.43.up_proj:  70%|██████▉   | 25560/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.43.down_proj:  70%|██████▉   | 25561/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.44.gate_proj:  70%|██████▉   | 25562/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.44.up_proj:  70%|██████▉   | 25563/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.44.down_proj:  70%|██████▉   | 25564/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.45.gate_proj:  70%|██████▉   | 25565/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.45.up_proj:  70%|██████▉   | 25566/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.45.down_proj:  70%|██████▉   | 25567/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.46.gate_proj:  70%|██████▉   | 25568/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.46.up_proj:  70%|██████▉   | 25569/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.46.down_proj:  70%|██████▉   | 25570/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.47.gate_proj:  70%|██████▉   | 25571/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.47.up_proj:  70%|██████▉   | 25572/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.47.down_proj:  70%|██████▉   | 25573/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.48.gate_proj:  70%|██████▉   | 25574/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.48.up_proj:  70%|██████▉   | 25575/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.48.down_proj:  70%|██████▉   | 25576/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.49.gate_proj:  70%|██████▉   | 25577/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.49.up_proj:  70%|██████▉   | 25578/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.49.down_proj:  70%|██████▉   | 25579/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.50.gate_proj:  70%|██████▉   | 25580/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.50.up_proj:  70%|██████▉   | 25581/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.50.down_proj:  70%|██████▉   | 25582/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.51.gate_proj:  70%|██████▉   | 25583/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.51.up_proj:  70%|██████▉   | 25584/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.51.down_proj:  70%|██████▉   | 25585/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.52.gate_proj:  70%|██████▉   | 25586/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.52.up_proj:  70%|██████▉   | 25587/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.52.down_proj:  70%|██████▉   | 25588/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.53.gate_proj:  70%|██████▉   | 25589/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.53.up_proj:  70%|██████▉   | 25590/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.53.down_proj:  70%|██████▉   | 25591/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.54.gate_proj:  70%|██████▉   | 25592/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.54.up_proj:  70%|██████▉   | 25593/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.54.down_proj:  70%|██████▉   | 25594/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.55.gate_proj:  70%|██████▉   | 25595/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.55.up_proj:  70%|██████▉   | 25596/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.55.down_proj:  70%|███████   | 25597/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.56.gate_proj:  70%|███████   | 25598/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.56.up_proj:  70%|███████   | 25599/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.56.down_proj:  70%|███████   | 25600/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.57.gate_proj:  70%|███████   | 25601/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.57.up_proj:  70%|███████   | 25602/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.57.down_proj:  70%|███████   | 25603/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.58.gate_proj:  70%|███████   | 25604/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.58.up_proj:  70%|███████   | 25605/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.58.down_proj:  70%|███████   | 25606/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.59.gate_proj:  70%|███████   | 25607/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.59.up_proj:  70%|███████   | 25608/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.59.down_proj:  70%|███████   | 25609/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.60.gate_proj:  70%|███████   | 25610/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.60.up_proj:  70%|███████   | 25611/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.60.down_proj:  70%|███████   | 25612/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.61.gate_proj:  70%|███████   | 25613/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.61.up_proj:  70%|███████   | 25614/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.61.down_proj:  70%|███████   | 25615/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.62.gate_proj:  70%|███████   | 25616/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.62.up_proj:  70%|███████   | 25617/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.62.down_proj:  70%|███████   | 25618/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.63.gate_proj:  70%|███████   | 25619/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.63.up_proj:  70%|███████   | 25620/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.63.down_proj:  70%|███████   | 25621/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.64.gate_proj:  70%|███████   | 25622/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.64.up_proj:  70%|███████   | 25623/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.64.down_proj:  70%|███████   | 25624/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.65.gate_proj:  70%|███████   | 25625/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.65.up_proj:  70%|███████   | 25626/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.65.down_proj:  70%|███████   | 25627/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.66.gate_proj:  70%|███████   | 25628/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.66.up_proj:  70%|███████   | 25629/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.66.down_proj:  70%|███████   | 25630/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.67.gate_proj:  70%|███████   | 25631/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.67.up_proj:  70%|███████   | 25632/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.67.down_proj:  70%|███████   | 25633/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.68.gate_proj:  70%|███████   | 25634/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.68.up_proj:  70%|███████   | 25635/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.68.down_proj:  70%|███████   | 25636/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.69.gate_proj:  70%|███████   | 25637/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.69.up_proj:  70%|███████   | 25638/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.69.down_proj:  70%|███████   | 25639/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.70.gate_proj:  70%|███████   | 25640/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.70.up_proj:  70%|███████   | 25641/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.70.down_proj:  70%|███████   | 25642/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.71.gate_proj:  70%|███████   | 25643/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.71.up_proj:  70%|███████   | 25644/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.71.down_proj:  70%|███████   | 25645/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.72.gate_proj:  70%|███████   | 25646/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.72.up_proj:  70%|███████   | 25647/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.72.down_proj:  70%|███████   | 25648/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.73.gate_proj:  70%|███████   | 25649/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.73.up_proj:  70%|███████   | 25650/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.73.down_proj:  70%|███████   | 25651/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.74.gate_proj:  70%|███████   | 25652/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.74.up_proj:  70%|███████   | 25653/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.74.down_proj:  70%|███████   | 25654/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.75.gate_proj:  70%|███████   | 25655/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.75.up_proj:  70%|███████   | 25656/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.75.down_proj:  70%|███████   | 25657/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.76.gate_proj:  70%|███████   | 25658/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.76.up_proj:  70%|███████   | 25659/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.76.down_proj:  70%|███████   | 25660/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.77.gate_proj:  70%|███████   | 25661/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.77.up_proj:  70%|███████   | 25662/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.77.down_proj:  70%|███████   | 25663/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.78.gate_proj:  70%|███████   | 25664/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.78.up_proj:  70%|███████   | 25665/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.78.down_proj:  70%|███████   | 25666/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.79.gate_proj:  70%|███████   | 25667/36566 [00:23<00:09, 1147.47it/s]
packing model.layers.65.mlp.experts.79.up_proj:  70%|███████   | 25668/36566 [00:23<00:09, 1147.47it/s]  
packing model.layers.65.mlp.experts.79.up_proj:  70%|███████   | 25669/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.79.down_proj:  70%|███████   | 25669/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.80.gate_proj:  70%|███████   | 25670/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.80.up_proj:  70%|███████   | 25671/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.80.down_proj:  70%|███████   | 25672/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.81.gate_proj:  70%|███████   | 25673/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.81.up_proj:  70%|███████   | 25674/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.81.down_proj:  70%|███████   | 25675/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.82.gate_proj:  70%|███████   | 25676/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.82.up_proj:  70%|███████   | 25677/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.82.down_proj:  70%|███████   | 25678/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.83.gate_proj:  70%|███████   | 25679/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.83.up_proj:  70%|███████   | 25680/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.83.down_proj:  70%|███████   | 25681/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.84.gate_proj:  70%|███████   | 25682/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.84.up_proj:  70%|███████   | 25683/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.84.down_proj:  70%|███████   | 25684/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.85.gate_proj:  70%|███████   | 25685/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.85.up_proj:  70%|███████   | 25686/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.85.down_proj:  70%|███████   | 25687/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.86.gate_proj:  70%|███████   | 25688/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.86.up_proj:  70%|███████   | 25689/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.86.down_proj:  70%|███████   | 25690/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.87.gate_proj:  70%|███████   | 25691/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.87.up_proj:  70%|███████   | 25692/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.87.down_proj:  70%|███████   | 25693/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.88.gate_proj:  70%|███████   | 25694/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.88.up_proj:  70%|███████   | 25695/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.88.down_proj:  70%|███████   | 25696/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.89.gate_proj:  70%|███████   | 25697/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.89.up_proj:  70%|███████   | 25698/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.89.down_proj:  70%|███████   | 25699/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.90.gate_proj:  70%|███████   | 25700/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.90.up_proj:  70%|███████   | 25701/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.90.down_proj:  70%|███████   | 25702/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.91.gate_proj:  70%|███████   | 25703/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.91.up_proj:  70%|███████   | 25704/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.91.down_proj:  70%|███████   | 25705/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.92.gate_proj:  70%|███████   | 25706/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.92.up_proj:  70%|███████   | 25707/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.92.down_proj:  70%|███████   | 25708/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.93.gate_proj:  70%|███████   | 25709/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.93.up_proj:  70%|███████   | 25710/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.93.down_proj:  70%|███████   | 25711/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.94.gate_proj:  70%|███████   | 25712/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.94.up_proj:  70%|███████   | 25713/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.94.down_proj:  70%|███████   | 25714/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.95.gate_proj:  70%|███████   | 25715/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.95.up_proj:  70%|███████   | 25716/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.95.down_proj:  70%|███████   | 25717/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.96.gate_proj:  70%|███████   | 25718/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.96.up_proj:  70%|███████   | 25719/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.96.down_proj:  70%|███████   | 25720/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.97.gate_proj:  70%|███████   | 25721/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.97.up_proj:  70%|███████   | 25722/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.97.down_proj:  70%|███████   | 25723/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.98.gate_proj:  70%|███████   | 25724/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.98.up_proj:  70%|███████   | 25725/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.98.down_proj:  70%|███████   | 25726/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.99.gate_proj:  70%|███████   | 25727/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.99.up_proj:  70%|███████   | 25728/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.99.down_proj:  70%|███████   | 25729/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.100.gate_proj:  70%|███████   | 25730/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.100.up_proj:  70%|███████   | 25731/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.100.down_proj:  70%|███████   | 25732/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.101.gate_proj:  70%|███████   | 25733/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.101.up_proj:  70%|███████   | 25734/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.101.down_proj:  70%|███████   | 25735/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.102.gate_proj:  70%|███████   | 25736/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.102.up_proj:  70%|███████   | 25737/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.102.down_proj:  70%|███████   | 25738/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.103.gate_proj:  70%|███████   | 25739/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.103.up_proj:  70%|███████   | 25740/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.103.down_proj:  70%|███████   | 25741/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.104.gate_proj:  70%|███████   | 25742/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.104.up_proj:  70%|███████   | 25743/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.104.down_proj:  70%|███████   | 25744/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.105.gate_proj:  70%|███████   | 25745/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.105.up_proj:  70%|███████   | 25746/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.105.down_proj:  70%|███████   | 25747/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.106.gate_proj:  70%|███████   | 25748/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.106.up_proj:  70%|███████   | 25749/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.106.down_proj:  70%|███████   | 25750/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.107.gate_proj:  70%|███████   | 25751/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.107.up_proj:  70%|███████   | 25752/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.107.down_proj:  70%|███████   | 25753/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.108.gate_proj:  70%|███████   | 25754/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.108.up_proj:  70%|███████   | 25755/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.108.down_proj:  70%|███████   | 25756/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.109.gate_proj:  70%|███████   | 25757/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.109.up_proj:  70%|███████   | 25758/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.109.down_proj:  70%|███████   | 25759/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.110.gate_proj:  70%|███████   | 25760/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.110.up_proj:  70%|███████   | 25761/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.110.down_proj:  70%|███████   | 25762/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.111.gate_proj:  70%|███████   | 25763/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.111.up_proj:  70%|███████   | 25764/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.111.down_proj:  70%|███████   | 25765/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.112.gate_proj:  70%|███████   | 25766/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.112.up_proj:  70%|███████   | 25767/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.112.down_proj:  70%|███████   | 25768/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.113.gate_proj:  70%|███████   | 25769/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.113.up_proj:  70%|███████   | 25770/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.113.down_proj:  70%|███████   | 25771/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.114.gate_proj:  70%|███████   | 25772/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.114.up_proj:  70%|███████   | 25773/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.114.down_proj:  70%|███████   | 25774/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.115.gate_proj:  70%|███████   | 25775/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.115.up_proj:  70%|███████   | 25776/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.115.down_proj:  70%|███████   | 25777/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.116.gate_proj:  70%|███████   | 25778/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.116.up_proj:  70%|███████   | 25779/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.116.down_proj:  71%|███████   | 25780/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.117.gate_proj:  71%|███████   | 25781/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.117.up_proj:  71%|███████   | 25782/36566 [00:23<00:09, 1146.29it/s]  
packing model.layers.65.mlp.experts.117.down_proj:  71%|███████   | 25783/36566 [00:23<00:09, 1146.29it/s]
packing model.layers.65.mlp.experts.117.down_proj:  71%|███████   | 25784/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.118.gate_proj:  71%|███████   | 25784/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.118.up_proj:  71%|███████   | 25785/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.118.down_proj:  71%|███████   | 25786/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.119.gate_proj:  71%|███████   | 25787/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.119.up_proj:  71%|███████   | 25788/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.119.down_proj:  71%|███████   | 25789/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.120.gate_proj:  71%|███████   | 25790/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.120.up_proj:  71%|███████   | 25791/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.120.down_proj:  71%|███████   | 25792/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.121.gate_proj:  71%|███████   | 25793/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.121.up_proj:  71%|███████   | 25794/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.121.down_proj:  71%|███████   | 25795/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.122.gate_proj:  71%|███████   | 25796/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.122.up_proj:  71%|███████   | 25797/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.122.down_proj:  71%|███████   | 25798/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.123.gate_proj:  71%|███████   | 25799/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.123.up_proj:  71%|███████   | 25800/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.123.down_proj:  71%|███████   | 25801/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.124.gate_proj:  71%|███████   | 25802/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.124.up_proj:  71%|███████   | 25803/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.124.down_proj:  71%|███████   | 25804/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.125.gate_proj:  71%|███████   | 25805/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.125.up_proj:  71%|███████   | 25806/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.125.down_proj:  71%|███████   | 25807/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.126.gate_proj:  71%|███████   | 25808/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.126.up_proj:  71%|███████   | 25809/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.126.down_proj:  71%|███████   | 25810/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.127.gate_proj:  71%|███████   | 25811/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.65.mlp.experts.127.up_proj:  71%|███████   | 25812/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.65.mlp.experts.127.down_proj:  71%|███████   | 25813/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.0.gate_proj:  71%|███████   | 25814/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.0.up_proj:  71%|███████   | 25815/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.0.down_proj:  71%|███████   | 25816/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.1.gate_proj:  71%|███████   | 25817/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.1.up_proj:  71%|███████   | 25818/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.1.down_proj:  71%|███████   | 25819/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.2.gate_proj:  71%|███████   | 25820/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.2.up_proj:  71%|███████   | 25821/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.2.down_proj:  71%|███████   | 25822/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.3.gate_proj:  71%|███████   | 25823/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.3.up_proj:  71%|███████   | 25824/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.3.down_proj:  71%|███████   | 25825/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.4.gate_proj:  71%|███████   | 25826/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.4.up_proj:  71%|███████   | 25827/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.4.down_proj:  71%|███████   | 25828/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.5.gate_proj:  71%|███████   | 25829/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.5.up_proj:  71%|███████   | 25830/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.5.down_proj:  71%|███████   | 25831/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.6.gate_proj:  71%|███████   | 25832/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.6.up_proj:  71%|███████   | 25833/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.6.down_proj:  71%|███████   | 25834/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.7.gate_proj:  71%|███████   | 25835/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.7.up_proj:  71%|███████   | 25836/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.7.down_proj:  71%|███████   | 25837/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.8.gate_proj:  71%|███████   | 25838/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.8.up_proj:  71%|███████   | 25839/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.8.down_proj:  71%|███████   | 25840/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.9.gate_proj:  71%|███████   | 25841/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.9.up_proj:  71%|███████   | 25842/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.9.down_proj:  71%|███████   | 25843/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.10.gate_proj:  71%|███████   | 25844/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.10.up_proj:  71%|███████   | 25845/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.10.down_proj:  71%|███████   | 25846/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.11.gate_proj:  71%|███████   | 25847/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.11.up_proj:  71%|███████   | 25848/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.11.down_proj:  71%|███████   | 25849/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.12.gate_proj:  71%|███████   | 25850/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.12.up_proj:  71%|███████   | 25851/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.12.down_proj:  71%|███████   | 25852/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.13.gate_proj:  71%|███████   | 25853/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.13.up_proj:  71%|███████   | 25854/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.13.down_proj:  71%|███████   | 25855/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.14.gate_proj:  71%|███████   | 25856/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.14.up_proj:  71%|███████   | 25857/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.14.down_proj:  71%|███████   | 25858/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.15.gate_proj:  71%|███████   | 25859/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.15.up_proj:  71%|███████   | 25860/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.15.down_proj:  71%|███████   | 25861/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.16.gate_proj:  71%|███████   | 25862/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.16.up_proj:  71%|███████   | 25863/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.16.down_proj:  71%|███████   | 25864/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.17.gate_proj:  71%|███████   | 25865/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.17.up_proj:  71%|███████   | 25866/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.17.down_proj:  71%|███████   | 25867/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.18.gate_proj:  71%|███████   | 25868/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.18.up_proj:  71%|███████   | 25869/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.18.down_proj:  71%|███████   | 25870/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.19.gate_proj:  71%|███████   | 25871/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.19.up_proj:  71%|███████   | 25872/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.19.down_proj:  71%|███████   | 25873/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.20.gate_proj:  71%|███████   | 25874/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.20.up_proj:  71%|███████   | 25875/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.20.down_proj:  71%|███████   | 25876/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.21.gate_proj:  71%|███████   | 25877/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.21.up_proj:  71%|███████   | 25878/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.21.down_proj:  71%|███████   | 25879/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.22.gate_proj:  71%|███████   | 25880/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.22.up_proj:  71%|███████   | 25881/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.22.down_proj:  71%|███████   | 25882/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.23.gate_proj:  71%|███████   | 25883/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.23.up_proj:  71%|███████   | 25884/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.23.down_proj:  71%|███████   | 25885/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.24.gate_proj:  71%|███████   | 25886/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.24.up_proj:  71%|███████   | 25887/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.24.down_proj:  71%|███████   | 25888/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.25.gate_proj:  71%|███████   | 25889/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.25.up_proj:  71%|███████   | 25890/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.25.down_proj:  71%|███████   | 25891/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.26.gate_proj:  71%|███████   | 25892/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.26.up_proj:  71%|███████   | 25893/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.26.down_proj:  71%|███████   | 25894/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.27.gate_proj:  71%|███████   | 25895/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.27.up_proj:  71%|███████   | 25896/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.27.down_proj:  71%|███████   | 25897/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.28.gate_proj:  71%|███████   | 25898/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.28.up_proj:  71%|███████   | 25899/36566 [00:23<00:09, 1146.56it/s]  
packing model.layers.66.mlp.experts.28.down_proj:  71%|███████   | 25900/36566 [00:23<00:09, 1146.56it/s]
packing model.layers.66.mlp.experts.28.down_proj:  71%|███████   | 25901/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.29.gate_proj:  71%|███████   | 25901/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.29.up_proj:  71%|███████   | 25902/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.29.down_proj:  71%|███████   | 25903/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.30.gate_proj:  71%|███████   | 25904/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.30.up_proj:  71%|███████   | 25905/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.30.down_proj:  71%|███████   | 25906/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.31.gate_proj:  71%|███████   | 25907/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.31.up_proj:  71%|███████   | 25908/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.31.down_proj:  71%|███████   | 25909/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.32.gate_proj:  71%|███████   | 25910/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.32.up_proj:  71%|███████   | 25911/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.32.down_proj:  71%|███████   | 25912/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.33.gate_proj:  71%|███████   | 25913/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.33.up_proj:  71%|███████   | 25914/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.33.down_proj:  71%|███████   | 25915/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.34.gate_proj:  71%|███████   | 25916/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.34.up_proj:  71%|███████   | 25917/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.34.down_proj:  71%|███████   | 25918/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.35.gate_proj:  71%|███████   | 25919/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.35.up_proj:  71%|███████   | 25920/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.35.down_proj:  71%|███████   | 25921/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.36.gate_proj:  71%|███████   | 25922/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.36.up_proj:  71%|███████   | 25923/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.36.down_proj:  71%|███████   | 25924/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.37.gate_proj:  71%|███████   | 25925/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.37.up_proj:  71%|███████   | 25926/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.37.down_proj:  71%|███████   | 25927/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.38.gate_proj:  71%|███████   | 25928/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.38.up_proj:  71%|███████   | 25929/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.38.down_proj:  71%|███████   | 25930/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.39.gate_proj:  71%|███████   | 25931/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.39.up_proj:  71%|███████   | 25932/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.39.down_proj:  71%|███████   | 25933/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.40.gate_proj:  71%|███████   | 25934/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.40.up_proj:  71%|███████   | 25935/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.40.down_proj:  71%|███████   | 25936/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.41.gate_proj:  71%|███████   | 25937/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.41.up_proj:  71%|███████   | 25938/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.41.down_proj:  71%|███████   | 25939/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.42.gate_proj:  71%|███████   | 25940/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.42.up_proj:  71%|███████   | 25941/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.42.down_proj:  71%|███████   | 25942/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.43.gate_proj:  71%|███████   | 25943/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.43.up_proj:  71%|███████   | 25944/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.43.down_proj:  71%|███████   | 25945/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.44.gate_proj:  71%|███████   | 25946/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.44.up_proj:  71%|███████   | 25947/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.44.down_proj:  71%|███████   | 25948/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.45.gate_proj:  71%|███████   | 25949/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.45.up_proj:  71%|███████   | 25950/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.45.down_proj:  71%|███████   | 25951/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.46.gate_proj:  71%|███████   | 25952/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.46.up_proj:  71%|███████   | 25953/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.46.down_proj:  71%|███████   | 25954/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.47.gate_proj:  71%|███████   | 25955/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.47.up_proj:  71%|███████   | 25956/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.47.down_proj:  71%|███████   | 25957/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.48.gate_proj:  71%|███████   | 25958/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.48.up_proj:  71%|███████   | 25959/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.48.down_proj:  71%|███████   | 25960/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.49.gate_proj:  71%|███████   | 25961/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.49.up_proj:  71%|███████   | 25962/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.49.down_proj:  71%|███████   | 25963/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.50.gate_proj:  71%|███████   | 25964/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.50.up_proj:  71%|███████   | 25965/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.50.down_proj:  71%|███████   | 25966/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.51.gate_proj:  71%|███████   | 25967/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.51.up_proj:  71%|███████   | 25968/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.51.down_proj:  71%|███████   | 25969/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.52.gate_proj:  71%|███████   | 25970/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.52.up_proj:  71%|███████   | 25971/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.52.down_proj:  71%|███████   | 25972/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.53.gate_proj:  71%|███████   | 25973/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.53.up_proj:  71%|███████   | 25974/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.53.down_proj:  71%|███████   | 25975/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.54.gate_proj:  71%|███████   | 25976/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.54.up_proj:  71%|███████   | 25977/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.54.down_proj:  71%|███████   | 25978/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.55.gate_proj:  71%|███████   | 25979/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.55.up_proj:  71%|███████   | 25980/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.55.down_proj:  71%|███████   | 25981/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.56.gate_proj:  71%|███████   | 25982/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.56.up_proj:  71%|███████   | 25983/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.56.down_proj:  71%|███████   | 25984/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.57.gate_proj:  71%|███████   | 25985/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.57.up_proj:  71%|███████   | 25986/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.57.down_proj:  71%|███████   | 25987/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.58.gate_proj:  71%|███████   | 25988/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.58.up_proj:  71%|███████   | 25989/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.58.down_proj:  71%|███████   | 25990/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.59.gate_proj:  71%|███████   | 25991/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.59.up_proj:  71%|███████   | 25992/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.59.down_proj:  71%|███████   | 25993/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.60.gate_proj:  71%|███████   | 25994/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.60.up_proj:  71%|███████   | 25995/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.60.down_proj:  71%|███████   | 25996/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.61.gate_proj:  71%|███████   | 25997/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.61.up_proj:  71%|███████   | 25998/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.61.down_proj:  71%|███████   | 25999/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.62.gate_proj:  71%|███████   | 26000/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.62.up_proj:  71%|███████   | 26001/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.62.down_proj:  71%|███████   | 26002/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.63.gate_proj:  71%|███████   | 26003/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.63.up_proj:  71%|███████   | 26004/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.63.down_proj:  71%|███████   | 26005/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.64.gate_proj:  71%|███████   | 26006/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.64.up_proj:  71%|███████   | 26007/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.64.down_proj:  71%|███████   | 26008/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.65.gate_proj:  71%|███████   | 26009/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.65.up_proj:  71%|███████   | 26010/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.65.down_proj:  71%|███████   | 26011/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.66.gate_proj:  71%|███████   | 26012/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.66.up_proj:  71%|███████   | 26013/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.66.down_proj:  71%|███████   | 26014/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.67.gate_proj:  71%|███████   | 26015/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.67.up_proj:  71%|███████   | 26016/36566 [00:23<00:09, 1150.74it/s]  
packing model.layers.66.mlp.experts.67.down_proj:  71%|███████   | 26017/36566 [00:23<00:09, 1150.74it/s]
packing model.layers.66.mlp.experts.67.down_proj:  71%|███████   | 26018/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.68.gate_proj:  71%|███████   | 26018/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.68.up_proj:  71%|███████   | 26019/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.68.down_proj:  71%|███████   | 26020/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.69.gate_proj:  71%|███████   | 26021/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.69.up_proj:  71%|███████   | 26022/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.69.down_proj:  71%|███████   | 26023/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.70.gate_proj:  71%|███████   | 26024/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.70.up_proj:  71%|███████   | 26025/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.70.down_proj:  71%|███████   | 26026/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.71.gate_proj:  71%|███████   | 26027/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.71.up_proj:  71%|███████   | 26028/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.71.down_proj:  71%|███████   | 26029/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.72.gate_proj:  71%|███████   | 26030/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.72.up_proj:  71%|███████   | 26031/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.72.down_proj:  71%|███████   | 26032/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.73.gate_proj:  71%|███████   | 26033/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.73.up_proj:  71%|███████   | 26034/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.73.down_proj:  71%|███████   | 26035/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.74.gate_proj:  71%|███████   | 26036/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.74.up_proj:  71%|███████   | 26037/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.74.down_proj:  71%|███████   | 26038/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.75.gate_proj:  71%|███████   | 26039/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.75.up_proj:  71%|███████   | 26040/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.75.down_proj:  71%|███████   | 26041/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.76.gate_proj:  71%|███████   | 26042/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.76.up_proj:  71%|███████   | 26043/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.76.down_proj:  71%|███████   | 26044/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.77.gate_proj:  71%|███████   | 26045/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.77.up_proj:  71%|███████   | 26046/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.77.down_proj:  71%|███████   | 26047/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.78.gate_proj:  71%|███████   | 26048/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.78.up_proj:  71%|███████   | 26049/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.78.down_proj:  71%|███████   | 26050/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.79.gate_proj:  71%|███████   | 26051/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.79.up_proj:  71%|███████   | 26052/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.79.down_proj:  71%|███████   | 26053/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.80.gate_proj:  71%|███████▏  | 26054/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.80.up_proj:  71%|███████▏  | 26055/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.80.down_proj:  71%|███████▏  | 26056/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.81.gate_proj:  71%|███████▏  | 26057/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.81.up_proj:  71%|███████▏  | 26058/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.81.down_proj:  71%|███████▏  | 26059/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.82.gate_proj:  71%|███████▏  | 26060/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.82.up_proj:  71%|███████▏  | 26061/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.82.down_proj:  71%|███████▏  | 26062/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.83.gate_proj:  71%|███████▏  | 26063/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.83.up_proj:  71%|███████▏  | 26064/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.83.down_proj:  71%|███████▏  | 26065/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.84.gate_proj:  71%|███████▏  | 26066/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.84.up_proj:  71%|███████▏  | 26067/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.84.down_proj:  71%|███████▏  | 26068/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.85.gate_proj:  71%|███████▏  | 26069/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.85.up_proj:  71%|███████▏  | 26070/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.85.down_proj:  71%|███████▏  | 26071/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.86.gate_proj:  71%|███████▏  | 26072/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.86.up_proj:  71%|███████▏  | 26073/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.86.down_proj:  71%|███████▏  | 26074/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.87.gate_proj:  71%|███████▏  | 26075/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.87.up_proj:  71%|███████▏  | 26076/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.87.down_proj:  71%|███████▏  | 26077/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.88.gate_proj:  71%|███████▏  | 26078/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.88.up_proj:  71%|███████▏  | 26079/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.88.down_proj:  71%|███████▏  | 26080/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.89.gate_proj:  71%|███████▏  | 26081/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.89.up_proj:  71%|███████▏  | 26082/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.89.down_proj:  71%|███████▏  | 26083/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.90.gate_proj:  71%|███████▏  | 26084/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.90.up_proj:  71%|███████▏  | 26085/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.90.down_proj:  71%|███████▏  | 26086/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.91.gate_proj:  71%|███████▏  | 26087/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.91.up_proj:  71%|███████▏  | 26088/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.91.down_proj:  71%|███████▏  | 26089/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.92.gate_proj:  71%|███████▏  | 26090/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.92.up_proj:  71%|███████▏  | 26091/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.92.down_proj:  71%|███████▏  | 26092/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.93.gate_proj:  71%|███████▏  | 26093/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.93.up_proj:  71%|███████▏  | 26094/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.93.down_proj:  71%|███████▏  | 26095/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.94.gate_proj:  71%|███████▏  | 26096/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.94.up_proj:  71%|███████▏  | 26097/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.94.down_proj:  71%|███████▏  | 26098/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.95.gate_proj:  71%|███████▏  | 26099/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.95.up_proj:  71%|███████▏  | 26100/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.95.down_proj:  71%|███████▏  | 26101/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.96.gate_proj:  71%|███████▏  | 26102/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.96.up_proj:  71%|███████▏  | 26103/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.96.down_proj:  71%|███████▏  | 26104/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.97.gate_proj:  71%|███████▏  | 26105/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.97.up_proj:  71%|███████▏  | 26106/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.97.down_proj:  71%|███████▏  | 26107/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.98.gate_proj:  71%|███████▏  | 26108/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.98.up_proj:  71%|███████▏  | 26109/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.98.down_proj:  71%|███████▏  | 26110/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.99.gate_proj:  71%|███████▏  | 26111/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.99.up_proj:  71%|███████▏  | 26112/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.99.down_proj:  71%|███████▏  | 26113/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.100.gate_proj:  71%|███████▏  | 26114/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.100.up_proj:  71%|███████▏  | 26115/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.100.down_proj:  71%|███████▏  | 26116/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.101.gate_proj:  71%|███████▏  | 26117/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.101.up_proj:  71%|███████▏  | 26118/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.101.down_proj:  71%|███████▏  | 26119/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.102.gate_proj:  71%|███████▏  | 26120/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.102.up_proj:  71%|███████▏  | 26121/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.102.down_proj:  71%|███████▏  | 26122/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.103.gate_proj:  71%|███████▏  | 26123/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.103.up_proj:  71%|███████▏  | 26124/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.103.down_proj:  71%|███████▏  | 26125/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.104.gate_proj:  71%|███████▏  | 26126/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.104.up_proj:  71%|███████▏  | 26127/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.104.down_proj:  71%|███████▏  | 26128/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.105.gate_proj:  71%|███████▏  | 26129/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.105.up_proj:  71%|███████▏  | 26130/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.105.down_proj:  71%|███████▏  | 26131/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.106.gate_proj:  71%|███████▏  | 26132/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.106.up_proj:  71%|███████▏  | 26133/36566 [00:23<00:09, 1154.10it/s]  
packing model.layers.66.mlp.experts.106.down_proj:  71%|███████▏  | 26134/36566 [00:23<00:09, 1154.10it/s]
packing model.layers.66.mlp.experts.106.down_proj:  71%|███████▏  | 26135/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.107.gate_proj:  71%|███████▏  | 26135/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.107.up_proj:  71%|███████▏  | 26136/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.107.down_proj:  71%|███████▏  | 26137/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.108.gate_proj:  71%|███████▏  | 26138/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.108.up_proj:  71%|███████▏  | 26139/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.108.down_proj:  71%|███████▏  | 26140/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.109.gate_proj:  71%|███████▏  | 26141/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.109.up_proj:  71%|███████▏  | 26142/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.109.down_proj:  71%|███████▏  | 26143/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.110.gate_proj:  71%|███████▏  | 26144/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.110.up_proj:  72%|███████▏  | 26145/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.110.down_proj:  72%|███████▏  | 26146/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.111.gate_proj:  72%|███████▏  | 26147/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.111.up_proj:  72%|███████▏  | 26148/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.111.down_proj:  72%|███████▏  | 26149/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.112.gate_proj:  72%|███████▏  | 26150/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.112.up_proj:  72%|███████▏  | 26151/36566 [00:23<00:09, 1156.92it/s]  
packing model.layers.66.mlp.experts.112.down_proj:  72%|███████▏  | 26152/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.113.gate_proj:  72%|███████▏  | 26153/36566 [00:23<00:09, 1156.92it/s]
packing model.layers.66.mlp.experts.113.up_proj:  72%|███████▏  | 26154/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.113.down_proj:  72%|███████▏  | 26155/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.114.gate_proj:  72%|███████▏  | 26156/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.114.up_proj:  72%|███████▏  | 26157/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.114.down_proj:  72%|███████▏  | 26158/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.115.gate_proj:  72%|███████▏  | 26159/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.115.up_proj:  72%|███████▏  | 26160/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.115.down_proj:  72%|███████▏  | 26161/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.116.gate_proj:  72%|███████▏  | 26162/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.116.up_proj:  72%|███████▏  | 26163/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.116.down_proj:  72%|███████▏  | 26164/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.117.gate_proj:  72%|███████▏  | 26165/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.117.up_proj:  72%|███████▏  | 26166/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.117.down_proj:  72%|███████▏  | 26167/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.118.gate_proj:  72%|███████▏  | 26168/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.118.up_proj:  72%|███████▏  | 26169/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.118.down_proj:  72%|███████▏  | 26170/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.119.gate_proj:  72%|███████▏  | 26171/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.119.up_proj:  72%|███████▏  | 26172/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.119.down_proj:  72%|███████▏  | 26173/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.120.gate_proj:  72%|███████▏  | 26174/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.120.up_proj:  72%|███████▏  | 26175/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.120.down_proj:  72%|███████▏  | 26176/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.121.gate_proj:  72%|███████▏  | 26177/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.121.up_proj:  72%|███████▏  | 26178/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.121.down_proj:  72%|███████▏  | 26179/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.122.gate_proj:  72%|███████▏  | 26180/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.122.up_proj:  72%|███████▏  | 26181/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.122.down_proj:  72%|███████▏  | 26182/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.123.gate_proj:  72%|███████▏  | 26183/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.123.up_proj:  72%|███████▏  | 26184/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.123.down_proj:  72%|███████▏  | 26185/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.124.gate_proj:  72%|███████▏  | 26186/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.124.up_proj:  72%|███████▏  | 26187/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.124.down_proj:  72%|███████▏  | 26188/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.125.gate_proj:  72%|███████▏  | 26189/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.125.up_proj:  72%|███████▏  | 26190/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.125.down_proj:  72%|███████▏  | 26191/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.126.gate_proj:  72%|███████▏  | 26192/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.126.up_proj:  72%|███████▏  | 26193/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.126.down_proj:  72%|███████▏  | 26194/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.127.gate_proj:  72%|███████▏  | 26195/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.66.mlp.experts.127.up_proj:  72%|███████▏  | 26196/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.66.mlp.experts.127.down_proj:  72%|███████▏  | 26197/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.0.gate_proj:  72%|███████▏  | 26198/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.0.up_proj:  72%|███████▏  | 26199/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.0.down_proj:  72%|███████▏  | 26200/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.1.gate_proj:  72%|███████▏  | 26201/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.1.up_proj:  72%|███████▏  | 26202/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.1.down_proj:  72%|███████▏  | 26203/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.2.gate_proj:  72%|███████▏  | 26204/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.2.up_proj:  72%|███████▏  | 26205/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.2.down_proj:  72%|███████▏  | 26206/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.3.gate_proj:  72%|███████▏  | 26207/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.3.up_proj:  72%|███████▏  | 26208/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.3.down_proj:  72%|███████▏  | 26209/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.4.gate_proj:  72%|███████▏  | 26210/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.4.up_proj:  72%|███████▏  | 26211/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.4.down_proj:  72%|███████▏  | 26212/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.5.gate_proj:  72%|███████▏  | 26213/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.5.up_proj:  72%|███████▏  | 26214/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.5.down_proj:  72%|███████▏  | 26215/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.6.gate_proj:  72%|███████▏  | 26216/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.6.up_proj:  72%|███████▏  | 26217/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.6.down_proj:  72%|███████▏  | 26218/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.7.gate_proj:  72%|███████▏  | 26219/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.7.up_proj:  72%|███████▏  | 26220/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.7.down_proj:  72%|███████▏  | 26221/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.8.gate_proj:  72%|███████▏  | 26222/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.8.up_proj:  72%|███████▏  | 26223/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.8.down_proj:  72%|███████▏  | 26224/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.9.gate_proj:  72%|███████▏  | 26225/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.9.up_proj:  72%|███████▏  | 26226/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.9.down_proj:  72%|███████▏  | 26227/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.10.gate_proj:  72%|███████▏  | 26228/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.10.up_proj:  72%|███████▏  | 26229/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.10.down_proj:  72%|███████▏  | 26230/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.11.gate_proj:  72%|███████▏  | 26231/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.11.up_proj:  72%|███████▏  | 26232/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.11.down_proj:  72%|███████▏  | 26233/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.12.gate_proj:  72%|███████▏  | 26234/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.12.up_proj:  72%|███████▏  | 26235/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.12.down_proj:  72%|███████▏  | 26236/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.13.gate_proj:  72%|███████▏  | 26237/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.13.up_proj:  72%|███████▏  | 26238/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.13.down_proj:  72%|███████▏  | 26239/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.14.gate_proj:  72%|███████▏  | 26240/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.14.up_proj:  72%|███████▏  | 26241/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.14.down_proj:  72%|███████▏  | 26242/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.15.gate_proj:  72%|███████▏  | 26243/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.15.up_proj:  72%|███████▏  | 26244/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.15.down_proj:  72%|███████▏  | 26245/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.16.gate_proj:  72%|███████▏  | 26246/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.16.up_proj:  72%|███████▏  | 26247/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.16.down_proj:  72%|███████▏  | 26248/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.17.gate_proj:  72%|███████▏  | 26249/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.17.up_proj:  72%|███████▏  | 26250/36566 [00:23<00:08, 1156.92it/s]  
packing model.layers.67.mlp.experts.17.down_proj:  72%|███████▏  | 26251/36566 [00:23<00:08, 1156.92it/s]
packing model.layers.67.mlp.experts.17.down_proj:  72%|███████▏  | 26252/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.18.gate_proj:  72%|███████▏  | 26252/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.18.up_proj:  72%|███████▏  | 26253/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.18.down_proj:  72%|███████▏  | 26254/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.19.gate_proj:  72%|███████▏  | 26255/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.19.up_proj:  72%|███████▏  | 26256/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.19.down_proj:  72%|███████▏  | 26257/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.20.gate_proj:  72%|███████▏  | 26258/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.20.up_proj:  72%|███████▏  | 26259/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.20.down_proj:  72%|███████▏  | 26260/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.21.gate_proj:  72%|███████▏  | 26261/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.21.up_proj:  72%|███████▏  | 26262/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.21.down_proj:  72%|███████▏  | 26263/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.22.gate_proj:  72%|███████▏  | 26264/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.22.up_proj:  72%|███████▏  | 26265/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.22.down_proj:  72%|███████▏  | 26266/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.23.gate_proj:  72%|███████▏  | 26267/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.23.up_proj:  72%|███████▏  | 26268/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.23.down_proj:  72%|███████▏  | 26269/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.24.gate_proj:  72%|███████▏  | 26270/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.24.up_proj:  72%|███████▏  | 26271/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.24.down_proj:  72%|███████▏  | 26272/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.25.gate_proj:  72%|███████▏  | 26273/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.25.up_proj:  72%|███████▏  | 26274/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.25.down_proj:  72%|███████▏  | 26275/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.26.gate_proj:  72%|███████▏  | 26276/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.26.up_proj:  72%|███████▏  | 26277/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.26.down_proj:  72%|███████▏  | 26278/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.27.gate_proj:  72%|███████▏  | 26279/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.27.up_proj:  72%|███████▏  | 26280/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.27.down_proj:  72%|███████▏  | 26281/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.28.gate_proj:  72%|███████▏  | 26282/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.28.up_proj:  72%|███████▏  | 26283/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.28.down_proj:  72%|███████▏  | 26284/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.29.gate_proj:  72%|███████▏  | 26285/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.29.up_proj:  72%|███████▏  | 26286/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.29.down_proj:  72%|███████▏  | 26287/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.30.gate_proj:  72%|███████▏  | 26288/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.30.up_proj:  72%|███████▏  | 26289/36566 [00:23<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.30.down_proj:  72%|███████▏  | 26290/36566 [00:23<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.31.gate_proj:  72%|███████▏  | 26291/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.31.up_proj:  72%|███████▏  | 26292/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.31.down_proj:  72%|███████▏  | 26293/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.32.gate_proj:  72%|███████▏  | 26294/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.32.up_proj:  72%|███████▏  | 26295/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.32.down_proj:  72%|███████▏  | 26296/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.33.gate_proj:  72%|███████▏  | 26297/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.33.up_proj:  72%|███████▏  | 26298/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.33.down_proj:  72%|███████▏  | 26299/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.34.gate_proj:  72%|███████▏  | 26300/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.34.up_proj:  72%|███████▏  | 26301/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.34.down_proj:  72%|███████▏  | 26302/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.35.gate_proj:  72%|███████▏  | 26303/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.35.up_proj:  72%|███████▏  | 26304/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.35.down_proj:  72%|███████▏  | 26305/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.36.gate_proj:  72%|███████▏  | 26306/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.36.up_proj:  72%|███████▏  | 26307/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.36.down_proj:  72%|███████▏  | 26308/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.37.gate_proj:  72%|███████▏  | 26309/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.37.up_proj:  72%|███████▏  | 26310/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.37.down_proj:  72%|███████▏  | 26311/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.38.gate_proj:  72%|███████▏  | 26312/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.38.up_proj:  72%|███████▏  | 26313/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.38.down_proj:  72%|███████▏  | 26314/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.39.gate_proj:  72%|███████▏  | 26315/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.39.up_proj:  72%|███████▏  | 26316/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.39.down_proj:  72%|███████▏  | 26317/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.40.gate_proj:  72%|███████▏  | 26318/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.40.up_proj:  72%|███████▏  | 26319/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.40.down_proj:  72%|███████▏  | 26320/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.41.gate_proj:  72%|███████▏  | 26321/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.41.up_proj:  72%|███████▏  | 26322/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.41.down_proj:  72%|███████▏  | 26323/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.42.gate_proj:  72%|███████▏  | 26324/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.42.up_proj:  72%|███████▏  | 26325/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.42.down_proj:  72%|███████▏  | 26326/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.43.gate_proj:  72%|███████▏  | 26327/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.43.up_proj:  72%|███████▏  | 26328/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.43.down_proj:  72%|███████▏  | 26329/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.44.gate_proj:  72%|███████▏  | 26330/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.44.up_proj:  72%|███████▏  | 26331/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.44.down_proj:  72%|███████▏  | 26332/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.45.gate_proj:  72%|███████▏  | 26333/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.45.up_proj:  72%|███████▏  | 26334/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.45.down_proj:  72%|███████▏  | 26335/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.46.gate_proj:  72%|███████▏  | 26336/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.46.up_proj:  72%|███████▏  | 26337/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.46.down_proj:  72%|███████▏  | 26338/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.47.gate_proj:  72%|███████▏  | 26339/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.47.up_proj:  72%|███████▏  | 26340/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.47.down_proj:  72%|███████▏  | 26341/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.48.gate_proj:  72%|███████▏  | 26342/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.48.up_proj:  72%|███████▏  | 26343/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.48.down_proj:  72%|███████▏  | 26344/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.49.gate_proj:  72%|███████▏  | 26345/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.49.up_proj:  72%|███████▏  | 26346/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.49.down_proj:  72%|███████▏  | 26347/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.50.gate_proj:  72%|███████▏  | 26348/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.50.up_proj:  72%|███████▏  | 26349/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.50.down_proj:  72%|███████▏  | 26350/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.51.gate_proj:  72%|███████▏  | 26351/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.51.up_proj:  72%|███████▏  | 26352/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.51.down_proj:  72%|███████▏  | 26353/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.52.gate_proj:  72%|███████▏  | 26354/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.52.up_proj:  72%|███████▏  | 26355/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.52.down_proj:  72%|███████▏  | 26356/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.53.gate_proj:  72%|███████▏  | 26357/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.53.up_proj:  72%|███████▏  | 26358/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.53.down_proj:  72%|███████▏  | 26359/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.54.gate_proj:  72%|███████▏  | 26360/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.54.up_proj:  72%|███████▏  | 26361/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.54.down_proj:  72%|███████▏  | 26362/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.55.gate_proj:  72%|███████▏  | 26363/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.55.up_proj:  72%|███████▏  | 26364/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.55.down_proj:  72%|███████▏  | 26365/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.56.gate_proj:  72%|███████▏  | 26366/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.56.up_proj:  72%|███████▏  | 26367/36566 [00:24<00:08, 1158.34it/s]  
packing model.layers.67.mlp.experts.56.down_proj:  72%|███████▏  | 26368/36566 [00:24<00:08, 1158.34it/s]
packing model.layers.67.mlp.experts.56.down_proj:  72%|███████▏  | 26369/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.57.gate_proj:  72%|███████▏  | 26369/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.57.up_proj:  72%|███████▏  | 26370/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.57.down_proj:  72%|███████▏  | 26371/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.58.gate_proj:  72%|███████▏  | 26372/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.58.up_proj:  72%|███████▏  | 26373/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.58.down_proj:  72%|███████▏  | 26374/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.59.gate_proj:  72%|███████▏  | 26375/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.59.up_proj:  72%|███████▏  | 26376/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.59.down_proj:  72%|███████▏  | 26377/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.60.gate_proj:  72%|███████▏  | 26378/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.60.up_proj:  72%|███████▏  | 26379/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.60.down_proj:  72%|███████▏  | 26380/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.61.gate_proj:  72%|███████▏  | 26381/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.61.up_proj:  72%|███████▏  | 26382/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.61.down_proj:  72%|███████▏  | 26383/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.62.gate_proj:  72%|███████▏  | 26384/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.62.up_proj:  72%|███████▏  | 26385/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.62.down_proj:  72%|███████▏  | 26386/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.63.gate_proj:  72%|███████▏  | 26387/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.63.up_proj:  72%|███████▏  | 26388/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.63.down_proj:  72%|███████▏  | 26389/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.64.gate_proj:  72%|███████▏  | 26390/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.64.up_proj:  72%|███████▏  | 26391/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.64.down_proj:  72%|███████▏  | 26392/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.65.gate_proj:  72%|███████▏  | 26393/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.65.up_proj:  72%|███████▏  | 26394/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.65.down_proj:  72%|███████▏  | 26395/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.66.gate_proj:  72%|███████▏  | 26396/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.66.up_proj:  72%|███████▏  | 26397/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.66.down_proj:  72%|███████▏  | 26398/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.67.gate_proj:  72%|███████▏  | 26399/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.67.up_proj:  72%|███████▏  | 26400/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.67.down_proj:  72%|███████▏  | 26401/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.68.gate_proj:  72%|███████▏  | 26402/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.68.up_proj:  72%|███████▏  | 26403/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.68.down_proj:  72%|███████▏  | 26404/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.69.gate_proj:  72%|███████▏  | 26405/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.69.up_proj:  72%|███████▏  | 26406/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.69.down_proj:  72%|███████▏  | 26407/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.70.gate_proj:  72%|███████▏  | 26408/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.70.up_proj:  72%|███████▏  | 26409/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.70.down_proj:  72%|███████▏  | 26410/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.71.gate_proj:  72%|███████▏  | 26411/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.71.up_proj:  72%|███████▏  | 26412/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.71.down_proj:  72%|███████▏  | 26413/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.72.gate_proj:  72%|███████▏  | 26414/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.72.up_proj:  72%|███████▏  | 26415/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.72.down_proj:  72%|███████▏  | 26416/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.73.gate_proj:  72%|███████▏  | 26417/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.73.up_proj:  72%|███████▏  | 26418/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.73.down_proj:  72%|███████▏  | 26419/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.74.gate_proj:  72%|███████▏  | 26420/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.74.up_proj:  72%|███████▏  | 26421/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.74.down_proj:  72%|███████▏  | 26422/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.75.gate_proj:  72%|███████▏  | 26423/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.75.up_proj:  72%|███████▏  | 26424/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.75.down_proj:  72%|███████▏  | 26425/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.76.gate_proj:  72%|███████▏  | 26426/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.76.up_proj:  72%|███████▏  | 26427/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.76.down_proj:  72%|███████▏  | 26428/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.77.gate_proj:  72%|███████▏  | 26429/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.77.up_proj:  72%|███████▏  | 26430/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.77.down_proj:  72%|███████▏  | 26431/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.78.gate_proj:  72%|███████▏  | 26432/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.78.up_proj:  72%|███████▏  | 26433/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.78.down_proj:  72%|███████▏  | 26434/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.79.gate_proj:  72%|███████▏  | 26435/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.79.up_proj:  72%|███████▏  | 26436/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.79.down_proj:  72%|███████▏  | 26437/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.80.gate_proj:  72%|███████▏  | 26438/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.80.up_proj:  72%|███████▏  | 26439/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.80.down_proj:  72%|███████▏  | 26440/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.81.gate_proj:  72%|███████▏  | 26441/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.81.up_proj:  72%|███████▏  | 26442/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.81.down_proj:  72%|███████▏  | 26443/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.82.gate_proj:  72%|███████▏  | 26444/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.82.up_proj:  72%|███████▏  | 26445/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.82.down_proj:  72%|███████▏  | 26446/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.83.gate_proj:  72%|███████▏  | 26447/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.83.up_proj:  72%|███████▏  | 26448/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.83.down_proj:  72%|███████▏  | 26449/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.84.gate_proj:  72%|███████▏  | 26450/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.84.up_proj:  72%|███████▏  | 26451/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.84.down_proj:  72%|███████▏  | 26452/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.85.gate_proj:  72%|███████▏  | 26453/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.85.up_proj:  72%|███████▏  | 26454/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.85.down_proj:  72%|███████▏  | 26455/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.86.gate_proj:  72%|███████▏  | 26456/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.86.up_proj:  72%|███████▏  | 26457/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.86.down_proj:  72%|███████▏  | 26458/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.87.gate_proj:  72%|███████▏  | 26459/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.87.up_proj:  72%|███████▏  | 26460/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.87.down_proj:  72%|███████▏  | 26461/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.88.gate_proj:  72%|███████▏  | 26462/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.88.up_proj:  72%|███████▏  | 26463/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.88.down_proj:  72%|███████▏  | 26464/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.89.gate_proj:  72%|███████▏  | 26465/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.89.up_proj:  72%|███████▏  | 26466/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.89.down_proj:  72%|███████▏  | 26467/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.90.gate_proj:  72%|███████▏  | 26468/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.90.up_proj:  72%|███████▏  | 26469/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.90.down_proj:  72%|███████▏  | 26470/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.91.gate_proj:  72%|███████▏  | 26471/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.91.up_proj:  72%|███████▏  | 26472/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.91.down_proj:  72%|███████▏  | 26473/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.92.gate_proj:  72%|███████▏  | 26474/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.92.up_proj:  72%|███████▏  | 26475/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.92.down_proj:  72%|███████▏  | 26476/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.93.gate_proj:  72%|███████▏  | 26477/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.93.up_proj:  72%|███████▏  | 26478/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.93.down_proj:  72%|███████▏  | 26479/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.94.gate_proj:  72%|███████▏  | 26480/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.94.up_proj:  72%|███████▏  | 26481/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.94.down_proj:  72%|███████▏  | 26482/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.95.gate_proj:  72%|███████▏  | 26483/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.95.up_proj:  72%|███████▏  | 26484/36566 [00:24<00:08, 1160.59it/s]  
packing model.layers.67.mlp.experts.95.down_proj:  72%|███████▏  | 26485/36566 [00:24<00:08, 1160.59it/s]
packing model.layers.67.mlp.experts.95.down_proj:  72%|███████▏  | 26486/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.96.gate_proj:  72%|███████▏  | 26486/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.96.up_proj:  72%|███████▏  | 26487/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.96.down_proj:  72%|███████▏  | 26488/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.97.gate_proj:  72%|███████▏  | 26489/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.97.up_proj:  72%|███████▏  | 26490/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.97.down_proj:  72%|███████▏  | 26491/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.98.gate_proj:  72%|███████▏  | 26492/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.98.up_proj:  72%|███████▏  | 26493/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.98.down_proj:  72%|███████▏  | 26494/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.99.gate_proj:  72%|███████▏  | 26495/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.99.up_proj:  72%|███████▏  | 26496/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.99.down_proj:  72%|███████▏  | 26497/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.100.gate_proj:  72%|███████▏  | 26498/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.100.up_proj:  72%|███████▏  | 26499/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.100.down_proj:  72%|███████▏  | 26500/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.101.gate_proj:  72%|███████▏  | 26501/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.101.up_proj:  72%|███████▏  | 26502/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.101.down_proj:  72%|███████▏  | 26503/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.102.gate_proj:  72%|███████▏  | 26504/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.102.up_proj:  72%|███████▏  | 26505/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.102.down_proj:  72%|███████▏  | 26506/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.103.gate_proj:  72%|███████▏  | 26507/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.103.up_proj:  72%|███████▏  | 26508/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.103.down_proj:  72%|███████▏  | 26509/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.104.gate_proj:  72%|███████▏  | 26510/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.104.up_proj:  73%|███████▎  | 26511/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.104.down_proj:  73%|███████▎  | 26512/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.105.gate_proj:  73%|███████▎  | 26513/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.105.up_proj:  73%|███████▎  | 26514/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.105.down_proj:  73%|███████▎  | 26515/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.106.gate_proj:  73%|███████▎  | 26516/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.106.up_proj:  73%|███████▎  | 26517/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.106.down_proj:  73%|███████▎  | 26518/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.107.gate_proj:  73%|███████▎  | 26519/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.107.up_proj:  73%|███████▎  | 26520/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.107.down_proj:  73%|███████▎  | 26521/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.108.gate_proj:  73%|███████▎  | 26522/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.108.up_proj:  73%|███████▎  | 26523/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.108.down_proj:  73%|███████▎  | 26524/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.109.gate_proj:  73%|███████▎  | 26525/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.109.up_proj:  73%|███████▎  | 26526/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.109.down_proj:  73%|███████▎  | 26527/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.110.gate_proj:  73%|███████▎  | 26528/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.110.up_proj:  73%|███████▎  | 26529/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.110.down_proj:  73%|███████▎  | 26530/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.111.gate_proj:  73%|███████▎  | 26531/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.111.up_proj:  73%|███████▎  | 26532/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.111.down_proj:  73%|███████▎  | 26533/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.112.gate_proj:  73%|███████▎  | 26534/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.112.up_proj:  73%|███████▎  | 26535/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.112.down_proj:  73%|███████▎  | 26536/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.113.gate_proj:  73%|███████▎  | 26537/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.113.up_proj:  73%|███████▎  | 26538/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.113.down_proj:  73%|███████▎  | 26539/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.114.gate_proj:  73%|███████▎  | 26540/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.114.up_proj:  73%|███████▎  | 26541/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.114.down_proj:  73%|███████▎  | 26542/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.115.gate_proj:  73%|███████▎  | 26543/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.115.up_proj:  73%|███████▎  | 26544/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.115.down_proj:  73%|███████▎  | 26545/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.116.gate_proj:  73%|███████▎  | 26546/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.116.up_proj:  73%|███████▎  | 26547/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.116.down_proj:  73%|███████▎  | 26548/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.117.gate_proj:  73%|███████▎  | 26549/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.117.up_proj:  73%|███████▎  | 26550/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.117.down_proj:  73%|███████▎  | 26551/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.118.gate_proj:  73%|███████▎  | 26552/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.118.up_proj:  73%|███████▎  | 26553/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.118.down_proj:  73%|███████▎  | 26554/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.119.gate_proj:  73%|███████▎  | 26555/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.119.up_proj:  73%|███████▎  | 26556/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.119.down_proj:  73%|███████▎  | 26557/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.120.gate_proj:  73%|███████▎  | 26558/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.120.up_proj:  73%|███████▎  | 26559/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.120.down_proj:  73%|███████▎  | 26560/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.121.gate_proj:  73%|███████▎  | 26561/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.121.up_proj:  73%|███████▎  | 26562/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.121.down_proj:  73%|███████▎  | 26563/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.122.gate_proj:  73%|███████▎  | 26564/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.122.up_proj:  73%|███████▎  | 26565/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.122.down_proj:  73%|███████▎  | 26566/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.123.gate_proj:  73%|███████▎  | 26567/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.123.up_proj:  73%|███████▎  | 26568/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.123.down_proj:  73%|███████▎  | 26569/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.124.gate_proj:  73%|███████▎  | 26570/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.124.up_proj:  73%|███████▎  | 26571/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.124.down_proj:  73%|███████▎  | 26572/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.125.gate_proj:  73%|███████▎  | 26573/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.125.up_proj:  73%|███████▎  | 26574/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.125.down_proj:  73%|███████▎  | 26575/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.126.gate_proj:  73%|███████▎  | 26576/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.126.up_proj:  73%|███████▎  | 26577/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.126.down_proj:  73%|███████▎  | 26578/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.127.gate_proj:  73%|███████▎  | 26579/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.67.mlp.experts.127.up_proj:  73%|███████▎  | 26580/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.67.mlp.experts.127.down_proj:  73%|███████▎  | 26581/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.0.gate_proj:  73%|███████▎  | 26582/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.0.up_proj:  73%|███████▎  | 26583/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.0.down_proj:  73%|███████▎  | 26584/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.1.gate_proj:  73%|███████▎  | 26585/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.1.up_proj:  73%|███████▎  | 26586/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.1.down_proj:  73%|███████▎  | 26587/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.2.gate_proj:  73%|███████▎  | 26588/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.2.up_proj:  73%|███████▎  | 26589/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.2.down_proj:  73%|███████▎  | 26590/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.3.gate_proj:  73%|███████▎  | 26591/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.3.up_proj:  73%|███████▎  | 26592/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.3.down_proj:  73%|███████▎  | 26593/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.4.gate_proj:  73%|███████▎  | 26594/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.4.up_proj:  73%|███████▎  | 26595/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.4.down_proj:  73%|███████▎  | 26596/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.5.gate_proj:  73%|███████▎  | 26597/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.5.up_proj:  73%|███████▎  | 26598/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.5.down_proj:  73%|███████▎  | 26599/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.6.gate_proj:  73%|███████▎  | 26600/36566 [00:24<00:08, 1159.25it/s]
packing model.layers.68.mlp.experts.6.up_proj:  73%|███████▎  | 26601/36566 [00:24<00:08, 1159.25it/s]  
packing model.layers.68.mlp.experts.6.up_proj:  73%|███████▎  | 26602/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.6.down_proj:  73%|███████▎  | 26602/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.7.gate_proj:  73%|███████▎  | 26603/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.7.up_proj:  73%|███████▎  | 26604/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.7.down_proj:  73%|███████▎  | 26605/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.8.gate_proj:  73%|███████▎  | 26606/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.8.up_proj:  73%|███████▎  | 26607/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.8.down_proj:  73%|███████▎  | 26608/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.9.gate_proj:  73%|███████▎  | 26609/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.9.up_proj:  73%|███████▎  | 26610/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.9.down_proj:  73%|███████▎  | 26611/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.10.gate_proj:  73%|███████▎  | 26612/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.10.up_proj:  73%|███████▎  | 26613/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.10.down_proj:  73%|███████▎  | 26614/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.11.gate_proj:  73%|███████▎  | 26615/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.11.up_proj:  73%|███████▎  | 26616/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.11.down_proj:  73%|███████▎  | 26617/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.12.gate_proj:  73%|███████▎  | 26618/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.12.up_proj:  73%|███████▎  | 26619/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.12.down_proj:  73%|███████▎  | 26620/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.13.gate_proj:  73%|███████▎  | 26621/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.13.up_proj:  73%|███████▎  | 26622/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.13.down_proj:  73%|███████▎  | 26623/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.14.gate_proj:  73%|███████▎  | 26624/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.14.up_proj:  73%|███████▎  | 26625/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.14.down_proj:  73%|███████▎  | 26626/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.15.gate_proj:  73%|███████▎  | 26627/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.15.up_proj:  73%|███████▎  | 26628/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.15.down_proj:  73%|███████▎  | 26629/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.16.gate_proj:  73%|███████▎  | 26630/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.16.up_proj:  73%|███████▎  | 26631/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.16.down_proj:  73%|███████▎  | 26632/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.17.gate_proj:  73%|███████▎  | 26633/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.17.up_proj:  73%|███████▎  | 26634/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.17.down_proj:  73%|███████▎  | 26635/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.18.gate_proj:  73%|███████▎  | 26636/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.18.up_proj:  73%|███████▎  | 26637/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.18.down_proj:  73%|███████▎  | 26638/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.19.gate_proj:  73%|███████▎  | 26639/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.19.up_proj:  73%|███████▎  | 26640/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.19.down_proj:  73%|███████▎  | 26641/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.20.gate_proj:  73%|███████▎  | 26642/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.20.up_proj:  73%|███████▎  | 26643/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.20.down_proj:  73%|███████▎  | 26644/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.21.gate_proj:  73%|███████▎  | 26645/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.21.up_proj:  73%|███████▎  | 26646/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.21.down_proj:  73%|███████▎  | 26647/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.22.gate_proj:  73%|███████▎  | 26648/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.22.up_proj:  73%|███████▎  | 26649/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.22.down_proj:  73%|███████▎  | 26650/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.23.gate_proj:  73%|███████▎  | 26651/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.23.up_proj:  73%|███████▎  | 26652/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.23.down_proj:  73%|███████▎  | 26653/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.24.gate_proj:  73%|███████▎  | 26654/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.24.up_proj:  73%|███████▎  | 26655/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.24.down_proj:  73%|███████▎  | 26656/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.25.gate_proj:  73%|███████▎  | 26657/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.25.up_proj:  73%|███████▎  | 26658/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.25.down_proj:  73%|███████▎  | 26659/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.26.gate_proj:  73%|███████▎  | 26660/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.26.up_proj:  73%|███████▎  | 26661/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.26.down_proj:  73%|███████▎  | 26662/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.27.gate_proj:  73%|███████▎  | 26663/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.27.up_proj:  73%|███████▎  | 26664/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.27.down_proj:  73%|███████▎  | 26665/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.28.gate_proj:  73%|███████▎  | 26666/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.28.up_proj:  73%|███████▎  | 26667/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.28.down_proj:  73%|███████▎  | 26668/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.29.gate_proj:  73%|███████▎  | 26669/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.29.up_proj:  73%|███████▎  | 26670/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.29.down_proj:  73%|███████▎  | 26671/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.30.gate_proj:  73%|███████▎  | 26672/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.30.up_proj:  73%|███████▎  | 26673/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.30.down_proj:  73%|███████▎  | 26674/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.31.gate_proj:  73%|███████▎  | 26675/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.31.up_proj:  73%|███████▎  | 26676/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.31.down_proj:  73%|███████▎  | 26677/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.32.gate_proj:  73%|███████▎  | 26678/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.32.up_proj:  73%|███████▎  | 26679/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.32.down_proj:  73%|███████▎  | 26680/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.33.gate_proj:  73%|███████▎  | 26681/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.33.up_proj:  73%|███████▎  | 26682/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.33.down_proj:  73%|███████▎  | 26683/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.34.gate_proj:  73%|███████▎  | 26684/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.34.up_proj:  73%|███████▎  | 26685/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.34.down_proj:  73%|███████▎  | 26686/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.35.gate_proj:  73%|███████▎  | 26687/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.35.up_proj:  73%|███████▎  | 26688/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.35.down_proj:  73%|███████▎  | 26689/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.36.gate_proj:  73%|███████▎  | 26690/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.36.up_proj:  73%|███████▎  | 26691/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.36.down_proj:  73%|███████▎  | 26692/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.37.gate_proj:  73%|███████▎  | 26693/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.37.up_proj:  73%|███████▎  | 26694/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.37.down_proj:  73%|███████▎  | 26695/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.38.gate_proj:  73%|███████▎  | 26696/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.38.up_proj:  73%|███████▎  | 26697/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.38.down_proj:  73%|███████▎  | 26698/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.39.gate_proj:  73%|███████▎  | 26699/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.39.up_proj:  73%|███████▎  | 26700/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.39.down_proj:  73%|███████▎  | 26701/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.40.gate_proj:  73%|███████▎  | 26702/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.40.up_proj:  73%|███████▎  | 26703/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.40.down_proj:  73%|███████▎  | 26704/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.41.gate_proj:  73%|███████▎  | 26705/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.41.up_proj:  73%|███████▎  | 26706/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.41.down_proj:  73%|███████▎  | 26707/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.42.gate_proj:  73%|███████▎  | 26708/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.42.up_proj:  73%|███████▎  | 26709/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.42.down_proj:  73%|███████▎  | 26710/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.43.gate_proj:  73%|███████▎  | 26711/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.43.up_proj:  73%|███████▎  | 26712/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.43.down_proj:  73%|███████▎  | 26713/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.44.gate_proj:  73%|███████▎  | 26714/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.44.up_proj:  73%|███████▎  | 26715/36566 [00:24<00:08, 1156.42it/s]  
packing model.layers.68.mlp.experts.44.down_proj:  73%|███████▎  | 26716/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.45.gate_proj:  73%|███████▎  | 26717/36566 [00:24<00:08, 1156.42it/s]
packing model.layers.68.mlp.experts.45.gate_proj:  73%|███████▎  | 26718/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.45.up_proj:  73%|███████▎  | 26718/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.45.down_proj:  73%|███████▎  | 26719/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.46.gate_proj:  73%|███████▎  | 26720/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.46.up_proj:  73%|███████▎  | 26721/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.46.down_proj:  73%|███████▎  | 26722/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.47.gate_proj:  73%|███████▎  | 26723/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.47.up_proj:  73%|███████▎  | 26724/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.47.down_proj:  73%|███████▎  | 26725/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.48.gate_proj:  73%|███████▎  | 26726/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.48.up_proj:  73%|███████▎  | 26727/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.48.down_proj:  73%|███████▎  | 26728/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.49.gate_proj:  73%|███████▎  | 26729/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.49.up_proj:  73%|███████▎  | 26730/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.49.down_proj:  73%|███████▎  | 26731/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.50.gate_proj:  73%|███████▎  | 26732/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.50.up_proj:  73%|███████▎  | 26733/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.50.down_proj:  73%|███████▎  | 26734/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.51.gate_proj:  73%|███████▎  | 26735/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.51.up_proj:  73%|███████▎  | 26736/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.51.down_proj:  73%|███████▎  | 26737/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.52.gate_proj:  73%|███████▎  | 26738/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.52.up_proj:  73%|███████▎  | 26739/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.52.down_proj:  73%|███████▎  | 26740/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.53.gate_proj:  73%|███████▎  | 26741/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.53.up_proj:  73%|███████▎  | 26742/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.53.down_proj:  73%|███████▎  | 26743/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.54.gate_proj:  73%|███████▎  | 26744/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.54.up_proj:  73%|███████▎  | 26745/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.54.down_proj:  73%|███████▎  | 26746/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.55.gate_proj:  73%|███████▎  | 26747/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.55.up_proj:  73%|███████▎  | 26748/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.55.down_proj:  73%|███████▎  | 26749/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.56.gate_proj:  73%|███████▎  | 26750/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.56.up_proj:  73%|███████▎  | 26751/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.56.down_proj:  73%|███████▎  | 26752/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.57.gate_proj:  73%|███████▎  | 26753/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.57.up_proj:  73%|███████▎  | 26754/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.57.down_proj:  73%|███████▎  | 26755/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.58.gate_proj:  73%|███████▎  | 26756/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.58.up_proj:  73%|███████▎  | 26757/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.58.down_proj:  73%|███████▎  | 26758/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.59.gate_proj:  73%|███████▎  | 26759/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.59.up_proj:  73%|███████▎  | 26760/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.59.down_proj:  73%|███████▎  | 26761/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.60.gate_proj:  73%|███████▎  | 26762/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.60.up_proj:  73%|███████▎  | 26763/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.60.down_proj:  73%|███████▎  | 26764/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.61.gate_proj:  73%|███████▎  | 26765/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.61.up_proj:  73%|███████▎  | 26766/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.61.down_proj:  73%|███████▎  | 26767/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.62.gate_proj:  73%|███████▎  | 26768/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.62.up_proj:  73%|███████▎  | 26769/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.62.down_proj:  73%|███████▎  | 26770/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.63.gate_proj:  73%|███████▎  | 26771/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.63.up_proj:  73%|███████▎  | 26772/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.63.down_proj:  73%|███████▎  | 26773/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.64.gate_proj:  73%|███████▎  | 26774/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.64.up_proj:  73%|███████▎  | 26775/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.64.down_proj:  73%|███████▎  | 26776/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.65.gate_proj:  73%|███████▎  | 26777/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.65.up_proj:  73%|███████▎  | 26778/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.65.down_proj:  73%|███████▎  | 26779/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.66.gate_proj:  73%|███████▎  | 26780/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.66.up_proj:  73%|███████▎  | 26781/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.66.down_proj:  73%|███████▎  | 26782/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.67.gate_proj:  73%|███████▎  | 26783/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.67.up_proj:  73%|███████▎  | 26784/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.67.down_proj:  73%|███████▎  | 26785/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.68.gate_proj:  73%|███████▎  | 26786/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.68.up_proj:  73%|███████▎  | 26787/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.68.down_proj:  73%|███████▎  | 26788/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.69.gate_proj:  73%|███████▎  | 26789/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.69.up_proj:  73%|███████▎  | 26790/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.69.down_proj:  73%|███████▎  | 26791/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.70.gate_proj:  73%|███████▎  | 26792/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.70.up_proj:  73%|███████▎  | 26793/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.70.down_proj:  73%|███████▎  | 26794/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.71.gate_proj:  73%|███████▎  | 26795/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.71.up_proj:  73%|███████▎  | 26796/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.71.down_proj:  73%|███████▎  | 26797/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.72.gate_proj:  73%|███████▎  | 26798/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.72.up_proj:  73%|███████▎  | 26799/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.72.down_proj:  73%|███████▎  | 26800/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.73.gate_proj:  73%|███████▎  | 26801/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.73.up_proj:  73%|███████▎  | 26802/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.73.down_proj:  73%|███████▎  | 26803/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.74.gate_proj:  73%|███████▎  | 26804/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.74.up_proj:  73%|███████▎  | 26805/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.74.down_proj:  73%|███████▎  | 26806/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.75.gate_proj:  73%|███████▎  | 26807/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.75.up_proj:  73%|███████▎  | 26808/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.75.down_proj:  73%|███████▎  | 26809/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.76.gate_proj:  73%|███████▎  | 26810/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.76.up_proj:  73%|███████▎  | 26811/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.76.down_proj:  73%|███████▎  | 26812/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.77.gate_proj:  73%|███████▎  | 26813/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.77.up_proj:  73%|███████▎  | 26814/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.77.down_proj:  73%|███████▎  | 26815/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.78.gate_proj:  73%|███████▎  | 26816/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.78.up_proj:  73%|███████▎  | 26817/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.78.down_proj:  73%|███████▎  | 26818/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.79.gate_proj:  73%|███████▎  | 26819/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.79.up_proj:  73%|███████▎  | 26820/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.79.down_proj:  73%|███████▎  | 26821/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.80.gate_proj:  73%|███████▎  | 26822/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.80.up_proj:  73%|███████▎  | 26823/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.80.down_proj:  73%|███████▎  | 26824/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.81.gate_proj:  73%|███████▎  | 26825/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.81.up_proj:  73%|███████▎  | 26826/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.81.down_proj:  73%|███████▎  | 26827/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.82.gate_proj:  73%|███████▎  | 26828/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.82.up_proj:  73%|███████▎  | 26829/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.82.down_proj:  73%|███████▎  | 26830/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.83.gate_proj:  73%|███████▎  | 26831/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.83.up_proj:  73%|███████▎  | 26832/36566 [00:24<00:08, 1153.73it/s]  
packing model.layers.68.mlp.experts.83.down_proj:  73%|███████▎  | 26833/36566 [00:24<00:08, 1153.73it/s]
packing model.layers.68.mlp.experts.83.down_proj:  73%|███████▎  | 26834/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.84.gate_proj:  73%|███████▎  | 26834/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.84.up_proj:  73%|███████▎  | 26835/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.84.down_proj:  73%|███████▎  | 26836/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.85.gate_proj:  73%|███████▎  | 26837/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.85.up_proj:  73%|███████▎  | 26838/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.85.down_proj:  73%|███████▎  | 26839/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.86.gate_proj:  73%|███████▎  | 26840/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.86.up_proj:  73%|███████▎  | 26841/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.86.down_proj:  73%|███████▎  | 26842/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.87.gate_proj:  73%|███████▎  | 26843/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.87.up_proj:  73%|███████▎  | 26844/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.87.down_proj:  73%|███████▎  | 26845/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.88.gate_proj:  73%|███████▎  | 26846/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.88.up_proj:  73%|███████▎  | 26847/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.88.down_proj:  73%|███████▎  | 26848/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.89.gate_proj:  73%|███████▎  | 26849/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.89.up_proj:  73%|███████▎  | 26850/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.89.down_proj:  73%|███████▎  | 26851/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.90.gate_proj:  73%|███████▎  | 26852/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.90.up_proj:  73%|███████▎  | 26853/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.90.down_proj:  73%|███████▎  | 26854/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.91.gate_proj:  73%|███████▎  | 26855/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.91.up_proj:  73%|███████▎  | 26856/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.91.down_proj:  73%|███████▎  | 26857/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.92.gate_proj:  73%|███████▎  | 26858/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.92.up_proj:  73%|███████▎  | 26859/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.92.down_proj:  73%|███████▎  | 26860/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.93.gate_proj:  73%|███████▎  | 26861/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.93.up_proj:  73%|███████▎  | 26862/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.93.down_proj:  73%|███████▎  | 26863/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.94.gate_proj:  73%|███████▎  | 26864/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.94.up_proj:  73%|███████▎  | 26865/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.94.down_proj:  73%|███████▎  | 26866/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.95.gate_proj:  73%|███████▎  | 26867/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.95.up_proj:  73%|███████▎  | 26868/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.95.down_proj:  73%|███████▎  | 26869/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.96.gate_proj:  73%|███████▎  | 26870/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.96.up_proj:  73%|███████▎  | 26871/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.96.down_proj:  73%|███████▎  | 26872/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.97.gate_proj:  73%|███████▎  | 26873/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.97.up_proj:  73%|███████▎  | 26874/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.97.down_proj:  73%|███████▎  | 26875/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.98.gate_proj:  73%|███████▎  | 26876/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.98.up_proj:  74%|███████▎  | 26877/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.98.down_proj:  74%|███████▎  | 26878/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.99.gate_proj:  74%|███████▎  | 26879/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.99.up_proj:  74%|███████▎  | 26880/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.99.down_proj:  74%|███████▎  | 26881/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.100.gate_proj:  74%|███████▎  | 26882/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.100.up_proj:  74%|███████▎  | 26883/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.100.down_proj:  74%|███████▎  | 26884/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.101.gate_proj:  74%|███████▎  | 26885/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.101.up_proj:  74%|███████▎  | 26886/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.101.down_proj:  74%|███████▎  | 26887/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.102.gate_proj:  74%|███████▎  | 26888/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.102.up_proj:  74%|███████▎  | 26889/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.102.down_proj:  74%|███████▎  | 26890/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.103.gate_proj:  74%|███████▎  | 26891/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.103.up_proj:  74%|███████▎  | 26892/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.103.down_proj:  74%|███████▎  | 26893/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.104.gate_proj:  74%|███████▎  | 26894/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.104.up_proj:  74%|███████▎  | 26895/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.104.down_proj:  74%|███████▎  | 26896/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.105.gate_proj:  74%|███████▎  | 26897/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.105.up_proj:  74%|███████▎  | 26898/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.105.down_proj:  74%|███████▎  | 26899/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.106.gate_proj:  74%|███████▎  | 26900/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.106.up_proj:  74%|███████▎  | 26901/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.106.down_proj:  74%|███████▎  | 26902/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.107.gate_proj:  74%|███████▎  | 26903/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.107.up_proj:  74%|███████▎  | 26904/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.107.down_proj:  74%|███████▎  | 26905/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.108.gate_proj:  74%|███████▎  | 26906/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.108.up_proj:  74%|███████▎  | 26907/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.108.down_proj:  74%|███████▎  | 26908/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.109.gate_proj:  74%|███████▎  | 26909/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.109.up_proj:  74%|███████▎  | 26910/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.109.down_proj:  74%|███████▎  | 26911/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.110.gate_proj:  74%|███████▎  | 26912/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.110.up_proj:  74%|███████▎  | 26913/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.110.down_proj:  74%|███████▎  | 26914/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.111.gate_proj:  74%|███████▎  | 26915/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.111.up_proj:  74%|███████▎  | 26916/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.111.down_proj:  74%|███████▎  | 26917/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.112.gate_proj:  74%|███████▎  | 26918/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.112.up_proj:  74%|███████▎  | 26919/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.112.down_proj:  74%|███████▎  | 26920/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.113.gate_proj:  74%|███████▎  | 26921/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.113.up_proj:  74%|███████▎  | 26922/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.113.down_proj:  74%|███████▎  | 26923/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.114.gate_proj:  74%|███████▎  | 26924/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.114.up_proj:  74%|███████▎  | 26925/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.114.down_proj:  74%|███████▎  | 26926/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.115.gate_proj:  74%|███████▎  | 26927/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.115.up_proj:  74%|███████▎  | 26928/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.115.down_proj:  74%|███████▎  | 26929/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.116.gate_proj:  74%|███████▎  | 26930/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.116.up_proj:  74%|███████▎  | 26931/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.116.down_proj:  74%|███████▎  | 26932/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.117.gate_proj:  74%|███████▎  | 26933/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.117.up_proj:  74%|███████▎  | 26934/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.117.down_proj:  74%|███████▎  | 26935/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.118.gate_proj:  74%|███████▎  | 26936/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.118.up_proj:  74%|███████▎  | 26937/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.118.down_proj:  74%|███████▎  | 26938/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.119.gate_proj:  74%|███████▎  | 26939/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.119.up_proj:  74%|███████▎  | 26940/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.119.down_proj:  74%|███████▎  | 26941/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.120.gate_proj:  74%|███████▎  | 26942/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.120.up_proj:  74%|███████▎  | 26943/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.120.down_proj:  74%|███████▎  | 26944/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.121.gate_proj:  74%|███████▎  | 26945/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.121.up_proj:  74%|███████▎  | 26946/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.121.down_proj:  74%|███████▎  | 26947/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.122.gate_proj:  74%|███████▎  | 26948/36566 [00:24<00:08, 1153.67it/s]
packing model.layers.68.mlp.experts.122.up_proj:  74%|███████▎  | 26949/36566 [00:24<00:08, 1153.67it/s]  
packing model.layers.68.mlp.experts.122.up_proj:  74%|███████▎  | 26950/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.122.down_proj:  74%|███████▎  | 26950/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.123.gate_proj:  74%|███████▎  | 26951/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.123.up_proj:  74%|███████▎  | 26952/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.68.mlp.experts.123.down_proj:  74%|███████▎  | 26953/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.124.gate_proj:  74%|███████▎  | 26954/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.124.up_proj:  74%|███████▎  | 26955/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.68.mlp.experts.124.down_proj:  74%|███████▎  | 26956/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.125.gate_proj:  74%|███████▎  | 26957/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.125.up_proj:  74%|███████▎  | 26958/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.68.mlp.experts.125.down_proj:  74%|███████▎  | 26959/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.126.gate_proj:  74%|███████▎  | 26960/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.126.up_proj:  74%|███████▎  | 26961/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.68.mlp.experts.126.down_proj:  74%|███████▎  | 26962/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.127.gate_proj:  74%|███████▎  | 26963/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.68.mlp.experts.127.up_proj:  74%|███████▎  | 26964/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.68.mlp.experts.127.down_proj:  74%|███████▎  | 26965/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.0.gate_proj:  74%|███████▎  | 26966/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.0.up_proj:  74%|███████▎  | 26967/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.0.down_proj:  74%|███████▍  | 26968/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.1.gate_proj:  74%|███████▍  | 26969/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.1.up_proj:  74%|███████▍  | 26970/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.1.down_proj:  74%|███████▍  | 26971/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.2.gate_proj:  74%|███████▍  | 26972/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.2.up_proj:  74%|███████▍  | 26973/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.2.down_proj:  74%|███████▍  | 26974/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.3.gate_proj:  74%|███████▍  | 26975/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.3.up_proj:  74%|███████▍  | 26976/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.3.down_proj:  74%|███████▍  | 26977/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.4.gate_proj:  74%|███████▍  | 26978/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.4.up_proj:  74%|███████▍  | 26979/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.4.down_proj:  74%|███████▍  | 26980/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.5.gate_proj:  74%|███████▍  | 26981/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.5.up_proj:  74%|███████▍  | 26982/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.5.down_proj:  74%|███████▍  | 26983/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.6.gate_proj:  74%|███████▍  | 26984/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.6.up_proj:  74%|███████▍  | 26985/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.6.down_proj:  74%|███████▍  | 26986/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.7.gate_proj:  74%|███████▍  | 26987/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.7.up_proj:  74%|███████▍  | 26988/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.7.down_proj:  74%|███████▍  | 26989/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.8.gate_proj:  74%|███████▍  | 26990/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.8.up_proj:  74%|███████▍  | 26991/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.8.down_proj:  74%|███████▍  | 26992/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.9.gate_proj:  74%|███████▍  | 26993/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.9.up_proj:  74%|███████▍  | 26994/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.9.down_proj:  74%|███████▍  | 26995/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.10.gate_proj:  74%|███████▍  | 26996/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.10.up_proj:  74%|███████▍  | 26997/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.10.down_proj:  74%|███████▍  | 26998/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.11.gate_proj:  74%|███████▍  | 26999/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.11.up_proj:  74%|███████▍  | 27000/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.11.down_proj:  74%|███████▍  | 27001/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.12.gate_proj:  74%|███████▍  | 27002/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.12.up_proj:  74%|███████▍  | 27003/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.12.down_proj:  74%|███████▍  | 27004/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.13.gate_proj:  74%|███████▍  | 27005/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.13.up_proj:  74%|███████▍  | 27006/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.13.down_proj:  74%|███████▍  | 27007/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.14.gate_proj:  74%|███████▍  | 27008/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.14.up_proj:  74%|███████▍  | 27009/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.14.down_proj:  74%|███████▍  | 27010/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.15.gate_proj:  74%|███████▍  | 27011/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.15.up_proj:  74%|███████▍  | 27012/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.15.down_proj:  74%|███████▍  | 27013/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.16.gate_proj:  74%|███████▍  | 27014/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.16.up_proj:  74%|███████▍  | 27015/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.16.down_proj:  74%|███████▍  | 27016/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.17.gate_proj:  74%|███████▍  | 27017/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.17.up_proj:  74%|███████▍  | 27018/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.17.down_proj:  74%|███████▍  | 27019/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.18.gate_proj:  74%|███████▍  | 27020/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.18.up_proj:  74%|███████▍  | 27021/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.18.down_proj:  74%|███████▍  | 27022/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.19.gate_proj:  74%|███████▍  | 27023/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.19.up_proj:  74%|███████▍  | 27024/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.19.down_proj:  74%|███████▍  | 27025/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.20.gate_proj:  74%|███████▍  | 27026/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.20.up_proj:  74%|███████▍  | 27027/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.20.down_proj:  74%|███████▍  | 27028/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.21.gate_proj:  74%|███████▍  | 27029/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.21.up_proj:  74%|███████▍  | 27030/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.21.down_proj:  74%|███████▍  | 27031/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.22.gate_proj:  74%|███████▍  | 27032/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.22.up_proj:  74%|███████▍  | 27033/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.22.down_proj:  74%|███████▍  | 27034/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.23.gate_proj:  74%|███████▍  | 27035/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.23.up_proj:  74%|███████▍  | 27036/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.23.down_proj:  74%|███████▍  | 27037/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.24.gate_proj:  74%|███████▍  | 27038/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.24.up_proj:  74%|███████▍  | 27039/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.24.down_proj:  74%|███████▍  | 27040/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.25.gate_proj:  74%|███████▍  | 27041/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.25.up_proj:  74%|███████▍  | 27042/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.25.down_proj:  74%|███████▍  | 27043/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.26.gate_proj:  74%|███████▍  | 27044/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.26.up_proj:  74%|███████▍  | 27045/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.26.down_proj:  74%|███████▍  | 27046/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.27.gate_proj:  74%|███████▍  | 27047/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.27.up_proj:  74%|███████▍  | 27048/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.27.down_proj:  74%|███████▍  | 27049/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.28.gate_proj:  74%|███████▍  | 27050/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.28.up_proj:  74%|███████▍  | 27051/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.28.down_proj:  74%|███████▍  | 27052/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.29.gate_proj:  74%|███████▍  | 27053/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.29.up_proj:  74%|███████▍  | 27054/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.29.down_proj:  74%|███████▍  | 27055/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.30.gate_proj:  74%|███████▍  | 27056/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.30.up_proj:  74%|███████▍  | 27057/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.30.down_proj:  74%|███████▍  | 27058/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.31.gate_proj:  74%|███████▍  | 27059/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.31.up_proj:  74%|███████▍  | 27060/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.31.down_proj:  74%|███████▍  | 27061/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.32.gate_proj:  74%|███████▍  | 27062/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.32.up_proj:  74%|███████▍  | 27063/36566 [00:24<00:08, 1154.20it/s]  
packing model.layers.69.mlp.experts.32.down_proj:  74%|███████▍  | 27064/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.33.gate_proj:  74%|███████▍  | 27065/36566 [00:24<00:08, 1154.20it/s]
packing model.layers.69.mlp.experts.33.gate_proj:  74%|███████▍  | 27066/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.33.up_proj:  74%|███████▍  | 27066/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.33.down_proj:  74%|███████▍  | 27067/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.34.gate_proj:  74%|███████▍  | 27068/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.34.up_proj:  74%|███████▍  | 27069/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.34.down_proj:  74%|███████▍  | 27070/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.35.gate_proj:  74%|███████▍  | 27071/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.35.up_proj:  74%|███████▍  | 27072/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.35.down_proj:  74%|███████▍  | 27073/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.36.gate_proj:  74%|███████▍  | 27074/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.36.up_proj:  74%|███████▍  | 27075/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.36.down_proj:  74%|███████▍  | 27076/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.37.gate_proj:  74%|███████▍  | 27077/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.37.up_proj:  74%|███████▍  | 27078/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.37.down_proj:  74%|███████▍  | 27079/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.38.gate_proj:  74%|███████▍  | 27080/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.38.up_proj:  74%|███████▍  | 27081/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.38.down_proj:  74%|███████▍  | 27082/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.39.gate_proj:  74%|███████▍  | 27083/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.39.up_proj:  74%|███████▍  | 27084/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.39.down_proj:  74%|███████▍  | 27085/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.40.gate_proj:  74%|███████▍  | 27086/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.40.up_proj:  74%|███████▍  | 27087/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.40.down_proj:  74%|███████▍  | 27088/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.41.gate_proj:  74%|███████▍  | 27089/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.41.up_proj:  74%|███████▍  | 27090/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.41.down_proj:  74%|███████▍  | 27091/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.42.gate_proj:  74%|███████▍  | 27092/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.42.up_proj:  74%|███████▍  | 27093/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.42.down_proj:  74%|███████▍  | 27094/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.43.gate_proj:  74%|███████▍  | 27095/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.43.up_proj:  74%|███████▍  | 27096/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.43.down_proj:  74%|███████▍  | 27097/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.44.gate_proj:  74%|███████▍  | 27098/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.44.up_proj:  74%|███████▍  | 27099/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.44.down_proj:  74%|███████▍  | 27100/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.45.gate_proj:  74%|███████▍  | 27101/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.45.up_proj:  74%|███████▍  | 27102/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.45.down_proj:  74%|███████▍  | 27103/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.46.gate_proj:  74%|███████▍  | 27104/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.46.up_proj:  74%|███████▍  | 27105/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.46.down_proj:  74%|███████▍  | 27106/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.47.gate_proj:  74%|███████▍  | 27107/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.47.up_proj:  74%|███████▍  | 27108/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.47.down_proj:  74%|███████▍  | 27109/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.48.gate_proj:  74%|███████▍  | 27110/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.48.up_proj:  74%|███████▍  | 27111/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.48.down_proj:  74%|███████▍  | 27112/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.49.gate_proj:  74%|███████▍  | 27113/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.49.up_proj:  74%|███████▍  | 27114/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.49.down_proj:  74%|███████▍  | 27115/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.50.gate_proj:  74%|███████▍  | 27116/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.50.up_proj:  74%|███████▍  | 27117/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.50.down_proj:  74%|███████▍  | 27118/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.51.gate_proj:  74%|███████▍  | 27119/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.51.up_proj:  74%|███████▍  | 27120/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.51.down_proj:  74%|███████▍  | 27121/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.52.gate_proj:  74%|███████▍  | 27122/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.52.up_proj:  74%|███████▍  | 27123/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.52.down_proj:  74%|███████▍  | 27124/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.53.gate_proj:  74%|███████▍  | 27125/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.53.up_proj:  74%|███████▍  | 27126/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.53.down_proj:  74%|███████▍  | 27127/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.54.gate_proj:  74%|███████▍  | 27128/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.54.up_proj:  74%|███████▍  | 27129/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.54.down_proj:  74%|███████▍  | 27130/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.55.gate_proj:  74%|███████▍  | 27131/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.55.up_proj:  74%|███████▍  | 27132/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.55.down_proj:  74%|███████▍  | 27133/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.56.gate_proj:  74%|███████▍  | 27134/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.56.up_proj:  74%|███████▍  | 27135/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.56.down_proj:  74%|███████▍  | 27136/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.57.gate_proj:  74%|███████▍  | 27137/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.57.up_proj:  74%|███████▍  | 27138/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.57.down_proj:  74%|███████▍  | 27139/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.58.gate_proj:  74%|███████▍  | 27140/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.58.up_proj:  74%|███████▍  | 27141/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.58.down_proj:  74%|███████▍  | 27142/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.59.gate_proj:  74%|███████▍  | 27143/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.59.up_proj:  74%|███████▍  | 27144/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.59.down_proj:  74%|███████▍  | 27145/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.60.gate_proj:  74%|███████▍  | 27146/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.60.up_proj:  74%|███████▍  | 27147/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.60.down_proj:  74%|███████▍  | 27148/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.61.gate_proj:  74%|███████▍  | 27149/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.61.up_proj:  74%|███████▍  | 27150/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.61.down_proj:  74%|███████▍  | 27151/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.62.gate_proj:  74%|███████▍  | 27152/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.62.up_proj:  74%|███████▍  | 27153/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.62.down_proj:  74%|███████▍  | 27154/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.63.gate_proj:  74%|███████▍  | 27155/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.63.up_proj:  74%|███████▍  | 27156/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.63.down_proj:  74%|███████▍  | 27157/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.64.gate_proj:  74%|███████▍  | 27158/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.64.up_proj:  74%|███████▍  | 27159/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.64.down_proj:  74%|███████▍  | 27160/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.65.gate_proj:  74%|███████▍  | 27161/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.65.up_proj:  74%|███████▍  | 27162/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.65.down_proj:  74%|███████▍  | 27163/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.66.gate_proj:  74%|███████▍  | 27164/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.66.up_proj:  74%|███████▍  | 27165/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.66.down_proj:  74%|███████▍  | 27166/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.67.gate_proj:  74%|███████▍  | 27167/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.67.up_proj:  74%|███████▍  | 27168/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.67.down_proj:  74%|███████▍  | 27169/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.68.gate_proj:  74%|███████▍  | 27170/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.68.up_proj:  74%|███████▍  | 27171/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.68.down_proj:  74%|███████▍  | 27172/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.69.gate_proj:  74%|███████▍  | 27173/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.69.up_proj:  74%|███████▍  | 27174/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.69.down_proj:  74%|███████▍  | 27175/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.70.gate_proj:  74%|███████▍  | 27176/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.70.up_proj:  74%|███████▍  | 27177/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.70.down_proj:  74%|███████▍  | 27178/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.71.gate_proj:  74%|███████▍  | 27179/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.71.up_proj:  74%|███████▍  | 27180/36566 [00:24<00:08, 1154.51it/s]  
packing model.layers.69.mlp.experts.71.down_proj:  74%|███████▍  | 27181/36566 [00:24<00:08, 1154.51it/s]
packing model.layers.69.mlp.experts.71.down_proj:  74%|███████▍  | 27182/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.72.gate_proj:  74%|███████▍  | 27182/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.72.up_proj:  74%|███████▍  | 27183/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.72.down_proj:  74%|███████▍  | 27184/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.73.gate_proj:  74%|███████▍  | 27185/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.73.up_proj:  74%|███████▍  | 27186/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.73.down_proj:  74%|███████▍  | 27187/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.74.gate_proj:  74%|███████▍  | 27188/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.74.up_proj:  74%|███████▍  | 27189/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.74.down_proj:  74%|███████▍  | 27190/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.75.gate_proj:  74%|███████▍  | 27191/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.75.up_proj:  74%|███████▍  | 27192/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.75.down_proj:  74%|███████▍  | 27193/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.76.gate_proj:  74%|███████▍  | 27194/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.76.up_proj:  74%|███████▍  | 27195/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.76.down_proj:  74%|███████▍  | 27196/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.77.gate_proj:  74%|███████▍  | 27197/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.77.up_proj:  74%|███████▍  | 27198/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.77.down_proj:  74%|███████▍  | 27199/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.78.gate_proj:  74%|███████▍  | 27200/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.78.up_proj:  74%|███████▍  | 27201/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.78.down_proj:  74%|███████▍  | 27202/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.79.gate_proj:  74%|███████▍  | 27203/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.79.up_proj:  74%|███████▍  | 27204/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.79.down_proj:  74%|███████▍  | 27205/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.80.gate_proj:  74%|███████▍  | 27206/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.80.up_proj:  74%|███████▍  | 27207/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.80.down_proj:  74%|███████▍  | 27208/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.81.gate_proj:  74%|███████▍  | 27209/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.81.up_proj:  74%|███████▍  | 27210/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.81.down_proj:  74%|███████▍  | 27211/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.82.gate_proj:  74%|███████▍  | 27212/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.82.up_proj:  74%|███████▍  | 27213/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.82.down_proj:  74%|███████▍  | 27214/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.83.gate_proj:  74%|███████▍  | 27215/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.83.up_proj:  74%|███████▍  | 27216/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.83.down_proj:  74%|███████▍  | 27217/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.84.gate_proj:  74%|███████▍  | 27218/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.84.up_proj:  74%|███████▍  | 27219/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.84.down_proj:  74%|███████▍  | 27220/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.85.gate_proj:  74%|███████▍  | 27221/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.85.up_proj:  74%|███████▍  | 27222/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.85.down_proj:  74%|███████▍  | 27223/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.86.gate_proj:  74%|███████▍  | 27224/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.86.up_proj:  74%|███████▍  | 27225/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.86.down_proj:  74%|███████▍  | 27226/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.87.gate_proj:  74%|███████▍  | 27227/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.87.up_proj:  74%|███████▍  | 27228/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.87.down_proj:  74%|███████▍  | 27229/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.88.gate_proj:  74%|███████▍  | 27230/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.88.up_proj:  74%|███████▍  | 27231/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.88.down_proj:  74%|███████▍  | 27232/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.89.gate_proj:  74%|███████▍  | 27233/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.89.up_proj:  74%|███████▍  | 27234/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.89.down_proj:  74%|███████▍  | 27235/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.90.gate_proj:  74%|███████▍  | 27236/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.90.up_proj:  74%|███████▍  | 27237/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.90.down_proj:  74%|███████▍  | 27238/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.91.gate_proj:  74%|███████▍  | 27239/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.91.up_proj:  74%|███████▍  | 27240/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.91.down_proj:  74%|███████▍  | 27241/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.92.gate_proj:  75%|███████▍  | 27242/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.92.up_proj:  75%|███████▍  | 27243/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.92.down_proj:  75%|███████▍  | 27244/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.93.gate_proj:  75%|███████▍  | 27245/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.93.up_proj:  75%|███████▍  | 27246/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.93.down_proj:  75%|███████▍  | 27247/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.94.gate_proj:  75%|███████▍  | 27248/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.94.up_proj:  75%|███████▍  | 27249/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.94.down_proj:  75%|███████▍  | 27250/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.95.gate_proj:  75%|███████▍  | 27251/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.95.up_proj:  75%|███████▍  | 27252/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.95.down_proj:  75%|███████▍  | 27253/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.96.gate_proj:  75%|███████▍  | 27254/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.96.up_proj:  75%|███████▍  | 27255/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.96.down_proj:  75%|███████▍  | 27256/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.97.gate_proj:  75%|███████▍  | 27257/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.97.up_proj:  75%|███████▍  | 27258/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.97.down_proj:  75%|███████▍  | 27259/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.98.gate_proj:  75%|███████▍  | 27260/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.98.up_proj:  75%|███████▍  | 27261/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.98.down_proj:  75%|███████▍  | 27262/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.99.gate_proj:  75%|███████▍  | 27263/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.99.up_proj:  75%|███████▍  | 27264/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.99.down_proj:  75%|███████▍  | 27265/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.100.gate_proj:  75%|███████▍  | 27266/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.100.up_proj:  75%|███████▍  | 27267/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.100.down_proj:  75%|███████▍  | 27268/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.101.gate_proj:  75%|███████▍  | 27269/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.101.up_proj:  75%|███████▍  | 27270/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.101.down_proj:  75%|███████▍  | 27271/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.102.gate_proj:  75%|███████▍  | 27272/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.102.up_proj:  75%|███████▍  | 27273/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.102.down_proj:  75%|███████▍  | 27274/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.103.gate_proj:  75%|███████▍  | 27275/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.103.up_proj:  75%|███████▍  | 27276/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.103.down_proj:  75%|███████▍  | 27277/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.104.gate_proj:  75%|███████▍  | 27278/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.104.up_proj:  75%|███████▍  | 27279/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.104.down_proj:  75%|███████▍  | 27280/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.105.gate_proj:  75%|███████▍  | 27281/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.105.up_proj:  75%|███████▍  | 27282/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.105.down_proj:  75%|███████▍  | 27283/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.106.gate_proj:  75%|███████▍  | 27284/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.106.up_proj:  75%|███████▍  | 27285/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.106.down_proj:  75%|███████▍  | 27286/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.107.gate_proj:  75%|███████▍  | 27287/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.107.up_proj:  75%|███████▍  | 27288/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.107.down_proj:  75%|███████▍  | 27289/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.108.gate_proj:  75%|███████▍  | 27290/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.108.up_proj:  75%|███████▍  | 27291/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.108.down_proj:  75%|███████▍  | 27292/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.109.gate_proj:  75%|███████▍  | 27293/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.109.up_proj:  75%|███████▍  | 27294/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.109.down_proj:  75%|███████▍  | 27295/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.110.gate_proj:  75%|███████▍  | 27296/36566 [00:24<00:08, 1152.81it/s]
packing model.layers.69.mlp.experts.110.up_proj:  75%|███████▍  | 27297/36566 [00:24<00:08, 1152.81it/s]  
packing model.layers.69.mlp.experts.110.up_proj:  75%|███████▍  | 27298/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.110.down_proj:  75%|███████▍  | 27298/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.111.gate_proj:  75%|███████▍  | 27299/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.111.up_proj:  75%|███████▍  | 27300/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.111.down_proj:  75%|███████▍  | 27301/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.112.gate_proj:  75%|███████▍  | 27302/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.112.up_proj:  75%|███████▍  | 27303/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.112.down_proj:  75%|███████▍  | 27304/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.113.gate_proj:  75%|███████▍  | 27305/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.113.up_proj:  75%|███████▍  | 27306/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.113.down_proj:  75%|███████▍  | 27307/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.114.gate_proj:  75%|███████▍  | 27308/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.114.up_proj:  75%|███████▍  | 27309/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.114.down_proj:  75%|███████▍  | 27310/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.115.gate_proj:  75%|███████▍  | 27311/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.115.up_proj:  75%|███████▍  | 27312/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.115.down_proj:  75%|███████▍  | 27313/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.116.gate_proj:  75%|███████▍  | 27314/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.116.up_proj:  75%|███████▍  | 27315/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.116.down_proj:  75%|███████▍  | 27316/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.117.gate_proj:  75%|███████▍  | 27317/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.117.up_proj:  75%|███████▍  | 27318/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.117.down_proj:  75%|███████▍  | 27319/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.118.gate_proj:  75%|███████▍  | 27320/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.118.up_proj:  75%|███████▍  | 27321/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.118.down_proj:  75%|███████▍  | 27322/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.119.gate_proj:  75%|███████▍  | 27323/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.119.up_proj:  75%|███████▍  | 27324/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.119.down_proj:  75%|███████▍  | 27325/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.120.gate_proj:  75%|███████▍  | 27326/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.120.up_proj:  75%|███████▍  | 27327/36566 [00:24<00:08, 1154.55it/s]  
packing model.layers.69.mlp.experts.120.down_proj:  75%|███████▍  | 27328/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.121.gate_proj:  75%|███████▍  | 27329/36566 [00:24<00:08, 1154.55it/s]
packing model.layers.69.mlp.experts.121.up_proj:  75%|███████▍  | 27330/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.121.down_proj:  75%|███████▍  | 27331/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.122.gate_proj:  75%|███████▍  | 27332/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.122.up_proj:  75%|███████▍  | 27333/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.122.down_proj:  75%|███████▍  | 27334/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.123.gate_proj:  75%|███████▍  | 27335/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.123.up_proj:  75%|███████▍  | 27336/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.123.down_proj:  75%|███████▍  | 27337/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.124.gate_proj:  75%|███████▍  | 27338/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.124.up_proj:  75%|███████▍  | 27339/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.124.down_proj:  75%|███████▍  | 27340/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.125.gate_proj:  75%|███████▍  | 27341/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.125.up_proj:  75%|███████▍  | 27342/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.125.down_proj:  75%|███████▍  | 27343/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.126.gate_proj:  75%|███████▍  | 27344/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.126.up_proj:  75%|███████▍  | 27345/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.126.down_proj:  75%|███████▍  | 27346/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.127.gate_proj:  75%|███████▍  | 27347/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.69.mlp.experts.127.up_proj:  75%|███████▍  | 27348/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.69.mlp.experts.127.down_proj:  75%|███████▍  | 27349/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.0.gate_proj:  75%|███████▍  | 27350/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.0.up_proj:  75%|███████▍  | 27351/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.0.down_proj:  75%|███████▍  | 27352/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.1.gate_proj:  75%|███████▍  | 27353/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.1.up_proj:  75%|███████▍  | 27354/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.1.down_proj:  75%|███████▍  | 27355/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.2.gate_proj:  75%|███████▍  | 27356/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.2.up_proj:  75%|███████▍  | 27357/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.2.down_proj:  75%|███████▍  | 27358/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.3.gate_proj:  75%|███████▍  | 27359/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.3.up_proj:  75%|███████▍  | 27360/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.3.down_proj:  75%|███████▍  | 27361/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.4.gate_proj:  75%|███████▍  | 27362/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.4.up_proj:  75%|███████▍  | 27363/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.4.down_proj:  75%|███████▍  | 27364/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.5.gate_proj:  75%|███████▍  | 27365/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.5.up_proj:  75%|███████▍  | 27366/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.5.down_proj:  75%|███████▍  | 27367/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.6.gate_proj:  75%|███████▍  | 27368/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.6.up_proj:  75%|███████▍  | 27369/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.6.down_proj:  75%|███████▍  | 27370/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.7.gate_proj:  75%|███████▍  | 27371/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.7.up_proj:  75%|███████▍  | 27372/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.7.down_proj:  75%|███████▍  | 27373/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.8.gate_proj:  75%|███████▍  | 27374/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.8.up_proj:  75%|███████▍  | 27375/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.8.down_proj:  75%|███████▍  | 27376/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.9.gate_proj:  75%|███████▍  | 27377/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.9.up_proj:  75%|███████▍  | 27378/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.9.down_proj:  75%|███████▍  | 27379/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.10.gate_proj:  75%|███████▍  | 27380/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.10.up_proj:  75%|███████▍  | 27381/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.10.down_proj:  75%|███████▍  | 27382/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.11.gate_proj:  75%|███████▍  | 27383/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.11.up_proj:  75%|███████▍  | 27384/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.11.down_proj:  75%|███████▍  | 27385/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.12.gate_proj:  75%|███████▍  | 27386/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.12.up_proj:  75%|███████▍  | 27387/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.12.down_proj:  75%|███████▍  | 27388/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.13.gate_proj:  75%|███████▍  | 27389/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.13.up_proj:  75%|███████▍  | 27390/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.13.down_proj:  75%|███████▍  | 27391/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.14.gate_proj:  75%|███████▍  | 27392/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.14.up_proj:  75%|███████▍  | 27393/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.14.down_proj:  75%|███████▍  | 27394/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.15.gate_proj:  75%|███████▍  | 27395/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.15.up_proj:  75%|███████▍  | 27396/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.15.down_proj:  75%|███████▍  | 27397/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.16.gate_proj:  75%|███████▍  | 27398/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.16.up_proj:  75%|███████▍  | 27399/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.16.down_proj:  75%|███████▍  | 27400/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.17.gate_proj:  75%|███████▍  | 27401/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.17.up_proj:  75%|███████▍  | 27402/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.17.down_proj:  75%|███████▍  | 27403/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.18.gate_proj:  75%|███████▍  | 27404/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.18.up_proj:  75%|███████▍  | 27405/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.18.down_proj:  75%|███████▍  | 27406/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.19.gate_proj:  75%|███████▍  | 27407/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.19.up_proj:  75%|███████▍  | 27408/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.19.down_proj:  75%|███████▍  | 27409/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.20.gate_proj:  75%|███████▍  | 27410/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.20.up_proj:  75%|███████▍  | 27411/36566 [00:24<00:07, 1154.55it/s]  
packing model.layers.70.mlp.experts.20.down_proj:  75%|███████▍  | 27412/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.21.gate_proj:  75%|███████▍  | 27413/36566 [00:24<00:07, 1154.55it/s]
packing model.layers.70.mlp.experts.21.gate_proj:  75%|███████▍  | 27414/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.21.up_proj:  75%|███████▍  | 27414/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.21.down_proj:  75%|███████▍  | 27415/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.22.gate_proj:  75%|███████▍  | 27416/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.22.up_proj:  75%|███████▍  | 27417/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.22.down_proj:  75%|███████▍  | 27418/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.23.gate_proj:  75%|███████▍  | 27419/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.23.up_proj:  75%|███████▍  | 27420/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.23.down_proj:  75%|███████▍  | 27421/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.24.gate_proj:  75%|███████▍  | 27422/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.24.up_proj:  75%|███████▍  | 27423/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.24.down_proj:  75%|███████▍  | 27424/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.25.gate_proj:  75%|███████▌  | 27425/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.25.up_proj:  75%|███████▌  | 27426/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.25.down_proj:  75%|███████▌  | 27427/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.26.gate_proj:  75%|███████▌  | 27428/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.26.up_proj:  75%|███████▌  | 27429/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.26.down_proj:  75%|███████▌  | 27430/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.27.gate_proj:  75%|███████▌  | 27431/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.27.up_proj:  75%|███████▌  | 27432/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.27.down_proj:  75%|███████▌  | 27433/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.28.gate_proj:  75%|███████▌  | 27434/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.28.up_proj:  75%|███████▌  | 27435/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.28.down_proj:  75%|███████▌  | 27436/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.29.gate_proj:  75%|███████▌  | 27437/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.29.up_proj:  75%|███████▌  | 27438/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.29.down_proj:  75%|███████▌  | 27439/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.30.gate_proj:  75%|███████▌  | 27440/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.30.up_proj:  75%|███████▌  | 27441/36566 [00:24<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.30.down_proj:  75%|███████▌  | 27442/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.31.gate_proj:  75%|███████▌  | 27443/36566 [00:24<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.31.up_proj:  75%|███████▌  | 27444/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.31.down_proj:  75%|███████▌  | 27445/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.32.gate_proj:  75%|███████▌  | 27446/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.32.up_proj:  75%|███████▌  | 27447/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.32.down_proj:  75%|███████▌  | 27448/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.33.gate_proj:  75%|███████▌  | 27449/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.33.up_proj:  75%|███████▌  | 27450/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.33.down_proj:  75%|███████▌  | 27451/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.34.gate_proj:  75%|███████▌  | 27452/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.34.up_proj:  75%|███████▌  | 27453/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.34.down_proj:  75%|███████▌  | 27454/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.35.gate_proj:  75%|███████▌  | 27455/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.35.up_proj:  75%|███████▌  | 27456/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.35.down_proj:  75%|███████▌  | 27457/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.36.gate_proj:  75%|███████▌  | 27458/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.36.up_proj:  75%|███████▌  | 27459/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.36.down_proj:  75%|███████▌  | 27460/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.37.gate_proj:  75%|███████▌  | 27461/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.37.up_proj:  75%|███████▌  | 27462/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.37.down_proj:  75%|███████▌  | 27463/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.38.gate_proj:  75%|███████▌  | 27464/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.38.up_proj:  75%|███████▌  | 27465/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.38.down_proj:  75%|███████▌  | 27466/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.39.gate_proj:  75%|███████▌  | 27467/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.39.up_proj:  75%|███████▌  | 27468/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.39.down_proj:  75%|███████▌  | 27469/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.40.gate_proj:  75%|███████▌  | 27470/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.40.up_proj:  75%|███████▌  | 27471/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.40.down_proj:  75%|███████▌  | 27472/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.41.gate_proj:  75%|███████▌  | 27473/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.41.up_proj:  75%|███████▌  | 27474/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.41.down_proj:  75%|███████▌  | 27475/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.42.gate_proj:  75%|███████▌  | 27476/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.42.up_proj:  75%|███████▌  | 27477/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.42.down_proj:  75%|███████▌  | 27478/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.43.gate_proj:  75%|███████▌  | 27479/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.43.up_proj:  75%|███████▌  | 27480/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.43.down_proj:  75%|███████▌  | 27481/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.44.gate_proj:  75%|███████▌  | 27482/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.44.up_proj:  75%|███████▌  | 27483/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.44.down_proj:  75%|███████▌  | 27484/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.45.gate_proj:  75%|███████▌  | 27485/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.45.up_proj:  75%|███████▌  | 27486/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.45.down_proj:  75%|███████▌  | 27487/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.46.gate_proj:  75%|███████▌  | 27488/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.46.up_proj:  75%|███████▌  | 27489/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.46.down_proj:  75%|███████▌  | 27490/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.47.gate_proj:  75%|███████▌  | 27491/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.47.up_proj:  75%|███████▌  | 27492/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.47.down_proj:  75%|███████▌  | 27493/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.48.gate_proj:  75%|███████▌  | 27494/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.48.up_proj:  75%|███████▌  | 27495/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.48.down_proj:  75%|███████▌  | 27496/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.49.gate_proj:  75%|███████▌  | 27497/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.49.up_proj:  75%|███████▌  | 27498/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.49.down_proj:  75%|███████▌  | 27499/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.50.gate_proj:  75%|███████▌  | 27500/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.50.up_proj:  75%|███████▌  | 27501/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.50.down_proj:  75%|███████▌  | 27502/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.51.gate_proj:  75%|███████▌  | 27503/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.51.up_proj:  75%|███████▌  | 27504/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.51.down_proj:  75%|███████▌  | 27505/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.52.gate_proj:  75%|███████▌  | 27506/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.52.up_proj:  75%|███████▌  | 27507/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.52.down_proj:  75%|███████▌  | 27508/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.53.gate_proj:  75%|███████▌  | 27509/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.53.up_proj:  75%|███████▌  | 27510/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.53.down_proj:  75%|███████▌  | 27511/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.54.gate_proj:  75%|███████▌  | 27512/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.54.up_proj:  75%|███████▌  | 27513/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.54.down_proj:  75%|███████▌  | 27514/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.55.gate_proj:  75%|███████▌  | 27515/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.55.up_proj:  75%|███████▌  | 27516/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.55.down_proj:  75%|███████▌  | 27517/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.56.gate_proj:  75%|███████▌  | 27518/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.56.up_proj:  75%|███████▌  | 27519/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.56.down_proj:  75%|███████▌  | 27520/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.57.gate_proj:  75%|███████▌  | 27521/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.57.up_proj:  75%|███████▌  | 27522/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.57.down_proj:  75%|███████▌  | 27523/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.58.gate_proj:  75%|███████▌  | 27524/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.58.up_proj:  75%|███████▌  | 27525/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.58.down_proj:  75%|███████▌  | 27526/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.59.gate_proj:  75%|███████▌  | 27527/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.59.up_proj:  75%|███████▌  | 27528/36566 [00:25<00:07, 1153.69it/s]  
packing model.layers.70.mlp.experts.59.down_proj:  75%|███████▌  | 27529/36566 [00:25<00:07, 1153.69it/s]
packing model.layers.70.mlp.experts.59.down_proj:  75%|███████▌  | 27530/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.60.gate_proj:  75%|███████▌  | 27530/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.60.up_proj:  75%|███████▌  | 27531/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.60.down_proj:  75%|███████▌  | 27532/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.61.gate_proj:  75%|███████▌  | 27533/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.61.up_proj:  75%|███████▌  | 27534/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.61.down_proj:  75%|███████▌  | 27535/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.62.gate_proj:  75%|███████▌  | 27536/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.62.up_proj:  75%|███████▌  | 27537/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.62.down_proj:  75%|███████▌  | 27538/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.63.gate_proj:  75%|███████▌  | 27539/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.63.up_proj:  75%|███████▌  | 27540/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.63.down_proj:  75%|███████▌  | 27541/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.64.gate_proj:  75%|███████▌  | 27542/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.64.up_proj:  75%|███████▌  | 27543/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.64.down_proj:  75%|███████▌  | 27544/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.65.gate_proj:  75%|███████▌  | 27545/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.65.up_proj:  75%|███████▌  | 27546/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.65.down_proj:  75%|███████▌  | 27547/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.66.gate_proj:  75%|███████▌  | 27548/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.66.up_proj:  75%|███████▌  | 27549/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.66.down_proj:  75%|███████▌  | 27550/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.67.gate_proj:  75%|███████▌  | 27551/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.67.up_proj:  75%|███████▌  | 27552/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.67.down_proj:  75%|███████▌  | 27553/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.68.gate_proj:  75%|███████▌  | 27554/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.68.up_proj:  75%|███████▌  | 27555/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.68.down_proj:  75%|███████▌  | 27556/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.69.gate_proj:  75%|███████▌  | 27557/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.69.up_proj:  75%|███████▌  | 27558/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.69.down_proj:  75%|███████▌  | 27559/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.70.gate_proj:  75%|███████▌  | 27560/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.70.up_proj:  75%|███████▌  | 27561/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.70.down_proj:  75%|███████▌  | 27562/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.71.gate_proj:  75%|███████▌  | 27563/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.71.up_proj:  75%|███████▌  | 27564/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.71.down_proj:  75%|███████▌  | 27565/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.72.gate_proj:  75%|███████▌  | 27566/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.72.up_proj:  75%|███████▌  | 27567/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.72.down_proj:  75%|███████▌  | 27568/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.73.gate_proj:  75%|███████▌  | 27569/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.73.up_proj:  75%|███████▌  | 27570/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.73.down_proj:  75%|███████▌  | 27571/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.74.gate_proj:  75%|███████▌  | 27572/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.74.up_proj:  75%|███████▌  | 27573/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.74.down_proj:  75%|███████▌  | 27574/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.75.gate_proj:  75%|███████▌  | 27575/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.75.up_proj:  75%|███████▌  | 27576/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.75.down_proj:  75%|███████▌  | 27577/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.76.gate_proj:  75%|███████▌  | 27578/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.76.up_proj:  75%|███████▌  | 27579/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.76.down_proj:  75%|███████▌  | 27580/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.77.gate_proj:  75%|███████▌  | 27581/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.77.up_proj:  75%|███████▌  | 27582/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.77.down_proj:  75%|███████▌  | 27583/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.78.gate_proj:  75%|███████▌  | 27584/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.78.up_proj:  75%|███████▌  | 27585/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.78.down_proj:  75%|███████▌  | 27586/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.79.gate_proj:  75%|███████▌  | 27587/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.79.up_proj:  75%|███████▌  | 27588/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.79.down_proj:  75%|███████▌  | 27589/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.80.gate_proj:  75%|███████▌  | 27590/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.80.up_proj:  75%|███████▌  | 27591/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.80.down_proj:  75%|███████▌  | 27592/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.81.gate_proj:  75%|███████▌  | 27593/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.81.up_proj:  75%|███████▌  | 27594/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.81.down_proj:  75%|███████▌  | 27595/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.82.gate_proj:  75%|███████▌  | 27596/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.82.up_proj:  75%|███████▌  | 27597/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.82.down_proj:  75%|███████▌  | 27598/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.83.gate_proj:  75%|███████▌  | 27599/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.83.up_proj:  75%|███████▌  | 27600/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.83.down_proj:  75%|███████▌  | 27601/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.84.gate_proj:  75%|███████▌  | 27602/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.84.up_proj:  75%|███████▌  | 27603/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.84.down_proj:  75%|███████▌  | 27604/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.85.gate_proj:  75%|███████▌  | 27605/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.85.up_proj:  75%|███████▌  | 27606/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.85.down_proj:  75%|███████▌  | 27607/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.86.gate_proj:  76%|███████▌  | 27608/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.86.up_proj:  76%|███████▌  | 27609/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.86.down_proj:  76%|███████▌  | 27610/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.87.gate_proj:  76%|███████▌  | 27611/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.87.up_proj:  76%|███████▌  | 27612/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.87.down_proj:  76%|███████▌  | 27613/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.88.gate_proj:  76%|███████▌  | 27614/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.88.up_proj:  76%|███████▌  | 27615/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.88.down_proj:  76%|███████▌  | 27616/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.89.gate_proj:  76%|███████▌  | 27617/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.89.up_proj:  76%|███████▌  | 27618/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.89.down_proj:  76%|███████▌  | 27619/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.90.gate_proj:  76%|███████▌  | 27620/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.90.up_proj:  76%|███████▌  | 27621/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.90.down_proj:  76%|███████▌  | 27622/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.91.gate_proj:  76%|███████▌  | 27623/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.91.up_proj:  76%|███████▌  | 27624/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.91.down_proj:  76%|███████▌  | 27625/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.92.gate_proj:  76%|███████▌  | 27626/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.92.up_proj:  76%|███████▌  | 27627/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.92.down_proj:  76%|███████▌  | 27628/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.93.gate_proj:  76%|███████▌  | 27629/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.93.up_proj:  76%|███████▌  | 27630/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.93.down_proj:  76%|███████▌  | 27631/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.94.gate_proj:  76%|███████▌  | 27632/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.94.up_proj:  76%|███████▌  | 27633/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.94.down_proj:  76%|███████▌  | 27634/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.95.gate_proj:  76%|███████▌  | 27635/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.95.up_proj:  76%|███████▌  | 27636/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.95.down_proj:  76%|███████▌  | 27637/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.96.gate_proj:  76%|███████▌  | 27638/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.96.up_proj:  76%|███████▌  | 27639/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.96.down_proj:  76%|███████▌  | 27640/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.97.gate_proj:  76%|███████▌  | 27641/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.97.up_proj:  76%|███████▌  | 27642/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.97.down_proj:  76%|███████▌  | 27643/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.98.gate_proj:  76%|███████▌  | 27644/36566 [00:25<00:07, 1151.93it/s]
packing model.layers.70.mlp.experts.98.up_proj:  76%|███████▌  | 27645/36566 [00:25<00:07, 1151.93it/s]  
packing model.layers.70.mlp.experts.98.up_proj:  76%|███████▌  | 27646/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.98.down_proj:  76%|███████▌  | 27646/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.99.gate_proj:  76%|███████▌  | 27647/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.99.up_proj:  76%|███████▌  | 27648/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.99.down_proj:  76%|███████▌  | 27649/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.100.gate_proj:  76%|███████▌  | 27650/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.100.up_proj:  76%|███████▌  | 27651/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.100.down_proj:  76%|███████▌  | 27652/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.101.gate_proj:  76%|███████▌  | 27653/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.101.up_proj:  76%|███████▌  | 27654/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.101.down_proj:  76%|███████▌  | 27655/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.102.gate_proj:  76%|███████▌  | 27656/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.102.up_proj:  76%|███████▌  | 27657/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.102.down_proj:  76%|███████▌  | 27658/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.103.gate_proj:  76%|███████▌  | 27659/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.103.up_proj:  76%|███████▌  | 27660/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.103.down_proj:  76%|███████▌  | 27661/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.104.gate_proj:  76%|███████▌  | 27662/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.104.up_proj:  76%|███████▌  | 27663/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.104.down_proj:  76%|███████▌  | 27664/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.105.gate_proj:  76%|███████▌  | 27665/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.105.up_proj:  76%|███████▌  | 27666/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.105.down_proj:  76%|███████▌  | 27667/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.106.gate_proj:  76%|███████▌  | 27668/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.106.up_proj:  76%|███████▌  | 27669/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.106.down_proj:  76%|███████▌  | 27670/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.107.gate_proj:  76%|███████▌  | 27671/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.107.up_proj:  76%|███████▌  | 27672/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.107.down_proj:  76%|███████▌  | 27673/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.108.gate_proj:  76%|███████▌  | 27674/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.108.up_proj:  76%|███████▌  | 27675/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.108.down_proj:  76%|███████▌  | 27676/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.109.gate_proj:  76%|███████▌  | 27677/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.109.up_proj:  76%|███████▌  | 27678/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.109.down_proj:  76%|███████▌  | 27679/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.110.gate_proj:  76%|███████▌  | 27680/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.110.up_proj:  76%|███████▌  | 27681/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.110.down_proj:  76%|███████▌  | 27682/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.111.gate_proj:  76%|███████▌  | 27683/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.111.up_proj:  76%|███████▌  | 27684/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.111.down_proj:  76%|███████▌  | 27685/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.112.gate_proj:  76%|███████▌  | 27686/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.112.up_proj:  76%|███████▌  | 27687/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.112.down_proj:  76%|███████▌  | 27688/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.113.gate_proj:  76%|███████▌  | 27689/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.113.up_proj:  76%|███████▌  | 27690/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.113.down_proj:  76%|███████▌  | 27691/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.114.gate_proj:  76%|███████▌  | 27692/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.114.up_proj:  76%|███████▌  | 27693/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.114.down_proj:  76%|███████▌  | 27694/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.115.gate_proj:  76%|███████▌  | 27695/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.115.up_proj:  76%|███████▌  | 27696/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.115.down_proj:  76%|███████▌  | 27697/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.116.gate_proj:  76%|███████▌  | 27698/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.116.up_proj:  76%|███████▌  | 27699/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.116.down_proj:  76%|███████▌  | 27700/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.117.gate_proj:  76%|███████▌  | 27701/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.117.up_proj:  76%|███████▌  | 27702/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.117.down_proj:  76%|███████▌  | 27703/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.118.gate_proj:  76%|███████▌  | 27704/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.118.up_proj:  76%|███████▌  | 27705/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.118.down_proj:  76%|███████▌  | 27706/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.119.gate_proj:  76%|███████▌  | 27707/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.119.up_proj:  76%|███████▌  | 27708/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.119.down_proj:  76%|███████▌  | 27709/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.120.gate_proj:  76%|███████▌  | 27710/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.120.up_proj:  76%|███████▌  | 27711/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.120.down_proj:  76%|███████▌  | 27712/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.121.gate_proj:  76%|███████▌  | 27713/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.121.up_proj:  76%|███████▌  | 27714/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.121.down_proj:  76%|███████▌  | 27715/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.122.gate_proj:  76%|███████▌  | 27716/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.122.up_proj:  76%|███████▌  | 27717/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.122.down_proj:  76%|███████▌  | 27718/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.123.gate_proj:  76%|███████▌  | 27719/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.123.up_proj:  76%|███████▌  | 27720/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.123.down_proj:  76%|███████▌  | 27721/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.124.gate_proj:  76%|███████▌  | 27722/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.124.up_proj:  76%|███████▌  | 27723/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.124.down_proj:  76%|███████▌  | 27724/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.125.gate_proj:  76%|███████▌  | 27725/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.125.up_proj:  76%|███████▌  | 27726/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.125.down_proj:  76%|███████▌  | 27727/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.126.gate_proj:  76%|███████▌  | 27728/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.126.up_proj:  76%|███████▌  | 27729/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.126.down_proj:  76%|███████▌  | 27730/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.127.gate_proj:  76%|███████▌  | 27731/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.70.mlp.experts.127.up_proj:  76%|███████▌  | 27732/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.70.mlp.experts.127.down_proj:  76%|███████▌  | 27733/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.0.gate_proj:  76%|███████▌  | 27734/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.0.up_proj:  76%|███████▌  | 27735/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.0.down_proj:  76%|███████▌  | 27736/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.1.gate_proj:  76%|███████▌  | 27737/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.1.up_proj:  76%|███████▌  | 27738/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.1.down_proj:  76%|███████▌  | 27739/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.2.gate_proj:  76%|███████▌  | 27740/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.2.up_proj:  76%|███████▌  | 27741/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.2.down_proj:  76%|███████▌  | 27742/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.3.gate_proj:  76%|███████▌  | 27743/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.3.up_proj:  76%|███████▌  | 27744/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.3.down_proj:  76%|███████▌  | 27745/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.4.gate_proj:  76%|███████▌  | 27746/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.4.up_proj:  76%|███████▌  | 27747/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.4.down_proj:  76%|███████▌  | 27748/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.5.gate_proj:  76%|███████▌  | 27749/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.5.up_proj:  76%|███████▌  | 27750/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.5.down_proj:  76%|███████▌  | 27751/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.6.gate_proj:  76%|███████▌  | 27752/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.6.up_proj:  76%|███████▌  | 27753/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.6.down_proj:  76%|███████▌  | 27754/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.7.gate_proj:  76%|███████▌  | 27755/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.7.up_proj:  76%|███████▌  | 27756/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.7.down_proj:  76%|███████▌  | 27757/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.8.gate_proj:  76%|███████▌  | 27758/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.8.up_proj:  76%|███████▌  | 27759/36566 [00:25<00:07, 1151.31it/s]  
packing model.layers.71.mlp.experts.8.down_proj:  76%|███████▌  | 27760/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.9.gate_proj:  76%|███████▌  | 27761/36566 [00:25<00:07, 1151.31it/s]
packing model.layers.71.mlp.experts.9.gate_proj:  76%|███████▌  | 27762/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.9.up_proj:  76%|███████▌  | 27762/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.9.down_proj:  76%|███████▌  | 27763/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.10.gate_proj:  76%|███████▌  | 27764/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.10.up_proj:  76%|███████▌  | 27765/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.10.down_proj:  76%|███████▌  | 27766/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.11.gate_proj:  76%|███████▌  | 27767/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.11.up_proj:  76%|███████▌  | 27768/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.11.down_proj:  76%|███████▌  | 27769/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.12.gate_proj:  76%|███████▌  | 27770/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.12.up_proj:  76%|███████▌  | 27771/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.12.down_proj:  76%|███████▌  | 27772/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.13.gate_proj:  76%|███████▌  | 27773/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.13.up_proj:  76%|███████▌  | 27774/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.13.down_proj:  76%|███████▌  | 27775/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.14.gate_proj:  76%|███████▌  | 27776/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.14.up_proj:  76%|███████▌  | 27777/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.14.down_proj:  76%|███████▌  | 27778/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.15.gate_proj:  76%|███████▌  | 27779/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.15.up_proj:  76%|███████▌  | 27780/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.15.down_proj:  76%|███████▌  | 27781/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.16.gate_proj:  76%|███████▌  | 27782/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.16.up_proj:  76%|███████▌  | 27783/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.16.down_proj:  76%|███████▌  | 27784/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.17.gate_proj:  76%|███████▌  | 27785/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.17.up_proj:  76%|███████▌  | 27786/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.17.down_proj:  76%|███████▌  | 27787/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.18.gate_proj:  76%|███████▌  | 27788/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.18.up_proj:  76%|███████▌  | 27789/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.18.down_proj:  76%|███████▌  | 27790/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.19.gate_proj:  76%|███████▌  | 27791/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.19.up_proj:  76%|███████▌  | 27792/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.19.down_proj:  76%|███████▌  | 27793/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.20.gate_proj:  76%|███████▌  | 27794/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.20.up_proj:  76%|███████▌  | 27795/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.20.down_proj:  76%|███████▌  | 27796/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.21.gate_proj:  76%|███████▌  | 27797/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.21.up_proj:  76%|███████▌  | 27798/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.21.down_proj:  76%|███████▌  | 27799/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.22.gate_proj:  76%|███████▌  | 27800/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.22.up_proj:  76%|███████▌  | 27801/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.22.down_proj:  76%|███████▌  | 27802/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.23.gate_proj:  76%|███████▌  | 27803/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.23.up_proj:  76%|███████▌  | 27804/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.23.down_proj:  76%|███████▌  | 27805/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.24.gate_proj:  76%|███████▌  | 27806/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.24.up_proj:  76%|███████▌  | 27807/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.24.down_proj:  76%|███████▌  | 27808/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.25.gate_proj:  76%|███████▌  | 27809/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.25.up_proj:  76%|███████▌  | 27810/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.25.down_proj:  76%|███████▌  | 27811/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.26.gate_proj:  76%|███████▌  | 27812/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.26.up_proj:  76%|███████▌  | 27813/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.26.down_proj:  76%|███████▌  | 27814/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.27.gate_proj:  76%|███████▌  | 27815/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.27.up_proj:  76%|███████▌  | 27816/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.27.down_proj:  76%|███████▌  | 27817/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.28.gate_proj:  76%|███████▌  | 27818/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.28.up_proj:  76%|███████▌  | 27819/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.28.down_proj:  76%|███████▌  | 27820/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.29.gate_proj:  76%|███████▌  | 27821/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.29.up_proj:  76%|███████▌  | 27822/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.29.down_proj:  76%|███████▌  | 27823/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.30.gate_proj:  76%|███████▌  | 27824/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.30.up_proj:  76%|███████▌  | 27825/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.30.down_proj:  76%|███████▌  | 27826/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.31.gate_proj:  76%|███████▌  | 27827/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.31.up_proj:  76%|███████▌  | 27828/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.31.down_proj:  76%|███████▌  | 27829/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.32.gate_proj:  76%|███████▌  | 27830/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.32.up_proj:  76%|███████▌  | 27831/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.32.down_proj:  76%|███████▌  | 27832/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.33.gate_proj:  76%|███████▌  | 27833/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.33.up_proj:  76%|███████▌  | 27834/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.33.down_proj:  76%|███████▌  | 27835/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.34.gate_proj:  76%|███████▌  | 27836/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.34.up_proj:  76%|███████▌  | 27837/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.34.down_proj:  76%|███████▌  | 27838/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.35.gate_proj:  76%|███████▌  | 27839/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.35.up_proj:  76%|███████▌  | 27840/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.35.down_proj:  76%|███████▌  | 27841/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.36.gate_proj:  76%|███████▌  | 27842/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.36.up_proj:  76%|███████▌  | 27843/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.36.down_proj:  76%|███████▌  | 27844/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.37.gate_proj:  76%|███████▌  | 27845/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.37.up_proj:  76%|███████▌  | 27846/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.37.down_proj:  76%|███████▌  | 27847/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.38.gate_proj:  76%|███████▌  | 27848/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.38.up_proj:  76%|███████▌  | 27849/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.38.down_proj:  76%|███████▌  | 27850/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.39.gate_proj:  76%|███████▌  | 27851/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.39.up_proj:  76%|███████▌  | 27852/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.39.down_proj:  76%|███████▌  | 27853/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.40.gate_proj:  76%|███████▌  | 27854/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.40.up_proj:  76%|███████▌  | 27855/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.40.down_proj:  76%|███████▌  | 27856/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.41.gate_proj:  76%|███████▌  | 27857/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.41.up_proj:  76%|███████▌  | 27858/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.41.down_proj:  76%|███████▌  | 27859/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.42.gate_proj:  76%|███████▌  | 27860/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.42.up_proj:  76%|███████▌  | 27861/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.42.down_proj:  76%|███████▌  | 27862/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.43.gate_proj:  76%|███████▌  | 27863/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.43.up_proj:  76%|███████▌  | 27864/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.43.down_proj:  76%|███████▌  | 27865/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.44.gate_proj:  76%|███████▌  | 27866/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.44.up_proj:  76%|███████▌  | 27867/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.44.down_proj:  76%|███████▌  | 27868/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.45.gate_proj:  76%|███████▌  | 27869/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.45.up_proj:  76%|███████▌  | 27870/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.45.down_proj:  76%|███████▌  | 27871/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.46.gate_proj:  76%|███████▌  | 27872/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.46.up_proj:  76%|███████▌  | 27873/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.46.down_proj:  76%|███████▌  | 27874/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.47.gate_proj:  76%|███████▌  | 27875/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.47.up_proj:  76%|███████▌  | 27876/36566 [00:25<00:07, 1152.11it/s]  
packing model.layers.71.mlp.experts.47.down_proj:  76%|███████▌  | 27877/36566 [00:25<00:07, 1152.11it/s]
packing model.layers.71.mlp.experts.47.down_proj:  76%|███████▌  | 27878/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.48.gate_proj:  76%|███████▌  | 27878/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.48.up_proj:  76%|███████▌  | 27879/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.48.down_proj:  76%|███████▌  | 27880/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.49.gate_proj:  76%|███████▌  | 27881/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.49.up_proj:  76%|███████▋  | 27882/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.49.down_proj:  76%|███████▋  | 27883/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.50.gate_proj:  76%|███████▋  | 27884/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.50.up_proj:  76%|███████▋  | 27885/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.50.down_proj:  76%|███████▋  | 27886/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.51.gate_proj:  76%|███████▋  | 27887/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.51.up_proj:  76%|███████▋  | 27888/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.51.down_proj:  76%|███████▋  | 27889/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.52.gate_proj:  76%|███████▋  | 27890/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.52.up_proj:  76%|███████▋  | 27891/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.52.down_proj:  76%|███████▋  | 27892/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.53.gate_proj:  76%|███████▋  | 27893/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.53.up_proj:  76%|███████▋  | 27894/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.53.down_proj:  76%|███████▋  | 27895/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.54.gate_proj:  76%|███████▋  | 27896/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.54.up_proj:  76%|███████▋  | 27897/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.54.down_proj:  76%|███████▋  | 27898/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.55.gate_proj:  76%|███████▋  | 27899/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.55.up_proj:  76%|███████▋  | 27900/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.55.down_proj:  76%|███████▋  | 27901/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.56.gate_proj:  76%|███████▋  | 27902/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.56.up_proj:  76%|███████▋  | 27903/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.56.down_proj:  76%|███████▋  | 27904/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.57.gate_proj:  76%|███████▋  | 27905/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.57.up_proj:  76%|███████▋  | 27906/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.57.down_proj:  76%|███████▋  | 27907/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.58.gate_proj:  76%|███████▋  | 27908/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.58.up_proj:  76%|███████▋  | 27909/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.58.down_proj:  76%|███████▋  | 27910/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.59.gate_proj:  76%|███████▋  | 27911/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.59.up_proj:  76%|███████▋  | 27912/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.59.down_proj:  76%|███████▋  | 27913/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.60.gate_proj:  76%|███████▋  | 27914/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.60.up_proj:  76%|███████▋  | 27915/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.60.down_proj:  76%|███████▋  | 27916/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.61.gate_proj:  76%|███████▋  | 27917/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.61.up_proj:  76%|███████▋  | 27918/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.61.down_proj:  76%|███████▋  | 27919/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.62.gate_proj:  76%|███████▋  | 27920/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.62.up_proj:  76%|███████▋  | 27921/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.62.down_proj:  76%|███████▋  | 27922/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.63.gate_proj:  76%|███████▋  | 27923/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.63.up_proj:  76%|███████▋  | 27924/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.63.down_proj:  76%|███████▋  | 27925/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.64.gate_proj:  76%|███████▋  | 27926/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.64.up_proj:  76%|███████▋  | 27927/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.64.down_proj:  76%|███████▋  | 27928/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.65.gate_proj:  76%|███████▋  | 27929/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.65.up_proj:  76%|███████▋  | 27930/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.65.down_proj:  76%|███████▋  | 27931/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.66.gate_proj:  76%|███████▋  | 27932/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.66.up_proj:  76%|███████▋  | 27933/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.66.down_proj:  76%|███████▋  | 27934/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.67.gate_proj:  76%|███████▋  | 27935/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.67.up_proj:  76%|███████▋  | 27936/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.67.down_proj:  76%|███████▋  | 27937/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.68.gate_proj:  76%|███████▋  | 27938/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.68.up_proj:  76%|███████▋  | 27939/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.68.down_proj:  76%|███████▋  | 27940/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.69.gate_proj:  76%|███████▋  | 27941/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.69.up_proj:  76%|███████▋  | 27942/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.69.down_proj:  76%|███████▋  | 27943/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.70.gate_proj:  76%|███████▋  | 27944/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.70.up_proj:  76%|███████▋  | 27945/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.70.down_proj:  76%|███████▋  | 27946/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.71.gate_proj:  76%|███████▋  | 27947/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.71.up_proj:  76%|███████▋  | 27948/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.71.down_proj:  76%|███████▋  | 27949/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.72.gate_proj:  76%|███████▋  | 27950/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.72.up_proj:  76%|███████▋  | 27951/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.72.down_proj:  76%|███████▋  | 27952/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.73.gate_proj:  76%|███████▋  | 27953/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.73.up_proj:  76%|███████▋  | 27954/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.73.down_proj:  76%|███████▋  | 27955/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.74.gate_proj:  76%|███████▋  | 27956/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.74.up_proj:  76%|███████▋  | 27957/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.74.down_proj:  76%|███████▋  | 27958/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.75.gate_proj:  76%|███████▋  | 27959/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.75.up_proj:  76%|███████▋  | 27960/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.75.down_proj:  76%|███████▋  | 27961/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.76.gate_proj:  76%|███████▋  | 27962/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.76.up_proj:  76%|███████▋  | 27963/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.76.down_proj:  76%|███████▋  | 27964/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.77.gate_proj:  76%|███████▋  | 27965/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.77.up_proj:  76%|███████▋  | 27966/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.77.down_proj:  76%|███████▋  | 27967/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.78.gate_proj:  76%|███████▋  | 27968/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.78.up_proj:  76%|███████▋  | 27969/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.78.down_proj:  76%|███████▋  | 27970/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.79.gate_proj:  76%|███████▋  | 27971/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.79.up_proj:  76%|███████▋  | 27972/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.79.down_proj:  77%|███████▋  | 27973/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.80.gate_proj:  77%|███████▋  | 27974/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.80.up_proj:  77%|███████▋  | 27975/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.80.down_proj:  77%|███████▋  | 27976/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.81.gate_proj:  77%|███████▋  | 27977/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.81.up_proj:  77%|███████▋  | 27978/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.81.down_proj:  77%|███████▋  | 27979/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.82.gate_proj:  77%|███████▋  | 27980/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.82.up_proj:  77%|███████▋  | 27981/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.82.down_proj:  77%|███████▋  | 27982/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.83.gate_proj:  77%|███████▋  | 27983/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.83.up_proj:  77%|███████▋  | 27984/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.83.down_proj:  77%|███████▋  | 27985/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.84.gate_proj:  77%|███████▋  | 27986/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.84.up_proj:  77%|███████▋  | 27987/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.84.down_proj:  77%|███████▋  | 27988/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.85.gate_proj:  77%|███████▋  | 27989/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.85.up_proj:  77%|███████▋  | 27990/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.85.down_proj:  77%|███████▋  | 27991/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.86.gate_proj:  77%|███████▋  | 27992/36566 [00:25<00:07, 1153.33it/s]
packing model.layers.71.mlp.experts.86.up_proj:  77%|███████▋  | 27993/36566 [00:25<00:07, 1153.33it/s]  
packing model.layers.71.mlp.experts.86.up_proj:  77%|███████▋  | 27994/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.86.down_proj:  77%|███████▋  | 27994/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.87.gate_proj:  77%|███████▋  | 27995/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.87.up_proj:  77%|███████▋  | 27996/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.87.down_proj:  77%|███████▋  | 27997/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.88.gate_proj:  77%|███████▋  | 27998/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.88.up_proj:  77%|███████▋  | 27999/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.88.down_proj:  77%|███████▋  | 28000/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.89.gate_proj:  77%|███████▋  | 28001/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.89.up_proj:  77%|███████▋  | 28002/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.89.down_proj:  77%|███████▋  | 28003/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.90.gate_proj:  77%|███████▋  | 28004/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.90.up_proj:  77%|███████▋  | 28005/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.90.down_proj:  77%|███████▋  | 28006/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.91.gate_proj:  77%|███████▋  | 28007/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.91.up_proj:  77%|███████▋  | 28008/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.91.down_proj:  77%|███████▋  | 28009/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.92.gate_proj:  77%|███████▋  | 28010/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.92.up_proj:  77%|███████▋  | 28011/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.92.down_proj:  77%|███████▋  | 28012/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.93.gate_proj:  77%|███████▋  | 28013/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.93.up_proj:  77%|███████▋  | 28014/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.93.down_proj:  77%|███████▋  | 28015/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.94.gate_proj:  77%|███████▋  | 28016/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.94.up_proj:  77%|███████▋  | 28017/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.94.down_proj:  77%|███████▋  | 28018/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.95.gate_proj:  77%|███████▋  | 28019/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.95.up_proj:  77%|███████▋  | 28020/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.95.down_proj:  77%|███████▋  | 28021/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.96.gate_proj:  77%|███████▋  | 28022/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.96.up_proj:  77%|███████▋  | 28023/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.96.down_proj:  77%|███████▋  | 28024/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.97.gate_proj:  77%|███████▋  | 28025/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.97.up_proj:  77%|███████▋  | 28026/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.97.down_proj:  77%|███████▋  | 28027/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.98.gate_proj:  77%|███████▋  | 28028/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.98.up_proj:  77%|███████▋  | 28029/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.98.down_proj:  77%|███████▋  | 28030/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.99.gate_proj:  77%|███████▋  | 28031/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.99.up_proj:  77%|███████▋  | 28032/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.99.down_proj:  77%|███████▋  | 28033/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.100.gate_proj:  77%|███████▋  | 28034/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.100.up_proj:  77%|███████▋  | 28035/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.100.down_proj:  77%|███████▋  | 28036/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.101.gate_proj:  77%|███████▋  | 28037/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.101.up_proj:  77%|███████▋  | 28038/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.101.down_proj:  77%|███████▋  | 28039/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.102.gate_proj:  77%|███████▋  | 28040/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.102.up_proj:  77%|███████▋  | 28041/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.102.down_proj:  77%|███████▋  | 28042/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.103.gate_proj:  77%|███████▋  | 28043/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.103.up_proj:  77%|███████▋  | 28044/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.103.down_proj:  77%|███████▋  | 28045/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.104.gate_proj:  77%|███████▋  | 28046/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.104.up_proj:  77%|███████▋  | 28047/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.104.down_proj:  77%|███████▋  | 28048/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.105.gate_proj:  77%|███████▋  | 28049/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.105.up_proj:  77%|███████▋  | 28050/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.105.down_proj:  77%|███████▋  | 28051/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.106.gate_proj:  77%|███████▋  | 28052/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.106.up_proj:  77%|███████▋  | 28053/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.106.down_proj:  77%|███████▋  | 28054/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.107.gate_proj:  77%|███████▋  | 28055/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.107.up_proj:  77%|███████▋  | 28056/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.107.down_proj:  77%|███████▋  | 28057/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.108.gate_proj:  77%|███████▋  | 28058/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.108.up_proj:  77%|███████▋  | 28059/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.108.down_proj:  77%|███████▋  | 28060/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.109.gate_proj:  77%|███████▋  | 28061/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.109.up_proj:  77%|███████▋  | 28062/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.109.down_proj:  77%|███████▋  | 28063/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.110.gate_proj:  77%|███████▋  | 28064/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.110.up_proj:  77%|███████▋  | 28065/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.110.down_proj:  77%|███████▋  | 28066/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.111.gate_proj:  77%|███████▋  | 28067/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.111.up_proj:  77%|███████▋  | 28068/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.111.down_proj:  77%|███████▋  | 28069/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.112.gate_proj:  77%|███████▋  | 28070/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.112.up_proj:  77%|███████▋  | 28071/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.112.down_proj:  77%|███████▋  | 28072/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.113.gate_proj:  77%|███████▋  | 28073/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.113.up_proj:  77%|███████▋  | 28074/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.113.down_proj:  77%|███████▋  | 28075/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.114.gate_proj:  77%|███████▋  | 28076/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.114.up_proj:  77%|███████▋  | 28077/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.114.down_proj:  77%|███████▋  | 28078/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.115.gate_proj:  77%|███████▋  | 28079/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.115.up_proj:  77%|███████▋  | 28080/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.115.down_proj:  77%|███████▋  | 28081/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.116.gate_proj:  77%|███████▋  | 28082/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.116.up_proj:  77%|███████▋  | 28083/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.116.down_proj:  77%|███████▋  | 28084/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.117.gate_proj:  77%|███████▋  | 28085/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.117.up_proj:  77%|███████▋  | 28086/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.117.down_proj:  77%|███████▋  | 28087/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.118.gate_proj:  77%|███████▋  | 28088/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.118.up_proj:  77%|███████▋  | 28089/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.118.down_proj:  77%|███████▋  | 28090/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.119.gate_proj:  77%|███████▋  | 28091/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.119.up_proj:  77%|███████▋  | 28092/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.119.down_proj:  77%|███████▋  | 28093/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.120.gate_proj:  77%|███████▋  | 28094/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.120.up_proj:  77%|███████▋  | 28095/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.120.down_proj:  77%|███████▋  | 28096/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.121.gate_proj:  77%|███████▋  | 28097/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.121.up_proj:  77%|███████▋  | 28098/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.121.down_proj:  77%|███████▋  | 28099/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.122.gate_proj:  77%|███████▋  | 28100/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.122.up_proj:  77%|███████▋  | 28101/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.122.down_proj:  77%|███████▋  | 28102/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.123.gate_proj:  77%|███████▋  | 28103/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.123.up_proj:  77%|███████▋  | 28104/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.123.down_proj:  77%|███████▋  | 28105/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.124.gate_proj:  77%|███████▋  | 28106/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.124.up_proj:  77%|███████▋  | 28107/36566 [00:25<00:07, 1154.09it/s]  
packing model.layers.71.mlp.experts.124.down_proj:  77%|███████▋  | 28108/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.125.gate_proj:  77%|███████▋  | 28109/36566 [00:25<00:07, 1154.09it/s]
packing model.layers.71.mlp.experts.125.gate_proj:  77%|███████▋  | 28110/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.71.mlp.experts.125.up_proj:  77%|███████▋  | 28110/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.71.mlp.experts.125.down_proj:  77%|███████▋  | 28111/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.71.mlp.experts.126.gate_proj:  77%|███████▋  | 28112/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.71.mlp.experts.126.up_proj:  77%|███████▋  | 28113/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.71.mlp.experts.126.down_proj:  77%|███████▋  | 28114/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.71.mlp.experts.127.gate_proj:  77%|███████▋  | 28115/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.71.mlp.experts.127.up_proj:  77%|███████▋  | 28116/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.71.mlp.experts.127.down_proj:  77%|███████▋  | 28117/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.0.gate_proj:  77%|███████▋  | 28118/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.0.up_proj:  77%|███████▋  | 28119/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.0.down_proj:  77%|███████▋  | 28120/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.1.gate_proj:  77%|███████▋  | 28121/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.1.up_proj:  77%|███████▋  | 28122/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.1.down_proj:  77%|███████▋  | 28123/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.2.gate_proj:  77%|███████▋  | 28124/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.2.up_proj:  77%|███████▋  | 28125/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.2.down_proj:  77%|███████▋  | 28126/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.3.gate_proj:  77%|███████▋  | 28127/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.3.up_proj:  77%|███████▋  | 28128/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.3.down_proj:  77%|███████▋  | 28129/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.4.gate_proj:  77%|███████▋  | 28130/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.4.up_proj:  77%|███████▋  | 28131/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.4.down_proj:  77%|███████▋  | 28132/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.5.gate_proj:  77%|███████▋  | 28133/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.5.up_proj:  77%|███████▋  | 28134/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.5.down_proj:  77%|███████▋  | 28135/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.6.gate_proj:  77%|███████▋  | 28136/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.6.up_proj:  77%|███████▋  | 28137/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.6.down_proj:  77%|███████▋  | 28138/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.7.gate_proj:  77%|███████▋  | 28139/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.7.up_proj:  77%|███████▋  | 28140/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.7.down_proj:  77%|███████▋  | 28141/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.8.gate_proj:  77%|███████▋  | 28142/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.8.up_proj:  77%|███████▋  | 28143/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.8.down_proj:  77%|███████▋  | 28144/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.9.gate_proj:  77%|███████▋  | 28145/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.9.up_proj:  77%|███████▋  | 28146/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.9.down_proj:  77%|███████▋  | 28147/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.10.gate_proj:  77%|███████▋  | 28148/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.10.up_proj:  77%|███████▋  | 28149/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.10.down_proj:  77%|███████▋  | 28150/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.11.gate_proj:  77%|███████▋  | 28151/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.11.up_proj:  77%|███████▋  | 28152/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.11.down_proj:  77%|███████▋  | 28153/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.12.gate_proj:  77%|███████▋  | 28154/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.12.up_proj:  77%|███████▋  | 28155/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.12.down_proj:  77%|███████▋  | 28156/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.13.gate_proj:  77%|███████▋  | 28157/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.13.up_proj:  77%|███████▋  | 28158/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.13.down_proj:  77%|███████▋  | 28159/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.14.gate_proj:  77%|███████▋  | 28160/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.14.up_proj:  77%|███████▋  | 28161/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.14.down_proj:  77%|███████▋  | 28162/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.15.gate_proj:  77%|███████▋  | 28163/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.15.up_proj:  77%|███████▋  | 28164/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.15.down_proj:  77%|███████▋  | 28165/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.16.gate_proj:  77%|███████▋  | 28166/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.16.up_proj:  77%|███████▋  | 28167/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.16.down_proj:  77%|███████▋  | 28168/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.17.gate_proj:  77%|███████▋  | 28169/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.17.up_proj:  77%|███████▋  | 28170/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.17.down_proj:  77%|███████▋  | 28171/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.18.gate_proj:  77%|███████▋  | 28172/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.18.up_proj:  77%|███████▋  | 28173/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.18.down_proj:  77%|███████▋  | 28174/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.19.gate_proj:  77%|███████▋  | 28175/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.19.up_proj:  77%|███████▋  | 28176/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.19.down_proj:  77%|███████▋  | 28177/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.20.gate_proj:  77%|███████▋  | 28178/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.20.up_proj:  77%|███████▋  | 28179/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.20.down_proj:  77%|███████▋  | 28180/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.21.gate_proj:  77%|███████▋  | 28181/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.21.up_proj:  77%|███████▋  | 28182/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.21.down_proj:  77%|███████▋  | 28183/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.22.gate_proj:  77%|███████▋  | 28184/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.22.up_proj:  77%|███████▋  | 28185/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.22.down_proj:  77%|███████▋  | 28186/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.23.gate_proj:  77%|███████▋  | 28187/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.23.up_proj:  77%|███████▋  | 28188/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.23.down_proj:  77%|███████▋  | 28189/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.24.gate_proj:  77%|███████▋  | 28190/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.24.up_proj:  77%|███████▋  | 28191/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.24.down_proj:  77%|███████▋  | 28192/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.25.gate_proj:  77%|███████▋  | 28193/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.25.up_proj:  77%|███████▋  | 28194/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.25.down_proj:  77%|███████▋  | 28195/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.26.gate_proj:  77%|███████▋  | 28196/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.26.up_proj:  77%|███████▋  | 28197/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.26.down_proj:  77%|███████▋  | 28198/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.27.gate_proj:  77%|███████▋  | 28199/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.27.up_proj:  77%|███████▋  | 28200/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.27.down_proj:  77%|███████▋  | 28201/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.28.gate_proj:  77%|███████▋  | 28202/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.28.up_proj:  77%|███████▋  | 28203/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.28.down_proj:  77%|███████▋  | 28204/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.29.gate_proj:  77%|███████▋  | 28205/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.29.up_proj:  77%|███████▋  | 28206/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.29.down_proj:  77%|███████▋  | 28207/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.30.gate_proj:  77%|███████▋  | 28208/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.30.up_proj:  77%|███████▋  | 28209/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.30.down_proj:  77%|███████▋  | 28210/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.31.gate_proj:  77%|███████▋  | 28211/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.31.up_proj:  77%|███████▋  | 28212/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.31.down_proj:  77%|███████▋  | 28213/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.32.gate_proj:  77%|███████▋  | 28214/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.32.up_proj:  77%|███████▋  | 28215/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.32.down_proj:  77%|███████▋  | 28216/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.33.gate_proj:  77%|███████▋  | 28217/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.33.up_proj:  77%|███████▋  | 28218/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.33.down_proj:  77%|███████▋  | 28219/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.34.gate_proj:  77%|███████▋  | 28220/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.34.up_proj:  77%|███████▋  | 28221/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.34.down_proj:  77%|███████▋  | 28222/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.35.gate_proj:  77%|███████▋  | 28223/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.35.up_proj:  77%|███████▋  | 28224/36566 [00:25<00:07, 1152.07it/s]  
packing model.layers.72.mlp.experts.35.down_proj:  77%|███████▋  | 28225/36566 [00:25<00:07, 1152.07it/s]
packing model.layers.72.mlp.experts.35.down_proj:  77%|███████▋  | 28226/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.36.gate_proj:  77%|███████▋  | 28226/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.36.up_proj:  77%|███████▋  | 28227/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.36.down_proj:  77%|███████▋  | 28228/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.37.gate_proj:  77%|███████▋  | 28229/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.37.up_proj:  77%|███████▋  | 28230/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.37.down_proj:  77%|███████▋  | 28231/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.38.gate_proj:  77%|███████▋  | 28232/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.38.up_proj:  77%|███████▋  | 28233/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.38.down_proj:  77%|███████▋  | 28234/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.39.gate_proj:  77%|███████▋  | 28235/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.39.up_proj:  77%|███████▋  | 28236/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.39.down_proj:  77%|███████▋  | 28237/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.40.gate_proj:  77%|███████▋  | 28238/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.40.up_proj:  77%|███████▋  | 28239/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.40.down_proj:  77%|███████▋  | 28240/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.41.gate_proj:  77%|███████▋  | 28241/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.41.up_proj:  77%|███████▋  | 28242/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.41.down_proj:  77%|███████▋  | 28243/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.42.gate_proj:  77%|███████▋  | 28244/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.42.up_proj:  77%|███████▋  | 28245/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.42.down_proj:  77%|███████▋  | 28246/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.43.gate_proj:  77%|███████▋  | 28247/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.43.up_proj:  77%|███████▋  | 28248/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.43.down_proj:  77%|███████▋  | 28249/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.44.gate_proj:  77%|███████▋  | 28250/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.44.up_proj:  77%|███████▋  | 28251/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.44.down_proj:  77%|███████▋  | 28252/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.45.gate_proj:  77%|███████▋  | 28253/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.45.up_proj:  77%|███████▋  | 28254/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.45.down_proj:  77%|███████▋  | 28255/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.46.gate_proj:  77%|███████▋  | 28256/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.46.up_proj:  77%|███████▋  | 28257/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.46.down_proj:  77%|███████▋  | 28258/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.47.gate_proj:  77%|███████▋  | 28259/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.47.up_proj:  77%|███████▋  | 28260/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.47.down_proj:  77%|███████▋  | 28261/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.48.gate_proj:  77%|███████▋  | 28262/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.48.up_proj:  77%|███████▋  | 28263/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.48.down_proj:  77%|███████▋  | 28264/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.49.gate_proj:  77%|███████▋  | 28265/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.49.up_proj:  77%|███████▋  | 28266/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.49.down_proj:  77%|███████▋  | 28267/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.50.gate_proj:  77%|███████▋  | 28268/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.50.up_proj:  77%|███████▋  | 28269/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.50.down_proj:  77%|███████▋  | 28270/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.51.gate_proj:  77%|███████▋  | 28271/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.51.up_proj:  77%|███████▋  | 28272/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.51.down_proj:  77%|███████▋  | 28273/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.52.gate_proj:  77%|███████▋  | 28274/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.52.up_proj:  77%|███████▋  | 28275/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.52.down_proj:  77%|███████▋  | 28276/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.53.gate_proj:  77%|███████▋  | 28277/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.53.up_proj:  77%|███████▋  | 28278/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.53.down_proj:  77%|███████▋  | 28279/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.54.gate_proj:  77%|███████▋  | 28280/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.54.up_proj:  77%|███████▋  | 28281/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.54.down_proj:  77%|███████▋  | 28282/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.55.gate_proj:  77%|███████▋  | 28283/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.55.up_proj:  77%|███████▋  | 28284/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.55.down_proj:  77%|███████▋  | 28285/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.56.gate_proj:  77%|███████▋  | 28286/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.56.up_proj:  77%|███████▋  | 28287/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.56.down_proj:  77%|███████▋  | 28288/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.57.gate_proj:  77%|███████▋  | 28289/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.57.up_proj:  77%|███████▋  | 28290/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.57.down_proj:  77%|███████▋  | 28291/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.58.gate_proj:  77%|███████▋  | 28292/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.58.up_proj:  77%|███████▋  | 28293/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.58.down_proj:  77%|███████▋  | 28294/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.59.gate_proj:  77%|███████▋  | 28295/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.59.up_proj:  77%|███████▋  | 28296/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.59.down_proj:  77%|███████▋  | 28297/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.60.gate_proj:  77%|███████▋  | 28298/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.60.up_proj:  77%|███████▋  | 28299/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.60.down_proj:  77%|███████▋  | 28300/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.61.gate_proj:  77%|███████▋  | 28301/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.61.up_proj:  77%|███████▋  | 28302/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.61.down_proj:  77%|███████▋  | 28303/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.62.gate_proj:  77%|███████▋  | 28304/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.62.up_proj:  77%|███████▋  | 28305/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.62.down_proj:  77%|███████▋  | 28306/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.63.gate_proj:  77%|███████▋  | 28307/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.63.up_proj:  77%|███████▋  | 28308/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.63.down_proj:  77%|███████▋  | 28309/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.64.gate_proj:  77%|███████▋  | 28310/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.64.up_proj:  77%|███████▋  | 28311/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.64.down_proj:  77%|███████▋  | 28312/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.65.gate_proj:  77%|███████▋  | 28313/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.65.up_proj:  77%|███████▋  | 28314/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.65.down_proj:  77%|███████▋  | 28315/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.66.gate_proj:  77%|███████▋  | 28316/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.66.up_proj:  77%|███████▋  | 28317/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.66.down_proj:  77%|███████▋  | 28318/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.67.gate_proj:  77%|███████▋  | 28319/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.67.up_proj:  77%|███████▋  | 28320/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.67.down_proj:  77%|███████▋  | 28321/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.68.gate_proj:  77%|███████▋  | 28322/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.68.up_proj:  77%|███████▋  | 28323/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.68.down_proj:  77%|███████▋  | 28324/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.69.gate_proj:  77%|███████▋  | 28325/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.69.up_proj:  77%|███████▋  | 28326/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.69.down_proj:  77%|███████▋  | 28327/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.70.gate_proj:  77%|███████▋  | 28328/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.70.up_proj:  77%|███████▋  | 28329/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.70.down_proj:  77%|███████▋  | 28330/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.71.gate_proj:  77%|███████▋  | 28331/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.71.up_proj:  77%|███████▋  | 28332/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.71.down_proj:  77%|███████▋  | 28333/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.72.gate_proj:  77%|███████▋  | 28334/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.72.up_proj:  77%|███████▋  | 28335/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.72.down_proj:  77%|███████▋  | 28336/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.73.gate_proj:  77%|███████▋  | 28337/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.73.up_proj:  77%|███████▋  | 28338/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.73.down_proj:  78%|███████▊  | 28339/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.74.gate_proj:  78%|███████▊  | 28340/36566 [00:25<00:07, 1151.72it/s]
packing model.layers.72.mlp.experts.74.up_proj:  78%|███████▊  | 28341/36566 [00:25<00:07, 1151.72it/s]  
packing model.layers.72.mlp.experts.74.up_proj:  78%|███████▊  | 28342/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.74.down_proj:  78%|███████▊  | 28342/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.75.gate_proj:  78%|███████▊  | 28343/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.75.up_proj:  78%|███████▊  | 28344/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.75.down_proj:  78%|███████▊  | 28345/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.76.gate_proj:  78%|███████▊  | 28346/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.76.up_proj:  78%|███████▊  | 28347/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.76.down_proj:  78%|███████▊  | 28348/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.77.gate_proj:  78%|███████▊  | 28349/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.77.up_proj:  78%|███████▊  | 28350/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.77.down_proj:  78%|███████▊  | 28351/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.78.gate_proj:  78%|███████▊  | 28352/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.78.up_proj:  78%|███████▊  | 28353/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.78.down_proj:  78%|███████▊  | 28354/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.79.gate_proj:  78%|███████▊  | 28355/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.79.up_proj:  78%|███████▊  | 28356/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.79.down_proj:  78%|███████▊  | 28357/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.80.gate_proj:  78%|███████▊  | 28358/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.80.up_proj:  78%|███████▊  | 28359/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.80.down_proj:  78%|███████▊  | 28360/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.81.gate_proj:  78%|███████▊  | 28361/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.81.up_proj:  78%|███████▊  | 28362/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.81.down_proj:  78%|███████▊  | 28363/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.82.gate_proj:  78%|███████▊  | 28364/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.82.up_proj:  78%|███████▊  | 28365/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.82.down_proj:  78%|███████▊  | 28366/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.83.gate_proj:  78%|███████▊  | 28367/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.83.up_proj:  78%|███████▊  | 28368/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.83.down_proj:  78%|███████▊  | 28369/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.84.gate_proj:  78%|███████▊  | 28370/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.84.up_proj:  78%|███████▊  | 28371/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.84.down_proj:  78%|███████▊  | 28372/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.85.gate_proj:  78%|███████▊  | 28373/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.85.up_proj:  78%|███████▊  | 28374/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.85.down_proj:  78%|███████▊  | 28375/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.86.gate_proj:  78%|███████▊  | 28376/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.86.up_proj:  78%|███████▊  | 28377/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.86.down_proj:  78%|███████▊  | 28378/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.87.gate_proj:  78%|███████▊  | 28379/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.87.up_proj:  78%|███████▊  | 28380/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.87.down_proj:  78%|███████▊  | 28381/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.88.gate_proj:  78%|███████▊  | 28382/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.88.up_proj:  78%|███████▊  | 28383/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.88.down_proj:  78%|███████▊  | 28384/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.89.gate_proj:  78%|███████▊  | 28385/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.89.up_proj:  78%|███████▊  | 28386/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.89.down_proj:  78%|███████▊  | 28387/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.90.gate_proj:  78%|███████▊  | 28388/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.90.up_proj:  78%|███████▊  | 28389/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.90.down_proj:  78%|███████▊  | 28390/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.91.gate_proj:  78%|███████▊  | 28391/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.91.up_proj:  78%|███████▊  | 28392/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.91.down_proj:  78%|███████▊  | 28393/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.92.gate_proj:  78%|███████▊  | 28394/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.92.up_proj:  78%|███████▊  | 28395/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.92.down_proj:  78%|███████▊  | 28396/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.93.gate_proj:  78%|███████▊  | 28397/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.93.up_proj:  78%|███████▊  | 28398/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.93.down_proj:  78%|███████▊  | 28399/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.94.gate_proj:  78%|███████▊  | 28400/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.94.up_proj:  78%|███████▊  | 28401/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.94.down_proj:  78%|███████▊  | 28402/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.95.gate_proj:  78%|███████▊  | 28403/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.95.up_proj:  78%|███████▊  | 28404/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.95.down_proj:  78%|███████▊  | 28405/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.96.gate_proj:  78%|███████▊  | 28406/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.96.up_proj:  78%|███████▊  | 28407/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.96.down_proj:  78%|███████▊  | 28408/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.97.gate_proj:  78%|███████▊  | 28409/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.97.up_proj:  78%|███████▊  | 28410/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.97.down_proj:  78%|███████▊  | 28411/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.98.gate_proj:  78%|███████▊  | 28412/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.98.up_proj:  78%|███████▊  | 28413/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.98.down_proj:  78%|███████▊  | 28414/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.99.gate_proj:  78%|███████▊  | 28415/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.99.up_proj:  78%|███████▊  | 28416/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.99.down_proj:  78%|███████▊  | 28417/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.100.gate_proj:  78%|███████▊  | 28418/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.100.up_proj:  78%|███████▊  | 28419/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.100.down_proj:  78%|███████▊  | 28420/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.101.gate_proj:  78%|███████▊  | 28421/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.101.up_proj:  78%|███████▊  | 28422/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.101.down_proj:  78%|███████▊  | 28423/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.102.gate_proj:  78%|███████▊  | 28424/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.102.up_proj:  78%|███████▊  | 28425/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.102.down_proj:  78%|███████▊  | 28426/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.103.gate_proj:  78%|███████▊  | 28427/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.103.up_proj:  78%|███████▊  | 28428/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.103.down_proj:  78%|███████▊  | 28429/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.104.gate_proj:  78%|███████▊  | 28430/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.104.up_proj:  78%|███████▊  | 28431/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.104.down_proj:  78%|███████▊  | 28432/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.105.gate_proj:  78%|███████▊  | 28433/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.105.up_proj:  78%|███████▊  | 28434/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.105.down_proj:  78%|███████▊  | 28435/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.106.gate_proj:  78%|███████▊  | 28436/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.106.up_proj:  78%|███████▊  | 28437/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.106.down_proj:  78%|███████▊  | 28438/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.107.gate_proj:  78%|███████▊  | 28439/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.107.up_proj:  78%|███████▊  | 28440/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.107.down_proj:  78%|███████▊  | 28441/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.108.gate_proj:  78%|███████▊  | 28442/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.108.up_proj:  78%|███████▊  | 28443/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.108.down_proj:  78%|███████▊  | 28444/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.109.gate_proj:  78%|███████▊  | 28445/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.109.up_proj:  78%|███████▊  | 28446/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.109.down_proj:  78%|███████▊  | 28447/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.110.gate_proj:  78%|███████▊  | 28448/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.110.up_proj:  78%|███████▊  | 28449/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.110.down_proj:  78%|███████▊  | 28450/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.111.gate_proj:  78%|███████▊  | 28451/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.111.up_proj:  78%|███████▊  | 28452/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.111.down_proj:  78%|███████▊  | 28453/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.112.gate_proj:  78%|███████▊  | 28454/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.112.up_proj:  78%|███████▊  | 28455/36566 [00:25<00:07, 1144.99it/s]  
packing model.layers.72.mlp.experts.112.down_proj:  78%|███████▊  | 28456/36566 [00:25<00:07, 1144.99it/s]
packing model.layers.72.mlp.experts.112.down_proj:  78%|███████▊  | 28457/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.113.gate_proj:  78%|███████▊  | 28457/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.113.up_proj:  78%|███████▊  | 28458/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.113.down_proj:  78%|███████▊  | 28459/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.114.gate_proj:  78%|███████▊  | 28460/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.114.up_proj:  78%|███████▊  | 28461/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.114.down_proj:  78%|███████▊  | 28462/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.115.gate_proj:  78%|███████▊  | 28463/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.115.up_proj:  78%|███████▊  | 28464/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.115.down_proj:  78%|███████▊  | 28465/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.116.gate_proj:  78%|███████▊  | 28466/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.116.up_proj:  78%|███████▊  | 28467/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.116.down_proj:  78%|███████▊  | 28468/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.117.gate_proj:  78%|███████▊  | 28469/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.117.up_proj:  78%|███████▊  | 28470/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.117.down_proj:  78%|███████▊  | 28471/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.118.gate_proj:  78%|███████▊  | 28472/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.118.up_proj:  78%|███████▊  | 28473/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.118.down_proj:  78%|███████▊  | 28474/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.119.gate_proj:  78%|███████▊  | 28475/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.119.up_proj:  78%|███████▊  | 28476/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.119.down_proj:  78%|███████▊  | 28477/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.120.gate_proj:  78%|███████▊  | 28478/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.120.up_proj:  78%|███████▊  | 28479/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.120.down_proj:  78%|███████▊  | 28480/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.121.gate_proj:  78%|███████▊  | 28481/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.121.up_proj:  78%|███████▊  | 28482/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.121.down_proj:  78%|███████▊  | 28483/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.122.gate_proj:  78%|███████▊  | 28484/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.122.up_proj:  78%|███████▊  | 28485/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.122.down_proj:  78%|███████▊  | 28486/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.123.gate_proj:  78%|███████▊  | 28487/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.123.up_proj:  78%|███████▊  | 28488/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.123.down_proj:  78%|███████▊  | 28489/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.124.gate_proj:  78%|███████▊  | 28490/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.124.up_proj:  78%|███████▊  | 28491/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.124.down_proj:  78%|███████▊  | 28492/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.125.gate_proj:  78%|███████▊  | 28493/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.125.up_proj:  78%|███████▊  | 28494/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.125.down_proj:  78%|███████▊  | 28495/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.126.gate_proj:  78%|███████▊  | 28496/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.126.up_proj:  78%|███████▊  | 28497/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.126.down_proj:  78%|███████▊  | 28498/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.127.gate_proj:  78%|███████▊  | 28499/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.72.mlp.experts.127.up_proj:  78%|███████▊  | 28500/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.72.mlp.experts.127.down_proj:  78%|███████▊  | 28501/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.0.gate_proj:  78%|███████▊  | 28502/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.0.up_proj:  78%|███████▊  | 28503/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.0.down_proj:  78%|███████▊  | 28504/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.1.gate_proj:  78%|███████▊  | 28505/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.1.up_proj:  78%|███████▊  | 28506/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.1.down_proj:  78%|███████▊  | 28507/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.2.gate_proj:  78%|███████▊  | 28508/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.2.up_proj:  78%|███████▊  | 28509/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.2.down_proj:  78%|███████▊  | 28510/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.3.gate_proj:  78%|███████▊  | 28511/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.3.up_proj:  78%|███████▊  | 28512/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.3.down_proj:  78%|███████▊  | 28513/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.4.gate_proj:  78%|███████▊  | 28514/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.4.up_proj:  78%|███████▊  | 28515/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.4.down_proj:  78%|███████▊  | 28516/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.5.gate_proj:  78%|███████▊  | 28517/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.5.up_proj:  78%|███████▊  | 28518/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.5.down_proj:  78%|███████▊  | 28519/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.6.gate_proj:  78%|███████▊  | 28520/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.6.up_proj:  78%|███████▊  | 28521/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.6.down_proj:  78%|███████▊  | 28522/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.7.gate_proj:  78%|███████▊  | 28523/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.7.up_proj:  78%|███████▊  | 28524/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.7.down_proj:  78%|███████▊  | 28525/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.8.gate_proj:  78%|███████▊  | 28526/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.8.up_proj:  78%|███████▊  | 28527/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.8.down_proj:  78%|███████▊  | 28528/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.9.gate_proj:  78%|███████▊  | 28529/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.9.up_proj:  78%|███████▊  | 28530/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.9.down_proj:  78%|███████▊  | 28531/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.10.gate_proj:  78%|███████▊  | 28532/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.10.up_proj:  78%|███████▊  | 28533/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.10.down_proj:  78%|███████▊  | 28534/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.11.gate_proj:  78%|███████▊  | 28535/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.11.up_proj:  78%|███████▊  | 28536/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.11.down_proj:  78%|███████▊  | 28537/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.12.gate_proj:  78%|███████▊  | 28538/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.12.up_proj:  78%|███████▊  | 28539/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.12.down_proj:  78%|███████▊  | 28540/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.13.gate_proj:  78%|███████▊  | 28541/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.13.up_proj:  78%|███████▊  | 28542/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.13.down_proj:  78%|███████▊  | 28543/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.14.gate_proj:  78%|███████▊  | 28544/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.14.up_proj:  78%|███████▊  | 28545/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.14.down_proj:  78%|███████▊  | 28546/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.15.gate_proj:  78%|███████▊  | 28547/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.15.up_proj:  78%|███████▊  | 28548/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.15.down_proj:  78%|███████▊  | 28549/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.16.gate_proj:  78%|███████▊  | 28550/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.16.up_proj:  78%|███████▊  | 28551/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.16.down_proj:  78%|███████▊  | 28552/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.17.gate_proj:  78%|███████▊  | 28553/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.17.up_proj:  78%|███████▊  | 28554/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.17.down_proj:  78%|███████▊  | 28555/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.18.gate_proj:  78%|███████▊  | 28556/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.18.up_proj:  78%|███████▊  | 28557/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.18.down_proj:  78%|███████▊  | 28558/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.19.gate_proj:  78%|███████▊  | 28559/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.19.up_proj:  78%|███████▊  | 28560/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.19.down_proj:  78%|███████▊  | 28561/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.20.gate_proj:  78%|███████▊  | 28562/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.20.up_proj:  78%|███████▊  | 28563/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.20.down_proj:  78%|███████▊  | 28564/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.21.gate_proj:  78%|███████▊  | 28565/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.21.up_proj:  78%|███████▊  | 28566/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.21.down_proj:  78%|███████▊  | 28567/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.22.gate_proj:  78%|███████▊  | 28568/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.22.up_proj:  78%|███████▊  | 28569/36566 [00:25<00:07, 1140.38it/s]  
packing model.layers.73.mlp.experts.22.down_proj:  78%|███████▊  | 28570/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.23.gate_proj:  78%|███████▊  | 28571/36566 [00:25<00:07, 1140.38it/s]
packing model.layers.73.mlp.experts.23.gate_proj:  78%|███████▊  | 28572/36566 [00:25<00:07, 1141.06it/s]
packing model.layers.73.mlp.experts.23.up_proj:  78%|███████▊  | 28572/36566 [00:25<00:07, 1141.06it/s]  
packing model.layers.73.mlp.experts.23.down_proj:  78%|███████▊  | 28573/36566 [00:25<00:07, 1141.06it/s]
packing model.layers.73.mlp.experts.24.gate_proj:  78%|███████▊  | 28574/36566 [00:25<00:07, 1141.06it/s]
packing model.layers.73.mlp.experts.24.up_proj:  78%|███████▊  | 28575/36566 [00:25<00:07, 1141.06it/s]  
packing model.layers.73.mlp.experts.24.down_proj:  78%|███████▊  | 28576/36566 [00:25<00:07, 1141.06it/s]
packing model.layers.73.mlp.experts.25.gate_proj:  78%|███████▊  | 28577/36566 [00:25<00:07, 1141.06it/s]
packing model.layers.73.mlp.experts.25.up_proj:  78%|███████▊  | 28578/36566 [00:25<00:07, 1141.06it/s]  
packing model.layers.73.mlp.experts.25.down_proj:  78%|███████▊  | 28579/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.26.gate_proj:  78%|███████▊  | 28580/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.26.up_proj:  78%|███████▊  | 28581/36566 [00:25<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.26.down_proj:  78%|███████▊  | 28582/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.27.gate_proj:  78%|███████▊  | 28583/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.27.up_proj:  78%|███████▊  | 28584/36566 [00:25<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.27.down_proj:  78%|███████▊  | 28585/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.28.gate_proj:  78%|███████▊  | 28586/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.28.up_proj:  78%|███████▊  | 28587/36566 [00:25<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.28.down_proj:  78%|███████▊  | 28588/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.29.gate_proj:  78%|███████▊  | 28589/36566 [00:25<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.29.up_proj:  78%|███████▊  | 28590/36566 [00:25<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.29.down_proj:  78%|███████▊  | 28591/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.30.gate_proj:  78%|███████▊  | 28592/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.30.up_proj:  78%|███████▊  | 28593/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.30.down_proj:  78%|███████▊  | 28594/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.31.gate_proj:  78%|███████▊  | 28595/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.31.up_proj:  78%|███████▊  | 28596/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.31.down_proj:  78%|███████▊  | 28597/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.32.gate_proj:  78%|███████▊  | 28598/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.32.up_proj:  78%|███████▊  | 28599/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.32.down_proj:  78%|███████▊  | 28600/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.33.gate_proj:  78%|███████▊  | 28601/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.33.up_proj:  78%|███████▊  | 28602/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.33.down_proj:  78%|███████▊  | 28603/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.34.gate_proj:  78%|███████▊  | 28604/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.34.up_proj:  78%|███████▊  | 28605/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.34.down_proj:  78%|███████▊  | 28606/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.35.gate_proj:  78%|███████▊  | 28607/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.35.up_proj:  78%|███████▊  | 28608/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.35.down_proj:  78%|███████▊  | 28609/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.36.gate_proj:  78%|███████▊  | 28610/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.36.up_proj:  78%|███████▊  | 28611/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.36.down_proj:  78%|███████▊  | 28612/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.37.gate_proj:  78%|███████▊  | 28613/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.37.up_proj:  78%|███████▊  | 28614/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.37.down_proj:  78%|███████▊  | 28615/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.38.gate_proj:  78%|███████▊  | 28616/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.38.up_proj:  78%|███████▊  | 28617/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.38.down_proj:  78%|███████▊  | 28618/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.39.gate_proj:  78%|███████▊  | 28619/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.39.up_proj:  78%|███████▊  | 28620/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.39.down_proj:  78%|███████▊  | 28621/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.40.gate_proj:  78%|███████▊  | 28622/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.40.up_proj:  78%|███████▊  | 28623/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.40.down_proj:  78%|███████▊  | 28624/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.41.gate_proj:  78%|███████▊  | 28625/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.41.up_proj:  78%|███████▊  | 28626/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.41.down_proj:  78%|███████▊  | 28627/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.42.gate_proj:  78%|███████▊  | 28628/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.42.up_proj:  78%|███████▊  | 28629/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.42.down_proj:  78%|███████▊  | 28630/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.43.gate_proj:  78%|███████▊  | 28631/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.43.up_proj:  78%|███████▊  | 28632/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.43.down_proj:  78%|███████▊  | 28633/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.44.gate_proj:  78%|███████▊  | 28634/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.44.up_proj:  78%|███████▊  | 28635/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.44.down_proj:  78%|███████▊  | 28636/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.45.gate_proj:  78%|███████▊  | 28637/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.45.up_proj:  78%|███████▊  | 28638/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.45.down_proj:  78%|███████▊  | 28639/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.46.gate_proj:  78%|███████▊  | 28640/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.46.up_proj:  78%|███████▊  | 28641/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.46.down_proj:  78%|███████▊  | 28642/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.47.gate_proj:  78%|███████▊  | 28643/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.47.up_proj:  78%|███████▊  | 28644/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.47.down_proj:  78%|███████▊  | 28645/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.48.gate_proj:  78%|███████▊  | 28646/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.48.up_proj:  78%|███████▊  | 28647/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.48.down_proj:  78%|███████▊  | 28648/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.49.gate_proj:  78%|███████▊  | 28649/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.49.up_proj:  78%|███████▊  | 28650/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.49.down_proj:  78%|███████▊  | 28651/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.50.gate_proj:  78%|███████▊  | 28652/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.50.up_proj:  78%|███████▊  | 28653/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.50.down_proj:  78%|███████▊  | 28654/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.51.gate_proj:  78%|███████▊  | 28655/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.51.up_proj:  78%|███████▊  | 28656/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.51.down_proj:  78%|███████▊  | 28657/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.52.gate_proj:  78%|███████▊  | 28658/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.52.up_proj:  78%|███████▊  | 28659/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.52.down_proj:  78%|███████▊  | 28660/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.53.gate_proj:  78%|███████▊  | 28661/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.53.up_proj:  78%|███████▊  | 28662/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.53.down_proj:  78%|███████▊  | 28663/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.54.gate_proj:  78%|███████▊  | 28664/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.54.up_proj:  78%|███████▊  | 28665/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.54.down_proj:  78%|███████▊  | 28666/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.55.gate_proj:  78%|███████▊  | 28667/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.55.up_proj:  78%|███████▊  | 28668/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.55.down_proj:  78%|███████▊  | 28669/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.56.gate_proj:  78%|███████▊  | 28670/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.56.up_proj:  78%|███████▊  | 28671/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.56.down_proj:  78%|███████▊  | 28672/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.57.gate_proj:  78%|███████▊  | 28673/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.57.up_proj:  78%|███████▊  | 28674/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.57.down_proj:  78%|███████▊  | 28675/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.58.gate_proj:  78%|███████▊  | 28676/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.58.up_proj:  78%|███████▊  | 28677/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.58.down_proj:  78%|███████▊  | 28678/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.59.gate_proj:  78%|███████▊  | 28679/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.59.up_proj:  78%|███████▊  | 28680/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.59.down_proj:  78%|███████▊  | 28681/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.60.gate_proj:  78%|███████▊  | 28682/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.60.up_proj:  78%|███████▊  | 28683/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.60.down_proj:  78%|███████▊  | 28684/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.61.gate_proj:  78%|███████▊  | 28685/36566 [00:26<00:06, 1141.06it/s]
packing model.layers.73.mlp.experts.61.up_proj:  78%|███████▊  | 28686/36566 [00:26<00:06, 1141.06it/s]  
packing model.layers.73.mlp.experts.61.up_proj:  78%|███████▊  | 28687/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.61.down_proj:  78%|███████▊  | 28687/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.62.gate_proj:  78%|███████▊  | 28688/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.62.up_proj:  78%|███████▊  | 28689/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.62.down_proj:  78%|███████▊  | 28690/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.63.gate_proj:  78%|███████▊  | 28691/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.63.up_proj:  78%|███████▊  | 28692/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.63.down_proj:  78%|███████▊  | 28693/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.64.gate_proj:  78%|███████▊  | 28694/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.64.up_proj:  78%|███████▊  | 28695/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.64.down_proj:  78%|███████▊  | 28696/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.65.gate_proj:  78%|███████▊  | 28697/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.65.up_proj:  78%|███████▊  | 28698/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.65.down_proj:  78%|███████▊  | 28699/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.66.gate_proj:  78%|███████▊  | 28700/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.66.up_proj:  78%|███████▊  | 28701/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.66.down_proj:  78%|███████▊  | 28702/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.67.gate_proj:  78%|███████▊  | 28703/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.67.up_proj:  78%|███████▊  | 28704/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.67.down_proj:  79%|███████▊  | 28705/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.68.gate_proj:  79%|███████▊  | 28706/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.68.up_proj:  79%|███████▊  | 28707/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.68.down_proj:  79%|███████▊  | 28708/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.69.gate_proj:  79%|███████▊  | 28709/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.69.up_proj:  79%|███████▊  | 28710/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.69.down_proj:  79%|███████▊  | 28711/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.70.gate_proj:  79%|███████▊  | 28712/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.70.up_proj:  79%|███████▊  | 28713/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.70.down_proj:  79%|███████▊  | 28714/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.71.gate_proj:  79%|███████▊  | 28715/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.71.up_proj:  79%|███████▊  | 28716/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.71.down_proj:  79%|███████▊  | 28717/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.72.gate_proj:  79%|███████▊  | 28718/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.72.up_proj:  79%|███████▊  | 28719/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.72.down_proj:  79%|███████▊  | 28720/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.73.gate_proj:  79%|███████▊  | 28721/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.73.up_proj:  79%|███████▊  | 28722/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.73.down_proj:  79%|███████▊  | 28723/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.74.gate_proj:  79%|███████▊  | 28724/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.74.up_proj:  79%|███████▊  | 28725/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.74.down_proj:  79%|███████▊  | 28726/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.75.gate_proj:  79%|███████▊  | 28727/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.75.up_proj:  79%|███████▊  | 28728/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.75.down_proj:  79%|███████▊  | 28729/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.76.gate_proj:  79%|███████▊  | 28730/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.76.up_proj:  79%|███████▊  | 28731/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.76.down_proj:  79%|███████▊  | 28732/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.77.gate_proj:  79%|███████▊  | 28733/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.77.up_proj:  79%|███████▊  | 28734/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.77.down_proj:  79%|███████▊  | 28735/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.78.gate_proj:  79%|███████▊  | 28736/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.78.up_proj:  79%|███████▊  | 28737/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.78.down_proj:  79%|███████▊  | 28738/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.79.gate_proj:  79%|███████▊  | 28739/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.79.up_proj:  79%|███████▊  | 28740/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.79.down_proj:  79%|███████▊  | 28741/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.80.gate_proj:  79%|███████▊  | 28742/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.80.up_proj:  79%|███████▊  | 28743/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.80.down_proj:  79%|███████▊  | 28744/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.81.gate_proj:  79%|███████▊  | 28745/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.81.up_proj:  79%|███████▊  | 28746/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.81.down_proj:  79%|███████▊  | 28747/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.82.gate_proj:  79%|███████▊  | 28748/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.82.up_proj:  79%|███████▊  | 28749/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.82.down_proj:  79%|███████▊  | 28750/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.83.gate_proj:  79%|███████▊  | 28751/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.83.up_proj:  79%|███████▊  | 28752/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.83.down_proj:  79%|███████▊  | 28753/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.84.gate_proj:  79%|███████▊  | 28754/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.84.up_proj:  79%|███████▊  | 28755/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.84.down_proj:  79%|███████▊  | 28756/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.85.gate_proj:  79%|███████▊  | 28757/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.85.up_proj:  79%|███████▊  | 28758/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.85.down_proj:  79%|███████▊  | 28759/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.86.gate_proj:  79%|███████▊  | 28760/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.86.up_proj:  79%|███████▊  | 28761/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.86.down_proj:  79%|███████▊  | 28762/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.87.gate_proj:  79%|███████▊  | 28763/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.87.up_proj:  79%|███████▊  | 28764/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.87.down_proj:  79%|███████▊  | 28765/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.88.gate_proj:  79%|███████▊  | 28766/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.88.up_proj:  79%|███████▊  | 28767/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.88.down_proj:  79%|███████▊  | 28768/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.89.gate_proj:  79%|███████▊  | 28769/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.89.up_proj:  79%|███████▊  | 28770/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.89.down_proj:  79%|███████▊  | 28771/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.90.gate_proj:  79%|███████▊  | 28772/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.90.up_proj:  79%|███████▊  | 28773/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.90.down_proj:  79%|███████▊  | 28774/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.91.gate_proj:  79%|███████▊  | 28775/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.91.up_proj:  79%|███████▊  | 28776/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.91.down_proj:  79%|███████▊  | 28777/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.92.gate_proj:  79%|███████▊  | 28778/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.92.up_proj:  79%|███████▊  | 28779/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.92.down_proj:  79%|███████▊  | 28780/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.93.gate_proj:  79%|███████▊  | 28781/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.93.up_proj:  79%|███████▊  | 28782/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.93.down_proj:  79%|███████▊  | 28783/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.94.gate_proj:  79%|███████▊  | 28784/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.94.up_proj:  79%|███████▊  | 28785/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.94.down_proj:  79%|███████▊  | 28786/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.95.gate_proj:  79%|███████▊  | 28787/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.95.up_proj:  79%|███████▊  | 28788/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.95.down_proj:  79%|███████▊  | 28789/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.96.gate_proj:  79%|███████▊  | 28790/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.96.up_proj:  79%|███████▊  | 28791/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.96.down_proj:  79%|███████▊  | 28792/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.97.gate_proj:  79%|███████▊  | 28793/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.97.up_proj:  79%|███████▊  | 28794/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.97.down_proj:  79%|███████▊  | 28795/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.98.gate_proj:  79%|███████▉  | 28796/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.98.up_proj:  79%|███████▉  | 28797/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.98.down_proj:  79%|███████▉  | 28798/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.99.gate_proj:  79%|███████▉  | 28799/36566 [00:26<00:06, 1133.64it/s]
packing model.layers.73.mlp.experts.99.up_proj:  79%|███████▉  | 28800/36566 [00:26<00:06, 1133.64it/s]  
packing model.layers.73.mlp.experts.99.up_proj:  79%|███████▉  | 28801/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.99.down_proj:  79%|███████▉  | 28801/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.100.gate_proj:  79%|███████▉  | 28802/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.100.up_proj:  79%|███████▉  | 28803/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.100.down_proj:  79%|███████▉  | 28804/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.101.gate_proj:  79%|███████▉  | 28805/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.101.up_proj:  79%|███████▉  | 28806/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.101.down_proj:  79%|███████▉  | 28807/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.102.gate_proj:  79%|███████▉  | 28808/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.102.up_proj:  79%|███████▉  | 28809/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.102.down_proj:  79%|███████▉  | 28810/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.103.gate_proj:  79%|███████▉  | 28811/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.103.up_proj:  79%|███████▉  | 28812/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.103.down_proj:  79%|███████▉  | 28813/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.104.gate_proj:  79%|███████▉  | 28814/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.104.up_proj:  79%|███████▉  | 28815/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.104.down_proj:  79%|███████▉  | 28816/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.105.gate_proj:  79%|███████▉  | 28817/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.105.up_proj:  79%|███████▉  | 28818/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.105.down_proj:  79%|███████▉  | 28819/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.106.gate_proj:  79%|███████▉  | 28820/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.106.up_proj:  79%|███████▉  | 28821/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.106.down_proj:  79%|███████▉  | 28822/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.107.gate_proj:  79%|███████▉  | 28823/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.107.up_proj:  79%|███████▉  | 28824/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.107.down_proj:  79%|███████▉  | 28825/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.108.gate_proj:  79%|███████▉  | 28826/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.108.up_proj:  79%|███████▉  | 28827/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.108.down_proj:  79%|███████▉  | 28828/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.109.gate_proj:  79%|███████▉  | 28829/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.109.up_proj:  79%|███████▉  | 28830/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.109.down_proj:  79%|███████▉  | 28831/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.110.gate_proj:  79%|███████▉  | 28832/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.110.up_proj:  79%|███████▉  | 28833/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.110.down_proj:  79%|███████▉  | 28834/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.111.gate_proj:  79%|███████▉  | 28835/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.111.up_proj:  79%|███████▉  | 28836/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.111.down_proj:  79%|███████▉  | 28837/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.112.gate_proj:  79%|███████▉  | 28838/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.112.up_proj:  79%|███████▉  | 28839/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.112.down_proj:  79%|███████▉  | 28840/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.113.gate_proj:  79%|███████▉  | 28841/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.113.up_proj:  79%|███████▉  | 28842/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.113.down_proj:  79%|███████▉  | 28843/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.114.gate_proj:  79%|███████▉  | 28844/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.114.up_proj:  79%|███████▉  | 28845/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.114.down_proj:  79%|███████▉  | 28846/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.115.gate_proj:  79%|███████▉  | 28847/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.115.up_proj:  79%|███████▉  | 28848/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.115.down_proj:  79%|███████▉  | 28849/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.116.gate_proj:  79%|███████▉  | 28850/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.116.up_proj:  79%|███████▉  | 28851/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.116.down_proj:  79%|███████▉  | 28852/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.117.gate_proj:  79%|███████▉  | 28853/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.117.up_proj:  79%|███████▉  | 28854/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.117.down_proj:  79%|███████▉  | 28855/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.118.gate_proj:  79%|███████▉  | 28856/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.118.up_proj:  79%|███████▉  | 28857/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.118.down_proj:  79%|███████▉  | 28858/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.119.gate_proj:  79%|███████▉  | 28859/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.119.up_proj:  79%|███████▉  | 28860/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.119.down_proj:  79%|███████▉  | 28861/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.120.gate_proj:  79%|███████▉  | 28862/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.120.up_proj:  79%|███████▉  | 28863/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.120.down_proj:  79%|███████▉  | 28864/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.121.gate_proj:  79%|███████▉  | 28865/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.121.up_proj:  79%|███████▉  | 28866/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.121.down_proj:  79%|███████▉  | 28867/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.122.gate_proj:  79%|███████▉  | 28868/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.122.up_proj:  79%|███████▉  | 28869/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.122.down_proj:  79%|███████▉  | 28870/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.123.gate_proj:  79%|███████▉  | 28871/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.123.up_proj:  79%|███████▉  | 28872/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.123.down_proj:  79%|███████▉  | 28873/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.124.gate_proj:  79%|███████▉  | 28874/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.124.up_proj:  79%|███████▉  | 28875/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.124.down_proj:  79%|███████▉  | 28876/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.125.gate_proj:  79%|███████▉  | 28877/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.125.up_proj:  79%|███████▉  | 28878/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.125.down_proj:  79%|███████▉  | 28879/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.126.gate_proj:  79%|███████▉  | 28880/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.126.up_proj:  79%|███████▉  | 28881/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.126.down_proj:  79%|███████▉  | 28882/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.127.gate_proj:  79%|███████▉  | 28883/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.73.mlp.experts.127.up_proj:  79%|███████▉  | 28884/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.73.mlp.experts.127.down_proj:  79%|███████▉  | 28885/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.0.gate_proj:  79%|███████▉  | 28886/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.0.up_proj:  79%|███████▉  | 28887/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.0.down_proj:  79%|███████▉  | 28888/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.1.gate_proj:  79%|███████▉  | 28889/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.1.up_proj:  79%|███████▉  | 28890/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.1.down_proj:  79%|███████▉  | 28891/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.2.gate_proj:  79%|███████▉  | 28892/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.2.up_proj:  79%|███████▉  | 28893/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.2.down_proj:  79%|███████▉  | 28894/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.3.gate_proj:  79%|███████▉  | 28895/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.3.up_proj:  79%|███████▉  | 28896/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.3.down_proj:  79%|███████▉  | 28897/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.4.gate_proj:  79%|███████▉  | 28898/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.4.up_proj:  79%|███████▉  | 28899/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.4.down_proj:  79%|███████▉  | 28900/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.5.gate_proj:  79%|███████▉  | 28901/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.5.up_proj:  79%|███████▉  | 28902/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.5.down_proj:  79%|███████▉  | 28903/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.6.gate_proj:  79%|███████▉  | 28904/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.6.up_proj:  79%|███████▉  | 28905/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.6.down_proj:  79%|███████▉  | 28906/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.7.gate_proj:  79%|███████▉  | 28907/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.7.up_proj:  79%|███████▉  | 28908/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.7.down_proj:  79%|███████▉  | 28909/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.8.gate_proj:  79%|███████▉  | 28910/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.8.up_proj:  79%|███████▉  | 28911/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.8.down_proj:  79%|███████▉  | 28912/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.9.gate_proj:  79%|███████▉  | 28913/36566 [00:26<00:06, 1131.27it/s]
packing model.layers.74.mlp.experts.9.up_proj:  79%|███████▉  | 28914/36566 [00:26<00:06, 1131.27it/s]  
packing model.layers.74.mlp.experts.9.up_proj:  79%|███████▉  | 28915/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.9.down_proj:  79%|███████▉  | 28915/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.10.gate_proj:  79%|███████▉  | 28916/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.10.up_proj:  79%|███████▉  | 28917/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.10.down_proj:  79%|███████▉  | 28918/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.11.gate_proj:  79%|███████▉  | 28919/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.11.up_proj:  79%|███████▉  | 28920/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.11.down_proj:  79%|███████▉  | 28921/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.12.gate_proj:  79%|███████▉  | 28922/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.12.up_proj:  79%|███████▉  | 28923/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.12.down_proj:  79%|███████▉  | 28924/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.13.gate_proj:  79%|███████▉  | 28925/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.13.up_proj:  79%|███████▉  | 28926/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.13.down_proj:  79%|███████▉  | 28927/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.14.gate_proj:  79%|███████▉  | 28928/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.14.up_proj:  79%|███████▉  | 28929/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.14.down_proj:  79%|███████▉  | 28930/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.15.gate_proj:  79%|███████▉  | 28931/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.15.up_proj:  79%|███████▉  | 28932/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.15.down_proj:  79%|███████▉  | 28933/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.16.gate_proj:  79%|███████▉  | 28934/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.16.up_proj:  79%|███████▉  | 28935/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.16.down_proj:  79%|███████▉  | 28936/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.17.gate_proj:  79%|███████▉  | 28937/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.17.up_proj:  79%|███████▉  | 28938/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.17.down_proj:  79%|███████▉  | 28939/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.18.gate_proj:  79%|███████▉  | 28940/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.18.up_proj:  79%|███████▉  | 28941/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.18.down_proj:  79%|███████▉  | 28942/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.19.gate_proj:  79%|███████▉  | 28943/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.19.up_proj:  79%|███████▉  | 28944/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.19.down_proj:  79%|███████▉  | 28945/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.20.gate_proj:  79%|███████▉  | 28946/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.20.up_proj:  79%|███████▉  | 28947/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.20.down_proj:  79%|███████▉  | 28948/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.21.gate_proj:  79%|███████▉  | 28949/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.21.up_proj:  79%|███████▉  | 28950/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.21.down_proj:  79%|███████▉  | 28951/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.22.gate_proj:  79%|███████▉  | 28952/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.22.up_proj:  79%|███████▉  | 28953/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.22.down_proj:  79%|███████▉  | 28954/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.23.gate_proj:  79%|███████▉  | 28955/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.23.up_proj:  79%|███████▉  | 28956/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.23.down_proj:  79%|███████▉  | 28957/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.24.gate_proj:  79%|███████▉  | 28958/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.24.up_proj:  79%|███████▉  | 28959/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.24.down_proj:  79%|███████▉  | 28960/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.25.gate_proj:  79%|███████▉  | 28961/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.25.up_proj:  79%|███████▉  | 28962/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.25.down_proj:  79%|███████▉  | 28963/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.26.gate_proj:  79%|███████▉  | 28964/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.26.up_proj:  79%|███████▉  | 28965/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.26.down_proj:  79%|███████▉  | 28966/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.27.gate_proj:  79%|███████▉  | 28967/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.27.up_proj:  79%|███████▉  | 28968/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.27.down_proj:  79%|███████▉  | 28969/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.28.gate_proj:  79%|███████▉  | 28970/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.28.up_proj:  79%|███████▉  | 28971/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.28.down_proj:  79%|███████▉  | 28972/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.29.gate_proj:  79%|███████▉  | 28973/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.29.up_proj:  79%|███████▉  | 28974/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.29.down_proj:  79%|███████▉  | 28975/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.30.gate_proj:  79%|███████▉  | 28976/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.30.up_proj:  79%|███████▉  | 28977/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.30.down_proj:  79%|███████▉  | 28978/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.31.gate_proj:  79%|███████▉  | 28979/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.31.up_proj:  79%|███████▉  | 28980/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.31.down_proj:  79%|███████▉  | 28981/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.32.gate_proj:  79%|███████▉  | 28982/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.32.up_proj:  79%|███████▉  | 28983/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.32.down_proj:  79%|███████▉  | 28984/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.33.gate_proj:  79%|███████▉  | 28985/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.33.up_proj:  79%|███████▉  | 28986/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.33.down_proj:  79%|███████▉  | 28987/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.34.gate_proj:  79%|███████▉  | 28988/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.34.up_proj:  79%|███████▉  | 28989/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.34.down_proj:  79%|███████▉  | 28990/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.35.gate_proj:  79%|███████▉  | 28991/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.35.up_proj:  79%|███████▉  | 28992/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.35.down_proj:  79%|███████▉  | 28993/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.36.gate_proj:  79%|███████▉  | 28994/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.36.up_proj:  79%|███████▉  | 28995/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.36.down_proj:  79%|███████▉  | 28996/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.37.gate_proj:  79%|███████▉  | 28997/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.37.up_proj:  79%|███████▉  | 28998/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.37.down_proj:  79%|███████▉  | 28999/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.38.gate_proj:  79%|███████▉  | 29000/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.38.up_proj:  79%|███████▉  | 29001/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.38.down_proj:  79%|███████▉  | 29002/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.39.gate_proj:  79%|███████▉  | 29003/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.39.up_proj:  79%|███████▉  | 29004/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.39.down_proj:  79%|███████▉  | 29005/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.40.gate_proj:  79%|███████▉  | 29006/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.40.up_proj:  79%|███████▉  | 29007/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.40.down_proj:  79%|███████▉  | 29008/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.41.gate_proj:  79%|███████▉  | 29009/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.41.up_proj:  79%|███████▉  | 29010/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.41.down_proj:  79%|███████▉  | 29011/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.42.gate_proj:  79%|███████▉  | 29012/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.42.up_proj:  79%|███████▉  | 29013/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.42.down_proj:  79%|███████▉  | 29014/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.43.gate_proj:  79%|███████▉  | 29015/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.43.up_proj:  79%|███████▉  | 29016/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.43.down_proj:  79%|███████▉  | 29017/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.44.gate_proj:  79%|███████▉  | 29018/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.44.up_proj:  79%|███████▉  | 29019/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.44.down_proj:  79%|███████▉  | 29020/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.45.gate_proj:  79%|███████▉  | 29021/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.45.up_proj:  79%|███████▉  | 29022/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.45.down_proj:  79%|███████▉  | 29023/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.46.gate_proj:  79%|███████▉  | 29024/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.46.up_proj:  79%|███████▉  | 29025/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.46.down_proj:  79%|███████▉  | 29026/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.47.gate_proj:  79%|███████▉  | 29027/36566 [00:26<00:06, 1130.71it/s]
packing model.layers.74.mlp.experts.47.up_proj:  79%|███████▉  | 29028/36566 [00:26<00:06, 1130.71it/s]  
packing model.layers.74.mlp.experts.47.up_proj:  79%|███████▉  | 29029/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.47.down_proj:  79%|███████▉  | 29029/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.48.gate_proj:  79%|███████▉  | 29030/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.48.up_proj:  79%|███████▉  | 29031/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.48.down_proj:  79%|███████▉  | 29032/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.49.gate_proj:  79%|███████▉  | 29033/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.49.up_proj:  79%|███████▉  | 29034/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.49.down_proj:  79%|███████▉  | 29035/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.50.gate_proj:  79%|███████▉  | 29036/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.50.up_proj:  79%|███████▉  | 29037/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.50.down_proj:  79%|███████▉  | 29038/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.51.gate_proj:  79%|███████▉  | 29039/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.51.up_proj:  79%|███████▉  | 29040/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.51.down_proj:  79%|███████▉  | 29041/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.52.gate_proj:  79%|███████▉  | 29042/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.52.up_proj:  79%|███████▉  | 29043/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.52.down_proj:  79%|███████▉  | 29044/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.53.gate_proj:  79%|███████▉  | 29045/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.53.up_proj:  79%|███████▉  | 29046/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.53.down_proj:  79%|███████▉  | 29047/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.54.gate_proj:  79%|███████▉  | 29048/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.54.up_proj:  79%|███████▉  | 29049/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.54.down_proj:  79%|███████▉  | 29050/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.55.gate_proj:  79%|███████▉  | 29051/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.55.up_proj:  79%|███████▉  | 29052/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.55.down_proj:  79%|███████▉  | 29053/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.56.gate_proj:  79%|███████▉  | 29054/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.56.up_proj:  79%|███████▉  | 29055/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.56.down_proj:  79%|███████▉  | 29056/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.57.gate_proj:  79%|███████▉  | 29057/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.57.up_proj:  79%|███████▉  | 29058/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.57.down_proj:  79%|███████▉  | 29059/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.58.gate_proj:  79%|███████▉  | 29060/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.58.up_proj:  79%|███████▉  | 29061/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.58.down_proj:  79%|███████▉  | 29062/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.59.gate_proj:  79%|███████▉  | 29063/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.59.up_proj:  79%|███████▉  | 29064/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.59.down_proj:  79%|███████▉  | 29065/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.60.gate_proj:  79%|███████▉  | 29066/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.60.up_proj:  79%|███████▉  | 29067/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.60.down_proj:  79%|███████▉  | 29068/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.61.gate_proj:  79%|███████▉  | 29069/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.61.up_proj:  80%|███████▉  | 29070/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.61.down_proj:  80%|███████▉  | 29071/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.62.gate_proj:  80%|███████▉  | 29072/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.62.up_proj:  80%|███████▉  | 29073/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.62.down_proj:  80%|███████▉  | 29074/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.63.gate_proj:  80%|███████▉  | 29075/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.63.up_proj:  80%|███████▉  | 29076/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.63.down_proj:  80%|███████▉  | 29077/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.64.gate_proj:  80%|███████▉  | 29078/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.64.up_proj:  80%|███████▉  | 29079/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.64.down_proj:  80%|███████▉  | 29080/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.65.gate_proj:  80%|███████▉  | 29081/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.65.up_proj:  80%|███████▉  | 29082/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.65.down_proj:  80%|███████▉  | 29083/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.66.gate_proj:  80%|███████▉  | 29084/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.66.up_proj:  80%|███████▉  | 29085/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.66.down_proj:  80%|███████▉  | 29086/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.67.gate_proj:  80%|███████▉  | 29087/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.67.up_proj:  80%|███████▉  | 29088/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.67.down_proj:  80%|███████▉  | 29089/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.68.gate_proj:  80%|███████▉  | 29090/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.68.up_proj:  80%|███████▉  | 29091/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.68.down_proj:  80%|███████▉  | 29092/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.69.gate_proj:  80%|███████▉  | 29093/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.69.up_proj:  80%|███████▉  | 29094/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.69.down_proj:  80%|███████▉  | 29095/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.70.gate_proj:  80%|███████▉  | 29096/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.70.up_proj:  80%|███████▉  | 29097/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.70.down_proj:  80%|███████▉  | 29098/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.71.gate_proj:  80%|███████▉  | 29099/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.71.up_proj:  80%|███████▉  | 29100/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.71.down_proj:  80%|███████▉  | 29101/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.72.gate_proj:  80%|███████▉  | 29102/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.72.up_proj:  80%|███████▉  | 29103/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.72.down_proj:  80%|███████▉  | 29104/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.73.gate_proj:  80%|███████▉  | 29105/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.73.up_proj:  80%|███████▉  | 29106/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.73.down_proj:  80%|███████▉  | 29107/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.74.gate_proj:  80%|███████▉  | 29108/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.74.up_proj:  80%|███████▉  | 29109/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.74.down_proj:  80%|███████▉  | 29110/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.75.gate_proj:  80%|███████▉  | 29111/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.75.up_proj:  80%|███████▉  | 29112/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.75.down_proj:  80%|███████▉  | 29113/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.76.gate_proj:  80%|███████▉  | 29114/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.76.up_proj:  80%|███████▉  | 29115/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.76.down_proj:  80%|███████▉  | 29116/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.77.gate_proj:  80%|███████▉  | 29117/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.77.up_proj:  80%|███████▉  | 29118/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.77.down_proj:  80%|███████▉  | 29119/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.78.gate_proj:  80%|███████▉  | 29120/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.78.up_proj:  80%|███████▉  | 29121/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.78.down_proj:  80%|███████▉  | 29122/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.79.gate_proj:  80%|███████▉  | 29123/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.79.up_proj:  80%|███████▉  | 29124/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.79.down_proj:  80%|███████▉  | 29125/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.80.gate_proj:  80%|███████▉  | 29126/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.80.up_proj:  80%|███████▉  | 29127/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.80.down_proj:  80%|███████▉  | 29128/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.81.gate_proj:  80%|███████▉  | 29129/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.81.up_proj:  80%|███████▉  | 29130/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.81.down_proj:  80%|███████▉  | 29131/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.82.gate_proj:  80%|███████▉  | 29132/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.82.up_proj:  80%|███████▉  | 29133/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.82.down_proj:  80%|███████▉  | 29134/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.83.gate_proj:  80%|███████▉  | 29135/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.83.up_proj:  80%|███████▉  | 29136/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.83.down_proj:  80%|███████▉  | 29137/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.84.gate_proj:  80%|███████▉  | 29138/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.84.up_proj:  80%|███████▉  | 29139/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.84.down_proj:  80%|███████▉  | 29140/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.85.gate_proj:  80%|███████▉  | 29141/36566 [00:26<00:06, 1131.53it/s]
packing model.layers.74.mlp.experts.85.up_proj:  80%|███████▉  | 29142/36566 [00:26<00:06, 1131.53it/s]  
packing model.layers.74.mlp.experts.85.up_proj:  80%|███████▉  | 29143/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.85.down_proj:  80%|███████▉  | 29143/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.86.gate_proj:  80%|███████▉  | 29144/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.86.up_proj:  80%|███████▉  | 29145/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.86.down_proj:  80%|███████▉  | 29146/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.87.gate_proj:  80%|███████▉  | 29147/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.87.up_proj:  80%|███████▉  | 29148/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.87.down_proj:  80%|███████▉  | 29149/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.88.gate_proj:  80%|███████▉  | 29150/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.88.up_proj:  80%|███████▉  | 29151/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.88.down_proj:  80%|███████▉  | 29152/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.89.gate_proj:  80%|███████▉  | 29153/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.89.up_proj:  80%|███████▉  | 29154/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.89.down_proj:  80%|███████▉  | 29155/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.90.gate_proj:  80%|███████▉  | 29156/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.90.up_proj:  80%|███████▉  | 29157/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.90.down_proj:  80%|███████▉  | 29158/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.91.gate_proj:  80%|███████▉  | 29159/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.91.up_proj:  80%|███████▉  | 29160/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.91.down_proj:  80%|███████▉  | 29161/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.92.gate_proj:  80%|███████▉  | 29162/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.92.up_proj:  80%|███████▉  | 29163/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.92.down_proj:  80%|███████▉  | 29164/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.93.gate_proj:  80%|███████▉  | 29165/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.93.up_proj:  80%|███████▉  | 29166/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.93.down_proj:  80%|███████▉  | 29167/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.94.gate_proj:  80%|███████▉  | 29168/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.94.up_proj:  80%|███████▉  | 29169/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.94.down_proj:  80%|███████▉  | 29170/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.95.gate_proj:  80%|███████▉  | 29171/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.95.up_proj:  80%|███████▉  | 29172/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.95.down_proj:  80%|███████▉  | 29173/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.96.gate_proj:  80%|███████▉  | 29174/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.96.up_proj:  80%|███████▉  | 29175/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.96.down_proj:  80%|███████▉  | 29176/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.97.gate_proj:  80%|███████▉  | 29177/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.97.up_proj:  80%|███████▉  | 29178/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.97.down_proj:  80%|███████▉  | 29179/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.98.gate_proj:  80%|███████▉  | 29180/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.98.up_proj:  80%|███████▉  | 29181/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.98.down_proj:  80%|███████▉  | 29182/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.99.gate_proj:  80%|███████▉  | 29183/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.99.up_proj:  80%|███████▉  | 29184/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.99.down_proj:  80%|███████▉  | 29185/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.100.gate_proj:  80%|███████▉  | 29186/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.100.up_proj:  80%|███████▉  | 29187/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.100.down_proj:  80%|███████▉  | 29188/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.101.gate_proj:  80%|███████▉  | 29189/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.101.up_proj:  80%|███████▉  | 29190/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.101.down_proj:  80%|███████▉  | 29191/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.102.gate_proj:  80%|███████▉  | 29192/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.102.up_proj:  80%|███████▉  | 29193/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.102.down_proj:  80%|███████▉  | 29194/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.103.gate_proj:  80%|███████▉  | 29195/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.103.up_proj:  80%|███████▉  | 29196/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.103.down_proj:  80%|███████▉  | 29197/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.104.gate_proj:  80%|███████▉  | 29198/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.104.up_proj:  80%|███████▉  | 29199/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.104.down_proj:  80%|███████▉  | 29200/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.105.gate_proj:  80%|███████▉  | 29201/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.105.up_proj:  80%|███████▉  | 29202/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.105.down_proj:  80%|███████▉  | 29203/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.106.gate_proj:  80%|███████▉  | 29204/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.106.up_proj:  80%|███████▉  | 29205/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.106.down_proj:  80%|███████▉  | 29206/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.107.gate_proj:  80%|███████▉  | 29207/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.107.up_proj:  80%|███████▉  | 29208/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.107.down_proj:  80%|███████▉  | 29209/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.108.gate_proj:  80%|███████▉  | 29210/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.108.up_proj:  80%|███████▉  | 29211/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.108.down_proj:  80%|███████▉  | 29212/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.109.gate_proj:  80%|███████▉  | 29213/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.109.up_proj:  80%|███████▉  | 29214/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.109.down_proj:  80%|███████▉  | 29215/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.110.gate_proj:  80%|███████▉  | 29216/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.110.up_proj:  80%|███████▉  | 29217/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.110.down_proj:  80%|███████▉  | 29218/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.111.gate_proj:  80%|███████▉  | 29219/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.111.up_proj:  80%|███████▉  | 29220/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.111.down_proj:  80%|███████▉  | 29221/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.112.gate_proj:  80%|███████▉  | 29222/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.112.up_proj:  80%|███████▉  | 29223/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.112.down_proj:  80%|███████▉  | 29224/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.113.gate_proj:  80%|███████▉  | 29225/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.113.up_proj:  80%|███████▉  | 29226/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.113.down_proj:  80%|███████▉  | 29227/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.114.gate_proj:  80%|███████▉  | 29228/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.114.up_proj:  80%|███████▉  | 29229/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.114.down_proj:  80%|███████▉  | 29230/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.115.gate_proj:  80%|███████▉  | 29231/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.115.up_proj:  80%|███████▉  | 29232/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.115.down_proj:  80%|███████▉  | 29233/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.116.gate_proj:  80%|███████▉  | 29234/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.116.up_proj:  80%|███████▉  | 29235/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.116.down_proj:  80%|███████▉  | 29236/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.117.gate_proj:  80%|███████▉  | 29237/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.117.up_proj:  80%|███████▉  | 29238/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.117.down_proj:  80%|███████▉  | 29239/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.118.gate_proj:  80%|███████▉  | 29240/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.118.up_proj:  80%|███████▉  | 29241/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.118.down_proj:  80%|███████▉  | 29242/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.119.gate_proj:  80%|███████▉  | 29243/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.119.up_proj:  80%|███████▉  | 29244/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.119.down_proj:  80%|███████▉  | 29245/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.120.gate_proj:  80%|███████▉  | 29246/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.120.up_proj:  80%|███████▉  | 29247/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.120.down_proj:  80%|███████▉  | 29248/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.121.gate_proj:  80%|███████▉  | 29249/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.121.up_proj:  80%|███████▉  | 29250/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.121.down_proj:  80%|███████▉  | 29251/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.122.gate_proj:  80%|███████▉  | 29252/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.122.up_proj:  80%|████████  | 29253/36566 [00:26<00:06, 1129.22it/s]  
packing model.layers.74.mlp.experts.122.down_proj:  80%|████████  | 29254/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.123.gate_proj:  80%|████████  | 29255/36566 [00:26<00:06, 1129.22it/s]
packing model.layers.74.mlp.experts.123.gate_proj:  80%|████████  | 29256/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.123.up_proj:  80%|████████  | 29256/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.74.mlp.experts.123.down_proj:  80%|████████  | 29257/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.124.gate_proj:  80%|████████  | 29258/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.124.up_proj:  80%|████████  | 29259/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.74.mlp.experts.124.down_proj:  80%|████████  | 29260/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.125.gate_proj:  80%|████████  | 29261/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.125.up_proj:  80%|████████  | 29262/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.74.mlp.experts.125.down_proj:  80%|████████  | 29263/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.126.gate_proj:  80%|████████  | 29264/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.126.up_proj:  80%|████████  | 29265/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.74.mlp.experts.126.down_proj:  80%|████████  | 29266/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.127.gate_proj:  80%|████████  | 29267/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.74.mlp.experts.127.up_proj:  80%|████████  | 29268/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.74.mlp.experts.127.down_proj:  80%|████████  | 29269/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.0.gate_proj:  80%|████████  | 29270/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.0.up_proj:  80%|████████  | 29271/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.0.down_proj:  80%|████████  | 29272/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.1.gate_proj:  80%|████████  | 29273/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.1.up_proj:  80%|████████  | 29274/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.1.down_proj:  80%|████████  | 29275/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.2.gate_proj:  80%|████████  | 29276/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.2.up_proj:  80%|████████  | 29277/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.2.down_proj:  80%|████████  | 29278/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.3.gate_proj:  80%|████████  | 29279/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.3.up_proj:  80%|████████  | 29280/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.3.down_proj:  80%|████████  | 29281/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.4.gate_proj:  80%|████████  | 29282/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.4.up_proj:  80%|████████  | 29283/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.4.down_proj:  80%|████████  | 29284/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.5.gate_proj:  80%|████████  | 29285/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.5.up_proj:  80%|████████  | 29286/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.5.down_proj:  80%|████████  | 29287/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.6.gate_proj:  80%|████████  | 29288/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.6.up_proj:  80%|████████  | 29289/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.6.down_proj:  80%|████████  | 29290/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.7.gate_proj:  80%|████████  | 29291/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.7.up_proj:  80%|████████  | 29292/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.7.down_proj:  80%|████████  | 29293/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.8.gate_proj:  80%|████████  | 29294/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.8.up_proj:  80%|████████  | 29295/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.8.down_proj:  80%|████████  | 29296/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.9.gate_proj:  80%|████████  | 29297/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.9.up_proj:  80%|████████  | 29298/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.9.down_proj:  80%|████████  | 29299/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.10.gate_proj:  80%|████████  | 29300/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.10.up_proj:  80%|████████  | 29301/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.10.down_proj:  80%|████████  | 29302/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.11.gate_proj:  80%|████████  | 29303/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.11.up_proj:  80%|████████  | 29304/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.11.down_proj:  80%|████████  | 29305/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.12.gate_proj:  80%|████████  | 29306/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.12.up_proj:  80%|████████  | 29307/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.12.down_proj:  80%|████████  | 29308/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.13.gate_proj:  80%|████████  | 29309/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.13.up_proj:  80%|████████  | 29310/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.13.down_proj:  80%|████████  | 29311/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.14.gate_proj:  80%|████████  | 29312/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.14.up_proj:  80%|████████  | 29313/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.14.down_proj:  80%|████████  | 29314/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.15.gate_proj:  80%|████████  | 29315/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.15.up_proj:  80%|████████  | 29316/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.15.down_proj:  80%|████████  | 29317/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.16.gate_proj:  80%|████████  | 29318/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.16.up_proj:  80%|████████  | 29319/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.16.down_proj:  80%|████████  | 29320/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.17.gate_proj:  80%|████████  | 29321/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.17.up_proj:  80%|████████  | 29322/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.17.down_proj:  80%|████████  | 29323/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.18.gate_proj:  80%|████████  | 29324/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.18.up_proj:  80%|████████  | 29325/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.18.down_proj:  80%|████████  | 29326/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.19.gate_proj:  80%|████████  | 29327/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.19.up_proj:  80%|████████  | 29328/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.19.down_proj:  80%|████████  | 29329/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.20.gate_proj:  80%|████████  | 29330/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.20.up_proj:  80%|████████  | 29331/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.20.down_proj:  80%|████████  | 29332/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.21.gate_proj:  80%|████████  | 29333/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.21.up_proj:  80%|████████  | 29334/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.21.down_proj:  80%|████████  | 29335/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.22.gate_proj:  80%|████████  | 29336/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.22.up_proj:  80%|████████  | 29337/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.22.down_proj:  80%|████████  | 29338/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.23.gate_proj:  80%|████████  | 29339/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.23.up_proj:  80%|████████  | 29340/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.23.down_proj:  80%|████████  | 29341/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.24.gate_proj:  80%|████████  | 29342/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.24.up_proj:  80%|████████  | 29343/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.24.down_proj:  80%|████████  | 29344/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.25.gate_proj:  80%|████████  | 29345/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.25.up_proj:  80%|████████  | 29346/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.25.down_proj:  80%|████████  | 29347/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.26.gate_proj:  80%|████████  | 29348/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.26.up_proj:  80%|████████  | 29349/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.26.down_proj:  80%|████████  | 29350/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.27.gate_proj:  80%|████████  | 29351/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.27.up_proj:  80%|████████  | 29352/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.27.down_proj:  80%|████████  | 29353/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.28.gate_proj:  80%|████████  | 29354/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.28.up_proj:  80%|████████  | 29355/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.28.down_proj:  80%|████████  | 29356/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.29.gate_proj:  80%|████████  | 29357/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.29.up_proj:  80%|████████  | 29358/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.29.down_proj:  80%|████████  | 29359/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.30.gate_proj:  80%|████████  | 29360/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.30.up_proj:  80%|████████  | 29361/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.30.down_proj:  80%|████████  | 29362/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.31.gate_proj:  80%|████████  | 29363/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.31.up_proj:  80%|████████  | 29364/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.31.down_proj:  80%|████████  | 29365/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.32.gate_proj:  80%|████████  | 29366/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.32.up_proj:  80%|████████  | 29367/36566 [00:26<00:06, 1129.25it/s]  
packing model.layers.75.mlp.experts.32.down_proj:  80%|████████  | 29368/36566 [00:26<00:06, 1129.25it/s]
packing model.layers.75.mlp.experts.32.down_proj:  80%|████████  | 29369/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.33.gate_proj:  80%|████████  | 29369/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.33.up_proj:  80%|████████  | 29370/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.33.down_proj:  80%|████████  | 29371/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.34.gate_proj:  80%|████████  | 29372/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.34.up_proj:  80%|████████  | 29373/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.34.down_proj:  80%|████████  | 29374/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.35.gate_proj:  80%|████████  | 29375/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.35.up_proj:  80%|████████  | 29376/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.35.down_proj:  80%|████████  | 29377/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.36.gate_proj:  80%|████████  | 29378/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.36.up_proj:  80%|████████  | 29379/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.36.down_proj:  80%|████████  | 29380/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.37.gate_proj:  80%|████████  | 29381/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.37.up_proj:  80%|████████  | 29382/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.37.down_proj:  80%|████████  | 29383/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.38.gate_proj:  80%|████████  | 29384/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.38.up_proj:  80%|████████  | 29385/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.38.down_proj:  80%|████████  | 29386/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.39.gate_proj:  80%|████████  | 29387/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.39.up_proj:  80%|████████  | 29388/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.39.down_proj:  80%|████████  | 29389/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.40.gate_proj:  80%|████████  | 29390/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.40.up_proj:  80%|████████  | 29391/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.40.down_proj:  80%|████████  | 29392/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.41.gate_proj:  80%|████████  | 29393/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.41.up_proj:  80%|████████  | 29394/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.41.down_proj:  80%|████████  | 29395/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.42.gate_proj:  80%|████████  | 29396/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.42.up_proj:  80%|████████  | 29397/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.42.down_proj:  80%|████████  | 29398/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.43.gate_proj:  80%|████████  | 29399/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.43.up_proj:  80%|████████  | 29400/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.43.down_proj:  80%|████████  | 29401/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.44.gate_proj:  80%|████████  | 29402/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.44.up_proj:  80%|████████  | 29403/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.44.down_proj:  80%|████████  | 29404/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.45.gate_proj:  80%|████████  | 29405/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.45.up_proj:  80%|████████  | 29406/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.45.down_proj:  80%|████████  | 29407/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.46.gate_proj:  80%|████████  | 29408/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.46.up_proj:  80%|████████  | 29409/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.46.down_proj:  80%|████████  | 29410/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.47.gate_proj:  80%|████████  | 29411/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.47.up_proj:  80%|████████  | 29412/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.47.down_proj:  80%|████████  | 29413/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.48.gate_proj:  80%|████████  | 29414/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.48.up_proj:  80%|████████  | 29415/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.48.down_proj:  80%|████████  | 29416/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.49.gate_proj:  80%|████████  | 29417/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.49.up_proj:  80%|████████  | 29418/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.49.down_proj:  80%|████████  | 29419/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.50.gate_proj:  80%|████████  | 29420/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.50.up_proj:  80%|████████  | 29421/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.50.down_proj:  80%|████████  | 29422/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.51.gate_proj:  80%|████████  | 29423/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.51.up_proj:  80%|████████  | 29424/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.51.down_proj:  80%|████████  | 29425/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.52.gate_proj:  80%|████████  | 29426/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.52.up_proj:  80%|████████  | 29427/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.52.down_proj:  80%|████████  | 29428/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.53.gate_proj:  80%|████████  | 29429/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.53.up_proj:  80%|████████  | 29430/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.53.down_proj:  80%|████████  | 29431/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.54.gate_proj:  80%|████████  | 29432/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.54.up_proj:  80%|████████  | 29433/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.54.down_proj:  80%|████████  | 29434/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.55.gate_proj:  80%|████████  | 29435/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.55.up_proj:  81%|████████  | 29436/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.55.down_proj:  81%|████████  | 29437/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.56.gate_proj:  81%|████████  | 29438/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.56.up_proj:  81%|████████  | 29439/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.56.down_proj:  81%|████████  | 29440/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.57.gate_proj:  81%|████████  | 29441/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.57.up_proj:  81%|████████  | 29442/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.57.down_proj:  81%|████████  | 29443/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.58.gate_proj:  81%|████████  | 29444/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.58.up_proj:  81%|████████  | 29445/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.58.down_proj:  81%|████████  | 29446/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.59.gate_proj:  81%|████████  | 29447/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.59.up_proj:  81%|████████  | 29448/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.59.down_proj:  81%|████████  | 29449/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.60.gate_proj:  81%|████████  | 29450/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.60.up_proj:  81%|████████  | 29451/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.60.down_proj:  81%|████████  | 29452/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.61.gate_proj:  81%|████████  | 29453/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.61.up_proj:  81%|████████  | 29454/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.61.down_proj:  81%|████████  | 29455/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.62.gate_proj:  81%|████████  | 29456/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.62.up_proj:  81%|████████  | 29457/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.62.down_proj:  81%|████████  | 29458/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.63.gate_proj:  81%|████████  | 29459/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.63.up_proj:  81%|████████  | 29460/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.63.down_proj:  81%|████████  | 29461/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.64.gate_proj:  81%|████████  | 29462/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.64.up_proj:  81%|████████  | 29463/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.64.down_proj:  81%|████████  | 29464/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.65.gate_proj:  81%|████████  | 29465/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.65.up_proj:  81%|████████  | 29466/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.65.down_proj:  81%|████████  | 29467/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.66.gate_proj:  81%|████████  | 29468/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.66.up_proj:  81%|████████  | 29469/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.66.down_proj:  81%|████████  | 29470/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.67.gate_proj:  81%|████████  | 29471/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.67.up_proj:  81%|████████  | 29472/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.67.down_proj:  81%|████████  | 29473/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.68.gate_proj:  81%|████████  | 29474/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.68.up_proj:  81%|████████  | 29475/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.68.down_proj:  81%|████████  | 29476/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.69.gate_proj:  81%|████████  | 29477/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.69.up_proj:  81%|████████  | 29478/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.69.down_proj:  81%|████████  | 29479/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.70.gate_proj:  81%|████████  | 29480/36566 [00:26<00:06, 1126.97it/s]
packing model.layers.75.mlp.experts.70.up_proj:  81%|████████  | 29481/36566 [00:26<00:06, 1126.97it/s]  
packing model.layers.75.mlp.experts.70.up_proj:  81%|████████  | 29482/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.70.down_proj:  81%|████████  | 29482/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.71.gate_proj:  81%|████████  | 29483/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.71.up_proj:  81%|████████  | 29484/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.71.down_proj:  81%|████████  | 29485/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.72.gate_proj:  81%|████████  | 29486/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.72.up_proj:  81%|████████  | 29487/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.72.down_proj:  81%|████████  | 29488/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.73.gate_proj:  81%|████████  | 29489/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.73.up_proj:  81%|████████  | 29490/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.73.down_proj:  81%|████████  | 29491/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.74.gate_proj:  81%|████████  | 29492/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.74.up_proj:  81%|████████  | 29493/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.74.down_proj:  81%|████████  | 29494/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.75.gate_proj:  81%|████████  | 29495/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.75.up_proj:  81%|████████  | 29496/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.75.down_proj:  81%|████████  | 29497/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.76.gate_proj:  81%|████████  | 29498/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.76.up_proj:  81%|████████  | 29499/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.76.down_proj:  81%|████████  | 29500/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.77.gate_proj:  81%|████████  | 29501/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.77.up_proj:  81%|████████  | 29502/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.77.down_proj:  81%|████████  | 29503/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.78.gate_proj:  81%|████████  | 29504/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.78.up_proj:  81%|████████  | 29505/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.78.down_proj:  81%|████████  | 29506/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.79.gate_proj:  81%|████████  | 29507/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.79.up_proj:  81%|████████  | 29508/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.79.down_proj:  81%|████████  | 29509/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.80.gate_proj:  81%|████████  | 29510/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.80.up_proj:  81%|████████  | 29511/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.80.down_proj:  81%|████████  | 29512/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.81.gate_proj:  81%|████████  | 29513/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.81.up_proj:  81%|████████  | 29514/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.81.down_proj:  81%|████████  | 29515/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.82.gate_proj:  81%|████████  | 29516/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.82.up_proj:  81%|████████  | 29517/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.82.down_proj:  81%|████████  | 29518/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.83.gate_proj:  81%|████████  | 29519/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.83.up_proj:  81%|████████  | 29520/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.83.down_proj:  81%|████████  | 29521/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.84.gate_proj:  81%|████████  | 29522/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.84.up_proj:  81%|████████  | 29523/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.84.down_proj:  81%|████████  | 29524/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.85.gate_proj:  81%|████████  | 29525/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.85.up_proj:  81%|████████  | 29526/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.85.down_proj:  81%|████████  | 29527/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.86.gate_proj:  81%|████████  | 29528/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.86.up_proj:  81%|████████  | 29529/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.86.down_proj:  81%|████████  | 29530/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.87.gate_proj:  81%|████████  | 29531/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.87.up_proj:  81%|████████  | 29532/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.87.down_proj:  81%|████████  | 29533/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.88.gate_proj:  81%|████████  | 29534/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.88.up_proj:  81%|████████  | 29535/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.88.down_proj:  81%|████████  | 29536/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.89.gate_proj:  81%|████████  | 29537/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.89.up_proj:  81%|████████  | 29538/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.89.down_proj:  81%|████████  | 29539/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.90.gate_proj:  81%|████████  | 29540/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.90.up_proj:  81%|████████  | 29541/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.90.down_proj:  81%|████████  | 29542/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.91.gate_proj:  81%|████████  | 29543/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.91.up_proj:  81%|████████  | 29544/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.91.down_proj:  81%|████████  | 29545/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.92.gate_proj:  81%|████████  | 29546/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.92.up_proj:  81%|████████  | 29547/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.92.down_proj:  81%|████████  | 29548/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.93.gate_proj:  81%|████████  | 29549/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.93.up_proj:  81%|████████  | 29550/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.93.down_proj:  81%|████████  | 29551/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.94.gate_proj:  81%|████████  | 29552/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.94.up_proj:  81%|████████  | 29553/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.94.down_proj:  81%|████████  | 29554/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.95.gate_proj:  81%|████████  | 29555/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.95.up_proj:  81%|████████  | 29556/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.95.down_proj:  81%|████████  | 29557/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.96.gate_proj:  81%|████████  | 29558/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.96.up_proj:  81%|████████  | 29559/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.96.down_proj:  81%|████████  | 29560/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.97.gate_proj:  81%|████████  | 29561/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.97.up_proj:  81%|████████  | 29562/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.97.down_proj:  81%|████████  | 29563/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.98.gate_proj:  81%|████████  | 29564/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.98.up_proj:  81%|████████  | 29565/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.98.down_proj:  81%|████████  | 29566/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.99.gate_proj:  81%|████████  | 29567/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.99.up_proj:  81%|████████  | 29568/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.99.down_proj:  81%|████████  | 29569/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.100.gate_proj:  81%|████████  | 29570/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.100.up_proj:  81%|████████  | 29571/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.100.down_proj:  81%|████████  | 29572/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.101.gate_proj:  81%|████████  | 29573/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.101.up_proj:  81%|████████  | 29574/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.101.down_proj:  81%|████████  | 29575/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.102.gate_proj:  81%|████████  | 29576/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.102.up_proj:  81%|████████  | 29577/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.102.down_proj:  81%|████████  | 29578/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.103.gate_proj:  81%|████████  | 29579/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.103.up_proj:  81%|████████  | 29580/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.103.down_proj:  81%|████████  | 29581/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.104.gate_proj:  81%|████████  | 29582/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.104.up_proj:  81%|████████  | 29583/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.104.down_proj:  81%|████████  | 29584/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.105.gate_proj:  81%|████████  | 29585/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.105.up_proj:  81%|████████  | 29586/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.105.down_proj:  81%|████████  | 29587/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.106.gate_proj:  81%|████████  | 29588/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.106.up_proj:  81%|████████  | 29589/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.106.down_proj:  81%|████████  | 29590/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.107.gate_proj:  81%|████████  | 29591/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.107.up_proj:  81%|████████  | 29592/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.107.down_proj:  81%|████████  | 29593/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.108.gate_proj:  81%|████████  | 29594/36566 [00:26<00:06, 1122.94it/s]
packing model.layers.75.mlp.experts.108.up_proj:  81%|████████  | 29595/36566 [00:26<00:06, 1122.94it/s]  
packing model.layers.75.mlp.experts.108.up_proj:  81%|████████  | 29596/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.108.down_proj:  81%|████████  | 29596/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.109.gate_proj:  81%|████████  | 29597/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.109.up_proj:  81%|████████  | 29598/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.109.down_proj:  81%|████████  | 29599/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.110.gate_proj:  81%|████████  | 29600/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.110.up_proj:  81%|████████  | 29601/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.110.down_proj:  81%|████████  | 29602/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.111.gate_proj:  81%|████████  | 29603/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.111.up_proj:  81%|████████  | 29604/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.111.down_proj:  81%|████████  | 29605/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.112.gate_proj:  81%|████████  | 29606/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.112.up_proj:  81%|████████  | 29607/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.112.down_proj:  81%|████████  | 29608/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.113.gate_proj:  81%|████████  | 29609/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.113.up_proj:  81%|████████  | 29610/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.113.down_proj:  81%|████████  | 29611/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.114.gate_proj:  81%|████████  | 29612/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.114.up_proj:  81%|████████  | 29613/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.114.down_proj:  81%|████████  | 29614/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.115.gate_proj:  81%|████████  | 29615/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.115.up_proj:  81%|████████  | 29616/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.115.down_proj:  81%|████████  | 29617/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.116.gate_proj:  81%|████████  | 29618/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.116.up_proj:  81%|████████  | 29619/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.116.down_proj:  81%|████████  | 29620/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.117.gate_proj:  81%|████████  | 29621/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.117.up_proj:  81%|████████  | 29622/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.117.down_proj:  81%|████████  | 29623/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.118.gate_proj:  81%|████████  | 29624/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.118.up_proj:  81%|████████  | 29625/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.118.down_proj:  81%|████████  | 29626/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.119.gate_proj:  81%|████████  | 29627/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.119.up_proj:  81%|████████  | 29628/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.119.down_proj:  81%|████████  | 29629/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.120.gate_proj:  81%|████████  | 29630/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.120.up_proj:  81%|████████  | 29631/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.120.down_proj:  81%|████████  | 29632/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.121.gate_proj:  81%|████████  | 29633/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.121.up_proj:  81%|████████  | 29634/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.121.down_proj:  81%|████████  | 29635/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.122.gate_proj:  81%|████████  | 29636/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.122.up_proj:  81%|████████  | 29637/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.122.down_proj:  81%|████████  | 29638/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.123.gate_proj:  81%|████████  | 29639/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.123.up_proj:  81%|████████  | 29640/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.123.down_proj:  81%|████████  | 29641/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.124.gate_proj:  81%|████████  | 29642/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.124.up_proj:  81%|████████  | 29643/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.124.down_proj:  81%|████████  | 29644/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.125.gate_proj:  81%|████████  | 29645/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.125.up_proj:  81%|████████  | 29646/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.125.down_proj:  81%|████████  | 29647/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.126.gate_proj:  81%|████████  | 29648/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.126.up_proj:  81%|████████  | 29649/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.126.down_proj:  81%|████████  | 29650/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.127.gate_proj:  81%|████████  | 29651/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.75.mlp.experts.127.up_proj:  81%|████████  | 29652/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.75.mlp.experts.127.down_proj:  81%|████████  | 29653/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.0.gate_proj:  81%|████████  | 29654/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.0.up_proj:  81%|████████  | 29655/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.0.down_proj:  81%|████████  | 29656/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.1.gate_proj:  81%|████████  | 29657/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.1.up_proj:  81%|████████  | 29658/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.1.down_proj:  81%|████████  | 29659/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.2.gate_proj:  81%|████████  | 29660/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.2.up_proj:  81%|████████  | 29661/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.2.down_proj:  81%|████████  | 29662/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.3.gate_proj:  81%|████████  | 29663/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.3.up_proj:  81%|████████  | 29664/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.3.down_proj:  81%|████████  | 29665/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.4.gate_proj:  81%|████████  | 29666/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.4.up_proj:  81%|████████  | 29667/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.4.down_proj:  81%|████████  | 29668/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.5.gate_proj:  81%|████████  | 29669/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.5.up_proj:  81%|████████  | 29670/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.5.down_proj:  81%|████████  | 29671/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.6.gate_proj:  81%|████████  | 29672/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.6.up_proj:  81%|████████  | 29673/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.6.down_proj:  81%|████████  | 29674/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.7.gate_proj:  81%|████████  | 29675/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.7.up_proj:  81%|████████  | 29676/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.7.down_proj:  81%|████████  | 29677/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.8.gate_proj:  81%|████████  | 29678/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.8.up_proj:  81%|████████  | 29679/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.8.down_proj:  81%|████████  | 29680/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.9.gate_proj:  81%|████████  | 29681/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.9.up_proj:  81%|████████  | 29682/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.9.down_proj:  81%|████████  | 29683/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.10.gate_proj:  81%|████████  | 29684/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.10.up_proj:  81%|████████  | 29685/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.10.down_proj:  81%|████████  | 29686/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.11.gate_proj:  81%|████████  | 29687/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.11.up_proj:  81%|████████  | 29688/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.11.down_proj:  81%|████████  | 29689/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.12.gate_proj:  81%|████████  | 29690/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.12.up_proj:  81%|████████  | 29691/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.12.down_proj:  81%|████████  | 29692/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.13.gate_proj:  81%|████████  | 29693/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.13.up_proj:  81%|████████  | 29694/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.13.down_proj:  81%|████████  | 29695/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.14.gate_proj:  81%|████████  | 29696/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.14.up_proj:  81%|████████  | 29697/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.14.down_proj:  81%|████████  | 29698/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.15.gate_proj:  81%|████████  | 29699/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.15.up_proj:  81%|████████  | 29700/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.15.down_proj:  81%|████████  | 29701/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.16.gate_proj:  81%|████████  | 29702/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.16.up_proj:  81%|████████  | 29703/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.16.down_proj:  81%|████████  | 29704/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.17.gate_proj:  81%|████████  | 29705/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.17.up_proj:  81%|████████  | 29706/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.17.down_proj:  81%|████████  | 29707/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.18.gate_proj:  81%|████████  | 29708/36566 [00:26<00:06, 1127.40it/s]
packing model.layers.76.mlp.experts.18.up_proj:  81%|████████  | 29709/36566 [00:26<00:06, 1127.40it/s]  
packing model.layers.76.mlp.experts.18.up_proj:  81%|████████▏ | 29710/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.18.down_proj:  81%|████████▏ | 29710/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.19.gate_proj:  81%|████████▏ | 29711/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.19.up_proj:  81%|████████▏ | 29712/36566 [00:26<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.19.down_proj:  81%|████████▏ | 29713/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.20.gate_proj:  81%|████████▏ | 29714/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.20.up_proj:  81%|████████▏ | 29715/36566 [00:26<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.20.down_proj:  81%|████████▏ | 29716/36566 [00:26<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.21.gate_proj:  81%|████████▏ | 29717/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.21.up_proj:  81%|████████▏ | 29718/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.21.down_proj:  81%|████████▏ | 29719/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.22.gate_proj:  81%|████████▏ | 29720/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.22.up_proj:  81%|████████▏ | 29721/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.22.down_proj:  81%|████████▏ | 29722/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.23.gate_proj:  81%|████████▏ | 29723/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.23.up_proj:  81%|████████▏ | 29724/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.23.down_proj:  81%|████████▏ | 29725/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.24.gate_proj:  81%|████████▏ | 29726/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.24.up_proj:  81%|████████▏ | 29727/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.24.down_proj:  81%|████████▏ | 29728/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.25.gate_proj:  81%|████████▏ | 29729/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.25.up_proj:  81%|████████▏ | 29730/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.25.down_proj:  81%|████████▏ | 29731/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.26.gate_proj:  81%|████████▏ | 29732/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.26.up_proj:  81%|████████▏ | 29733/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.26.down_proj:  81%|████████▏ | 29734/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.27.gate_proj:  81%|████████▏ | 29735/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.27.up_proj:  81%|████████▏ | 29736/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.27.down_proj:  81%|████████▏ | 29737/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.28.gate_proj:  81%|████████▏ | 29738/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.28.up_proj:  81%|████████▏ | 29739/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.28.down_proj:  81%|████████▏ | 29740/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.29.gate_proj:  81%|████████▏ | 29741/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.29.up_proj:  81%|████████▏ | 29742/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.29.down_proj:  81%|████████▏ | 29743/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.30.gate_proj:  81%|████████▏ | 29744/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.30.up_proj:  81%|████████▏ | 29745/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.30.down_proj:  81%|████████▏ | 29746/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.31.gate_proj:  81%|████████▏ | 29747/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.31.up_proj:  81%|████████▏ | 29748/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.31.down_proj:  81%|████████▏ | 29749/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.32.gate_proj:  81%|████████▏ | 29750/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.32.up_proj:  81%|████████▏ | 29751/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.32.down_proj:  81%|████████▏ | 29752/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.33.gate_proj:  81%|████████▏ | 29753/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.33.up_proj:  81%|████████▏ | 29754/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.33.down_proj:  81%|████████▏ | 29755/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.34.gate_proj:  81%|████████▏ | 29756/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.34.up_proj:  81%|████████▏ | 29757/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.34.down_proj:  81%|████████▏ | 29758/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.35.gate_proj:  81%|████████▏ | 29759/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.35.up_proj:  81%|████████▏ | 29760/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.35.down_proj:  81%|████████▏ | 29761/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.36.gate_proj:  81%|████████▏ | 29762/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.36.up_proj:  81%|████████▏ | 29763/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.36.down_proj:  81%|████████▏ | 29764/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.37.gate_proj:  81%|████████▏ | 29765/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.37.up_proj:  81%|████████▏ | 29766/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.37.down_proj:  81%|████████▏ | 29767/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.38.gate_proj:  81%|████████▏ | 29768/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.38.up_proj:  81%|████████▏ | 29769/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.38.down_proj:  81%|████████▏ | 29770/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.39.gate_proj:  81%|████████▏ | 29771/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.39.up_proj:  81%|████████▏ | 29772/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.39.down_proj:  81%|████████▏ | 29773/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.40.gate_proj:  81%|████████▏ | 29774/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.40.up_proj:  81%|████████▏ | 29775/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.40.down_proj:  81%|████████▏ | 29776/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.41.gate_proj:  81%|████████▏ | 29777/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.41.up_proj:  81%|████████▏ | 29778/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.41.down_proj:  81%|████████▏ | 29779/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.42.gate_proj:  81%|████████▏ | 29780/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.42.up_proj:  81%|████████▏ | 29781/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.42.down_proj:  81%|████████▏ | 29782/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.43.gate_proj:  81%|████████▏ | 29783/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.43.up_proj:  81%|████████▏ | 29784/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.43.down_proj:  81%|████████▏ | 29785/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.44.gate_proj:  81%|████████▏ | 29786/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.44.up_proj:  81%|████████▏ | 29787/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.44.down_proj:  81%|████████▏ | 29788/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.45.gate_proj:  81%|████████▏ | 29789/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.45.up_proj:  81%|████████▏ | 29790/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.45.down_proj:  81%|████████▏ | 29791/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.46.gate_proj:  81%|████████▏ | 29792/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.46.up_proj:  81%|████████▏ | 29793/36566 [00:27<00:06, 1128.61it/s]  
packing model.layers.76.mlp.experts.46.down_proj:  81%|████████▏ | 29794/36566 [00:27<00:06, 1128.61it/s]
packing model.layers.76.mlp.experts.47.gate_proj:  81%|████████▏ | 29795/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.47.up_proj:  81%|████████▏ | 29796/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.47.down_proj:  81%|████████▏ | 29797/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.48.gate_proj:  81%|████████▏ | 29798/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.48.up_proj:  81%|████████▏ | 29799/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.48.down_proj:  81%|████████▏ | 29800/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.49.gate_proj:  81%|████████▏ | 29801/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.49.up_proj:  82%|████████▏ | 29802/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.49.down_proj:  82%|████████▏ | 29803/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.50.gate_proj:  82%|████████▏ | 29804/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.50.up_proj:  82%|████████▏ | 29805/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.50.down_proj:  82%|████████▏ | 29806/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.51.gate_proj:  82%|████████▏ | 29807/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.51.up_proj:  82%|████████▏ | 29808/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.51.down_proj:  82%|████████▏ | 29809/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.52.gate_proj:  82%|████████▏ | 29810/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.52.up_proj:  82%|████████▏ | 29811/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.52.down_proj:  82%|████████▏ | 29812/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.53.gate_proj:  82%|████████▏ | 29813/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.53.up_proj:  82%|████████▏ | 29814/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.53.down_proj:  82%|████████▏ | 29815/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.54.gate_proj:  82%|████████▏ | 29816/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.54.up_proj:  82%|████████▏ | 29817/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.54.down_proj:  82%|████████▏ | 29818/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.55.gate_proj:  82%|████████▏ | 29819/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.55.up_proj:  82%|████████▏ | 29820/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.76.mlp.experts.55.down_proj:  82%|████████▏ | 29821/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.56.gate_proj:  82%|████████▏ | 29822/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.76.mlp.experts.56.gate_proj:  82%|████████▏ | 29823/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.56.up_proj:  82%|████████▏ | 29823/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.56.down_proj:  82%|████████▏ | 29824/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.57.gate_proj:  82%|████████▏ | 29825/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.57.up_proj:  82%|████████▏ | 29826/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.57.down_proj:  82%|████████▏ | 29827/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.58.gate_proj:  82%|████████▏ | 29828/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.58.up_proj:  82%|████████▏ | 29829/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.58.down_proj:  82%|████████▏ | 29830/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.59.gate_proj:  82%|████████▏ | 29831/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.59.up_proj:  82%|████████▏ | 29832/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.59.down_proj:  82%|████████▏ | 29833/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.60.gate_proj:  82%|████████▏ | 29834/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.60.up_proj:  82%|████████▏ | 29835/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.60.down_proj:  82%|████████▏ | 29836/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.61.gate_proj:  82%|████████▏ | 29837/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.61.up_proj:  82%|████████▏ | 29838/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.61.down_proj:  82%|████████▏ | 29839/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.62.gate_proj:  82%|████████▏ | 29840/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.62.up_proj:  82%|████████▏ | 29841/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.62.down_proj:  82%|████████▏ | 29842/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.63.gate_proj:  82%|████████▏ | 29843/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.63.up_proj:  82%|████████▏ | 29844/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.63.down_proj:  82%|████████▏ | 29845/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.64.gate_proj:  82%|████████▏ | 29846/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.64.up_proj:  82%|████████▏ | 29847/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.64.down_proj:  82%|████████▏ | 29848/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.65.gate_proj:  82%|████████▏ | 29849/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.65.up_proj:  82%|████████▏ | 29850/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.65.down_proj:  82%|████████▏ | 29851/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.66.gate_proj:  82%|████████▏ | 29852/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.66.up_proj:  82%|████████▏ | 29853/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.66.down_proj:  82%|████████▏ | 29854/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.67.gate_proj:  82%|████████▏ | 29855/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.67.up_proj:  82%|████████▏ | 29856/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.67.down_proj:  82%|████████▏ | 29857/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.68.gate_proj:  82%|████████▏ | 29858/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.68.up_proj:  82%|████████▏ | 29859/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.68.down_proj:  82%|████████▏ | 29860/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.69.gate_proj:  82%|████████▏ | 29861/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.69.up_proj:  82%|████████▏ | 29862/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.69.down_proj:  82%|████████▏ | 29863/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.70.gate_proj:  82%|████████▏ | 29864/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.70.up_proj:  82%|████████▏ | 29865/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.70.down_proj:  82%|████████▏ | 29866/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.71.gate_proj:  82%|████████▏ | 29867/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.71.up_proj:  82%|████████▏ | 29868/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.71.down_proj:  82%|████████▏ | 29869/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.72.gate_proj:  82%|████████▏ | 29870/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.72.up_proj:  82%|████████▏ | 29871/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.72.down_proj:  82%|████████▏ | 29872/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.73.gate_proj:  82%|████████▏ | 29873/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.73.up_proj:  82%|████████▏ | 29874/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.73.down_proj:  82%|████████▏ | 29875/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.74.gate_proj:  82%|████████▏ | 29876/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.74.up_proj:  82%|████████▏ | 29877/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.74.down_proj:  82%|████████▏ | 29878/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.75.gate_proj:  82%|████████▏ | 29879/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.75.up_proj:  82%|████████▏ | 29880/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.75.down_proj:  82%|████████▏ | 29881/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.76.gate_proj:  82%|████████▏ | 29882/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.76.up_proj:  82%|████████▏ | 29883/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.76.down_proj:  82%|████████▏ | 29884/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.77.gate_proj:  82%|████████▏ | 29885/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.77.up_proj:  82%|████████▏ | 29886/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.77.down_proj:  82%|████████▏ | 29887/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.78.gate_proj:  82%|████████▏ | 29888/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.78.up_proj:  82%|████████▏ | 29889/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.78.down_proj:  82%|████████▏ | 29890/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.79.gate_proj:  82%|████████▏ | 29891/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.79.up_proj:  82%|████████▏ | 29892/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.79.down_proj:  82%|████████▏ | 29893/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.80.gate_proj:  82%|████████▏ | 29894/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.80.up_proj:  82%|████████▏ | 29895/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.80.down_proj:  82%|████████▏ | 29896/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.81.gate_proj:  82%|████████▏ | 29897/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.81.up_proj:  82%|████████▏ | 29898/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.81.down_proj:  82%|████████▏ | 29899/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.82.gate_proj:  82%|████████▏ | 29900/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.82.up_proj:  82%|████████▏ | 29901/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.82.down_proj:  82%|████████▏ | 29902/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.83.gate_proj:  82%|████████▏ | 29903/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.83.up_proj:  82%|████████▏ | 29904/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.83.down_proj:  82%|████████▏ | 29905/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.84.gate_proj:  82%|████████▏ | 29906/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.84.up_proj:  82%|████████▏ | 29907/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.84.down_proj:  82%|████████▏ | 29908/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.85.gate_proj:  82%|████████▏ | 29909/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.85.up_proj:  82%|████████▏ | 29910/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.85.down_proj:  82%|████████▏ | 29911/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.86.gate_proj:  82%|████████▏ | 29912/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.86.up_proj:  82%|████████▏ | 29913/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.86.down_proj:  82%|████████▏ | 29914/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.87.gate_proj:  82%|████████▏ | 29915/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.87.up_proj:  82%|████████▏ | 29916/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.87.down_proj:  82%|████████▏ | 29917/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.88.gate_proj:  82%|████████▏ | 29918/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.88.up_proj:  82%|████████▏ | 29919/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.88.down_proj:  82%|████████▏ | 29920/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.89.gate_proj:  82%|████████▏ | 29921/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.89.up_proj:  82%|████████▏ | 29922/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.89.down_proj:  82%|████████▏ | 29923/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.90.gate_proj:  82%|████████▏ | 29924/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.90.up_proj:  82%|████████▏ | 29925/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.90.down_proj:  82%|████████▏ | 29926/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.91.gate_proj:  82%|████████▏ | 29927/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.91.up_proj:  82%|████████▏ | 29928/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.91.down_proj:  82%|████████▏ | 29929/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.92.gate_proj:  82%|████████▏ | 29930/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.92.up_proj:  82%|████████▏ | 29931/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.92.down_proj:  82%|████████▏ | 29932/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.93.gate_proj:  82%|████████▏ | 29933/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.93.up_proj:  82%|████████▏ | 29934/36566 [00:27<00:05, 1128.80it/s]  
packing model.layers.76.mlp.experts.93.down_proj:  82%|████████▏ | 29935/36566 [00:27<00:05, 1128.80it/s]
packing model.layers.76.mlp.experts.93.down_proj:  82%|████████▏ | 29936/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.94.gate_proj:  82%|████████▏ | 29936/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.94.up_proj:  82%|████████▏ | 29937/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.94.down_proj:  82%|████████▏ | 29938/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.95.gate_proj:  82%|████████▏ | 29939/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.95.up_proj:  82%|████████▏ | 29940/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.95.down_proj:  82%|████████▏ | 29941/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.96.gate_proj:  82%|████████▏ | 29942/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.96.up_proj:  82%|████████▏ | 29943/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.96.down_proj:  82%|████████▏ | 29944/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.97.gate_proj:  82%|████████▏ | 29945/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.97.up_proj:  82%|████████▏ | 29946/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.97.down_proj:  82%|████████▏ | 29947/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.98.gate_proj:  82%|████████▏ | 29948/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.98.up_proj:  82%|████████▏ | 29949/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.98.down_proj:  82%|████████▏ | 29950/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.99.gate_proj:  82%|████████▏ | 29951/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.99.up_proj:  82%|████████▏ | 29952/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.99.down_proj:  82%|████████▏ | 29953/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.100.gate_proj:  82%|████████▏ | 29954/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.100.up_proj:  82%|████████▏ | 29955/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.100.down_proj:  82%|████████▏ | 29956/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.101.gate_proj:  82%|████████▏ | 29957/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.101.up_proj:  82%|████████▏ | 29958/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.101.down_proj:  82%|████████▏ | 29959/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.102.gate_proj:  82%|████████▏ | 29960/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.102.up_proj:  82%|████████▏ | 29961/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.102.down_proj:  82%|████████▏ | 29962/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.103.gate_proj:  82%|████████▏ | 29963/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.103.up_proj:  82%|████████▏ | 29964/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.103.down_proj:  82%|████████▏ | 29965/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.104.gate_proj:  82%|████████▏ | 29966/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.104.up_proj:  82%|████████▏ | 29967/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.104.down_proj:  82%|████████▏ | 29968/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.105.gate_proj:  82%|████████▏ | 29969/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.105.up_proj:  82%|████████▏ | 29970/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.105.down_proj:  82%|████████▏ | 29971/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.106.gate_proj:  82%|████████▏ | 29972/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.106.up_proj:  82%|████████▏ | 29973/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.106.down_proj:  82%|████████▏ | 29974/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.107.gate_proj:  82%|████████▏ | 29975/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.107.up_proj:  82%|████████▏ | 29976/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.107.down_proj:  82%|████████▏ | 29977/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.108.gate_proj:  82%|████████▏ | 29978/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.108.up_proj:  82%|████████▏ | 29979/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.108.down_proj:  82%|████████▏ | 29980/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.109.gate_proj:  82%|████████▏ | 29981/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.109.up_proj:  82%|████████▏ | 29982/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.109.down_proj:  82%|████████▏ | 29983/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.110.gate_proj:  82%|████████▏ | 29984/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.110.up_proj:  82%|████████▏ | 29985/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.110.down_proj:  82%|████████▏ | 29986/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.111.gate_proj:  82%|████████▏ | 29987/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.111.up_proj:  82%|████████▏ | 29988/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.111.down_proj:  82%|████████▏ | 29989/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.112.gate_proj:  82%|████████▏ | 29990/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.112.up_proj:  82%|████████▏ | 29991/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.112.down_proj:  82%|████████▏ | 29992/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.113.gate_proj:  82%|████████▏ | 29993/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.113.up_proj:  82%|████████▏ | 29994/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.113.down_proj:  82%|████████▏ | 29995/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.114.gate_proj:  82%|████████▏ | 29996/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.114.up_proj:  82%|████████▏ | 29997/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.114.down_proj:  82%|████████▏ | 29998/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.115.gate_proj:  82%|████████▏ | 29999/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.115.up_proj:  82%|████████▏ | 30000/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.115.down_proj:  82%|████████▏ | 30001/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.116.gate_proj:  82%|████████▏ | 30002/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.116.up_proj:  82%|████████▏ | 30003/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.116.down_proj:  82%|████████▏ | 30004/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.117.gate_proj:  82%|████████▏ | 30005/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.117.up_proj:  82%|████████▏ | 30006/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.117.down_proj:  82%|████████▏ | 30007/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.118.gate_proj:  82%|████████▏ | 30008/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.118.up_proj:  82%|████████▏ | 30009/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.118.down_proj:  82%|████████▏ | 30010/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.119.gate_proj:  82%|████████▏ | 30011/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.119.up_proj:  82%|████████▏ | 30012/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.119.down_proj:  82%|████████▏ | 30013/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.120.gate_proj:  82%|████████▏ | 30014/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.120.up_proj:  82%|████████▏ | 30015/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.120.down_proj:  82%|████████▏ | 30016/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.121.gate_proj:  82%|████████▏ | 30017/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.121.up_proj:  82%|████████▏ | 30018/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.121.down_proj:  82%|████████▏ | 30019/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.122.gate_proj:  82%|████████▏ | 30020/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.122.up_proj:  82%|████████▏ | 30021/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.122.down_proj:  82%|████████▏ | 30022/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.123.gate_proj:  82%|████████▏ | 30023/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.123.up_proj:  82%|████████▏ | 30024/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.123.down_proj:  82%|████████▏ | 30025/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.124.gate_proj:  82%|████████▏ | 30026/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.124.up_proj:  82%|████████▏ | 30027/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.124.down_proj:  82%|████████▏ | 30028/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.125.gate_proj:  82%|████████▏ | 30029/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.125.up_proj:  82%|████████▏ | 30030/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.125.down_proj:  82%|████████▏ | 30031/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.126.gate_proj:  82%|████████▏ | 30032/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.126.up_proj:  82%|████████▏ | 30033/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.126.down_proj:  82%|████████▏ | 30034/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.127.gate_proj:  82%|████████▏ | 30035/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.76.mlp.experts.127.up_proj:  82%|████████▏ | 30036/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.76.mlp.experts.127.down_proj:  82%|████████▏ | 30037/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.0.gate_proj:  82%|████████▏ | 30038/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.77.mlp.experts.0.up_proj:  82%|████████▏ | 30039/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.77.mlp.experts.0.down_proj:  82%|████████▏ | 30040/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.1.gate_proj:  82%|████████▏ | 30041/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.1.up_proj:  82%|████████▏ | 30042/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.77.mlp.experts.1.down_proj:  82%|████████▏ | 30043/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.2.gate_proj:  82%|████████▏ | 30044/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.2.up_proj:  82%|████████▏ | 30045/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.77.mlp.experts.2.down_proj:  82%|████████▏ | 30046/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.3.gate_proj:  82%|████████▏ | 30047/36566 [00:27<00:05, 1128.88it/s]
packing model.layers.77.mlp.experts.3.up_proj:  82%|████████▏ | 30048/36566 [00:27<00:05, 1128.88it/s]  
packing model.layers.77.mlp.experts.3.up_proj:  82%|████████▏ | 30049/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.3.down_proj:  82%|████████▏ | 30049/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.4.gate_proj:  82%|████████▏ | 30050/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.4.up_proj:  82%|████████▏ | 30051/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.4.down_proj:  82%|████████▏ | 30052/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.5.gate_proj:  82%|████████▏ | 30053/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.5.up_proj:  82%|████████▏ | 30054/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.5.down_proj:  82%|████████▏ | 30055/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.6.gate_proj:  82%|████████▏ | 30056/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.6.up_proj:  82%|████████▏ | 30057/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.6.down_proj:  82%|████████▏ | 30058/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.7.gate_proj:  82%|████████▏ | 30059/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.7.up_proj:  82%|████████▏ | 30060/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.7.down_proj:  82%|████████▏ | 30061/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.8.gate_proj:  82%|████████▏ | 30062/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.8.up_proj:  82%|████████▏ | 30063/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.8.down_proj:  82%|████████▏ | 30064/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.9.gate_proj:  82%|████████▏ | 30065/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.9.up_proj:  82%|████████▏ | 30066/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.9.down_proj:  82%|████████▏ | 30067/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.10.gate_proj:  82%|████████▏ | 30068/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.10.up_proj:  82%|████████▏ | 30069/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.10.down_proj:  82%|████████▏ | 30070/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.11.gate_proj:  82%|████████▏ | 30071/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.11.up_proj:  82%|████████▏ | 30072/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.11.down_proj:  82%|████████▏ | 30073/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.12.gate_proj:  82%|████████▏ | 30074/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.12.up_proj:  82%|████████▏ | 30075/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.12.down_proj:  82%|████████▏ | 30076/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.13.gate_proj:  82%|████████▏ | 30077/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.13.up_proj:  82%|████████▏ | 30078/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.13.down_proj:  82%|████████▏ | 30079/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.14.gate_proj:  82%|████████▏ | 30080/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.14.up_proj:  82%|████████▏ | 30081/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.14.down_proj:  82%|████████▏ | 30082/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.15.gate_proj:  82%|████████▏ | 30083/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.15.up_proj:  82%|████████▏ | 30084/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.15.down_proj:  82%|████████▏ | 30085/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.16.gate_proj:  82%|████████▏ | 30086/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.16.up_proj:  82%|████████▏ | 30087/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.16.down_proj:  82%|████████▏ | 30088/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.17.gate_proj:  82%|████████▏ | 30089/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.17.up_proj:  82%|████████▏ | 30090/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.17.down_proj:  82%|████████▏ | 30091/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.18.gate_proj:  82%|████████▏ | 30092/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.18.up_proj:  82%|████████▏ | 30093/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.18.down_proj:  82%|████████▏ | 30094/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.19.gate_proj:  82%|████████▏ | 30095/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.19.up_proj:  82%|████████▏ | 30096/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.19.down_proj:  82%|████████▏ | 30097/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.20.gate_proj:  82%|████████▏ | 30098/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.20.up_proj:  82%|████████▏ | 30099/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.20.down_proj:  82%|████████▏ | 30100/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.21.gate_proj:  82%|████████▏ | 30101/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.21.up_proj:  82%|████████▏ | 30102/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.21.down_proj:  82%|████████▏ | 30103/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.22.gate_proj:  82%|████████▏ | 30104/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.22.up_proj:  82%|████████▏ | 30105/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.22.down_proj:  82%|████████▏ | 30106/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.23.gate_proj:  82%|████████▏ | 30107/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.23.up_proj:  82%|████████▏ | 30108/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.23.down_proj:  82%|████████▏ | 30109/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.24.gate_proj:  82%|████████▏ | 30110/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.24.up_proj:  82%|████████▏ | 30111/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.24.down_proj:  82%|████████▏ | 30112/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.25.gate_proj:  82%|████████▏ | 30113/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.25.up_proj:  82%|████████▏ | 30114/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.25.down_proj:  82%|████████▏ | 30115/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.26.gate_proj:  82%|████████▏ | 30116/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.26.up_proj:  82%|████████▏ | 30117/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.26.down_proj:  82%|████████▏ | 30118/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.27.gate_proj:  82%|████████▏ | 30119/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.27.up_proj:  82%|████████▏ | 30120/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.27.down_proj:  82%|████████▏ | 30121/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.28.gate_proj:  82%|████████▏ | 30122/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.28.up_proj:  82%|████████▏ | 30123/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.28.down_proj:  82%|████████▏ | 30124/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.29.gate_proj:  82%|████████▏ | 30125/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.29.up_proj:  82%|████████▏ | 30126/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.29.down_proj:  82%|████████▏ | 30127/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.30.gate_proj:  82%|████████▏ | 30128/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.30.up_proj:  82%|████████▏ | 30129/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.30.down_proj:  82%|████████▏ | 30130/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.31.gate_proj:  82%|████████▏ | 30131/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.31.up_proj:  82%|████████▏ | 30132/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.31.down_proj:  82%|████████▏ | 30133/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.32.gate_proj:  82%|████████▏ | 30134/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.32.up_proj:  82%|████████▏ | 30135/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.32.down_proj:  82%|████████▏ | 30136/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.33.gate_proj:  82%|████████▏ | 30137/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.33.up_proj:  82%|████████▏ | 30138/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.33.down_proj:  82%|████████▏ | 30139/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.34.gate_proj:  82%|████████▏ | 30140/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.34.up_proj:  82%|████████▏ | 30141/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.34.down_proj:  82%|████████▏ | 30142/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.35.gate_proj:  82%|████████▏ | 30143/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.35.up_proj:  82%|████████▏ | 30144/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.35.down_proj:  82%|████████▏ | 30145/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.36.gate_proj:  82%|████████▏ | 30146/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.36.up_proj:  82%|████████▏ | 30147/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.36.down_proj:  82%|████████▏ | 30148/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.37.gate_proj:  82%|████████▏ | 30149/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.37.up_proj:  82%|████████▏ | 30150/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.37.down_proj:  82%|████████▏ | 30151/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.38.gate_proj:  82%|████████▏ | 30152/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.38.up_proj:  82%|████████▏ | 30153/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.38.down_proj:  82%|████████▏ | 30154/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.39.gate_proj:  82%|████████▏ | 30155/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.39.up_proj:  82%|████████▏ | 30156/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.39.down_proj:  82%|████████▏ | 30157/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.40.gate_proj:  82%|████████▏ | 30158/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.40.up_proj:  82%|████████▏ | 30159/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.40.down_proj:  82%|████████▏ | 30160/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.41.gate_proj:  82%|████████▏ | 30161/36566 [00:27<00:05, 1128.61it/s]
packing model.layers.77.mlp.experts.41.up_proj:  82%|████████▏ | 30162/36566 [00:27<00:05, 1128.61it/s]  
packing model.layers.77.mlp.experts.41.up_proj:  82%|████████▏ | 30163/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.41.down_proj:  82%|████████▏ | 30163/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.42.gate_proj:  82%|████████▏ | 30164/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.42.up_proj:  82%|████████▏ | 30165/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.42.down_proj:  82%|████████▏ | 30166/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.43.gate_proj:  83%|████████▎ | 30167/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.43.up_proj:  83%|████████▎ | 30168/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.43.down_proj:  83%|████████▎ | 30169/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.44.gate_proj:  83%|████████▎ | 30170/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.44.up_proj:  83%|████████▎ | 30171/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.44.down_proj:  83%|████████▎ | 30172/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.45.gate_proj:  83%|████████▎ | 30173/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.45.up_proj:  83%|████████▎ | 30174/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.45.down_proj:  83%|████████▎ | 30175/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.46.gate_proj:  83%|████████▎ | 30176/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.46.up_proj:  83%|████████▎ | 30177/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.46.down_proj:  83%|████████▎ | 30178/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.47.gate_proj:  83%|████████▎ | 30179/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.47.up_proj:  83%|████████▎ | 30180/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.47.down_proj:  83%|████████▎ | 30181/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.48.gate_proj:  83%|████████▎ | 30182/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.48.up_proj:  83%|████████▎ | 30183/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.48.down_proj:  83%|████████▎ | 30184/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.49.gate_proj:  83%|████████▎ | 30185/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.49.up_proj:  83%|████████▎ | 30186/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.49.down_proj:  83%|████████▎ | 30187/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.50.gate_proj:  83%|████████▎ | 30188/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.50.up_proj:  83%|████████▎ | 30189/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.50.down_proj:  83%|████████▎ | 30190/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.51.gate_proj:  83%|████████▎ | 30191/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.51.up_proj:  83%|████████▎ | 30192/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.51.down_proj:  83%|████████▎ | 30193/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.52.gate_proj:  83%|████████▎ | 30194/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.52.up_proj:  83%|████████▎ | 30195/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.52.down_proj:  83%|████████▎ | 30196/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.53.gate_proj:  83%|████████▎ | 30197/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.53.up_proj:  83%|████████▎ | 30198/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.53.down_proj:  83%|████████▎ | 30199/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.54.gate_proj:  83%|████████▎ | 30200/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.54.up_proj:  83%|████████▎ | 30201/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.54.down_proj:  83%|████████▎ | 30202/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.55.gate_proj:  83%|████████▎ | 30203/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.55.up_proj:  83%|████████▎ | 30204/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.55.down_proj:  83%|████████▎ | 30205/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.56.gate_proj:  83%|████████▎ | 30206/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.56.up_proj:  83%|████████▎ | 30207/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.56.down_proj:  83%|████████▎ | 30208/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.57.gate_proj:  83%|████████▎ | 30209/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.57.up_proj:  83%|████████▎ | 30210/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.57.down_proj:  83%|████████▎ | 30211/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.58.gate_proj:  83%|████████▎ | 30212/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.58.up_proj:  83%|████████▎ | 30213/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.58.down_proj:  83%|████████▎ | 30214/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.59.gate_proj:  83%|████████▎ | 30215/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.59.up_proj:  83%|████████▎ | 30216/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.59.down_proj:  83%|████████▎ | 30217/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.60.gate_proj:  83%|████████▎ | 30218/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.60.up_proj:  83%|████████▎ | 30219/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.60.down_proj:  83%|████████▎ | 30220/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.61.gate_proj:  83%|████████▎ | 30221/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.61.up_proj:  83%|████████▎ | 30222/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.61.down_proj:  83%|████████▎ | 30223/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.62.gate_proj:  83%|████████▎ | 30224/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.62.up_proj:  83%|████████▎ | 30225/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.62.down_proj:  83%|████████▎ | 30226/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.63.gate_proj:  83%|████████▎ | 30227/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.63.up_proj:  83%|████████▎ | 30228/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.63.down_proj:  83%|████████▎ | 30229/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.64.gate_proj:  83%|████████▎ | 30230/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.64.up_proj:  83%|████████▎ | 30231/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.64.down_proj:  83%|████████▎ | 30232/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.65.gate_proj:  83%|████████▎ | 30233/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.65.up_proj:  83%|████████▎ | 30234/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.65.down_proj:  83%|████████▎ | 30235/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.66.gate_proj:  83%|████████▎ | 30236/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.66.up_proj:  83%|████████▎ | 30237/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.66.down_proj:  83%|████████▎ | 30238/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.67.gate_proj:  83%|████████▎ | 30239/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.67.up_proj:  83%|████████▎ | 30240/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.67.down_proj:  83%|████████▎ | 30241/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.68.gate_proj:  83%|████████▎ | 30242/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.68.up_proj:  83%|████████▎ | 30243/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.68.down_proj:  83%|████████▎ | 30244/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.69.gate_proj:  83%|████████▎ | 30245/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.69.up_proj:  83%|████████▎ | 30246/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.69.down_proj:  83%|████████▎ | 30247/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.70.gate_proj:  83%|████████▎ | 30248/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.70.up_proj:  83%|████████▎ | 30249/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.70.down_proj:  83%|████████▎ | 30250/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.71.gate_proj:  83%|████████▎ | 30251/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.71.up_proj:  83%|████████▎ | 30252/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.71.down_proj:  83%|████████▎ | 30253/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.72.gate_proj:  83%|████████▎ | 30254/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.72.up_proj:  83%|████████▎ | 30255/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.72.down_proj:  83%|████████▎ | 30256/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.73.gate_proj:  83%|████████▎ | 30257/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.73.up_proj:  83%|████████▎ | 30258/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.73.down_proj:  83%|████████▎ | 30259/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.74.gate_proj:  83%|████████▎ | 30260/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.74.up_proj:  83%|████████▎ | 30261/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.74.down_proj:  83%|████████▎ | 30262/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.75.gate_proj:  83%|████████▎ | 30263/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.75.up_proj:  83%|████████▎ | 30264/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.75.down_proj:  83%|████████▎ | 30265/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.76.gate_proj:  83%|████████▎ | 30266/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.76.up_proj:  83%|████████▎ | 30267/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.76.down_proj:  83%|████████▎ | 30268/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.77.gate_proj:  83%|████████▎ | 30269/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.77.up_proj:  83%|████████▎ | 30270/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.77.down_proj:  83%|████████▎ | 30271/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.78.gate_proj:  83%|████████▎ | 30272/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.78.up_proj:  83%|████████▎ | 30273/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.78.down_proj:  83%|████████▎ | 30274/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.79.gate_proj:  83%|████████▎ | 30275/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.79.up_proj:  83%|████████▎ | 30276/36566 [00:27<00:05, 1129.57it/s]  
packing model.layers.77.mlp.experts.79.down_proj:  83%|████████▎ | 30277/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.80.gate_proj:  83%|████████▎ | 30278/36566 [00:27<00:05, 1129.57it/s]
packing model.layers.77.mlp.experts.80.gate_proj:  83%|████████▎ | 30279/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.80.up_proj:  83%|████████▎ | 30279/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.80.down_proj:  83%|████████▎ | 30280/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.81.gate_proj:  83%|████████▎ | 30281/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.81.up_proj:  83%|████████▎ | 30282/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.81.down_proj:  83%|████████▎ | 30283/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.82.gate_proj:  83%|████████▎ | 30284/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.82.up_proj:  83%|████████▎ | 30285/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.82.down_proj:  83%|████████▎ | 30286/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.83.gate_proj:  83%|████████▎ | 30287/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.83.up_proj:  83%|████████▎ | 30288/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.83.down_proj:  83%|████████▎ | 30289/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.84.gate_proj:  83%|████████▎ | 30290/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.84.up_proj:  83%|████████▎ | 30291/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.84.down_proj:  83%|████████▎ | 30292/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.85.gate_proj:  83%|████████▎ | 30293/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.85.up_proj:  83%|████████▎ | 30294/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.85.down_proj:  83%|████████▎ | 30295/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.86.gate_proj:  83%|████████▎ | 30296/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.86.up_proj:  83%|████████▎ | 30297/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.86.down_proj:  83%|████████▎ | 30298/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.87.gate_proj:  83%|████████▎ | 30299/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.87.up_proj:  83%|████████▎ | 30300/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.87.down_proj:  83%|████████▎ | 30301/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.88.gate_proj:  83%|████████▎ | 30302/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.88.up_proj:  83%|████████▎ | 30303/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.88.down_proj:  83%|████████▎ | 30304/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.89.gate_proj:  83%|████████▎ | 30305/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.89.up_proj:  83%|████████▎ | 30306/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.89.down_proj:  83%|████████▎ | 30307/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.90.gate_proj:  83%|████████▎ | 30308/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.90.up_proj:  83%|████████▎ | 30309/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.90.down_proj:  83%|████████▎ | 30310/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.91.gate_proj:  83%|████████▎ | 30311/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.91.up_proj:  83%|████████▎ | 30312/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.91.down_proj:  83%|████████▎ | 30313/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.92.gate_proj:  83%|████████▎ | 30314/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.92.up_proj:  83%|████████▎ | 30315/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.92.down_proj:  83%|████████▎ | 30316/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.93.gate_proj:  83%|████████▎ | 30317/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.93.up_proj:  83%|████████▎ | 30318/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.93.down_proj:  83%|████████▎ | 30319/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.94.gate_proj:  83%|████████▎ | 30320/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.94.up_proj:  83%|████████▎ | 30321/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.94.down_proj:  83%|████████▎ | 30322/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.95.gate_proj:  83%|████████▎ | 30323/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.95.up_proj:  83%|████████▎ | 30324/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.95.down_proj:  83%|████████▎ | 30325/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.96.gate_proj:  83%|████████▎ | 30326/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.96.up_proj:  83%|████████▎ | 30327/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.96.down_proj:  83%|████████▎ | 30328/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.97.gate_proj:  83%|████████▎ | 30329/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.97.up_proj:  83%|████████▎ | 30330/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.97.down_proj:  83%|████████▎ | 30331/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.98.gate_proj:  83%|████████▎ | 30332/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.98.up_proj:  83%|████████▎ | 30333/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.98.down_proj:  83%|████████▎ | 30334/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.99.gate_proj:  83%|████████▎ | 30335/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.99.up_proj:  83%|████████▎ | 30336/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.99.down_proj:  83%|████████▎ | 30337/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.100.gate_proj:  83%|████████▎ | 30338/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.100.up_proj:  83%|████████▎ | 30339/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.100.down_proj:  83%|████████▎ | 30340/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.101.gate_proj:  83%|████████▎ | 30341/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.101.up_proj:  83%|████████▎ | 30342/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.101.down_proj:  83%|████████▎ | 30343/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.102.gate_proj:  83%|████████▎ | 30344/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.102.up_proj:  83%|████████▎ | 30345/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.102.down_proj:  83%|████████▎ | 30346/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.103.gate_proj:  83%|████████▎ | 30347/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.103.up_proj:  83%|████████▎ | 30348/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.103.down_proj:  83%|████████▎ | 30349/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.104.gate_proj:  83%|████████▎ | 30350/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.104.up_proj:  83%|████████▎ | 30351/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.104.down_proj:  83%|████████▎ | 30352/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.105.gate_proj:  83%|████████▎ | 30353/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.105.up_proj:  83%|████████▎ | 30354/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.105.down_proj:  83%|████████▎ | 30355/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.106.gate_proj:  83%|████████▎ | 30356/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.106.up_proj:  83%|████████▎ | 30357/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.106.down_proj:  83%|████████▎ | 30358/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.107.gate_proj:  83%|████████▎ | 30359/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.107.up_proj:  83%|████████▎ | 30360/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.107.down_proj:  83%|████████▎ | 30361/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.108.gate_proj:  83%|████████▎ | 30362/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.108.up_proj:  83%|████████▎ | 30363/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.108.down_proj:  83%|████████▎ | 30364/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.109.gate_proj:  83%|████████▎ | 30365/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.109.up_proj:  83%|████████▎ | 30366/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.109.down_proj:  83%|████████▎ | 30367/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.110.gate_proj:  83%|████████▎ | 30368/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.110.up_proj:  83%|████████▎ | 30369/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.110.down_proj:  83%|████████▎ | 30370/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.111.gate_proj:  83%|████████▎ | 30371/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.111.up_proj:  83%|████████▎ | 30372/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.111.down_proj:  83%|████████▎ | 30373/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.112.gate_proj:  83%|████████▎ | 30374/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.112.up_proj:  83%|████████▎ | 30375/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.112.down_proj:  83%|████████▎ | 30376/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.113.gate_proj:  83%|████████▎ | 30377/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.113.up_proj:  83%|████████▎ | 30378/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.113.down_proj:  83%|████████▎ | 30379/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.114.gate_proj:  83%|████████▎ | 30380/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.114.up_proj:  83%|████████▎ | 30381/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.114.down_proj:  83%|████████▎ | 30382/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.115.gate_proj:  83%|████████▎ | 30383/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.115.up_proj:  83%|████████▎ | 30384/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.115.down_proj:  83%|████████▎ | 30385/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.116.gate_proj:  83%|████████▎ | 30386/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.116.up_proj:  83%|████████▎ | 30387/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.116.down_proj:  83%|████████▎ | 30388/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.117.gate_proj:  83%|████████▎ | 30389/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.117.up_proj:  83%|████████▎ | 30390/36566 [00:27<00:05, 1135.85it/s]  
packing model.layers.77.mlp.experts.117.down_proj:  83%|████████▎ | 30391/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.118.gate_proj:  83%|████████▎ | 30392/36566 [00:27<00:05, 1135.85it/s]
packing model.layers.77.mlp.experts.118.gate_proj:  83%|████████▎ | 30393/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.118.up_proj:  83%|████████▎ | 30393/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.118.down_proj:  83%|████████▎ | 30394/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.119.gate_proj:  83%|████████▎ | 30395/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.119.up_proj:  83%|████████▎ | 30396/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.119.down_proj:  83%|████████▎ | 30397/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.120.gate_proj:  83%|████████▎ | 30398/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.120.up_proj:  83%|████████▎ | 30399/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.120.down_proj:  83%|████████▎ | 30400/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.121.gate_proj:  83%|████████▎ | 30401/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.121.up_proj:  83%|████████▎ | 30402/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.121.down_proj:  83%|████████▎ | 30403/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.122.gate_proj:  83%|████████▎ | 30404/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.122.up_proj:  83%|████████▎ | 30405/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.122.down_proj:  83%|████████▎ | 30406/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.123.gate_proj:  83%|████████▎ | 30407/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.123.up_proj:  83%|████████▎ | 30408/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.123.down_proj:  83%|████████▎ | 30409/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.124.gate_proj:  83%|████████▎ | 30410/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.124.up_proj:  83%|████████▎ | 30411/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.124.down_proj:  83%|████████▎ | 30412/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.125.gate_proj:  83%|████████▎ | 30413/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.125.up_proj:  83%|████████▎ | 30414/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.125.down_proj:  83%|████████▎ | 30415/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.126.gate_proj:  83%|████████▎ | 30416/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.126.up_proj:  83%|████████▎ | 30417/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.126.down_proj:  83%|████████▎ | 30418/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.127.gate_proj:  83%|████████▎ | 30419/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.77.mlp.experts.127.up_proj:  83%|████████▎ | 30420/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.77.mlp.experts.127.down_proj:  83%|████████▎ | 30421/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.0.gate_proj:  83%|████████▎ | 30422/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.0.up_proj:  83%|████████▎ | 30423/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.0.down_proj:  83%|████████▎ | 30424/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.1.gate_proj:  83%|████████▎ | 30425/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.1.up_proj:  83%|████████▎ | 30426/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.1.down_proj:  83%|████████▎ | 30427/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.2.gate_proj:  83%|████████▎ | 30428/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.2.up_proj:  83%|████████▎ | 30429/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.2.down_proj:  83%|████████▎ | 30430/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.3.gate_proj:  83%|████████▎ | 30431/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.3.up_proj:  83%|████████▎ | 30432/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.3.down_proj:  83%|████████▎ | 30433/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.4.gate_proj:  83%|████████▎ | 30434/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.4.up_proj:  83%|████████▎ | 30435/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.4.down_proj:  83%|████████▎ | 30436/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.5.gate_proj:  83%|████████▎ | 30437/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.5.up_proj:  83%|████████▎ | 30438/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.5.down_proj:  83%|████████▎ | 30439/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.6.gate_proj:  83%|████████▎ | 30440/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.6.up_proj:  83%|████████▎ | 30441/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.6.down_proj:  83%|████████▎ | 30442/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.7.gate_proj:  83%|████████▎ | 30443/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.7.up_proj:  83%|████████▎ | 30444/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.7.down_proj:  83%|████████▎ | 30445/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.8.gate_proj:  83%|████████▎ | 30446/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.8.up_proj:  83%|████████▎ | 30447/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.8.down_proj:  83%|████████▎ | 30448/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.9.gate_proj:  83%|████████▎ | 30449/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.9.up_proj:  83%|████████▎ | 30450/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.9.down_proj:  83%|████████▎ | 30451/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.10.gate_proj:  83%|████████▎ | 30452/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.10.up_proj:  83%|████████▎ | 30453/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.10.down_proj:  83%|████████▎ | 30454/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.11.gate_proj:  83%|████████▎ | 30455/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.11.up_proj:  83%|████████▎ | 30456/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.11.down_proj:  83%|████████▎ | 30457/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.12.gate_proj:  83%|████████▎ | 30458/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.12.up_proj:  83%|████████▎ | 30459/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.12.down_proj:  83%|████████▎ | 30460/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.13.gate_proj:  83%|████████▎ | 30461/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.13.up_proj:  83%|████████▎ | 30462/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.13.down_proj:  83%|████████▎ | 30463/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.14.gate_proj:  83%|████████▎ | 30464/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.14.up_proj:  83%|████████▎ | 30465/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.14.down_proj:  83%|████████▎ | 30466/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.15.gate_proj:  83%|████████▎ | 30467/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.15.up_proj:  83%|████████▎ | 30468/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.15.down_proj:  83%|████████▎ | 30469/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.16.gate_proj:  83%|████████▎ | 30470/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.16.up_proj:  83%|████████▎ | 30471/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.16.down_proj:  83%|████████▎ | 30472/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.17.gate_proj:  83%|████████▎ | 30473/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.17.up_proj:  83%|████████▎ | 30474/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.17.down_proj:  83%|████████▎ | 30475/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.18.gate_proj:  83%|████████▎ | 30476/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.18.up_proj:  83%|████████▎ | 30477/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.18.down_proj:  83%|████████▎ | 30478/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.19.gate_proj:  83%|████████▎ | 30479/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.19.up_proj:  83%|████████▎ | 30480/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.19.down_proj:  83%|████████▎ | 30481/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.20.gate_proj:  83%|████████▎ | 30482/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.20.up_proj:  83%|████████▎ | 30483/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.20.down_proj:  83%|████████▎ | 30484/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.21.gate_proj:  83%|████████▎ | 30485/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.21.up_proj:  83%|████████▎ | 30486/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.21.down_proj:  83%|████████▎ | 30487/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.22.gate_proj:  83%|████████▎ | 30488/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.22.up_proj:  83%|████████▎ | 30489/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.22.down_proj:  83%|████████▎ | 30490/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.23.gate_proj:  83%|████████▎ | 30491/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.23.up_proj:  83%|████████▎ | 30492/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.23.down_proj:  83%|████████▎ | 30493/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.24.gate_proj:  83%|████████▎ | 30494/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.24.up_proj:  83%|████████▎ | 30495/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.24.down_proj:  83%|████████▎ | 30496/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.25.gate_proj:  83%|████████▎ | 30497/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.25.up_proj:  83%|████████▎ | 30498/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.25.down_proj:  83%|████████▎ | 30499/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.26.gate_proj:  83%|████████▎ | 30500/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.26.up_proj:  83%|████████▎ | 30501/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.26.down_proj:  83%|████████▎ | 30502/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.27.gate_proj:  83%|████████▎ | 30503/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.27.up_proj:  83%|████████▎ | 30504/36566 [00:27<00:05, 1134.26it/s]  
packing model.layers.78.mlp.experts.27.down_proj:  83%|████████▎ | 30505/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.28.gate_proj:  83%|████████▎ | 30506/36566 [00:27<00:05, 1134.26it/s]
packing model.layers.78.mlp.experts.28.gate_proj:  83%|████████▎ | 30507/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.28.up_proj:  83%|████████▎ | 30507/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.28.down_proj:  83%|████████▎ | 30508/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.29.gate_proj:  83%|████████▎ | 30509/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.29.up_proj:  83%|████████▎ | 30510/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.29.down_proj:  83%|████████▎ | 30511/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.30.gate_proj:  83%|████████▎ | 30512/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.30.up_proj:  83%|████████▎ | 30513/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.30.down_proj:  83%|████████▎ | 30514/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.31.gate_proj:  83%|████████▎ | 30515/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.31.up_proj:  83%|████████▎ | 30516/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.31.down_proj:  83%|████████▎ | 30517/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.32.gate_proj:  83%|████████▎ | 30518/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.32.up_proj:  83%|████████▎ | 30519/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.32.down_proj:  83%|████████▎ | 30520/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.33.gate_proj:  83%|████████▎ | 30521/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.33.up_proj:  83%|████████▎ | 30522/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.33.down_proj:  83%|████████▎ | 30523/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.34.gate_proj:  83%|████████▎ | 30524/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.34.up_proj:  83%|████████▎ | 30525/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.34.down_proj:  83%|████████▎ | 30526/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.35.gate_proj:  83%|████████▎ | 30527/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.35.up_proj:  83%|████████▎ | 30528/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.35.down_proj:  83%|████████▎ | 30529/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.36.gate_proj:  83%|████████▎ | 30530/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.36.up_proj:  83%|████████▎ | 30531/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.36.down_proj:  83%|████████▎ | 30532/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.37.gate_proj:  84%|████████▎ | 30533/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.37.up_proj:  84%|████████▎ | 30534/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.37.down_proj:  84%|████████▎ | 30535/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.38.gate_proj:  84%|████████▎ | 30536/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.38.up_proj:  84%|████████▎ | 30537/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.38.down_proj:  84%|████████▎ | 30538/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.39.gate_proj:  84%|████████▎ | 30539/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.39.up_proj:  84%|████████▎ | 30540/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.39.down_proj:  84%|████████▎ | 30541/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.40.gate_proj:  84%|████████▎ | 30542/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.40.up_proj:  84%|████████▎ | 30543/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.40.down_proj:  84%|████████▎ | 30544/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.41.gate_proj:  84%|████████▎ | 30545/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.41.up_proj:  84%|████████▎ | 30546/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.41.down_proj:  84%|████████▎ | 30547/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.42.gate_proj:  84%|████████▎ | 30548/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.42.up_proj:  84%|████████▎ | 30549/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.42.down_proj:  84%|████████▎ | 30550/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.43.gate_proj:  84%|████████▎ | 30551/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.43.up_proj:  84%|████████▎ | 30552/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.43.down_proj:  84%|████████▎ | 30553/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.44.gate_proj:  84%|████████▎ | 30554/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.44.up_proj:  84%|████████▎ | 30555/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.44.down_proj:  84%|████████▎ | 30556/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.45.gate_proj:  84%|████████▎ | 30557/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.45.up_proj:  84%|████████▎ | 30558/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.45.down_proj:  84%|████████▎ | 30559/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.46.gate_proj:  84%|████████▎ | 30560/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.46.up_proj:  84%|████████▎ | 30561/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.46.down_proj:  84%|████████▎ | 30562/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.47.gate_proj:  84%|████████▎ | 30563/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.47.up_proj:  84%|████████▎ | 30564/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.47.down_proj:  84%|████████▎ | 30565/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.48.gate_proj:  84%|████████▎ | 30566/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.48.up_proj:  84%|████████▎ | 30567/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.48.down_proj:  84%|████████▎ | 30568/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.49.gate_proj:  84%|████████▎ | 30569/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.49.up_proj:  84%|████████▎ | 30570/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.49.down_proj:  84%|████████▎ | 30571/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.50.gate_proj:  84%|████████▎ | 30572/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.50.up_proj:  84%|████████▎ | 30573/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.50.down_proj:  84%|████████▎ | 30574/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.51.gate_proj:  84%|████████▎ | 30575/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.51.up_proj:  84%|████████▎ | 30576/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.51.down_proj:  84%|████████▎ | 30577/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.52.gate_proj:  84%|████████▎ | 30578/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.52.up_proj:  84%|████████▎ | 30579/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.52.down_proj:  84%|████████▎ | 30580/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.53.gate_proj:  84%|████████▎ | 30581/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.53.up_proj:  84%|████████▎ | 30582/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.53.down_proj:  84%|████████▎ | 30583/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.54.gate_proj:  84%|████████▎ | 30584/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.54.up_proj:  84%|████████▎ | 30585/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.54.down_proj:  84%|████████▎ | 30586/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.55.gate_proj:  84%|████████▎ | 30587/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.55.up_proj:  84%|████████▎ | 30588/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.55.down_proj:  84%|████████▎ | 30589/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.56.gate_proj:  84%|████████▎ | 30590/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.56.up_proj:  84%|████████▎ | 30591/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.56.down_proj:  84%|████████▎ | 30592/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.57.gate_proj:  84%|████████▎ | 30593/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.57.up_proj:  84%|████████▎ | 30594/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.57.down_proj:  84%|████████▎ | 30595/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.58.gate_proj:  84%|████████▎ | 30596/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.58.up_proj:  84%|████████▎ | 30597/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.58.down_proj:  84%|████████▎ | 30598/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.59.gate_proj:  84%|████████▎ | 30599/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.59.up_proj:  84%|████████▎ | 30600/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.59.down_proj:  84%|████████▎ | 30601/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.60.gate_proj:  84%|████████▎ | 30602/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.60.up_proj:  84%|████████▎ | 30603/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.60.down_proj:  84%|████████▎ | 30604/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.61.gate_proj:  84%|████████▎ | 30605/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.61.up_proj:  84%|████████▎ | 30606/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.61.down_proj:  84%|████████▎ | 30607/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.62.gate_proj:  84%|████████▎ | 30608/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.62.up_proj:  84%|████████▎ | 30609/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.62.down_proj:  84%|████████▎ | 30610/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.63.gate_proj:  84%|████████▎ | 30611/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.63.up_proj:  84%|████████▎ | 30612/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.63.down_proj:  84%|████████▎ | 30613/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.64.gate_proj:  84%|████████▎ | 30614/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.64.up_proj:  84%|████████▎ | 30615/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.64.down_proj:  84%|████████▎ | 30616/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.65.gate_proj:  84%|████████▎ | 30617/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.65.up_proj:  84%|████████▎ | 30618/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.65.down_proj:  84%|████████▎ | 30619/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.66.gate_proj:  84%|████████▎ | 30620/36566 [00:27<00:05, 1130.46it/s]
packing model.layers.78.mlp.experts.66.up_proj:  84%|████████▎ | 30621/36566 [00:27<00:05, 1130.46it/s]  
packing model.layers.78.mlp.experts.66.up_proj:  84%|████████▎ | 30622/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.66.down_proj:  84%|████████▎ | 30622/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.67.gate_proj:  84%|████████▎ | 30623/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.67.up_proj:  84%|████████▎ | 30624/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.67.down_proj:  84%|████████▍ | 30625/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.68.gate_proj:  84%|████████▍ | 30626/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.68.up_proj:  84%|████████▍ | 30627/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.68.down_proj:  84%|████████▍ | 30628/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.69.gate_proj:  84%|████████▍ | 30629/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.69.up_proj:  84%|████████▍ | 30630/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.69.down_proj:  84%|████████▍ | 30631/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.70.gate_proj:  84%|████████▍ | 30632/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.70.up_proj:  84%|████████▍ | 30633/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.70.down_proj:  84%|████████▍ | 30634/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.71.gate_proj:  84%|████████▍ | 30635/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.71.up_proj:  84%|████████▍ | 30636/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.71.down_proj:  84%|████████▍ | 30637/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.72.gate_proj:  84%|████████▍ | 30638/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.72.up_proj:  84%|████████▍ | 30639/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.72.down_proj:  84%|████████▍ | 30640/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.73.gate_proj:  84%|████████▍ | 30641/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.73.up_proj:  84%|████████▍ | 30642/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.73.down_proj:  84%|████████▍ | 30643/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.74.gate_proj:  84%|████████▍ | 30644/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.74.up_proj:  84%|████████▍ | 30645/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.74.down_proj:  84%|████████▍ | 30646/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.75.gate_proj:  84%|████████▍ | 30647/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.75.up_proj:  84%|████████▍ | 30648/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.75.down_proj:  84%|████████▍ | 30649/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.76.gate_proj:  84%|████████▍ | 30650/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.76.up_proj:  84%|████████▍ | 30651/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.76.down_proj:  84%|████████▍ | 30652/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.77.gate_proj:  84%|████████▍ | 30653/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.77.up_proj:  84%|████████▍ | 30654/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.77.down_proj:  84%|████████▍ | 30655/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.78.gate_proj:  84%|████████▍ | 30656/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.78.up_proj:  84%|████████▍ | 30657/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.78.down_proj:  84%|████████▍ | 30658/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.79.gate_proj:  84%|████████▍ | 30659/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.79.up_proj:  84%|████████▍ | 30660/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.79.down_proj:  84%|████████▍ | 30661/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.80.gate_proj:  84%|████████▍ | 30662/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.80.up_proj:  84%|████████▍ | 30663/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.80.down_proj:  84%|████████▍ | 30664/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.81.gate_proj:  84%|████████▍ | 30665/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.81.up_proj:  84%|████████▍ | 30666/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.81.down_proj:  84%|████████▍ | 30667/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.82.gate_proj:  84%|████████▍ | 30668/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.82.up_proj:  84%|████████▍ | 30669/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.82.down_proj:  84%|████████▍ | 30670/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.83.gate_proj:  84%|████████▍ | 30671/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.83.up_proj:  84%|████████▍ | 30672/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.83.down_proj:  84%|████████▍ | 30673/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.84.gate_proj:  84%|████████▍ | 30674/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.84.up_proj:  84%|████████▍ | 30675/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.84.down_proj:  84%|████████▍ | 30676/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.85.gate_proj:  84%|████████▍ | 30677/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.85.up_proj:  84%|████████▍ | 30678/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.85.down_proj:  84%|████████▍ | 30679/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.86.gate_proj:  84%|████████▍ | 30680/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.86.up_proj:  84%|████████▍ | 30681/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.86.down_proj:  84%|████████▍ | 30682/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.87.gate_proj:  84%|████████▍ | 30683/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.87.up_proj:  84%|████████▍ | 30684/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.87.down_proj:  84%|████████▍ | 30685/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.88.gate_proj:  84%|████████▍ | 30686/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.88.up_proj:  84%|████████▍ | 30687/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.88.down_proj:  84%|████████▍ | 30688/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.89.gate_proj:  84%|████████▍ | 30689/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.89.up_proj:  84%|████████▍ | 30690/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.89.down_proj:  84%|████████▍ | 30691/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.90.gate_proj:  84%|████████▍ | 30692/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.90.up_proj:  84%|████████▍ | 30693/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.90.down_proj:  84%|████████▍ | 30694/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.91.gate_proj:  84%|████████▍ | 30695/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.91.up_proj:  84%|████████▍ | 30696/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.91.down_proj:  84%|████████▍ | 30697/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.92.gate_proj:  84%|████████▍ | 30698/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.92.up_proj:  84%|████████▍ | 30699/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.92.down_proj:  84%|████████▍ | 30700/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.93.gate_proj:  84%|████████▍ | 30701/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.93.up_proj:  84%|████████▍ | 30702/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.93.down_proj:  84%|████████▍ | 30703/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.94.gate_proj:  84%|████████▍ | 30704/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.94.up_proj:  84%|████████▍ | 30705/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.94.down_proj:  84%|████████▍ | 30706/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.95.gate_proj:  84%|████████▍ | 30707/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.95.up_proj:  84%|████████▍ | 30708/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.95.down_proj:  84%|████████▍ | 30709/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.96.gate_proj:  84%|████████▍ | 30710/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.96.up_proj:  84%|████████▍ | 30711/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.96.down_proj:  84%|████████▍ | 30712/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.97.gate_proj:  84%|████████▍ | 30713/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.97.up_proj:  84%|████████▍ | 30714/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.97.down_proj:  84%|████████▍ | 30715/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.98.gate_proj:  84%|████████▍ | 30716/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.98.up_proj:  84%|████████▍ | 30717/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.98.down_proj:  84%|████████▍ | 30718/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.99.gate_proj:  84%|████████▍ | 30719/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.99.up_proj:  84%|████████▍ | 30720/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.99.down_proj:  84%|████████▍ | 30721/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.100.gate_proj:  84%|████████▍ | 30722/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.100.up_proj:  84%|████████▍ | 30723/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.100.down_proj:  84%|████████▍ | 30724/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.101.gate_proj:  84%|████████▍ | 30725/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.101.up_proj:  84%|████████▍ | 30726/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.101.down_proj:  84%|████████▍ | 30727/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.102.gate_proj:  84%|████████▍ | 30728/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.102.up_proj:  84%|████████▍ | 30729/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.102.down_proj:  84%|████████▍ | 30730/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.103.gate_proj:  84%|████████▍ | 30731/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.103.up_proj:  84%|████████▍ | 30732/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.103.down_proj:  84%|████████▍ | 30733/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.104.gate_proj:  84%|████████▍ | 30734/36566 [00:27<00:05, 1135.09it/s]
packing model.layers.78.mlp.experts.104.up_proj:  84%|████████▍ | 30735/36566 [00:27<00:05, 1135.09it/s]  
packing model.layers.78.mlp.experts.104.up_proj:  84%|████████▍ | 30736/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.104.down_proj:  84%|████████▍ | 30736/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.105.gate_proj:  84%|████████▍ | 30737/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.105.up_proj:  84%|████████▍ | 30738/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.105.down_proj:  84%|████████▍ | 30739/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.106.gate_proj:  84%|████████▍ | 30740/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.106.up_proj:  84%|████████▍ | 30741/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.106.down_proj:  84%|████████▍ | 30742/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.107.gate_proj:  84%|████████▍ | 30743/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.107.up_proj:  84%|████████▍ | 30744/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.107.down_proj:  84%|████████▍ | 30745/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.108.gate_proj:  84%|████████▍ | 30746/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.108.up_proj:  84%|████████▍ | 30747/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.108.down_proj:  84%|████████▍ | 30748/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.109.gate_proj:  84%|████████▍ | 30749/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.109.up_proj:  84%|████████▍ | 30750/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.109.down_proj:  84%|████████▍ | 30751/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.110.gate_proj:  84%|████████▍ | 30752/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.110.up_proj:  84%|████████▍ | 30753/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.110.down_proj:  84%|████████▍ | 30754/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.111.gate_proj:  84%|████████▍ | 30755/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.111.up_proj:  84%|████████▍ | 30756/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.111.down_proj:  84%|████████▍ | 30757/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.112.gate_proj:  84%|████████▍ | 30758/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.112.up_proj:  84%|████████▍ | 30759/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.112.down_proj:  84%|████████▍ | 30760/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.113.gate_proj:  84%|████████▍ | 30761/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.113.up_proj:  84%|████████▍ | 30762/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.113.down_proj:  84%|████████▍ | 30763/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.114.gate_proj:  84%|████████▍ | 30764/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.114.up_proj:  84%|████████▍ | 30765/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.114.down_proj:  84%|████████▍ | 30766/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.115.gate_proj:  84%|████████▍ | 30767/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.115.up_proj:  84%|████████▍ | 30768/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.115.down_proj:  84%|████████▍ | 30769/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.116.gate_proj:  84%|████████▍ | 30770/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.116.up_proj:  84%|████████▍ | 30771/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.116.down_proj:  84%|████████▍ | 30772/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.117.gate_proj:  84%|████████▍ | 30773/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.117.up_proj:  84%|████████▍ | 30774/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.117.down_proj:  84%|████████▍ | 30775/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.118.gate_proj:  84%|████████▍ | 30776/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.118.up_proj:  84%|████████▍ | 30777/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.118.down_proj:  84%|████████▍ | 30778/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.119.gate_proj:  84%|████████▍ | 30779/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.119.up_proj:  84%|████████▍ | 30780/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.119.down_proj:  84%|████████▍ | 30781/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.120.gate_proj:  84%|████████▍ | 30782/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.120.up_proj:  84%|████████▍ | 30783/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.120.down_proj:  84%|████████▍ | 30784/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.121.gate_proj:  84%|████████▍ | 30785/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.121.up_proj:  84%|████████▍ | 30786/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.121.down_proj:  84%|████████▍ | 30787/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.122.gate_proj:  84%|████████▍ | 30788/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.122.up_proj:  84%|████████▍ | 30789/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.122.down_proj:  84%|████████▍ | 30790/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.123.gate_proj:  84%|████████▍ | 30791/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.123.up_proj:  84%|████████▍ | 30792/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.123.down_proj:  84%|████████▍ | 30793/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.124.gate_proj:  84%|████████▍ | 30794/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.124.up_proj:  84%|████████▍ | 30795/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.124.down_proj:  84%|████████▍ | 30796/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.125.gate_proj:  84%|████████▍ | 30797/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.125.up_proj:  84%|████████▍ | 30798/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.125.down_proj:  84%|████████▍ | 30799/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.126.gate_proj:  84%|████████▍ | 30800/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.126.up_proj:  84%|████████▍ | 30801/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.126.down_proj:  84%|████████▍ | 30802/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.127.gate_proj:  84%|████████▍ | 30803/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.78.mlp.experts.127.up_proj:  84%|████████▍ | 30804/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.78.mlp.experts.127.down_proj:  84%|████████▍ | 30805/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.0.gate_proj:  84%|████████▍ | 30806/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.0.up_proj:  84%|████████▍ | 30807/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.0.down_proj:  84%|████████▍ | 30808/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.1.gate_proj:  84%|████████▍ | 30809/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.1.up_proj:  84%|████████▍ | 30810/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.1.down_proj:  84%|████████▍ | 30811/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.2.gate_proj:  84%|████████▍ | 30812/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.2.up_proj:  84%|████████▍ | 30813/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.2.down_proj:  84%|████████▍ | 30814/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.3.gate_proj:  84%|████████▍ | 30815/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.3.up_proj:  84%|████████▍ | 30816/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.3.down_proj:  84%|████████▍ | 30817/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.4.gate_proj:  84%|████████▍ | 30818/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.4.up_proj:  84%|████████▍ | 30819/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.4.down_proj:  84%|████████▍ | 30820/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.5.gate_proj:  84%|████████▍ | 30821/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.5.up_proj:  84%|████████▍ | 30822/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.5.down_proj:  84%|████████▍ | 30823/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.6.gate_proj:  84%|████████▍ | 30824/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.6.up_proj:  84%|████████▍ | 30825/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.6.down_proj:  84%|████████▍ | 30826/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.7.gate_proj:  84%|████████▍ | 30827/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.7.up_proj:  84%|████████▍ | 30828/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.7.down_proj:  84%|████████▍ | 30829/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.8.gate_proj:  84%|████████▍ | 30830/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.8.up_proj:  84%|████████▍ | 30831/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.8.down_proj:  84%|████████▍ | 30832/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.9.gate_proj:  84%|████████▍ | 30833/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.9.up_proj:  84%|████████▍ | 30834/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.9.down_proj:  84%|████████▍ | 30835/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.10.gate_proj:  84%|████████▍ | 30836/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.10.up_proj:  84%|████████▍ | 30837/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.10.down_proj:  84%|████████▍ | 30838/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.11.gate_proj:  84%|████████▍ | 30839/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.11.up_proj:  84%|████████▍ | 30840/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.11.down_proj:  84%|████████▍ | 30841/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.12.gate_proj:  84%|████████▍ | 30842/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.12.up_proj:  84%|████████▍ | 30843/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.12.down_proj:  84%|████████▍ | 30844/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.13.gate_proj:  84%|████████▍ | 30845/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.13.up_proj:  84%|████████▍ | 30846/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.13.down_proj:  84%|████████▍ | 30847/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.14.gate_proj:  84%|████████▍ | 30848/36566 [00:27<00:05, 1136.03it/s]
packing model.layers.79.mlp.experts.14.up_proj:  84%|████████▍ | 30849/36566 [00:27<00:05, 1136.03it/s]  
packing model.layers.79.mlp.experts.14.up_proj:  84%|████████▍ | 30850/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.14.down_proj:  84%|████████▍ | 30850/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.15.gate_proj:  84%|████████▍ | 30851/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.15.up_proj:  84%|████████▍ | 30852/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.15.down_proj:  84%|████████▍ | 30853/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.16.gate_proj:  84%|████████▍ | 30854/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.16.up_proj:  84%|████████▍ | 30855/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.16.down_proj:  84%|████████▍ | 30856/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.17.gate_proj:  84%|████████▍ | 30857/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.17.up_proj:  84%|████████▍ | 30858/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.17.down_proj:  84%|████████▍ | 30859/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.18.gate_proj:  84%|████████▍ | 30860/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.18.up_proj:  84%|████████▍ | 30861/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.18.down_proj:  84%|████████▍ | 30862/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.19.gate_proj:  84%|████████▍ | 30863/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.19.up_proj:  84%|████████▍ | 30864/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.19.down_proj:  84%|████████▍ | 30865/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.20.gate_proj:  84%|████████▍ | 30866/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.20.up_proj:  84%|████████▍ | 30867/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.20.down_proj:  84%|████████▍ | 30868/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.21.gate_proj:  84%|████████▍ | 30869/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.21.up_proj:  84%|████████▍ | 30870/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.21.down_proj:  84%|████████▍ | 30871/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.22.gate_proj:  84%|████████▍ | 30872/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.22.up_proj:  84%|████████▍ | 30873/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.22.down_proj:  84%|████████▍ | 30874/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.23.gate_proj:  84%|████████▍ | 30875/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.23.up_proj:  84%|████████▍ | 30876/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.23.down_proj:  84%|████████▍ | 30877/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.24.gate_proj:  84%|████████▍ | 30878/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.24.up_proj:  84%|████████▍ | 30879/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.24.down_proj:  84%|████████▍ | 30880/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.25.gate_proj:  84%|████████▍ | 30881/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.25.up_proj:  84%|████████▍ | 30882/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.25.down_proj:  84%|████████▍ | 30883/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.26.gate_proj:  84%|████████▍ | 30884/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.26.up_proj:  84%|████████▍ | 30885/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.26.down_proj:  84%|████████▍ | 30886/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.27.gate_proj:  84%|████████▍ | 30887/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.27.up_proj:  84%|████████▍ | 30888/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.27.down_proj:  84%|████████▍ | 30889/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.28.gate_proj:  84%|████████▍ | 30890/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.28.up_proj:  84%|████████▍ | 30891/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.28.down_proj:  84%|████████▍ | 30892/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.29.gate_proj:  84%|████████▍ | 30893/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.29.up_proj:  84%|████████▍ | 30894/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.29.down_proj:  84%|████████▍ | 30895/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.30.gate_proj:  84%|████████▍ | 30896/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.30.up_proj:  84%|████████▍ | 30897/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.30.down_proj:  84%|████████▍ | 30898/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.31.gate_proj:  85%|████████▍ | 30899/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.31.up_proj:  85%|████████▍ | 30900/36566 [00:28<00:05, 1132.87it/s]  
packing model.layers.79.mlp.experts.31.down_proj:  85%|████████▍ | 30901/36566 [00:28<00:05, 1132.87it/s]
packing model.layers.79.mlp.experts.32.gate_proj:  85%|████████▍ | 30902/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.32.up_proj:  85%|████████▍ | 30903/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.32.down_proj:  85%|████████▍ | 30904/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.33.gate_proj:  85%|████████▍ | 30905/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.33.up_proj:  85%|████████▍ | 30906/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.33.down_proj:  85%|████████▍ | 30907/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.34.gate_proj:  85%|████████▍ | 30908/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.34.up_proj:  85%|████████▍ | 30909/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.34.down_proj:  85%|████████▍ | 30910/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.35.gate_proj:  85%|████████▍ | 30911/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.35.up_proj:  85%|████████▍ | 30912/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.35.down_proj:  85%|████████▍ | 30913/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.36.gate_proj:  85%|████████▍ | 30914/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.36.up_proj:  85%|████████▍ | 30915/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.36.down_proj:  85%|████████▍ | 30916/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.37.gate_proj:  85%|████████▍ | 30917/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.37.up_proj:  85%|████████▍ | 30918/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.37.down_proj:  85%|████████▍ | 30919/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.38.gate_proj:  85%|████████▍ | 30920/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.38.up_proj:  85%|████████▍ | 30921/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.38.down_proj:  85%|████████▍ | 30922/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.39.gate_proj:  85%|████████▍ | 30923/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.39.up_proj:  85%|████████▍ | 30924/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.39.down_proj:  85%|████████▍ | 30925/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.40.gate_proj:  85%|████████▍ | 30926/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.40.up_proj:  85%|████████▍ | 30927/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.40.down_proj:  85%|████████▍ | 30928/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.41.gate_proj:  85%|████████▍ | 30929/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.41.up_proj:  85%|████████▍ | 30930/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.41.down_proj:  85%|████████▍ | 30931/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.42.gate_proj:  85%|████████▍ | 30932/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.42.up_proj:  85%|████████▍ | 30933/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.42.down_proj:  85%|████████▍ | 30934/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.43.gate_proj:  85%|████████▍ | 30935/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.43.up_proj:  85%|████████▍ | 30936/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.43.down_proj:  85%|████████▍ | 30937/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.44.gate_proj:  85%|████████▍ | 30938/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.44.up_proj:  85%|████████▍ | 30939/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.44.down_proj:  85%|████████▍ | 30940/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.45.gate_proj:  85%|████████▍ | 30941/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.45.up_proj:  85%|████████▍ | 30942/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.45.down_proj:  85%|████████▍ | 30943/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.46.gate_proj:  85%|████████▍ | 30944/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.46.up_proj:  85%|████████▍ | 30945/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.46.down_proj:  85%|████████▍ | 30946/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.47.gate_proj:  85%|████████▍ | 30947/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.47.up_proj:  85%|████████▍ | 30948/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.47.down_proj:  85%|████████▍ | 30949/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.48.gate_proj:  85%|████████▍ | 30950/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.48.up_proj:  85%|████████▍ | 30951/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.48.down_proj:  85%|████████▍ | 30952/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.49.gate_proj:  85%|████████▍ | 30953/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.49.up_proj:  85%|████████▍ | 30954/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.49.down_proj:  85%|████████▍ | 30955/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.50.gate_proj:  85%|████████▍ | 30956/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.50.up_proj:  85%|████████▍ | 30957/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.50.down_proj:  85%|████████▍ | 30958/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.51.gate_proj:  85%|████████▍ | 30959/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.51.up_proj:  85%|████████▍ | 30960/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.51.down_proj:  85%|████████▍ | 30961/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.52.gate_proj:  85%|████████▍ | 30962/36566 [00:28<00:04, 1132.87it/s]
packing model.layers.79.mlp.experts.52.up_proj:  85%|████████▍ | 30963/36566 [00:28<00:04, 1132.87it/s]  
packing model.layers.79.mlp.experts.52.up_proj:  85%|████████▍ | 30964/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.52.down_proj:  85%|████████▍ | 30964/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.53.gate_proj:  85%|████████▍ | 30965/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.53.up_proj:  85%|████████▍ | 30966/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.53.down_proj:  85%|████████▍ | 30967/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.54.gate_proj:  85%|████████▍ | 30968/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.54.up_proj:  85%|████████▍ | 30969/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.54.down_proj:  85%|████████▍ | 30970/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.55.gate_proj:  85%|████████▍ | 30971/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.55.up_proj:  85%|████████▍ | 30972/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.55.down_proj:  85%|████████▍ | 30973/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.56.gate_proj:  85%|████████▍ | 30974/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.56.up_proj:  85%|████████▍ | 30975/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.56.down_proj:  85%|████████▍ | 30976/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.57.gate_proj:  85%|████████▍ | 30977/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.57.up_proj:  85%|████████▍ | 30978/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.57.down_proj:  85%|████████▍ | 30979/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.58.gate_proj:  85%|████████▍ | 30980/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.58.up_proj:  85%|████████▍ | 30981/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.58.down_proj:  85%|████████▍ | 30982/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.59.gate_proj:  85%|████████▍ | 30983/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.59.up_proj:  85%|████████▍ | 30984/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.59.down_proj:  85%|████████▍ | 30985/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.60.gate_proj:  85%|████████▍ | 30986/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.60.up_proj:  85%|████████▍ | 30987/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.60.down_proj:  85%|████████▍ | 30988/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.61.gate_proj:  85%|████████▍ | 30989/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.61.up_proj:  85%|████████▍ | 30990/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.61.down_proj:  85%|████████▍ | 30991/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.62.gate_proj:  85%|████████▍ | 30992/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.62.up_proj:  85%|████████▍ | 30993/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.62.down_proj:  85%|████████▍ | 30994/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.63.gate_proj:  85%|████████▍ | 30995/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.63.up_proj:  85%|████████▍ | 30996/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.63.down_proj:  85%|████████▍ | 30997/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.64.gate_proj:  85%|████████▍ | 30998/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.64.up_proj:  85%|████████▍ | 30999/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.64.down_proj:  85%|████████▍ | 31000/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.65.gate_proj:  85%|████████▍ | 31001/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.65.up_proj:  85%|████████▍ | 31002/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.65.down_proj:  85%|████████▍ | 31003/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.66.gate_proj:  85%|████████▍ | 31004/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.66.up_proj:  85%|████████▍ | 31005/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.66.down_proj:  85%|████████▍ | 31006/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.67.gate_proj:  85%|████████▍ | 31007/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.67.up_proj:  85%|████████▍ | 31008/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.67.down_proj:  85%|████████▍ | 31009/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.68.gate_proj:  85%|████████▍ | 31010/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.68.up_proj:  85%|████████▍ | 31011/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.68.down_proj:  85%|████████▍ | 31012/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.69.gate_proj:  85%|████████▍ | 31013/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.69.up_proj:  85%|████████▍ | 31014/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.69.down_proj:  85%|████████▍ | 31015/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.70.gate_proj:  85%|████████▍ | 31016/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.70.up_proj:  85%|████████▍ | 31017/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.70.down_proj:  85%|████████▍ | 31018/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.71.gate_proj:  85%|████████▍ | 31019/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.71.up_proj:  85%|████████▍ | 31020/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.71.down_proj:  85%|████████▍ | 31021/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.72.gate_proj:  85%|████████▍ | 31022/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.72.up_proj:  85%|████████▍ | 31023/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.72.down_proj:  85%|████████▍ | 31024/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.73.gate_proj:  85%|████████▍ | 31025/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.73.up_proj:  85%|████████▍ | 31026/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.73.down_proj:  85%|████████▍ | 31027/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.74.gate_proj:  85%|████████▍ | 31028/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.74.up_proj:  85%|████████▍ | 31029/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.74.down_proj:  85%|████████▍ | 31030/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.75.gate_proj:  85%|████████▍ | 31031/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.75.up_proj:  85%|████████▍ | 31032/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.75.down_proj:  85%|████████▍ | 31033/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.76.gate_proj:  85%|████████▍ | 31034/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.76.up_proj:  85%|████████▍ | 31035/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.76.down_proj:  85%|████████▍ | 31036/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.77.gate_proj:  85%|████████▍ | 31037/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.77.up_proj:  85%|████████▍ | 31038/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.77.down_proj:  85%|████████▍ | 31039/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.78.gate_proj:  85%|████████▍ | 31040/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.78.up_proj:  85%|████████▍ | 31041/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.78.down_proj:  85%|████████▍ | 31042/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.79.gate_proj:  85%|████████▍ | 31043/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.79.up_proj:  85%|████████▍ | 31044/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.79.down_proj:  85%|████████▍ | 31045/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.80.gate_proj:  85%|████████▍ | 31046/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.80.up_proj:  85%|████████▍ | 31047/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.80.down_proj:  85%|████████▍ | 31048/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.81.gate_proj:  85%|████████▍ | 31049/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.81.up_proj:  85%|████████▍ | 31050/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.81.down_proj:  85%|████████▍ | 31051/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.82.gate_proj:  85%|████████▍ | 31052/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.82.up_proj:  85%|████████▍ | 31053/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.82.down_proj:  85%|████████▍ | 31054/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.83.gate_proj:  85%|████████▍ | 31055/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.83.up_proj:  85%|████████▍ | 31056/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.83.down_proj:  85%|████████▍ | 31057/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.84.gate_proj:  85%|████████▍ | 31058/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.84.up_proj:  85%|████████▍ | 31059/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.84.down_proj:  85%|████████▍ | 31060/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.85.gate_proj:  85%|████████▍ | 31061/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.85.up_proj:  85%|████████▍ | 31062/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.85.down_proj:  85%|████████▍ | 31063/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.86.gate_proj:  85%|████████▍ | 31064/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.86.up_proj:  85%|████████▍ | 31065/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.86.down_proj:  85%|████████▍ | 31066/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.87.gate_proj:  85%|████████▍ | 31067/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.87.up_proj:  85%|████████▍ | 31068/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.87.down_proj:  85%|████████▍ | 31069/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.88.gate_proj:  85%|████████▍ | 31070/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.88.up_proj:  85%|████████▍ | 31071/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.88.down_proj:  85%|████████▍ | 31072/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.89.gate_proj:  85%|████████▍ | 31073/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.89.up_proj:  85%|████████▍ | 31074/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.89.down_proj:  85%|████████▍ | 31075/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.90.gate_proj:  85%|████████▍ | 31076/36566 [00:28<00:04, 1130.44it/s]
packing model.layers.79.mlp.experts.90.up_proj:  85%|████████▍ | 31077/36566 [00:28<00:04, 1130.44it/s]  
packing model.layers.79.mlp.experts.90.up_proj:  85%|████████▍ | 31078/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.90.down_proj:  85%|████████▍ | 31078/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.91.gate_proj:  85%|████████▍ | 31079/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.91.up_proj:  85%|████████▍ | 31080/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.91.down_proj:  85%|████████▍ | 31081/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.92.gate_proj:  85%|████████▌ | 31082/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.92.up_proj:  85%|████████▌ | 31083/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.92.down_proj:  85%|████████▌ | 31084/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.93.gate_proj:  85%|████████▌ | 31085/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.93.up_proj:  85%|████████▌ | 31086/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.93.down_proj:  85%|████████▌ | 31087/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.94.gate_proj:  85%|████████▌ | 31088/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.94.up_proj:  85%|████████▌ | 31089/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.94.down_proj:  85%|████████▌ | 31090/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.95.gate_proj:  85%|████████▌ | 31091/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.95.up_proj:  85%|████████▌ | 31092/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.95.down_proj:  85%|████████▌ | 31093/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.96.gate_proj:  85%|████████▌ | 31094/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.96.up_proj:  85%|████████▌ | 31095/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.96.down_proj:  85%|████████▌ | 31096/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.97.gate_proj:  85%|████████▌ | 31097/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.97.up_proj:  85%|████████▌ | 31098/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.97.down_proj:  85%|████████▌ | 31099/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.98.gate_proj:  85%|████████▌ | 31100/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.98.up_proj:  85%|████████▌ | 31101/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.98.down_proj:  85%|████████▌ | 31102/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.99.gate_proj:  85%|████████▌ | 31103/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.99.up_proj:  85%|████████▌ | 31104/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.99.down_proj:  85%|████████▌ | 31105/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.100.gate_proj:  85%|████████▌ | 31106/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.100.up_proj:  85%|████████▌ | 31107/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.100.down_proj:  85%|████████▌ | 31108/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.101.gate_proj:  85%|████████▌ | 31109/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.101.up_proj:  85%|████████▌ | 31110/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.101.down_proj:  85%|████████▌ | 31111/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.102.gate_proj:  85%|████████▌ | 31112/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.102.up_proj:  85%|████████▌ | 31113/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.102.down_proj:  85%|████████▌ | 31114/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.103.gate_proj:  85%|████████▌ | 31115/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.103.up_proj:  85%|████████▌ | 31116/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.103.down_proj:  85%|████████▌ | 31117/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.104.gate_proj:  85%|████████▌ | 31118/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.104.up_proj:  85%|████████▌ | 31119/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.104.down_proj:  85%|████████▌ | 31120/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.105.gate_proj:  85%|████████▌ | 31121/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.105.up_proj:  85%|████████▌ | 31122/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.105.down_proj:  85%|████████▌ | 31123/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.106.gate_proj:  85%|████████▌ | 31124/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.106.up_proj:  85%|████████▌ | 31125/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.106.down_proj:  85%|████████▌ | 31126/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.107.gate_proj:  85%|████████▌ | 31127/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.107.up_proj:  85%|████████▌ | 31128/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.107.down_proj:  85%|████████▌ | 31129/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.108.gate_proj:  85%|████████▌ | 31130/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.108.up_proj:  85%|████████▌ | 31131/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.108.down_proj:  85%|████████▌ | 31132/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.109.gate_proj:  85%|████████▌ | 31133/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.109.up_proj:  85%|████████▌ | 31134/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.109.down_proj:  85%|████████▌ | 31135/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.110.gate_proj:  85%|████████▌ | 31136/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.110.up_proj:  85%|████████▌ | 31137/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.110.down_proj:  85%|████████▌ | 31138/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.111.gate_proj:  85%|████████▌ | 31139/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.111.up_proj:  85%|████████▌ | 31140/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.111.down_proj:  85%|████████▌ | 31141/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.112.gate_proj:  85%|████████▌ | 31142/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.112.up_proj:  85%|████████▌ | 31143/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.112.down_proj:  85%|████████▌ | 31144/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.113.gate_proj:  85%|████████▌ | 31145/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.113.up_proj:  85%|████████▌ | 31146/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.113.down_proj:  85%|████████▌ | 31147/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.114.gate_proj:  85%|████████▌ | 31148/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.114.up_proj:  85%|████████▌ | 31149/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.114.down_proj:  85%|████████▌ | 31150/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.115.gate_proj:  85%|████████▌ | 31151/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.115.up_proj:  85%|████████▌ | 31152/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.115.down_proj:  85%|████████▌ | 31153/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.116.gate_proj:  85%|████████▌ | 31154/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.116.up_proj:  85%|████████▌ | 31155/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.116.down_proj:  85%|████████▌ | 31156/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.117.gate_proj:  85%|████████▌ | 31157/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.117.up_proj:  85%|████████▌ | 31158/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.117.down_proj:  85%|████████▌ | 31159/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.118.gate_proj:  85%|████████▌ | 31160/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.118.up_proj:  85%|████████▌ | 31161/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.118.down_proj:  85%|████████▌ | 31162/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.119.gate_proj:  85%|████████▌ | 31163/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.119.up_proj:  85%|████████▌ | 31164/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.119.down_proj:  85%|████████▌ | 31165/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.120.gate_proj:  85%|████████▌ | 31166/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.120.up_proj:  85%|████████▌ | 31167/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.120.down_proj:  85%|████████▌ | 31168/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.121.gate_proj:  85%|████████▌ | 31169/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.121.up_proj:  85%|████████▌ | 31170/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.121.down_proj:  85%|████████▌ | 31171/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.122.gate_proj:  85%|████████▌ | 31172/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.122.up_proj:  85%|████████▌ | 31173/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.122.down_proj:  85%|████████▌ | 31174/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.123.gate_proj:  85%|████████▌ | 31175/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.123.up_proj:  85%|████████▌ | 31176/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.123.down_proj:  85%|████████▌ | 31177/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.124.gate_proj:  85%|████████▌ | 31178/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.124.up_proj:  85%|████████▌ | 31179/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.124.down_proj:  85%|████████▌ | 31180/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.125.gate_proj:  85%|████████▌ | 31181/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.125.up_proj:  85%|████████▌ | 31182/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.125.down_proj:  85%|████████▌ | 31183/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.126.gate_proj:  85%|████████▌ | 31184/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.126.up_proj:  85%|████████▌ | 31185/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.126.down_proj:  85%|████████▌ | 31186/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.127.gate_proj:  85%|████████▌ | 31187/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.79.mlp.experts.127.up_proj:  85%|████████▌ | 31188/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.79.mlp.experts.127.down_proj:  85%|████████▌ | 31189/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.80.mlp.experts.0.gate_proj:  85%|████████▌ | 31190/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.80.mlp.experts.0.up_proj:  85%|████████▌ | 31191/36566 [00:28<00:04, 1132.51it/s]  
packing model.layers.80.mlp.experts.0.down_proj:  85%|████████▌ | 31192/36566 [00:28<00:04, 1132.51it/s]
packing model.layers.80.mlp.experts.0.down_proj:  85%|████████▌ | 31193/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.1.gate_proj:  85%|████████▌ | 31193/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.1.up_proj:  85%|████████▌ | 31194/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.1.down_proj:  85%|████████▌ | 31195/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.2.gate_proj:  85%|████████▌ | 31196/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.2.up_proj:  85%|████████▌ | 31197/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.2.down_proj:  85%|████████▌ | 31198/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.3.gate_proj:  85%|████████▌ | 31199/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.3.up_proj:  85%|████████▌ | 31200/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.3.down_proj:  85%|████████▌ | 31201/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.4.gate_proj:  85%|████████▌ | 31202/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.4.up_proj:  85%|████████▌ | 31203/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.4.down_proj:  85%|████████▌ | 31204/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.5.gate_proj:  85%|████████▌ | 31205/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.5.up_proj:  85%|████████▌ | 31206/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.5.down_proj:  85%|████████▌ | 31207/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.6.gate_proj:  85%|████████▌ | 31208/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.6.up_proj:  85%|████████▌ | 31209/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.6.down_proj:  85%|████████▌ | 31210/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.7.gate_proj:  85%|████████▌ | 31211/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.7.up_proj:  85%|████████▌ | 31212/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.7.down_proj:  85%|████████▌ | 31213/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.8.gate_proj:  85%|████████▌ | 31214/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.8.up_proj:  85%|████████▌ | 31215/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.8.down_proj:  85%|████████▌ | 31216/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.9.gate_proj:  85%|████████▌ | 31217/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.9.up_proj:  85%|████████▌ | 31218/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.9.down_proj:  85%|████████▌ | 31219/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.10.gate_proj:  85%|████████▌ | 31220/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.10.up_proj:  85%|████████▌ | 31221/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.10.down_proj:  85%|████████▌ | 31222/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.11.gate_proj:  85%|████████▌ | 31223/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.11.up_proj:  85%|████████▌ | 31224/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.11.down_proj:  85%|████████▌ | 31225/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.12.gate_proj:  85%|████████▌ | 31226/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.12.up_proj:  85%|████████▌ | 31227/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.12.down_proj:  85%|████████▌ | 31228/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.13.gate_proj:  85%|████████▌ | 31229/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.13.up_proj:  85%|████████▌ | 31230/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.13.down_proj:  85%|████████▌ | 31231/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.14.gate_proj:  85%|████████▌ | 31232/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.14.up_proj:  85%|████████▌ | 31233/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.14.down_proj:  85%|████████▌ | 31234/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.15.gate_proj:  85%|████████▌ | 31235/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.15.up_proj:  85%|████████▌ | 31236/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.15.down_proj:  85%|████████▌ | 31237/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.16.gate_proj:  85%|████████▌ | 31238/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.16.up_proj:  85%|████████▌ | 31239/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.16.down_proj:  85%|████████▌ | 31240/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.17.gate_proj:  85%|████████▌ | 31241/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.17.up_proj:  85%|████████▌ | 31242/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.17.down_proj:  85%|████████▌ | 31243/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.18.gate_proj:  85%|████████▌ | 31244/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.18.up_proj:  85%|████████▌ | 31245/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.18.down_proj:  85%|████████▌ | 31246/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.19.gate_proj:  85%|████████▌ | 31247/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.19.up_proj:  85%|████████▌ | 31248/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.19.down_proj:  85%|████████▌ | 31249/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.20.gate_proj:  85%|████████▌ | 31250/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.20.up_proj:  85%|████████▌ | 31251/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.20.down_proj:  85%|████████▌ | 31252/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.21.gate_proj:  85%|████████▌ | 31253/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.21.up_proj:  85%|████████▌ | 31254/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.21.down_proj:  85%|████████▌ | 31255/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.22.gate_proj:  85%|████████▌ | 31256/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.22.up_proj:  85%|████████▌ | 31257/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.22.down_proj:  85%|████████▌ | 31258/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.23.gate_proj:  85%|████████▌ | 31259/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.23.up_proj:  85%|████████▌ | 31260/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.23.down_proj:  85%|████████▌ | 31261/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.24.gate_proj:  85%|████████▌ | 31262/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.24.up_proj:  85%|████████▌ | 31263/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.24.down_proj:  86%|████████▌ | 31264/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.25.gate_proj:  86%|████████▌ | 31265/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.25.up_proj:  86%|████████▌ | 31266/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.25.down_proj:  86%|████████▌ | 31267/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.26.gate_proj:  86%|████████▌ | 31268/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.26.up_proj:  86%|████████▌ | 31269/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.26.down_proj:  86%|████████▌ | 31270/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.27.gate_proj:  86%|████████▌ | 31271/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.27.up_proj:  86%|████████▌ | 31272/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.27.down_proj:  86%|████████▌ | 31273/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.28.gate_proj:  86%|████████▌ | 31274/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.28.up_proj:  86%|████████▌ | 31275/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.28.down_proj:  86%|████████▌ | 31276/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.29.gate_proj:  86%|████████▌ | 31277/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.29.up_proj:  86%|████████▌ | 31278/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.29.down_proj:  86%|████████▌ | 31279/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.30.gate_proj:  86%|████████▌ | 31280/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.30.up_proj:  86%|████████▌ | 31281/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.30.down_proj:  86%|████████▌ | 31282/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.31.gate_proj:  86%|████████▌ | 31283/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.31.up_proj:  86%|████████▌ | 31284/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.31.down_proj:  86%|████████▌ | 31285/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.32.gate_proj:  86%|████████▌ | 31286/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.32.up_proj:  86%|████████▌ | 31287/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.32.down_proj:  86%|████████▌ | 31288/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.33.gate_proj:  86%|████████▌ | 31289/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.33.up_proj:  86%|████████▌ | 31290/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.33.down_proj:  86%|████████▌ | 31291/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.34.gate_proj:  86%|████████▌ | 31292/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.34.up_proj:  86%|████████▌ | 31293/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.34.down_proj:  86%|████████▌ | 31294/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.35.gate_proj:  86%|████████▌ | 31295/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.35.up_proj:  86%|████████▌ | 31296/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.35.down_proj:  86%|████████▌ | 31297/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.36.gate_proj:  86%|████████▌ | 31298/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.36.up_proj:  86%|████████▌ | 31299/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.36.down_proj:  86%|████████▌ | 31300/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.37.gate_proj:  86%|████████▌ | 31301/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.37.up_proj:  86%|████████▌ | 31302/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.37.down_proj:  86%|████████▌ | 31303/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.38.gate_proj:  86%|████████▌ | 31304/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.38.up_proj:  86%|████████▌ | 31305/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.38.down_proj:  86%|████████▌ | 31306/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.39.gate_proj:  86%|████████▌ | 31307/36566 [00:28<00:04, 1135.47it/s]
packing model.layers.80.mlp.experts.39.up_proj:  86%|████████▌ | 31308/36566 [00:28<00:04, 1135.47it/s]  
packing model.layers.80.mlp.experts.39.up_proj:  86%|████████▌ | 31309/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.39.down_proj:  86%|████████▌ | 31309/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.40.gate_proj:  86%|████████▌ | 31310/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.40.up_proj:  86%|████████▌ | 31311/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.40.down_proj:  86%|████████▌ | 31312/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.41.gate_proj:  86%|████████▌ | 31313/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.41.up_proj:  86%|████████▌ | 31314/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.41.down_proj:  86%|████████▌ | 31315/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.42.gate_proj:  86%|████████▌ | 31316/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.42.up_proj:  86%|████████▌ | 31317/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.42.down_proj:  86%|████████▌ | 31318/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.43.gate_proj:  86%|████████▌ | 31319/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.43.up_proj:  86%|████████▌ | 31320/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.43.down_proj:  86%|████████▌ | 31321/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.44.gate_proj:  86%|████████▌ | 31322/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.44.up_proj:  86%|████████▌ | 31323/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.44.down_proj:  86%|████████▌ | 31324/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.45.gate_proj:  86%|████████▌ | 31325/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.45.up_proj:  86%|████████▌ | 31326/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.45.down_proj:  86%|████████▌ | 31327/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.46.gate_proj:  86%|████████▌ | 31328/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.46.up_proj:  86%|████████▌ | 31329/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.46.down_proj:  86%|████████▌ | 31330/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.47.gate_proj:  86%|████████▌ | 31331/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.47.up_proj:  86%|████████▌ | 31332/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.47.down_proj:  86%|████████▌ | 31333/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.48.gate_proj:  86%|████████▌ | 31334/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.48.up_proj:  86%|████████▌ | 31335/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.48.down_proj:  86%|████████▌ | 31336/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.49.gate_proj:  86%|████████▌ | 31337/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.49.up_proj:  86%|████████▌ | 31338/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.49.down_proj:  86%|████████▌ | 31339/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.50.gate_proj:  86%|████████▌ | 31340/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.50.up_proj:  86%|████████▌ | 31341/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.50.down_proj:  86%|████████▌ | 31342/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.51.gate_proj:  86%|████████▌ | 31343/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.51.up_proj:  86%|████████▌ | 31344/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.51.down_proj:  86%|████████▌ | 31345/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.52.gate_proj:  86%|████████▌ | 31346/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.52.up_proj:  86%|████████▌ | 31347/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.52.down_proj:  86%|████████▌ | 31348/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.53.gate_proj:  86%|████████▌ | 31349/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.53.up_proj:  86%|████████▌ | 31350/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.53.down_proj:  86%|████████▌ | 31351/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.54.gate_proj:  86%|████████▌ | 31352/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.54.up_proj:  86%|████████▌ | 31353/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.54.down_proj:  86%|████████▌ | 31354/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.55.gate_proj:  86%|████████▌ | 31355/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.55.up_proj:  86%|████████▌ | 31356/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.55.down_proj:  86%|████████▌ | 31357/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.56.gate_proj:  86%|████████▌ | 31358/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.56.up_proj:  86%|████████▌ | 31359/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.56.down_proj:  86%|████████▌ | 31360/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.57.gate_proj:  86%|████████▌ | 31361/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.57.up_proj:  86%|████████▌ | 31362/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.57.down_proj:  86%|████████▌ | 31363/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.58.gate_proj:  86%|████████▌ | 31364/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.58.up_proj:  86%|████████▌ | 31365/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.58.down_proj:  86%|████████▌ | 31366/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.59.gate_proj:  86%|████████▌ | 31367/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.59.up_proj:  86%|████████▌ | 31368/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.59.down_proj:  86%|████████▌ | 31369/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.60.gate_proj:  86%|████████▌ | 31370/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.60.up_proj:  86%|████████▌ | 31371/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.60.down_proj:  86%|████████▌ | 31372/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.61.gate_proj:  86%|████████▌ | 31373/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.61.up_proj:  86%|████████▌ | 31374/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.61.down_proj:  86%|████████▌ | 31375/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.62.gate_proj:  86%|████████▌ | 31376/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.62.up_proj:  86%|████████▌ | 31377/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.62.down_proj:  86%|████████▌ | 31378/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.63.gate_proj:  86%|████████▌ | 31379/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.63.up_proj:  86%|████████▌ | 31380/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.63.down_proj:  86%|████████▌ | 31381/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.64.gate_proj:  86%|████████▌ | 31382/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.64.up_proj:  86%|████████▌ | 31383/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.64.down_proj:  86%|████████▌ | 31384/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.65.gate_proj:  86%|████████▌ | 31385/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.65.up_proj:  86%|████████▌ | 31386/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.65.down_proj:  86%|████████▌ | 31387/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.66.gate_proj:  86%|████████▌ | 31388/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.66.up_proj:  86%|████████▌ | 31389/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.66.down_proj:  86%|████████▌ | 31390/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.67.gate_proj:  86%|████████▌ | 31391/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.67.up_proj:  86%|████████▌ | 31392/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.67.down_proj:  86%|████████▌ | 31393/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.68.gate_proj:  86%|████████▌ | 31394/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.68.up_proj:  86%|████████▌ | 31395/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.68.down_proj:  86%|████████▌ | 31396/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.69.gate_proj:  86%|████████▌ | 31397/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.69.up_proj:  86%|████████▌ | 31398/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.69.down_proj:  86%|████████▌ | 31399/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.70.gate_proj:  86%|████████▌ | 31400/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.70.up_proj:  86%|████████▌ | 31401/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.70.down_proj:  86%|████████▌ | 31402/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.71.gate_proj:  86%|████████▌ | 31403/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.71.up_proj:  86%|████████▌ | 31404/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.71.down_proj:  86%|████████▌ | 31405/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.72.gate_proj:  86%|████████▌ | 31406/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.72.up_proj:  86%|████████▌ | 31407/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.72.down_proj:  86%|████████▌ | 31408/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.73.gate_proj:  86%|████████▌ | 31409/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.73.up_proj:  86%|████████▌ | 31410/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.73.down_proj:  86%|████████▌ | 31411/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.74.gate_proj:  86%|████████▌ | 31412/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.74.up_proj:  86%|████████▌ | 31413/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.74.down_proj:  86%|████████▌ | 31414/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.75.gate_proj:  86%|████████▌ | 31415/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.75.up_proj:  86%|████████▌ | 31416/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.75.down_proj:  86%|████████▌ | 31417/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.76.gate_proj:  86%|████████▌ | 31418/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.76.up_proj:  86%|████████▌ | 31419/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.76.down_proj:  86%|████████▌ | 31420/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.77.gate_proj:  86%|████████▌ | 31421/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.77.up_proj:  86%|████████▌ | 31422/36566 [00:28<00:04, 1140.55it/s]  
packing model.layers.80.mlp.experts.77.down_proj:  86%|████████▌ | 31423/36566 [00:28<00:04, 1140.55it/s]
packing model.layers.80.mlp.experts.77.down_proj:  86%|████████▌ | 31424/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.78.gate_proj:  86%|████████▌ | 31424/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.78.up_proj:  86%|████████▌ | 31425/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.78.down_proj:  86%|████████▌ | 31426/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.79.gate_proj:  86%|████████▌ | 31427/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.79.up_proj:  86%|████████▌ | 31428/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.79.down_proj:  86%|████████▌ | 31429/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.80.gate_proj:  86%|████████▌ | 31430/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.80.up_proj:  86%|████████▌ | 31431/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.80.down_proj:  86%|████████▌ | 31432/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.81.gate_proj:  86%|████████▌ | 31433/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.81.up_proj:  86%|████████▌ | 31434/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.81.down_proj:  86%|████████▌ | 31435/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.82.gate_proj:  86%|████████▌ | 31436/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.82.up_proj:  86%|████████▌ | 31437/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.82.down_proj:  86%|████████▌ | 31438/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.83.gate_proj:  86%|████████▌ | 31439/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.83.up_proj:  86%|████████▌ | 31440/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.83.down_proj:  86%|████████▌ | 31441/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.84.gate_proj:  86%|████████▌ | 31442/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.84.up_proj:  86%|████████▌ | 31443/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.84.down_proj:  86%|████████▌ | 31444/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.85.gate_proj:  86%|████████▌ | 31445/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.85.up_proj:  86%|████████▌ | 31446/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.85.down_proj:  86%|████████▌ | 31447/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.86.gate_proj:  86%|████████▌ | 31448/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.86.up_proj:  86%|████████▌ | 31449/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.86.down_proj:  86%|████████▌ | 31450/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.87.gate_proj:  86%|████████▌ | 31451/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.87.up_proj:  86%|████████▌ | 31452/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.87.down_proj:  86%|████████▌ | 31453/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.88.gate_proj:  86%|████████▌ | 31454/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.88.up_proj:  86%|████████▌ | 31455/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.88.down_proj:  86%|████████▌ | 31456/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.89.gate_proj:  86%|████████▌ | 31457/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.89.up_proj:  86%|████████▌ | 31458/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.89.down_proj:  86%|████████▌ | 31459/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.90.gate_proj:  86%|████████▌ | 31460/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.90.up_proj:  86%|████████▌ | 31461/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.90.down_proj:  86%|████████▌ | 31462/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.91.gate_proj:  86%|████████▌ | 31463/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.91.up_proj:  86%|████████▌ | 31464/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.91.down_proj:  86%|████████▌ | 31465/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.92.gate_proj:  86%|████████▌ | 31466/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.92.up_proj:  86%|████████▌ | 31467/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.92.down_proj:  86%|████████▌ | 31468/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.93.gate_proj:  86%|████████▌ | 31469/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.93.up_proj:  86%|████████▌ | 31470/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.93.down_proj:  86%|████████▌ | 31471/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.94.gate_proj:  86%|████████▌ | 31472/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.94.up_proj:  86%|████████▌ | 31473/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.94.down_proj:  86%|████████▌ | 31474/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.95.gate_proj:  86%|████████▌ | 31475/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.95.up_proj:  86%|████████▌ | 31476/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.95.down_proj:  86%|████████▌ | 31477/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.96.gate_proj:  86%|████████▌ | 31478/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.96.up_proj:  86%|████████▌ | 31479/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.96.down_proj:  86%|████████▌ | 31480/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.97.gate_proj:  86%|████████▌ | 31481/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.97.up_proj:  86%|████████▌ | 31482/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.97.down_proj:  86%|████████▌ | 31483/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.98.gate_proj:  86%|████████▌ | 31484/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.98.up_proj:  86%|████████▌ | 31485/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.98.down_proj:  86%|████████▌ | 31486/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.99.gate_proj:  86%|████████▌ | 31487/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.99.up_proj:  86%|████████▌ | 31488/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.99.down_proj:  86%|████████▌ | 31489/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.100.gate_proj:  86%|████████▌ | 31490/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.100.up_proj:  86%|████████▌ | 31491/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.100.down_proj:  86%|████████▌ | 31492/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.101.gate_proj:  86%|████████▌ | 31493/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.101.up_proj:  86%|████████▌ | 31494/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.101.down_proj:  86%|████████▌ | 31495/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.102.gate_proj:  86%|████████▌ | 31496/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.102.up_proj:  86%|████████▌ | 31497/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.102.down_proj:  86%|████████▌ | 31498/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.103.gate_proj:  86%|████████▌ | 31499/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.103.up_proj:  86%|████████▌ | 31500/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.103.down_proj:  86%|████████▌ | 31501/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.104.gate_proj:  86%|████████▌ | 31502/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.104.up_proj:  86%|████████▌ | 31503/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.104.down_proj:  86%|████████▌ | 31504/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.105.gate_proj:  86%|████████▌ | 31505/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.105.up_proj:  86%|████████▌ | 31506/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.105.down_proj:  86%|████████▌ | 31507/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.106.gate_proj:  86%|████████▌ | 31508/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.106.up_proj:  86%|████████▌ | 31509/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.106.down_proj:  86%|████████▌ | 31510/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.107.gate_proj:  86%|████████▌ | 31511/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.107.up_proj:  86%|████████▌ | 31512/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.107.down_proj:  86%|████████▌ | 31513/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.108.gate_proj:  86%|████████▌ | 31514/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.108.up_proj:  86%|████████▌ | 31515/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.108.down_proj:  86%|████████▌ | 31516/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.109.gate_proj:  86%|████████▌ | 31517/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.109.up_proj:  86%|████████▌ | 31518/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.109.down_proj:  86%|████████▌ | 31519/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.110.gate_proj:  86%|████████▌ | 31520/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.110.up_proj:  86%|████████▌ | 31521/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.110.down_proj:  86%|████████▌ | 31522/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.111.gate_proj:  86%|████████▌ | 31523/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.111.up_proj:  86%|████████▌ | 31524/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.111.down_proj:  86%|████████▌ | 31525/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.112.gate_proj:  86%|████████▌ | 31526/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.112.up_proj:  86%|████████▌ | 31527/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.112.down_proj:  86%|████████▌ | 31528/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.113.gate_proj:  86%|████████▌ | 31529/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.113.up_proj:  86%|████████▌ | 31530/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.113.down_proj:  86%|████████▌ | 31531/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.114.gate_proj:  86%|████████▌ | 31532/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.114.up_proj:  86%|████████▌ | 31533/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.114.down_proj:  86%|████████▌ | 31534/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.115.gate_proj:  86%|████████▌ | 31535/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.115.up_proj:  86%|████████▌ | 31536/36566 [00:28<00:04, 1137.22it/s]  
packing model.layers.80.mlp.experts.115.down_proj:  86%|████████▌ | 31537/36566 [00:28<00:04, 1137.22it/s]
packing model.layers.80.mlp.experts.115.down_proj:  86%|████████▌ | 31538/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.116.gate_proj:  86%|████████▌ | 31538/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.116.up_proj:  86%|████████▋ | 31539/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.116.down_proj:  86%|████████▋ | 31540/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.117.gate_proj:  86%|████████▋ | 31541/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.117.up_proj:  86%|████████▋ | 31542/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.117.down_proj:  86%|████████▋ | 31543/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.118.gate_proj:  86%|████████▋ | 31544/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.118.up_proj:  86%|████████▋ | 31545/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.118.down_proj:  86%|████████▋ | 31546/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.119.gate_proj:  86%|████████▋ | 31547/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.119.up_proj:  86%|████████▋ | 31548/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.119.down_proj:  86%|████████▋ | 31549/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.120.gate_proj:  86%|████████▋ | 31550/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.120.up_proj:  86%|████████▋ | 31551/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.120.down_proj:  86%|████████▋ | 31552/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.121.gate_proj:  86%|████████▋ | 31553/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.121.up_proj:  86%|████████▋ | 31554/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.121.down_proj:  86%|████████▋ | 31555/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.122.gate_proj:  86%|████████▋ | 31556/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.122.up_proj:  86%|████████▋ | 31557/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.122.down_proj:  86%|████████▋ | 31558/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.123.gate_proj:  86%|████████▋ | 31559/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.123.up_proj:  86%|████████▋ | 31560/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.123.down_proj:  86%|████████▋ | 31561/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.124.gate_proj:  86%|████████▋ | 31562/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.124.up_proj:  86%|████████▋ | 31563/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.124.down_proj:  86%|████████▋ | 31564/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.125.gate_proj:  86%|████████▋ | 31565/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.125.up_proj:  86%|████████▋ | 31566/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.125.down_proj:  86%|████████▋ | 31567/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.126.gate_proj:  86%|████████▋ | 31568/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.126.up_proj:  86%|████████▋ | 31569/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.126.down_proj:  86%|████████▋ | 31570/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.127.gate_proj:  86%|████████▋ | 31571/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.80.mlp.experts.127.up_proj:  86%|████████▋ | 31572/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.80.mlp.experts.127.down_proj:  86%|████████▋ | 31573/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.0.gate_proj:  86%|████████▋ | 31574/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.0.up_proj:  86%|████████▋ | 31575/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.0.down_proj:  86%|████████▋ | 31576/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.1.gate_proj:  86%|████████▋ | 31577/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.1.up_proj:  86%|████████▋ | 31578/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.1.down_proj:  86%|████████▋ | 31579/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.2.gate_proj:  86%|████████▋ | 31580/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.2.up_proj:  86%|████████▋ | 31581/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.2.down_proj:  86%|████████▋ | 31582/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.3.gate_proj:  86%|████████▋ | 31583/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.3.up_proj:  86%|████████▋ | 31584/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.3.down_proj:  86%|████████▋ | 31585/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.4.gate_proj:  86%|████████▋ | 31586/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.4.up_proj:  86%|████████▋ | 31587/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.4.down_proj:  86%|████████▋ | 31588/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.5.gate_proj:  86%|████████▋ | 31589/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.5.up_proj:  86%|████████▋ | 31590/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.5.down_proj:  86%|████████▋ | 31591/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.6.gate_proj:  86%|████████▋ | 31592/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.6.up_proj:  86%|████████▋ | 31593/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.6.down_proj:  86%|████████▋ | 31594/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.7.gate_proj:  86%|████████▋ | 31595/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.7.up_proj:  86%|████████▋ | 31596/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.7.down_proj:  86%|████████▋ | 31597/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.8.gate_proj:  86%|████████▋ | 31598/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.8.up_proj:  86%|████████▋ | 31599/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.8.down_proj:  86%|████████▋ | 31600/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.9.gate_proj:  86%|████████▋ | 31601/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.9.up_proj:  86%|████████▋ | 31602/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.9.down_proj:  86%|████████▋ | 31603/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.10.gate_proj:  86%|████████▋ | 31604/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.10.up_proj:  86%|████████▋ | 31605/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.10.down_proj:  86%|████████▋ | 31606/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.11.gate_proj:  86%|████████▋ | 31607/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.11.up_proj:  86%|████████▋ | 31608/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.11.down_proj:  86%|████████▋ | 31609/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.12.gate_proj:  86%|████████▋ | 31610/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.12.up_proj:  86%|████████▋ | 31611/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.12.down_proj:  86%|████████▋ | 31612/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.13.gate_proj:  86%|████████▋ | 31613/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.13.up_proj:  86%|████████▋ | 31614/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.13.down_proj:  86%|████████▋ | 31615/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.14.gate_proj:  86%|████████▋ | 31616/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.14.up_proj:  86%|████████▋ | 31617/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.14.down_proj:  86%|████████▋ | 31618/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.15.gate_proj:  86%|████████▋ | 31619/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.15.up_proj:  86%|████████▋ | 31620/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.15.down_proj:  86%|████████▋ | 31621/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.16.gate_proj:  86%|████████▋ | 31622/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.16.up_proj:  86%|████████▋ | 31623/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.16.down_proj:  86%|████████▋ | 31624/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.17.gate_proj:  86%|████████▋ | 31625/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.17.up_proj:  86%|████████▋ | 31626/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.17.down_proj:  86%|████████▋ | 31627/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.18.gate_proj:  86%|████████▋ | 31628/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.18.up_proj:  86%|████████▋ | 31629/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.18.down_proj:  87%|████████▋ | 31630/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.19.gate_proj:  87%|████████▋ | 31631/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.19.up_proj:  87%|████████▋ | 31632/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.19.down_proj:  87%|████████▋ | 31633/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.20.gate_proj:  87%|████████▋ | 31634/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.20.up_proj:  87%|████████▋ | 31635/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.20.down_proj:  87%|████████▋ | 31636/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.21.gate_proj:  87%|████████▋ | 31637/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.21.up_proj:  87%|████████▋ | 31638/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.21.down_proj:  87%|████████▋ | 31639/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.22.gate_proj:  87%|████████▋ | 31640/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.22.up_proj:  87%|████████▋ | 31641/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.22.down_proj:  87%|████████▋ | 31642/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.23.gate_proj:  87%|████████▋ | 31643/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.23.up_proj:  87%|████████▋ | 31644/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.23.down_proj:  87%|████████▋ | 31645/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.24.gate_proj:  87%|████████▋ | 31646/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.24.up_proj:  87%|████████▋ | 31647/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.24.down_proj:  87%|████████▋ | 31648/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.25.gate_proj:  87%|████████▋ | 31649/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.25.up_proj:  87%|████████▋ | 31650/36566 [00:28<00:04, 1134.61it/s]  
packing model.layers.81.mlp.experts.25.down_proj:  87%|████████▋ | 31651/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.26.gate_proj:  87%|████████▋ | 31652/36566 [00:28<00:04, 1134.61it/s]
packing model.layers.81.mlp.experts.26.gate_proj:  87%|████████▋ | 31653/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.26.up_proj:  87%|████████▋ | 31653/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.26.down_proj:  87%|████████▋ | 31654/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.27.gate_proj:  87%|████████▋ | 31655/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.27.up_proj:  87%|████████▋ | 31656/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.27.down_proj:  87%|████████▋ | 31657/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.28.gate_proj:  87%|████████▋ | 31658/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.28.up_proj:  87%|████████▋ | 31659/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.28.down_proj:  87%|████████▋ | 31660/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.29.gate_proj:  87%|████████▋ | 31661/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.29.up_proj:  87%|████████▋ | 31662/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.29.down_proj:  87%|████████▋ | 31663/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.30.gate_proj:  87%|████████▋ | 31664/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.30.up_proj:  87%|████████▋ | 31665/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.30.down_proj:  87%|████████▋ | 31666/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.31.gate_proj:  87%|████████▋ | 31667/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.31.up_proj:  87%|████████▋ | 31668/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.31.down_proj:  87%|████████▋ | 31669/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.32.gate_proj:  87%|████████▋ | 31670/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.32.up_proj:  87%|████████▋ | 31671/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.32.down_proj:  87%|████████▋ | 31672/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.33.gate_proj:  87%|████████▋ | 31673/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.33.up_proj:  87%|████████▋ | 31674/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.33.down_proj:  87%|████████▋ | 31675/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.34.gate_proj:  87%|████████▋ | 31676/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.34.up_proj:  87%|████████▋ | 31677/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.34.down_proj:  87%|████████▋ | 31678/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.35.gate_proj:  87%|████████▋ | 31679/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.35.up_proj:  87%|████████▋ | 31680/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.35.down_proj:  87%|████████▋ | 31681/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.36.gate_proj:  87%|████████▋ | 31682/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.36.up_proj:  87%|████████▋ | 31683/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.36.down_proj:  87%|████████▋ | 31684/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.37.gate_proj:  87%|████████▋ | 31685/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.37.up_proj:  87%|████████▋ | 31686/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.37.down_proj:  87%|████████▋ | 31687/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.38.gate_proj:  87%|████████▋ | 31688/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.38.up_proj:  87%|████████▋ | 31689/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.38.down_proj:  87%|████████▋ | 31690/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.39.gate_proj:  87%|████████▋ | 31691/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.39.up_proj:  87%|████████▋ | 31692/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.39.down_proj:  87%|████████▋ | 31693/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.40.gate_proj:  87%|████████▋ | 31694/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.40.up_proj:  87%|████████▋ | 31695/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.40.down_proj:  87%|████████▋ | 31696/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.41.gate_proj:  87%|████████▋ | 31697/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.41.up_proj:  87%|████████▋ | 31698/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.41.down_proj:  87%|████████▋ | 31699/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.42.gate_proj:  87%|████████▋ | 31700/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.42.up_proj:  87%|████████▋ | 31701/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.42.down_proj:  87%|████████▋ | 31702/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.43.gate_proj:  87%|████████▋ | 31703/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.43.up_proj:  87%|████████▋ | 31704/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.43.down_proj:  87%|████████▋ | 31705/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.44.gate_proj:  87%|████████▋ | 31706/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.44.up_proj:  87%|████████▋ | 31707/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.44.down_proj:  87%|████████▋ | 31708/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.45.gate_proj:  87%|████████▋ | 31709/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.45.up_proj:  87%|████████▋ | 31710/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.45.down_proj:  87%|████████▋ | 31711/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.46.gate_proj:  87%|████████▋ | 31712/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.46.up_proj:  87%|████████▋ | 31713/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.46.down_proj:  87%|████████▋ | 31714/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.47.gate_proj:  87%|████████▋ | 31715/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.47.up_proj:  87%|████████▋ | 31716/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.47.down_proj:  87%|████████▋ | 31717/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.48.gate_proj:  87%|████████▋ | 31718/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.48.up_proj:  87%|████████▋ | 31719/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.48.down_proj:  87%|████████▋ | 31720/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.49.gate_proj:  87%|████████▋ | 31721/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.49.up_proj:  87%|████████▋ | 31722/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.49.down_proj:  87%|████████▋ | 31723/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.50.gate_proj:  87%|████████▋ | 31724/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.50.up_proj:  87%|████████▋ | 31725/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.50.down_proj:  87%|████████▋ | 31726/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.51.gate_proj:  87%|████████▋ | 31727/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.51.up_proj:  87%|████████▋ | 31728/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.51.down_proj:  87%|████████▋ | 31729/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.52.gate_proj:  87%|████████▋ | 31730/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.52.up_proj:  87%|████████▋ | 31731/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.52.down_proj:  87%|████████▋ | 31732/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.53.gate_proj:  87%|████████▋ | 31733/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.53.up_proj:  87%|████████▋ | 31734/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.53.down_proj:  87%|████████▋ | 31735/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.54.gate_proj:  87%|████████▋ | 31736/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.54.up_proj:  87%|████████▋ | 31737/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.54.down_proj:  87%|████████▋ | 31738/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.55.gate_proj:  87%|████████▋ | 31739/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.55.up_proj:  87%|████████▋ | 31740/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.55.down_proj:  87%|████████▋ | 31741/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.56.gate_proj:  87%|████████▋ | 31742/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.56.up_proj:  87%|████████▋ | 31743/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.56.down_proj:  87%|████████▋ | 31744/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.57.gate_proj:  87%|████████▋ | 31745/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.57.up_proj:  87%|████████▋ | 31746/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.57.down_proj:  87%|████████▋ | 31747/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.58.gate_proj:  87%|████████▋ | 31748/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.58.up_proj:  87%|████████▋ | 31749/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.58.down_proj:  87%|████████▋ | 31750/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.59.gate_proj:  87%|████████▋ | 31751/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.59.up_proj:  87%|████████▋ | 31752/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.59.down_proj:  87%|████████▋ | 31753/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.60.gate_proj:  87%|████████▋ | 31754/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.60.up_proj:  87%|████████▋ | 31755/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.60.down_proj:  87%|████████▋ | 31756/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.61.gate_proj:  87%|████████▋ | 31757/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.61.up_proj:  87%|████████▋ | 31758/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.61.down_proj:  87%|████████▋ | 31759/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.62.gate_proj:  87%|████████▋ | 31760/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.62.up_proj:  87%|████████▋ | 31761/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.62.down_proj:  87%|████████▋ | 31762/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.63.gate_proj:  87%|████████▋ | 31763/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.63.up_proj:  87%|████████▋ | 31764/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.63.down_proj:  87%|████████▋ | 31765/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.64.gate_proj:  87%|████████▋ | 31766/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.64.up_proj:  87%|████████▋ | 31767/36566 [00:28<00:04, 1138.58it/s]  
packing model.layers.81.mlp.experts.64.down_proj:  87%|████████▋ | 31768/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.65.gate_proj:  87%|████████▋ | 31769/36566 [00:28<00:04, 1138.58it/s]
packing model.layers.81.mlp.experts.65.gate_proj:  87%|████████▋ | 31770/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.65.up_proj:  87%|████████▋ | 31770/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.65.down_proj:  87%|████████▋ | 31771/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.66.gate_proj:  87%|████████▋ | 31772/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.66.up_proj:  87%|████████▋ | 31773/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.66.down_proj:  87%|████████▋ | 31774/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.67.gate_proj:  87%|████████▋ | 31775/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.67.up_proj:  87%|████████▋ | 31776/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.67.down_proj:  87%|████████▋ | 31777/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.68.gate_proj:  87%|████████▋ | 31778/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.68.up_proj:  87%|████████▋ | 31779/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.68.down_proj:  87%|████████▋ | 31780/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.69.gate_proj:  87%|████████▋ | 31781/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.69.up_proj:  87%|████████▋ | 31782/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.69.down_proj:  87%|████████▋ | 31783/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.70.gate_proj:  87%|████████▋ | 31784/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.70.up_proj:  87%|████████▋ | 31785/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.70.down_proj:  87%|████████▋ | 31786/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.71.gate_proj:  87%|████████▋ | 31787/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.71.up_proj:  87%|████████▋ | 31788/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.71.down_proj:  87%|████████▋ | 31789/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.72.gate_proj:  87%|████████▋ | 31790/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.72.up_proj:  87%|████████▋ | 31791/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.72.down_proj:  87%|████████▋ | 31792/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.73.gate_proj:  87%|████████▋ | 31793/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.73.up_proj:  87%|████████▋ | 31794/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.73.down_proj:  87%|████████▋ | 31795/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.74.gate_proj:  87%|████████▋ | 31796/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.74.up_proj:  87%|████████▋ | 31797/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.74.down_proj:  87%|████████▋ | 31798/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.75.gate_proj:  87%|████████▋ | 31799/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.75.up_proj:  87%|████████▋ | 31800/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.75.down_proj:  87%|████████▋ | 31801/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.76.gate_proj:  87%|████████▋ | 31802/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.76.up_proj:  87%|████████▋ | 31803/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.76.down_proj:  87%|████████▋ | 31804/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.77.gate_proj:  87%|████████▋ | 31805/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.77.up_proj:  87%|████████▋ | 31806/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.77.down_proj:  87%|████████▋ | 31807/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.78.gate_proj:  87%|████████▋ | 31808/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.78.up_proj:  87%|████████▋ | 31809/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.78.down_proj:  87%|████████▋ | 31810/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.79.gate_proj:  87%|████████▋ | 31811/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.79.up_proj:  87%|████████▋ | 31812/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.79.down_proj:  87%|████████▋ | 31813/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.80.gate_proj:  87%|████████▋ | 31814/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.80.up_proj:  87%|████████▋ | 31815/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.80.down_proj:  87%|████████▋ | 31816/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.81.gate_proj:  87%|████████▋ | 31817/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.81.up_proj:  87%|████████▋ | 31818/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.81.down_proj:  87%|████████▋ | 31819/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.82.gate_proj:  87%|████████▋ | 31820/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.82.up_proj:  87%|████████▋ | 31821/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.82.down_proj:  87%|████████▋ | 31822/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.83.gate_proj:  87%|████████▋ | 31823/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.83.up_proj:  87%|████████▋ | 31824/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.83.down_proj:  87%|████████▋ | 31825/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.84.gate_proj:  87%|████████▋ | 31826/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.84.up_proj:  87%|████████▋ | 31827/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.84.down_proj:  87%|████████▋ | 31828/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.85.gate_proj:  87%|████████▋ | 31829/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.85.up_proj:  87%|████████▋ | 31830/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.85.down_proj:  87%|████████▋ | 31831/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.86.gate_proj:  87%|████████▋ | 31832/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.86.up_proj:  87%|████████▋ | 31833/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.86.down_proj:  87%|████████▋ | 31834/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.87.gate_proj:  87%|████████▋ | 31835/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.87.up_proj:  87%|████████▋ | 31836/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.87.down_proj:  87%|████████▋ | 31837/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.88.gate_proj:  87%|████████▋ | 31838/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.88.up_proj:  87%|████████▋ | 31839/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.88.down_proj:  87%|████████▋ | 31840/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.89.gate_proj:  87%|████████▋ | 31841/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.89.up_proj:  87%|████████▋ | 31842/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.89.down_proj:  87%|████████▋ | 31843/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.90.gate_proj:  87%|████████▋ | 31844/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.90.up_proj:  87%|████████▋ | 31845/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.90.down_proj:  87%|████████▋ | 31846/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.91.gate_proj:  87%|████████▋ | 31847/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.91.up_proj:  87%|████████▋ | 31848/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.91.down_proj:  87%|████████▋ | 31849/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.92.gate_proj:  87%|████████▋ | 31850/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.92.up_proj:  87%|████████▋ | 31851/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.92.down_proj:  87%|████████▋ | 31852/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.93.gate_proj:  87%|████████▋ | 31853/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.93.up_proj:  87%|████████▋ | 31854/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.93.down_proj:  87%|████████▋ | 31855/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.94.gate_proj:  87%|████████▋ | 31856/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.94.up_proj:  87%|████████▋ | 31857/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.94.down_proj:  87%|████████▋ | 31858/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.95.gate_proj:  87%|████████▋ | 31859/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.95.up_proj:  87%|████████▋ | 31860/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.95.down_proj:  87%|████████▋ | 31861/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.96.gate_proj:  87%|████████▋ | 31862/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.96.up_proj:  87%|████████▋ | 31863/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.96.down_proj:  87%|████████▋ | 31864/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.97.gate_proj:  87%|████████▋ | 31865/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.97.up_proj:  87%|████████▋ | 31866/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.97.down_proj:  87%|████████▋ | 31867/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.98.gate_proj:  87%|████████▋ | 31868/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.98.up_proj:  87%|████████▋ | 31869/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.98.down_proj:  87%|████████▋ | 31870/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.99.gate_proj:  87%|████████▋ | 31871/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.99.up_proj:  87%|████████▋ | 31872/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.99.down_proj:  87%|████████▋ | 31873/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.100.gate_proj:  87%|████████▋ | 31874/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.100.up_proj:  87%|████████▋ | 31875/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.100.down_proj:  87%|████████▋ | 31876/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.101.gate_proj:  87%|████████▋ | 31877/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.101.up_proj:  87%|████████▋ | 31878/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.101.down_proj:  87%|████████▋ | 31879/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.102.gate_proj:  87%|████████▋ | 31880/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.102.up_proj:  87%|████████▋ | 31881/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.102.down_proj:  87%|████████▋ | 31882/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.103.gate_proj:  87%|████████▋ | 31883/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.103.up_proj:  87%|████████▋ | 31884/36566 [00:28<00:04, 1145.71it/s]  
packing model.layers.81.mlp.experts.103.down_proj:  87%|████████▋ | 31885/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.104.gate_proj:  87%|████████▋ | 31886/36566 [00:28<00:04, 1145.71it/s]
packing model.layers.81.mlp.experts.104.gate_proj:  87%|████████▋ | 31887/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.104.up_proj:  87%|████████▋ | 31887/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.104.down_proj:  87%|████████▋ | 31888/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.105.gate_proj:  87%|████████▋ | 31889/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.105.up_proj:  87%|████████▋ | 31890/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.105.down_proj:  87%|████████▋ | 31891/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.106.gate_proj:  87%|████████▋ | 31892/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.106.up_proj:  87%|████████▋ | 31893/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.106.down_proj:  87%|████████▋ | 31894/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.107.gate_proj:  87%|████████▋ | 31895/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.107.up_proj:  87%|████████▋ | 31896/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.107.down_proj:  87%|████████▋ | 31897/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.108.gate_proj:  87%|████████▋ | 31898/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.108.up_proj:  87%|████████▋ | 31899/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.108.down_proj:  87%|████████▋ | 31900/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.109.gate_proj:  87%|████████▋ | 31901/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.109.up_proj:  87%|████████▋ | 31902/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.109.down_proj:  87%|████████▋ | 31903/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.110.gate_proj:  87%|████████▋ | 31904/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.110.up_proj:  87%|████████▋ | 31905/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.110.down_proj:  87%|████████▋ | 31906/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.111.gate_proj:  87%|████████▋ | 31907/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.111.up_proj:  87%|████████▋ | 31908/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.111.down_proj:  87%|████████▋ | 31909/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.112.gate_proj:  87%|████████▋ | 31910/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.112.up_proj:  87%|████████▋ | 31911/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.112.down_proj:  87%|████████▋ | 31912/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.113.gate_proj:  87%|████████▋ | 31913/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.113.up_proj:  87%|████████▋ | 31914/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.113.down_proj:  87%|████████▋ | 31915/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.114.gate_proj:  87%|████████▋ | 31916/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.114.up_proj:  87%|████████▋ | 31917/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.114.down_proj:  87%|████████▋ | 31918/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.115.gate_proj:  87%|████████▋ | 31919/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.115.up_proj:  87%|████████▋ | 31920/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.115.down_proj:  87%|████████▋ | 31921/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.116.gate_proj:  87%|████████▋ | 31922/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.116.up_proj:  87%|████████▋ | 31923/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.116.down_proj:  87%|████████▋ | 31924/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.117.gate_proj:  87%|████████▋ | 31925/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.117.up_proj:  87%|████████▋ | 31926/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.117.down_proj:  87%|████████▋ | 31927/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.118.gate_proj:  87%|████████▋ | 31928/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.118.up_proj:  87%|████████▋ | 31929/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.118.down_proj:  87%|████████▋ | 31930/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.119.gate_proj:  87%|████████▋ | 31931/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.119.up_proj:  87%|████████▋ | 31932/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.119.down_proj:  87%|████████▋ | 31933/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.120.gate_proj:  87%|████████▋ | 31934/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.120.up_proj:  87%|████████▋ | 31935/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.120.down_proj:  87%|████████▋ | 31936/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.121.gate_proj:  87%|████████▋ | 31937/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.121.up_proj:  87%|████████▋ | 31938/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.121.down_proj:  87%|████████▋ | 31939/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.122.gate_proj:  87%|████████▋ | 31940/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.122.up_proj:  87%|████████▋ | 31941/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.122.down_proj:  87%|████████▋ | 31942/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.123.gate_proj:  87%|████████▋ | 31943/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.123.up_proj:  87%|████████▋ | 31944/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.123.down_proj:  87%|████████▋ | 31945/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.124.gate_proj:  87%|████████▋ | 31946/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.124.up_proj:  87%|████████▋ | 31947/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.124.down_proj:  87%|████████▋ | 31948/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.125.gate_proj:  87%|████████▋ | 31949/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.125.up_proj:  87%|████████▋ | 31950/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.125.down_proj:  87%|████████▋ | 31951/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.126.gate_proj:  87%|████████▋ | 31952/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.126.up_proj:  87%|████████▋ | 31953/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.126.down_proj:  87%|████████▋ | 31954/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.127.gate_proj:  87%|████████▋ | 31955/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.81.mlp.experts.127.up_proj:  87%|████████▋ | 31956/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.81.mlp.experts.127.down_proj:  87%|████████▋ | 31957/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.82.mlp.experts.0.gate_proj:  87%|████████▋ | 31958/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.82.mlp.experts.0.up_proj:  87%|████████▋ | 31959/36566 [00:28<00:04, 1151.01it/s]  
packing model.layers.82.mlp.experts.0.down_proj:  87%|████████▋ | 31960/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.82.mlp.experts.1.gate_proj:  87%|████████▋ | 31961/36566 [00:28<00:04, 1151.01it/s]
packing model.layers.82.mlp.experts.1.up_proj:  87%|████████▋ | 31962/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.1.down_proj:  87%|████████▋ | 31963/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.2.gate_proj:  87%|████████▋ | 31964/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.2.up_proj:  87%|████████▋ | 31965/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.2.down_proj:  87%|████████▋ | 31966/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.3.gate_proj:  87%|████████▋ | 31967/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.3.up_proj:  87%|████████▋ | 31968/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.3.down_proj:  87%|████████▋ | 31969/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.4.gate_proj:  87%|████████▋ | 31970/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.4.up_proj:  87%|████████▋ | 31971/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.4.down_proj:  87%|████████▋ | 31972/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.5.gate_proj:  87%|████████▋ | 31973/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.5.up_proj:  87%|████████▋ | 31974/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.5.down_proj:  87%|████████▋ | 31975/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.6.gate_proj:  87%|████████▋ | 31976/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.6.up_proj:  87%|████████▋ | 31977/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.6.down_proj:  87%|████████▋ | 31978/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.7.gate_proj:  87%|████████▋ | 31979/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.7.up_proj:  87%|████████▋ | 31980/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.7.down_proj:  87%|████████▋ | 31981/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.8.gate_proj:  87%|████████▋ | 31982/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.8.up_proj:  87%|████████▋ | 31983/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.8.down_proj:  87%|████████▋ | 31984/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.9.gate_proj:  87%|████████▋ | 31985/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.9.up_proj:  87%|████████▋ | 31986/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.9.down_proj:  87%|████████▋ | 31987/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.10.gate_proj:  87%|████████▋ | 31988/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.10.up_proj:  87%|████████▋ | 31989/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.10.down_proj:  87%|████████▋ | 31990/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.11.gate_proj:  87%|████████▋ | 31991/36566 [00:28<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.11.up_proj:  87%|████████▋ | 31992/36566 [00:28<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.11.down_proj:  87%|████████▋ | 31993/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.12.gate_proj:  87%|████████▋ | 31994/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.12.up_proj:  87%|████████▋ | 31995/36566 [00:29<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.12.down_proj:  88%|████████▊ | 31996/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.13.gate_proj:  88%|████████▊ | 31997/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.13.up_proj:  88%|████████▊ | 31998/36566 [00:29<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.13.down_proj:  88%|████████▊ | 31999/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.14.gate_proj:  88%|████████▊ | 32000/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.14.up_proj:  88%|████████▊ | 32001/36566 [00:29<00:03, 1151.01it/s]  
packing model.layers.82.mlp.experts.14.down_proj:  88%|████████▊ | 32002/36566 [00:29<00:03, 1151.01it/s]
packing model.layers.82.mlp.experts.14.down_proj:  88%|████████▊ | 32003/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.15.gate_proj:  88%|████████▊ | 32003/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.15.up_proj:  88%|████████▊ | 32004/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.15.down_proj:  88%|████████▊ | 32005/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.16.gate_proj:  88%|████████▊ | 32006/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.16.up_proj:  88%|████████▊ | 32007/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.16.down_proj:  88%|████████▊ | 32008/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.17.gate_proj:  88%|████████▊ | 32009/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.17.up_proj:  88%|████████▊ | 32010/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.17.down_proj:  88%|████████▊ | 32011/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.18.gate_proj:  88%|████████▊ | 32012/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.18.up_proj:  88%|████████▊ | 32013/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.18.down_proj:  88%|████████▊ | 32014/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.19.gate_proj:  88%|████████▊ | 32015/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.19.up_proj:  88%|████████▊ | 32016/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.19.down_proj:  88%|████████▊ | 32017/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.20.gate_proj:  88%|████████▊ | 32018/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.20.up_proj:  88%|████████▊ | 32019/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.20.down_proj:  88%|████████▊ | 32020/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.21.gate_proj:  88%|████████▊ | 32021/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.21.up_proj:  88%|████████▊ | 32022/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.21.down_proj:  88%|████████▊ | 32023/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.22.gate_proj:  88%|████████▊ | 32024/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.22.up_proj:  88%|████████▊ | 32025/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.22.down_proj:  88%|████████▊ | 32026/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.23.gate_proj:  88%|████████▊ | 32027/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.23.up_proj:  88%|████████▊ | 32028/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.23.down_proj:  88%|████████▊ | 32029/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.24.gate_proj:  88%|████████▊ | 32030/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.24.up_proj:  88%|████████▊ | 32031/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.24.down_proj:  88%|████████▊ | 32032/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.25.gate_proj:  88%|████████▊ | 32033/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.25.up_proj:  88%|████████▊ | 32034/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.25.down_proj:  88%|████████▊ | 32035/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.26.gate_proj:  88%|████████▊ | 32036/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.26.up_proj:  88%|████████▊ | 32037/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.26.down_proj:  88%|████████▊ | 32038/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.27.gate_proj:  88%|████████▊ | 32039/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.27.up_proj:  88%|████████▊ | 32040/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.27.down_proj:  88%|████████▊ | 32041/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.28.gate_proj:  88%|████████▊ | 32042/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.28.up_proj:  88%|████████▊ | 32043/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.28.down_proj:  88%|████████▊ | 32044/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.29.gate_proj:  88%|████████▊ | 32045/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.29.up_proj:  88%|████████▊ | 32046/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.29.down_proj:  88%|████████▊ | 32047/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.30.gate_proj:  88%|████████▊ | 32048/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.30.up_proj:  88%|████████▊ | 32049/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.30.down_proj:  88%|████████▊ | 32050/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.31.gate_proj:  88%|████████▊ | 32051/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.31.up_proj:  88%|████████▊ | 32052/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.31.down_proj:  88%|████████▊ | 32053/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.32.gate_proj:  88%|████████▊ | 32054/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.32.up_proj:  88%|████████▊ | 32055/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.32.down_proj:  88%|████████▊ | 32056/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.33.gate_proj:  88%|████████▊ | 32057/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.33.up_proj:  88%|████████▊ | 32058/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.33.down_proj:  88%|████████▊ | 32059/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.34.gate_proj:  88%|████████▊ | 32060/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.34.up_proj:  88%|████████▊ | 32061/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.34.down_proj:  88%|████████▊ | 32062/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.35.gate_proj:  88%|████████▊ | 32063/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.35.up_proj:  88%|████████▊ | 32064/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.35.down_proj:  88%|████████▊ | 32065/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.36.gate_proj:  88%|████████▊ | 32066/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.36.up_proj:  88%|████████▊ | 32067/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.36.down_proj:  88%|████████▊ | 32068/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.37.gate_proj:  88%|████████▊ | 32069/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.37.up_proj:  88%|████████▊ | 32070/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.37.down_proj:  88%|████████▊ | 32071/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.38.gate_proj:  88%|████████▊ | 32072/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.38.up_proj:  88%|████████▊ | 32073/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.38.down_proj:  88%|████████▊ | 32074/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.39.gate_proj:  88%|████████▊ | 32075/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.39.up_proj:  88%|████████▊ | 32076/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.39.down_proj:  88%|████████▊ | 32077/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.40.gate_proj:  88%|████████▊ | 32078/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.40.up_proj:  88%|████████▊ | 32079/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.40.down_proj:  88%|████████▊ | 32080/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.41.gate_proj:  88%|████████▊ | 32081/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.41.up_proj:  88%|████████▊ | 32082/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.41.down_proj:  88%|████████▊ | 32083/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.42.gate_proj:  88%|████████▊ | 32084/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.42.up_proj:  88%|████████▊ | 32085/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.42.down_proj:  88%|████████▊ | 32086/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.43.gate_proj:  88%|████████▊ | 32087/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.43.up_proj:  88%|████████▊ | 32088/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.43.down_proj:  88%|████████▊ | 32089/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.44.gate_proj:  88%|████████▊ | 32090/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.44.up_proj:  88%|████████▊ | 32091/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.44.down_proj:  88%|████████▊ | 32092/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.45.gate_proj:  88%|████████▊ | 32093/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.45.up_proj:  88%|████████▊ | 32094/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.45.down_proj:  88%|████████▊ | 32095/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.46.gate_proj:  88%|████████▊ | 32096/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.46.up_proj:  88%|████████▊ | 32097/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.46.down_proj:  88%|████████▊ | 32098/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.47.gate_proj:  88%|████████▊ | 32099/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.47.up_proj:  88%|████████▊ | 32100/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.47.down_proj:  88%|████████▊ | 32101/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.48.gate_proj:  88%|████████▊ | 32102/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.48.up_proj:  88%|████████▊ | 32103/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.48.down_proj:  88%|████████▊ | 32104/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.49.gate_proj:  88%|████████▊ | 32105/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.49.up_proj:  88%|████████▊ | 32106/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.49.down_proj:  88%|████████▊ | 32107/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.50.gate_proj:  88%|████████▊ | 32108/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.50.up_proj:  88%|████████▊ | 32109/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.50.down_proj:  88%|████████▊ | 32110/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.51.gate_proj:  88%|████████▊ | 32111/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.51.up_proj:  88%|████████▊ | 32112/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.51.down_proj:  88%|████████▊ | 32113/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.52.gate_proj:  88%|████████▊ | 32114/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.52.up_proj:  88%|████████▊ | 32115/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.52.down_proj:  88%|████████▊ | 32116/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.53.gate_proj:  88%|████████▊ | 32117/36566 [00:29<00:03, 1148.80it/s]
packing model.layers.82.mlp.experts.53.up_proj:  88%|████████▊ | 32118/36566 [00:29<00:03, 1148.80it/s]  
packing model.layers.82.mlp.experts.53.up_proj:  88%|████████▊ | 32119/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.53.down_proj:  88%|████████▊ | 32119/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.54.gate_proj:  88%|████████▊ | 32120/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.54.up_proj:  88%|████████▊ | 32121/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.54.down_proj:  88%|████████▊ | 32122/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.55.gate_proj:  88%|████████▊ | 32123/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.55.up_proj:  88%|████████▊ | 32124/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.55.down_proj:  88%|████████▊ | 32125/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.56.gate_proj:  88%|████████▊ | 32126/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.56.up_proj:  88%|████████▊ | 32127/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.56.down_proj:  88%|████████▊ | 32128/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.57.gate_proj:  88%|████████▊ | 32129/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.57.up_proj:  88%|████████▊ | 32130/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.57.down_proj:  88%|████████▊ | 32131/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.58.gate_proj:  88%|████████▊ | 32132/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.58.up_proj:  88%|████████▊ | 32133/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.58.down_proj:  88%|████████▊ | 32134/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.59.gate_proj:  88%|████████▊ | 32135/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.59.up_proj:  88%|████████▊ | 32136/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.59.down_proj:  88%|████████▊ | 32137/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.60.gate_proj:  88%|████████▊ | 32138/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.60.up_proj:  88%|████████▊ | 32139/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.60.down_proj:  88%|████████▊ | 32140/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.61.gate_proj:  88%|████████▊ | 32141/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.61.up_proj:  88%|████████▊ | 32142/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.61.down_proj:  88%|████████▊ | 32143/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.62.gate_proj:  88%|████████▊ | 32144/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.62.up_proj:  88%|████████▊ | 32145/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.62.down_proj:  88%|████████▊ | 32146/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.63.gate_proj:  88%|████████▊ | 32147/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.63.up_proj:  88%|████████▊ | 32148/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.63.down_proj:  88%|████████▊ | 32149/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.64.gate_proj:  88%|████████▊ | 32150/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.64.up_proj:  88%|████████▊ | 32151/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.64.down_proj:  88%|████████▊ | 32152/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.65.gate_proj:  88%|████████▊ | 32153/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.65.up_proj:  88%|████████▊ | 32154/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.65.down_proj:  88%|████████▊ | 32155/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.66.gate_proj:  88%|████████▊ | 32156/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.66.up_proj:  88%|████████▊ | 32157/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.66.down_proj:  88%|████████▊ | 32158/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.67.gate_proj:  88%|████████▊ | 32159/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.67.up_proj:  88%|████████▊ | 32160/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.67.down_proj:  88%|████████▊ | 32161/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.68.gate_proj:  88%|████████▊ | 32162/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.68.up_proj:  88%|████████▊ | 32163/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.68.down_proj:  88%|████████▊ | 32164/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.69.gate_proj:  88%|████████▊ | 32165/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.69.up_proj:  88%|████████▊ | 32166/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.69.down_proj:  88%|████████▊ | 32167/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.70.gate_proj:  88%|████████▊ | 32168/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.70.up_proj:  88%|████████▊ | 32169/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.70.down_proj:  88%|████████▊ | 32170/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.71.gate_proj:  88%|████████▊ | 32171/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.71.up_proj:  88%|████████▊ | 32172/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.71.down_proj:  88%|████████▊ | 32173/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.72.gate_proj:  88%|████████▊ | 32174/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.72.up_proj:  88%|████████▊ | 32175/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.72.down_proj:  88%|████████▊ | 32176/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.73.gate_proj:  88%|████████▊ | 32177/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.73.up_proj:  88%|████████▊ | 32178/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.73.down_proj:  88%|████████▊ | 32179/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.74.gate_proj:  88%|████████▊ | 32180/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.74.up_proj:  88%|████████▊ | 32181/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.74.down_proj:  88%|████████▊ | 32182/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.75.gate_proj:  88%|████████▊ | 32183/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.75.up_proj:  88%|████████▊ | 32184/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.75.down_proj:  88%|████████▊ | 32185/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.76.gate_proj:  88%|████████▊ | 32186/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.76.up_proj:  88%|████████▊ | 32187/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.76.down_proj:  88%|████████▊ | 32188/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.77.gate_proj:  88%|████████▊ | 32189/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.77.up_proj:  88%|████████▊ | 32190/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.77.down_proj:  88%|████████▊ | 32191/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.78.gate_proj:  88%|████████▊ | 32192/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.78.up_proj:  88%|████████▊ | 32193/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.78.down_proj:  88%|████████▊ | 32194/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.79.gate_proj:  88%|████████▊ | 32195/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.79.up_proj:  88%|████████▊ | 32196/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.79.down_proj:  88%|████████▊ | 32197/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.80.gate_proj:  88%|████████▊ | 32198/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.80.up_proj:  88%|████████▊ | 32199/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.80.down_proj:  88%|████████▊ | 32200/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.81.gate_proj:  88%|████████▊ | 32201/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.81.up_proj:  88%|████████▊ | 32202/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.81.down_proj:  88%|████████▊ | 32203/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.82.gate_proj:  88%|████████▊ | 32204/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.82.up_proj:  88%|████████▊ | 32205/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.82.down_proj:  88%|████████▊ | 32206/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.83.gate_proj:  88%|████████▊ | 32207/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.83.up_proj:  88%|████████▊ | 32208/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.83.down_proj:  88%|████████▊ | 32209/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.84.gate_proj:  88%|████████▊ | 32210/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.84.up_proj:  88%|████████▊ | 32211/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.84.down_proj:  88%|████████▊ | 32212/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.85.gate_proj:  88%|████████▊ | 32213/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.85.up_proj:  88%|████████▊ | 32214/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.85.down_proj:  88%|████████▊ | 32215/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.86.gate_proj:  88%|████████▊ | 32216/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.86.up_proj:  88%|████████▊ | 32217/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.86.down_proj:  88%|████████▊ | 32218/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.87.gate_proj:  88%|████████▊ | 32219/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.87.up_proj:  88%|████████▊ | 32220/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.87.down_proj:  88%|████████▊ | 32221/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.88.gate_proj:  88%|████████▊ | 32222/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.88.up_proj:  88%|████████▊ | 32223/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.88.down_proj:  88%|████████▊ | 32224/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.89.gate_proj:  88%|████████▊ | 32225/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.89.up_proj:  88%|████████▊ | 32226/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.89.down_proj:  88%|████████▊ | 32227/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.90.gate_proj:  88%|████████▊ | 32228/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.90.up_proj:  88%|████████▊ | 32229/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.90.down_proj:  88%|████████▊ | 32230/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.91.gate_proj:  88%|████████▊ | 32231/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.91.up_proj:  88%|████████▊ | 32232/36566 [00:29<00:03, 1149.69it/s]  
packing model.layers.82.mlp.experts.91.down_proj:  88%|████████▊ | 32233/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.92.gate_proj:  88%|████████▊ | 32234/36566 [00:29<00:03, 1149.69it/s]
packing model.layers.82.mlp.experts.92.gate_proj:  88%|████████▊ | 32235/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.92.up_proj:  88%|████████▊ | 32235/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.92.down_proj:  88%|████████▊ | 32236/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.93.gate_proj:  88%|████████▊ | 32237/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.93.up_proj:  88%|████████▊ | 32238/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.93.down_proj:  88%|████████▊ | 32239/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.94.gate_proj:  88%|████████▊ | 32240/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.94.up_proj:  88%|████████▊ | 32241/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.94.down_proj:  88%|████████▊ | 32242/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.95.gate_proj:  88%|████████▊ | 32243/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.95.up_proj:  88%|████████▊ | 32244/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.95.down_proj:  88%|████████▊ | 32245/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.96.gate_proj:  88%|████████▊ | 32246/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.96.up_proj:  88%|████████▊ | 32247/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.96.down_proj:  88%|████████▊ | 32248/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.97.gate_proj:  88%|████████▊ | 32249/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.97.up_proj:  88%|████████▊ | 32250/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.97.down_proj:  88%|████████▊ | 32251/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.98.gate_proj:  88%|████████▊ | 32252/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.98.up_proj:  88%|████████▊ | 32253/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.98.down_proj:  88%|████████▊ | 32254/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.99.gate_proj:  88%|████████▊ | 32255/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.99.up_proj:  88%|████████▊ | 32256/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.99.down_proj:  88%|████████▊ | 32257/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.100.gate_proj:  88%|████████▊ | 32258/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.100.up_proj:  88%|████████▊ | 32259/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.100.down_proj:  88%|████████▊ | 32260/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.101.gate_proj:  88%|████████▊ | 32261/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.101.up_proj:  88%|████████▊ | 32262/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.101.down_proj:  88%|████████▊ | 32263/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.102.gate_proj:  88%|████████▊ | 32264/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.102.up_proj:  88%|████████▊ | 32265/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.102.down_proj:  88%|████████▊ | 32266/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.103.gate_proj:  88%|████████▊ | 32267/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.103.up_proj:  88%|████████▊ | 32268/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.103.down_proj:  88%|████████▊ | 32269/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.104.gate_proj:  88%|████████▊ | 32270/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.104.up_proj:  88%|████████▊ | 32271/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.104.down_proj:  88%|████████▊ | 32272/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.105.gate_proj:  88%|████████▊ | 32273/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.105.up_proj:  88%|████████▊ | 32274/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.105.down_proj:  88%|████████▊ | 32275/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.106.gate_proj:  88%|████████▊ | 32276/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.106.up_proj:  88%|████████▊ | 32277/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.106.down_proj:  88%|████████▊ | 32278/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.107.gate_proj:  88%|████████▊ | 32279/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.107.up_proj:  88%|████████▊ | 32280/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.107.down_proj:  88%|████████▊ | 32281/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.108.gate_proj:  88%|████████▊ | 32282/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.108.up_proj:  88%|████████▊ | 32283/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.108.down_proj:  88%|████████▊ | 32284/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.109.gate_proj:  88%|████████▊ | 32285/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.109.up_proj:  88%|████████▊ | 32286/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.109.down_proj:  88%|████████▊ | 32287/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.110.gate_proj:  88%|████████▊ | 32288/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.110.up_proj:  88%|████████▊ | 32289/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.110.down_proj:  88%|████████▊ | 32290/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.111.gate_proj:  88%|████████▊ | 32291/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.111.up_proj:  88%|████████▊ | 32292/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.111.down_proj:  88%|████████▊ | 32293/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.112.gate_proj:  88%|████████▊ | 32294/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.112.up_proj:  88%|████████▊ | 32295/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.112.down_proj:  88%|████████▊ | 32296/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.113.gate_proj:  88%|████████▊ | 32297/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.113.up_proj:  88%|████████▊ | 32298/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.113.down_proj:  88%|████████▊ | 32299/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.114.gate_proj:  88%|████████▊ | 32300/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.114.up_proj:  88%|████████▊ | 32301/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.114.down_proj:  88%|████████▊ | 32302/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.115.gate_proj:  88%|████████▊ | 32303/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.115.up_proj:  88%|████████▊ | 32304/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.115.down_proj:  88%|████████▊ | 32305/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.116.gate_proj:  88%|████████▊ | 32306/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.116.up_proj:  88%|████████▊ | 32307/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.116.down_proj:  88%|████████▊ | 32308/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.117.gate_proj:  88%|████████▊ | 32309/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.117.up_proj:  88%|████████▊ | 32310/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.117.down_proj:  88%|████████▊ | 32311/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.118.gate_proj:  88%|████████▊ | 32312/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.118.up_proj:  88%|████████▊ | 32313/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.118.down_proj:  88%|████████▊ | 32314/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.119.gate_proj:  88%|████████▊ | 32315/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.119.up_proj:  88%|████████▊ | 32316/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.119.down_proj:  88%|████████▊ | 32317/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.120.gate_proj:  88%|████████▊ | 32318/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.120.up_proj:  88%|████████▊ | 32319/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.120.down_proj:  88%|████████▊ | 32320/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.121.gate_proj:  88%|████████▊ | 32321/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.121.up_proj:  88%|████████▊ | 32322/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.121.down_proj:  88%|████████▊ | 32323/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.122.gate_proj:  88%|████████▊ | 32324/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.122.up_proj:  88%|████████▊ | 32325/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.122.down_proj:  88%|████████▊ | 32326/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.123.gate_proj:  88%|████████▊ | 32327/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.123.up_proj:  88%|████████▊ | 32328/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.123.down_proj:  88%|████████▊ | 32329/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.124.gate_proj:  88%|████████▊ | 32330/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.124.up_proj:  88%|████████▊ | 32331/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.124.down_proj:  88%|████████▊ | 32332/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.125.gate_proj:  88%|████████▊ | 32333/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.125.up_proj:  88%|████████▊ | 32334/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.125.down_proj:  88%|████████▊ | 32335/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.126.gate_proj:  88%|████████▊ | 32336/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.126.up_proj:  88%|████████▊ | 32337/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.126.down_proj:  88%|████████▊ | 32338/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.127.gate_proj:  88%|████████▊ | 32339/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.82.mlp.experts.127.up_proj:  88%|████████▊ | 32340/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.82.mlp.experts.127.down_proj:  88%|████████▊ | 32341/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.0.gate_proj:  88%|████████▊ | 32342/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.83.mlp.experts.0.up_proj:  88%|████████▊ | 32343/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.83.mlp.experts.0.down_proj:  88%|████████▊ | 32344/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.1.gate_proj:  88%|████████▊ | 32345/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.1.up_proj:  88%|████████▊ | 32346/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.83.mlp.experts.1.down_proj:  88%|████████▊ | 32347/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.2.gate_proj:  88%|████████▊ | 32348/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.2.up_proj:  88%|████████▊ | 32349/36566 [00:29<00:03, 1151.32it/s]  
packing model.layers.83.mlp.experts.2.down_proj:  88%|████████▊ | 32350/36566 [00:29<00:03, 1151.32it/s]
packing model.layers.83.mlp.experts.2.down_proj:  88%|████████▊ | 32351/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.3.gate_proj:  88%|████████▊ | 32351/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.3.up_proj:  88%|████████▊ | 32352/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.3.down_proj:  88%|████████▊ | 32353/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.4.gate_proj:  88%|████████▊ | 32354/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.4.up_proj:  88%|████████▊ | 32355/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.4.down_proj:  88%|████████▊ | 32356/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.5.gate_proj:  88%|████████▊ | 32357/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.5.up_proj:  88%|████████▊ | 32358/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.5.down_proj:  88%|████████▊ | 32359/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.6.gate_proj:  88%|████████▊ | 32360/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.6.up_proj:  89%|████████▊ | 32361/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.6.down_proj:  89%|████████▊ | 32362/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.7.gate_proj:  89%|████████▊ | 32363/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.7.up_proj:  89%|████████▊ | 32364/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.7.down_proj:  89%|████████▊ | 32365/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.8.gate_proj:  89%|████████▊ | 32366/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.8.up_proj:  89%|████████▊ | 32367/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.8.down_proj:  89%|████████▊ | 32368/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.9.gate_proj:  89%|████████▊ | 32369/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.9.up_proj:  89%|████████▊ | 32370/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.9.down_proj:  89%|████████▊ | 32371/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.10.gate_proj:  89%|████████▊ | 32372/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.10.up_proj:  89%|████████▊ | 32373/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.10.down_proj:  89%|████████▊ | 32374/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.11.gate_proj:  89%|████████▊ | 32375/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.11.up_proj:  89%|████████▊ | 32376/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.11.down_proj:  89%|████████▊ | 32377/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.12.gate_proj:  89%|████████▊ | 32378/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.12.up_proj:  89%|████████▊ | 32379/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.12.down_proj:  89%|████████▊ | 32380/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.13.gate_proj:  89%|████████▊ | 32381/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.13.up_proj:  89%|████████▊ | 32382/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.13.down_proj:  89%|████████▊ | 32383/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.14.gate_proj:  89%|████████▊ | 32384/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.14.up_proj:  89%|████████▊ | 32385/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.14.down_proj:  89%|████████▊ | 32386/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.15.gate_proj:  89%|████████▊ | 32387/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.15.up_proj:  89%|████████▊ | 32388/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.15.down_proj:  89%|████████▊ | 32389/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.16.gate_proj:  89%|████████▊ | 32390/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.16.up_proj:  89%|████████▊ | 32391/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.16.down_proj:  89%|████████▊ | 32392/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.17.gate_proj:  89%|████████▊ | 32393/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.17.up_proj:  89%|████████▊ | 32394/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.17.down_proj:  89%|████████▊ | 32395/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.18.gate_proj:  89%|████████▊ | 32396/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.18.up_proj:  89%|████████▊ | 32397/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.18.down_proj:  89%|████████▊ | 32398/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.19.gate_proj:  89%|████████▊ | 32399/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.19.up_proj:  89%|████████▊ | 32400/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.19.down_proj:  89%|████████▊ | 32401/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.20.gate_proj:  89%|████████▊ | 32402/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.20.up_proj:  89%|████████▊ | 32403/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.20.down_proj:  89%|████████▊ | 32404/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.21.gate_proj:  89%|████████▊ | 32405/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.21.up_proj:  89%|████████▊ | 32406/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.21.down_proj:  89%|████████▊ | 32407/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.22.gate_proj:  89%|████████▊ | 32408/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.22.up_proj:  89%|████████▊ | 32409/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.22.down_proj:  89%|████████▊ | 32410/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.23.gate_proj:  89%|████████▊ | 32411/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.23.up_proj:  89%|████████▊ | 32412/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.23.down_proj:  89%|████████▊ | 32413/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.24.gate_proj:  89%|████████▊ | 32414/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.24.up_proj:  89%|████████▊ | 32415/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.24.down_proj:  89%|████████▊ | 32416/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.25.gate_proj:  89%|████████▊ | 32417/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.25.up_proj:  89%|████████▊ | 32418/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.25.down_proj:  89%|████████▊ | 32419/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.26.gate_proj:  89%|████████▊ | 32420/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.26.up_proj:  89%|████████▊ | 32421/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.26.down_proj:  89%|████████▊ | 32422/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.27.gate_proj:  89%|████████▊ | 32423/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.27.up_proj:  89%|████████▊ | 32424/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.27.down_proj:  89%|████████▊ | 32425/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.28.gate_proj:  89%|████████▊ | 32426/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.28.up_proj:  89%|████████▊ | 32427/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.28.down_proj:  89%|████████▊ | 32428/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.29.gate_proj:  89%|████████▊ | 32429/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.29.up_proj:  89%|████████▊ | 32430/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.29.down_proj:  89%|████████▊ | 32431/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.30.gate_proj:  89%|████████▊ | 32432/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.30.up_proj:  89%|████████▊ | 32433/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.30.down_proj:  89%|████████▊ | 32434/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.31.gate_proj:  89%|████████▊ | 32435/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.31.up_proj:  89%|████████▊ | 32436/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.31.down_proj:  89%|████████▊ | 32437/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.32.gate_proj:  89%|████████▊ | 32438/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.32.up_proj:  89%|████████▊ | 32439/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.32.down_proj:  89%|████████▊ | 32440/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.33.gate_proj:  89%|████████▊ | 32441/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.33.up_proj:  89%|████████▊ | 32442/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.33.down_proj:  89%|████████▊ | 32443/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.34.gate_proj:  89%|████████▊ | 32444/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.34.up_proj:  89%|████████▊ | 32445/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.34.down_proj:  89%|████████▊ | 32446/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.35.gate_proj:  89%|████████▊ | 32447/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.35.up_proj:  89%|████████▊ | 32448/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.35.down_proj:  89%|████████▊ | 32449/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.36.gate_proj:  89%|████████▊ | 32450/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.36.up_proj:  89%|████████▊ | 32451/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.36.down_proj:  89%|████████▊ | 32452/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.37.gate_proj:  89%|████████▉ | 32453/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.37.up_proj:  89%|████████▉ | 32454/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.37.down_proj:  89%|████████▉ | 32455/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.38.gate_proj:  89%|████████▉ | 32456/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.38.up_proj:  89%|████████▉ | 32457/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.38.down_proj:  89%|████████▉ | 32458/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.39.gate_proj:  89%|████████▉ | 32459/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.39.up_proj:  89%|████████▉ | 32460/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.39.down_proj:  89%|████████▉ | 32461/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.40.gate_proj:  89%|████████▉ | 32462/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.40.up_proj:  89%|████████▉ | 32463/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.40.down_proj:  89%|████████▉ | 32464/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.41.gate_proj:  89%|████████▉ | 32465/36566 [00:29<00:03, 1153.84it/s]
packing model.layers.83.mlp.experts.41.up_proj:  89%|████████▉ | 32466/36566 [00:29<00:03, 1153.84it/s]  
packing model.layers.83.mlp.experts.41.up_proj:  89%|████████▉ | 32467/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.41.down_proj:  89%|████████▉ | 32467/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.42.gate_proj:  89%|████████▉ | 32468/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.42.up_proj:  89%|████████▉ | 32469/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.42.down_proj:  89%|████████▉ | 32470/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.43.gate_proj:  89%|████████▉ | 32471/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.43.up_proj:  89%|████████▉ | 32472/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.43.down_proj:  89%|████████▉ | 32473/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.44.gate_proj:  89%|████████▉ | 32474/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.44.up_proj:  89%|████████▉ | 32475/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.44.down_proj:  89%|████████▉ | 32476/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.45.gate_proj:  89%|████████▉ | 32477/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.45.up_proj:  89%|████████▉ | 32478/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.45.down_proj:  89%|████████▉ | 32479/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.46.gate_proj:  89%|████████▉ | 32480/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.46.up_proj:  89%|████████▉ | 32481/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.46.down_proj:  89%|████████▉ | 32482/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.47.gate_proj:  89%|████████▉ | 32483/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.47.up_proj:  89%|████████▉ | 32484/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.47.down_proj:  89%|████████▉ | 32485/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.48.gate_proj:  89%|████████▉ | 32486/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.48.up_proj:  89%|████████▉ | 32487/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.48.down_proj:  89%|████████▉ | 32488/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.49.gate_proj:  89%|████████▉ | 32489/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.49.up_proj:  89%|████████▉ | 32490/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.49.down_proj:  89%|████████▉ | 32491/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.50.gate_proj:  89%|████████▉ | 32492/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.50.up_proj:  89%|████████▉ | 32493/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.50.down_proj:  89%|████████▉ | 32494/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.51.gate_proj:  89%|████████▉ | 32495/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.51.up_proj:  89%|████████▉ | 32496/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.51.down_proj:  89%|████████▉ | 32497/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.52.gate_proj:  89%|████████▉ | 32498/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.52.up_proj:  89%|████████▉ | 32499/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.52.down_proj:  89%|████████▉ | 32500/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.53.gate_proj:  89%|████████▉ | 32501/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.53.up_proj:  89%|████████▉ | 32502/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.53.down_proj:  89%|████████▉ | 32503/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.54.gate_proj:  89%|████████▉ | 32504/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.54.up_proj:  89%|████████▉ | 32505/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.54.down_proj:  89%|████████▉ | 32506/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.55.gate_proj:  89%|████████▉ | 32507/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.55.up_proj:  89%|████████▉ | 32508/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.55.down_proj:  89%|████████▉ | 32509/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.56.gate_proj:  89%|████████▉ | 32510/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.56.up_proj:  89%|████████▉ | 32511/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.56.down_proj:  89%|████████▉ | 32512/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.57.gate_proj:  89%|████████▉ | 32513/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.57.up_proj:  89%|████████▉ | 32514/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.57.down_proj:  89%|████████▉ | 32515/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.58.gate_proj:  89%|████████▉ | 32516/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.58.up_proj:  89%|████████▉ | 32517/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.58.down_proj:  89%|████████▉ | 32518/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.59.gate_proj:  89%|████████▉ | 32519/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.59.up_proj:  89%|████████▉ | 32520/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.59.down_proj:  89%|████████▉ | 32521/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.60.gate_proj:  89%|████████▉ | 32522/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.60.up_proj:  89%|████████▉ | 32523/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.60.down_proj:  89%|████████▉ | 32524/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.61.gate_proj:  89%|████████▉ | 32525/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.61.up_proj:  89%|████████▉ | 32526/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.61.down_proj:  89%|████████▉ | 32527/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.62.gate_proj:  89%|████████▉ | 32528/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.62.up_proj:  89%|████████▉ | 32529/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.62.down_proj:  89%|████████▉ | 32530/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.63.gate_proj:  89%|████████▉ | 32531/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.63.up_proj:  89%|████████▉ | 32532/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.63.down_proj:  89%|████████▉ | 32533/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.64.gate_proj:  89%|████████▉ | 32534/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.64.up_proj:  89%|████████▉ | 32535/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.64.down_proj:  89%|████████▉ | 32536/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.65.gate_proj:  89%|████████▉ | 32537/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.65.up_proj:  89%|████████▉ | 32538/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.65.down_proj:  89%|████████▉ | 32539/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.66.gate_proj:  89%|████████▉ | 32540/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.66.up_proj:  89%|████████▉ | 32541/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.66.down_proj:  89%|████████▉ | 32542/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.67.gate_proj:  89%|████████▉ | 32543/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.67.up_proj:  89%|████████▉ | 32544/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.67.down_proj:  89%|████████▉ | 32545/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.68.gate_proj:  89%|████████▉ | 32546/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.68.up_proj:  89%|████████▉ | 32547/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.68.down_proj:  89%|████████▉ | 32548/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.69.gate_proj:  89%|████████▉ | 32549/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.69.up_proj:  89%|████████▉ | 32550/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.69.down_proj:  89%|████████▉ | 32551/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.70.gate_proj:  89%|████████▉ | 32552/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.70.up_proj:  89%|████████▉ | 32553/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.70.down_proj:  89%|████████▉ | 32554/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.71.gate_proj:  89%|████████▉ | 32555/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.71.up_proj:  89%|████████▉ | 32556/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.71.down_proj:  89%|████████▉ | 32557/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.72.gate_proj:  89%|████████▉ | 32558/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.72.up_proj:  89%|████████▉ | 32559/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.72.down_proj:  89%|████████▉ | 32560/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.73.gate_proj:  89%|████████▉ | 32561/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.73.up_proj:  89%|████████▉ | 32562/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.73.down_proj:  89%|████████▉ | 32563/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.74.gate_proj:  89%|████████▉ | 32564/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.74.up_proj:  89%|████████▉ | 32565/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.74.down_proj:  89%|████████▉ | 32566/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.75.gate_proj:  89%|████████▉ | 32567/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.75.up_proj:  89%|████████▉ | 32568/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.75.down_proj:  89%|████████▉ | 32569/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.76.gate_proj:  89%|████████▉ | 32570/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.76.up_proj:  89%|████████▉ | 32571/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.76.down_proj:  89%|████████▉ | 32572/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.77.gate_proj:  89%|████████▉ | 32573/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.77.up_proj:  89%|████████▉ | 32574/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.77.down_proj:  89%|████████▉ | 32575/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.78.gate_proj:  89%|████████▉ | 32576/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.78.up_proj:  89%|████████▉ | 32577/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.78.down_proj:  89%|████████▉ | 32578/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.79.gate_proj:  89%|████████▉ | 32579/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.79.up_proj:  89%|████████▉ | 32580/36566 [00:29<00:03, 1154.90it/s]  
packing model.layers.83.mlp.experts.79.down_proj:  89%|████████▉ | 32581/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.80.gate_proj:  89%|████████▉ | 32582/36566 [00:29<00:03, 1154.90it/s]
packing model.layers.83.mlp.experts.80.gate_proj:  89%|████████▉ | 32583/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.80.up_proj:  89%|████████▉ | 32583/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.80.down_proj:  89%|████████▉ | 32584/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.81.gate_proj:  89%|████████▉ | 32585/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.81.up_proj:  89%|████████▉ | 32586/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.81.down_proj:  89%|████████▉ | 32587/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.82.gate_proj:  89%|████████▉ | 32588/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.82.up_proj:  89%|████████▉ | 32589/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.82.down_proj:  89%|████████▉ | 32590/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.83.gate_proj:  89%|████████▉ | 32591/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.83.up_proj:  89%|████████▉ | 32592/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.83.down_proj:  89%|████████▉ | 32593/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.84.gate_proj:  89%|████████▉ | 32594/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.84.up_proj:  89%|████████▉ | 32595/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.84.down_proj:  89%|████████▉ | 32596/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.85.gate_proj:  89%|████████▉ | 32597/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.85.up_proj:  89%|████████▉ | 32598/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.85.down_proj:  89%|████████▉ | 32599/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.86.gate_proj:  89%|████████▉ | 32600/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.86.up_proj:  89%|████████▉ | 32601/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.86.down_proj:  89%|████████▉ | 32602/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.87.gate_proj:  89%|████████▉ | 32603/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.87.up_proj:  89%|████████▉ | 32604/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.87.down_proj:  89%|████████▉ | 32605/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.88.gate_proj:  89%|████████▉ | 32606/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.88.up_proj:  89%|████████▉ | 32607/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.88.down_proj:  89%|████████▉ | 32608/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.89.gate_proj:  89%|████████▉ | 32609/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.89.up_proj:  89%|████████▉ | 32610/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.89.down_proj:  89%|████████▉ | 32611/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.90.gate_proj:  89%|████████▉ | 32612/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.90.up_proj:  89%|████████▉ | 32613/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.90.down_proj:  89%|████████▉ | 32614/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.91.gate_proj:  89%|████████▉ | 32615/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.91.up_proj:  89%|████████▉ | 32616/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.91.down_proj:  89%|████████▉ | 32617/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.92.gate_proj:  89%|████████▉ | 32618/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.92.up_proj:  89%|████████▉ | 32619/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.92.down_proj:  89%|████████▉ | 32620/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.93.gate_proj:  89%|████████▉ | 32621/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.93.up_proj:  89%|████████▉ | 32622/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.93.down_proj:  89%|████████▉ | 32623/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.94.gate_proj:  89%|████████▉ | 32624/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.94.up_proj:  89%|████████▉ | 32625/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.94.down_proj:  89%|████████▉ | 32626/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.95.gate_proj:  89%|████████▉ | 32627/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.95.up_proj:  89%|████████▉ | 32628/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.95.down_proj:  89%|████████▉ | 32629/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.96.gate_proj:  89%|████████▉ | 32630/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.96.up_proj:  89%|████████▉ | 32631/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.96.down_proj:  89%|████████▉ | 32632/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.97.gate_proj:  89%|████████▉ | 32633/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.97.up_proj:  89%|████████▉ | 32634/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.97.down_proj:  89%|████████▉ | 32635/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.98.gate_proj:  89%|████████▉ | 32636/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.98.up_proj:  89%|████████▉ | 32637/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.98.down_proj:  89%|████████▉ | 32638/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.99.gate_proj:  89%|████████▉ | 32639/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.99.up_proj:  89%|████████▉ | 32640/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.99.down_proj:  89%|████████▉ | 32641/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.100.gate_proj:  89%|████████▉ | 32642/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.100.up_proj:  89%|████████▉ | 32643/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.100.down_proj:  89%|████████▉ | 32644/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.101.gate_proj:  89%|████████▉ | 32645/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.101.up_proj:  89%|████████▉ | 32646/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.101.down_proj:  89%|████████▉ | 32647/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.102.gate_proj:  89%|████████▉ | 32648/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.102.up_proj:  89%|████████▉ | 32649/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.102.down_proj:  89%|████████▉ | 32650/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.103.gate_proj:  89%|████████▉ | 32651/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.103.up_proj:  89%|████████▉ | 32652/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.103.down_proj:  89%|████████▉ | 32653/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.104.gate_proj:  89%|████████▉ | 32654/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.104.up_proj:  89%|████████▉ | 32655/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.104.down_proj:  89%|████████▉ | 32656/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.105.gate_proj:  89%|████████▉ | 32657/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.105.up_proj:  89%|████████▉ | 32658/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.105.down_proj:  89%|████████▉ | 32659/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.106.gate_proj:  89%|████████▉ | 32660/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.106.up_proj:  89%|████████▉ | 32661/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.106.down_proj:  89%|████████▉ | 32662/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.107.gate_proj:  89%|████████▉ | 32663/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.107.up_proj:  89%|████████▉ | 32664/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.107.down_proj:  89%|████████▉ | 32665/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.108.gate_proj:  89%|████████▉ | 32666/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.108.up_proj:  89%|████████▉ | 32667/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.108.down_proj:  89%|████████▉ | 32668/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.109.gate_proj:  89%|████████▉ | 32669/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.109.up_proj:  89%|████████▉ | 32670/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.109.down_proj:  89%|████████▉ | 32671/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.110.gate_proj:  89%|████████▉ | 32672/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.110.up_proj:  89%|████████▉ | 32673/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.110.down_proj:  89%|████████▉ | 32674/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.111.gate_proj:  89%|████████▉ | 32675/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.111.up_proj:  89%|████████▉ | 32676/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.111.down_proj:  89%|████████▉ | 32677/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.112.gate_proj:  89%|████████▉ | 32678/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.112.up_proj:  89%|████████▉ | 32679/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.112.down_proj:  89%|████████▉ | 32680/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.113.gate_proj:  89%|████████▉ | 32681/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.113.up_proj:  89%|████████▉ | 32682/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.113.down_proj:  89%|████████▉ | 32683/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.114.gate_proj:  89%|████████▉ | 32684/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.114.up_proj:  89%|████████▉ | 32685/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.114.down_proj:  89%|████████▉ | 32686/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.115.gate_proj:  89%|████████▉ | 32687/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.115.up_proj:  89%|████████▉ | 32688/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.115.down_proj:  89%|████████▉ | 32689/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.116.gate_proj:  89%|████████▉ | 32690/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.116.up_proj:  89%|████████▉ | 32691/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.116.down_proj:  89%|████████▉ | 32692/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.117.gate_proj:  89%|████████▉ | 32693/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.117.up_proj:  89%|████████▉ | 32694/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.117.down_proj:  89%|████████▉ | 32695/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.118.gate_proj:  89%|████████▉ | 32696/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.118.up_proj:  89%|████████▉ | 32697/36566 [00:29<00:03, 1155.50it/s]  
packing model.layers.83.mlp.experts.118.down_proj:  89%|████████▉ | 32698/36566 [00:29<00:03, 1155.50it/s]
packing model.layers.83.mlp.experts.118.down_proj:  89%|████████▉ | 32699/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.119.gate_proj:  89%|████████▉ | 32699/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.119.up_proj:  89%|████████▉ | 32700/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.119.down_proj:  89%|████████▉ | 32701/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.120.gate_proj:  89%|████████▉ | 32702/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.120.up_proj:  89%|████████▉ | 32703/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.120.down_proj:  89%|████████▉ | 32704/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.121.gate_proj:  89%|████████▉ | 32705/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.121.up_proj:  89%|████████▉ | 32706/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.121.down_proj:  89%|████████▉ | 32707/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.122.gate_proj:  89%|████████▉ | 32708/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.122.up_proj:  89%|████████▉ | 32709/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.122.down_proj:  89%|████████▉ | 32710/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.123.gate_proj:  89%|████████▉ | 32711/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.123.up_proj:  89%|████████▉ | 32712/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.123.down_proj:  89%|████████▉ | 32713/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.124.gate_proj:  89%|████████▉ | 32714/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.124.up_proj:  89%|████████▉ | 32715/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.124.down_proj:  89%|████████▉ | 32716/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.125.gate_proj:  89%|████████▉ | 32717/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.125.up_proj:  89%|████████▉ | 32718/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.125.down_proj:  89%|████████▉ | 32719/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.126.gate_proj:  89%|████████▉ | 32720/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.126.up_proj:  89%|████████▉ | 32721/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.126.down_proj:  89%|████████▉ | 32722/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.127.gate_proj:  89%|████████▉ | 32723/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.83.mlp.experts.127.up_proj:  89%|████████▉ | 32724/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.83.mlp.experts.127.down_proj:  89%|████████▉ | 32725/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.0.gate_proj:  89%|████████▉ | 32726/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.0.up_proj:  90%|████████▉ | 32727/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.0.down_proj:  90%|████████▉ | 32728/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.1.gate_proj:  90%|████████▉ | 32729/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.1.up_proj:  90%|████████▉ | 32730/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.1.down_proj:  90%|████████▉ | 32731/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.2.gate_proj:  90%|████████▉ | 32732/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.2.up_proj:  90%|████████▉ | 32733/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.2.down_proj:  90%|████████▉ | 32734/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.3.gate_proj:  90%|████████▉ | 32735/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.3.up_proj:  90%|████████▉ | 32736/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.3.down_proj:  90%|████████▉ | 32737/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.4.gate_proj:  90%|████████▉ | 32738/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.4.up_proj:  90%|████████▉ | 32739/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.4.down_proj:  90%|████████▉ | 32740/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.5.gate_proj:  90%|████████▉ | 32741/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.5.up_proj:  90%|████████▉ | 32742/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.5.down_proj:  90%|████████▉ | 32743/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.6.gate_proj:  90%|████████▉ | 32744/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.6.up_proj:  90%|████████▉ | 32745/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.6.down_proj:  90%|████████▉ | 32746/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.7.gate_proj:  90%|████████▉ | 32747/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.7.up_proj:  90%|████████▉ | 32748/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.7.down_proj:  90%|████████▉ | 32749/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.8.gate_proj:  90%|████████▉ | 32750/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.8.up_proj:  90%|████████▉ | 32751/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.8.down_proj:  90%|████████▉ | 32752/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.9.gate_proj:  90%|████████▉ | 32753/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.9.up_proj:  90%|████████▉ | 32754/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.9.down_proj:  90%|████████▉ | 32755/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.10.gate_proj:  90%|████████▉ | 32756/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.10.up_proj:  90%|████████▉ | 32757/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.10.down_proj:  90%|████████▉ | 32758/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.11.gate_proj:  90%|████████▉ | 32759/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.11.up_proj:  90%|████████▉ | 32760/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.11.down_proj:  90%|████████▉ | 32761/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.12.gate_proj:  90%|████████▉ | 32762/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.12.up_proj:  90%|████████▉ | 32763/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.12.down_proj:  90%|████████▉ | 32764/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.13.gate_proj:  90%|████████▉ | 32765/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.13.up_proj:  90%|████████▉ | 32766/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.13.down_proj:  90%|████████▉ | 32767/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.14.gate_proj:  90%|████████▉ | 32768/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.14.up_proj:  90%|████████▉ | 32769/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.14.down_proj:  90%|████████▉ | 32770/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.15.gate_proj:  90%|████████▉ | 32771/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.15.up_proj:  90%|████████▉ | 32772/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.15.down_proj:  90%|████████▉ | 32773/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.16.gate_proj:  90%|████████▉ | 32774/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.16.up_proj:  90%|████████▉ | 32775/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.16.down_proj:  90%|████████▉ | 32776/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.17.gate_proj:  90%|████████▉ | 32777/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.17.up_proj:  90%|████████▉ | 32778/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.17.down_proj:  90%|████████▉ | 32779/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.18.gate_proj:  90%|████████▉ | 32780/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.18.up_proj:  90%|████████▉ | 32781/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.18.down_proj:  90%|████████▉ | 32782/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.19.gate_proj:  90%|████████▉ | 32783/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.19.up_proj:  90%|████████▉ | 32784/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.19.down_proj:  90%|████████▉ | 32785/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.20.gate_proj:  90%|████████▉ | 32786/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.20.up_proj:  90%|████████▉ | 32787/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.20.down_proj:  90%|████████▉ | 32788/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.21.gate_proj:  90%|████████▉ | 32789/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.21.up_proj:  90%|████████▉ | 32790/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.21.down_proj:  90%|████████▉ | 32791/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.22.gate_proj:  90%|████████▉ | 32792/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.22.up_proj:  90%|████████▉ | 32793/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.22.down_proj:  90%|████████▉ | 32794/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.23.gate_proj:  90%|████████▉ | 32795/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.23.up_proj:  90%|████████▉ | 32796/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.23.down_proj:  90%|████████▉ | 32797/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.24.gate_proj:  90%|████████▉ | 32798/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.24.up_proj:  90%|████████▉ | 32799/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.24.down_proj:  90%|████████▉ | 32800/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.25.gate_proj:  90%|████████▉ | 32801/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.25.up_proj:  90%|████████▉ | 32802/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.25.down_proj:  90%|████████▉ | 32803/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.26.gate_proj:  90%|████████▉ | 32804/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.26.up_proj:  90%|████████▉ | 32805/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.26.down_proj:  90%|████████▉ | 32806/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.27.gate_proj:  90%|████████▉ | 32807/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.27.up_proj:  90%|████████▉ | 32808/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.27.down_proj:  90%|████████▉ | 32809/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.28.gate_proj:  90%|████████▉ | 32810/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.28.up_proj:  90%|████████▉ | 32811/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.28.down_proj:  90%|████████▉ | 32812/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.29.gate_proj:  90%|████████▉ | 32813/36566 [00:29<00:03, 1154.72it/s]
packing model.layers.84.mlp.experts.29.up_proj:  90%|████████▉ | 32814/36566 [00:29<00:03, 1154.72it/s]  
packing model.layers.84.mlp.experts.29.up_proj:  90%|████████▉ | 32815/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.29.down_proj:  90%|████████▉ | 32815/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.30.gate_proj:  90%|████████▉ | 32816/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.30.up_proj:  90%|████████▉ | 32817/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.30.down_proj:  90%|████████▉ | 32818/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.31.gate_proj:  90%|████████▉ | 32819/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.31.up_proj:  90%|████████▉ | 32820/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.31.down_proj:  90%|████████▉ | 32821/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.32.gate_proj:  90%|████████▉ | 32822/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.32.up_proj:  90%|████████▉ | 32823/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.32.down_proj:  90%|████████▉ | 32824/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.33.gate_proj:  90%|████████▉ | 32825/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.33.up_proj:  90%|████████▉ | 32826/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.33.down_proj:  90%|████████▉ | 32827/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.34.gate_proj:  90%|████████▉ | 32828/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.34.up_proj:  90%|████████▉ | 32829/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.34.down_proj:  90%|████████▉ | 32830/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.35.gate_proj:  90%|████████▉ | 32831/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.35.up_proj:  90%|████████▉ | 32832/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.35.down_proj:  90%|████████▉ | 32833/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.36.gate_proj:  90%|████████▉ | 32834/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.36.up_proj:  90%|████████▉ | 32835/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.36.down_proj:  90%|████████▉ | 32836/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.37.gate_proj:  90%|████████▉ | 32837/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.37.up_proj:  90%|████████▉ | 32838/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.37.down_proj:  90%|████████▉ | 32839/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.38.gate_proj:  90%|████████▉ | 32840/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.38.up_proj:  90%|████████▉ | 32841/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.38.down_proj:  90%|████████▉ | 32842/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.39.gate_proj:  90%|████████▉ | 32843/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.39.up_proj:  90%|████████▉ | 32844/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.39.down_proj:  90%|████████▉ | 32845/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.40.gate_proj:  90%|████████▉ | 32846/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.40.up_proj:  90%|████████▉ | 32847/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.40.down_proj:  90%|████████▉ | 32848/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.41.gate_proj:  90%|████████▉ | 32849/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.41.up_proj:  90%|████████▉ | 32850/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.41.down_proj:  90%|████████▉ | 32851/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.42.gate_proj:  90%|████████▉ | 32852/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.42.up_proj:  90%|████████▉ | 32853/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.42.down_proj:  90%|████████▉ | 32854/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.43.gate_proj:  90%|████████▉ | 32855/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.43.up_proj:  90%|████████▉ | 32856/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.43.down_proj:  90%|████████▉ | 32857/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.44.gate_proj:  90%|████████▉ | 32858/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.44.up_proj:  90%|████████▉ | 32859/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.44.down_proj:  90%|████████▉ | 32860/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.45.gate_proj:  90%|████████▉ | 32861/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.45.up_proj:  90%|████████▉ | 32862/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.45.down_proj:  90%|████████▉ | 32863/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.46.gate_proj:  90%|████████▉ | 32864/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.46.up_proj:  90%|████████▉ | 32865/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.46.down_proj:  90%|████████▉ | 32866/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.47.gate_proj:  90%|████████▉ | 32867/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.47.up_proj:  90%|████████▉ | 32868/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.47.down_proj:  90%|████████▉ | 32869/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.48.gate_proj:  90%|████████▉ | 32870/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.48.up_proj:  90%|████████▉ | 32871/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.48.down_proj:  90%|████████▉ | 32872/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.49.gate_proj:  90%|████████▉ | 32873/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.49.up_proj:  90%|████████▉ | 32874/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.49.down_proj:  90%|████████▉ | 32875/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.50.gate_proj:  90%|████████▉ | 32876/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.50.up_proj:  90%|████████▉ | 32877/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.50.down_proj:  90%|████████▉ | 32878/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.51.gate_proj:  90%|████████▉ | 32879/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.51.up_proj:  90%|████████▉ | 32880/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.51.down_proj:  90%|████████▉ | 32881/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.52.gate_proj:  90%|████████▉ | 32882/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.52.up_proj:  90%|████████▉ | 32883/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.52.down_proj:  90%|████████▉ | 32884/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.53.gate_proj:  90%|████████▉ | 32885/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.53.up_proj:  90%|████████▉ | 32886/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.53.down_proj:  90%|████████▉ | 32887/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.54.gate_proj:  90%|████████▉ | 32888/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.54.up_proj:  90%|████████▉ | 32889/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.54.down_proj:  90%|████████▉ | 32890/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.55.gate_proj:  90%|████████▉ | 32891/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.55.up_proj:  90%|████████▉ | 32892/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.55.down_proj:  90%|████████▉ | 32893/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.56.gate_proj:  90%|████████▉ | 32894/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.56.up_proj:  90%|████████▉ | 32895/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.56.down_proj:  90%|████████▉ | 32896/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.57.gate_proj:  90%|████████▉ | 32897/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.57.up_proj:  90%|████████▉ | 32898/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.57.down_proj:  90%|████████▉ | 32899/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.58.gate_proj:  90%|████████▉ | 32900/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.58.up_proj:  90%|████████▉ | 32901/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.58.down_proj:  90%|████████▉ | 32902/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.59.gate_proj:  90%|████████▉ | 32903/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.59.up_proj:  90%|████████▉ | 32904/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.59.down_proj:  90%|████████▉ | 32905/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.60.gate_proj:  90%|████████▉ | 32906/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.60.up_proj:  90%|████████▉ | 32907/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.60.down_proj:  90%|████████▉ | 32908/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.61.gate_proj:  90%|████████▉ | 32909/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.61.up_proj:  90%|█████████ | 32910/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.61.down_proj:  90%|█████████ | 32911/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.62.gate_proj:  90%|█████████ | 32912/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.62.up_proj:  90%|█████████ | 32913/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.62.down_proj:  90%|█████████ | 32914/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.63.gate_proj:  90%|█████████ | 32915/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.63.up_proj:  90%|█████████ | 32916/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.63.down_proj:  90%|█████████ | 32917/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.64.gate_proj:  90%|█████████ | 32918/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.64.up_proj:  90%|█████████ | 32919/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.64.down_proj:  90%|█████████ | 32920/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.65.gate_proj:  90%|█████████ | 32921/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.65.up_proj:  90%|█████████ | 32922/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.65.down_proj:  90%|█████████ | 32923/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.66.gate_proj:  90%|█████████ | 32924/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.66.up_proj:  90%|█████████ | 32925/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.66.down_proj:  90%|█████████ | 32926/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.67.gate_proj:  90%|█████████ | 32927/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.67.up_proj:  90%|█████████ | 32928/36566 [00:29<00:03, 1155.47it/s]  
packing model.layers.84.mlp.experts.67.down_proj:  90%|█████████ | 32929/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.68.gate_proj:  90%|█████████ | 32930/36566 [00:29<00:03, 1155.47it/s]
packing model.layers.84.mlp.experts.68.gate_proj:  90%|█████████ | 32931/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.68.up_proj:  90%|█████████ | 32931/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.68.down_proj:  90%|█████████ | 32932/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.69.gate_proj:  90%|█████████ | 32933/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.69.up_proj:  90%|█████████ | 32934/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.69.down_proj:  90%|█████████ | 32935/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.70.gate_proj:  90%|█████████ | 32936/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.70.up_proj:  90%|█████████ | 32937/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.70.down_proj:  90%|█████████ | 32938/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.71.gate_proj:  90%|█████████ | 32939/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.71.up_proj:  90%|█████████ | 32940/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.71.down_proj:  90%|█████████ | 32941/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.72.gate_proj:  90%|█████████ | 32942/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.72.up_proj:  90%|█████████ | 32943/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.72.down_proj:  90%|█████████ | 32944/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.73.gate_proj:  90%|█████████ | 32945/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.73.up_proj:  90%|█████████ | 32946/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.73.down_proj:  90%|█████████ | 32947/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.74.gate_proj:  90%|█████████ | 32948/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.74.up_proj:  90%|█████████ | 32949/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.74.down_proj:  90%|█████████ | 32950/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.75.gate_proj:  90%|█████████ | 32951/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.75.up_proj:  90%|█████████ | 32952/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.75.down_proj:  90%|█████████ | 32953/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.76.gate_proj:  90%|█████████ | 32954/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.76.up_proj:  90%|█████████ | 32955/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.76.down_proj:  90%|█████████ | 32956/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.77.gate_proj:  90%|█████████ | 32957/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.77.up_proj:  90%|█████████ | 32958/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.77.down_proj:  90%|█████████ | 32959/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.78.gate_proj:  90%|█████████ | 32960/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.78.up_proj:  90%|█████████ | 32961/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.78.down_proj:  90%|█████████ | 32962/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.79.gate_proj:  90%|█████████ | 32963/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.79.up_proj:  90%|█████████ | 32964/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.79.down_proj:  90%|█████████ | 32965/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.80.gate_proj:  90%|█████████ | 32966/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.80.up_proj:  90%|█████████ | 32967/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.80.down_proj:  90%|█████████ | 32968/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.81.gate_proj:  90%|█████████ | 32969/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.81.up_proj:  90%|█████████ | 32970/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.81.down_proj:  90%|█████████ | 32971/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.82.gate_proj:  90%|█████████ | 32972/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.82.up_proj:  90%|█████████ | 32973/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.82.down_proj:  90%|█████████ | 32974/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.83.gate_proj:  90%|█████████ | 32975/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.83.up_proj:  90%|█████████ | 32976/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.83.down_proj:  90%|█████████ | 32977/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.84.gate_proj:  90%|█████████ | 32978/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.84.up_proj:  90%|█████████ | 32979/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.84.down_proj:  90%|█████████ | 32980/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.85.gate_proj:  90%|█████████ | 32981/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.85.up_proj:  90%|█████████ | 32982/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.85.down_proj:  90%|█████████ | 32983/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.86.gate_proj:  90%|█████████ | 32984/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.86.up_proj:  90%|█████████ | 32985/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.86.down_proj:  90%|█████████ | 32986/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.87.gate_proj:  90%|█████████ | 32987/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.87.up_proj:  90%|█████████ | 32988/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.87.down_proj:  90%|█████████ | 32989/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.88.gate_proj:  90%|█████████ | 32990/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.88.up_proj:  90%|█████████ | 32991/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.88.down_proj:  90%|█████████ | 32992/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.89.gate_proj:  90%|█████████ | 32993/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.89.up_proj:  90%|█████████ | 32994/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.89.down_proj:  90%|█████████ | 32995/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.90.gate_proj:  90%|█████████ | 32996/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.90.up_proj:  90%|█████████ | 32997/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.90.down_proj:  90%|█████████ | 32998/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.91.gate_proj:  90%|█████████ | 32999/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.91.up_proj:  90%|█████████ | 33000/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.91.down_proj:  90%|█████████ | 33001/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.92.gate_proj:  90%|█████████ | 33002/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.92.up_proj:  90%|█████████ | 33003/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.92.down_proj:  90%|█████████ | 33004/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.93.gate_proj:  90%|█████████ | 33005/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.93.up_proj:  90%|█████████ | 33006/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.93.down_proj:  90%|█████████ | 33007/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.94.gate_proj:  90%|█████████ | 33008/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.94.up_proj:  90%|█████████ | 33009/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.94.down_proj:  90%|█████████ | 33010/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.95.gate_proj:  90%|█████████ | 33011/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.95.up_proj:  90%|█████████ | 33012/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.95.down_proj:  90%|█████████ | 33013/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.96.gate_proj:  90%|█████████ | 33014/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.96.up_proj:  90%|█████████ | 33015/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.96.down_proj:  90%|█████████ | 33016/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.97.gate_proj:  90%|█████████ | 33017/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.97.up_proj:  90%|█████████ | 33018/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.97.down_proj:  90%|█████████ | 33019/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.98.gate_proj:  90%|█████████ | 33020/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.98.up_proj:  90%|█████████ | 33021/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.98.down_proj:  90%|█████████ | 33022/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.99.gate_proj:  90%|█████████ | 33023/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.99.up_proj:  90%|█████████ | 33024/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.99.down_proj:  90%|█████████ | 33025/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.100.gate_proj:  90%|█████████ | 33026/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.100.up_proj:  90%|█████████ | 33027/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.100.down_proj:  90%|█████████ | 33028/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.101.gate_proj:  90%|█████████ | 33029/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.101.up_proj:  90%|█████████ | 33030/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.101.down_proj:  90%|█████████ | 33031/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.102.gate_proj:  90%|█████████ | 33032/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.102.up_proj:  90%|█████████ | 33033/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.102.down_proj:  90%|█████████ | 33034/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.103.gate_proj:  90%|█████████ | 33035/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.103.up_proj:  90%|█████████ | 33036/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.103.down_proj:  90%|█████████ | 33037/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.104.gate_proj:  90%|█████████ | 33038/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.104.up_proj:  90%|█████████ | 33039/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.104.down_proj:  90%|█████████ | 33040/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.105.gate_proj:  90%|█████████ | 33041/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.105.up_proj:  90%|█████████ | 33042/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.105.down_proj:  90%|█████████ | 33043/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.106.gate_proj:  90%|█████████ | 33044/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.106.up_proj:  90%|█████████ | 33045/36566 [00:29<00:03, 1153.86it/s]  
packing model.layers.84.mlp.experts.106.down_proj:  90%|█████████ | 33046/36566 [00:29<00:03, 1153.86it/s]
packing model.layers.84.mlp.experts.106.down_proj:  90%|█████████ | 33047/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.107.gate_proj:  90%|█████████ | 33047/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.107.up_proj:  90%|█████████ | 33048/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.107.down_proj:  90%|█████████ | 33049/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.108.gate_proj:  90%|█████████ | 33050/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.108.up_proj:  90%|█████████ | 33051/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.108.down_proj:  90%|█████████ | 33052/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.109.gate_proj:  90%|█████████ | 33053/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.109.up_proj:  90%|█████████ | 33054/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.109.down_proj:  90%|█████████ | 33055/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.110.gate_proj:  90%|█████████ | 33056/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.110.up_proj:  90%|█████████ | 33057/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.110.down_proj:  90%|█████████ | 33058/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.111.gate_proj:  90%|█████████ | 33059/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.111.up_proj:  90%|█████████ | 33060/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.111.down_proj:  90%|█████████ | 33061/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.112.gate_proj:  90%|█████████ | 33062/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.112.up_proj:  90%|█████████ | 33063/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.112.down_proj:  90%|█████████ | 33064/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.113.gate_proj:  90%|█████████ | 33065/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.113.up_proj:  90%|█████████ | 33066/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.113.down_proj:  90%|█████████ | 33067/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.114.gate_proj:  90%|█████████ | 33068/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.114.up_proj:  90%|█████████ | 33069/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.114.down_proj:  90%|█████████ | 33070/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.115.gate_proj:  90%|█████████ | 33071/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.115.up_proj:  90%|█████████ | 33072/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.115.down_proj:  90%|█████████ | 33073/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.116.gate_proj:  90%|█████████ | 33074/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.116.up_proj:  90%|█████████ | 33075/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.116.down_proj:  90%|█████████ | 33076/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.117.gate_proj:  90%|█████████ | 33077/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.117.up_proj:  90%|█████████ | 33078/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.117.down_proj:  90%|█████████ | 33079/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.118.gate_proj:  90%|█████████ | 33080/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.118.up_proj:  90%|█████████ | 33081/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.118.down_proj:  90%|█████████ | 33082/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.119.gate_proj:  90%|█████████ | 33083/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.119.up_proj:  90%|█████████ | 33084/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.119.down_proj:  90%|█████████ | 33085/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.120.gate_proj:  90%|█████████ | 33086/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.120.up_proj:  90%|█████████ | 33087/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.120.down_proj:  90%|█████████ | 33088/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.121.gate_proj:  90%|█████████ | 33089/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.121.up_proj:  90%|█████████ | 33090/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.121.down_proj:  90%|█████████ | 33091/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.122.gate_proj:  90%|█████████ | 33092/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.122.up_proj:  91%|█████████ | 33093/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.122.down_proj:  91%|█████████ | 33094/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.123.gate_proj:  91%|█████████ | 33095/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.123.up_proj:  91%|█████████ | 33096/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.123.down_proj:  91%|█████████ | 33097/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.124.gate_proj:  91%|█████████ | 33098/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.124.up_proj:  91%|█████████ | 33099/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.124.down_proj:  91%|█████████ | 33100/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.125.gate_proj:  91%|█████████ | 33101/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.125.up_proj:  91%|█████████ | 33102/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.125.down_proj:  91%|█████████ | 33103/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.126.gate_proj:  91%|█████████ | 33104/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.126.up_proj:  91%|█████████ | 33105/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.126.down_proj:  91%|█████████ | 33106/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.127.gate_proj:  91%|█████████ | 33107/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.84.mlp.experts.127.up_proj:  91%|█████████ | 33108/36566 [00:29<00:03, 1152.05it/s]  
packing model.layers.84.mlp.experts.127.down_proj:  91%|█████████ | 33109/36566 [00:29<00:03, 1152.05it/s]
packing model.layers.85.mlp.experts.0.gate_proj:  91%|█████████ | 33110/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.0.up_proj:  91%|█████████ | 33111/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.0.down_proj:  91%|█████████ | 33112/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.1.gate_proj:  91%|█████████ | 33113/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.1.up_proj:  91%|█████████ | 33114/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.1.down_proj:  91%|█████████ | 33115/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.2.gate_proj:  91%|█████████ | 33116/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.2.up_proj:  91%|█████████ | 33117/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.2.down_proj:  91%|█████████ | 33118/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.3.gate_proj:  91%|█████████ | 33119/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.3.up_proj:  91%|█████████ | 33120/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.3.down_proj:  91%|█████████ | 33121/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.4.gate_proj:  91%|█████████ | 33122/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.4.up_proj:  91%|█████████ | 33123/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.4.down_proj:  91%|█████████ | 33124/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.5.gate_proj:  91%|█████████ | 33125/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.5.up_proj:  91%|█████████ | 33126/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.5.down_proj:  91%|█████████ | 33127/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.6.gate_proj:  91%|█████████ | 33128/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.6.up_proj:  91%|█████████ | 33129/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.6.down_proj:  91%|█████████ | 33130/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.7.gate_proj:  91%|█████████ | 33131/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.7.up_proj:  91%|█████████ | 33132/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.7.down_proj:  91%|█████████ | 33133/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.8.gate_proj:  91%|█████████ | 33134/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.8.up_proj:  91%|█████████ | 33135/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.8.down_proj:  91%|█████████ | 33136/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.9.gate_proj:  91%|█████████ | 33137/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.9.up_proj:  91%|█████████ | 33138/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.9.down_proj:  91%|█████████ | 33139/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.10.gate_proj:  91%|█████████ | 33140/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.10.up_proj:  91%|█████████ | 33141/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.10.down_proj:  91%|█████████ | 33142/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.11.gate_proj:  91%|█████████ | 33143/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.11.up_proj:  91%|█████████ | 33144/36566 [00:29<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.11.down_proj:  91%|█████████ | 33145/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.12.gate_proj:  91%|█████████ | 33146/36566 [00:29<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.12.up_proj:  91%|█████████ | 33147/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.12.down_proj:  91%|█████████ | 33148/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.13.gate_proj:  91%|█████████ | 33149/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.13.up_proj:  91%|█████████ | 33150/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.13.down_proj:  91%|█████████ | 33151/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.14.gate_proj:  91%|█████████ | 33152/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.14.up_proj:  91%|█████████ | 33153/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.14.down_proj:  91%|█████████ | 33154/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.15.gate_proj:  91%|█████████ | 33155/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.15.up_proj:  91%|█████████ | 33156/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.15.down_proj:  91%|█████████ | 33157/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.16.gate_proj:  91%|█████████ | 33158/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.16.up_proj:  91%|█████████ | 33159/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.16.down_proj:  91%|█████████ | 33160/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.17.gate_proj:  91%|█████████ | 33161/36566 [00:30<00:02, 1152.05it/s]
packing model.layers.85.mlp.experts.17.up_proj:  91%|█████████ | 33162/36566 [00:30<00:02, 1152.05it/s]  
packing model.layers.85.mlp.experts.17.up_proj:  91%|█████████ | 33163/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.17.down_proj:  91%|█████████ | 33163/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.18.gate_proj:  91%|█████████ | 33164/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.18.up_proj:  91%|█████████ | 33165/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.18.down_proj:  91%|█████████ | 33166/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.19.gate_proj:  91%|█████████ | 33167/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.19.up_proj:  91%|█████████ | 33168/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.19.down_proj:  91%|█████████ | 33169/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.20.gate_proj:  91%|█████████ | 33170/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.20.up_proj:  91%|█████████ | 33171/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.20.down_proj:  91%|█████████ | 33172/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.21.gate_proj:  91%|█████████ | 33173/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.21.up_proj:  91%|█████████ | 33174/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.21.down_proj:  91%|█████████ | 33175/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.22.gate_proj:  91%|█████████ | 33176/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.22.up_proj:  91%|█████████ | 33177/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.22.down_proj:  91%|█████████ | 33178/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.23.gate_proj:  91%|█████████ | 33179/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.23.up_proj:  91%|█████████ | 33180/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.23.down_proj:  91%|█████████ | 33181/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.24.gate_proj:  91%|█████████ | 33182/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.24.up_proj:  91%|█████████ | 33183/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.24.down_proj:  91%|█████████ | 33184/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.25.gate_proj:  91%|█████████ | 33185/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.25.up_proj:  91%|█████████ | 33186/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.25.down_proj:  91%|█████████ | 33187/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.26.gate_proj:  91%|█████████ | 33188/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.26.up_proj:  91%|█████████ | 33189/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.26.down_proj:  91%|█████████ | 33190/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.27.gate_proj:  91%|█████████ | 33191/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.27.up_proj:  91%|█████████ | 33192/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.27.down_proj:  91%|█████████ | 33193/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.28.gate_proj:  91%|█████████ | 33194/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.28.up_proj:  91%|█████████ | 33195/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.28.down_proj:  91%|█████████ | 33196/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.29.gate_proj:  91%|█████████ | 33197/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.29.up_proj:  91%|█████████ | 33198/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.29.down_proj:  91%|█████████ | 33199/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.30.gate_proj:  91%|█████████ | 33200/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.30.up_proj:  91%|█████████ | 33201/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.30.down_proj:  91%|█████████ | 33202/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.31.gate_proj:  91%|█████████ | 33203/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.31.up_proj:  91%|█████████ | 33204/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.31.down_proj:  91%|█████████ | 33205/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.32.gate_proj:  91%|█████████ | 33206/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.32.up_proj:  91%|█████████ | 33207/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.32.down_proj:  91%|█████████ | 33208/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.33.gate_proj:  91%|█████████ | 33209/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.33.up_proj:  91%|█████████ | 33210/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.33.down_proj:  91%|█████████ | 33211/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.34.gate_proj:  91%|█████████ | 33212/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.34.up_proj:  91%|█████████ | 33213/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.34.down_proj:  91%|█████████ | 33214/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.35.gate_proj:  91%|█████████ | 33215/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.35.up_proj:  91%|█████████ | 33216/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.35.down_proj:  91%|█████████ | 33217/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.36.gate_proj:  91%|█████████ | 33218/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.36.up_proj:  91%|█████████ | 33219/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.36.down_proj:  91%|█████████ | 33220/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.37.gate_proj:  91%|█████████ | 33221/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.37.up_proj:  91%|█████████ | 33222/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.37.down_proj:  91%|█████████ | 33223/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.38.gate_proj:  91%|█████████ | 33224/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.38.up_proj:  91%|█████████ | 33225/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.38.down_proj:  91%|█████████ | 33226/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.39.gate_proj:  91%|█████████ | 33227/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.39.up_proj:  91%|█████████ | 33228/36566 [00:30<00:02, 1149.51it/s]  
packing model.layers.85.mlp.experts.39.down_proj:  91%|█████████ | 33229/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.40.gate_proj:  91%|█████████ | 33230/36566 [00:30<00:02, 1149.51it/s]
packing model.layers.85.mlp.experts.40.up_proj:
chaiml-muster-v2-q235b-77862-v1-uploader: .79it/s]  
packing model.layers.87.mlp.experts.85.down_proj:  93%|█████████▎| 34135/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.86.gate_proj:  93%|█████████▎| 34136/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.86.up_proj:  93%|█████████▎| 34137/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.86.down_proj:  93%|█████████▎| 34138/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.87.gate_proj:  93%|█████████▎| 34139/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.87.up_proj:  93%|█████████▎| 34140/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.87.down_proj:  93%|█████████▎| 34141/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.88.gate_proj:  93%|█████████▎| 34142/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.88.up_proj:  93%|█████████▎| 34143/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.88.down_proj:  93%|█████████▎| 34144/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.89.gate_proj:  93%|█████████▎| 34145/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.89.up_proj:  93%|█████████▎| 34146/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.89.down_proj:  93%|█████████▎| 34147/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.90.gate_proj:  93%|█████████▎| 34148/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.90.up_proj:  93%|█████████▎| 34149/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.90.down_proj:  93%|█████████▎| 34150/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.91.gate_proj:  93%|█████████▎| 34151/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.91.up_proj:  93%|█████████▎| 34152/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.91.down_proj:  93%|█████████▎| 34153/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.92.gate_proj:  93%|█████████▎| 34154/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.92.up_proj:  93%|█████████▎| 34155/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.92.down_proj:  93%|█████████▎| 34156/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.93.gate_proj:  93%|█████████▎| 34157/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.93.up_proj:  93%|█████████▎| 34158/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.93.down_proj:  93%|█████████▎| 34159/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.94.gate_proj:  93%|█████████▎| 34160/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.94.up_proj:  93%|█████████▎| 34161/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.94.down_proj:  93%|█████████▎| 34162/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.95.gate_proj:  93%|█████████▎| 34163/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.95.up_proj:  93%|█████████▎| 34164/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.95.down_proj:  93%|█████████▎| 34165/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.96.gate_proj:  93%|█████████▎| 34166/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.96.up_proj:  93%|█████████▎| 34167/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.96.down_proj:  93%|█████████▎| 34168/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.97.gate_proj:  93%|█████████▎| 34169/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.97.up_proj:  93%|█████████▎| 34170/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.97.down_proj:  93%|█████████▎| 34171/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.98.gate_proj:  93%|█████████▎| 34172/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.98.up_proj:  93%|█████████▎| 34173/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.98.down_proj:  93%|█████████▎| 34174/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.99.gate_proj:  93%|█████████▎| 34175/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.99.up_proj:  93%|█████████▎| 34176/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.99.down_proj:  93%|█████████▎| 34177/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.100.gate_proj:  93%|█████████▎| 34178/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.100.up_proj:  93%|█████████▎| 34179/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.100.down_proj:  93%|█████████▎| 34180/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.101.gate_proj:  93%|█████████▎| 34181/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.101.up_proj:  93%|█████████▎| 34182/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.101.down_proj:  93%|█████████▎| 34183/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.102.gate_proj:  93%|█████████▎| 34184/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.102.up_proj:  93%|█████████▎| 34185/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.102.down_proj:  93%|█████████▎| 34186/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.103.gate_proj:  93%|█████████▎| 34187/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.103.up_proj:  93%|█████████▎| 34188/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.103.down_proj:  93%|█████████▎| 34189/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.104.gate_proj:  94%|█████████▎| 34190/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.104.up_proj:  94%|█████████▎| 34191/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.104.down_proj:  94%|█████████▎| 34192/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.105.gate_proj:  94%|█████████▎| 34193/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.105.up_proj:  94%|█████████▎| 34194/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.105.down_proj:  94%|█████████▎| 34195/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.106.gate_proj:  94%|█████████▎| 34196/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.106.up_proj:  94%|█████████▎| 34197/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.106.down_proj:  94%|█████████▎| 34198/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.107.gate_proj:  94%|█████████▎| 34199/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.107.up_proj:  94%|█████████▎| 34200/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.107.down_proj:  94%|█████████▎| 34201/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.108.gate_proj:  94%|█████████▎| 34202/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.108.up_proj:  94%|█████████▎| 34203/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.108.down_proj:  94%|█████████▎| 34204/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.109.gate_proj:  94%|█████████▎| 34205/36566 [00:30<00:02, 1148.79it/s]
packing model.layers.87.mlp.experts.109.up_proj:  94%|█████████▎| 34206/36566 [00:30<00:02, 1148.79it/s]  
packing model.layers.87.mlp.experts.109.up_proj:  94%|█████████▎| 34207/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.109.down_proj:  94%|█████████▎| 34207/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.110.gate_proj:  94%|█████████▎| 34208/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.110.up_proj:  94%|█████████▎| 34209/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.110.down_proj:  94%|█████████▎| 34210/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.111.gate_proj:  94%|█████████▎| 34211/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.111.up_proj:  94%|█████████▎| 34212/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.111.down_proj:  94%|█████████▎| 34213/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.112.gate_proj:  94%|█████████▎| 34214/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.112.up_proj:  94%|█████████▎| 34215/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.112.down_proj:  94%|█████████▎| 34216/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.113.gate_proj:  94%|█████████▎| 34217/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.113.up_proj:  94%|█████████▎| 34218/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.113.down_proj:  94%|█████████▎| 34219/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.114.gate_proj:  94%|█████████▎| 34220/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.114.up_proj:  94%|█████████▎| 34221/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.114.down_proj:  94%|█████████▎| 34222/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.115.gate_proj:  94%|█████████▎| 34223/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.115.up_proj:  94%|█████████▎| 34224/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.115.down_proj:  94%|█████████▎| 34225/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.116.gate_proj:  94%|█████████▎| 34226/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.116.up_proj:  94%|█████████▎| 34227/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.116.down_proj:  94%|█████████▎| 34228/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.117.gate_proj:  94%|█████████▎| 34229/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.117.up_proj:  94%|█████████▎| 34230/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.117.down_proj:  94%|█████████▎| 34231/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.118.gate_proj:  94%|█████████▎| 34232/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.118.up_proj:  94%|█████████▎| 34233/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.118.down_proj:  94%|█████████▎| 34234/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.119.gate_proj:  94%|█████████▎| 34235/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.119.up_proj:  94%|█████████▎| 34236/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.119.down_proj:  94%|█████████▎| 34237/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.120.gate_proj:  94%|█████████▎| 34238/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.120.up_proj:  94%|█████████▎| 34239/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.120.down_proj:  94%|█████████▎| 34240/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.121.gate_proj:  94%|█████████▎| 34241/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.121.up_proj:  94%|█████████▎| 34242/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.121.down_proj:  94%|█████████▎| 34243/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.122.gate_proj:  94%|█████████▎| 34244/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.122.up_proj:  94%|█████████▎| 34245/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.122.down_proj:  94%|█████████▎| 34246/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.123.gate_proj:  94%|█████████▎| 34247/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.123.up_proj:  94%|█████████▎| 34248/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.123.down_proj:  94%|█████████▎| 34249/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.124.gate_proj:  94%|█████████▎| 34250/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.124.up_proj:  94%|█████████▎| 34251/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.124.down_proj:  94%|█████████▎| 34252/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.125.gate_proj:  94%|█████████▎| 34253/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.125.up_proj:  94%|█████████▎| 34254/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.125.down_proj:  94%|█████████▎| 34255/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.126.gate_proj:  94%|█████████▎| 34256/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.126.up_proj:  94%|█████████▎| 34257/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.126.down_proj:  94%|█████████▎| 34258/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.127.gate_proj:  94%|█████████▎| 34259/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.87.mlp.experts.127.up_proj:  94%|█████████▎| 34260/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.87.mlp.experts.127.down_proj:  94%|█████████▎| 34261/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.88.mlp.experts.0.gate_proj:  94%|█████████▎| 34262/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.88.mlp.experts.0.up_proj:  94%|█████████▎| 34263/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.88.mlp.experts.0.down_proj:  94%|█████████▎| 34264/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.88.mlp.experts.1.gate_proj:  94%|█████████▎| 34265/36566 [00:30<00:02, 1149.74it/s]
packing model.layers.88.mlp.experts.1.up_proj:  94%|█████████▎| 34266/36566 [00:30<00:02, 1149.74it/s]  
packing model.layers.88.mlp.experts.1.down_proj:  94%|█████████▎| 34267/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.2.gate_proj:  94%|█████████▎| 34268/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.2.up_proj:  94%|█████████▎| 34269/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.2.down_proj:  94%|█████████▎| 34270/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.3.gate_proj:  94%|█████████▎| 34271/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.3.up_proj:  94%|█████████▎| 34272/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.3.down_proj:  94%|█████████▎| 34273/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.4.gate_proj:  94%|█████████▎| 34274/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.4.up_proj:  94%|█████████▎| 34275/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.4.down_proj:  94%|█████████▎| 34276/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.5.gate_proj:  94%|█████████▎| 34277/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.5.up_proj:  94%|█████████▎| 34278/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.5.down_proj:  94%|█████████▎| 34279/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.6.gate_proj:  94%|█████████▎| 34280/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.6.up_proj:  94%|█████████▍| 34281/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.6.down_proj:  94%|█████████▍| 34282/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.7.gate_proj:  94%|█████████▍| 34283/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.7.up_proj:  94%|█████████▍| 34284/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.7.down_proj:  94%|█████████▍| 34285/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.8.gate_proj:  94%|█████████▍| 34286/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.8.up_proj:  94%|█████████▍| 34287/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.8.down_proj:  94%|█████████▍| 34288/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.9.gate_proj:  94%|█████████▍| 34289/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.9.up_proj:  94%|█████████▍| 34290/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.9.down_proj:  94%|█████████▍| 34291/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.10.gate_proj:  94%|█████████▍| 34292/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.10.up_proj:  94%|█████████▍| 34293/36566 [00:30<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.10.down_proj:  94%|█████████▍| 34294/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.11.gate_proj:  94%|█████████▍| 34295/36566 [00:30<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.11.up_proj:  94%|█████████▍| 34296/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.11.down_proj:  94%|█████████▍| 34297/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.12.gate_proj:  94%|█████████▍| 34298/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.12.up_proj:  94%|█████████▍| 34299/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.12.down_proj:  94%|█████████▍| 34300/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.13.gate_proj:  94%|█████████▍| 34301/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.13.up_proj:  94%|█████████▍| 34302/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.13.down_proj:  94%|█████████▍| 34303/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.14.gate_proj:  94%|█████████▍| 34304/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.14.up_proj:  94%|█████████▍| 34305/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.14.down_proj:  94%|█████████▍| 34306/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.15.gate_proj:  94%|█████████▍| 34307/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.15.up_proj:  94%|█████████▍| 34308/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.15.down_proj:  94%|█████████▍| 34309/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.16.gate_proj:  94%|█████████▍| 34310/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.16.up_proj:  94%|█████████▍| 34311/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.16.down_proj:  94%|█████████▍| 34312/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.17.gate_proj:  94%|█████████▍| 34313/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.17.up_proj:  94%|█████████▍| 34314/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.17.down_proj:  94%|█████████▍| 34315/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.18.gate_proj:  94%|█████████▍| 34316/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.18.up_proj:  94%|█████████▍| 34317/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.18.down_proj:  94%|█████████▍| 34318/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.19.gate_proj:  94%|█████████▍| 34319/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.19.up_proj:  94%|█████████▍| 34320/36566 [00:31<00:01, 1149.74it/s]  
packing model.layers.88.mlp.experts.19.down_proj:  94%|█████████▍| 34321/36566 [00:31<00:01, 1149.74it/s]
packing model.layers.88.mlp.experts.19.down_proj:  94%|█████████▍| 34322/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.20.gate_proj:  94%|█████████▍| 34322/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.20.up_proj:  94%|█████████▍| 34323/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.20.down_proj:  94%|█████████▍| 34324/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.21.gate_proj:  94%|█████████▍| 34325/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.21.up_proj:  94%|█████████▍| 34326/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.21.down_proj:  94%|█████████▍| 34327/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.22.gate_proj:  94%|█████████▍| 34328/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.22.up_proj:  94%|█████████▍| 34329/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.22.down_proj:  94%|█████████▍| 34330/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.23.gate_proj:  94%|█████████▍| 34331/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.23.up_proj:  94%|█████████▍| 34332/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.23.down_proj:  94%|█████████▍| 34333/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.24.gate_proj:  94%|█████████▍| 34334/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.24.up_proj:  94%|█████████▍| 34335/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.24.down_proj:  94%|█████████▍| 34336/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.25.gate_proj:  94%|█████████▍| 34337/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.25.up_proj:  94%|█████████▍| 34338/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.25.down_proj:  94%|█████████▍| 34339/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.26.gate_proj:  94%|█████████▍| 34340/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.26.up_proj:  94%|█████████▍| 34341/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.26.down_proj:  94%|█████████▍| 34342/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.27.gate_proj:  94%|█████████▍| 34343/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.27.up_proj:  94%|█████████▍| 34344/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.27.down_proj:  94%|█████████▍| 34345/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.28.gate_proj:  94%|█████████▍| 34346/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.28.up_proj:  94%|█████████▍| 34347/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.28.down_proj:  94%|█████████▍| 34348/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.29.gate_proj:  94%|█████████▍| 34349/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.29.up_proj:  94%|█████████▍| 34350/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.29.down_proj:  94%|█████████▍| 34351/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.30.gate_proj:  94%|█████████▍| 34352/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.30.up_proj:  94%|█████████▍| 34353/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.30.down_proj:  94%|█████████▍| 34354/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.31.gate_proj:  94%|█████████▍| 34355/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.31.up_proj:  94%|█████████▍| 34356/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.31.down_proj:  94%|█████████▍| 34357/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.32.gate_proj:  94%|█████████▍| 34358/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.32.up_proj:  94%|█████████▍| 34359/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.32.down_proj:  94%|█████████▍| 34360/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.33.gate_proj:  94%|█████████▍| 34361/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.33.up_proj:  94%|█████████▍| 34362/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.33.down_proj:  94%|█████████▍| 34363/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.34.gate_proj:  94%|█████████▍| 34364/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.34.up_proj:  94%|█████████▍| 34365/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.34.down_proj:  94%|█████████▍| 34366/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.35.gate_proj:  94%|█████████▍| 34367/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.35.up_proj:  94%|█████████▍| 34368/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.35.down_proj:  94%|█████████▍| 34369/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.36.gate_proj:  94%|█████████▍| 34370/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.36.up_proj:  94%|█████████▍| 34371/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.36.down_proj:  94%|█████████▍| 34372/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.37.gate_proj:  94%|█████████▍| 34373/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.37.up_proj:  94%|█████████▍| 34374/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.37.down_proj:  94%|█████████▍| 34375/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.38.gate_proj:  94%|█████████▍| 34376/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.38.up_proj:  94%|█████████▍| 34377/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.38.down_proj:  94%|█████████▍| 34378/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.39.gate_proj:  94%|█████████▍| 34379/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.39.up_proj:  94%|█████████▍| 34380/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.39.down_proj:  94%|█████████▍| 34381/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.40.gate_proj:  94%|█████████▍| 34382/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.40.up_proj:  94%|█████████▍| 34383/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.40.down_proj:  94%|█████████▍| 34384/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.41.gate_proj:  94%|█████████▍| 34385/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.41.up_proj:  94%|█████████▍| 34386/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.41.down_proj:  94%|█████████▍| 34387/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.42.gate_proj:  94%|█████████▍| 34388/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.42.up_proj:  94%|█████████▍| 34389/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.42.down_proj:  94%|█████████▍| 34390/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.43.gate_proj:  94%|█████████▍| 34391/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.43.up_proj:  94%|█████████▍| 34392/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.43.down_proj:  94%|█████████▍| 34393/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.44.gate_proj:  94%|█████████▍| 34394/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.44.up_proj:  94%|█████████▍| 34395/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.44.down_proj:  94%|█████████▍| 34396/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.45.gate_proj:  94%|█████████▍| 34397/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.45.up_proj:  94%|█████████▍| 34398/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.45.down_proj:  94%|█████████▍| 34399/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.46.gate_proj:  94%|█████████▍| 34400/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.46.up_proj:  94%|█████████▍| 34401/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.46.down_proj:  94%|█████████▍| 34402/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.47.gate_proj:  94%|█████████▍| 34403/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.47.up_proj:  94%|█████████▍| 34404/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.47.down_proj:  94%|█████████▍| 34405/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.48.gate_proj:  94%|█████████▍| 34406/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.48.up_proj:  94%|█████████▍| 34407/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.48.down_proj:  94%|█████████▍| 34408/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.49.gate_proj:  94%|█████████▍| 34409/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.49.up_proj:  94%|█████████▍| 34410/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.49.down_proj:  94%|█████████▍| 34411/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.50.gate_proj:  94%|█████████▍| 34412/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.50.up_proj:  94%|█████████▍| 34413/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.50.down_proj:  94%|█████████▍| 34414/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.51.gate_proj:  94%|█████████▍| 34415/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.51.up_proj:  94%|█████████▍| 34416/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.51.down_proj:  94%|█████████▍| 34417/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.52.gate_proj:  94%|█████████▍| 34418/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.52.up_proj:  94%|█████████▍| 34419/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.52.down_proj:  94%|█████████▍| 34420/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.53.gate_proj:  94%|█████████▍| 34421/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.53.up_proj:  94%|█████████▍| 34422/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.53.down_proj:  94%|█████████▍| 34423/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.54.gate_proj:  94%|█████████▍| 34424/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.54.up_proj:  94%|█████████▍| 34425/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.54.down_proj:  94%|█████████▍| 34426/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.55.gate_proj:  94%|█████████▍| 34427/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.55.up_proj:  94%|█████████▍| 34428/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.55.down_proj:  94%|█████████▍| 34429/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.56.gate_proj:  94%|█████████▍| 34430/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.56.up_proj:  94%|█████████▍| 34431/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.56.down_proj:  94%|█████████▍| 34432/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.57.gate_proj:  94%|█████████▍| 34433/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.57.up_proj:  94%|█████████▍| 34434/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.57.down_proj:  94%|█████████▍| 34435/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.58.gate_proj:  94%|█████████▍| 34436/36566 [00:31<00:01, 1148.90it/s]
packing model.layers.88.mlp.experts.58.up_proj:  94%|█████████▍| 34437/36566 [00:31<00:01, 1148.90it/s]  
packing model.layers.88.mlp.experts.58.up_proj:  94%|█████████▍| 34438/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.58.down_proj:  94%|█████████▍| 34438/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.59.gate_proj:  94%|█████████▍| 34439/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.59.up_proj:  94%|█████████▍| 34440/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.59.down_proj:  94%|█████████▍| 34441/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.60.gate_proj:  94%|█████████▍| 34442/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.60.up_proj:  94%|█████████▍| 34443/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.60.down_proj:  94%|█████████▍| 34444/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.61.gate_proj:  94%|█████████▍| 34445/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.61.up_proj:  94%|█████████▍| 34446/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.61.down_proj:  94%|█████████▍| 34447/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.62.gate_proj:  94%|█████████▍| 34448/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.62.up_proj:  94%|█████████▍| 34449/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.62.down_proj:  94%|█████████▍| 34450/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.63.gate_proj:  94%|█████████▍| 34451/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.63.up_proj:  94%|█████████▍| 34452/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.63.down_proj:  94%|█████████▍| 34453/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.64.gate_proj:  94%|█████████▍| 34454/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.64.up_proj:  94%|█████████▍| 34455/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.64.down_proj:  94%|█████████▍| 34456/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.65.gate_proj:  94%|█████████▍| 34457/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.65.up_proj:  94%|█████████▍| 34458/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.65.down_proj:  94%|█████████▍| 34459/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.66.gate_proj:  94%|█████████▍| 34460/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.66.up_proj:  94%|█████████▍| 34461/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.66.down_proj:  94%|█████████▍| 34462/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.67.gate_proj:  94%|█████████▍| 34463/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.67.up_proj:  94%|█████████▍| 34464/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.67.down_proj:  94%|█████████▍| 34465/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.68.gate_proj:  94%|█████████▍| 34466/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.68.up_proj:  94%|█████████▍| 34467/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.68.down_proj:  94%|█████████▍| 34468/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.69.gate_proj:  94%|█████████▍| 34469/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.69.up_proj:  94%|█████████▍| 34470/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.69.down_proj:  94%|█████████▍| 34471/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.70.gate_proj:  94%|█████████▍| 34472/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.70.up_proj:  94%|█████████▍| 34473/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.70.down_proj:  94%|█████████▍| 34474/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.71.gate_proj:  94%|█████████▍| 34475/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.71.up_proj:  94%|█████████▍| 34476/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.71.down_proj:  94%|█████████▍| 34477/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.72.gate_proj:  94%|█████████▍| 34478/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.72.up_proj:  94%|█████████▍| 34479/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.72.down_proj:  94%|█████████▍| 34480/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.73.gate_proj:  94%|█████████▍| 34481/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.73.up_proj:  94%|█████████▍| 34482/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.73.down_proj:  94%|█████████▍| 34483/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.74.gate_proj:  94%|█████████▍| 34484/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.74.up_proj:  94%|█████████▍| 34485/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.74.down_proj:  94%|█████████▍| 34486/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.75.gate_proj:  94%|█████████▍| 34487/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.75.up_proj:  94%|█████████▍| 34488/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.75.down_proj:  94%|█████████▍| 34489/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.76.gate_proj:  94%|█████████▍| 34490/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.76.up_proj:  94%|█████████▍| 34491/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.76.down_proj:  94%|█████████▍| 34492/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.77.gate_proj:  94%|█████████▍| 34493/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.77.up_proj:  94%|█████████▍| 34494/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.77.down_proj:  94%|█████████▍| 34495/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.78.gate_proj:  94%|█████████▍| 34496/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.78.up_proj:  94%|█████████▍| 34497/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.78.down_proj:  94%|█████████▍| 34498/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.79.gate_proj:  94%|█████████▍| 34499/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.79.up_proj:  94%|█████████▍| 34500/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.79.down_proj:  94%|█████████▍| 34501/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.80.gate_proj:  94%|█████████▍| 34502/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.80.up_proj:  94%|█████████▍| 34503/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.80.down_proj:  94%|█████████▍| 34504/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.81.gate_proj:  94%|█████████▍| 34505/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.81.up_proj:  94%|█████████▍| 34506/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.81.down_proj:  94%|█████████▍| 34507/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.82.gate_proj:  94%|█████████▍| 34508/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.82.up_proj:  94%|█████████▍| 34509/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.82.down_proj:  94%|█████████▍| 34510/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.83.gate_proj:  94%|█████████▍| 34511/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.83.up_proj:  94%|█████████▍| 34512/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.83.down_proj:  94%|█████████▍| 34513/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.84.gate_proj:  94%|█████████▍| 34514/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.84.up_proj:  94%|█████████▍| 34515/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.84.down_proj:  94%|█████████▍| 34516/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.85.gate_proj:  94%|█████████▍| 34517/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.85.up_proj:  94%|█████████▍| 34518/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.85.down_proj:  94%|█████████▍| 34519/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.86.gate_proj:  94%|█████████▍| 34520/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.86.up_proj:  94%|█████████▍| 34521/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.86.down_proj:  94%|█████████▍| 34522/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.87.gate_proj:  94%|█████████▍| 34523/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.87.up_proj:  94%|█████████▍| 34524/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.87.down_proj:  94%|█████████▍| 34525/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.88.gate_proj:  94%|█████████▍| 34526/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.88.up_proj:  94%|█████████▍| 34527/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.88.down_proj:  94%|█████████▍| 34528/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.89.gate_proj:  94%|█████████▍| 34529/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.89.up_proj:  94%|█████████▍| 34530/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.89.down_proj:  94%|█████████▍| 34531/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.90.gate_proj:  94%|█████████▍| 34532/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.90.up_proj:  94%|█████████▍| 34533/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.90.down_proj:  94%|█████████▍| 34534/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.91.gate_proj:  94%|█████████▍| 34535/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.91.up_proj:  94%|█████████▍| 34536/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.91.down_proj:  94%|█████████▍| 34537/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.92.gate_proj:  94%|█████████▍| 34538/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.92.up_proj:  94%|█████████▍| 34539/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.92.down_proj:  94%|█████████▍| 34540/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.93.gate_proj:  94%|█████████▍| 34541/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.93.up_proj:  94%|█████████▍| 34542/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.93.down_proj:  94%|█████████▍| 34543/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.94.gate_proj:  94%|█████████▍| 34544/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.94.up_proj:  94%|█████████▍| 34545/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.94.down_proj:  94%|█████████▍| 34546/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.95.gate_proj:  94%|█████████▍| 34547/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.95.up_proj:  94%|█████████▍| 34548/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.95.down_proj:  94%|█████████▍| 34549/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.96.gate_proj:  94%|█████████▍| 34550/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.96.up_proj:  94%|█████████▍| 34551/36566 [00:31<00:01, 1150.61it/s]  
packing model.layers.88.mlp.experts.96.down_proj:  94%|█████████▍| 34552/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.97.gate_proj:  94%|█████████▍| 34553/36566 [00:31<00:01, 1150.61it/s]
packing model.layers.88.mlp.experts.97.gate_proj:  94%|█████████▍| 34554/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.97.up_proj:  94%|█████████▍| 34554/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.97.down_proj:  95%|█████████▍| 34555/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.98.gate_proj:  95%|█████████▍| 34556/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.98.up_proj:  95%|█████████▍| 34557/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.98.down_proj:  95%|█████████▍| 34558/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.99.gate_proj:  95%|█████████▍| 34559/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.99.up_proj:  95%|█████████▍| 34560/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.99.down_proj:  95%|█████████▍| 34561/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.100.gate_proj:  95%|█████████▍| 34562/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.100.up_proj:  95%|█████████▍| 34563/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.100.down_proj:  95%|█████████▍| 34564/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.101.gate_proj:  95%|█████████▍| 34565/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.101.up_proj:  95%|█████████▍| 34566/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.101.down_proj:  95%|█████████▍| 34567/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.102.gate_proj:  95%|█████████▍| 34568/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.102.up_proj:  95%|█████████▍| 34569/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.102.down_proj:  95%|█████████▍| 34570/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.103.gate_proj:  95%|█████████▍| 34571/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.103.up_proj:  95%|█████████▍| 34572/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.103.down_proj:  95%|█████████▍| 34573/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.104.gate_proj:  95%|█████████▍| 34574/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.104.up_proj:  95%|█████████▍| 34575/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.104.down_proj:  95%|█████████▍| 34576/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.105.gate_proj:  95%|█████████▍| 34577/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.105.up_proj:  95%|█████████▍| 34578/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.105.down_proj:  95%|█████████▍| 34579/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.106.gate_proj:  95%|█████████▍| 34580/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.106.up_proj:  95%|█████████▍| 34581/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.106.down_proj:  95%|█████████▍| 34582/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.107.gate_proj:  95%|█████████▍| 34583/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.107.up_proj:  95%|█████████▍| 34584/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.107.down_proj:  95%|█████████▍| 34585/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.108.gate_proj:  95%|█████████▍| 34586/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.108.up_proj:  95%|█████████▍| 34587/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.108.down_proj:  95%|█████████▍| 34588/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.109.gate_proj:  95%|█████████▍| 34589/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.109.up_proj:  95%|█████████▍| 34590/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.109.down_proj:  95%|█████████▍| 34591/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.110.gate_proj:  95%|█████████▍| 34592/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.110.up_proj:  95%|█████████▍| 34593/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.110.down_proj:  95%|█████████▍| 34594/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.111.gate_proj:  95%|█████████▍| 34595/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.111.up_proj:  95%|█████████▍| 34596/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.111.down_proj:  95%|█████████▍| 34597/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.112.gate_proj:  95%|█████████▍| 34598/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.112.up_proj:  95%|█████████▍| 34599/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.112.down_proj:  95%|█████████▍| 34600/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.113.gate_proj:  95%|█████████▍| 34601/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.113.up_proj:  95%|█████████▍| 34602/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.113.down_proj:  95%|█████████▍| 34603/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.114.gate_proj:  95%|█████████▍| 34604/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.114.up_proj:  95%|█████████▍| 34605/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.114.down_proj:  95%|█████████▍| 34606/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.115.gate_proj:  95%|█████████▍| 34607/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.115.up_proj:  95%|█████████▍| 34608/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.115.down_proj:  95%|█████████▍| 34609/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.116.gate_proj:  95%|█████████▍| 34610/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.116.up_proj:  95%|█████████▍| 34611/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.116.down_proj:  95%|█████████▍| 34612/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.117.gate_proj:  95%|█████████▍| 34613/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.117.up_proj:  95%|█████████▍| 34614/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.117.down_proj:  95%|█████████▍| 34615/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.118.gate_proj:  95%|█████████▍| 34616/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.118.up_proj:  95%|█████████▍| 34617/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.118.down_proj:  95%|█████████▍| 34618/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.119.gate_proj:  95%|█████████▍| 34619/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.119.up_proj:  95%|█████████▍| 34620/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.119.down_proj:  95%|█████████▍| 34621/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.120.gate_proj:  95%|█████████▍| 34622/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.120.up_proj:  95%|█████████▍| 34623/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.120.down_proj:  95%|█████████▍| 34624/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.121.gate_proj:  95%|█████████▍| 34625/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.121.up_proj:  95%|█████████▍| 34626/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.121.down_proj:  95%|█████████▍| 34627/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.122.gate_proj:  95%|█████████▍| 34628/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.122.up_proj:  95%|█████████▍| 34629/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.122.down_proj:  95%|█████████▍| 34630/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.123.gate_proj:  95%|█████████▍| 34631/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.123.up_proj:  95%|█████████▍| 34632/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.123.down_proj:  95%|█████████▍| 34633/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.124.gate_proj:  95%|█████████▍| 34634/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.124.up_proj:  95%|█████████▍| 34635/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.124.down_proj:  95%|█████████▍| 34636/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.125.gate_proj:  95%|█████████▍| 34637/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.125.up_proj:  95%|█████████▍| 34638/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.125.down_proj:  95%|█████████▍| 34639/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.126.gate_proj:  95%|█████████▍| 34640/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.126.up_proj:  95%|█████████▍| 34641/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.126.down_proj:  95%|█████████▍| 34642/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.127.gate_proj:  95%|█████████▍| 34643/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.88.mlp.experts.127.up_proj:  95%|█████████▍| 34644/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.88.mlp.experts.127.down_proj:  95%|█████████▍| 34645/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.0.gate_proj:  95%|█████████▍| 34646/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.0.up_proj:  95%|█████████▍| 34647/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.0.down_proj:  95%|█████████▍| 34648/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.1.gate_proj:  95%|█████████▍| 34649/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.1.up_proj:  95%|█████████▍| 34650/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.1.down_proj:  95%|█████████▍| 34651/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.2.gate_proj:  95%|█████████▍| 34652/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.2.up_proj:  95%|█████████▍| 34653/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.2.down_proj:  95%|█████████▍| 34654/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.3.gate_proj:  95%|█████████▍| 34655/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.3.up_proj:  95%|█████████▍| 34656/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.3.down_proj:  95%|█████████▍| 34657/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.4.gate_proj:  95%|█████████▍| 34658/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.4.up_proj:  95%|█████████▍| 34659/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.4.down_proj:  95%|█████████▍| 34660/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.5.gate_proj:  95%|█████████▍| 34661/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.5.up_proj:  95%|█████████▍| 34662/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.5.down_proj:  95%|█████████▍| 34663/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.6.gate_proj:  95%|█████████▍| 34664/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.6.up_proj:  95%|█████████▍| 34665/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.6.down_proj:  95%|█████████▍| 34666/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.7.gate_proj:  95%|█████████▍| 34667/36566 [00:31<00:01, 1149.44it/s]
packing model.layers.89.mlp.experts.7.up_proj:  95%|█████████▍| 34668/36566 [00:31<00:01, 1149.44it/s]  
packing model.layers.89.mlp.experts.7.up_proj:  95%|█████████▍| 34669/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.7.down_proj:  95%|█████████▍| 34669/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.8.gate_proj:  95%|█████████▍| 34670/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.8.up_proj:  95%|█████████▍| 34671/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.8.down_proj:  95%|█████████▍| 34672/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.9.gate_proj:  95%|█████████▍| 34673/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.9.up_proj:  95%|█████████▍| 34674/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.9.down_proj:  95%|█████████▍| 34675/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.10.gate_proj:  95%|█████████▍| 34676/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.10.up_proj:  95%|█████████▍| 34677/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.10.down_proj:  95%|█████████▍| 34678/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.11.gate_proj:  95%|█████████▍| 34679/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.11.up_proj:  95%|█████████▍| 34680/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.11.down_proj:  95%|█████████▍| 34681/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.12.gate_proj:  95%|█████████▍| 34682/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.12.up_proj:  95%|█████████▍| 34683/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.12.down_proj:  95%|█████████▍| 34684/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.13.gate_proj:  95%|█████████▍| 34685/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.13.up_proj:  95%|█████████▍| 34686/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.13.down_proj:  95%|█████████▍| 34687/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.14.gate_proj:  95%|█████████▍| 34688/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.14.up_proj:  95%|█████████▍| 34689/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.14.down_proj:  95%|█████████▍| 34690/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.15.gate_proj:  95%|█████████▍| 34691/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.15.up_proj:  95%|█████████▍| 34692/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.15.down_proj:  95%|█████████▍| 34693/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.16.gate_proj:  95%|█████████▍| 34694/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.16.up_proj:  95%|█████████▍| 34695/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.16.down_proj:  95%|█████████▍| 34696/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.17.gate_proj:  95%|█████████▍| 34697/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.17.up_proj:  95%|█████████▍| 34698/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.17.down_proj:  95%|█████████▍| 34699/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.18.gate_proj:  95%|█████████▍| 34700/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.18.up_proj:  95%|█████████▍| 34701/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.18.down_proj:  95%|█████████▍| 34702/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.19.gate_proj:  95%|█████████▍| 34703/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.19.up_proj:  95%|█████████▍| 34704/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.19.down_proj:  95%|█████████▍| 34705/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.20.gate_proj:  95%|█████████▍| 34706/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.20.up_proj:  95%|█████████▍| 34707/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.20.down_proj:  95%|█████████▍| 34708/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.21.gate_proj:  95%|█████████▍| 34709/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.21.up_proj:  95%|█████████▍| 34710/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.21.down_proj:  95%|█████████▍| 34711/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.22.gate_proj:  95%|█████████▍| 34712/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.22.up_proj:  95%|█████████▍| 34713/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.22.down_proj:  95%|█████████▍| 34714/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.23.gate_proj:  95%|█████████▍| 34715/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.23.up_proj:  95%|█████████▍| 34716/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.23.down_proj:  95%|█████████▍| 34717/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.24.gate_proj:  95%|█████████▍| 34718/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.24.up_proj:  95%|█████████▍| 34719/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.24.down_proj:  95%|█████████▍| 34720/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.25.gate_proj:  95%|█████████▍| 34721/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.25.up_proj:  95%|█████████▍| 34722/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.25.down_proj:  95%|█████████▍| 34723/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.26.gate_proj:  95%|█████████▍| 34724/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.26.up_proj:  95%|█████████▍| 34725/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.26.down_proj:  95%|█████████▍| 34726/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.27.gate_proj:  95%|█████████▍| 34727/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.27.up_proj:  95%|█████████▍| 34728/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.27.down_proj:  95%|█████████▍| 34729/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.28.gate_proj:  95%|█████████▍| 34730/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.28.up_proj:  95%|█████████▍| 34731/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.28.down_proj:  95%|█████████▍| 34732/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.29.gate_proj:  95%|█████████▍| 34733/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.29.up_proj:  95%|█████████▍| 34734/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.29.down_proj:  95%|█████████▍| 34735/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.30.gate_proj:  95%|█████████▍| 34736/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.30.up_proj:  95%|█████████▍| 34737/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.30.down_proj:  95%|█████████▌| 34738/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.31.gate_proj:  95%|█████████▌| 34739/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.31.up_proj:  95%|█████████▌| 34740/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.31.down_proj:  95%|█████████▌| 34741/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.32.gate_proj:  95%|█████████▌| 34742/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.32.up_proj:  95%|█████████▌| 34743/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.32.down_proj:  95%|█████████▌| 34744/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.33.gate_proj:  95%|█████████▌| 34745/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.33.up_proj:  95%|█████████▌| 34746/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.33.down_proj:  95%|█████████▌| 34747/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.34.gate_proj:  95%|█████████▌| 34748/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.34.up_proj:  95%|█████████▌| 34749/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.34.down_proj:  95%|█████████▌| 34750/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.35.gate_proj:  95%|█████████▌| 34751/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.35.up_proj:  95%|█████████▌| 34752/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.35.down_proj:  95%|█████████▌| 34753/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.36.gate_proj:  95%|█████████▌| 34754/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.36.up_proj:  95%|█████████▌| 34755/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.36.down_proj:  95%|█████████▌| 34756/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.37.gate_proj:  95%|█████████▌| 34757/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.37.up_proj:  95%|█████████▌| 34758/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.37.down_proj:  95%|█████████▌| 34759/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.38.gate_proj:  95%|█████████▌| 34760/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.38.up_proj:  95%|█████████▌| 34761/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.38.down_proj:  95%|█████████▌| 34762/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.39.gate_proj:  95%|█████████▌| 34763/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.39.up_proj:  95%|█████████▌| 34764/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.39.down_proj:  95%|█████████▌| 34765/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.40.gate_proj:  95%|█████████▌| 34766/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.40.up_proj:  95%|█████████▌| 34767/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.40.down_proj:  95%|█████████▌| 34768/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.41.gate_proj:  95%|█████████▌| 34769/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.41.up_proj:  95%|█████████▌| 34770/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.41.down_proj:  95%|█████████▌| 34771/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.42.gate_proj:  95%|█████████▌| 34772/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.42.up_proj:  95%|█████████▌| 34773/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.42.down_proj:  95%|█████████▌| 34774/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.43.gate_proj:  95%|█████████▌| 34775/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.43.up_proj:  95%|█████████▌| 34776/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.43.down_proj:  95%|█████████▌| 34777/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.44.gate_proj:  95%|█████████▌| 34778/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.44.up_proj:  95%|█████████▌| 34779/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.44.down_proj:  95%|█████████▌| 34780/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.45.gate_proj:  95%|█████████▌| 34781/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.45.up_proj:  95%|█████████▌| 34782/36566 [00:31<00:01, 1145.83it/s]  
packing model.layers.89.mlp.experts.45.down_proj:  95%|█████████▌| 34783/36566 [00:31<00:01, 1145.83it/s]
packing model.layers.89.mlp.experts.45.down_proj:  95%|█████████▌| 34784/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.46.gate_proj:  95%|█████████▌| 34784/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.46.up_proj:  95%|█████████▌| 34785/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.46.down_proj:  95%|█████████▌| 34786/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.47.gate_proj:  95%|█████████▌| 34787/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.47.up_proj:  95%|█████████▌| 34788/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.47.down_proj:  95%|█████████▌| 34789/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.48.gate_proj:  95%|█████████▌| 34790/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.48.up_proj:  95%|█████████▌| 34791/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.48.down_proj:  95%|█████████▌| 34792/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.49.gate_proj:  95%|█████████▌| 34793/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.49.up_proj:  95%|█████████▌| 34794/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.49.down_proj:  95%|█████████▌| 34795/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.50.gate_proj:  95%|█████████▌| 34796/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.50.up_proj:  95%|█████████▌| 34797/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.50.down_proj:  95%|█████████▌| 34798/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.51.gate_proj:  95%|█████████▌| 34799/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.51.up_proj:  95%|█████████▌| 34800/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.51.down_proj:  95%|█████████▌| 34801/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.52.gate_proj:  95%|█████████▌| 34802/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.52.up_proj:  95%|█████████▌| 34803/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.52.down_proj:  95%|█████████▌| 34804/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.53.gate_proj:  95%|█████████▌| 34805/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.53.up_proj:  95%|█████████▌| 34806/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.53.down_proj:  95%|█████████▌| 34807/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.54.gate_proj:  95%|█████████▌| 34808/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.54.up_proj:  95%|█████████▌| 34809/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.54.down_proj:  95%|█████████▌| 34810/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.55.gate_proj:  95%|█████████▌| 34811/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.55.up_proj:  95%|█████████▌| 34812/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.55.down_proj:  95%|█████████▌| 34813/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.56.gate_proj:  95%|█████████▌| 34814/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.56.up_proj:  95%|█████████▌| 34815/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.56.down_proj:  95%|█████████▌| 34816/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.57.gate_proj:  95%|█████████▌| 34817/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.57.up_proj:  95%|█████████▌| 34818/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.57.down_proj:  95%|█████████▌| 34819/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.58.gate_proj:  95%|█████████▌| 34820/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.58.up_proj:  95%|█████████▌| 34821/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.58.down_proj:  95%|█████████▌| 34822/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.59.gate_proj:  95%|█████████▌| 34823/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.59.up_proj:  95%|█████████▌| 34824/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.59.down_proj:  95%|█████████▌| 34825/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.60.gate_proj:  95%|█████████▌| 34826/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.60.up_proj:  95%|█████████▌| 34827/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.60.down_proj:  95%|█████████▌| 34828/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.61.gate_proj:  95%|█████████▌| 34829/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.61.up_proj:  95%|█████████▌| 34830/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.61.down_proj:  95%|█████████▌| 34831/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.62.gate_proj:  95%|█████████▌| 34832/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.62.up_proj:  95%|█████████▌| 34833/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.62.down_proj:  95%|█████████▌| 34834/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.63.gate_proj:  95%|█████████▌| 34835/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.63.up_proj:  95%|█████████▌| 34836/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.63.down_proj:  95%|█████████▌| 34837/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.64.gate_proj:  95%|█████████▌| 34838/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.64.up_proj:  95%|█████████▌| 34839/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.64.down_proj:  95%|█████████▌| 34840/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.65.gate_proj:  95%|█████████▌| 34841/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.65.up_proj:  95%|█████████▌| 34842/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.65.down_proj:  95%|█████████▌| 34843/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.66.gate_proj:  95%|█████████▌| 34844/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.66.up_proj:  95%|█████████▌| 34845/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.66.down_proj:  95%|█████████▌| 34846/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.67.gate_proj:  95%|█████████▌| 34847/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.67.up_proj:  95%|█████████▌| 34848/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.67.down_proj:  95%|█████████▌| 34849/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.68.gate_proj:  95%|█████████▌| 34850/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.68.up_proj:  95%|█████████▌| 34851/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.68.down_proj:  95%|█████████▌| 34852/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.69.gate_proj:  95%|█████████▌| 34853/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.69.up_proj:  95%|█████████▌| 34854/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.69.down_proj:  95%|█████████▌| 34855/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.70.gate_proj:  95%|█████████▌| 34856/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.70.up_proj:  95%|█████████▌| 34857/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.70.down_proj:  95%|█████████▌| 34858/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.71.gate_proj:  95%|█████████▌| 34859/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.71.up_proj:  95%|█████████▌| 34860/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.71.down_proj:  95%|█████████▌| 34861/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.72.gate_proj:  95%|█████████▌| 34862/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.72.up_proj:  95%|█████████▌| 34863/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.72.down_proj:  95%|█████████▌| 34864/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.73.gate_proj:  95%|█████████▌| 34865/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.73.up_proj:  95%|█████████▌| 34866/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.73.down_proj:  95%|█████████▌| 34867/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.74.gate_proj:  95%|█████████▌| 34868/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.74.up_proj:  95%|█████████▌| 34869/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.74.down_proj:  95%|█████████▌| 34870/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.75.gate_proj:  95%|█████████▌| 34871/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.75.up_proj:  95%|█████████▌| 34872/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.75.down_proj:  95%|█████████▌| 34873/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.76.gate_proj:  95%|█████████▌| 34874/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.76.up_proj:  95%|█████████▌| 34875/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.76.down_proj:  95%|█████████▌| 34876/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.77.gate_proj:  95%|█████████▌| 34877/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.77.up_proj:  95%|█████████▌| 34878/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.77.down_proj:  95%|█████████▌| 34879/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.78.gate_proj:  95%|█████████▌| 34880/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.78.up_proj:  95%|█████████▌| 34881/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.78.down_proj:  95%|█████████▌| 34882/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.79.gate_proj:  95%|█████████▌| 34883/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.79.up_proj:  95%|█████████▌| 34884/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.79.down_proj:  95%|█████████▌| 34885/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.80.gate_proj:  95%|█████████▌| 34886/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.80.up_proj:  95%|█████████▌| 34887/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.80.down_proj:  95%|█████████▌| 34888/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.81.gate_proj:  95%|█████████▌| 34889/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.81.up_proj:  95%|█████████▌| 34890/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.81.down_proj:  95%|█████████▌| 34891/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.82.gate_proj:  95%|█████████▌| 34892/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.82.up_proj:  95%|█████████▌| 34893/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.82.down_proj:  95%|█████████▌| 34894/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.83.gate_proj:  95%|█████████▌| 34895/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.83.up_proj:  95%|█████████▌| 34896/36566 [00:31<00:01, 1145.61it/s]  
packing model.layers.89.mlp.experts.83.down_proj:  95%|█████████▌| 34897/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.84.gate_proj:  95%|█████████▌| 34898/36566 [00:31<00:01, 1145.61it/s]
packing model.layers.89.mlp.experts.84.gate_proj:  95%|█████████▌| 34899/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.84.up_proj:  95%|█████████▌| 34899/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.84.down_proj:  95%|█████████▌| 34900/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.85.gate_proj:  95%|█████████▌| 34901/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.85.up_proj:  95%|█████████▌| 34902/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.85.down_proj:  95%|█████████▌| 34903/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.86.gate_proj:  95%|█████████▌| 34904/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.86.up_proj:  95%|█████████▌| 34905/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.86.down_proj:  95%|█████████▌| 34906/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.87.gate_proj:  95%|█████████▌| 34907/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.87.up_proj:  95%|█████████▌| 34908/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.87.down_proj:  95%|█████████▌| 34909/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.88.gate_proj:  95%|█████████▌| 34910/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.88.up_proj:  95%|█████████▌| 34911/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.88.down_proj:  95%|█████████▌| 34912/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.89.gate_proj:  95%|█████████▌| 34913/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.89.up_proj:  95%|█████████▌| 34914/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.89.down_proj:  95%|█████████▌| 34915/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.90.gate_proj:  95%|█████████▌| 34916/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.90.up_proj:  95%|█████████▌| 34917/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.90.down_proj:  95%|█████████▌| 34918/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.91.gate_proj:  95%|█████████▌| 34919/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.91.up_proj:  95%|█████████▌| 34920/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.91.down_proj:  96%|█████████▌| 34921/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.92.gate_proj:  96%|█████████▌| 34922/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.92.up_proj:  96%|█████████▌| 34923/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.92.down_proj:  96%|█████████▌| 34924/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.93.gate_proj:  96%|█████████▌| 34925/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.93.up_proj:  96%|█████████▌| 34926/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.93.down_proj:  96%|█████████▌| 34927/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.94.gate_proj:  96%|█████████▌| 34928/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.94.up_proj:  96%|█████████▌| 34929/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.94.down_proj:  96%|█████████▌| 34930/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.95.gate_proj:  96%|█████████▌| 34931/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.95.up_proj:  96%|█████████▌| 34932/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.95.down_proj:  96%|█████████▌| 34933/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.96.gate_proj:  96%|█████████▌| 34934/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.96.up_proj:  96%|█████████▌| 34935/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.96.down_proj:  96%|█████████▌| 34936/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.97.gate_proj:  96%|█████████▌| 34937/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.97.up_proj:  96%|█████████▌| 34938/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.97.down_proj:  96%|█████████▌| 34939/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.98.gate_proj:  96%|█████████▌| 34940/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.98.up_proj:  96%|█████████▌| 34941/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.98.down_proj:  96%|█████████▌| 34942/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.99.gate_proj:  96%|█████████▌| 34943/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.99.up_proj:  96%|█████████▌| 34944/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.99.down_proj:  96%|█████████▌| 34945/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.100.gate_proj:  96%|█████████▌| 34946/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.100.up_proj:  96%|█████████▌| 34947/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.100.down_proj:  96%|█████████▌| 34948/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.101.gate_proj:  96%|█████████▌| 34949/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.101.up_proj:  96%|█████████▌| 34950/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.101.down_proj:  96%|█████████▌| 34951/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.102.gate_proj:  96%|█████████▌| 34952/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.102.up_proj:  96%|█████████▌| 34953/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.102.down_proj:  96%|█████████▌| 34954/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.103.gate_proj:  96%|█████████▌| 34955/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.103.up_proj:  96%|█████████▌| 34956/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.103.down_proj:  96%|█████████▌| 34957/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.104.gate_proj:  96%|█████████▌| 34958/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.104.up_proj:  96%|█████████▌| 34959/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.104.down_proj:  96%|█████████▌| 34960/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.105.gate_proj:  96%|█████████▌| 34961/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.105.up_proj:  96%|█████████▌| 34962/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.105.down_proj:  96%|█████████▌| 34963/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.106.gate_proj:  96%|█████████▌| 34964/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.106.up_proj:  96%|█████████▌| 34965/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.106.down_proj:  96%|█████████▌| 34966/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.107.gate_proj:  96%|█████████▌| 34967/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.107.up_proj:  96%|█████████▌| 34968/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.107.down_proj:  96%|█████████▌| 34969/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.108.gate_proj:  96%|█████████▌| 34970/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.108.up_proj:  96%|█████████▌| 34971/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.108.down_proj:  96%|█████████▌| 34972/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.109.gate_proj:  96%|█████████▌| 34973/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.109.up_proj:  96%|█████████▌| 34974/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.109.down_proj:  96%|█████████▌| 34975/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.110.gate_proj:  96%|█████████▌| 34976/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.110.up_proj:  96%|█████████▌| 34977/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.110.down_proj:  96%|█████████▌| 34978/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.111.gate_proj:  96%|█████████▌| 34979/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.111.up_proj:  96%|█████████▌| 34980/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.111.down_proj:  96%|█████████▌| 34981/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.112.gate_proj:  96%|█████████▌| 34982/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.112.up_proj:  96%|█████████▌| 34983/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.112.down_proj:  96%|█████████▌| 34984/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.113.gate_proj:  96%|█████████▌| 34985/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.113.up_proj:  96%|█████████▌| 34986/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.113.down_proj:  96%|█████████▌| 34987/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.114.gate_proj:  96%|█████████▌| 34988/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.114.up_proj:  96%|█████████▌| 34989/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.114.down_proj:  96%|█████████▌| 34990/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.115.gate_proj:  96%|█████████▌| 34991/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.115.up_proj:  96%|█████████▌| 34992/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.115.down_proj:  96%|█████████▌| 34993/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.116.gate_proj:  96%|█████████▌| 34994/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.116.up_proj:  96%|█████████▌| 34995/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.116.down_proj:  96%|█████████▌| 34996/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.117.gate_proj:  96%|█████████▌| 34997/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.117.up_proj:  96%|█████████▌| 34998/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.117.down_proj:  96%|█████████▌| 34999/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.118.gate_proj:  96%|█████████▌| 35000/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.118.up_proj:  96%|█████████▌| 35001/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.118.down_proj:  96%|█████████▌| 35002/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.119.gate_proj:  96%|█████████▌| 35003/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.119.up_proj:  96%|█████████▌| 35004/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.119.down_proj:  96%|█████████▌| 35005/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.120.gate_proj:  96%|█████████▌| 35006/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.120.up_proj:  96%|█████████▌| 35007/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.120.down_proj:  96%|█████████▌| 35008/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.121.gate_proj:  96%|█████████▌| 35009/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.121.up_proj:  96%|█████████▌| 35010/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.121.down_proj:  96%|█████████▌| 35011/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.122.gate_proj:  96%|█████████▌| 35012/36566 [00:31<00:01, 1146.30it/s]
packing model.layers.89.mlp.experts.122.up_proj:  96%|█████████▌| 35013/36566 [00:31<00:01, 1146.30it/s]  
packing model.layers.89.mlp.experts.122.up_proj:  96%|█████████▌| 35014/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.122.down_proj:  96%|█████████▌| 35014/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.123.gate_proj:  96%|█████████▌| 35015/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.123.up_proj:  96%|█████████▌| 35016/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.89.mlp.experts.123.down_proj:  96%|█████████▌| 35017/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.124.gate_proj:  96%|█████████▌| 35018/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.124.up_proj:  96%|█████████▌| 35019/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.89.mlp.experts.124.down_proj:  96%|█████████▌| 35020/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.125.gate_proj:  96%|█████████▌| 35021/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.125.up_proj:  96%|█████████▌| 35022/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.89.mlp.experts.125.down_proj:  96%|█████████▌| 35023/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.126.gate_proj:  96%|█████████▌| 35024/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.126.up_proj:  96%|█████████▌| 35025/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.89.mlp.experts.126.down_proj:  96%|█████████▌| 35026/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.127.gate_proj:  96%|█████████▌| 35027/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.89.mlp.experts.127.up_proj:  96%|█████████▌| 35028/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.89.mlp.experts.127.down_proj:  96%|█████████▌| 35029/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.0.gate_proj:  96%|█████████▌| 35030/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.0.up_proj:  96%|█████████▌| 35031/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.0.down_proj:  96%|█████████▌| 35032/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.1.gate_proj:  96%|█████████▌| 35033/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.1.up_proj:  96%|█████████▌| 35034/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.1.down_proj:  96%|█████████▌| 35035/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.2.gate_proj:  96%|█████████▌| 35036/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.2.up_proj:  96%|█████████▌| 35037/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.2.down_proj:  96%|█████████▌| 35038/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.3.gate_proj:  96%|█████████▌| 35039/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.3.up_proj:  96%|█████████▌| 35040/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.3.down_proj:  96%|█████████▌| 35041/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.4.gate_proj:  96%|█████████▌| 35042/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.4.up_proj:  96%|█████████▌| 35043/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.4.down_proj:  96%|█████████▌| 35044/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.5.gate_proj:  96%|█████████▌| 35045/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.5.up_proj:  96%|█████████▌| 35046/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.5.down_proj:  96%|█████████▌| 35047/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.6.gate_proj:  96%|█████████▌| 35048/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.6.up_proj:  96%|█████████▌| 35049/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.6.down_proj:  96%|█████████▌| 35050/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.7.gate_proj:  96%|█████████▌| 35051/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.7.up_proj:  96%|█████████▌| 35052/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.7.down_proj:  96%|█████████▌| 35053/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.8.gate_proj:  96%|█████████▌| 35054/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.8.up_proj:  96%|█████████▌| 35055/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.8.down_proj:  96%|█████████▌| 35056/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.9.gate_proj:  96%|█████████▌| 35057/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.9.up_proj:  96%|█████████▌| 35058/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.9.down_proj:  96%|█████████▌| 35059/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.10.gate_proj:  96%|█████████▌| 35060/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.10.up_proj:  96%|█████████▌| 35061/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.10.down_proj:  96%|█████████▌| 35062/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.11.gate_proj:  96%|█████████▌| 35063/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.11.up_proj:  96%|█████████▌| 35064/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.11.down_proj:  96%|█████████▌| 35065/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.12.gate_proj:  96%|█████████▌| 35066/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.12.up_proj:  96%|█████████▌| 35067/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.12.down_proj:  96%|█████████▌| 35068/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.13.gate_proj:  96%|█████████▌| 35069/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.13.up_proj:  96%|█████████▌| 35070/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.13.down_proj:  96%|█████████▌| 35071/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.14.gate_proj:  96%|█████████▌| 35072/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.14.up_proj:  96%|█████████▌| 35073/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.14.down_proj:  96%|█████████▌| 35074/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.15.gate_proj:  96%|█████████▌| 35075/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.15.up_proj:  96%|█████████▌| 35076/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.15.down_proj:  96%|█████████▌| 35077/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.16.gate_proj:  96%|█████████▌| 35078/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.16.up_proj:  96%|█████████▌| 35079/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.16.down_proj:  96%|█████████▌| 35080/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.17.gate_proj:  96%|█████████▌| 35081/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.17.up_proj:  96%|█████████▌| 35082/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.17.down_proj:  96%|█████████▌| 35083/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.18.gate_proj:  96%|█████████▌| 35084/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.18.up_proj:  96%|█████████▌| 35085/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.18.down_proj:  96%|█████████▌| 35086/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.19.gate_proj:  96%|█████████▌| 35087/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.19.up_proj:  96%|█████████▌| 35088/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.19.down_proj:  96%|█████████▌| 35089/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.20.gate_proj:  96%|█████████▌| 35090/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.20.up_proj:  96%|█████████▌| 35091/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.20.down_proj:  96%|█████████▌| 35092/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.21.gate_proj:  96%|█████████▌| 35093/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.21.up_proj:  96%|█████████▌| 35094/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.21.down_proj:  96%|█████████▌| 35095/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.22.gate_proj:  96%|█████████▌| 35096/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.22.up_proj:  96%|█████████▌| 35097/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.22.down_proj:  96%|█████████▌| 35098/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.23.gate_proj:  96%|█████████▌| 35099/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.23.up_proj:  96%|█████████▌| 35100/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.23.down_proj:  96%|█████████▌| 35101/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.24.gate_proj:  96%|█████████▌| 35102/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.24.up_proj:  96%|█████████▌| 35103/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.24.down_proj:  96%|█████████▌| 35104/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.25.gate_proj:  96%|█████████▌| 35105/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.25.up_proj:  96%|█████████▌| 35106/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.25.down_proj:  96%|█████████▌| 35107/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.26.gate_proj:  96%|█████████▌| 35108/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.26.up_proj:  96%|█████████▌| 35109/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.26.down_proj:  96%|█████████▌| 35110/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.27.gate_proj:  96%|█████████▌| 35111/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.27.up_proj:  96%|█████████▌| 35112/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.27.down_proj:  96%|█████████▌| 35113/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.28.gate_proj:  96%|█████████▌| 35114/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.28.up_proj:  96%|█████████▌| 35115/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.28.down_proj:  96%|█████████▌| 35116/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.29.gate_proj:  96%|█████████▌| 35117/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.29.up_proj:  96%|█████████▌| 35118/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.29.down_proj:  96%|█████████▌| 35119/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.30.gate_proj:  96%|█████████▌| 35120/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.30.up_proj:  96%|█████████▌| 35121/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.30.down_proj:  96%|█████████▌| 35122/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.31.gate_proj:  96%|█████████▌| 35123/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.31.up_proj:  96%|█████████▌| 35124/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.31.down_proj:  96%|█████████▌| 35125/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.32.gate_proj:  96%|█████████▌| 35126/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.32.up_proj:  96%|█████████▌| 35127/36566 [00:31<00:01, 1146.55it/s]  
packing model.layers.90.mlp.experts.32.down_proj:  96%|█████████▌| 35128/36566 [00:31<00:01, 1146.55it/s]
packing model.layers.90.mlp.experts.32.down_proj:  96%|█████████▌| 35129/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.33.gate_proj:  96%|█████████▌| 35129/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.33.up_proj:  96%|█████████▌| 35130/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.33.down_proj:  96%|█████████▌| 35131/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.34.gate_proj:  96%|█████████▌| 35132/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.34.up_proj:  96%|█████████▌| 35133/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.34.down_proj:  96%|█████████▌| 35134/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.35.gate_proj:  96%|█████████▌| 35135/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.35.up_proj:  96%|█████████▌| 35136/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.35.down_proj:  96%|█████████▌| 35137/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.36.gate_proj:  96%|█████████▌| 35138/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.36.up_proj:  96%|█████████▌| 35139/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.36.down_proj:  96%|█████████▌| 35140/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.37.gate_proj:  96%|█████████▌| 35141/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.37.up_proj:  96%|█████████▌| 35142/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.37.down_proj:  96%|█████████▌| 35143/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.38.gate_proj:  96%|█████████▌| 35144/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.38.up_proj:  96%|█████████▌| 35145/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.38.down_proj:  96%|█████████▌| 35146/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.39.gate_proj:  96%|█████████▌| 35147/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.39.up_proj:  96%|█████████▌| 35148/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.39.down_proj:  96%|█████████▌| 35149/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.40.gate_proj:  96%|█████████▌| 35150/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.40.up_proj:  96%|█████████▌| 35151/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.40.down_proj:  96%|█████████▌| 35152/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.41.gate_proj:  96%|█████████▌| 35153/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.41.up_proj:  96%|█████████▌| 35154/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.41.down_proj:  96%|█████████▌| 35155/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.42.gate_proj:  96%|█████████▌| 35156/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.42.up_proj:  96%|█████████▌| 35157/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.42.down_proj:  96%|█████████▌| 35158/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.43.gate_proj:  96%|█████████▌| 35159/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.43.up_proj:  96%|█████████▌| 35160/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.43.down_proj:  96%|█████████▌| 35161/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.44.gate_proj:  96%|█████████▌| 35162/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.44.up_proj:  96%|█████████▌| 35163/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.44.down_proj:  96%|█████████▌| 35164/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.45.gate_proj:  96%|█████████▌| 35165/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.45.up_proj:  96%|█████████▌| 35166/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.45.down_proj:  96%|█████████▌| 35167/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.46.gate_proj:  96%|█████████▌| 35168/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.46.up_proj:  96%|█████████▌| 35169/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.46.down_proj:  96%|█████████▌| 35170/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.47.gate_proj:  96%|█████████▌| 35171/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.47.up_proj:  96%|█████████▌| 35172/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.47.down_proj:  96%|█████████▌| 35173/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.48.gate_proj:  96%|█████████▌| 35174/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.48.up_proj:  96%|█████████▌| 35175/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.48.down_proj:  96%|█████████▌| 35176/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.49.gate_proj:  96%|█████████▌| 35177/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.49.up_proj:  96%|█████████▌| 35178/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.49.down_proj:  96%|█████████▌| 35179/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.50.gate_proj:  96%|█████████▌| 35180/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.50.up_proj:  96%|█████████▌| 35181/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.50.down_proj:  96%|█████████▌| 35182/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.51.gate_proj:  96%|█████████▌| 35183/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.51.up_proj:  96%|█████████▌| 35184/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.51.down_proj:  96%|█████████▌| 35185/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.52.gate_proj:  96%|█████████▌| 35186/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.52.up_proj:  96%|█████████▌| 35187/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.52.down_proj:  96%|█████████▌| 35188/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.53.gate_proj:  96%|█████████▌| 35189/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.53.up_proj:  96%|█████████▌| 35190/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.53.down_proj:  96%|█████████▌| 35191/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.54.gate_proj:  96%|█████████▌| 35192/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.54.up_proj:  96%|█████████▌| 35193/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.54.down_proj:  96%|█████████▌| 35194/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.55.gate_proj:  96%|█████████▋| 35195/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.55.up_proj:  96%|█████████▋| 35196/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.55.down_proj:  96%|█████████▋| 35197/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.56.gate_proj:  96%|█████████▋| 35198/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.56.up_proj:  96%|█████████▋| 35199/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.56.down_proj:  96%|█████████▋| 35200/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.57.gate_proj:  96%|█████████▋| 35201/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.57.up_proj:  96%|█████████▋| 35202/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.57.down_proj:  96%|█████████▋| 35203/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.58.gate_proj:  96%|█████████▋| 35204/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.58.up_proj:  96%|█████████▋| 35205/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.58.down_proj:  96%|█████████▋| 35206/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.59.gate_proj:  96%|█████████▋| 35207/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.59.up_proj:  96%|█████████▋| 35208/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.59.down_proj:  96%|█████████▋| 35209/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.60.gate_proj:  96%|█████████▋| 35210/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.60.up_proj:  96%|█████████▋| 35211/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.60.down_proj:  96%|█████████▋| 35212/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.61.gate_proj:  96%|█████████▋| 35213/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.61.up_proj:  96%|█████████▋| 35214/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.61.down_proj:  96%|█████████▋| 35215/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.62.gate_proj:  96%|█████████▋| 35216/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.62.up_proj:  96%|█████████▋| 35217/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.62.down_proj:  96%|█████████▋| 35218/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.63.gate_proj:  96%|█████████▋| 35219/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.63.up_proj:  96%|█████████▋| 35220/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.63.down_proj:  96%|█████████▋| 35221/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.64.gate_proj:  96%|█████████▋| 35222/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.64.up_proj:  96%|█████████▋| 35223/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.64.down_proj:  96%|█████████▋| 35224/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.65.gate_proj:  96%|█████████▋| 35225/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.65.up_proj:  96%|█████████▋| 35226/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.65.down_proj:  96%|█████████▋| 35227/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.66.gate_proj:  96%|█████████▋| 35228/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.66.up_proj:  96%|█████████▋| 35229/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.66.down_proj:  96%|█████████▋| 35230/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.67.gate_proj:  96%|█████████▋| 35231/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.67.up_proj:  96%|█████████▋| 35232/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.67.down_proj:  96%|█████████▋| 35233/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.68.gate_proj:  96%|█████████▋| 35234/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.68.up_proj:  96%|█████████▋| 35235/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.68.down_proj:  96%|█████████▋| 35236/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.69.gate_proj:  96%|█████████▋| 35237/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.69.up_proj:  96%|█████████▋| 35238/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.69.down_proj:  96%|█████████▋| 35239/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.70.gate_proj:  96%|█████████▋| 35240/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.70.up_proj:  96%|█████████▋| 35241/36566 [00:31<00:01, 1146.27it/s]  
packing model.layers.90.mlp.experts.70.down_proj:  96%|█████████▋| 35242/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.71.gate_proj:  96%|█████████▋| 35243/36566 [00:31<00:01, 1146.27it/s]
packing model.layers.90.mlp.experts.71.gate_proj:  96%|█████████▋| 35244/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.71.up_proj:  96%|█████████▋| 35244/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.71.down_proj:  96%|█████████▋| 35245/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.72.gate_proj:  96%|█████████▋| 35246/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.72.up_proj:  96%|█████████▋| 35247/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.72.down_proj:  96%|█████████▋| 35248/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.73.gate_proj:  96%|█████████▋| 35249/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.73.up_proj:  96%|█████████▋| 35250/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.73.down_proj:  96%|█████████▋| 35251/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.74.gate_proj:  96%|█████████▋| 35252/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.74.up_proj:  96%|█████████▋| 35253/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.74.down_proj:  96%|█████████▋| 35254/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.75.gate_proj:  96%|█████████▋| 35255/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.75.up_proj:  96%|█████████▋| 35256/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.75.down_proj:  96%|█████████▋| 35257/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.76.gate_proj:  96%|█████████▋| 35258/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.76.up_proj:  96%|█████████▋| 35259/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.76.down_proj:  96%|█████████▋| 35260/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.77.gate_proj:  96%|█████████▋| 35261/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.77.up_proj:  96%|█████████▋| 35262/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.77.down_proj:  96%|█████████▋| 35263/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.78.gate_proj:  96%|█████████▋| 35264/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.78.up_proj:  96%|█████████▋| 35265/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.78.down_proj:  96%|█████████▋| 35266/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.79.gate_proj:  96%|█████████▋| 35267/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.79.up_proj:  96%|█████████▋| 35268/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.79.down_proj:  96%|█████████▋| 35269/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.80.gate_proj:  96%|█████████▋| 35270/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.80.up_proj:  96%|█████████▋| 35271/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.80.down_proj:  96%|█████████▋| 35272/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.81.gate_proj:  96%|█████████▋| 35273/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.81.up_proj:  96%|█████████▋| 35274/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.81.down_proj:  96%|█████████▋| 35275/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.82.gate_proj:  96%|█████████▋| 35276/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.82.up_proj:  96%|█████████▋| 35277/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.82.down_proj:  96%|█████████▋| 35278/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.83.gate_proj:  96%|█████████▋| 35279/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.83.up_proj:  96%|█████████▋| 35280/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.83.down_proj:  96%|█████████▋| 35281/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.84.gate_proj:  96%|█████████▋| 35282/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.84.up_proj:  96%|█████████▋| 35283/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.84.down_proj:  96%|█████████▋| 35284/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.85.gate_proj:  96%|█████████▋| 35285/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.85.up_proj:  96%|█████████▋| 35286/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.85.down_proj:  97%|█████████▋| 35287/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.86.gate_proj:  97%|█████████▋| 35288/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.86.up_proj:  97%|█████████▋| 35289/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.86.down_proj:  97%|█████████▋| 35290/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.87.gate_proj:  97%|█████████▋| 35291/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.87.up_proj:  97%|█████████▋| 35292/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.87.down_proj:  97%|█████████▋| 35293/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.88.gate_proj:  97%|█████████▋| 35294/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.88.up_proj:  97%|█████████▋| 35295/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.88.down_proj:  97%|█████████▋| 35296/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.89.gate_proj:  97%|█████████▋| 35297/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.89.up_proj:  97%|█████████▋| 35298/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.89.down_proj:  97%|█████████▋| 35299/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.90.gate_proj:  97%|█████████▋| 35300/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.90.up_proj:  97%|█████████▋| 35301/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.90.down_proj:  97%|█████████▋| 35302/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.91.gate_proj:  97%|█████████▋| 35303/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.91.up_proj:  97%|█████████▋| 35304/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.91.down_proj:  97%|█████████▋| 35305/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.92.gate_proj:  97%|█████████▋| 35306/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.92.up_proj:  97%|█████████▋| 35307/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.92.down_proj:  97%|█████████▋| 35308/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.93.gate_proj:  97%|█████████▋| 35309/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.93.up_proj:  97%|█████████▋| 35310/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.93.down_proj:  97%|█████████▋| 35311/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.94.gate_proj:  97%|█████████▋| 35312/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.94.up_proj:  97%|█████████▋| 35313/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.94.down_proj:  97%|█████████▋| 35314/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.95.gate_proj:  97%|█████████▋| 35315/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.95.up_proj:  97%|█████████▋| 35316/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.95.down_proj:  97%|█████████▋| 35317/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.96.gate_proj:  97%|█████████▋| 35318/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.96.up_proj:  97%|█████████▋| 35319/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.96.down_proj:  97%|█████████▋| 35320/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.97.gate_proj:  97%|█████████▋| 35321/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.97.up_proj:  97%|█████████▋| 35322/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.97.down_proj:  97%|█████████▋| 35323/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.98.gate_proj:  97%|█████████▋| 35324/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.98.up_proj:  97%|█████████▋| 35325/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.98.down_proj:  97%|█████████▋| 35326/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.99.gate_proj:  97%|█████████▋| 35327/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.99.up_proj:  97%|█████████▋| 35328/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.99.down_proj:  97%|█████████▋| 35329/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.100.gate_proj:  97%|█████████▋| 35330/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.100.up_proj:  97%|█████████▋| 35331/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.100.down_proj:  97%|█████████▋| 35332/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.101.gate_proj:  97%|█████████▋| 35333/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.101.up_proj:  97%|█████████▋| 35334/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.101.down_proj:  97%|█████████▋| 35335/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.102.gate_proj:  97%|█████████▋| 35336/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.102.up_proj:  97%|█████████▋| 35337/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.102.down_proj:  97%|█████████▋| 35338/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.103.gate_proj:  97%|█████████▋| 35339/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.103.up_proj:  97%|█████████▋| 35340/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.103.down_proj:  97%|█████████▋| 35341/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.104.gate_proj:  97%|█████████▋| 35342/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.104.up_proj:  97%|█████████▋| 35343/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.104.down_proj:  97%|█████████▋| 35344/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.105.gate_proj:  97%|█████████▋| 35345/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.105.up_proj:  97%|█████████▋| 35346/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.105.down_proj:  97%|█████████▋| 35347/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.106.gate_proj:  97%|█████████▋| 35348/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.106.up_proj:  97%|█████████▋| 35349/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.106.down_proj:  97%|█████████▋| 35350/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.107.gate_proj:  97%|█████████▋| 35351/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.107.up_proj:  97%|█████████▋| 35352/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.107.down_proj:  97%|█████████▋| 35353/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.108.gate_proj:  97%|█████████▋| 35354/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.108.up_proj:  97%|█████████▋| 35355/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.108.down_proj:  97%|█████████▋| 35356/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.109.gate_proj:  97%|█████████▋| 35357/36566 [00:31<00:01, 1146.10it/s]
packing model.layers.90.mlp.experts.109.up_proj:  97%|█████████▋| 35358/36566 [00:31<00:01, 1146.10it/s]  
packing model.layers.90.mlp.experts.109.up_proj:  97%|█████████▋| 35359/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.109.down_proj:  97%|█████████▋| 35359/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.110.gate_proj:  97%|█████████▋| 35360/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.110.up_proj:  97%|█████████▋| 35361/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.110.down_proj:  97%|█████████▋| 35362/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.111.gate_proj:  97%|█████████▋| 35363/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.111.up_proj:  97%|█████████▋| 35364/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.111.down_proj:  97%|█████████▋| 35365/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.112.gate_proj:  97%|█████████▋| 35366/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.112.up_proj:  97%|█████████▋| 35367/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.112.down_proj:  97%|█████████▋| 35368/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.113.gate_proj:  97%|█████████▋| 35369/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.113.up_proj:  97%|█████████▋| 35370/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.113.down_proj:  97%|█████████▋| 35371/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.114.gate_proj:  97%|█████████▋| 35372/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.114.up_proj:  97%|█████████▋| 35373/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.114.down_proj:  97%|█████████▋| 35374/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.115.gate_proj:  97%|█████████▋| 35375/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.115.up_proj:  97%|█████████▋| 35376/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.115.down_proj:  97%|█████████▋| 35377/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.116.gate_proj:  97%|█████████▋| 35378/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.116.up_proj:  97%|█████████▋| 35379/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.116.down_proj:  97%|█████████▋| 35380/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.117.gate_proj:  97%|█████████▋| 35381/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.117.up_proj:  97%|█████████▋| 35382/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.117.down_proj:  97%|█████████▋| 35383/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.118.gate_proj:  97%|█████████▋| 35384/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.118.up_proj:  97%|█████████▋| 35385/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.118.down_proj:  97%|█████████▋| 35386/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.119.gate_proj:  97%|█████████▋| 35387/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.119.up_proj:  97%|█████████▋| 35388/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.119.down_proj:  97%|█████████▋| 35389/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.120.gate_proj:  97%|█████████▋| 35390/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.120.up_proj:  97%|█████████▋| 35391/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.120.down_proj:  97%|█████████▋| 35392/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.121.gate_proj:  97%|█████████▋| 35393/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.121.up_proj:  97%|█████████▋| 35394/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.121.down_proj:  97%|█████████▋| 35395/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.122.gate_proj:  97%|█████████▋| 35396/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.122.up_proj:  97%|█████████▋| 35397/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.122.down_proj:  97%|█████████▋| 35398/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.123.gate_proj:  97%|█████████▋| 35399/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.123.up_proj:  97%|█████████▋| 35400/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.123.down_proj:  97%|█████████▋| 35401/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.124.gate_proj:  97%|█████████▋| 35402/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.124.up_proj:  97%|█████████▋| 35403/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.124.down_proj:  97%|█████████▋| 35404/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.125.gate_proj:  97%|█████████▋| 35405/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.125.up_proj:  97%|█████████▋| 35406/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.125.down_proj:  97%|█████████▋| 35407/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.126.gate_proj:  97%|█████████▋| 35408/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.126.up_proj:  97%|█████████▋| 35409/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.126.down_proj:  97%|█████████▋| 35410/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.127.gate_proj:  97%|█████████▋| 35411/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.90.mlp.experts.127.up_proj:  97%|█████████▋| 35412/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.90.mlp.experts.127.down_proj:  97%|█████████▋| 35413/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.91.mlp.experts.0.gate_proj:  97%|█████████▋| 35414/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.91.mlp.experts.0.up_proj:  97%|█████████▋| 35415/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.91.mlp.experts.0.down_proj:  97%|█████████▋| 35416/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.91.mlp.experts.1.gate_proj:  97%|█████████▋| 35417/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.91.mlp.experts.1.up_proj:  97%|█████████▋| 35418/36566 [00:31<00:01, 1146.12it/s]  
packing model.layers.91.mlp.experts.1.down_proj:  97%|█████████▋| 35419/36566 [00:31<00:01, 1146.12it/s]
packing model.layers.91.mlp.experts.2.gate_proj:  97%|█████████▋| 35420/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.2.up_proj:  97%|█████████▋| 35421/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.2.down_proj:  97%|█████████▋| 35422/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.3.gate_proj:  97%|█████████▋| 35423/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.3.up_proj:  97%|█████████▋| 35424/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.3.down_proj:  97%|█████████▋| 35425/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.4.gate_proj:  97%|█████████▋| 35426/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.4.up_proj:  97%|█████████▋| 35427/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.4.down_proj:  97%|█████████▋| 35428/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.5.gate_proj:  97%|█████████▋| 35429/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.5.up_proj:  97%|█████████▋| 35430/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.5.down_proj:  97%|█████████▋| 35431/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.6.gate_proj:  97%|█████████▋| 35432/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.6.up_proj:  97%|█████████▋| 35433/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.6.down_proj:  97%|█████████▋| 35434/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.7.gate_proj:  97%|█████████▋| 35435/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.7.up_proj:  97%|█████████▋| 35436/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.7.down_proj:  97%|█████████▋| 35437/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.8.gate_proj:  97%|█████████▋| 35438/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.8.up_proj:  97%|█████████▋| 35439/36566 [00:31<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.8.down_proj:  97%|█████████▋| 35440/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.9.gate_proj:  97%|█████████▋| 35441/36566 [00:31<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.9.up_proj:  97%|█████████▋| 35442/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.9.down_proj:  97%|█████████▋| 35443/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.10.gate_proj:  97%|█████████▋| 35444/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.10.up_proj:  97%|█████████▋| 35445/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.10.down_proj:  97%|█████████▋| 35446/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.11.gate_proj:  97%|█████████▋| 35447/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.11.up_proj:  97%|█████████▋| 35448/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.11.down_proj:  97%|█████████▋| 35449/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.12.gate_proj:  97%|█████████▋| 35450/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.12.up_proj:  97%|█████████▋| 35451/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.12.down_proj:  97%|█████████▋| 35452/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.13.gate_proj:  97%|█████████▋| 35453/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.13.up_proj:  97%|█████████▋| 35454/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.13.down_proj:  97%|█████████▋| 35455/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.14.gate_proj:  97%|█████████▋| 35456/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.14.up_proj:  97%|█████████▋| 35457/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.14.down_proj:  97%|█████████▋| 35458/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.15.gate_proj:  97%|█████████▋| 35459/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.15.up_proj:  97%|█████████▋| 35460/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.15.down_proj:  97%|█████████▋| 35461/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.16.gate_proj:  97%|█████████▋| 35462/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.16.up_proj:  97%|█████████▋| 35463/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.16.down_proj:  97%|█████████▋| 35464/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.17.gate_proj:  97%|█████████▋| 35465/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.17.up_proj:  97%|█████████▋| 35466/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.17.down_proj:  97%|█████████▋| 35467/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.18.gate_proj:  97%|█████████▋| 35468/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.18.up_proj:  97%|█████████▋| 35469/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.18.down_proj:  97%|█████████▋| 35470/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.19.gate_proj:  97%|█████████▋| 35471/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.19.up_proj:  97%|█████████▋| 35472/36566 [00:32<00:00, 1146.12it/s]  
packing model.layers.91.mlp.experts.19.down_proj:  97%|█████████▋| 35473/36566 [00:32<00:00, 1146.12it/s]
packing model.layers.91.mlp.experts.19.down_proj:  97%|█████████▋| 35474/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.20.gate_proj:  97%|█████████▋| 35474/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.20.up_proj:  97%|█████████▋| 35475/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.20.down_proj:  97%|█████████▋| 35476/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.21.gate_proj:  97%|█████████▋| 35477/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.21.up_proj:  97%|█████████▋| 35478/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.21.down_proj:  97%|█████████▋| 35479/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.22.gate_proj:  97%|█████████▋| 35480/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.22.up_proj:  97%|█████████▋| 35481/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.22.down_proj:  97%|█████████▋| 35482/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.23.gate_proj:  97%|█████████▋| 35483/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.23.up_proj:  97%|█████████▋| 35484/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.23.down_proj:  97%|█████████▋| 35485/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.24.gate_proj:  97%|█████████▋| 35486/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.24.up_proj:  97%|█████████▋| 35487/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.24.down_proj:  97%|█████████▋| 35488/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.25.gate_proj:  97%|█████████▋| 35489/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.25.up_proj:  97%|█████████▋| 35490/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.25.down_proj:  97%|█████████▋| 35491/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.26.gate_proj:  97%|█████████▋| 35492/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.26.up_proj:  97%|█████████▋| 35493/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.26.down_proj:  97%|█████████▋| 35494/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.27.gate_proj:  97%|█████████▋| 35495/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.27.up_proj:  97%|█████████▋| 35496/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.27.down_proj:  97%|█████████▋| 35497/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.28.gate_proj:  97%|█████████▋| 35498/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.28.up_proj:  97%|█████████▋| 35499/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.28.down_proj:  97%|█████████▋| 35500/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.29.gate_proj:  97%|█████████▋| 35501/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.29.up_proj:  97%|█████████▋| 35502/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.29.down_proj:  97%|█████████▋| 35503/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.30.gate_proj:  97%|█████████▋| 35504/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.30.up_proj:  97%|█████████▋| 35505/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.30.down_proj:  97%|█████████▋| 35506/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.31.gate_proj:  97%|█████████▋| 35507/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.31.up_proj:  97%|█████████▋| 35508/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.31.down_proj:  97%|█████████▋| 35509/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.32.gate_proj:  97%|█████████▋| 35510/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.32.up_proj:  97%|█████████▋| 35511/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.32.down_proj:  97%|█████████▋| 35512/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.33.gate_proj:  97%|█████████▋| 35513/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.33.up_proj:  97%|█████████▋| 35514/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.33.down_proj:  97%|█████████▋| 35515/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.34.gate_proj:  97%|█████████▋| 35516/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.34.up_proj:  97%|█████████▋| 35517/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.34.down_proj:  97%|█████████▋| 35518/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.35.gate_proj:  97%|█████████▋| 35519/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.35.up_proj:  97%|█████████▋| 35520/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.35.down_proj:  97%|█████████▋| 35521/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.36.gate_proj:  97%|█████████▋| 35522/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.36.up_proj:  97%|█████████▋| 35523/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.36.down_proj:  97%|█████████▋| 35524/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.37.gate_proj:  97%|█████████▋| 35525/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.37.up_proj:  97%|█████████▋| 35526/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.37.down_proj:  97%|█████████▋| 35527/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.38.gate_proj:  97%|█████████▋| 35528/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.38.up_proj:  97%|█████████▋| 35529/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.38.down_proj:  97%|█████████▋| 35530/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.39.gate_proj:  97%|█████████▋| 35531/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.39.up_proj:  97%|█████████▋| 35532/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.39.down_proj:  97%|█████████▋| 35533/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.40.gate_proj:  97%|█████████▋| 35534/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.40.up_proj:  97%|█████████▋| 35535/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.40.down_proj:  97%|█████████▋| 35536/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.41.gate_proj:  97%|█████████▋| 35537/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.41.up_proj:  97%|█████████▋| 35538/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.41.down_proj:  97%|█████████▋| 35539/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.42.gate_proj:  97%|█████████▋| 35540/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.42.up_proj:  97%|█████████▋| 35541/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.42.down_proj:  97%|█████████▋| 35542/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.43.gate_proj:  97%|█████████▋| 35543/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.43.up_proj:  97%|█████████▋| 35544/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.43.down_proj:  97%|█████████▋| 35545/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.44.gate_proj:  97%|█████████▋| 35546/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.44.up_proj:  97%|█████████▋| 35547/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.44.down_proj:  97%|█████████▋| 35548/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.45.gate_proj:  97%|█████████▋| 35549/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.45.up_proj:  97%|█████████▋| 35550/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.45.down_proj:  97%|█████████▋| 35551/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.46.gate_proj:  97%|█████████▋| 35552/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.46.up_proj:  97%|█████████▋| 35553/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.46.down_proj:  97%|█████████▋| 35554/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.47.gate_proj:  97%|█████████▋| 35555/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.47.up_proj:  97%|█████████▋| 35556/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.47.down_proj:  97%|█████████▋| 35557/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.48.gate_proj:  97%|█████████▋| 35558/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.48.up_proj:  97%|█████████▋| 35559/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.48.down_proj:  97%|█████████▋| 35560/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.49.gate_proj:  97%|█████████▋| 35561/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.49.up_proj:  97%|█████████▋| 35562/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.49.down_proj:  97%|█████████▋| 35563/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.50.gate_proj:  97%|█████████▋| 35564/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.50.up_proj:  97%|█████████▋| 35565/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.50.down_proj:  97%|█████████▋| 35566/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.51.gate_proj:  97%|█████████▋| 35567/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.51.up_proj:  97%|█████████▋| 35568/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.51.down_proj:  97%|█████████▋| 35569/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.52.gate_proj:  97%|█████████▋| 35570/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.52.up_proj:  97%|█████████▋| 35571/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.52.down_proj:  97%|█████████▋| 35572/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.53.gate_proj:  97%|█████████▋| 35573/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.53.up_proj:  97%|█████████▋| 35574/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.53.down_proj:  97%|█████████▋| 35575/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.54.gate_proj:  97%|█████████▋| 35576/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.54.up_proj:  97%|█████████▋| 35577/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.54.down_proj:  97%|█████████▋| 35578/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.55.gate_proj:  97%|█████████▋| 35579/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.55.up_proj:  97%|█████████▋| 35580/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.55.down_proj:  97%|█████████▋| 35581/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.56.gate_proj:  97%|█████████▋| 35582/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.56.up_proj:  97%|█████████▋| 35583/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.56.down_proj:  97%|█████████▋| 35584/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.57.gate_proj:  97%|█████████▋| 35585/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.57.up_proj:  97%|█████████▋| 35586/36566 [00:32<00:00, 1146.81it/s]  
packing model.layers.91.mlp.experts.57.down_proj:  97%|█████████▋| 35587/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.58.gate_proj:  97%|█████████▋| 35588/36566 [00:32<00:00, 1146.81it/s]
packing model.layers.91.mlp.experts.58.gate_proj:  97%|█████████▋| 35589/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.58.up_proj:  97%|█████████▋| 35589/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.58.down_proj:  97%|█████████▋| 35590/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.59.gate_proj:  97%|█████████▋| 35591/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.59.up_proj:  97%|█████████▋| 35592/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.59.down_proj:  97%|█████████▋| 35593/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.60.gate_proj:  97%|█████████▋| 35594/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.60.up_proj:  97%|█████████▋| 35595/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.60.down_proj:  97%|█████████▋| 35596/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.61.gate_proj:  97%|█████████▋| 35597/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.61.up_proj:  97%|█████████▋| 35598/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.61.down_proj:  97%|█████████▋| 35599/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.62.gate_proj:  97%|█████████▋| 35600/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.62.up_proj:  97%|█████████▋| 35601/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.62.down_proj:  97%|█████████▋| 35602/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.63.gate_proj:  97%|█████████▋| 35603/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.63.up_proj:  97%|█████████▋| 35604/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.63.down_proj:  97%|█████████▋| 35605/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.64.gate_proj:  97%|█████████▋| 35606/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.64.up_proj:  97%|█████████▋| 35607/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.64.down_proj:  97%|█████████▋| 35608/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.65.gate_proj:  97%|█████████▋| 35609/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.65.up_proj:  97%|█████████▋| 35610/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.65.down_proj:  97%|█████████▋| 35611/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.66.gate_proj:  97%|█████████▋| 35612/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.66.up_proj:  97%|█████████▋| 35613/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.66.down_proj:  97%|█████████▋| 35614/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.67.gate_proj:  97%|█████████▋| 35615/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.67.up_proj:  97%|█████████▋| 35616/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.67.down_proj:  97%|█████████▋| 35617/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.68.gate_proj:  97%|█████████▋| 35618/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.68.up_proj:  97%|█████████▋| 35619/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.68.down_proj:  97%|█████████▋| 35620/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.69.gate_proj:  97%|█████████▋| 35621/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.69.up_proj:  97%|█████████▋| 35622/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.69.down_proj:  97%|█████████▋| 35623/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.70.gate_proj:  97%|█████████▋| 35624/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.70.up_proj:  97%|█████████▋| 35625/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.70.down_proj:  97%|█████████▋| 35626/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.71.gate_proj:  97%|█████████▋| 35627/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.71.up_proj:  97%|█████████▋| 35628/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.71.down_proj:  97%|█████████▋| 35629/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.72.gate_proj:  97%|█████████▋| 35630/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.72.up_proj:  97%|█████████▋| 35631/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.72.down_proj:  97%|█████████▋| 35632/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.73.gate_proj:  97%|█████████▋| 35633/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.73.up_proj:  97%|█████████▋| 35634/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.73.down_proj:  97%|█████████▋| 35635/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.74.gate_proj:  97%|█████████▋| 35636/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.74.up_proj:  97%|█████████▋| 35637/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.74.down_proj:  97%|█████████▋| 35638/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.75.gate_proj:  97%|█████████▋| 35639/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.75.up_proj:  97%|█████████▋| 35640/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.75.down_proj:  97%|█████████▋| 35641/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.76.gate_proj:  97%|█████████▋| 35642/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.76.up_proj:  97%|█████████▋| 35643/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.76.down_proj:  97%|█████████▋| 35644/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.77.gate_proj:  97%|█████████▋| 35645/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.77.up_proj:  97%|█████████▋| 35646/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.77.down_proj:  97%|█████████▋| 35647/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.78.gate_proj:  97%|█████████▋| 35648/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.78.up_proj:  97%|█████████▋| 35649/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.78.down_proj:  97%|█████████▋| 35650/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.79.gate_proj:  97%|█████████▋| 35651/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.79.up_proj:  98%|█████████▊| 35652/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.79.down_proj:  98%|█████████▊| 35653/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.80.gate_proj:  98%|█████████▊| 35654/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.80.up_proj:  98%|█████████▊| 35655/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.80.down_proj:  98%|█████████▊| 35656/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.81.gate_proj:  98%|█████████▊| 35657/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.81.up_proj:  98%|█████████▊| 35658/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.81.down_proj:  98%|█████████▊| 35659/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.82.gate_proj:  98%|█████████▊| 35660/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.82.up_proj:  98%|█████████▊| 35661/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.82.down_proj:  98%|█████████▊| 35662/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.83.gate_proj:  98%|█████████▊| 35663/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.83.up_proj:  98%|█████████▊| 35664/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.83.down_proj:  98%|█████████▊| 35665/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.84.gate_proj:  98%|█████████▊| 35666/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.84.up_proj:  98%|█████████▊| 35667/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.84.down_proj:  98%|█████████▊| 35668/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.85.gate_proj:  98%|█████████▊| 35669/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.85.up_proj:  98%|█████████▊| 35670/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.85.down_proj:  98%|█████████▊| 35671/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.86.gate_proj:  98%|█████████▊| 35672/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.86.up_proj:  98%|█████████▊| 35673/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.86.down_proj:  98%|█████████▊| 35674/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.87.gate_proj:  98%|█████████▊| 35675/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.87.up_proj:  98%|█████████▊| 35676/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.87.down_proj:  98%|█████████▊| 35677/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.88.gate_proj:  98%|█████████▊| 35678/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.88.up_proj:  98%|█████████▊| 35679/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.88.down_proj:  98%|█████████▊| 35680/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.89.gate_proj:  98%|█████████▊| 35681/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.89.up_proj:  98%|█████████▊| 35682/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.89.down_proj:  98%|█████████▊| 35683/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.90.gate_proj:  98%|█████████▊| 35684/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.90.up_proj:  98%|█████████▊| 35685/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.90.down_proj:  98%|█████████▊| 35686/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.91.gate_proj:  98%|█████████▊| 35687/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.91.up_proj:  98%|█████████▊| 35688/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.91.down_proj:  98%|█████████▊| 35689/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.92.gate_proj:  98%|█████████▊| 35690/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.92.up_proj:  98%|█████████▊| 35691/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.92.down_proj:  98%|█████████▊| 35692/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.93.gate_proj:  98%|█████████▊| 35693/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.93.up_proj:  98%|█████████▊| 35694/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.93.down_proj:  98%|█████████▊| 35695/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.94.gate_proj:  98%|█████████▊| 35696/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.94.up_proj:  98%|█████████▊| 35697/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.94.down_proj:  98%|█████████▊| 35698/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.95.gate_proj:  98%|█████████▊| 35699/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.95.up_proj:  98%|█████████▊| 35700/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.95.down_proj:  98%|█████████▊| 35701/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.96.gate_proj:  98%|█████████▊| 35702/36566 [00:32<00:00, 1146.94it/s]
packing model.layers.91.mlp.experts.96.up_proj:  98%|█████████▊| 35703/36566 [00:32<00:00, 1146.94it/s]  
packing model.layers.91.mlp.experts.96.up_proj:  98%|█████████▊| 35704/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.96.down_proj:  98%|█████████▊| 35704/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.97.gate_proj:  98%|█████████▊| 35705/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.97.up_proj:  98%|█████████▊| 35706/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.97.down_proj:  98%|█████████▊| 35707/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.98.gate_proj:  98%|█████████▊| 35708/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.98.up_proj:  98%|█████████▊| 35709/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.98.down_proj:  98%|█████████▊| 35710/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.99.gate_proj:  98%|█████████▊| 35711/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.99.up_proj:  98%|█████████▊| 35712/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.99.down_proj:  98%|█████████▊| 35713/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.100.gate_proj:  98%|█████████▊| 35714/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.100.up_proj:  98%|█████████▊| 35715/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.100.down_proj:  98%|█████████▊| 35716/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.101.gate_proj:  98%|█████████▊| 35717/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.101.up_proj:  98%|█████████▊| 35718/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.101.down_proj:  98%|█████████▊| 35719/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.102.gate_proj:  98%|█████████▊| 35720/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.102.up_proj:  98%|█████████▊| 35721/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.102.down_proj:  98%|█████████▊| 35722/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.103.gate_proj:  98%|█████████▊| 35723/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.103.up_proj:  98%|█████████▊| 35724/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.103.down_proj:  98%|█████████▊| 35725/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.104.gate_proj:  98%|█████████▊| 35726/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.104.up_proj:  98%|█████████▊| 35727/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.104.down_proj:  98%|█████████▊| 35728/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.105.gate_proj:  98%|█████████▊| 35729/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.105.up_proj:  98%|█████████▊| 35730/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.105.down_proj:  98%|█████████▊| 35731/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.106.gate_proj:  98%|█████████▊| 35732/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.106.up_proj:  98%|█████████▊| 35733/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.106.down_proj:  98%|█████████▊| 35734/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.107.gate_proj:  98%|█████████▊| 35735/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.107.up_proj:  98%|█████████▊| 35736/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.107.down_proj:  98%|█████████▊| 35737/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.108.gate_proj:  98%|█████████▊| 35738/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.108.up_proj:  98%|█████████▊| 35739/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.108.down_proj:  98%|█████████▊| 35740/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.109.gate_proj:  98%|█████████▊| 35741/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.109.up_proj:  98%|█████████▊| 35742/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.109.down_proj:  98%|█████████▊| 35743/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.110.gate_proj:  98%|█████████▊| 35744/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.110.up_proj:  98%|█████████▊| 35745/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.110.down_proj:  98%|█████████▊| 35746/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.111.gate_proj:  98%|█████████▊| 35747/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.111.up_proj:  98%|█████████▊| 35748/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.111.down_proj:  98%|█████████▊| 35749/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.112.gate_proj:  98%|█████████▊| 35750/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.112.up_proj:  98%|█████████▊| 35751/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.112.down_proj:  98%|█████████▊| 35752/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.113.gate_proj:  98%|█████████▊| 35753/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.113.up_proj:  98%|█████████▊| 35754/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.113.down_proj:  98%|█████████▊| 35755/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.114.gate_proj:  98%|█████████▊| 35756/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.114.up_proj:  98%|█████████▊| 35757/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.114.down_proj:  98%|█████████▊| 35758/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.115.gate_proj:  98%|█████████▊| 35759/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.115.up_proj:  98%|█████████▊| 35760/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.115.down_proj:  98%|█████████▊| 35761/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.116.gate_proj:  98%|█████████▊| 35762/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.116.up_proj:  98%|█████████▊| 35763/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.116.down_proj:  98%|█████████▊| 35764/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.117.gate_proj:  98%|█████████▊| 35765/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.117.up_proj:  98%|█████████▊| 35766/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.117.down_proj:  98%|█████████▊| 35767/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.118.gate_proj:  98%|█████████▊| 35768/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.118.up_proj:  98%|█████████▊| 35769/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.118.down_proj:  98%|█████████▊| 35770/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.119.gate_proj:  98%|█████████▊| 35771/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.119.up_proj:  98%|█████████▊| 35772/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.119.down_proj:  98%|█████████▊| 35773/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.120.gate_proj:  98%|█████████▊| 35774/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.120.up_proj:  98%|█████████▊| 35775/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.120.down_proj:  98%|█████████▊| 35776/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.121.gate_proj:  98%|█████████▊| 35777/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.121.up_proj:  98%|█████████▊| 35778/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.121.down_proj:  98%|█████████▊| 35779/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.122.gate_proj:  98%|█████████▊| 35780/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.122.up_proj:  98%|█████████▊| 35781/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.122.down_proj:  98%|█████████▊| 35782/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.123.gate_proj:  98%|█████████▊| 35783/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.123.up_proj:  98%|█████████▊| 35784/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.123.down_proj:  98%|█████████▊| 35785/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.124.gate_proj:  98%|█████████▊| 35786/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.124.up_proj:  98%|█████████▊| 35787/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.124.down_proj:  98%|█████████▊| 35788/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.125.gate_proj:  98%|█████████▊| 35789/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.125.up_proj:  98%|█████████▊| 35790/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.125.down_proj:  98%|█████████▊| 35791/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.126.gate_proj:  98%|█████████▊| 35792/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.126.up_proj:  98%|█████████▊| 35793/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.126.down_proj:  98%|█████████▊| 35794/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.127.gate_proj:  98%|█████████▊| 35795/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.91.mlp.experts.127.up_proj:  98%|█████████▊| 35796/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.91.mlp.experts.127.down_proj:  98%|█████████▊| 35797/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.0.gate_proj:  98%|█████████▊| 35798/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.0.up_proj:  98%|█████████▊| 35799/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.0.down_proj:  98%|█████████▊| 35800/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.1.gate_proj:  98%|█████████▊| 35801/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.1.up_proj:  98%|█████████▊| 35802/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.1.down_proj:  98%|█████████▊| 35803/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.2.gate_proj:  98%|█████████▊| 35804/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.2.up_proj:  98%|█████████▊| 35805/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.2.down_proj:  98%|█████████▊| 35806/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.3.gate_proj:  98%|█████████▊| 35807/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.3.up_proj:  98%|█████████▊| 35808/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.3.down_proj:  98%|█████████▊| 35809/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.4.gate_proj:  98%|█████████▊| 35810/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.4.up_proj:  98%|█████████▊| 35811/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.4.down_proj:  98%|█████████▊| 35812/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.5.gate_proj:  98%|█████████▊| 35813/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.5.up_proj:  98%|█████████▊| 35814/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.5.down_proj:  98%|█████████▊| 35815/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.6.gate_proj:  98%|█████████▊| 35816/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.6.up_proj:  98%|█████████▊| 35817/36566 [00:32<00:00, 1144.43it/s]  
packing model.layers.92.mlp.experts.6.down_proj:  98%|█████████▊| 35818/36566 [00:32<00:00, 1144.43it/s]
packing model.layers.92.mlp.experts.6.down_proj:  98%|█████████▊| 35819/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.7.gate_proj:  98%|█████████▊| 35819/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.7.up_proj:  98%|█████████▊| 35820/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.7.down_proj:  98%|█████████▊| 35821/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.8.gate_proj:  98%|█████████▊| 35822/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.8.up_proj:  98%|█████████▊| 35823/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.8.down_proj:  98%|█████████▊| 35824/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.9.gate_proj:  98%|█████████▊| 35825/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.9.up_proj:  98%|█████████▊| 35826/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.9.down_proj:  98%|█████████▊| 35827/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.10.gate_proj:  98%|█████████▊| 35828/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.10.up_proj:  98%|█████████▊| 35829/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.10.down_proj:  98%|█████████▊| 35830/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.11.gate_proj:  98%|█████████▊| 35831/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.11.up_proj:  98%|█████████▊| 35832/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.11.down_proj:  98%|█████████▊| 35833/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.12.gate_proj:  98%|█████████▊| 35834/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.12.up_proj:  98%|█████████▊| 35835/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.12.down_proj:  98%|█████████▊| 35836/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.13.gate_proj:  98%|█████████▊| 35837/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.13.up_proj:  98%|█████████▊| 35838/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.13.down_proj:  98%|█████████▊| 35839/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.14.gate_proj:  98%|█████████▊| 35840/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.14.up_proj:  98%|█████████▊| 35841/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.14.down_proj:  98%|█████████▊| 35842/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.15.gate_proj:  98%|█████████▊| 35843/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.15.up_proj:  98%|█████████▊| 35844/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.15.down_proj:  98%|█████████▊| 35845/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.16.gate_proj:  98%|█████████▊| 35846/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.16.up_proj:  98%|█████████▊| 35847/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.16.down_proj:  98%|█████████▊| 35848/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.17.gate_proj:  98%|█████████▊| 35849/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.17.up_proj:  98%|█████████▊| 35850/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.17.down_proj:  98%|█████████▊| 35851/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.18.gate_proj:  98%|█████████▊| 35852/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.18.up_proj:  98%|█████████▊| 35853/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.18.down_proj:  98%|█████████▊| 35854/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.19.gate_proj:  98%|█████████▊| 35855/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.19.up_proj:  98%|█████████▊| 35856/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.19.down_proj:  98%|█████████▊| 35857/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.20.gate_proj:  98%|█████████▊| 35858/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.20.up_proj:  98%|█████████▊| 35859/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.20.down_proj:  98%|█████████▊| 35860/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.21.gate_proj:  98%|█████████▊| 35861/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.21.up_proj:  98%|█████████▊| 35862/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.21.down_proj:  98%|█████████▊| 35863/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.22.gate_proj:  98%|█████████▊| 35864/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.22.up_proj:  98%|█████████▊| 35865/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.22.down_proj:  98%|█████████▊| 35866/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.23.gate_proj:  98%|█████████▊| 35867/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.23.up_proj:  98%|█████████▊| 35868/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.23.down_proj:  98%|█████████▊| 35869/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.24.gate_proj:  98%|█████████▊| 35870/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.24.up_proj:  98%|█████████▊| 35871/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.24.down_proj:  98%|█████████▊| 35872/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.25.gate_proj:  98%|█████████▊| 35873/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.25.up_proj:  98%|█████████▊| 35874/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.25.down_proj:  98%|█████████▊| 35875/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.26.gate_proj:  98%|█████████▊| 35876/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.26.up_proj:  98%|█████████▊| 35877/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.26.down_proj:  98%|█████████▊| 35878/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.27.gate_proj:  98%|█████████▊| 35879/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.27.up_proj:  98%|█████████▊| 35880/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.27.down_proj:  98%|█████████▊| 35881/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.28.gate_proj:  98%|█████████▊| 35882/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.28.up_proj:  98%|█████████▊| 35883/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.28.down_proj:  98%|█████████▊| 35884/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.29.gate_proj:  98%|█████████▊| 35885/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.29.up_proj:  98%|█████████▊| 35886/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.29.down_proj:  98%|█████████▊| 35887/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.30.gate_proj:  98%|█████████▊| 35888/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.30.up_proj:  98%|█████████▊| 35889/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.30.down_proj:  98%|█████████▊| 35890/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.31.gate_proj:  98%|█████████▊| 35891/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.31.up_proj:  98%|█████████▊| 35892/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.31.down_proj:  98%|█████████▊| 35893/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.32.gate_proj:  98%|█████████▊| 35894/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.32.up_proj:  98%|█████████▊| 35895/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.32.down_proj:  98%|█████████▊| 35896/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.33.gate_proj:  98%|█████████▊| 35897/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.33.up_proj:  98%|█████████▊| 35898/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.33.down_proj:  98%|█████████▊| 35899/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.34.gate_proj:  98%|█████████▊| 35900/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.34.up_proj:  98%|█████████▊| 35901/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.34.down_proj:  98%|█████████▊| 35902/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.35.gate_proj:  98%|█████████▊| 35903/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.35.up_proj:  98%|█████████▊| 35904/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.35.down_proj:  98%|█████████▊| 35905/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.36.gate_proj:  98%|█████████▊| 35906/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.36.up_proj:  98%|█████████▊| 35907/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.36.down_proj:  98%|█████████▊| 35908/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.37.gate_proj:  98%|█████████▊| 35909/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.37.up_proj:  98%|█████████▊| 35910/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.37.down_proj:  98%|█████████▊| 35911/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.38.gate_proj:  98%|█████████▊| 35912/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.38.up_proj:  98%|█████████▊| 35913/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.38.down_proj:  98%|█████████▊| 35914/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.39.gate_proj:  98%|█████████▊| 35915/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.39.up_proj:  98%|█████████▊| 35916/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.39.down_proj:  98%|█████████▊| 35917/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.40.gate_proj:  98%|█████████▊| 35918/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.40.up_proj:  98%|█████████▊| 35919/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.40.down_proj:  98%|█████████▊| 35920/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.41.gate_proj:  98%|█████████▊| 35921/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.41.up_proj:  98%|█████████▊| 35922/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.41.down_proj:  98%|█████████▊| 35923/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.42.gate_proj:  98%|█████████▊| 35924/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.42.up_proj:  98%|█████████▊| 35925/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.42.down_proj:  98%|█████████▊| 35926/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.43.gate_proj:  98%|█████████▊| 35927/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.43.up_proj:  98%|█████████▊| 35928/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.43.down_proj:  98%|█████████▊| 35929/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.44.gate_proj:  98%|█████████▊| 35930/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.44.up_proj:  98%|█████████▊| 35931/36566 [00:32<00:00, 1144.38it/s]  
packing model.layers.92.mlp.experts.44.down_proj:  98%|█████████▊| 35932/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.45.gate_proj:  98%|█████████▊| 35933/36566 [00:32<00:00, 1144.38it/s]
packing model.layers.92.mlp.experts.45.gate_proj:  98%|█████████▊| 35934/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.45.up_proj:  98%|█████████▊| 35934/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.45.down_proj:  98%|█████████▊| 35935/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.46.gate_proj:  98%|█████████▊| 35936/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.46.up_proj:  98%|█████████▊| 35937/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.46.down_proj:  98%|█████████▊| 35938/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.47.gate_proj:  98%|█████████▊| 35939/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.47.up_proj:  98%|█████████▊| 35940/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.47.down_proj:  98%|█████████▊| 35941/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.48.gate_proj:  98%|█████████▊| 35942/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.48.up_proj:  98%|█████████▊| 35943/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.48.down_proj:  98%|█████████▊| 35944/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.49.gate_proj:  98%|█████████▊| 35945/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.49.up_proj:  98%|█████████▊| 35946/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.49.down_proj:  98%|█████████▊| 35947/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.50.gate_proj:  98%|█████████▊| 35948/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.50.up_proj:  98%|█████████▊| 35949/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.50.down_proj:  98%|█████████▊| 35950/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.51.gate_proj:  98%|█████████▊| 35951/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.51.up_proj:  98%|█████████▊| 35952/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.51.down_proj:  98%|█████████▊| 35953/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.52.gate_proj:  98%|█████████▊| 35954/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.52.up_proj:  98%|█████████▊| 35955/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.52.down_proj:  98%|█████████▊| 35956/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.53.gate_proj:  98%|█████████▊| 35957/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.53.up_proj:  98%|█████████▊| 35958/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.53.down_proj:  98%|█████████▊| 35959/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.54.gate_proj:  98%|█████████▊| 35960/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.54.up_proj:  98%|█████████▊| 35961/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.54.down_proj:  98%|█████████▊| 35962/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.55.gate_proj:  98%|█████████▊| 35963/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.55.up_proj:  98%|█████████▊| 35964/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.55.down_proj:  98%|█████████▊| 35965/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.56.gate_proj:  98%|█████████▊| 35966/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.56.up_proj:  98%|█████████▊| 35967/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.56.down_proj:  98%|█████████▊| 35968/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.57.gate_proj:  98%|█████████▊| 35969/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.57.up_proj:  98%|█████████▊| 35970/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.57.down_proj:  98%|█████████▊| 35971/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.58.gate_proj:  98%|█████████▊| 35972/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.58.up_proj:  98%|█████████▊| 35973/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.58.down_proj:  98%|█████████▊| 35974/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.59.gate_proj:  98%|█████████▊| 35975/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.59.up_proj:  98%|█████████▊| 35976/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.59.down_proj:  98%|█████████▊| 35977/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.60.gate_proj:  98%|█████████▊| 35978/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.60.up_proj:  98%|█████████▊| 35979/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.60.down_proj:  98%|█████████▊| 35980/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.61.gate_proj:  98%|█████████▊| 35981/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.61.up_proj:  98%|█████████▊| 35982/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.61.down_proj:  98%|█████████▊| 35983/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.62.gate_proj:  98%|█████████▊| 35984/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.62.up_proj:  98%|█████████▊| 35985/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.62.down_proj:  98%|█████████▊| 35986/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.63.gate_proj:  98%|█████████▊| 35987/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.63.up_proj:  98%|█████████▊| 35988/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.63.down_proj:  98%|█████████▊| 35989/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.64.gate_proj:  98%|█████████▊| 35990/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.64.up_proj:  98%|█████████▊| 35991/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.64.down_proj:  98%|█████████▊| 35992/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.65.gate_proj:  98%|█████████▊| 35993/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.65.up_proj:  98%|█████████▊| 35994/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.65.down_proj:  98%|█████████▊| 35995/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.66.gate_proj:  98%|█████████▊| 35996/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.66.up_proj:  98%|█████████▊| 35997/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.66.down_proj:  98%|█████████▊| 35998/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.67.gate_proj:  98%|█████████▊| 35999/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.67.up_proj:  98%|█████████▊| 36000/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.67.down_proj:  98%|█████████▊| 36001/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.68.gate_proj:  98%|█████████▊| 36002/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.68.up_proj:  98%|█████████▊| 36003/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.68.down_proj:  98%|█████████▊| 36004/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.69.gate_proj:  98%|█████████▊| 36005/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.69.up_proj:  98%|█████████▊| 36006/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.69.down_proj:  98%|█████████▊| 36007/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.70.gate_proj:  98%|█████████▊| 36008/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.70.up_proj:  98%|█████████▊| 36009/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.70.down_proj:  98%|█████████▊| 36010/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.71.gate_proj:  98%|█████████▊| 36011/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.71.up_proj:  98%|█████████▊| 36012/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.71.down_proj:  98%|█████████▊| 36013/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.72.gate_proj:  98%|█████████▊| 36014/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.72.up_proj:  98%|█████████▊| 36015/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.72.down_proj:  98%|█████████▊| 36016/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.73.gate_proj:  98%|█████████▊| 36017/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.73.up_proj:  99%|█████████▊| 36018/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.73.down_proj:  99%|█████████▊| 36019/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.74.gate_proj:  99%|█████████▊| 36020/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.74.up_proj:  99%|█████████▊| 36021/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.74.down_proj:  99%|█████████▊| 36022/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.75.gate_proj:  99%|█████████▊| 36023/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.75.up_proj:  99%|█████████▊| 36024/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.75.down_proj:  99%|█████████▊| 36025/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.76.gate_proj:  99%|█████████▊| 36026/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.76.up_proj:  99%|█████████▊| 36027/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.76.down_proj:  99%|█████████▊| 36028/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.77.gate_proj:  99%|█████████▊| 36029/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.77.up_proj:  99%|█████████▊| 36030/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.77.down_proj:  99%|█████████▊| 36031/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.78.gate_proj:  99%|█████████▊| 36032/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.78.up_proj:  99%|█████████▊| 36033/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.78.down_proj:  99%|█████████▊| 36034/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.79.gate_proj:  99%|█████████▊| 36035/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.79.up_proj:  99%|█████████▊| 36036/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.79.down_proj:  99%|█████████▊| 36037/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.80.gate_proj:  99%|█████████▊| 36038/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.80.up_proj:  99%|█████████▊| 36039/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.80.down_proj:  99%|█████████▊| 36040/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.81.gate_proj:  99%|█████████▊| 36041/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.81.up_proj:  99%|█████████▊| 36042/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.81.down_proj:  99%|█████████▊| 36043/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.82.gate_proj:  99%|█████████▊| 36044/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.82.up_proj:  99%|█████████▊| 36045/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.82.down_proj:  99%|█████████▊| 36046/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.83.gate_proj:  99%|█████████▊| 36047/36566 [00:32<00:00, 1143.31it/s]
packing model.layers.92.mlp.experts.83.up_proj:  99%|█████████▊| 36048/36566 [00:32<00:00, 1143.31it/s]  
packing model.layers.92.mlp.experts.83.up_proj:  99%|█████████▊| 36049/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.83.down_proj:  99%|█████████▊| 36049/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.84.gate_proj:  99%|█████████▊| 36050/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.84.up_proj:  99%|█████████▊| 36051/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.84.down_proj:  99%|█████████▊| 36052/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.85.gate_proj:  99%|█████████▊| 36053/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.85.up_proj:  99%|█████████▊| 36054/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.85.down_proj:  99%|█████████▊| 36055/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.86.gate_proj:  99%|█████████▊| 36056/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.86.up_proj:  99%|█████████▊| 36057/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.86.down_proj:  99%|█████████▊| 36058/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.87.gate_proj:  99%|█████████▊| 36059/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.87.up_proj:  99%|█████████▊| 36060/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.87.down_proj:  99%|█████████▊| 36061/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.88.gate_proj:  99%|█████████▊| 36062/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.88.up_proj:  99%|█████████▊| 36063/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.88.down_proj:  99%|█████████▊| 36064/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.89.gate_proj:  99%|█████████▊| 36065/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.89.up_proj:  99%|█████████▊| 36066/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.89.down_proj:  99%|█████████▊| 36067/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.90.gate_proj:  99%|█████████▊| 36068/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.90.up_proj:  99%|█████████▊| 36069/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.90.down_proj:  99%|█████████▊| 36070/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.91.gate_proj:  99%|█████████▊| 36071/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.91.up_proj:  99%|█████████▊| 36072/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.91.down_proj:  99%|█████████▊| 36073/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.92.gate_proj:  99%|█████████▊| 36074/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.92.up_proj:  99%|█████████▊| 36075/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.92.down_proj:  99%|█████████▊| 36076/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.93.gate_proj:  99%|█████████▊| 36077/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.93.up_proj:  99%|█████████▊| 36078/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.93.down_proj:  99%|█████████▊| 36079/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.94.gate_proj:  99%|█████████▊| 36080/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.94.up_proj:  99%|█████████▊| 36081/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.94.down_proj:  99%|█████████▊| 36082/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.95.gate_proj:  99%|█████████▊| 36083/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.95.up_proj:  99%|█████████▊| 36084/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.95.down_proj:  99%|█████████▊| 36085/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.96.gate_proj:  99%|█████████▊| 36086/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.96.up_proj:  99%|█████████▊| 36087/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.96.down_proj:  99%|█████████▊| 36088/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.97.gate_proj:  99%|█████████▊| 36089/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.97.up_proj:  99%|█████████▊| 36090/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.97.down_proj:  99%|█████████▊| 36091/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.98.gate_proj:  99%|█████████▊| 36092/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.98.up_proj:  99%|█████████▊| 36093/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.98.down_proj:  99%|█████████▊| 36094/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.99.gate_proj:  99%|█████████▊| 36095/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.99.up_proj:  99%|█████████▊| 36096/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.99.down_proj:  99%|█████████▊| 36097/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.100.gate_proj:  99%|█████████▊| 36098/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.100.up_proj:  99%|█████████▊| 36099/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.100.down_proj:  99%|█████████▊| 36100/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.101.gate_proj:  99%|█████████▊| 36101/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.101.up_proj:  99%|█████████▊| 36102/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.101.down_proj:  99%|█████████▊| 36103/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.102.gate_proj:  99%|█████████▊| 36104/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.102.up_proj:  99%|█████████▊| 36105/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.102.down_proj:  99%|█████████▊| 36106/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.103.gate_proj:  99%|█████████▊| 36107/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.103.up_proj:  99%|█████████▊| 36108/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.103.down_proj:  99%|█████████▉| 36109/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.104.gate_proj:  99%|█████████▉| 36110/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.104.up_proj:  99%|█████████▉| 36111/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.104.down_proj:  99%|█████████▉| 36112/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.105.gate_proj:  99%|█████████▉| 36113/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.105.up_proj:  99%|█████████▉| 36114/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.105.down_proj:  99%|█████████▉| 36115/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.106.gate_proj:  99%|█████████▉| 36116/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.106.up_proj:  99%|█████████▉| 36117/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.106.down_proj:  99%|█████████▉| 36118/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.107.gate_proj:  99%|█████████▉| 36119/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.107.up_proj:  99%|█████████▉| 36120/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.107.down_proj:  99%|█████████▉| 36121/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.108.gate_proj:  99%|█████████▉| 36122/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.108.up_proj:  99%|█████████▉| 36123/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.108.down_proj:  99%|█████████▉| 36124/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.109.gate_proj:  99%|█████████▉| 36125/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.109.up_proj:  99%|█████████▉| 36126/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.109.down_proj:  99%|█████████▉| 36127/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.110.gate_proj:  99%|█████████▉| 36128/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.110.up_proj:  99%|█████████▉| 36129/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.110.down_proj:  99%|█████████▉| 36130/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.111.gate_proj:  99%|█████████▉| 36131/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.111.up_proj:  99%|█████████▉| 36132/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.111.down_proj:  99%|█████████▉| 36133/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.112.gate_proj:  99%|█████████▉| 36134/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.112.up_proj:  99%|█████████▉| 36135/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.112.down_proj:  99%|█████████▉| 36136/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.113.gate_proj:  99%|█████████▉| 36137/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.113.up_proj:  99%|█████████▉| 36138/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.113.down_proj:  99%|█████████▉| 36139/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.114.gate_proj:  99%|█████████▉| 36140/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.114.up_proj:  99%|█████████▉| 36141/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.114.down_proj:  99%|█████████▉| 36142/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.115.gate_proj:  99%|█████████▉| 36143/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.115.up_proj:  99%|█████████▉| 36144/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.115.down_proj:  99%|█████████▉| 36145/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.116.gate_proj:  99%|█████████▉| 36146/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.116.up_proj:  99%|█████████▉| 36147/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.116.down_proj:  99%|█████████▉| 36148/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.117.gate_proj:  99%|█████████▉| 36149/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.117.up_proj:  99%|█████████▉| 36150/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.117.down_proj:  99%|█████████▉| 36151/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.118.gate_proj:  99%|█████████▉| 36152/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.118.up_proj:  99%|█████████▉| 36153/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.118.down_proj:  99%|█████████▉| 36154/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.119.gate_proj:  99%|█████████▉| 36155/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.119.up_proj:  99%|█████████▉| 36156/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.119.down_proj:  99%|█████████▉| 36157/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.120.gate_proj:  99%|█████████▉| 36158/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.120.up_proj:  99%|█████████▉| 36159/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.120.down_proj:  99%|█████████▉| 36160/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.121.gate_proj:  99%|█████████▉| 36161/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.121.up_proj:  99%|█████████▉| 36162/36566 [00:32<00:00, 1142.55it/s]  
packing model.layers.92.mlp.experts.121.down_proj:  99%|█████████▉| 36163/36566 [00:32<00:00, 1142.55it/s]
packing model.layers.92.mlp.experts.121.down_proj:  99%|█████████▉| 36164/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.122.gate_proj:  99%|█████████▉| 36164/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.122.up_proj:  99%|█████████▉| 36165/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.122.down_proj:  99%|█████████▉| 36166/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.123.gate_proj:  99%|█████████▉| 36167/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.123.up_proj:  99%|█████████▉| 36168/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.123.down_proj:  99%|█████████▉| 36169/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.124.gate_proj:  99%|█████████▉| 36170/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.124.up_proj:  99%|█████████▉| 36171/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.124.down_proj:  99%|█████████▉| 36172/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.125.gate_proj:  99%|█████████▉| 36173/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.125.up_proj:  99%|█████████▉| 36174/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.125.down_proj:  99%|█████████▉| 36175/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.126.gate_proj:  99%|█████████▉| 36176/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.126.up_proj:  99%|█████████▉| 36177/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.126.down_proj:  99%|█████████▉| 36178/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.127.gate_proj:  99%|█████████▉| 36179/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.92.mlp.experts.127.up_proj:  99%|█████████▉| 36180/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.92.mlp.experts.127.down_proj:  99%|█████████▉| 36181/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.0.gate_proj:  99%|█████████▉| 36182/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.0.up_proj:  99%|█████████▉| 36183/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.0.down_proj:  99%|█████████▉| 36184/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.1.gate_proj:  99%|█████████▉| 36185/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.1.up_proj:  99%|█████████▉| 36186/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.1.down_proj:  99%|█████████▉| 36187/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.2.gate_proj:  99%|█████████▉| 36188/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.2.up_proj:  99%|█████████▉| 36189/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.2.down_proj:  99%|█████████▉| 36190/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.3.gate_proj:  99%|█████████▉| 36191/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.3.up_proj:  99%|█████████▉| 36192/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.3.down_proj:  99%|█████████▉| 36193/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.4.gate_proj:  99%|█████████▉| 36194/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.4.up_proj:  99%|█████████▉| 36195/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.4.down_proj:  99%|█████████▉| 36196/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.5.gate_proj:  99%|█████████▉| 36197/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.5.up_proj:  99%|█████████▉| 36198/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.5.down_proj:  99%|█████████▉| 36199/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.6.gate_proj:  99%|█████████▉| 36200/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.6.up_proj:  99%|█████████▉| 36201/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.6.down_proj:  99%|█████████▉| 36202/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.7.gate_proj:  99%|█████████▉| 36203/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.7.up_proj:  99%|█████████▉| 36204/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.7.down_proj:  99%|█████████▉| 36205/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.8.gate_proj:  99%|█████████▉| 36206/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.8.up_proj:  99%|█████████▉| 36207/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.8.down_proj:  99%|█████████▉| 36208/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.9.gate_proj:  99%|█████████▉| 36209/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.9.up_proj:  99%|█████████▉| 36210/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.9.down_proj:  99%|█████████▉| 36211/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.10.gate_proj:  99%|█████████▉| 36212/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.10.up_proj:  99%|█████████▉| 36213/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.10.down_proj:  99%|█████████▉| 36214/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.11.gate_proj:  99%|█████████▉| 36215/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.11.up_proj:  99%|█████████▉| 36216/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.11.down_proj:  99%|█████████▉| 36217/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.12.gate_proj:  99%|█████████▉| 36218/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.12.up_proj:  99%|█████████▉| 36219/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.12.down_proj:  99%|█████████▉| 36220/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.13.gate_proj:  99%|█████████▉| 36221/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.13.up_proj:  99%|█████████▉| 36222/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.13.down_proj:  99%|█████████▉| 36223/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.14.gate_proj:  99%|█████████▉| 36224/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.14.up_proj:  99%|█████████▉| 36225/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.14.down_proj:  99%|█████████▉| 36226/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.15.gate_proj:  99%|█████████▉| 36227/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.15.up_proj:  99%|█████████▉| 36228/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.15.down_proj:  99%|█████████▉| 36229/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.16.gate_proj:  99%|█████████▉| 36230/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.16.up_proj:  99%|█████████▉| 36231/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.16.down_proj:  99%|█████████▉| 36232/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.17.gate_proj:  99%|█████████▉| 36233/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.17.up_proj:  99%|█████████▉| 36234/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.17.down_proj:  99%|█████████▉| 36235/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.18.gate_proj:  99%|█████████▉| 36236/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.18.up_proj:  99%|█████████▉| 36237/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.18.down_proj:  99%|█████████▉| 36238/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.19.gate_proj:  99%|█████████▉| 36239/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.19.up_proj:  99%|█████████▉| 36240/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.19.down_proj:  99%|█████████▉| 36241/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.20.gate_proj:  99%|█████████▉| 36242/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.20.up_proj:  99%|█████████▉| 36243/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.20.down_proj:  99%|█████████▉| 36244/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.21.gate_proj:  99%|█████████▉| 36245/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.21.up_proj:  99%|█████████▉| 36246/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.21.down_proj:  99%|█████████▉| 36247/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.22.gate_proj:  99%|█████████▉| 36248/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.22.up_proj:  99%|█████████▉| 36249/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.22.down_proj:  99%|█████████▉| 36250/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.23.gate_proj:  99%|█████████▉| 36251/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.23.up_proj:  99%|█████████▉| 36252/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.23.down_proj:  99%|█████████▉| 36253/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.24.gate_proj:  99%|█████████▉| 36254/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.24.up_proj:  99%|█████████▉| 36255/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.24.down_proj:  99%|█████████▉| 36256/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.25.gate_proj:  99%|█████████▉| 36257/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.25.up_proj:  99%|█████████▉| 36258/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.25.down_proj:  99%|█████████▉| 36259/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.26.gate_proj:  99%|█████████▉| 36260/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.26.up_proj:  99%|█████████▉| 36261/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.26.down_proj:  99%|█████████▉| 36262/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.27.gate_proj:  99%|█████████▉| 36263/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.27.up_proj:  99%|█████████▉| 36264/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.27.down_proj:  99%|█████████▉| 36265/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.28.gate_proj:  99%|█████████▉| 36266/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.28.up_proj:  99%|█████████▉| 36267/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.28.down_proj:  99%|█████████▉| 36268/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.29.gate_proj:  99%|█████████▉| 36269/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.29.up_proj:  99%|█████████▉| 36270/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.29.down_proj:  99%|█████████▉| 36271/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.30.gate_proj:  99%|█████████▉| 36272/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.30.up_proj:  99%|█████████▉| 36273/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.30.down_proj:  99%|█████████▉| 36274/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.31.gate_proj:  99%|█████████▉| 36275/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.31.up_proj:  99%|█████████▉| 36276/36566 [00:32<00:00, 1142.26it/s]  
packing model.layers.93.mlp.experts.31.down_proj:  99%|█████████▉| 36277/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.32.gate_proj:  99%|█████████▉| 36278/36566 [00:32<00:00, 1142.26it/s]
packing model.layers.93.mlp.experts.32.gate_proj:  99%|█████████▉| 36279/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.32.up_proj:  99%|█████████▉| 36279/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.32.down_proj:  99%|█████████▉| 36280/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.33.gate_proj:  99%|█████████▉| 36281/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.33.up_proj:  99%|█████████▉| 36282/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.33.down_proj:  99%|█████████▉| 36283/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.34.gate_proj:  99%|█████████▉| 36284/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.34.up_proj:  99%|█████████▉| 36285/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.34.down_proj:  99%|█████████▉| 36286/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.35.gate_proj:  99%|█████████▉| 36287/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.35.up_proj:  99%|█████████▉| 36288/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.35.down_proj:  99%|█████████▉| 36289/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.36.gate_proj:  99%|█████████▉| 36290/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.36.up_proj:  99%|█████████▉| 36291/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.36.down_proj:  99%|█████████▉| 36292/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.37.gate_proj:  99%|█████████▉| 36293/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.37.up_proj:  99%|█████████▉| 36294/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.37.down_proj:  99%|█████████▉| 36295/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.38.gate_proj:  99%|█████████▉| 36296/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.38.up_proj:  99%|█████████▉| 36297/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.38.down_proj:  99%|█████████▉| 36298/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.39.gate_proj:  99%|█████████▉| 36299/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.39.up_proj:  99%|█████████▉| 36300/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.39.down_proj:  99%|█████████▉| 36301/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.40.gate_proj:  99%|█████████▉| 36302/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.40.up_proj:  99%|█████████▉| 36303/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.40.down_proj:  99%|█████████▉| 36304/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.41.gate_proj:  99%|█████████▉| 36305/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.41.up_proj:  99%|█████████▉| 36306/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.41.down_proj:  99%|█████████▉| 36307/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.42.gate_proj:  99%|█████████▉| 36308/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.42.up_proj:  99%|█████████▉| 36309/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.42.down_proj:  99%|█████████▉| 36310/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.43.gate_proj:  99%|█████████▉| 36311/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.43.up_proj:  99%|█████████▉| 36312/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.43.down_proj:  99%|█████████▉| 36313/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.44.gate_proj:  99%|█████████▉| 36314/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.44.up_proj:  99%|█████████▉| 36315/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.44.down_proj:  99%|█████████▉| 36316/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.45.gate_proj:  99%|█████████▉| 36317/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.45.up_proj:  99%|█████████▉| 36318/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.45.down_proj:  99%|█████████▉| 36319/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.46.gate_proj:  99%|█████████▉| 36320/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.46.up_proj:  99%|█████████▉| 36321/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.46.down_proj:  99%|█████████▉| 36322/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.47.gate_proj:  99%|█████████▉| 36323/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.47.up_proj:  99%|█████████▉| 36324/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.47.down_proj:  99%|█████████▉| 36325/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.48.gate_proj:  99%|█████████▉| 36326/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.48.up_proj:  99%|█████████▉| 36327/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.48.down_proj:  99%|█████████▉| 36328/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.49.gate_proj:  99%|█████████▉| 36329/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.49.up_proj:  99%|█████████▉| 36330/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.49.down_proj:  99%|█████████▉| 36331/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.50.gate_proj:  99%|█████████▉| 36332/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.50.up_proj:  99%|█████████▉| 36333/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.50.down_proj:  99%|█████████▉| 36334/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.51.gate_proj:  99%|█████████▉| 36335/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.51.up_proj:  99%|█████████▉| 36336/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.51.down_proj:  99%|█████████▉| 36337/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.52.gate_proj:  99%|█████████▉| 36338/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.52.up_proj:  99%|█████████▉| 36339/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.52.down_proj:  99%|█████████▉| 36340/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.53.gate_proj:  99%|█████████▉| 36341/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.53.up_proj:  99%|█████████▉| 36342/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.53.down_proj:  99%|█████████▉| 36343/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.54.gate_proj:  99%|█████████▉| 36344/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.54.up_proj:  99%|█████████▉| 36345/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.54.down_proj:  99%|█████████▉| 36346/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.55.gate_proj:  99%|█████████▉| 36347/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.55.up_proj:  99%|█████████▉| 36348/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.55.down_proj:  99%|█████████▉| 36349/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.56.gate_proj:  99%|█████████▉| 36350/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.56.up_proj:  99%|█████████▉| 36351/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.56.down_proj:  99%|█████████▉| 36352/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.57.gate_proj:  99%|█████████▉| 36353/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.57.up_proj:  99%|█████████▉| 36354/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.57.down_proj:  99%|█████████▉| 36355/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.58.gate_proj:  99%|█████████▉| 36356/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.58.up_proj:  99%|█████████▉| 36357/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.58.down_proj:  99%|█████████▉| 36358/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.59.gate_proj:  99%|█████████▉| 36359/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.59.up_proj:  99%|█████████▉| 36360/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.59.down_proj:  99%|█████████▉| 36361/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.60.gate_proj:  99%|█████████▉| 36362/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.60.up_proj:  99%|█████████▉| 36363/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.60.down_proj:  99%|█████████▉| 36364/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.61.gate_proj:  99%|█████████▉| 36365/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.61.up_proj:  99%|█████████▉| 36366/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.61.down_proj:  99%|█████████▉| 36367/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.62.gate_proj:  99%|█████████▉| 36368/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.62.up_proj:  99%|█████████▉| 36369/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.62.down_proj:  99%|█████████▉| 36370/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.63.gate_proj:  99%|█████████▉| 36371/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.63.up_proj:  99%|█████████▉| 36372/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.63.down_proj:  99%|█████████▉| 36373/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.64.gate_proj:  99%|█████████▉| 36374/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.64.up_proj:  99%|█████████▉| 36375/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.64.down_proj:  99%|█████████▉| 36376/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.65.gate_proj:  99%|█████████▉| 36377/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.65.up_proj:  99%|█████████▉| 36378/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.65.down_proj:  99%|█████████▉| 36379/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.66.gate_proj:  99%|█████████▉| 36380/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.66.up_proj:  99%|█████████▉| 36381/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.66.down_proj:  99%|█████████▉| 36382/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.67.gate_proj:  99%|█████████▉| 36383/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.67.up_proj: 100%|█████████▉| 36384/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.67.down_proj: 100%|█████████▉| 36385/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.68.gate_proj: 100%|█████████▉| 36386/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.68.up_proj: 100%|█████████▉| 36387/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.68.down_proj: 100%|█████████▉| 36388/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.69.gate_proj: 100%|█████████▉| 36389/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.69.up_proj: 100%|█████████▉| 36390/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.69.down_proj: 100%|█████████▉| 36391/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.70.gate_proj: 100%|█████████▉| 36392/36566 [00:32<00:00, 1141.95it/s]
packing model.layers.93.mlp.experts.70.up_proj: 100%|█████████▉| 36393/36566 [00:32<00:00, 1141.95it/s]  
packing model.layers.93.mlp.experts.70.up_proj: 100%|█████████▉| 36394/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.70.down_proj: 100%|█████████▉| 36394/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.71.gate_proj: 100%|█████████▉| 36395/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.71.up_proj: 100%|█████████▉| 36396/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.71.down_proj: 100%|█████████▉| 36397/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.72.gate_proj: 100%|█████████▉| 36398/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.72.up_proj: 100%|█████████▉| 36399/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.72.down_proj: 100%|█████████▉| 36400/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.73.gate_proj: 100%|█████████▉| 36401/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.73.up_proj: 100%|█████████▉| 36402/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.73.down_proj: 100%|█████████▉| 36403/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.74.gate_proj: 100%|█████████▉| 36404/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.74.up_proj: 100%|█████████▉| 36405/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.74.down_proj: 100%|█████████▉| 36406/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.75.gate_proj: 100%|█████████▉| 36407/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.75.up_proj: 100%|█████████▉| 36408/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.75.down_proj: 100%|█████████▉| 36409/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.76.gate_proj: 100%|█████████▉| 36410/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.76.up_proj: 100%|█████████▉| 36411/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.76.down_proj: 100%|█████████▉| 36412/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.77.gate_proj: 100%|█████████▉| 36413/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.77.up_proj: 100%|█████████▉| 36414/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.77.down_proj: 100%|█████████▉| 36415/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.78.gate_proj: 100%|█████████▉| 36416/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.78.up_proj: 100%|█████████▉| 36417/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.78.down_proj: 100%|█████████▉| 36418/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.79.gate_proj: 100%|█████████▉| 36419/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.79.up_proj: 100%|█████████▉| 36420/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.79.down_proj: 100%|█████████▉| 36421/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.80.gate_proj: 100%|█████████▉| 36422/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.80.up_proj: 100%|█████████▉| 36423/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.80.down_proj: 100%|█████████▉| 36424/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.81.gate_proj: 100%|█████████▉| 36425/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.81.up_proj: 100%|█████████▉| 36426/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.81.down_proj: 100%|█████████▉| 36427/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.82.gate_proj: 100%|█████████▉| 36428/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.82.up_proj: 100%|█████████▉| 36429/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.82.down_proj: 100%|█████████▉| 36430/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.83.gate_proj: 100%|█████████▉| 36431/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.83.up_proj: 100%|█████████▉| 36432/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.83.down_proj: 100%|█████████▉| 36433/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.84.gate_proj: 100%|█████████▉| 36434/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.84.up_proj: 100%|█████████▉| 36435/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.84.down_proj: 100%|█████████▉| 36436/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.85.gate_proj: 100%|█████████▉| 36437/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.85.up_proj: 100%|█████████▉| 36438/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.85.down_proj: 100%|█████████▉| 36439/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.86.gate_proj: 100%|█████████▉| 36440/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.86.up_proj: 100%|█████████▉| 36441/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.86.down_proj: 100%|█████████▉| 36442/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.87.gate_proj: 100%|█████████▉| 36443/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.87.up_proj: 100%|█████████▉| 36444/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.87.down_proj: 100%|█████████▉| 36445/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.88.gate_proj: 100%|█████████▉| 36446/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.88.up_proj: 100%|█████████▉| 36447/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.88.down_proj: 100%|█████████▉| 36448/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.89.gate_proj: 100%|█████████▉| 36449/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.89.up_proj: 100%|█████████▉| 36450/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.89.down_proj: 100%|█████████▉| 36451/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.90.gate_proj: 100%|█████████▉| 36452/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.90.up_proj: 100%|█████████▉| 36453/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.90.down_proj: 100%|█████████▉| 36454/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.91.gate_proj: 100%|█████████▉| 36455/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.91.up_proj: 100%|█████████▉| 36456/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.91.down_proj: 100%|█████████▉| 36457/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.92.gate_proj: 100%|█████████▉| 36458/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.92.up_proj: 100%|█████████▉| 36459/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.92.down_proj: 100%|█████████▉| 36460/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.93.gate_proj: 100%|█████████▉| 36461/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.93.up_proj: 100%|█████████▉| 36462/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.93.down_proj: 100%|█████████▉| 36463/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.94.gate_proj: 100%|█████████▉| 36464/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.94.up_proj: 100%|█████████▉| 36465/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.94.down_proj: 100%|█████████▉| 36466/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.95.gate_proj: 100%|█████████▉| 36467/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.95.up_proj: 100%|█████████▉| 36468/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.95.down_proj: 100%|█████████▉| 36469/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.96.gate_proj: 100%|█████████▉| 36470/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.96.up_proj: 100%|█████████▉| 36471/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.96.down_proj: 100%|█████████▉| 36472/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.97.gate_proj: 100%|█████████▉| 36473/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.97.up_proj: 100%|█████████▉| 36474/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.97.down_proj: 100%|█████████▉| 36475/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.98.gate_proj: 100%|█████████▉| 36476/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.98.up_proj: 100%|█████████▉| 36477/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.98.down_proj: 100%|█████████▉| 36478/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.99.gate_proj: 100%|█████████▉| 36479/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.99.up_proj: 100%|█████████▉| 36480/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.99.down_proj: 100%|█████████▉| 36481/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.100.gate_proj: 100%|█████████▉| 36482/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.100.up_proj: 100%|█████████▉| 36483/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.100.down_proj: 100%|█████████▉| 36484/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.101.gate_proj: 100%|█████████▉| 36485/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.101.up_proj: 100%|█████████▉| 36486/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.101.down_proj: 100%|█████████▉| 36487/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.102.gate_proj: 100%|█████████▉| 36488/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.102.up_proj: 100%|█████████▉| 36489/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.102.down_proj: 100%|█████████▉| 36490/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.103.gate_proj: 100%|█████████▉| 36491/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.103.up_proj: 100%|█████████▉| 36492/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.103.down_proj: 100%|█████████▉| 36493/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.104.gate_proj: 100%|█████████▉| 36494/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.104.up_proj: 100%|█████████▉| 36495/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.104.down_proj: 100%|█████████▉| 36496/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.105.gate_proj: 100%|█████████▉| 36497/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.105.up_proj: 100%|█████████▉| 36498/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.105.down_proj: 100%|█████████▉| 36499/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.106.gate_proj: 100%|█████████▉| 36500/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.106.up_proj: 100%|█████████▉| 36501/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.106.down_proj: 100%|█████████▉| 36502/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.107.gate_proj: 100%|█████████▉| 36503/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.107.up_proj: 100%|█████████▉| 36504/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.107.down_proj: 100%|█████████▉| 36505/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.108.gate_proj: 100%|█████████▉| 36506/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.108.up_proj: 100%|█████████▉| 36507/36566 [00:32<00:00, 1143.05it/s]  
packing model.layers.93.mlp.experts.108.down_proj: 100%|█████████▉| 36508/36566 [00:32<00:00, 1143.05it/s]
packing model.layers.93.mlp.experts.108.down_proj: 100%|█████████▉| 36509/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.109.gate_proj: 100%|█████████▉| 36509/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.109.up_proj: 100%|█████████▉| 36510/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.109.down_proj: 100%|█████████▉| 36511/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.110.gate_proj: 100%|█████████▉| 36512/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.110.up_proj: 100%|█████████▉| 36513/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.110.down_proj: 100%|█████████▉| 36514/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.111.gate_proj: 100%|█████████▉| 36515/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.111.up_proj: 100%|█████████▉| 36516/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.111.down_proj: 100%|█████████▉| 36517/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.112.gate_proj: 100%|█████████▉| 36518/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.112.up_proj: 100%|█████████▉| 36519/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.112.down_proj: 100%|█████████▉| 36520/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.113.gate_proj: 100%|█████████▉| 36521/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.113.up_proj: 100%|█████████▉| 36522/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.113.down_proj: 100%|█████████▉| 36523/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.114.gate_proj: 100%|█████████▉| 36524/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.114.up_proj: 100%|█████████▉| 36525/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.114.down_proj: 100%|█████████▉| 36526/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.115.gate_proj: 100%|█████████▉| 36527/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.115.up_proj: 100%|█████████▉| 36528/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.115.down_proj: 100%|█████████▉| 36529/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.116.gate_proj: 100%|█████████▉| 36530/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.116.up_proj: 100%|█████████▉| 36531/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.116.down_proj: 100%|█████████▉| 36532/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.117.gate_proj: 100%|█████████▉| 36533/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.117.up_proj: 100%|█████████▉| 36534/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.117.down_proj: 100%|█████████▉| 36535/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.118.gate_proj: 100%|█████████▉| 36536/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.118.up_proj: 100%|█████████▉| 36537/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.118.down_proj: 100%|█████████▉| 36538/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.119.gate_proj: 100%|█████████▉| 36539/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.119.up_proj: 100%|█████████▉| 36540/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.119.down_proj: 100%|█████████▉| 36541/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.120.gate_proj: 100%|█████████▉| 36542/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.120.up_proj: 100%|█████████▉| 36543/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.120.down_proj: 100%|█████████▉| 36544/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.121.gate_proj: 100%|█████████▉| 36545/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.121.up_proj: 100%|█████████▉| 36546/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.121.down_proj: 100%|█████████▉| 36547/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.122.gate_proj: 100%|█████████▉| 36548/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.122.up_proj: 100%|█████████▉| 36549/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.122.down_proj: 100%|█████████▉| 36550/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.123.gate_proj: 100%|█████████▉| 36551/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.123.up_proj: 100%|█████████▉| 36552/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.123.down_proj: 100%|█████████▉| 36553/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.124.gate_proj: 100%|█████████▉| 36554/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.124.up_proj: 100%|█████████▉| 36555/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.124.down_proj: 100%|█████████▉| 36556/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.125.gate_proj: 100%|█████████▉| 36557/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.125.up_proj: 100%|█████████▉| 36558/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.125.down_proj: 100%|█████████▉| 36559/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.126.gate_proj: 100%|█████████▉| 36560/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.126.up_proj: 100%|█████████▉| 36561/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.126.down_proj: 100%|█████████▉| 36562/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.127.gate_proj: 100%|█████████▉| 36563/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.127.up_proj: 100%|█████████▉| 36564/36566 [00:32<00:00, 1142.39it/s]  
packing model.layers.93.mlp.experts.127.down_proj: 100%|█████████▉| 36565/36566 [00:32<00:00, 1142.39it/s]
packing model.layers.93.mlp.experts.127.down_proj: 100%|██████████| 36566/36566 [00:32<00:00, 1108.60it/s]
HTTP Request: %s %s "%s %d %s"
chaiml-muster-v2-q235b-77862-v1-uploader: Checking if ChaiML/muster-v2-q235b-lr1e4ep2r64g4-W4A16 already exists in ChaiML
chaiml-muster-v2-q235b-77862-v1-uploader: Creating repo ChaiML/muster-v2-q235b-lr1e4ep2r64g4-W4A16 and uploading /dev/shm/model_output to it
chaiml-muster-v2-q235b-77862-v1-uploader: 
Recovering from metadata files:   0%|          | 0/38 [00:00<?, ?it/s]
Recovering from metadata files: 100%|██████████| 38/38 [00:00<00:00, 8453.57it/s]
chaiml-muster-v2-q235b-77862-v1-uploader: ---------- 2026-02-09 20:50:30 (0:00:00) ----------
chaiml-muster-v2-q235b-77862-v1-uploader: Files:   hashed 11/38 (26.1M/131.9G) | pre-uploaded: 0/1 (0.0/131.9G) (+27 unsure) | committed: 0/38 (0.0/131.9G) | ignored: 0
chaiml-muster-v2-q235b-77862-v1-uploader: Workers: hashing: 27 | get upload mode: 0 | pre-uploading: 1 | committing: 0 | waiting: 98
chaiml-muster-v2-q235b-77862-v1-uploader: ---------------------------------------------------
chaiml-muster-v2-q235b-77862-v1-uploader: 
Processing Files (0 / 0)      : |          |  0.00B /  0.00B            
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : |          |  0.00B /  0.00B            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
Processing Files (1 / 1)      : 100%|██████████| 11.4MB / 11.4MB, 19.0MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
Processing Files (1 / 1)      : 100%|██████████| 11.4MB / 11.4MB, 11.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : |          |  0.00B /  0.00B,  0.00B/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...del_output/tokenizer.json: 100%|██████████| 11.4MB / 11.4MB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
Processing Files (0 / 0)      : |          |  0.00B /  0.00B            
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : |          |  0.00B /  0.00B            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:   0%|          | 73.3kB / 1.93GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:   0%|          | 73.3kB / 1.93GB            
Processing Files (0 / 1)      :   0%|          | 73.3kB / 1.93GB,   ???B/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:   0%|          | 73.3kB / 1.93GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:   3%|▎         | 67.1MB / 1.93GB            
Processing Files (0 / 1)      :   3%|▎         | 67.1MB / 1.93GB,  167MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  50%|████▉     | 67.0MB /  134MB,  167MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:   7%|▋         |  134MB / 1.93GB            
Processing Files (0 / 1)      :   7%|▋         |  134MB / 1.93GB,  223MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  67%|██████▋   |  134MB /  201MB,  223MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  10%|█         |  200MB / 1.93GB            
Processing Files (0 / 1)      :  10%|█         |  200MB / 1.93GB,  250MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  75%|███████▍  |  200MB /  268MB,  250MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  14%|█▍        |  267MB / 1.93GB            
Processing Files (0 / 1)      :  14%|█▍        |  267MB / 1.93GB,  267MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉|  267MB /  268MB,  267MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  17%|█▋        |  334MB / 1.93GB            
Processing Files (0 / 1)      :  17%|█▋        |  334MB / 1.93GB,  278MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉|  334MB /  335MB,  278MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  21%|██        |  401MB / 1.93GB            
Processing Files (0 / 1)      :  21%|██        |  401MB / 1.93GB,  286MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉|  401MB /  402MB,  286MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  22%|██▏       |  432MB / 1.93GB            
Processing Files (0 / 1)      :  22%|██▏       |  432MB / 1.93GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  92%|█████████▏|  432MB /  469MB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  25%|██▍       |  482MB / 1.93GB            
Processing Files (0 / 1)      :  25%|██▍       |  482MB / 1.93GB,  268MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  90%|████████▉ |  482MB /  536MB,  268MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  28%|██▊       |  536MB / 1.93GB            
Processing Files (0 / 1)      :  28%|██▊       |  536MB / 1.93GB,  268MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  89%|████████▉ |  536MB /  603MB,  268MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  31%|███       |  602MB / 1.93GB            
Processing Files (0 / 1)      :  31%|███       |  602MB / 1.93GB,  274MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  90%|████████▉ |  602MB /  670MB,  274MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  35%|███▍      |  670MB / 1.93GB            
Processing Files (0 / 1)      :  35%|███▍      |  670MB / 1.93GB,  279MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉|  670MB /  670MB,  279MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  36%|███▌      |  695MB / 1.93GB            
Processing Files (0 / 1)      :  36%|███▌      |  695MB / 1.93GB,  267MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  40%|███▉      |  763MB / 1.93GB            
Processing Files (0 / 1)      :  40%|███▉      |  763MB / 1.93GB,  272MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉|  670MB /  670MB,  239MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  43%|████▎     |  838MB / 1.93GB            
Processing Files (0 / 1)      :  43%|████▎     |  838MB / 1.93GB,  279MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  47%|████▋     |  914MB / 1.93GB            
Processing Files (0 / 1)      :  47%|████▋     |  914MB / 1.93GB,  286MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|██████████|  670MB /  670MB,  210MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0027-of-00027.safetensors:  51%|█████     |  981MB / 1.93GB            
Processing Files (0 / 1)      :  51%|█████     |  981MB / 1.93GB,  289MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
Processing Files (0 / 1)      :  21%|██▏       | 1.07GB / 5.00GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.07GB / 1.14GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  20%|██        | 1.01GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  19%|█▉        |  939MB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  20%|██        | 1.01GB / 4.98GB            
Processing Files (0 / 1)      :  20%|██        | 1.01GB / 4.98GB, 65.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.01GB / 1.07GB, 65.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
Processing Files (0 / 1)      :  20%|██        | 1.01GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▎| 1.01GB / 1.07GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
Processing Files (0 / 1)      :  20%|██        | 1.01GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▎| 1.01GB / 1.07GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  22%|██▏       | 1.07GB / 4.98GB            
Processing Files (0 / 1)      :  22%|██▏       | 1.07GB / 4.98GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.07GB / 1.14GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  22%|██▏       | 1.07GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.14GB / 1.14GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
Processing Files (0 / 1)      :  21%|██▏       | 1.07GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.07GB / 1.14GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.21GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.14GB / 1.14GB, 78.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  22%|██▏       | 1.07GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  20%|██        | 1.01GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  22%|██▏       | 1.07GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
Processing Files (0 / 1)      :  21%|██▏       | 1.07GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.07GB / 1.07GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  23%|██▎       | 1.14GB / 4.98GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  23%|██▎       | 1.14GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.21GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  23%|██▎       | 1.14GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.27GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 73.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 73.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  23%|██▎       | 1.14GB / 4.98GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  22%|██▏       | 1.08GB / 5.00GB            
Processing Files (0 / 1)      :  22%|██▏       | 1.08GB / 5.00GB, 73.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.08GB / 1.14GB, 73.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  24%|██▍       | 1.21GB / 4.98GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  24%|██▍       | 1.21GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.27GB / 1.27GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  24%|██▍       | 1.21GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.27GB / 1.27GB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  24%|██▍       | 1.21GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.34GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.27GB / 1.34GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  26%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  26%|██▌       | 1.27GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.27GB / 1.27GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  24%|██▍       | 1.21GB / 4.98GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  26%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  26%|██▌       | 1.27GB / 4.98GB            
Processing Files (0 / 1)      :  26%|██▌       | 1.27GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  26%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  26%|██▌       | 1.27GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  26%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  26%|██▌       | 1.27GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  26%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  26%|██▌       | 1.27GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  24%|██▍       | 1.22GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.3MB/s  
Processing Files (0 / 1)      :  24%|██▍       | 1.22GB / 5.00GB, 67.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.41GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.22GB / 1.27GB, 67.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  26%|██▋       | 1.32GB / 4.98GB            
Processing Files (0 / 1)      :  26%|██▋       | 1.32GB / 4.98GB, 69.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 1.32GB / 1.34GB, 69.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.40GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.40GB / 5.00GB, 74.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 1.40GB / 1.41GB, 74.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  27%|██▋       | 1.34GB / 4.98GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  27%|██▋       | 1.34GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.41GB / 1.41GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  27%|██▋       | 1.34GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  25%|██▌       | 1.27GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▌       | 1.27GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.27GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  28%|██▊       | 1.42GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.42GB / 5.00GB, 66.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.42GB / 1.48GB, 66.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  28%|██▊       | 1.38GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.38GB / 5.00GB, 69.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 1.38GB / 1.41GB, 69.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  27%|██▋       | 1.34GB / 4.98GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 4.98GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.34GB / 1.34GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.47GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  27%|██▋       | 1.34GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  28%|██▊       | 1.41GB / 4.98GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.41GB / 1.41GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  28%|██▊       | 1.41GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  28%|██▊       | 1.41GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  27%|██▋       | 1.34GB / 5.00GB, 65.8MB/s  
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.34GB / 1.41GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.48GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  28%|██▊       | 1.41GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  28%|██▊       | 1.41GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.54GB / 1.54GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  30%|██▉       | 1.48GB / 4.98GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.47GB / 1.54GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  30%|██▉       | 1.48GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  30%|██▉       | 1.48GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.4MB/s  
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.61GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▌| 1.41GB / 1.48GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.54GB / 1.54GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  30%|██▉       | 1.48GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.61GB / 1.61GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  31%|███       | 1.54GB / 4.98GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 4.98GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  31%|███       | 1.54GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.61GB / 1.61GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  31%|███       | 1.54GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.61GB / 1.61GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  31%|███       | 1.54GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  30%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.48GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.48GB / 1.54GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  31%|███       | 1.54GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB, 72.4MB/s  
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.68GB / 1.68GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  32%|███▏      | 1.61GB / 4.98GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.68GB / 1.68GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  32%|███▏      | 1.61GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  32%|███▏      | 1.61GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  32%|███▏      | 1.61GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.3MB/s  
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 65.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  34%|███▎      | 1.68GB / 4.98GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 4.98GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.68GB / 1.68GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.74GB / 1.74GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  34%|███▎      | 1.68GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.74GB / 1.74GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  33%|███▎      | 1.66GB / 5.00GB            
Processing Files (0 / 1)      :  33%|███▎      | 1.66GB / 5.00GB, 71.0MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 1.66GB / 1.68GB, 71.0MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 71.6MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 71.6MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  34%|███▎      | 1.68GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  34%|███▎      | 1.68GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.81GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.68GB / 1.68GB, 72.4MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  34%|███▎      | 1.68GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.81GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  35%|███▌      | 1.74GB / 4.98GB            
Processing Files (0 / 1)      :  35%|███▌      | 1.74GB / 4.98GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.74GB / 1.74GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0004-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.81GB / 1.88GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0006-of-00027.safetensors:  35%|███▍      | 1.75GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.75GB / 5.00GB, 72.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.75GB / 1.81GB, 72.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0023-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.81GB / 1.88GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0011-of-00027.safetensors:  35%|███▌      | 1.74GB / 4.98GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0003-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.81GB / 1.88GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0021-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB, 72.3MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0022-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0015-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.34GB / 1.34GB,  112MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  13%|█▎        |  670MB / 5.00GB            
Processing Files (0 / 1)      :  13%|█▎        |  670MB / 5.00GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  91%|█████████ |  670MB /  738MB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  27%|██▋       | 1.34GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  13%|█▎        |  670MB / 5.00GB            
Processing Files (0 / 1)      :  13%|█▎        |  670MB / 5.00GB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  91%|█████████ |  670MB /  738MB, 65.7MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  29%|██▉       | 1.48GB / 5.00GB            
Processing Files (0 / 1)      :  29%|██▉       | 1.48GB / 5.00GB,  118MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.47GB / 1.48GB,  118MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  15%|█▍        |  737MB / 5.00GB            
Processing Files (0 / 1)      :  15%|█▍        |  737MB / 5.00GB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  92%|█████████▏|  737MB /  805MB, 72.2MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  30%|███       | 1.50GB / 5.00GB            
Processing Files (0 / 1)      :  30%|███       | 1.50GB / 5.00GB,  121MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 1.50GB / 1.54GB,  121MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  16%|█▌        |  804MB / 5.00GB            
Processing Files (0 / 1)      :  16%|█▌        |  804MB / 5.00GB, 78.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  92%|█████████▏|  804MB /  872MB, 78.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB,  125MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB,  125MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  18%|█▊        |  876MB / 5.00GB            
Processing Files (0 / 1)      :  18%|█▊        |  876MB / 5.00GB, 85.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  93%|█████████▎|  875MB /  939MB, 85.8MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB,  131MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB,  131MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  19%|█▉        |  938MB / 5.00GB            
Processing Files (0 / 1)      :  19%|█▉        |  938MB / 5.00GB, 91.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  93%|█████████▎|  937MB / 1.01GB, 91.9MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  20%|██        | 1.00GB / 5.00GB            
Processing Files (0 / 1)      :  20%|██        | 1.00GB / 5.00GB, 98.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.00GB / 1.01GB, 98.5MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.74GB / 1.81GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  21%|██▏       | 1.07GB / 5.00GB            
Processing Files (0 / 1)      :  21%|██▏       | 1.07GB / 5.00GB,  105MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.07GB / 1.14GB,  105MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  36%|███▌      | 1.81GB / 5.00GB            
Processing Files (0 / 1)      :  36%|███▌      | 1.81GB / 5.00GB,  145MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▋| 1.81GB / 1.88GB,  145MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  23%|██▎       | 1.14GB / 5.00GB            
Processing Files (0 / 1)      :  23%|██▎       | 1.14GB / 5.00GB,  112MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  94%|█████████▍| 1.14GB / 1.21GB,  112MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  38%|███▊      | 1.88GB / 5.00GB            
Processing Files (0 / 1)      :  38%|███▊      | 1.88GB / 5.00GB,  151MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 1.88GB / 1.94GB,  151MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  24%|██▍       | 1.21GB / 5.00GB            
Processing Files (0 / 1)      :  24%|██▍       | 1.21GB / 5.00GB,  118MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  95%|█████████▍| 1.21GB / 1.27GB,  118MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  38%|███▊      | 1.88GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  25%|██▍       | 1.25GB / 5.00GB            
Processing Files (0 / 1)      :  25%|██▍       | 1.25GB / 5.00GB,  122MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 1.25GB / 1.27GB,  122MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  39%|███▉      | 1.94GB / 5.00GB            
Processing Files (0 / 1)      :  39%|███▉      | 1.94GB / 5.00GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 1.94GB / 2.01GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  26%|██▌       | 1.31GB / 5.00GB            
Processing Files (0 / 1)      :  26%|██▌       | 1.31GB / 5.00GB,  128MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 1.31GB / 1.34GB,  128MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  40%|████      | 2.01GB / 5.00GB            
Processing Files (0 / 1)      :  40%|████      | 2.01GB / 5.00GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.01GB / 2.08GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
Processing Files (0 / 1)      :  28%|██▊       | 1.41GB / 5.00GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.41GB / 1.41GB,  138MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  42%|████▏     | 2.08GB / 5.00GB            
Processing Files (0 / 1)      :  42%|████▏     | 2.08GB / 5.00GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.08GB / 2.15GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  28%|██▊       | 1.41GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  42%|████▏     | 2.08GB / 5.00GB            
Processing Files (0 / 1)      :  42%|████▏     | 2.08GB / 5.00GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.08GB / 2.15GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  30%|██▉       | 1.47GB / 5.00GB            
Processing Files (0 / 1)      :  30%|██▉       | 1.47GB / 5.00GB,  145MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.47GB / 1.48GB,  145MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  43%|████▎     | 2.15GB / 5.00GB            
Processing Files (0 / 1)      :  43%|████▎     | 2.15GB / 5.00GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.14GB / 2.21GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  31%|███       | 1.54GB / 5.00GB            
Processing Files (0 / 1)      :  31%|███       | 1.54GB / 5.00GB,  151MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.54GB / 1.61GB,  151MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  44%|████▍     | 2.21GB / 5.00GB            
Processing Files (0 / 1)      :  44%|████▍     | 2.21GB / 5.00GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.21GB / 2.28GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  32%|███▏      | 1.61GB / 5.00GB            
Processing Files (0 / 1)      :  32%|███▏      | 1.61GB / 5.00GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.61GB / 1.68GB,  158MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  46%|████▌     | 2.28GB / 5.00GB            
Processing Files (0 / 1)      :  46%|████▌     | 2.28GB / 5.00GB,  177MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.28GB / 2.35GB,  177MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  34%|███▎      | 1.68GB / 5.00GB            
Processing Files (0 / 1)      :  34%|███▎      | 1.68GB / 5.00GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  96%|█████████▌| 1.68GB / 1.74GB,  164MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  46%|████▌     | 2.28GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
Processing Files (0 / 1)      :  35%|███▍      | 1.74GB / 5.00GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.74GB / 1.74GB,  171MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  46%|████▌     | 2.28GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  35%|███▍      | 1.74GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  48%|████▊     | 2.41GB / 5.00GB            
Processing Files (0 / 1)      :  48%|████▊     | 2.41GB / 5.00GB,  190MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.41GB / 2.41GB,  190MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  37%|███▋      | 1.84GB / 5.00GB            
Processing Files (0 / 1)      :  37%|███▋      | 1.84GB / 5.00GB,  180MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 1.84GB / 1.88GB,  180MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  50%|████▉     | 2.48GB / 5.00GB            
Processing Files (0 / 1)      :  50%|████▉     | 2.48GB / 5.00GB,  191MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.48GB / 2.48GB,  191MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  39%|███▉      | 1.94GB / 5.00GB            
Processing Files (0 / 1)      :  39%|███▉      | 1.94GB / 5.00GB,  191MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 1.94GB / 1.94GB,  191MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  50%|████▉     | 2.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  39%|███▉      | 1.94GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  50%|████▉     | 2.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  39%|███▉      | 1.94GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  52%|█████▏    | 2.61GB / 5.00GB            
Processing Files (0 / 1)      :  52%|█████▏    | 2.61GB / 5.00GB,  203MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.61GB / 2.62GB,  203MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  41%|████▏     | 2.07GB / 5.00GB            
Processing Files (0 / 1)      :  41%|████▏     | 2.07GB / 5.00GB,  203MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 2.07GB / 2.08GB,  203MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  54%|█████▎    | 2.68GB / 5.00GB            
Processing Files (0 / 1)      :  54%|█████▎    | 2.68GB / 5.00GB,  204MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.68GB / 2.68GB,  204MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  43%|████▎     | 2.13GB / 5.00GB            
Processing Files (0 / 1)      :  43%|████▎     | 2.13GB / 5.00GB,  209MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 2.13GB / 2.15GB,  209MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  55%|█████▍    | 2.75GB / 5.00GB            
Processing Files (0 / 1)      :  55%|█████▍    | 2.75GB / 5.00GB,  210MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.75GB / 2.75GB,  210MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  43%|████▎     | 2.15GB / 5.00GB            
Processing Files (0 / 1)      :  43%|████▎     | 2.15GB / 5.00GB,  210MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.15GB / 2.21GB,  210MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  55%|█████▍    | 2.75GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  43%|████▎     | 2.15GB / 5.00GB            
Processing Files (0 / 1)      :  43%|████▎     | 2.15GB / 5.00GB,  211MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.15GB / 2.21GB,  211MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  56%|█████▌    | 2.80GB / 5.00GB            
Processing Files (0 / 1)      :  56%|█████▌    | 2.80GB / 5.00GB,  215MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 2.80GB / 2.82GB,  215MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  44%|████▍     | 2.22GB / 5.00GB            
Processing Files (0 / 1)      :  44%|████▍     | 2.22GB / 5.00GB,  218MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.22GB / 2.28GB,  218MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  58%|█████▊    | 2.88GB / 5.00GB            
Processing Files (0 / 1)      :  58%|█████▊    | 2.88GB / 5.00GB,  224MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.88GB / 2.88GB,  223MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  46%|████▌     | 2.28GB / 5.00GB            
Processing Files (0 / 1)      :  46%|████▌     | 2.28GB / 5.00GB,  224MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.28GB / 2.35GB,  223MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  58%|█████▊    | 2.88GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  47%|████▋     | 2.34GB / 5.00GB            
Processing Files (0 / 1)      :  47%|████▋     | 2.34GB / 5.00GB,  229MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.34GB / 2.35GB,  229MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  59%|█████▉    | 2.95GB / 5.00GB            
Processing Files (0 / 1)      :  59%|█████▉    | 2.95GB / 5.00GB,  230MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 2.95GB / 3.02GB,  230MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  47%|████▋     | 2.35GB / 5.00GB            
Processing Files (0 / 1)      :  47%|████▋     | 2.35GB / 5.00GB,  230MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.35GB / 2.41GB,  230MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  60%|██████    | 3.02GB / 5.00GB            
Processing Files (0 / 1)      :  60%|██████    | 3.02GB / 5.00GB,  231MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.02GB / 3.02GB,  231MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  48%|████▊     | 2.41GB / 5.00GB            
Processing Files (0 / 1)      :  48%|████▊     | 2.41GB / 5.00GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.41GB / 2.48GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  62%|██████▏   | 3.08GB / 5.00GB            
Processing Files (0 / 1)      :  62%|██████▏   | 3.08GB / 5.00GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.08GB / 3.08GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  50%|████▉     | 2.48GB / 5.00GB            
Processing Files (0 / 1)      :  50%|████▉     | 2.48GB / 5.00GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.48GB / 2.55GB,  237MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  62%|██████▏   | 3.08GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  50%|████▉     | 2.48GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  63%|██████▎   | 3.15GB / 5.00GB            
Processing Files (0 / 1)      :  63%|██████▎   | 3.15GB / 5.00GB,  243MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.15GB / 3.15GB,  243MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  51%|█████     | 2.55GB / 5.00GB            
Processing Files (0 / 1)      :  51%|█████     | 2.55GB / 5.00GB,  243MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  97%|█████████▋| 2.55GB / 2.62GB,  243MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  64%|██████▍   | 3.20GB / 5.00GB            
Processing Files (0 / 1)      :  64%|██████▍   | 3.20GB / 5.00GB,  248MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 3.19GB / 3.22GB,  248MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  54%|█████▎    | 2.68GB / 5.00GB            
Processing Files (0 / 1)      :  54%|█████▎    | 2.68GB / 5.00GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.68GB / 2.68GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  66%|██████▌   | 3.29GB / 5.00GB            
Processing Files (0 / 1)      :  66%|██████▌   | 3.29GB / 5.00GB,  250MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.29GB / 3.29GB,  250MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  55%|█████▌    | 2.75GB / 5.00GB            
Processing Files (0 / 1)      :  55%|█████▌    | 2.75GB / 5.00GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.75GB / 2.75GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  67%|██████▋   | 3.35GB / 5.00GB            
Processing Files (0 / 1)      :  67%|██████▋   | 3.35GB / 5.00GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.35GB / 3.35GB,  256MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  55%|█████▌    | 2.75GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  67%|██████▋   | 3.35GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  56%|█████▋    | 2.82GB / 5.00GB            
Processing Files (0 / 1)      :  56%|█████▋    | 2.82GB / 5.00GB,  263MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 2.82GB / 2.82GB,  263MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  68%|██████▊   | 3.42GB / 5.00GB            
Processing Files (0 / 1)      :  68%|██████▊   | 3.42GB / 5.00GB,  263MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.42GB / 3.49GB,  263MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  58%|█████▊    | 2.88GB / 5.00GB            
Processing Files (0 / 1)      :  58%|█████▊    | 2.88GB / 5.00GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 2.88GB / 2.95GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  70%|██████▉   | 3.49GB / 5.00GB            
Processing Files (0 / 1)      :  70%|██████▉   | 3.49GB / 5.00GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.49GB / 3.55GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  59%|█████▊    | 2.93GB / 5.00GB            
Processing Files (0 / 1)      :  59%|█████▊    | 2.93GB / 5.00GB,  274MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 2.93GB / 2.95GB,  274MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  71%|███████   | 3.55GB / 5.00GB            
Processing Files (0 / 1)      :  71%|███████   | 3.55GB / 5.00GB,  269MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.55GB / 3.62GB,  269MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  60%|██████    | 3.02GB / 5.00GB            
Processing Files (0 / 1)      :  60%|██████    | 3.02GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.02GB / 3.02GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  72%|███████▏  | 3.62GB / 5.00GB            
Processing Files (0 / 1)      :  72%|███████▏  | 3.62GB / 5.00GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.62GB / 3.69GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  60%|██████    | 3.02GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  72%|███████▏  | 3.62GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  62%|██████▏   | 3.08GB / 5.00GB            
Processing Files (0 / 1)      :  62%|██████▏   | 3.08GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.08GB / 3.08GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  74%|███████▍  | 3.69GB / 5.00GB            
Processing Files (0 / 1)      :  74%|███████▍  | 3.69GB / 5.00GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.69GB / 3.76GB,  270MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  63%|██████▎   | 3.15GB / 5.00GB            
Processing Files (0 / 1)      :  63%|██████▎   | 3.15GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.15GB / 3.15GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  76%|███████▋  | 3.82GB / 5.00GB            
Processing Files (0 / 1)      :  76%|███████▋  | 3.82GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.82GB / 3.82GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  64%|██████▍   | 3.22GB / 5.00GB            
Processing Files (0 / 1)      :  64%|██████▍   | 3.22GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.22GB / 3.29GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  78%|███████▊  | 3.89GB / 5.00GB            
Processing Files (0 / 1)      :  78%|███████▊  | 3.89GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.89GB / 3.89GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  66%|██████▌   | 3.29GB / 5.00GB            
Processing Files (0 / 1)      :  66%|██████▌   | 3.29GB / 5.00GB,  283MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  98%|█████████▊| 3.28GB / 3.35GB,  283MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  78%|███████▊  | 3.89GB / 5.00GB            
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  67%|██████▋   | 3.35GB / 5.00GB            
Processing Files (0 / 1)      :  67%|██████▋   | 3.35GB / 5.00GB,  283MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.35GB / 3.35GB,  283MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  79%|███████▉  | 3.96GB / 5.00GB            
Processing Files (0 / 1)      :  79%|███████▉  | 3.96GB / 5.00GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               : 100%|█████████▉| 3.96GB / 3.96GB,  276MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0019-of-00027.safetensors:  68%|██████▊   | 3.39GB / 5.00GB            
Processing Files (0 / 1)      :  68%|██████▊   | 3.39GB / 5.00GB,  280MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
New Data Upload               :  99%|█████████▉| 3.39GB / 3.42GB,  280MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader: 
  ...0026-of-00027.safetensors:  80%|████████  | 4.02GB / 5.00GB            
Processing Files (0 / 1)      :  80%|████████  | 4.02GB / 5.00GB,  274MB/s  
chaiml-muster-v2-q235b-77862-v1-uploader:                              Processed model ChaiML/muster-v2-q235b-lr1e4ep2r64g4 in 4832.031s
chaiml-muster-v2-q235b-77862-v1-uploader: creating bucket guanaco-vllm-models
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:56: SyntaxWarning: invalid escape sequence '\.'
chaiml-muster-v2-q235b-77862-v1-uploader:   RE_S3_DATESTRING = re.compile('\.[0-9]*(?:[Z\\-\\+]*?)')
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/BaseUtils.py:57: SyntaxWarning: invalid escape sequence '\s'
chaiml-muster-v2-q235b-77862-v1-uploader:   RE_XML_NAMESPACE = re.compile(b'^(<?[^>]+?>\s*|\s*)(<\w+) xmlns=[\'"](https?://[^\'"]+)[\'"]', re.MULTILINE)
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:240: SyntaxWarning: invalid escape sequence '\.'
chaiml-muster-v2-q235b-77862-v1-uploader:   invalid = re.search("([^a-z0-9\.-])", bucket, re.UNICODE)
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:244: SyntaxWarning: invalid escape sequence '\.'
chaiml-muster-v2-q235b-77862-v1-uploader:   invalid = re.search("([^A-Za-z0-9\._-])", bucket, re.UNICODE)
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:255: SyntaxWarning: invalid escape sequence '\.'
chaiml-muster-v2-q235b-77862-v1-uploader:   if re.search("-\.", bucket, re.UNICODE):
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/Utils.py:257: SyntaxWarning: invalid escape sequence '\.'
chaiml-muster-v2-q235b-77862-v1-uploader:   if re.search("\.\.", bucket, re.UNICODE):
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/S3Uri.py:155: SyntaxWarning: invalid escape sequence '\w'
chaiml-muster-v2-q235b-77862-v1-uploader:   _re = re.compile("^(\w+://)?(.*)", re.UNICODE)
chaiml-muster-v2-q235b-77862-v1-uploader: /usr/lib/python3/dist-packages/S3/FileLists.py:480: SyntaxWarning: invalid escape sequence '\*'
chaiml-muster-v2-q235b-77862-v1-uploader:   wildcard_split_result = re.split("\*|\?", uri_str, maxsplit=1)
chaiml-muster-v2-q235b-77862-v1-uploader: Bucket 's3://guanaco-vllm-models/' created
chaiml-muster-v2-q235b-77862-v1-uploader: uploading /dev/shm/model_output to s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/added_tokens.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/added_tokens.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/chat_template.jinja s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/chat_template.jinja
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/tokenizer_config.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/tokenizer_config.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/generation_config.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/generation_config.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/config.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/config.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/quantization_config.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/quantization_config.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/special_tokens_map.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/special_tokens_map.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/merges.txt s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/merges.txt
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/vocab.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/vocab.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/tokenizer.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/tokenizer.json
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model.safetensors.index.json s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model.safetensors.index.json
HTTP Request: %s %s "%s %d %s"
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00027-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00027-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00022-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00022-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00014-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00014-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00005-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00005-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00024-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00024-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00025-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00025-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00004-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00004-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00015-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00015-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00019-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00019-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00026-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00026-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00006-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00006-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00018-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00018-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00010-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00010-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00002-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00002-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00021-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00021-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00008-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00008-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00020-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00020-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00013-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00013-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00001-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00001-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00023-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00023-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00016-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00016-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00009-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00009-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00012-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00012-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00003-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00003-of-00027.safetensors
chaiml-muster-v2-q235b-77862-v1-uploader: cp /dev/shm/model_output/model-00007-of-00027.safetensors s3://guanaco-vllm-models/chaiml-muster-v2-q235b-77862-v1/model-00007-of-00027.safetensors
Job chaiml-muster-v2-q235b-77862-v1-uploader completed after 5104.55s with status: succeeded
Stopping job with name chaiml-muster-v2-q235b-77862-v1-uploader
Pipeline stage VLLMUploader completed in 5105.53s
run pipeline stage %s
Running pipeline stage VLLMTemplater
Pipeline stage VLLMTemplater completed in 0.51s
run pipeline stage %s
Running pipeline stage VLLMDeployer
Creating inference service chaiml-muster-v2-q235b-77862-v1
Waiting for inference service chaiml-muster-v2-q235b-77862-v1 to be ready
Unable to record family friendly update due to error: Invalid JSON input: Expecting value: line 1 column 1 (char 0)
Inference service chaiml-muster-v2-q235b-77862-v1 ready after 580.5534174442291s
Pipeline stage VLLMDeployer completed in 582.21s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.352090358734131s
Received healthy response to inference request in 2.0871784687042236s
Received healthy response to inference request in 2.280965805053711s
Received healthy response to inference request in 2.7001595497131348s
Received healthy response to inference request in 2.2432374954223633s
Received healthy response to inference request in 2.1904101371765137s
Received healthy response to inference request in 2.2657320499420166s
Received healthy response to inference request in 2.137221574783325s
Received healthy response to inference request in 2.2956976890563965s
Received healthy response to inference request in 2.3165533542633057s
Received healthy response to inference request in 2.1064796447753906s
Received healthy response to inference request in 2.278088092803955s
Received healthy response to inference request in 2.2419915199279785s
Received healthy response to inference request in 2.5875322818756104s
Received healthy response to inference request in 2.6672234535217285s
Received healthy response to inference request in 2.458538770675659s
Received healthy response to inference request in 2.064523458480835s
Received healthy response to inference request in 2.411168336868286s
Received healthy response to inference request in 2.2840468883514404s
Received healthy response to inference request in 2.314743995666504s
Received healthy response to inference request in 2.1915042400360107s
Received healthy response to inference request in 2.2819573879241943s
Received healthy response to inference request in 2.031850576400757s
Received healthy response to inference request in 2.104580879211426s
Received healthy response to inference request in 2.3401825428009033s
Received healthy response to inference request in 2.0855631828308105s
Received healthy response to inference request in 2.325845718383789s
Received healthy response to inference request in 2.260740041732788s
Received healthy response to inference request in 2.999593734741211s
Received healthy response to inference request in 1.9958908557891846s
30 requests
0 failed requests
5th percentile: 2.046553373336792
10th percentile: 2.083459210395813
20th percentile: 2.1060998916625975
30th percentile: 2.191176009178162
40th percentile: 2.253739023208618
50th percentile: 2.279526948928833
60th percentile: 2.288707208633423
70th percentile: 2.3193410634994507
80th percentile: 2.363905954360962
90th percentile: 2.5955013990402223
95th percentile: 2.6853383064270018
99th percentile: 2.912757821083069
mean time: 2.296709736188253
Pipeline stage StressChecker completed in 88.30s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.52s
Shutdown handler de-registered
chaiml-muster-v2-q235b-_77862_v1 status is now deployed due to DeploymentManager action
chaiml-muster-v2-q235b-_77862_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-muster-v2-q235b-_77862_v1 status is now torndown due to DeploymentManager action