zonemercy-vingt-deux-gfv_4513

submission_id: zonemercy-vingt-deux-gfv_4513_v1
developer_uid: zonemercy
best_of: 8
celo_rating: 1228.62
display_name: temp-5
family_friendly_score: 0.5990033222591362
family_friendly_standard_error: 0.00891911471563191
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-gfv1v2ep2-bak
latencies: [{'batch_size': 1, 'throughput': 0.3812372596855335, 'latency_mean': 2.6229410469532013, 'latency_p50': 2.617831826210022, 'latency_p90': 2.923531723022461}, {'batch_size': 2, 'throughput': 0.5952712745566366, 'latency_mean': 3.356254712343216, 'latency_p50': 3.3835630416870117, 'latency_p90': 3.673544502258301}, {'batch_size': 3, 'throughput': 0.7507315744059958, 'latency_mean': 3.982591390609741, 'latency_p50': 4.00880241394043, 'latency_p90': 4.392302513122559}, {'batch_size': 4, 'throughput': 0.8693962317460285, 'latency_mean': 4.575014321804047, 'latency_p50': 4.588945627212524, 'latency_p90': 5.164961886405945}, {'batch_size': 5, 'throughput': 0.9684800386907672, 'latency_mean': 5.141881135702133, 'latency_p50': 5.133690595626831, 'latency_p90': 5.83477520942688}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-gfv
model_name: temp-5
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-gfv1v2ep2-bak
model_size: 22B
num_battles: 3114
num_wins: 1488
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.69
timestamp: 2024-09-26T17:19:31+00:00
us_pacific_date: 2024-09-26
win_ratio: 0.47784200385356457
Download Preference Data
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name zonemercy-vingt-deux-gfv-4513-v1-mkmlizer
Waiting for job on zonemercy-vingt-deux-gfv-4513-v1-mkmlizer to finish
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Downloaded to shared memory in 47.965s
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpdcubjc6b, device:0
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:17, 28.25it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:11, 43.13it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.59it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.23it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:11, 40.39it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 32.76it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 39.35it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.51it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 33.98it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:18, 23.91it/s]
Loading 0:  11%|█         | 56/507 [00:01<00:19, 22.90it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:14, 30.22it/s]
Loading 0:  13%|█▎        | 67/507 [00:02<00:14, 30.90it/s]
Loading 0:  14%|█▍        | 72/507 [00:02<00:12, 34.90it/s]
Loading 0:  15%|█▌        | 78/507 [00:02<00:10, 39.10it/s]
Loading 0:  16%|█▋        | 83/507 [00:02<00:11, 36.58it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:11, 36.36it/s]
Loading 0:  18%|█▊        | 91/507 [00:02<00:11, 35.49it/s]
Loading 0:  19%|█▉        | 96/507 [00:02<00:11, 37.33it/s]
Loading 0:  20%|█▉        | 100/507 [00:02<00:11, 34.52it/s]
Loading 0:  21%|██        | 105/507 [00:03<00:10, 36.95it/s]
Loading 0:  21%|██▏       | 109/507 [00:03<00:11, 35.93it/s]
Loading 0:  22%|██▏       | 113/507 [00:03<00:16, 24.43it/s]
Loading 0:  23%|██▎       | 116/507 [00:03<00:16, 23.25it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 27.25it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.00it/s]
Loading 0:  26%|██▌       | 133/507 [00:04<00:11, 33.72it/s]
Loading 0:  27%|██▋       | 138/507 [00:04<00:10, 36.28it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.42it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.09it/s]
Loading 0:  30%|██▉       | 151/507 [00:04<00:09, 35.83it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.44it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 36.87it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.36it/s]
Loading 0:  33%|███▎      | 169/507 [00:05<00:12, 27.46it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.19it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.96it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.70it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.58it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.78it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 36.42it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 37.38it/s]
Loading 0:  40%|████      | 205/507 [00:06<00:08, 36.96it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 39.94it/s]
Loading 0:  42%|████▏     | 215/507 [00:06<00:07, 40.28it/s]
Loading 0:  43%|████▎     | 220/507 [00:06<00:08, 35.15it/s]
Loading 0:  44%|████▍     | 224/507 [00:06<00:10, 26.39it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 27.64it/s]
Loading 0:  47%|████▋     | 237/507 [00:07<00:07, 33.93it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:07, 33.76it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 36.16it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 35.56it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.36it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.17it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.59it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 37.12it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 39.19it/s]
Loading 0:  55%|█████▍    | 277/507 [00:08<00:06, 36.68it/s]
Loading 0:  56%|█████▌    | 283/507 [00:08<00:06, 36.81it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:09, 24.24it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.77it/s]
Loading 0:  59%|█████▉    | 299/507 [00:23<00:07, 27.77it/s]
Loading 0:  59%|█████▉    | 300/507 [00:23<02:42,  1.27it/s]
Loading 0:  60%|█████▉    | 302/507 [00:23<02:21,  1.45it/s]
Loading 0:  61%|██████    | 307/507 [00:23<01:35,  2.09it/s]
Loading 0:  61%|██████    | 310/507 [00:23<01:16,  2.58it/s]
Loading 0:  62%|██████▏   | 313/507 [00:23<00:58,  3.29it/s]
Loading 0:  63%|██████▎   | 318/507 [00:23<00:38,  4.93it/s]
Loading 0:  64%|██████▎   | 322/507 [00:23<00:28,  6.56it/s]
Loading 0:  64%|██████▍   | 327/507 [00:23<00:19,  9.30it/s]
Loading 0:  65%|██████▌   | 331/507 [00:24<00:15, 11.67it/s]
Loading 0:  66%|██████▌   | 335/507 [00:24<00:11, 14.57it/s]
Loading 0:  67%|██████▋   | 340/507 [00:24<00:10, 15.96it/s]
Loading 0:  68%|██████▊   | 344/507 [00:24<00:08, 18.78it/s]
Loading 0:  69%|██████▊   | 348/507 [00:24<00:07, 20.68it/s]
Loading 0:  70%|██████▉   | 354/507 [00:24<00:05, 26.96it/s]
Loading 0:  71%|███████   | 358/507 [00:24<00:05, 28.46it/s]
Loading 0:  72%|███████▏  | 363/507 [00:25<00:04, 32.38it/s]
Loading 0:  72%|███████▏  | 367/507 [00:25<00:04, 32.31it/s]
Loading 0:  73%|███████▎  | 372/507 [00:25<00:03, 34.34it/s]
Loading 0:  74%|███████▍  | 376/507 [00:25<00:03, 34.82it/s]
Loading 0:  75%|███████▌  | 381/507 [00:25<00:03, 38.18it/s]
Loading 0:  76%|███████▌  | 386/507 [00:25<00:03, 39.07it/s]
Loading 0:  77%|███████▋  | 391/507 [00:25<00:03, 34.52it/s]
Loading 0:  78%|███████▊  | 395/507 [00:26<00:04, 26.47it/s]
Loading 0:  79%|███████▉  | 401/507 [00:26<00:03, 28.93it/s]
Loading 0:  80%|████████  | 408/507 [00:26<00:02, 35.24it/s]
Loading 0:  81%|████████▏ | 412/507 [00:26<00:02, 34.20it/s]
Loading 0:  82%|████████▏ | 417/507 [00:26<00:02, 36.60it/s]
Loading 0:  83%|████████▎ | 421/507 [00:26<00:02, 35.83it/s]
Loading 0:  84%|████████▍ | 426/507 [00:26<00:02, 38.69it/s]
Loading 0:  85%|████████▌ | 431/507 [00:26<00:01, 38.46it/s]
Loading 0:  86%|████████▌ | 436/507 [00:27<00:01, 39.23it/s]
Loading 0:  87%|████████▋ | 440/507 [00:27<00:01, 39.21it/s]
Loading 0:  88%|████████▊ | 445/507 [00:27<00:01, 39.86it/s]
Loading 0:  89%|████████▉ | 450/507 [00:27<00:01, 42.16it/s]
Loading 0:  90%|████████▉ | 455/507 [00:29<00:08,  6.39it/s]
Loading 0:  91%|█████████ | 459/507 [00:29<00:05,  8.01it/s]
Loading 0:  92%|█████████▏| 465/507 [00:30<00:03, 11.17it/s]
Loading 0:  93%|█████████▎| 472/507 [00:30<00:02, 15.89it/s]
Loading 0:  94%|█████████▍| 476/507 [00:30<00:01, 18.20it/s]
Loading 0:  95%|█████████▍| 481/507 [00:30<00:01, 22.13it/s]
Loading 0:  96%|█████████▌| 486/507 [00:30<00:00, 25.32it/s]
Loading 0:  97%|█████████▋| 490/507 [00:30<00:00, 27.23it/s]
Loading 0:  97%|█████████▋| 494/507 [00:30<00:00, 27.98it/s]
Loading 0:  98%|█████████▊| 499/507 [00:30<00:00, 31.38it/s]
Loading 0:  99%|█████████▉| 503/507 [00:30<00:00, 32.20it/s]
                                                            
Traceback (most recent call last):
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 151, in <module>
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     cli()
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return self.main(*args, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     rv = self.invoke(ctx)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return _process_result(sub_ctx.command.invoke(sub_ctx))
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return ctx.invoke(self.callback, **ctx.params)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return __callback(*args, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 42, in quantize
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     quantize_model(temp_folder, output_path, profile, device)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 135, in quantize_model
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     flywheel.instrument(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/mk1/flywheel/instrument.py", line 96, in instrument
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     tokenizer = AutoTokenizer.from_pretrained(input_model_path, verbose=False)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 897, in from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2271, in from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return cls._from_pretrained(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2505, in _from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     tokenizer = cls(*init_inputs, **init_kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 157, in __init__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     super().__init__(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 115, in __init__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Exception: data did not match any variant of untagged enum ModelWrapper at line 275732 column 3
Job zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer completed after 117.42s with status: failed
Stopping job with name zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer
%s, retrying in %s seconds...
Starting job with name zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer
Waiting for job on zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer to finish
Inference service nousresearch-hermes-2-pr-1418-v5 ready after 350.7747962474823s
Pipeline stage MKMLDeployer completed in 351.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.4446451663970947s
Received healthy response to inference request in 0.8907690048217773s
Received healthy response to inference request in 0.8413486480712891s
Received healthy response to inference request in 1.2591774463653564s
Received healthy response to inference request in 0.9848537445068359s
5 requests
0 failed requests
5th percentile: 0.8512327194213867
10th percentile: 0.8611167907714844
20th percentile: 0.8808849334716797
30th percentile: 0.9095859527587891
40th percentile: 0.9472198486328125
50th percentile: 0.9848537445068359
60th percentile: 1.094583225250244
70th percentile: 1.2043127059936523
80th percentile: 1.2962709903717042
90th percentile: 1.3704580783843994
95th percentile: 1.407551622390747
99th percentile: 1.4372264575958251
mean time: 1.0841588020324706
Pipeline stage StressChecker completed in 8.34s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.30s
Shutdown handler de-registered
nousresearch-hermes-2-pr_1418_v5 status is now deployed due to DeploymentManager action
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  Version: 0.11.12                                                   ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: Downloaded to shared memory in 115.380s
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8fhb1boi, device:0
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Downloaded to shared memory in 49.159s
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjzl25wkf, device:0
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: quantized model in 65.821s
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: Processed model zonemercy/Vingt-Deux-gfv1v2ep2-bak in 181.202s
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1/config.json
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1/special_tokens_map.json
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1/tokenizer_config.json
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1/tokenizer.json
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:19, 25.60it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:12, 40.91it/s]
Loading 0:   3%|▎         | 17/507 [00:00<00:12, 39.69it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:12, 39.48it/s]
Loading 0:   5%|▌         | 27/507 [00:00<00:12, 39.39it/s]
Loading 0:   6%|▋         | 32/507 [00:00<00:14, 32.34it/s]
Loading 0:   8%|▊         | 39/507 [00:01<00:11, 39.40it/s]
Loading 0:   9%|▊         | 44/507 [00:01<00:11, 39.67it/s]
Loading 0:  10%|▉         | 49/507 [00:01<00:13, 35.01it/s]
Loading 0:  10%|█         | 53/507 [00:01<00:17, 26.61it/s]
Loading 0:  11%|█         | 57/507 [00:01<00:16, 26.88it/s]
Loading 0:  12%|█▏        | 63/507 [00:01<00:13, 32.06it/s]
Loading 0:  13%|█▎        | 67/507 [00:01<00:13, 32.27it/s]
Loading 0:  14%|█▍        | 71/507 [00:02<00:12, 33.74it/s]
Loading 0:  15%|█▌        | 77/507 [00:02<00:10, 40.13it/s]
Loading 0:  16%|█▌        | 82/507 [00:02<00:11, 37.97it/s]
Loading 0:  17%|█▋        | 87/507 [00:02<00:10, 39.44it/s]
Loading 0:  18%|█▊        | 92/507 [00:02<00:10, 38.88it/s]
Loading 0:  19%|█▉        | 97/507 [00:02<00:10, 38.33it/s]
Loading 0:  20%|█▉        | 101/507 [00:02<00:10, 37.50it/s]
Loading 0:  21%|██        | 106/507 [00:02<00:10, 38.08it/s]
Loading 0:  22%|██▏       | 110/507 [00:03<00:10, 37.69it/s]
Loading 0:  22%|██▏       | 114/507 [00:03<00:14, 26.54it/s]
Loading 0:  23%|██▎       | 118/507 [00:03<00:14, 27.16it/s]
Loading 0:  24%|██▍       | 122/507 [00:03<00:14, 26.60it/s]
Loading 0:  25%|██▌       | 129/507 [00:03<00:11, 34.17it/s]
Loading 0:  26%|██▌       | 133/507 [00:03<00:10, 34.13it/s]
Loading 0:  27%|██▋       | 138/507 [00:03<00:09, 37.10it/s]
Loading 0:  28%|██▊       | 142/507 [00:04<00:10, 35.98it/s]
Loading 0:  29%|██▉       | 147/507 [00:04<00:09, 38.83it/s]
Loading 0:  30%|██▉       | 152/507 [00:04<00:09, 38.63it/s]
Loading 0:  31%|███       | 156/507 [00:04<00:09, 38.14it/s]
Loading 0:  32%|███▏      | 160/507 [00:04<00:09, 37.14it/s]
Loading 0:  32%|███▏      | 164/507 [00:04<00:09, 36.94it/s]
Loading 0:  33%|███▎      | 169/507 [00:04<00:11, 28.31it/s]
Loading 0:  34%|███▍      | 173/507 [00:05<00:11, 29.65it/s]
Loading 0:  35%|███▍      | 177/507 [00:05<00:11, 28.94it/s]
Loading 0:  36%|███▌      | 183/507 [00:05<00:09, 34.46it/s]
Loading 0:  37%|███▋      | 187/507 [00:05<00:09, 34.37it/s]
Loading 0:  38%|███▊      | 192/507 [00:05<00:08, 37.02it/s]
Loading 0:  39%|███▊      | 196/507 [00:05<00:08, 34.99it/s]
Loading 0:  40%|███▉      | 201/507 [00:05<00:08, 37.50it/s]
Loading 0:  40%|████      | 205/507 [00:05<00:08, 36.48it/s]
Loading 0:  41%|████▏     | 210/507 [00:06<00:07, 39.20it/s]
Loading 0:  42%|████▏     | 214/507 [00:06<00:07, 37.86it/s]
Loading 0:  43%|████▎     | 218/507 [00:06<00:07, 37.43it/s]
Loading 0:  44%|████▍     | 222/507 [00:06<00:07, 36.39it/s]
Loading 0:  45%|████▍     | 226/507 [00:06<00:10, 25.90it/s]
Loading 0:  45%|████▌     | 230/507 [00:06<00:10, 26.26it/s]
Loading 0:  47%|████▋     | 237/507 [00:06<00:08, 33.64it/s]
Loading 0:  48%|████▊     | 241/507 [00:07<00:08, 33.20it/s]
Loading 0:  49%|████▊     | 246/507 [00:07<00:07, 35.50it/s]
Loading 0:  49%|████▉     | 250/507 [00:07<00:07, 34.91it/s]
Loading 0:  50%|█████     | 255/507 [00:07<00:06, 37.19it/s]
Loading 0:  51%|█████     | 259/507 [00:07<00:06, 36.36it/s]
Loading 0:  52%|█████▏    | 264/507 [00:07<00:06, 38.30it/s]
Loading 0:  53%|█████▎    | 268/507 [00:07<00:06, 36.98it/s]
Loading 0:  54%|█████▍    | 273/507 [00:07<00:05, 39.24it/s]
Loading 0:  55%|█████▍    | 277/507 [00:07<00:06, 37.76it/s]
Loading 0:  56%|█████▌    | 282/507 [00:08<00:05, 40.86it/s]
Loading 0:  57%|█████▋    | 287/507 [00:08<00:08, 24.77it/s]
Loading 0:  58%|█████▊    | 293/507 [00:08<00:07, 27.83it/s]
Loading 0:  59%|█████▉    | 299/507 [00:24<00:07, 27.83it/s]
Loading 0:  59%|█████▉    | 300/507 [00:24<02:53,  1.19it/s]
Loading 0:  60%|█████▉    | 302/507 [00:24<02:31,  1.35it/s]
Loading 0:  61%|██████    | 307/507 [00:24<01:42,  1.95it/s]
Loading 0:  61%|██████    | 310/507 [00:24<01:21,  2.42it/s]
Loading 0:  62%|██████▏   | 314/507 [00:24<00:58,  3.32it/s]
Loading 0:  63%|██████▎   | 319/507 [00:24<00:38,  4.83it/s]
Loading 0:  64%|██████▎   | 323/507 [00:24<00:28,  6.39it/s]
Loading 0:  64%|██████▍   | 327/507 [00:24<00:21,  8.41it/s]
Loading 0:  65%|██████▌   | 331/507 [00:25<00:16, 10.75it/s]
Loading 0:  66%|██████▌   | 335/507 [00:25<00:12, 13.57it/s]
Loading 0:  67%|██████▋   | 340/507 [00:25<00:10, 15.34it/s]
Loading 0:  68%|██████▊   | 344/507 [00:25<00:08, 18.21it/s]
Loading 0:  69%|██████▊   | 348/507 [00:25<00:07, 20.04it/s]
Loading 0:  70%|██████▉   | 354/507 [00:25<00:05, 26.08it/s]
Loading 0:  71%|███████   | 358/507 [00:25<00:05, 27.18it/s]
Loading 0:  72%|███████▏  | 363/507 [00:26<00:04, 31.03it/s]
Loading 0:  72%|███████▏  | 367/507 [00:26<00:04, 31.54it/s]
Loading 0:  73%|███████▎  | 372/507 [00:26<00:03, 35.33it/s]
Loading 0:  74%|███████▍  | 376/507 [00:26<00:03, 35.55it/s]
Loading 0:  75%|███████▌  | 381/507 [00:26<00:03, 38.90it/s]
Loading 0:  76%|███████▌  | 386/507 [00:26<00:03, 39.64it/s]
Loading 0:  77%|███████▋  | 391/507 [00:26<00:03, 34.08it/s]
Loading 0:  78%|███████▊  | 395/507 [00:27<00:04, 26.72it/s]
Loading 0:  79%|███████▉  | 401/507 [00:27<00:03, 28.83it/s]
Loading 0:  80%|████████  | 408/507 [00:27<00:02, 35.16it/s]
Loading 0:  81%|████████▏ | 412/507 [00:27<00:02, 34.32it/s]
Loading 0:  82%|████████▏ | 417/507 [00:27<00:02, 36.63it/s]
Loading 0:  83%|████████▎ | 421/507 [00:27<00:02, 35.68it/s]
Loading 0:  84%|████████▍ | 426/507 [00:27<00:02, 38.23it/s]
Loading 0:  85%|████████▍ | 430/507 [00:27<00:02, 37.08it/s]
Loading 0:  86%|████████▌ | 435/507 [00:28<00:01, 39.61it/s]
Loading 0:  87%|████████▋ | 440/507 [00:28<00:01, 40.02it/s]
Loading 0:  88%|████████▊ | 445/507 [00:28<00:01, 40.01it/s]
Loading 0:  89%|████████▉ | 450/507 [00:28<00:01, 41.92it/s]
Loading 0:  90%|████████▉ | 455/507 [00:30<00:08,  6.18it/s]
Loading 0:  91%|█████████ | 459/507 [00:30<00:06,  7.74it/s]
Loading 0:  92%|█████████▏| 465/507 [00:31<00:03, 10.81it/s]
Loading 0:  93%|█████████▎| 472/507 [00:31<00:02, 15.46it/s]
Loading 0:  94%|█████████▍| 476/507 [00:31<00:01, 17.69it/s]
Loading 0:  95%|█████████▍| 481/507 [00:31<00:01, 21.48it/s]
Loading 0:  96%|█████████▌| 485/507 [00:31<00:00, 23.66it/s]
Loading 0:  97%|█████████▋| 490/507 [00:31<00:00, 27.47it/s]
Loading 0:  97%|█████████▋| 494/507 [00:31<00:00, 28.78it/s]
Loading 0:  98%|█████████▊| 499/507 [00:31<00:00, 32.17it/s]
Loading 0:  99%|█████████▉| 503/507 [00:32<00:00, 32.80it/s]
                                                            
Traceback (most recent call last):
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 151, in <module>
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     cli()
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1157, in __call__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return self.main(*args, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1078, in main
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     rv = self.invoke(ctx)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1688, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return _process_result(sub_ctx.command.invoke(sub_ctx))
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 1434, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return ctx.invoke(self.callback, **ctx.params)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/click/core.py", line 783, in invoke
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return __callback(*args, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 42, in quantize
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     quantize_model(temp_folder, output_path, profile, device)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/code/uploading/mkmlize.py", line 135, in quantize_model
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     flywheel.instrument(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/mk1/flywheel/instrument.py", line 96, in instrument
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     tokenizer = AutoTokenizer.from_pretrained(input_model_path, verbose=False)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 897, in from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2271, in from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     return cls._from_pretrained(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2505, in _from_pretrained
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     tokenizer = cls(*init_inputs, **init_kwargs)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 157, in __init__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     super().__init__(
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:   File "/opt/conda/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 115, in __init__
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer:     fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer: Exception: data did not match any variant of untagged enum ModelWrapper at line 275732 column 3
Job zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer completed after 146.93s with status: failed
Stopping job with name zonemercy-vingt-deux-v5-1e5v0-v5-mkmlizer
clean up pipeline due to error=%s
Shutdown handler de-registered
MKMLizerError('')
zonemercy-vingt-deux-v5-1e5v0_v5 status is now failed due to DeploymentManager action
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-4513-v1/flywheel_model.0.safetensors
zonemercy-vingt-deux-gfv-4513-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/507 [00:00<00:14, 34.86it/s]
Loading 0:   2%|▏         | 8/507 [00:00<00:18, 26.80it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:19, 25.37it/s]
Loading 0:   3%|▎         | 15/507 [00:00<00:23, 20.53it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:20, 23.54it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:17, 26.90it/s]
Loading 0:   5%|▌         | 26/507 [00:01<00:26, 17.86it/s]
Loading 0:   6%|▌         | 29/507 [00:01<00:24, 19.13it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:28, 16.60it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:21, 21.78it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:20, 22.76it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:20, 22.48it/s]
Loading 0:   9%|▉         | 46/507 [00:02<00:19, 23.35it/s]
Loading 0:  10%|▉         | 50/507 [00:02<00:17, 26.54it/s]
Loading 0:  10%|█         | 53/507 [00:02<00:25, 17.85it/s]
Loading 0:  11%|█         | 56/507 [00:02<00:24, 18.73it/s]
Loading 0:  12%|█▏        | 59/507 [00:02<00:28, 15.57it/s]
Loading 0:  13%|█▎        | 64/507 [00:03<00:21, 20.34it/s]
Loading 0:  13%|█▎        | 67/507 [00:03<00:21, 20.80it/s]
Loading 0:  14%|█▍        | 70/507 [00:03<00:20, 20.97it/s]
Loading 0:  14%|█▍        | 73/507 [00:03<00:19, 22.14it/s]
Loading 0:  15%|█▌        | 77/507 [00:03<00:17, 24.97it/s]
Loading 0:  16%|█▌        | 80/507 [00:03<00:26, 16.28it/s]
Loading 0:  16%|█▋        | 83/507 [00:04<00:26, 16.03it/s]
Loading 0:  17%|█▋        | 87/507 [00:04<00:21, 19.54it/s]
Loading 0:  18%|█▊        | 91/507 [00:04<00:18, 22.81it/s]
Loading 0:  19%|█▊        | 94/507 [00:04<00:18, 21.91it/s]
Loading 0:  19%|█▉        | 97/507 [00:04<00:18, 22.40it/s]
Loading 0:  20%|█▉        | 100/507 [00:04<00:22, 18.26it/s]
Loading 0:  21%|██        | 105/507 [00:05<00:17, 23.26it/s]
Loading 0:  21%|██▏       | 108/507 [00:05<00:26, 15.32it/s]
Loading 0:  22%|██▏       | 112/507 [00:05<00:21, 18.48it/s]
Loading 0:  23%|██▎       | 115/507 [00:05<00:20, 19.13it/s]
Loading 0:  23%|██▎       | 118/507 [00:05<00:18, 20.85it/s]
Loading 0:  24%|██▍       | 121/507 [00:05<00:17, 21.50it/s]
Loading 0:  24%|██▍       | 124/507 [00:06<00:17, 21.62it/s]
Loading 0:  25%|██▌       | 127/507 [00:06<00:16, 22.86it/s]
Loading 0:  26%|██▌       | 131/507 [00:06<00:14, 26.19it/s]
Loading 0:  26%|██▋       | 134/507 [00:06<00:20, 17.78it/s]
Loading 0:  27%|██▋       | 137/507 [00:06<00:19, 19.47it/s]
Loading 0:  28%|██▊       | 140/507 [00:06<00:21, 17.03it/s]
Loading 0:  29%|██▊       | 145/507 [00:07<00:16, 22.61it/s]
Loading 0:  29%|██▉       | 148/507 [00:07<00:15, 23.53it/s]
Loading 0:  30%|██▉       | 151/507 [00:07<00:14, 23.74it/s]
Loading 0:  30%|███       | 154/507 [00:07<00:14, 25.04it/s]
Loading 0:  31%|███       | 158/507 [00:07<00:12, 28.01it/s]
Loading 0:  32%|███▏      | 161/507 [00:07<00:17, 19.26it/s]
Loading 0:  32%|███▏      | 164/507 [00:07<00:16, 20.74it/s]
Loading 0:  33%|███▎      | 167/507 [00:08<00:19, 17.67it/s]
Loading 0:  34%|███▍      | 172/507 [00:08<00:14, 23.24it/s]
Loading 0:  35%|███▍      | 175/507 [00:08<00:14, 23.70it/s]
Loading 0:  35%|███▌      | 178/507 [00:08<00:13, 23.60it/s]
Loading 0:  36%|███▌      | 181/507 [00:08<00:13, 24.81it/s]
Loading 0:  36%|███▋      | 185/507 [00:08<00:11, 27.96it/s]
Loading 0:  37%|███▋      | 188/507 [00:08<00:16, 19.41it/s]
Loading 0:  38%|███▊      | 191/507 [00:09<00:15, 20.98it/s]
Loading 0:  38%|███▊      | 194/507 [00:09<00:17, 18.12it/s]
Loading 0:  39%|███▉      | 199/507 [00:09<00:12, 23.80it/s]
Loading 0:  40%|███▉      | 202/507 [00:09<00:12, 24.60it/s]
Loading 0:  40%|████      | 205/507 [00:09<00:13, 23.19it/s]
Loading 0:  41%|████      | 208/507 [00:09<00:12, 23.66it/s]
Loading 0:  42%|████▏     | 211/507 [00:09<00:12, 24.18it/s]
Loading 0:  42%|████▏     | 214/507 [00:10<00:15, 18.32it/s]
Loading 0:  43%|████▎     | 217/507 [00:10<00:17, 16.94it/s]
Loading 0:  43%|████▎     | 220/507 [00:10<00:16, 17.65it/s]
Loading 0:  44%|████▍     | 222/507 [00:10<00:16, 16.99it/s]
Loading 0:  45%|████▍     | 226/507 [00:10<00:13, 20.42it/s]
Loading 0:  45%|████▌     | 229/507 [00:10<00:13, 20.10it/s]
Loading 0:  46%|████▌     | 232/507 [00:11<00:13, 20.34it/s]
Loading 0:  46%|████▋     | 235/507 [00:11<00:12, 21.61it/s]
Loading 0:  47%|████▋     | 238/507 [00:11<00:11, 22.85it/s]
Loading 0:  48%|████▊     | 241/507 [00:11<00:16, 16.44it/s]
Loading 0:  48%|████▊     | 243/507 [00:11<00:18, 14.23it/s]
Loading 0:  49%|████▊     | 247/507 [00:12<00:14, 17.35it/s]
Loading 0:  49%|████▉     | 249/507 [00:12<00:15, 16.68it/s]
Loading 0:  50%|████▉     | 253/507 [00:12<00:12, 20.21it/s]
Loading 0:  50%|█████     | 256/507 [00:12<00:12, 20.04it/s]
Loading 0:  51%|█████     | 259/507 [00:12<00:12, 20.26it/s]
Loading 0:  52%|█████▏    | 262/507 [00:12<00:11, 21.58it/s]
Loading 0:  52%|█████▏    | 265/507 [00:12<00:10, 22.78it/s]
Loading 0:  53%|█████▎    | 268/507 [00:13<00:14, 16.65it/s]
Loading 0:  53%|█████▎    | 270/507 [00:13<00:16, 14.39it/s]
Loading 0:  54%|█████▍    | 274/507 [00:13<00:13, 17.50it/s]
Loading 0:  54%|█████▍    | 276/507 [00:13<00:13, 16.97it/s]
Loading 0:  55%|█████▌    | 280/507 [00:13<00:11, 20.47it/s]
Loading 0:  56%|█████▌    | 283/507 [00:13<00:11, 20.14it/s]
Loading 0:  56%|█████▋    | 286/507 [00:14<00:10, 20.28it/s]
Loading 0:  57%|█████▋    | 289/507 [00:14<00:10, 21.38it/s]
Loading 0:  58%|█████▊    | 292/507 [00:14<00:09, 22.59it/s]
Loading 0:  58%|█████▊    | 295/507 [00:14<00:12, 16.78it/s]
Loading 0:  59%|█████▊    | 297/507 [00:14<00:14, 14.47it/s]
Loading 0:  59%|█████▉    | 299/507 [00:26<00:14, 14.47it/s]
Loading 0:  59%|█████▉    | 300/507 [00:36<08:06,  2.35s/it]
Loading 0:  60%|█████▉    | 302/507 [00:36<06:14,  1.83s/it]
Loading 0:  60%|██████    | 306/507 [00:36<03:43,  1.11s/it]
Loading 0:  61%|██████    | 309/507 [00:36<02:37,  1.25it/s]
Loading 0:  61%|██████▏   | 311/507 [00:37<02:06,  1.55it/s]
Loading 0:  62%|██████▏   | 316/507 [00:37<01:11,  2.68it/s]
Loading 0:  63%|██████▎   | 319/507 [00:37<00:52,  3.57it/s]
Loading 0:  64%|██████▎   | 322/507 [00:37<00:42,  4.32it/s]
Loading 0:  64%|██████▍   | 324/507 [00:37<00:37,  4.86it/s]
Loading 0:  65%|██████▍   | 328/507 [00:38<00:25,  7.00it/s]
Loading 0:  65%|██████▌   | 330/507 [00:38<00:22,  7.80it/s]
Loading 0:  66%|██████▌   | 334/507 [00:38<00:16, 10.74it/s]
Loading 0:  66%|██████▋   | 337/507 [00:38<00:13, 12.24it/s]
Loading 0:  67%|██████▋   | 339/507 [00:38<00:13, 12.56it/s]
Loading 0:  68%|██████▊   | 343/507 [00:38<00:10, 16.20it/s]
Loading 0:  68%|██████▊   | 346/507 [00:38<00:08, 18.12it/s]
Loading 0:  69%|██████▉   | 349/507 [00:39<00:10, 14.69it/s]
Loading 0:  69%|██████▉   | 351/507 [00:39<00:11, 13.11it/s]
Loading 0:  70%|███████   | 355/507 [00:39<00:09, 16.39it/s]
Loading 0:  70%|███████   | 357/507 [00:39<00:09, 16.13it/s]
Loading 0:  71%|███████   | 361/507 [00:39<00:07, 19.66it/s]
Loading 0:  72%|███████▏  | 364/507 [00:39<00:07, 19.63it/s]
Loading 0:  72%|███████▏  | 367/507 [00:40<00:06, 20.06it/s]
Loading 0:  73%|███████▎  | 370/507 [00:40<00:06, 21.40it/s]
Loading 0:  74%|███████▎  | 373/507 [00:40<00:05, 22.56it/s]
Loading 0:  74%|███████▍  | 376/507 [00:40<00:08, 16.16it/s]
Loading 0:  75%|███████▍  | 378/507 [00:40<00:09, 14.01it/s]
Loading 0:  75%|███████▌  | 382/507 [00:41<00:07, 17.15it/s]
Loading 0:  76%|███████▌  | 384/507 [00:41<00:07, 16.38it/s]
Loading 0:  77%|███████▋  | 388/507 [00:41<00:06, 19.45it/s]
Loading 0:  77%|███████▋  | 391/507 [00:41<00:06, 19.31it/s]
Loading 0:  78%|███████▊  | 394/507 [00:41<00:05, 19.40it/s]
Loading 0:  78%|███████▊  | 397/507 [00:41<00:05, 20.46it/s]
Loading 0:  79%|███████▉  | 400/507 [00:41<00:04, 21.93it/s]
Loading 0:  79%|███████▉  | 403/507 [00:42<00:06, 16.13it/s]
Loading 0:  80%|███████▉  | 405/507 [00:42<00:07, 14.10it/s]
Loading 0:  81%|████████  | 409/507 [00:42<00:05, 17.27it/s]
Loading 0:  81%|████████  | 411/507 [00:42<00:05, 16.87it/s]
Loading 0:  82%|████████▏ | 415/507 [00:42<00:04, 20.44it/s]
Loading 0:  82%|████████▏ | 418/507 [00:42<00:04, 20.54it/s]
Loading 0:  83%|████████▎ | 421/507 [00:43<00:04, 20.86it/s]
Loading 0:  84%|████████▎ | 424/507 [00:43<00:03, 22.07it/s]
Loading 0:  84%|████████▍ | 427/507 [00:43<00:03, 23.28it/s]
Loading 0:  85%|████████▍ | 430/507 [00:43<00:04, 17.72it/s]
Loading 0:  85%|████████▌ | 433/507 [00:43<00:04, 16.62it/s]
Loading 0:  86%|████████▌ | 436/507 [00:43<00:04, 17.52it/s]
Loading 0:  86%|████████▋ | 438/507 [00:44<00:04, 16.97it/s]
Loading 0:  87%|████████▋ | 442/507 [00:44<00:03, 20.35it/s]
Loading 0:  88%|████████▊ | 445/507 [00:44<00:03, 20.25it/s]
Loading 0:  88%|████████▊ | 448/507 [00:44<00:02, 20.40it/s]
Loading 0:  89%|████████▉ | 451/507 [00:44<00:02, 21.68it/s]
Loading 0:  90%|████████▉ | 454/507 [00:44<00:02, 23.04it/s]
Loading 0:  90%|█████████ | 457/507 [00:44<00:02, 16.92it/s]
Loading 0:  91%|█████████ | 459/507 [00:45<00:03, 14.54it/s]
Loading 0:  91%|█████████▏| 463/507 [00:45<00:02, 17.49it/s]
Loading 0:  92%|█████████▏| 465/507 [00:45<00:02, 16.96it/s]
Loading 0:  93%|█████████▎| 469/507 [00:45<00:01, 20.46it/s]
Loading 0:  93%|█████████▎| 472/507 [00:45<00:01, 20.27it/s]
Loading 0:  94%|█████████▎| 475/507 [00:45<00:01, 20.58it/s]
Loading 0:  94%|█████████▍| 478/507 [00:45<00:01, 21.98it/s]
Loading 0:  95%|█████████▍| 481/507 [00:46<00:01, 23.13it/s]
Loading 0:  95%|█████████▌| 484/507 [00:48<00:06,  3.54it/s]
Loading 0:  96%|█████████▌| 487/507 [00:48<00:04,  4.58it/s]
Loading 0:  97%|█████████▋| 491/507 [00:48<00:02,  6.58it/s]
Loading 0:  97%|█████████▋| 493/507 [00:49<00:01,  7.46it/s]
Loading 0:  98%|█████████▊| 497/507 [00:49<00:00, 10.47it/s]
Loading 0:  99%|█████████▊| 500/507 [00:49<00:00, 12.08it/s]
Loading 0:  99%|█████████▉| 503/507 [00:49<00:00, 13.77it/s]
Loading 0: 100%|█████████▉| 506/507 [00:49<00:00, 15.97it/s]
                                                            
Job zonemercy-vingt-deux-gfv-4513-v1-mkmlizer completed after 226.75s with status: succeeded
Stopping job with name zonemercy-vingt-deux-gfv-4513-v1-mkmlizer
Pipeline stage MKMLizer completed in 227.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-gfv-4513-v1
Waiting for inference service zonemercy-vingt-deux-gfv-4513-v1 to be ready
admin requested tearing down of rirv938-llama-8b-big-ret_9237_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLDeleter completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Skipping deletion as no model was successfully uploaded
Pipeline stage MKMLModelDeleter completed in 0.31s
Shutdown handler de-registered
rirv938-llama-8b-big-ret_9237_v1 status is now torndown due to DeploymentManager action
Inference service zonemercy-vingt-deux-gfv-4513-v1 ready after 220.49940085411072s
Pipeline stage MKMLDeployer completed in 220.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.018899917602539s
Received healthy response to inference request in 2.8996386528015137s
Received healthy response to inference request in 2.595360040664673s
Received healthy response to inference request in 2.5715668201446533s
Received healthy response to inference request in 2.490821123123169s
5 requests
0 failed requests
5th percentile: 2.506970262527466
10th percentile: 2.523119401931763
20th percentile: 2.5554176807403564
30th percentile: 2.576325464248657
40th percentile: 2.585842752456665
50th percentile: 2.595360040664673
60th percentile: 2.7170714855194094
70th percentile: 2.8387829303741454
80th percentile: 2.9234909057617187
90th percentile: 2.971195411682129
95th percentile: 2.995047664642334
99th percentile: 3.014129467010498
mean time: 2.7152573108673095
Pipeline stage StressChecker completed in 14.51s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.07s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_4513_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-gfv-4513-v1-profiler
Waiting for inference service zonemercy-vingt-deux-gfv-4513-v1-profiler to be ready
Inference service zonemercy-vingt-deux-gfv-4513-v1-profiler ready after 210.45945262908936s
Pipeline stage MKMLProfilerDeployer completed in 210.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux3e9db0456b1474fd1a774817e44c81a9-deploff92w:/code/chaiverse_profiler_1727371895 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux3e9db0456b1474fd1a774817e44c81a9-deploff92w --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727371895 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727371895/summary.json'
kubectl exec -it zonemercy-vingt-deux3e9db0456b1474fd1a774817e44c81a9-deploff92w --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727371895/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1568.37s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-gfv-4513-v1-profiler is running
Tearing down inference service zonemercy-vingt-deux-gfv-4513-v1-profiler
Service zonemercy-vingt-deux-gfv-4513-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.47s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_4513_v1 status is now inactive due to auto deactivation removed underperforming models
Shutdown handler de-registered
chaiml-albert-dpo-0912-v_8296_v2 status is now torndown due to DeploymentManager action
Service nousresearch-hermes-2-pr-1418-v5 has been torndown
Pipeline stage MKMLDeleter completed in 56.75s
run pipeline stage %s
Checking if service rirv938-llama-8b-big-ret-5422-v1 is running
Running pipeline stage MKMLDeleter
Tearing down inference service rirv938-llama-8b-big-ret-5210-v1
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-gfv_4513_v1
chaiml-albert-dpo-0912-v_9673_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 65.22s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Tearing down inference service rirv938-llama-8b-big-ret-5422-v1
Checking if service rirv938-llama-8b-big-ret-9237-v3 is running
Service rirv938-llama-8b-big-ret-5210-v1 has been torndown
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v3-_7871_v1
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Service rirv938-llama-8b-big-ret-5422-v1 has been torndown
Tearing down inference service rirv938-llama-8b-big-ret-9237-v3
Pipeline stage MKMLDeleter completed in 73.20s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
admin requested tearing down of blend_rofur_2024-10-03
admin requested tearing down of blend_rofur_2024-10-03
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
admin requested tearing down of blend_rofur_2024-10-03
Cleaning model data from model cache
Pipeline stage MKMLDeleter completed in 119.45s
Service rirv938-llama-8b-big-ret-9237-v3 has been torndown
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 88.17s
Checking if service zonemercy-elite-edit-v1-1e5-v1 is running
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Cleaning model data from model cache
Cleaning model data from S3
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key jic062-dpo-v1-9-nemo-v1/config.json from bucket guanaco-mkml-models
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 154.64s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
run pipeline %s
run pipeline %s
Skipping teardown as no inference service was found
run pipeline %s
run pipeline stage %s
Checking if service zonemercy-elite-pref-v4-1e5-v1 is running
Running pipeline stage MKMLDeleter
Deleting key jic062-dpo-v1-9-nemo-v2/config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
run pipeline %s
Deleting key jic062-dpo-v1-9-nemo-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 182.27s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Tearing down inference service zonemercy-elite-pref-v4-1e5-v1
Checking if service zonemercy-vingt-deux-gfv-4513-v1 is running
Deleting key jic062-dpo-v1-9-nemo-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v5/added_tokens.json from bucket guanaco-mkml-models
run pipeline stage %s
Deleting key jic062-dpo-v1-9-nemo-v1/special_tokens_map.json from bucket guanaco-mkml-models
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
Cleaning model data from model cache
Cleaning model data from S3
Running pipeline stage MKMLDeleter
Running pipeline stage ProductionBlendMKMLTemplater
run pipeline stage %s
Running pipeline stage ProductionBlendMKMLTemplater
Checking if service zonemercy-virgo-edit-v3-7871-v1 is running
Service zonemercy-elite-pref-v4-1e5-v1 has been torndown
Tearing down inference service zonemercy-vingt-deux-gfv-4513-v1
Deleting key jic062-dpo-v1-9-nemo-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v5/config.json from bucket guanaco-mkml-models
Running pipeline stage ProductionBlendMKMLTemplater
Deleting key jic062-dpo-v1-9-nemo-v1/tokenizer.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Cleaning model data from S3
Deleting key rirv938-llama-8b-big-ret-5210-v1/config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Tearing down inference service zonemercy-virgo-edit-v3-7871-v1
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
Pipeline stage MKMLDeleter completed in 215.40s
admin requested tearing down of blend_rofur_2024-10-03
Service zonemercy-vingt-deux-gfv-4513-v1 has been torndown
Deleting key jic062-dpo-v1-9-nemo-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
admin requested tearing down of blend_rofur_2024-10-03
Pipeline stage %s skipped, reason=%s
Deleting key jic062-dpo-v1-9-nemo-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-5422-v1/config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key rirv938-llama-8b-big-ret-5210-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-cogent-nemo-v-3266-v11/config.json from bucket guanaco-mkml-models
Pipeline stage MKMLDeleter completed in 144.20s
Pipeline stage ProductionBlendMKMLTemplater completed in 146.69s
Cleaning model data from S3
Pipeline stage ProductionBlendMKMLTemplater completed in 151.85s
Service zonemercy-virgo-edit-v3-7871-v1 has been torndown
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 282.47s
Deleting key jic062-dpo-v1-9-nemo-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key nousresearch-hermes-2-pr-1418-v5/special_tokens_map.json from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage ProductionBlendMKMLTemplater completed in 178.13s
Pipeline stage MKMLModelDeleter completed in 481.79s
Tearing down inference service blend-rofur-2024-10-03
Deleting key rirv938-llama-8b-big-ret-5422-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-5210-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-9237-v3/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-cogent-nemo-v-3266-v11/flywheel_model.0.safetensors from bucket guanaco-mkml-models
run pipeline stage %s
run pipeline stage %s
Cleaning model data from model cache
run pipeline stage %s
run pipeline %s
Pipeline stage MKMLDeleter completed in 320.87s
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 549.00s
Deleting key nousresearch-hermes-2-pr-1418-v5/tokenizer.json from bucket guanaco-mkml-models
run pipeline %s
run pipeline stage %s
Shutdown handler de-registered
%s, retrying in %s seconds...
Deleting key rirv938-llama-8b-big-ret-5422-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-5210-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-9237-v3/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-cogent-nemo-v-3266-v11/special_tokens_map.json from bucket guanaco-mkml-models
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLDeployer
Deleting key zonemercy-elite-edit-v1-1e5-v1/config.json from bucket guanaco-mkml-models
Running pipeline stage MKMLDeployer
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
run pipeline stage %s
admin requested tearing down of blend_rofur_2024-10-03
run pipeline stage %s
run pipeline stage %s
admin requested tearing down of blend_rofur_2024-10-03
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
Shutdown handler de-registered
Deleting key nousresearch-hermes-2-pr-1418-v5/tokenizer.model from bucket guanaco-mkml-models
run pipeline stage %s
Running pipeline stage MKMLDeployer
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
Deleting key rirv938-llama-8b-big-ret-9237-v3/special_tokens_map.json from bucket guanaco-mkml-models
Creating inference service blend-rofur-2024-10-03
Connection pool is full, discarding connection: %s. Connection pool size: %s
Running pipeline stage ProductionBlendMKMLTemplater
Shutdown handler not registered because Python interpreter is not running in the main thread
Cleaning model data from S3
jic062-dpo-v1-9-nemo_v2 status is now torndown due to DeploymentManager action
Deleting key nousresearch-hermes-2-pr-1418-v5/tokenizer_config.json from bucket guanaco-mkml-models
Running pipeline stage ProductionBlendMKMLTemplater
Deleting key rirv938-llama-8b-big-ret-9237-v3/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-cogent-nemo-v-3266-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-5422-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-5210-v1/tokenizer_config.json from bucket guanaco-mkml-models
Creating inference service blend-rofur-2024-10-03
Waiting for inference service blend-rofur-2024-10-03 to be ready
Pipeline stage %s skipped, reason=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 25.86s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-gfv_4513_v1
Pipeline stage MKMLModelDeleter completed in 28.20s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 27.70s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
run pipeline stage %s
admin requested tearing down of blend_rofur_2024-10-03
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v3-_7871_v1
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
admin requested tearing down of blend_rofur_2024-10-03
admin requested tearing down of blend_rofur_2024-10-03
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 104.37s
Pipeline stage MKMLDeleter completed in 99.78s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
run pipeline %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
run pipeline %s
Pipeline stage %s skipped, reason=%s
jic062-dpo-v1-9-nemo_v2 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Shutdown handler de-registered
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 147.96s
run pipeline %s
run pipeline stage %s
run pipeline stage %s
run pipeline stage %s
run pipeline %s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 131.01s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 96.16s
nousresearch-hermes-2-pr_1418_v5 status is now torndown due to DeploymentManager action
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
run pipeline stage %s
Running pipeline stage ProductionBlendMKMLTemplater
Running pipeline stage MKMLDeleter
Running pipeline stage MKMLDeleter
run pipeline stage %s
Cleaning model data from S3
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 101.92s
Cleaning model data from S3
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
rirv938-llama-8b-big-ret_5210_v1 status is now torndown due to DeploymentManager action
Running pipeline stage ProductionBlendMKMLTemplater
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Pipeline stage %s skipped, reason=%s
Running pipeline stage ProductionBlendMKMLTemplater
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
Cleaning model data from model cache
admin requested tearing down of blend_rofur_2024-10-03
rirv938-llama-8b-big-ret_5422_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLDeleter completed in 110.25s
admin requested tearing down of blend_rofur_2024-10-03
Pipeline stage MKMLDeleter completed in 124.22s
Pipeline stage %s skipped, reason=%s
Pipeline stage ProductionBlendMKMLTemplater completed in 133.11s
Pipeline stage MKMLDeleter completed in 130.38s
Pipeline stage %s skipped, reason=%s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key zonemercy-cogent-nemo-v-3266-v11/tokenizer.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-big-ret-9237-v3/tokenizer_config.json from bucket guanaco-mkml-models
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage ProductionBlendMKMLTemplater completed in 149.32s
Cleaning model data from model cache
run pipeline stage %s
Pipeline stage ProductionBlendMKMLTemplater completed in 179.95s
run pipeline stage %s
run pipeline %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
run pipeline %s
Tearing down inference service blend-rofur-2024-10-03
Deleting key zonemercy-cogent-nemo-v-3266-v11/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 301.74s
run pipeline %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Deleting key zonemercy-elite-edit-v1-1e5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Running pipeline stage MKMLDeployer
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Cleaning model data from S3
Cleaning model data from model cache
run pipeline stage %s
%s, retrying in %s seconds...
Pipeline stage MKMLModelDeleter completed in 359.42s
Shutdown handler de-registered
run pipeline stage %s
Cleaning model data from S3
Running pipeline stage MKMLDeployer
Deleting key zonemercy-elite-edit-v1-1e5-v1/special_tokens_map.json from bucket guanaco-mkml-models
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
Running pipeline stage MKMLDeployer
Creating inference service blend-rofur-2024-10-03
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
admin requested tearing down of blend_rofur_2024-10-03
admin requested tearing down of blend_rofur_2024-10-03
Cleaning model data from model cache
Deleting key zonemercy-elite-pref-v4-1e5-v1/config.json from bucket guanaco-mkml-models
Running pipeline stage ProductionBlendMKMLTemplater
Creating inference service blend-rofur-2024-10-03
Shutdown handler de-registered
rirv938-llama-8b-big-ret_9237_v3 status is now torndown due to DeploymentManager action
Connection pool is full, discarding connection: %s. Connection pool size: %s
Deleting key zonemercy-elite-edit-v1-1e5-v1/tokenizer.json from bucket guanaco-mkml-models
Running pipeline stage ProductionBlendMKMLTemplater
Cleaning model data from model cache
Shutdown handler not registered because Python interpreter is not running in the main thread
Creating inference service blend-rofur-2024-10-03
Pipeline stage %s skipped, reason=%s
Waiting for inference service blend-rofur-2024-10-03 to be ready
Shutdown handler not registered because Python interpreter is not running in the main thread
Creating inference service blend-rofur-2024-10-03
Pipeline stage MKMLModelDeleter completed in 228.36s
Shutdown handler not registered because Python interpreter is not running in the main thread
Deleting key zonemercy-virgo-edit-v3-7871-v1/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-elite-pref-v4-1e5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Pipeline stage %s skipped, reason=%s
Ignoring service blend-rofur-2024-10-03 already deployed
zonemercy-cogent-nemo-v_3266_v11 status is now torndown due to DeploymentManager action
Deleting key zonemercy-elite-edit-v1-1e5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage %s skipped, reason=%s
Deleting key zonemercy-vingt-deux-gfv-4513-v1/config.json from bucket guanaco-mkml-models
run pipeline %s
Ignoring service blend-rofur-2024-10-03 already deployed
Pipeline stage MKMLDeleter completed in 254.27s
run pipeline %s
Ignoring service blend-rofur-2024-10-03 already deployed
Shutdown handler de-registered
run pipeline %s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
Deleting key zonemercy-virgo-edit-v3-7871-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-elite-pref-v4-1e5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Pipeline stage ProductionBlendMKMLTemplater completed in 251.49s
admin requested tearing down of blend_rofur_2024-10-03
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 33.23s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
run pipeline %s
admin requested tearing down of blend_rofur_2024-10-03
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLizer
admin requested tearing down of zonemercy-vingt-deux-gfv_4513_v1
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 41.75s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 49.16s
Pipeline stage %s skipped, reason=%s
admin requested tearing down of blend_rofur_2024-10-03
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
Starting job with name mistralai-mistral-nemo-9330-v138-mkmlizer
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 96.98s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 107.61s
run pipeline %s
run pipeline %s
Running pipeline stage MKMLDeleter
Waiting for job on mistralai-mistral-nemo-9330-v138-mkmlizer to finish
run pipeline stage %s
run pipeline %s
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLModelDeleter completed in 152.79s
run pipeline stage %s
run pipeline %s
run pipeline %s
run pipeline stage %s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
jic062-dpo-v1-9-nemo_v2 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 130.76s
Pipeline stage %s skipped, reason=%s
run pipeline stage %s
Shutdown handler de-registered
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
run pipeline stage %s
Running pipeline stage ProductionBlendMKMLTemplater
mistralai-mistral-nemo-9330-v138-mkmlizer: quantized model in 37.014s
Running pipeline stage MKMLDeleter
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 115.88s
Running pipeline stage ProductionBlendMKMLTemplater
nousresearch-hermes-2-pr_1418_v5 status is now torndown due to DeploymentManager action
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
admin requested tearing down of blend_rofur_2024-10-03
Running pipeline stage ProductionBlendMKMLTemplater
Pipeline stage %s skipped, reason=%s
admin requested tearing down of blend_rofur_2024-10-03
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 147.46s
rirv938-llama-8b-big-ret_5210_v1 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 138.94s
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
Pipeline stage ProductionBlendMKMLTemplater completed in 145.39s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Shutdown handler de-registered
rirv938-llama-8b-big-ret_5422_v1 status is now torndown due to DeploymentManager action
Pipeline stage ProductionBlendMKMLTemplater completed in 170.73s
run pipeline %s
run pipeline stage %s
Pipeline stage MKMLModelDeleter completed in 175.26s
run pipeline %s
Pipeline stage ProductionBlendMKMLTemplater completed in 172.80s
run pipeline %s
Cleaning model data from S3
Running pipeline stage MKMLModelDeleter
rirv938-llama-8b-big-ret_9237_v3 status is now torndown due to DeploymentManager action
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLDeployer
run pipeline stage %s
Shutdown handler de-registered
run pipeline stage %s
%s, retrying in %s seconds...
Running pipeline stage MKMLModelDeleter
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
mistralai-mistral-nemo-9330-v138-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/mistralai-mistral-nemo-9330-v138
admin requested tearing down of blend_rofur_2024-10-03
Running pipeline stage MKMLModelDeleter
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 27.09s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-gfv_4513_v1
Pipeline stage MKMLModelDeleter completed in 31.17s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLModelDeleter
admin requested tearing down of chaiml-0916-intent-suppo_6584_v3
run pipeline stage %s
admin requested tearing down of blend_rofur_2024-10-03
Pipeline stage MKMLDeleter completed in 39.32s
Pipeline stage %s skipped, reason=%s
run pipeline %s
Pipeline stage MKMLModelDeleter completed in 49.49s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v3-_7871_v1
Shutdown handler de-registered
Pipeline stage %s skipped, reason=%s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of chaiml-0917-bot-dominant_6324_v5
Running pipeline stage MKMLModelDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline stage %s
Pipeline stage MKMLDeleter completed in 71.47s
Pipeline stage %s skipped, reason=%s
Running pipeline stage MKMLDeleter
run pipeline stage %s
Shutdown handler de-registered
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-virgo-edit-v5-1e5b1_v2
jic062-dpo-v1-9-nemo_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 85.36s
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Pipeline stage %s skipped, reason=%s
admin requested tearing down of chaiml-albert-dpo-0912-v_1751_v2
run pipeline %s
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 87.39s
run pipeline stage %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-gfv_4513_v1 status is now torndown due to DeploymentManager action