submission_id: meta-llama-meta-llama-3-_6070_v6
developer_uid: Jellywibble
alignment_samples: 148012
alignment_score: 3.2245886894017435
best_of: 4
celo_rating: 1205.66
display_name: metallama4
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{bot_name}:', 'truncate_by_message': True}
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 512, 'best_of': 4, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
is_internal_developer: True
language_model: meta-llama/Meta-Llama-3.1-70B-Instruct
latencies: [{'batch_size': 1, 'throughput': 0.25773915021103877, 'latency_mean': 3.8798277950286866, 'latency_p50': 3.8986105918884277, 'latency_p90': 4.333385872840881}, {'batch_size': 2, 'throughput': 0.4270534916620706, 'latency_mean': 4.6650712525844575, 'latency_p50': 4.667619943618774, 'latency_p90': 5.182049560546875}, {'batch_size': 3, 'throughput': 0.5820332587929833, 'latency_mean': 5.128748081922531, 'latency_p50': 5.139838933944702, 'latency_p90': 5.657339406013489}, {'batch_size': 5, 'throughput': 0.8101632586253794, 'latency_mean': 6.1311121642589566, 'latency_p50': 6.131119728088379, 'latency_p90': 6.9429954290390015}]
max_input_tokens: 512
max_output_tokens: 64
model_architecture: LlamaForCausalLM
model_group: meta-llama/Meta-Llama-3.
model_name: metallama4
model_num_parameters: 70553706496.0
model_repo: meta-llama/Meta-Llama-3.1-70B-Instruct
model_size: 71B
num_battles: 148012
num_wins: 67921
propriety_score: 0.6275816610517064
propriety_total_count: 13654.0
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-08-20T16:55:43+00:00
us_pacific_date: 2024-08-20
win_ratio: 0.4588884685025538
Download Preference Data
Resubmit model
Running pipeline stage MKMLizer
Starting job with name meta-llama-meta-llama-3-6070-v6-mkmlizer
Waiting for job on meta-llama-meta-llama-3-6070-v6-mkmlizer to finish
meta-llama-meta-llama-3-6070-v6-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ _____ __ __ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ /___/ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ Version: 0.9.11 ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ https://mk1.ai ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ The license key for the current software has been verified as ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ belonging to: ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ Chai Research Corp. ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ║ ║
meta-llama-meta-llama-3-6070-v6-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
meta-llama-meta-llama-3-6070-v6-mkmlizer: Downloaded to shared memory in 269.009s
meta-llama-meta-llama-3-6070-v6-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp6vfi8yio, device:0
meta-llama-meta-llama-3-6070-v6-mkmlizer: Saving flywheel model at /dev/shm/model_cache
meta-llama-meta-llama-3-6070-v6-mkmlizer: quantized model in 142.810s
meta-llama-meta-llama-3-6070-v6-mkmlizer: Processed model meta-llama/Meta-Llama-3.1-70B-Instruct in 411.820s
meta-llama-meta-llama-3-6070-v6-mkmlizer: creating bucket guanaco-mkml-models
meta-llama-meta-llama-3-6070-v6-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
meta-llama-meta-llama-3-6070-v6-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/config.json
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/special_tokens_map.json
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/tokenizer_config.json
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/tokenizer.json
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.5.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.5.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.0.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.1.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.4.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.4.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.2.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.2.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: cp /dev/shm/model_cache/flywheel_model.3.safetensors s3://guanaco-mkml-models/meta-llama-meta-llama-3-6070-v6/flywheel_model.3.safetensors
meta-llama-meta-llama-3-6070-v6-mkmlizer: Loading 0: 0%| | 0/723 [00:00<?, ?it/s] Loading 0: 1%| | 4/723 [00:00<00:26, 27.52it/s] Loading 0: 1%| | 7/723 [00:00<00:31, 22.58it/s] Loading 0: 2%|▏ | 11/723 [00:00<00:30, 23.19it/s] Loading 0: 2%|▏ | 15/723 [00:00<00:26, 27.10it/s] Loading 0: 2%|▏ | 18/723 [00:00<00:45, 15.48it/s] Loading 0: 3%|▎ | 22/723 [00:01<00:39, 17.88it/s] Loading 0: 3%|▎ | 25/723 [00:01<00:37, 18.46it/s] Loading 0: 4%|▍ | 28/723 [00:01<00:34, 20.07it/s] Loading 0: 4%|▍ | 31/723 [00:01<00:34, 20.09it/s] Loading 0: 5%|▍ | 34/723 [00:01<00:33, 20.36it/s] Loading 0: 5%|▌ | 37/723 [00:01<00:31, 22.03it/s] Loading 0: 6%|▌ | 41/723 [00:01<00:26, 25.98it/s] Loading 0: 6%|▌ | 44/723 [00:02<00:38, 17.52it/s] Loading 0: 7%|▋ | 47/723 [00:02<00:36, 18.53it/s] Loading 0: 7%|▋ | 50/723 [00:02<00:44, 15.04it/s] Loading 0: 8%|▊ | 55/723 [00:02<00:33, 20.08it/s] Loading 0: 8%|▊ | 58/723 [00:02<00:33, 19.74it/s] Loading 0: 8%|▊ | 61/723 [00:03<00:33, 20.01it/s] Loading 0: 9%|▉ | 64/723 [00:03<00:31, 21.24it/s] Loading 0: 9%|▉ | 68/723 [00:03<00:35, 18.51it/s] Loading 0: 10%|▉ | 71/723 [00:03<00:43, 15.12it/s] Loading 0: 10%|█ | 75/723 [00:03<00:34, 18.75it/s] Loading 0: 11%|█ | 78/723 [00:04<00:37, 17.20it/s] Loading 0: 11%|█▏ | 82/723 [00:04<00:31, 20.41it/s] Loading 0: 12%|█▏ | 85/723 [00:04<00:31, 20.37it/s] Loading 0: 12%|█▏ | 88/723 [00:04<00:31, 20.24it/s] Loading 0: 13%|█▎ | 91/723 [00:04<00:29, 21.46it/s] Loading 0: 13%|█▎ | 94/723 [00:04<00:40, 15.70it/s] Loading 0: 13%|█▎ | 96/723 [00:05<00:40, 15.46it/s] Loading 0: 14%|█▍ | 100/723 [00:05<00:32, 19.44it/s] Loading 0: 14%|█▍ | 103/723 [00:05<00:31, 19.42it/s] Loading 0: 15%|█▍ | 106/723 [00:05<00:31, 19.51it/s] Loading 0: 15%|█▌ | 109/723 [00:05<00:28, 21.18it/s] Loading 0: 15%|█▌ | 112/723 [00:05<00:34, 17.72it/s] Loading 0: 16%|█▌ | 115/723 [00:05<00:32, 18.69it/s] Loading 0: 16%|█▋ | 118/723 [00:06<00:38, 15.88it/s] Loading 0: 17%|█▋ | 121/723 [00:06<00:35, 16.80it/s] Loading 0: 17%|█▋ | 123/723 [00:06<00:37, 16.19it/s] Loading 0: 17%|█▋ | 124/723 [00:21<00:36, 16.19it/s] Loading 0: 17%|█▋ | 125/723 [00:21<18:51, 1.89s/it] Loading 0: 18%|█▊ | 127/723 [00:22<14:08, 1.42s/it] Loading 0: 18%|█▊ | 129/723 [00:22<10:39, 1.08s/it] Loading 0: 18%|█▊ | 131/723 [00:22<07:58, 1.24it/s] Loading 0: 19%|█▉ | 136/723 [00:22<04:05, 2.39it/s] Loading 0: 19%|█▉ | 139/723 [00:22<02:58, 3.28it/s] Loading 0: 20%|█▉ | 142/723 [00:22<02:18, 4.19it/s] Loading 0: 20%|█▉ | 144/723 [00:23<02:00, 4.79it/s] Loading 0: 20%|██ | 148/723 [00:23<01:22, 6.97it/s] Loading 0: 21%|██ | 150/723 [00:23<01:13, 7.82it/s] Loading 0: 21%|██▏ | 154/723 [00:23<00:51, 10.94it/s] Loading 0: 22%|██▏ | 157/723 [00:23<00:45, 12.57it/s] Loading 0: 22%|██▏ | 160/723 [00:23<00:39, 14.18it/s] Loading 0: 23%|██▎ | 163/723 [00:24<00:34, 16.18it/s] Loading 0: 23%|██▎ | 167/723 [00:24<00:27, 20.15it/s] Loading 0: 24%|██▎ | 170/723 [00:24<00:35, 15.49it/s] Loading 0: 24%|██▍ | 173/723 [00:24<00:32, 16.77it/s] Loading 0: 24%|██▍ | 176/723 [00:24<00:40, 13.54it/s] Loading 0: 25%|██▌ | 181/723 [00:25<00:30, 18.02it/s] Loading 0: 25%|██▌ | 184/723 [00:25<00:29, 18.00it/s] Loading 0: 26%|██▌ | 187/723 [00:25<00:28, 18.54it/s] Loading 0: 26%|██▋ | 190/723 [00:25<00:26, 20.12it/s] Loading 0: 27%|██▋ | 194/723 [00:25<00:29, 17.94it/s] Loading 0: 27%|██▋ | 197/723 [00:26<00:35, 14.92it/s] Loading 0: 28%|██▊ | 201/723 [00:26<00:27, 18.67it/s] Loading 0: 28%|██▊ | 204/723 [00:26<00:30, 17.05it/s] Loading 0: 29%|██▉ | 208/723 [00:26<00:26, 19.57it/s] Loading 0: 29%|██▉ | 211/723 [00:26<00:26, 19.19it/s] Loading 0: 30%|██▉ | 214/723 [00:26<00:25, 19.61it/s] Loading 0: 30%|███ | 217/723 [00:26<00:24, 21.03it/s] Loading 0: 30%|███ | 220/723 [00:27<00:32, 15.42it/s] Loading 0: 31%|███ | 222/723 [00:27<00:32, 15.29it/s] Loading 0: 31%|███▏ | 226/723 [00:27<00:26, 19.03it/s] Loading 0: 32%|███▏ | 229/723 [00:27<00:26, 18.81it/s] Loading 0: 32%|███▏ | 232/723 [00:27<00:25, 19.01it/s] Loading 0: 33%|███▎ | 235/723 [00:27<00:23, 20.88it/s] Loading 0: 33%|███▎ | 238/723 [00:28<00:28, 17.12it/s] Loading 0: 33%|███▎ | 241/723 [00:28<00:25, 18.61it/s] Loading 0: 34%|███▎ | 244/723 [00:28<00:30, 15.81it/s] Loading 0: 34%|███▍ | 247/723 [00:28<00:27, 17.00it/s] Loading 0: 34%|███▍ | 249/723 [00:28<00:29, 16.32it/s] Loading 0: 35%|███▍ | 253/723 [00:29<00:23, 19.66it/s] Loading 0: 35%|███▌ | 256/723 [00:29<00:24, 19.34it/s] Loading 0: 36%|███▌ | 259/723 [00:29<00:23, 19.68it/s] Loading 0: 36%|███▌ | 262/723 [00:29<00:22, 20.91it/s] Loading 0: 37%|███▋ | 265/723 [00:29<00:20, 22.15it/s] Loading 0: 37%|███▋ | 268/723 [00:29<00:25, 17.61it/s] Loading 0: 37%|███▋ | 268/723 [00:45<00:25, 17.61it/s] Loading 0: 37%|███▋ | 269/723 [00:45<14:40, 1.94s/it] Loading 0: 37%|███▋ | 270/723 [00:45<12:37, 1.67s/it] Loading 0: 38%|███▊ | 273/723 [00:45<07:52, 1.05s/it] Loading 0: 38%|███▊ | 275/723 [00:45<05:57, 1.25it/s] Loading 0: 39%|███▊ | 280/723 [00:45<03:05, 2.39it/s] Loading 0: 39%|███▉ | 283/723 [00:46<02:17, 3.21it/s] Loading 0: 39%|███▉ | 285/723 [00:46<01:53, 3.85it/s] Loading 0: 40%|███▉ | 289/723 [00:46<01:14, 5.81it/s] Loading 0: 41%|████ | 293/723 [00:46<00:52, 8.14it/s] Loading 0: 41%|████ | 296/723 [00:46<00:50, 8.49it/s] Loading 0: 41%|████ | 298/723 [00:46<00:45, 9.31it/s] Loading 0: 42%|████▏ | 301/723 [00:47<00:38, 10.83it/s] Loading 0: 42%|████▏ | 303/723 [00:47<00:36, 11.41it/s] Loading 0: 42%|████▏ | 307/723 [00:47<00:27, 14.98it/s] Loading 0: 43%|████▎ | 310/723 [00:47<00:26, 15.69it/s] Loading 0: 43%|████▎ | 312/723 [00:47<00:26, 15.23it/s] Loading 0: 44%|████▎ | 316/723 [00:47<00:21, 19.19it/s] Loading 0: 44%|████▍ | 319/723 [00:47<00:19, 21.24it/s] Loading 0: 45%|████▍ | 322/723 [00:48<00:25, 15.47it/s] Loading 0: 45%|████▍ | 324/723 [00:48<00:26, 15.19it/s] Loading 0: 45%|████▌ | 327/723 [00:48<00:22, 17.36it/s] Loading 0: 46%|████▌ | 330/723 [00:48<00:24, 16.02it/s] Loading 0: 46%|████▌ | 334/723 [00:48<00:20, 19.08it/s] Loading 0: 47%|████▋ | 337/723 [00:48<00:20, 18.67it/s] Loading 0: 47%|████▋ | 340/723 [00:49<00:20, 18.94it/s] Loading 0: 47%|████▋ | 343/723 [00:49<00:18, 20.21it/s] Loading 0: 48%|████▊ | 346/723 [00:49<00:25, 14.90it/s] Loading 0: 48%|████▊ | 348/723 [00:49<00:25, 14.85it/s] Loading 0: 49%|████▊ | 352/723 [00:49<00:19, 18.84it/s] Loading 0: 49%|████▉ | 355/723 [00:50<00:19, 18.51it/s] Loading 0: 50%|████▉ | 358/723 [00:50<00:19, 19.12it/s] Loading 0: 50%|████▉ | 361/723 [00:50<00:17, 20.83it/s] Loading 0: 50%|█████ | 364/723 [00:50<00:21, 16.98it/s] Loading 0: 51%|█████ | 367/723 [00:50<00:19, 18.69it/s] Loading 0: 51%|█████ | 370/723 [00:50<00:21, 16.21it/s] Loading 0: 52%|█████▏ | 373/723 [00:51<00:20, 17.32it/s] Loading 0: 52%|█████▏ | 375/723 [00:51<00:20, 16.69it/s] Loading 0: 52%|█████▏ | 379/723 [00:51<00:16, 20.50it/s] Loading 0: 53%|█████▎ | 382/723 [00:51<00:17, 19.58it/s] Loading 0: 53%|█████▎ | 385/723 [00:51<00:17, 19.75it/s] Loading 0: 54%|█████▎ | 388/723 [00:51<00:15, 21.01it/s] Loading 0: 54%|█████▍ | 391/723 [00:51<00:15, 22.05it/s] Loading 0: 54%|█████▍ | 394/723 [00:52<00:18, 17.53it/s] Loading 0: 55%|█████▍ | 396/723 [00:52<00:22, 14.76it/s] Loading 0: 55%|█████▌ | 400/723 [00:52<00:18, 17.46it/s] Loading 0: 55%|█████▌ | 400/723 [01:07<00:18, 17.46it/s] Loading 0: 55%|█████▌ | 401/723 [01:07<10:02, 1.87s/it] Loading 0: 56%|█████▌ | 405/723 [01:07<05:56, 1.12s/it] Loading 0: 56%|█████▋ | 408/723 [01:07<04:12, 1.25it/s] Loading 0: 57%|█████▋ | 410/723 [01:08<03:21, 1.55it/s] Loading 0: 57%|█████▋ | 415/723 [01:08<01:53, 2.71it/s] Loading 0: 58%|█████▊ | 419/723 [01:08<01:17, 3.92it/s] Loading 0: 58%|█████▊ | 422/723 [01:08<01:04, 4.67it/s] Loading 0: 59%|█████▉ | 425/723 [01:08<00:50, 5.95it/s] Loading 0: 59%|█████▉ | 428/723 [01:09<00:44, 6.69it/s] Loading 0: 60%|█████▉ | 433/723 [01:09<00:29, 9.89it/s] Loading 0: 60%|██████ | 436/723 [01:09<00:25, 11.27it/s] Loading 0: 61%|██████ | 439/723 [01:09<00:22, 12.82it/s] Loading 0: 61%|██████ | 442/723 [01:09<00:18, 14.94it/s] Loading 0: 62%|██████▏ | 445/723 [01:09<00:16, 16.93it/s] Loading 0: 62%|██████▏ | 448/723 [01:10<00:19, 13.81it/s] Loading 0: 62%|██████▏ | 450/723 [01:10<00:19, 13.96it/s] Loading 0: 63%|██████▎ | 453/723 [01:10<00:16, 16.48it/s] Loading 0: 63%|██████▎ | 456/723 [01:10<00:17, 15.48it/s] Loading 0: 64%|██████▎ | 460/723 [01:10<00:13, 18.92it/s] Loading 0: 64%|██████▍ | 463/723 [01:10<00:13, 18.70it/s] Loading 0: 64%|██████▍ | 466/723 [01:10<00:13, 19.29it/s] Loading 0: 65%|██████▍ | 469/723 [01:11<00:12, 20.59it/s] Loading 0: 65%|██████▌ | 472/723 [01:11<00:17, 14.74it/s] Loading 0: 66%|██████▌ | 474/723 [01:11<00:17, 14.46it/s] Loading 0: 66%|██████▌ | 478/723 [01:11<00:13, 18.55it/s] Loading 0: 67%|██████▋ | 481/723 [01:11<00:13, 18.40it/s] Loading 0: 67%|██████▋ | 484/723 [01:12<00:12, 18.86it/s] Loading 0: 67%|██████▋ | 487/723 [01:12<00:11, 20.47it/s] Loading 0: 68%|██████▊ | 490/723 [01:12<00:13, 17.20it/s] Loading 0: 68%|██████▊ | 493/723 [01:12<00:12, 18.76it/s] Loading 0: 69%|██████▊ | 496/723 [01:12<00:13, 16.26it/s] Loading 0: 69%|██████▉ | 499/723 [01:12<00:12, 17.52it/s] Loading 0: 69%|██████▉ | 501/723 [01:13<00:13, 16.60it/s] Loading 0: 70%|██████▉ | 505/723 [01:13<00:10, 20.29it/s] Loading 0: 70%|███████ | 508/723 [01:13<00:10, 19.66it/s] Loading 0: 71%|███████ | 511/723 [01:13<00:10, 19.94it/s] Loading 0: 71%|███████ | 514/723 [01:13<00:10, 20.49it/s] Loading 0: 72%|███████▏ | 517/723 [01:13<00:09, 22.01it/s] Loading 0: 72%|███████▏ | 520/723 [01:13<00:11, 17.37it/s] Loading 0: 72%|███████▏ | 522/723 [01:14<00:13, 14.57it/s] Loading 0: 73%|███████▎ | 526/723 [01:14<00:11, 17.35it/s] Loading 0: 73%|███████▎ | 528/723 [01:14<00:11, 16.60it/s] Loading 0: 74%|███████▎ | 532/723 [01:14<00:09, 20.24it/s] Loading 0: 74%|███████▍ | 535/723 [01:14<00:09, 19.64it/s] Loading 0: 74%|███████▍ | 535/723 [01:29<00:09, 19.64it/s] Loading 0: 74%|███████▍ | 536/723 [01:29<05:46, 1.86s/it] Loading 0: 75%|███████▍ | 540/723 [01:29<03:23, 1.11s/it] Loading 0: 75%|███████▌ | 543/723 [01:29<02:22, 1.27it/s] Loading 0: 76%|███████▌ | 546/723 [01:30<01:41, 1.74it/s] Loading 0: 76%|███████▌ | 548/723 [01:30<01:20, 2.16it/s] Loading 0: 76%|███████▌ | 550/723 [01:30<01:03, 2.73it/s] Loading 0: 76%|███████▋ | 553/723 [01:30<00:44, 3.85it/s] Loading 0: 77%|███████▋ | 555/723 [01:30<00:36, 4.64it/s] Loading 0: 77%|███████▋ | 559/723 [01:30<00:23, 7.06it/s] Loading 0: 78%|███████▊ | 562/723 [01:31<00:18, 8.70it/s] Loading 0: 78%|███████▊ | 564/723 [01:31<00:16, 9.54it/s] Loading 0: 79%|███████▊ | 568/723 [01:31<00:11, 13.16it/s] Loading 0: 79%|███████▉ | 572/723 [01:31<00:10, 13.73it/s] Loading 0: 79%|███████▉ | 574/723 [01:31<00:10, 13.77it/s] Loading 0: 80%|███████▉ | 576/723 [01:31<00:10, 13.85it/s] Loading 0: 80%|████████ | 579/723 [01:32<00:08, 16.49it/s] Loading 0: 80%|████████ | 581/723 [01:32<00:10, 14.14it/s] Loading 0: 81%|████████ | 586/723 [01:32<00:07, 19.48it/s] Loading 0: 81%|████████▏ | 589/723 [01:32<00:07, 19.13it/s] Loading 0: 82%|████████▏ | 592/723 [01:32<00:06, 19.65it/s] Loading 0: 82%|████████▏ | 595/723 [01:32<00:06, 20.95it/s] Loading 0: 83%|████████▎ | 598/723 [01:33<00:08, 15.54it/s] Loading 0: 83%|████████▎ | 600/723 [01:33<00:08, 15.14it/s] Loading 0: 84%|████████▎ | 604/723 [01:33<00:06, 18.91it/s] Loading 0: 84%|████████▍ | 607/723 [01:33<00:06, 18.80it/s] Loading 0: 84%|████████▍ | 610/723 [01:33<00:05, 19.16it/s] Loading 0: 85%|████████▍ | 613/723 [01:33<00:05, 20.70it/s] Loading 0: 85%|████████▌ | 616/723 [01:34<00:06, 17.57it/s] Loading 0: 86%|████████▌ | 619/723 [01:34<00:05, 19.42it/s] Loading 0: 86%|████████▌ | 622/723 [01:34<00:06, 16.79it/s] Loading 0: 86%|████████▋ | 625/723 [01:34<00:05, 17.85it/s] Loading 0: 87%|████████▋ | 627/723 [01:34<00:05, 16.91it/s] Loading 0: 87%|████████▋ | 631/723 [01:34<00:04, 20.50it/s] Loading 0: 88%|████████▊ | 634/723 [01:35<00:04, 19.91it/s] Loading 0: 88%|████████▊ | 637/723 [01:35<00:04, 19.90it/s] Loading 0: 89%|████████▊ | 640/723 [01:35<00:04, 20.65it/s] Loading 0: 89%|████████▉ | 643/723 [01:35<00:03, 22.05it/s] Loading 0: 89%|████████▉ | 646/723 [01:35<00:04, 17.72it/s] Loading 0: 90%|████████▉ | 648/723 [01:35<00:05, 14.66it/s] Loading 0: 90%|█████████ | 652/723 [01:36<00:04, 17.43it/s] Loading 0: 90%|█████████ | 654/723 [01:36<00:04, 16.51it/s] Loading 0: 91%|█████████ | 658/723 [01:36<00:03, 19.72it/s] Loading 0: 91%|█████████▏| 661/723 [01:36<00:03, 19.28it/s] Loading 0: 92%|█████████▏| 664/723 [01:36<00:02, 19.67it/s] Loading 0: 92%|█████████▏| 667/723 [01:36<00:02, 21.05it/s] Loading 0: 93%|█████████▎| 671/723 [01:36<00:02, 24.21it/s] Loading 0: 93%|█████████▎| 674/723 [01:37<00:02, 17.06it/s] Loading 0: 93%|█████████▎| 674/723 [01:52<00:02, 17.06it/s] Loading 0: 93%|█████████▎| 675/723 [01:52<01:28, 1.83s/it] Loading 0: 94%|█████████▍| 678/723 [01:52<00:56, 1.25s/it] Loading 0: 94%|█████████▍| 680/723 [01:52<00:42, 1.02it/s] Loading 0: 95%|█████████▍| 685/723 [01:53<00:20, 1.86it/s] Loading 0: 95%|█████████▌| 688/723 [01:53<00:14, 2.50it/s] Loading 0: 96%|█████████▌| 691/723 [01:53<00:09, 3.34it/s] Loading 0: 96%|█████████▌| 694/723 [01:53<00:06, 4.47it/s] Loading 0: 97%|█████████▋| 698/723 [01:53<00:04, 5.97it/s] Loading 0: 97%|█████████▋| 700/723 [01:53<00:03, 6.74it/s] Loading 0: 97%|█████████▋| 702/723 [01:54<00:02, 7.65it/s] Loading 0: 98%|█████████▊| 705/723 [01:54<00:01, 9.98it/s] Loading 0: 98%|█████████▊| 707/723 [01:54<00:01, 9.86it/s] Loading 0: 98%|█████████▊| 712/723 [01:54<00:00, 14.92it/s] Loading 0: 99%|█████████▉| 715/723 [01:54<00:00, 15.69it/s] Loading 0: 99%|█████████▉| 718/723 [01:54<00:00, 16.83it/s] Loading 0: 100%|█████████▉| 721/723 [01:54<00:00, 18.78it/s] Loading 0: 100%|█████████▉| 722/723 [02:05<00:00, 18.78it/s] Loading 0: 100%|██████████| 723/723 [02:05<00:00, 1.18s/it]
Job meta-llama-meta-llama-3-6070-v6-mkmlizer completed after 467.33s with status: succeeded
Stopping job with name meta-llama-meta-llama-3-6070-v6-mkmlizer
Pipeline stage MKMLizer completed in 468.34s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.12s
Running pipeline stage ISVCDeployer
Creating inference service meta-llama-meta-llama-3-6070-v6
Waiting for inference service meta-llama-meta-llama-3-6070-v6 to be ready
Inference service meta-llama-meta-llama-3-6070-v6 ready after 241.5708122253418s
Pipeline stage ISVCDeployer completed in 242.57s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.525856971740723s
Received healthy response to inference request in 3.9421334266662598s
Received healthy response to inference request in 3.8914294242858887s
Received healthy response to inference request in 3.7466747760772705s
Received healthy response to inference request in 4.139533281326294s
5 requests
0 failed requests
5th percentile: 3.775625705718994
10th percentile: 3.8045766353607178
20th percentile: 3.862478494644165
30th percentile: 3.901570224761963
40th percentile: 3.9218518257141115
50th percentile: 3.9421334266662598
60th percentile: 4.021093368530273
70th percentile: 4.100053310394287
80th percentile: 4.21679801940918
90th percentile: 4.371327495574951
95th percentile: 4.448592233657837
99th percentile: 4.510404024124146
mean time: 4.0491255760192875
Pipeline stage StressChecker completed in 21.01s
meta-llama-meta-llama-3-_6070_v6 status is now deployed due to DeploymentManager action
meta-llama-meta-llama-3-_6070_v6 status is now inactive due to auto deactivation removed underperforming models
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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service meta-llama-meta-llama-3-6070-v6-profiler
Waiting for inference service meta-llama-meta-llama-3-6070-v6-profiler to be ready
Inference service meta-llama-meta-llama-3-6070-v6-profiler ready after 210.55694723129272s
Pipeline stage MKMLProfilerDeployer completed in 210.94s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/meta-llama-meta-llam9e582911ebdc83883ad83225055e5321-deplobvxh7:/code/chaiverse_profiler_1725514950 --namespace tenant-chaiml-guanaco
kubectl exec -it meta-llama-meta-llam9e582911ebdc83883ad83225055e5321-deplobvxh7 --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1725514950 && python profiles.py profile --best_of_n 4 --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 512 --output_tokens 64 --summary /code/chaiverse_profiler_1725514950/summary.json'
kubectl exec -it meta-llama-meta-llam9e582911ebdc83883ad83225055e5321-deplobvxh7 --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1725514950/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1842.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service meta-llama-meta-llama-3-6070-v6-profiler is running
Tearing down inference service meta-llama-meta-llama-3-6070-v6-profiler
Service meta-llama-meta-llama-3-6070-v6-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.67s
Shutdown handler de-registered
meta-llama-meta-llama-3-_6070_v6 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics