chaiml-llama-8b-multihea_7810

developer_uid: chai_backend_admin
submission_id: chaiml-llama-8b-multihea_7810_v4
model_name: chaiml-llama-8b-multihea_7810_v4
model_group: ChaiML/llama_8b_multihea
status: inactive
timestamp: 2024-12-09T23:04:19+00:00
num_battles: 15551
num_wins: 7634
celo_rating: 1257.47
family_friendly_score: 0.5833999999999999
family_friendly_standard_error: 0.006972007458401059
submission_type: basic
model_repo: ChaiML/llama_8b_multihead_181m_preference
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: chaiml-llama-8b-multihea_7810_v4
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/llama_8b_multihead_181m_preference
model_size: 8B
ranking_group: single
us_pacific_date: 2024-12-09
win_ratio: 0.4909009066941033
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 256, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': True}
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 chaiml-llama-8b-multihea-7810-v4-mkmlizer
Waiting for job on chaiml-llama-8b-multihea-7810-v4-mkmlizer to finish
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║       /___/                                                         ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ║                                                                     ║
chaiml-llama-8b-multihea-7810-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-llama-8b-multihea-7810-v4-mkmlizer: Downloaded to shared memory in 42.747s
chaiml-llama-8b-multihea-7810-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpqrh0tjf8, device:0
chaiml-llama-8b-multihea-7810-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-llama-8b-multihea-7810-v4-mkmlizer: quantized model in 88.418s
chaiml-llama-8b-multihea-7810-v4-mkmlizer: Processed model ChaiML/llama_8b_multihead_181m_preference in 131.165s
chaiml-llama-8b-multihea-7810-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-llama-8b-multihea-7810-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-llama-8b-multihea-7810-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4
chaiml-llama-8b-multihea-7810-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4/config.json
chaiml-llama-8b-multihea-7810-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4/special_tokens_map.json
chaiml-llama-8b-multihea-7810-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4/tokenizer_config.json
chaiml-llama-8b-multihea-7810-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4/tokenizer.json
chaiml-llama-8b-multihea-7810-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-llama-8b-multihea-7810-v4/flywheel_model.0.safetensors
chaiml-llama-8b-multihea-7810-v4-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:58,  4.91it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:34,  3.02it/s]
Loading 0:   2%|▏         | 5/291 [00:01<02:06,  2.25it/s]
Loading 0:   3%|▎         | 8/291 [00:02<01:05,  4.32it/s]
Loading 0:   3%|▎         | 9/291 [00:02<01:04,  4.39it/s]
Loading 0:   3%|▎         | 10/291 [00:02<00:56,  5.02it/s]
Loading 0:   4%|▍         | 12/291 [00:03<01:07,  4.16it/s]
Loading 0:   4%|▍         | 13/291 [00:03<01:29,  3.12it/s]
Loading 0:   5%|▍         | 14/291 [00:04<01:52,  2.46it/s]
Loading 0:   6%|▌         | 17/291 [00:04<01:04,  4.23it/s]
Loading 0:   6%|▌         | 18/291 [00:04<01:01,  4.42it/s]
Loading 0:   7%|▋         | 19/291 [00:04<00:55,  4.92it/s]
Loading 0:   7%|▋         | 21/291 [00:05<01:05,  4.14it/s]
Loading 0:   8%|▊         | 22/291 [00:06<01:26,  3.13it/s]
Loading 0:   8%|▊         | 23/291 [00:06<01:49,  2.44it/s]
Loading 0:   9%|▉         | 26/291 [00:06<01:03,  4.20it/s]
Loading 0:   9%|▉         | 27/291 [00:07<00:59,  4.43it/s]
Loading 0:  10%|▉         | 28/291 [00:07<00:52,  5.03it/s]
Loading 0:  10%|█         | 30/291 [00:07<00:42,  6.12it/s]
Loading 0:  11%|█         | 31/291 [00:07<00:43,  6.02it/s]
Loading 0:  11%|█         | 32/291 [00:07<00:39,  6.52it/s]
Loading 0:  11%|█▏        | 33/291 [00:07<00:45,  5.69it/s]
Loading 0:  12%|█▏        | 34/291 [00:08<01:13,  3.49it/s]
Loading 0:  12%|█▏        | 35/291 [00:09<01:34,  2.70it/s]
Loading 0:  12%|█▏        | 36/291 [00:09<01:55,  2.21it/s]
Loading 0:  13%|█▎        | 39/291 [00:10<01:19,  3.18it/s]
Loading 0:  14%|█▎        | 40/291 [00:11<01:33,  2.68it/s]
Loading 0:  14%|█▍        | 41/291 [00:11<01:50,  2.26it/s]
Loading 0:  15%|█▌        | 44/291 [00:11<01:03,  3.89it/s]
Loading 0:  15%|█▌        | 45/291 [00:12<00:59,  4.14it/s]
Loading 0:  16%|█▌        | 46/291 [00:12<00:52,  4.67it/s]
Loading 0:  16%|█▋        | 48/291 [00:12<01:00,  4.04it/s]
Loading 0:  17%|█▋        | 49/291 [00:13<01:18,  3.10it/s]
Loading 0:  17%|█▋        | 50/291 [00:14<01:37,  2.47it/s]
Loading 0:  18%|█▊        | 53/291 [00:14<00:56,  4.20it/s]
Loading 0:  19%|█▊        | 54/291 [00:14<00:52,  4.50it/s]
Loading 0:  19%|█▉        | 55/291 [00:14<00:46,  5.06it/s]
Loading 0:  20%|█▉        | 57/291 [00:15<00:55,  4.25it/s]
Loading 0:  20%|█▉        | 58/291 [00:15<01:12,  3.20it/s]
Loading 0:  20%|██        | 59/291 [00:16<01:32,  2.52it/s]
Loading 0:  21%|██▏       | 62/291 [00:16<00:52,  4.33it/s]
Loading 0:  22%|██▏       | 63/291 [00:16<00:50,  4.54it/s]
Loading 0:  22%|██▏       | 64/291 [00:16<00:44,  5.11it/s]
Loading 0:  23%|██▎       | 66/291 [00:17<00:52,  4.25it/s]
Loading 0:  23%|██▎       | 67/291 [00:18<01:09,  3.21it/s]
Loading 0:  23%|██▎       | 68/291 [00:18<01:27,  2.53it/s]
Loading 0:  24%|██▍       | 71/291 [00:18<00:51,  4.29it/s]
Loading 0:  25%|██▍       | 72/291 [00:19<00:48,  4.52it/s]
Loading 0:  25%|██▌       | 73/291 [00:19<00:42,  5.12it/s]
Loading 0:  25%|██▌       | 74/291 [00:19<01:02,  3.45it/s]
Loading 0:  26%|██▌       | 75/291 [00:20<01:23,  2.59it/s]
Loading 0:  26%|██▋       | 77/291 [00:20<00:57,  3.72it/s]
Loading 0:  27%|██▋       | 78/291 [00:20<00:51,  4.12it/s]
Loading 0:  27%|██▋       | 79/291 [00:20<00:44,  4.81it/s]
Loading 0:  27%|██▋       | 80/291 [00:21<00:42,  4.93it/s]
Loading 0:  28%|██▊       | 81/291 [00:21<01:05,  3.23it/s]
Loading 0:  28%|██▊       | 82/291 [00:22<01:21,  2.57it/s]
Loading 0:  29%|██▊       | 83/291 [00:23<01:38,  2.11it/s]
Loading 0:  30%|██▉       | 86/291 [00:23<00:51,  3.96it/s]
Loading 0:  30%|██▉       | 87/291 [00:23<00:48,  4.24it/s]
Loading 0:  30%|███       | 88/291 [00:23<00:41,  4.85it/s]
Loading 0:  31%|███       | 90/291 [00:24<00:48,  4.11it/s]
Loading 0:  31%|███▏      | 91/291 [00:24<01:03,  3.13it/s]
Loading 0:  32%|███▏      | 92/291 [00:25<01:19,  2.50it/s]
Loading 0:  33%|███▎      | 95/291 [00:25<00:44,  4.36it/s]
Loading 0:  33%|███▎      | 96/291 [00:25<00:41,  4.66it/s]
Loading 0:  33%|███▎      | 97/291 [00:25<00:36,  5.25it/s]
Loading 0:  34%|███▍      | 99/291 [00:26<00:44,  4.32it/s]
Loading 0:  34%|███▍      | 100/291 [00:27<00:59,  3.24it/s]
Loading 0:  35%|███▍      | 101/291 [00:27<01:14,  2.56it/s]
Loading 0:  36%|███▌      | 104/291 [00:27<00:42,  4.42it/s]
Loading 0:  36%|███▌      | 105/291 [00:28<00:40,  4.64it/s]
Loading 0:  36%|███▋      | 106/291 [00:28<00:35,  5.24it/s]
Loading 0:  37%|███▋      | 108/291 [00:28<00:42,  4.28it/s]
Loading 0:  37%|███▋      | 109/291 [00:29<00:56,  3.22it/s]
Loading 0:  38%|███▊      | 110/291 [00:29<01:11,  2.54it/s]
Loading 0:  39%|███▉      | 113/291 [00:30<00:40,  4.38it/s]
Loading 0:  39%|███▉      | 114/291 [00:30<00:37,  4.68it/s]
Loading 0:  40%|███▉      | 115/291 [00:30<00:33,  5.25it/s]
Loading 0:  40%|███▉      | 116/291 [00:31<00:50,  3.49it/s]
Loading 0:  41%|████      | 118/291 [00:31<00:37,  4.67it/s]
Loading 0:  41%|████      | 119/291 [00:31<00:35,  4.87it/s]
Loading 0:  41%|████      | 120/291 [00:31<00:31,  5.49it/s]
Loading 0:  42%|████▏     | 122/291 [00:32<00:38,  4.37it/s]
Loading 0:  43%|████▎     | 125/291 [00:32<00:35,  4.68it/s]
Loading 0:  43%|████▎     | 126/291 [00:33<00:46,  3.55it/s]
Loading 0:  44%|████▎     | 127/291 [00:33<00:58,  2.79it/s]
Loading 0:  45%|████▍     | 130/291 [00:34<00:35,  4.55it/s]
Loading 0:  45%|████▌     | 131/291 [00:34<00:33,  4.75it/s]
Loading 0:  45%|████▌     | 132/291 [00:34<00:29,  5.31it/s]
Loading 0:  46%|████▌     | 133/291 [00:34<00:29,  5.30it/s]
Loading 0:  46%|████▌     | 134/291 [00:35<00:45,  3.47it/s]
Loading 0:  46%|████▋     | 135/291 [00:35<01:00,  2.59it/s]
Loading 0:  47%|████▋     | 138/291 [00:36<00:43,  3.50it/s]
Loading 0:  48%|████▊     | 139/291 [00:37<00:52,  2.88it/s]
Loading 0:  48%|████▊     | 140/291 [00:37<01:02,  2.40it/s]
Loading 0:  49%|████▉     | 143/291 [00:37<00:36,  4.04it/s]
Loading 0:  49%|████▉     | 144/291 [00:38<00:34,  4.29it/s]
Loading 0:  50%|████▉     | 145/291 [00:38<00:30,  4.83it/s]
Loading 0:  51%|█████     | 147/291 [00:38<00:34,  4.14it/s]
Loading 0:  51%|█████     | 148/291 [00:39<00:45,  3.16it/s]
Loading 0:  51%|█████     | 149/291 [00:40<00:56,  2.51it/s]
Loading 0:  52%|█████▏    | 152/291 [00:40<00:32,  4.27it/s]
Loading 0:  53%|█████▎    | 153/291 [00:40<00:30,  4.50it/s]
Loading 0:  53%|█████▎    | 154/291 [00:40<00:26,  5.08it/s]
Loading 0:  54%|█████▎    | 156/291 [00:41<00:31,  4.23it/s]
Loading 0:  54%|█████▍    | 157/291 [00:41<00:41,  3.21it/s]
Loading 0:  54%|█████▍    | 158/291 [00:42<00:52,  2.55it/s]
Loading 0:  55%|█████▌    | 161/291 [00:42<00:30,  4.31it/s]
Loading 0:  56%|█████▌    | 162/291 [00:42<00:28,  4.54it/s]
Loading 0:  56%|█████▌    | 163/291 [00:42<00:25,  5.07it/s]
Loading 0:  57%|█████▋    | 165/291 [00:43<00:29,  4.23it/s]
Loading 0:  57%|█████▋    | 166/291 [00:44<00:39,  3.20it/s]
Loading 0:  57%|█████▋    | 167/291 [00:44<00:48,  2.53it/s]
Loading 0:  58%|█████▊    | 170/291 [00:44<00:28,  4.29it/s]
Loading 0:  59%|█████▉    | 171/291 [00:45<00:26,  4.53it/s]
Loading 0:  59%|█████▉    | 172/291 [00:45<00:23,  5.10it/s]
Loading 0:  60%|█████▉    | 174/291 [00:45<00:27,  4.23it/s]
Loading 0:  60%|██████    | 175/291 [00:46<00:36,  3.20it/s]
Loading 0:  60%|██████    | 176/291 [00:47<00:45,  2.53it/s]
Loading 0:  62%|██████▏   | 179/291 [00:47<00:26,  4.29it/s]
Loading 0:  62%|██████▏   | 180/291 [00:47<00:24,  4.52it/s]
Loading 0:  62%|██████▏   | 181/291 [00:47<00:21,  5.01it/s]
Loading 0:  63%|██████▎   | 183/291 [00:47<00:17,  6.21it/s]
Loading 0:  63%|██████▎   | 184/291 [00:47<00:17,  6.13it/s]
Loading 0:  64%|██████▎   | 185/291 [00:48<00:15,  6.73it/s]
Loading 0:  64%|██████▍   | 186/291 [00:48<00:16,  6.41it/s]
Loading 0:  64%|██████▍   | 187/291 [00:48<00:28,  3.70it/s]
Loading 0:  65%|██████▍   | 188/291 [00:49<00:36,  2.81it/s]
Loading 0:  65%|██████▍   | 189/291 [00:50<00:44,  2.27it/s]
Loading 0:  66%|██████▌   | 192/291 [00:50<00:30,  3.26it/s]
Loading 0:  66%|██████▋   | 193/291 [00:51<00:35,  2.74it/s]
Loading 0:  67%|██████▋   | 194/291 [00:51<00:41,  2.33it/s]
Loading 0:  68%|██████▊   | 197/291 [00:52<00:23,  3.98it/s]
Loading 0:  68%|██████▊   | 198/291 [00:52<00:21,  4.25it/s]
Loading 0:  68%|██████▊   | 199/291 [00:52<00:19,  4.75it/s]
Loading 0:  69%|██████▉   | 201/291 [00:52<00:21,  4.12it/s]
Loading 0:  69%|██████▉   | 202/291 [00:53<00:28,  3.18it/s]
Loading 0:  70%|██████▉   | 203/291 [00:54<00:34,  2.54it/s]
Loading 0:  71%|███████   | 206/291 [00:54<00:19,  4.31it/s]
Loading 0:  71%|███████   | 207/291 [00:54<00:18,  4.55it/s]
Loading 0:  71%|███████▏  | 208/291 [00:54<00:16,  5.12it/s]
Loading 0:  72%|███████▏  | 210/291 [00:55<00:18,  4.28it/s]
Loading 0:  73%|███████▎  | 211/291 [00:55<00:24,  3.24it/s]
Loading 0:  73%|███████▎  | 212/291 [00:56<00:30,  2.58it/s]
Loading 0:  74%|███████▍  | 215/291 [00:56<00:17,  4.36it/s]
Loading 0:  74%|███████▍  | 216/291 [00:56<00:16,  4.60it/s]
Loading 0:  75%|███████▍  | 217/291 [00:57<00:14,  5.14it/s]
Loading 0:  75%|███████▌  | 219/291 [00:57<00:16,  4.25it/s]
Loading 0:  76%|███████▌  | 220/291 [00:58<00:22,  3.22it/s]
Loading 0:  76%|███████▌  | 221/291 [00:58<00:27,  2.55it/s]
Loading 0:  77%|███████▋  | 224/291 [00:59<00:15,  4.34it/s]
Loading 0:  77%|███████▋  | 225/291 [00:59<00:14,  4.58it/s]
Loading 0:  78%|███████▊  | 226/291 [00:59<00:12,  5.16it/s]
Loading 0:  78%|███████▊  | 227/291 [00:59<00:18,  3.48it/s]
Loading 0:  78%|███████▊  | 228/291 [01:00<00:24,  2.61it/s]
Loading 0:  79%|███████▉  | 230/291 [01:00<00:16,  3.75it/s]
Loading 0:  79%|███████▉  | 231/291 [01:00<00:14,  4.09it/s]
Loading 0:  80%|███████▉  | 232/291 [01:01<00:12,  4.78it/s]
Loading 0:  80%|████████  | 233/291 [01:01<00:11,  5.04it/s]
Loading 0:  80%|████████  | 234/291 [01:01<00:17,  3.30it/s]
Loading 0:  81%|████████▏ | 237/291 [01:02<00:13,  4.10it/s]
Loading 0:  82%|████████▏ | 238/291 [01:03<00:16,  3.19it/s]
Loading 0:  82%|████████▏ | 239/291 [01:03<00:20,  2.57it/s]
Loading 0:  83%|████████▎ | 242/291 [01:03<00:11,  4.31it/s]
Loading 0:  84%|████████▎ | 243/291 [01:04<00:10,  4.55it/s]
Loading 0:  84%|████████▍ | 244/291 [01:04<00:09,  5.11it/s]
Loading 0:  85%|████████▍ | 246/291 [01:04<00:10,  4.27it/s]
Loading 0:  85%|████████▍ | 247/291 [01:05<00:13,  3.25it/s]
Loading 0:  85%|████████▌ | 248/291 [01:05<00:16,  2.56it/s]
Loading 0:  86%|████████▋ | 251/291 [01:06<00:09,  4.41it/s]
Loading 0:  87%|████████▋ | 252/291 [01:06<00:08,  4.64it/s]
Loading 0:  87%|████████▋ | 253/291 [01:06<00:07,  5.22it/s]
Loading 0:  88%|████████▊ | 255/291 [01:07<00:08,  4.34it/s]
Loading 0:  88%|████████▊ | 256/291 [01:07<00:10,  3.27it/s]
Loading 0:  88%|████████▊ | 257/291 [01:08<00:13,  2.59it/s]
Loading 0:  89%|████████▉ | 260/291 [01:08<00:07,  4.41it/s]
Loading 0:  90%|████████▉ | 261/291 [01:08<00:06,  4.64it/s]
Loading 0:  90%|█████████ | 262/291 [01:08<00:05,  5.22it/s]
Loading 0:  91%|█████████ | 264/291 [01:09<00:06,  4.33it/s]
Loading 0:  91%|█████████ | 265/291 [01:09<00:07,  3.27it/s]
Loading 0:  91%|█████████▏| 266/291 [01:10<00:09,  2.59it/s]
Loading 0:  92%|█████████▏| 269/291 [01:10<00:04,  4.40it/s]
Loading 0:  93%|█████████▎| 270/291 [01:10<00:04,  4.63it/s]
Loading 0:  93%|█████████▎| 271/291 [01:11<00:03,  5.18it/s]
Loading 0:  94%|█████████▍| 273/291 [01:11<00:04,  4.31it/s]
Loading 0:  94%|█████████▍| 274/291 [01:12<00:05,  3.26it/s]
Loading 0:  95%|█████████▍| 275/291 [01:12<00:06,  2.57it/s]
Loading 0:  96%|█████████▌| 278/291 [01:13<00:02,  4.42it/s]
Loading 0:  96%|█████████▌| 279/291 [01:13<00:02,  4.65it/s]
Loading 0:  96%|█████████▌| 280/291 [01:13<00:02,  5.21it/s]
Loading 0:  97%|█████████▋| 281/291 [01:13<00:02,  3.50it/s]
Loading 0:  97%|█████████▋| 283/291 [01:14<00:01,  4.70it/s]
Loading 0:  98%|█████████▊| 284/291 [01:14<00:01,  4.94it/s]
Loading 0:  98%|█████████▊| 285/291 [01:14<00:01,  5.52it/s]
Loading 0:  98%|█████████▊| 286/291 [01:14<00:00,  5.44it/s]
Loading 0:  99%|█████████▊| 287/291 [01:15<00:01,  3.43it/s]
Loading 0:  99%|█████████▉| 288/291 [01:15<00:01,  2.54it/s]
                                                            
Job chaiml-llama-8b-multihea-7810-v4-mkmlizer completed after 156.28s with status: succeeded
Stopping job with name chaiml-llama-8b-multihea-7810-v4-mkmlizer
Pipeline stage MKMLizer completed in 156.80s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-llama-8b-multihea-7810-v4
Waiting for inference service chaiml-llama-8b-multihea-7810-v4 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-llama-8b-multihea-7810-v4 ready after 170.59201645851135s
Pipeline stage MKMLDeployer completed in 171.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9335951805114746s
Received healthy response to inference request in 3.073554754257202s
Received healthy response to inference request in 3.3067188262939453s
Received healthy response to inference request in 3.9843175411224365s
Received healthy response to inference request in 3.3031487464904785s
5 requests
0 failed requests
5th percentile: 2.96158709526062
10th percentile: 2.9895790100097654
20th percentile: 3.0455628395080567
30th percentile: 3.1194735527038575
40th percentile: 3.211311149597168
50th percentile: 3.3031487464904785
60th percentile: 3.304576778411865
70th percentile: 3.3060048103332518
80th percentile: 3.4422385692596436
90th percentile: 3.71327805519104
95th percentile: 3.8487977981567383
99th percentile: 3.957213592529297
mean time: 3.3202670097351072
Pipeline stage StressChecker completed in 18.64s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 2.34s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 2.11s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7810_v4 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihea-7810-v4-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v4-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v4-profiler ready after 170.3907744884491s
Pipeline stage MKMLProfilerDeployer completed in 170.80s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplocdbjk:/code/chaiverse_profiler_1733786027 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplocdbjk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733786027 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733786027/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplocdbjk:/code/chaiverse_profiler_1733788797 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplocdbjk:/code/chaiverse_profiler_1733788798 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplocdbjk --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733788798 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733788798/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v4-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v4-profiler
Service chaiml-llama-8b-multihea-7810-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.01s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.96s
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 chaiml-llama-8b-multihea-7810-v4-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v4-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v4-profiler ready after 140.31733202934265s
Pipeline stage MKMLProfilerDeployer completed in 140.65s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplofsrnt:/code/chaiverse_profiler_1733789628 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplofsrnt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733789628 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733789628/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplofsrnt:/code/chaiverse_profiler_1733792427 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplofsrnt:/code/chaiverse_profiler_1733792428 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplofsrnt --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733792428 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733792428/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v4-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v4-profiler
Service chaiml-llama-8b-multihea-7810-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.00s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v4-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.06s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-llama-8b-multihea-7810-v4-profiler
Waiting for inference service chaiml-llama-8b-multihea-7810-v4-profiler to be ready
Inference service chaiml-llama-8b-multihea-7810-v4-profiler ready after 110.25683069229126s
Pipeline stage MKMLProfilerDeployer completed in 110.62s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplogcnkx:/code/chaiverse_profiler_1733793224 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplogcnkx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733793224 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733793224/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplogcnkx:/code/chaiverse_profiler_1733795993 --namespace tenant-chaiml-guanaco
kubectl exec -it chaiml-llama-8b-mult2d3d50d8ce664942def3f34ff77104c0-deplogcnkx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1733795993 && python profiles.py profile --best_of_n 1 --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 256 --output_tokens 1 --summary /code/chaiverse_profiler_1733795993/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service chaiml-llama-8b-multihea-7810-v4-profiler is running
Tearing down inference service chaiml-llama-8b-multihea-7810-v4-profiler
Service chaiml-llama-8b-multihea-7810-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.94s
Shutdown handler de-registered
chaiml-llama-8b-multihea_7810_v4 status is now inactive due to auto deactivation removed underperforming models