rirv938-llama-8b-multihe_9554

developer_uid: robert_irvine
submission_id: rirv938-llama-8b-multihe_9554_v1
model_name: rirv938-llama-8b-multihe_9554_v1
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2024-11-14T18:18:54+00:00
num_battles: 20188
num_wins: 10455
celo_rating: 1257.78
family_friendly_score: 0.5788
family_friendly_standard_error: 0.006982700910106346
submission_type: basic
model_repo: rirv938/llama_8b_multihead_204m_preference
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
display_name: rirv938-llama-8b-multihe_9554_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_204m_preference
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-14
win_ratio: 0.5178819100455716
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': False}
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 rirv938-llama-8b-multihe-9554-v1-mkmlizer
Waiting for job on rirv938-llama-8b-multihe-9554-v1-mkmlizer to finish
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-9554-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-multihe-9554-v1-mkmlizer: Downloaded to shared memory in 209.188s
rirv938-llama-8b-multihe-9554-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpizyw2kmv, device:0
rirv938-llama-8b-multihe-9554-v1-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
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-multihe-9554-v1-mkmlizer: quantized model in 87.178s
rirv938-llama-8b-multihe-9554-v1-mkmlizer: Processed model rirv938/llama_8b_multihead_204m_preference in 296.367s
rirv938-llama-8b-multihe-9554-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multihe-9554-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multihe-9554-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1
rirv938-llama-8b-multihe-9554-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1/config.json
rirv938-llama-8b-multihe-9554-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1/special_tokens_map.json
rirv938-llama-8b-multihe-9554-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1/tokenizer_config.json
rirv938-llama-8b-multihe-9554-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1/tokenizer.json
rirv938-llama-8b-multihe-9554-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multihe-9554-v1/flywheel_model.0.safetensors
rirv938-llama-8b-multihe-9554-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:58,  4.95it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:35,  3.01it/s]
Loading 0:   2%|▏         | 5/291 [00:01<02:09,  2.20it/s]
Loading 0:   3%|▎         | 8/291 [00:02<01:07,  4.22it/s]
Loading 0:   3%|▎         | 9/291 [00:02<01:05,  4.30it/s]
Loading 0:   3%|▎         | 10/291 [00:02<00:57,  4.90it/s]
Loading 0:   4%|▍         | 12/291 [00:03<01:08,  4.09it/s]
Loading 0:   4%|▍         | 13/291 [00:03<01:30,  3.08it/s]
Loading 0:   5%|▍         | 14/291 [00:04<01:53,  2.45it/s]
Loading 0:   6%|▌         | 17/291 [00:04<01:05,  4.21it/s]
Loading 0:   6%|▌         | 18/291 [00:04<01:00,  4.50it/s]
Loading 0:   7%|▋         | 21/291 [00:05<01:00,  4.43it/s]
Loading 0:   8%|▊         | 22/291 [00:06<01:18,  3.43it/s]
Loading 0:   8%|▊         | 23/291 [00:06<01:38,  2.71it/s]
Loading 0:   9%|▉         | 26/291 [00:06<01:00,  4.36it/s]
Loading 0:   9%|▉         | 27/291 [00:07<00:57,  4.56it/s]
Loading 0:  10%|▉         | 29/291 [00:07<00:43,  5.97it/s]
Loading 0:  10%|█         | 30/291 [00:07<00:44,  5.91it/s]
Loading 0:  11%|█         | 31/291 [00:07<00:44,  5.88it/s]
Loading 0:  11%|█         | 32/291 [00:07<00:40,  6.33it/s]
Loading 0:  11%|█▏        | 33/291 [00:07<00:42,  6.04it/s]
Loading 0:  12%|█▏        | 34/291 [00:08<01:11,  3.59it/s]
Loading 0:  12%|█▏        | 35/291 [00:09<01:33,  2.74it/s]
Loading 0:  12%|█▏        | 36/291 [00:09<01:55,  2.22it/s]
Loading 0:  13%|█▎        | 39/291 [00:10<01:18,  3.19it/s]
Loading 0:  14%|█▎        | 40/291 [00:10<01:33,  2.68it/s]
Loading 0:  14%|█▍        | 41/291 [00:11<01:50,  2.27it/s]
Loading 0:  15%|█▌        | 44/291 [00:11<01:03,  3.89it/s]
Loading 0:  15%|█▌        | 45/291 [00:11<00:59,  4.14it/s]
Loading 0:  16%|█▌        | 46/291 [00:12<00:51,  4.72it/s]
Loading 0:  16%|█▋        | 48/291 [00:12<00:59,  4.10it/s]
Loading 0:  17%|█▋        | 49/291 [00:13<01:17,  3.14it/s]
Loading 0:  17%|█▋        | 50/291 [00:13<01:36,  2.50it/s]
Loading 0:  18%|█▊        | 53/291 [00:14<00:55,  4.31it/s]
Loading 0:  19%|█▊        | 54/291 [00:14<00:52,  4.53it/s]
Loading 0:  20%|█▉        | 57/291 [00:15<00:52,  4.44it/s]
Loading 0:  20%|█▉        | 58/291 [00:15<01:07,  3.44it/s]
Loading 0:  20%|██        | 59/291 [00:16<01:25,  2.72it/s]
Loading 0:  21%|██▏       | 62/291 [00:16<00:52,  4.40it/s]
Loading 0:  22%|██▏       | 63/291 [00:16<00:49,  4.61it/s]
Loading 0:  23%|██▎       | 66/291 [00:17<00:50,  4.48it/s]
Loading 0:  23%|██▎       | 67/291 [00:17<01:04,  3.48it/s]
Loading 0:  23%|██▎       | 68/291 [00:18<01:20,  2.78it/s]
Loading 0:  24%|██▍       | 71/291 [00:18<00:49,  4.42it/s]
Loading 0:  25%|██▍       | 72/291 [00:18<00:47,  4.62it/s]
Loading 0:  25%|██▌       | 74/291 [00:19<00:56,  3.85it/s]
Loading 0:  26%|██▌       | 75/291 [00:20<01:13,  2.96it/s]
Loading 0:  26%|██▋       | 77/291 [00:20<00:53,  3.97it/s]
Loading 0:  27%|██▋       | 78/291 [00:20<00:50,  4.24it/s]
Loading 0:  27%|██▋       | 80/291 [00:20<00:42,  5.01it/s]
Loading 0:  28%|██▊       | 81/291 [00:21<00:58,  3.56it/s]
Loading 0:  28%|██▊       | 82/291 [00:22<01:13,  2.85it/s]
Loading 0:  29%|██▊       | 83/291 [00:22<01:29,  2.33it/s]
Loading 0:  30%|██▉       | 86/291 [00:23<00:50,  4.08it/s]
Loading 0:  30%|██▉       | 87/291 [00:23<00:47,  4.33it/s]
Loading 0:  30%|███       | 88/291 [00:23<00:41,  4.94it/s]
Loading 0:  31%|███       | 90/291 [00:23<00:48,  4.18it/s]
Loading 0:  31%|███▏      | 91/291 [00:24<01:03,  3.17it/s]
Loading 0:  32%|███▏      | 92/291 [00:25<01:18,  2.53it/s]
Loading 0:  33%|███▎      | 95/291 [00:25<00:45,  4.31it/s]
Loading 0:  33%|███▎      | 96/291 [00:25<00:42,  4.54it/s]
Loading 0:  34%|███▍      | 99/291 [00:26<00:43,  4.45it/s]
Loading 0:  34%|███▍      | 100/291 [00:26<00:55,  3.46it/s]
Loading 0:  35%|███▍      | 101/291 [00:27<01:08,  2.76it/s]
Loading 0:  36%|███▌      | 104/291 [00:27<00:42,  4.42it/s]
Loading 0:  36%|███▌      | 105/291 [00:27<00:40,  4.62it/s]
Loading 0:  37%|███▋      | 108/291 [00:28<00:40,  4.50it/s]
Loading 0:  37%|███▋      | 109/291 [00:29<00:51,  3.51it/s]
Loading 0:  38%|███▊      | 110/291 [00:29<01:04,  2.79it/s]
Loading 0:  39%|███▉      | 113/291 [00:29<00:40,  4.42it/s]
Loading 0:  39%|███▉      | 114/291 [00:30<00:38,  4.62it/s]
Loading 0:  40%|███▉      | 115/291 [00:30<00:34,  5.12it/s]
Loading 0:  40%|███▉      | 116/291 [00:30<00:49,  3.51it/s]
Loading 0:  41%|████      | 118/291 [00:31<00:37,  4.66it/s]
Loading 0:  41%|████      | 119/291 [00:31<00:35,  4.88it/s]
Loading 0:  42%|████▏     | 122/291 [00:31<00:36,  4.60it/s]
Loading 0:  43%|████▎     | 125/291 [00:32<00:34,  4.81it/s]
Loading 0:  43%|████▎     | 126/291 [00:33<00:44,  3.71it/s]
Loading 0:  44%|████▎     | 127/291 [00:33<00:55,  2.94it/s]
Loading 0:  45%|████▍     | 130/291 [00:33<00:35,  4.55it/s]
Loading 0:  45%|████▌     | 131/291 [00:34<00:33,  4.73it/s]
Loading 0:  45%|████▌     | 132/291 [00:34<00:30,  5.25it/s]
Loading 0:  46%|████▌     | 133/291 [00:34<00:29,  5.38it/s]
Loading 0:  46%|████▌     | 134/291 [00:34<00:44,  3.52it/s]
Loading 0:  46%|████▋     | 135/291 [00:35<00:58,  2.66it/s]
Loading 0:  47%|████▋     | 138/291 [00:36<00:43,  3.55it/s]
Loading 0:  48%|████▊     | 139/291 [00:36<00:52,  2.91it/s]
Loading 0:  48%|████▊     | 140/291 [00:37<01:01,  2.44it/s]
Loading 0:  49%|████▉     | 143/291 [00:37<00:36,  4.08it/s]
Loading 0:  49%|████▉     | 144/291 [00:37<00:33,  4.33it/s]
Loading 0:  50%|████▉     | 145/291 [00:37<00:29,  4.92it/s]
Loading 0:  51%|█████     | 147/291 [00:38<00:34,  4.18it/s]
Loading 0:  51%|█████     | 148/291 [00:39<00:44,  3.18it/s]
Loading 0:  51%|█████     | 149/291 [00:39<00:56,  2.54it/s]
Loading 0:  52%|█████▏    | 152/291 [00:39<00:32,  4.30it/s]
Loading 0:  53%|█████▎    | 153/291 [00:40<00:30,  4.53it/s]
Loading 0:  53%|█████▎    | 154/291 [00:40<00:26,  5.12it/s]
Loading 0:  54%|█████▎    | 156/291 [00:40<00:31,  4.28it/s]
Loading 0:  54%|█████▍    | 157/291 [00:41<00:41,  3.24it/s]
Loading 0:  54%|█████▍    | 158/291 [00:42<00:51,  2.58it/s]
Loading 0:  55%|█████▌    | 161/291 [00:42<00:29,  4.35it/s]
Loading 0:  56%|█████▌    | 162/291 [00:42<00:28,  4.58it/s]
Loading 0:  56%|█████▌    | 163/291 [00:42<00:24,  5.16it/s]
Loading 0:  57%|█████▋    | 165/291 [00:43<00:29,  4.30it/s]
Loading 0:  57%|█████▋    | 166/291 [00:43<00:38,  3.24it/s]
Loading 0:  57%|█████▋    | 167/291 [00:44<00:48,  2.57it/s]
Loading 0:  58%|█████▊    | 170/291 [00:44<00:27,  4.34it/s]
Loading 0:  59%|█████▉    | 171/291 [00:44<00:26,  4.57it/s]
Loading 0:  59%|█████▉    | 172/291 [00:44<00:23,  5.13it/s]
Loading 0:  60%|█████▉    | 174/291 [00:45<00:27,  4.28it/s]
Loading 0:  60%|██████    | 175/291 [00:46<00:35,  3.25it/s]
Loading 0:  60%|██████    | 176/291 [00:46<00:44,  2.59it/s]
Loading 0:  62%|██████▏   | 179/291 [00:46<00:25,  4.37it/s]
Loading 0:  62%|██████▏   | 180/291 [00:47<00:24,  4.59it/s]
Loading 0:  63%|██████▎   | 182/291 [00:47<00:17,  6.06it/s]
Loading 0:  63%|██████▎   | 183/291 [00:47<00:17,  6.00it/s]
Loading 0:  63%|██████▎   | 184/291 [00:47<00:18,  5.94it/s]
Loading 0:  64%|██████▎   | 185/291 [00:47<00:16,  6.51it/s]
Loading 0:  64%|██████▍   | 186/291 [00:47<00:16,  6.29it/s]
Loading 0:  64%|██████▍   | 187/291 [00:48<00:28,  3.65it/s]
Loading 0:  65%|██████▍   | 188/291 [00:49<00:37,  2.77it/s]
Loading 0:  65%|██████▍   | 189/291 [00:49<00:45,  2.26it/s]
Loading 0:  66%|██████▌   | 192/291 [00:50<00:30,  3.25it/s]
Loading 0:  66%|██████▋   | 193/291 [00:50<00:35,  2.74it/s]
Loading 0:  67%|██████▋   | 194/291 [00:51<00:41,  2.31it/s]
Loading 0:  68%|██████▊   | 197/291 [00:51<00:23,  3.93it/s]
Loading 0:  68%|██████▊   | 198/291 [00:51<00:22,  4.19it/s]
Loading 0:  68%|██████▊   | 199/291 [00:52<00:19,  4.74it/s]
Loading 0:  69%|██████▉   | 201/291 [00:52<00:21,  4.11it/s]
Loading 0:  69%|██████▉   | 202/291 [00:53<00:28,  3.17it/s]
Loading 0:  70%|██████▉   | 203/291 [00:53<00:34,  2.55it/s]
Loading 0:  71%|███████   | 206/291 [00:54<00:19,  4.31it/s]
Loading 0:  71%|███████   | 207/291 [00:54<00:18,  4.54it/s]
Loading 0:  71%|███████▏  | 208/291 [00:54<00:16,  5.03it/s]
Loading 0:  72%|███████▏  | 210/291 [00:54<00:19,  4.25it/s]
Loading 0:  73%|███████▎  | 211/291 [00:55<00:24,  3.23it/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,  4.59it/s]
Loading 0:  75%|███████▍  | 217/291 [00:56<00:14,  5.16it/s]
Loading 0:  75%|███████▌  | 219/291 [00:57<00:16,  4.31it/s]
Loading 0:  76%|███████▌  | 220/291 [00:57<00:21,  3.27it/s]
Loading 0:  76%|███████▌  | 221/291 [00:58<00:26,  2.60it/s]
Loading 0:  77%|███████▋  | 224/291 [00:58<00:15,  4.38it/s]
Loading 0:  77%|███████▋  | 225/291 [00:58<00:14,  4.61it/s]
Loading 0:  78%|███████▊  | 226/291 [00:58<00:12,  5.19it/s]
Loading 0:  78%|███████▊  | 227/291 [00:59<00:18,  3.51it/s]
Loading 0:  78%|███████▊  | 228/291 [01:00<00:23,  2.67it/s]
Loading 0:  79%|███████▉  | 230/291 [01:00<00:16,  3.80it/s]
Loading 0:  79%|███████▉  | 231/291 [01:00<00:14,  4.12it/s]
Loading 0:  80%|███████▉  | 232/291 [01:00<00:12,  4.78it/s]
Loading 0:  80%|████████  | 233/291 [01:00<00:11,  5.08it/s]
Loading 0:  80%|████████  | 234/291 [01:01<00:17,  3.32it/s]
Loading 0:  81%|████████▏ | 237/291 [01:02<00:13,  4.10it/s]
Loading 0:  82%|████████▏ | 238/291 [01:02<00:16,  3.20it/s]
Loading 0:  82%|████████▏ | 239/291 [01:03<00:20,  2.57it/s]
Loading 0:  83%|████████▎ | 242/291 [01:03<00:11,  4.29it/s]
Loading 0:  84%|████████▎ | 243/291 [01:03<00:10,  4.52it/s]
Loading 0:  84%|████████▍ | 244/291 [01:03<00:09,  5.08it/s]
Loading 0:  85%|████████▍ | 246/291 [01:04<00:10,  4.29it/s]
Loading 0:  85%|████████▍ | 247/291 [01:04<00:13,  3.27it/s]
Loading 0:  85%|████████▌ | 248/291 [01:05<00:16,  2.60it/s]
Loading 0:  86%|████████▋ | 251/291 [01:05<00:09,  4.40it/s]
Loading 0:  87%|████████▋ | 252/291 [01:05<00:08,  4.62it/s]
Loading 0:  87%|████████▋ | 253/291 [01:06<00:07,  5.22it/s]
Loading 0:  88%|████████▊ | 255/291 [01:06<00:08,  4.33it/s]
Loading 0:  88%|████████▊ | 256/291 [01:07<00:10,  3.27it/s]
Loading 0:  88%|████████▊ | 257/291 [01:07<00:13,  2.60it/s]
Loading 0:  89%|████████▉ | 260/291 [01:08<00:07,  4.40it/s]
Loading 0:  90%|████████▉ | 261/291 [01:08<00:06,  4.62it/s]
Loading 0:  90%|█████████ | 262/291 [01:08<00:05,  5.21it/s]
Loading 0:  91%|█████████ | 264/291 [01:08<00:06,  4.34it/s]
Loading 0:  91%|█████████ | 265/291 [01:09<00:07,  3.26it/s]
Loading 0:  91%|█████████▏| 266/291 [01:10<00:09,  2.61it/s]
Loading 0:  92%|█████████▏| 269/291 [01:10<00:04,  4.41it/s]
Loading 0:  93%|█████████▎| 270/291 [01:10<00:04,  4.64it/s]
Loading 0:  93%|█████████▎| 271/291 [01:10<00:03,  5.22it/s]
Loading 0:  94%|█████████▍| 273/291 [01:11<00:04,  4.34it/s]
Loading 0:  94%|█████████▍| 274/291 [01:11<00:05,  3.28it/s]
Loading 0:  95%|█████████▍| 275/291 [01:12<00:06,  2.59it/s]
Loading 0:  96%|█████████▌| 278/291 [01:12<00:02,  4.37it/s]
Loading 0:  96%|█████████▌| 279/291 [01:12<00:02,  4.60it/s]
Loading 0:  96%|█████████▌| 280/291 [01:12<00:02,  5.18it/s]
Loading 0:  97%|█████████▋| 281/291 [01:13<00:02,  3.50it/s]
Loading 0:  97%|█████████▋| 283/291 [01:13<00:01,  4.68it/s]
Loading 0:  98%|█████████▊| 284/291 [01:13<00:01,  4.91it/s]
Loading 0:  98%|█████████▊| 285/291 [01:13<00:01,  5.59it/s]
Loading 0:  98%|█████████▊| 286/291 [01:14<00:00,  5.81it/s]
Loading 0:  99%|█████████▊| 287/291 [01:14<00:01,  3.54it/s]
Loading 0:  99%|█████████▉| 288/291 [01:15<00:01,  2.59it/s]
                                                            
Job rirv938-llama-8b-multihe-9554-v1-mkmlizer completed after 320.13s with status: succeeded
Stopping job with name rirv938-llama-8b-multihe-9554-v1-mkmlizer
Pipeline stage MKMLizer completed in 320.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-multihe-9554-v1
Waiting for inference service rirv938-llama-8b-multihe-9554-v1 to be ready
Failed to get response for submission jic062-dpo-v3-0-nemo_v1: ('http://jic062-dpo-v3-0-nemo-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
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 rirv938-llama-8b-multihe-9554-v1 ready after 200.72153520584106s
Pipeline stage MKMLDeployer completed in 201.65s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.26226544380188s
Received healthy response to inference request in 2.0086376667022705s
Received healthy response to inference request in 1.95157790184021s
Received healthy response to inference request in 3.028712034225464s
Received healthy response to inference request in 3.0148203372955322s
5 requests
0 failed requests
5th percentile: 1.9629898548126221
10th percentile: 1.9744018077850343
20th percentile: 1.9972257137298584
30th percentile: 2.2098742008209227
40th percentile: 2.6123472690582275
50th percentile: 3.0148203372955322
60th percentile: 3.020377016067505
70th percentile: 3.0259336948394777
80th percentile: 3.2754227161407474
90th percentile: 3.7688440799713137
95th percentile: 4.015554761886596
99th percentile: 4.212923307418823
mean time: 2.8532026767730714
Pipeline stage StressChecker completed in 16.12s
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 2.63s
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 2.99s
Shutdown handler de-registered
rirv938-llama-8b-multihe_9554_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 0.16s
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 rirv938-llama-8b-multihe-9554-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-9554-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-9554-v1-profiler ready after 210.50992608070374s
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/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplor5nzz:/code/chaiverse_profiler_1731609125 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplor5nzz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731609125 && 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_1731609125/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplor5nzz:/code/chaiverse_profiler_1731611899 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplor5nzz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731611899 && 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_1731611899/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-9554-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-9554-v1-profiler
Service rirv938-llama-8b-multihe-9554-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.19s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-9554-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.17s
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 rirv938-llama-8b-multihe-9554-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-9554-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-9554-v1-profiler ready after 200.55423879623413s
Pipeline stage MKMLProfilerDeployer completed in 200.90s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplox4zbz:/code/chaiverse_profiler_1731612740 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplox4zbz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731612740 && 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_1731612740/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplox4zbz:/code/chaiverse_profiler_1731615524 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplox4zbz:/code/chaiverse_profiler_1731615524 --namespace tenant-chaiml-guanaco
clean up pipeline due to error=ISVCScriptError('Command failed with error: Defaulted container "kserve-container" out of: kserve-container, queue-proxy\nerror: unable to upgrade connection: container not found ("kserve-container")\n, output: ')
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-9554-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-9554-v1-profiler
Service rirv938-llama-8b-multihe-9554-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.06s
Shutdown handler de-registered
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-9554-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.33s
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 rirv938-llama-8b-multihe-9554-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-9554-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-9554-v1-profiler ready after 50.16007685661316s
Pipeline stage MKMLProfilerDeployer completed in 50.63s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplozx7bb:/code/chaiverse_profiler_1731615611 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplozx7bb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731615611 && 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_1731615611/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplozx7bb:/code/chaiverse_profiler_1731618386 --namespace tenant-chaiml-guanaco
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplozx7bb:/code/chaiverse_profiler_1731618386 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul48cb841d838ce52bf5432b21bb513b3a-deplozx7bb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731618386 && 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_1731618386/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-9554-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-9554-v1-profiler
Service rirv938-llama-8b-multihe-9554-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.05s
Shutdown handler de-registered
rirv938-llama-8b-multihe_9554_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rirv938-llama-8b-multihe_9554_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
Checking if service rirv938-llama-8b-multihe-9554-v1 is running
Tearing down inference service rirv938-llama-8b-multihe-9554-v1
Service rirv938-llama-8b-multihe-9554-v1 has been torndown
Pipeline stage MKMLDeleter completed in 2.49s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key rirv938-llama-8b-multihe-9554-v1/config.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-multihe-9554-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-multihe-9554-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-multihe-9554-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key rirv938-llama-8b-multihe-9554-v1/tokenizer_config.json from bucket guanaco-mkml-models
admin requested tearing down of sao10k-mn-12b-lyra-v4a1_v30
Pipeline stage MKMLModelDeleter completed in 3.15s
Shutdown handler not registered because Python interpreter is not running in the main thread
Shutdown handler de-registered
run pipeline %s
run pipeline %s
rirv938-llama-8b-multihe_9554_v1 status is now torndown due to DeploymentManager action
run pipeline stage %s