rirv938-llama-8b-multihe_8123

developer_uid: robert_irvine
submission_id: rirv938-llama-8b-multihe_8123_v1
model_name: rirv938-llama-8b-multihe_8123_v1
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2024-11-07T22:15:08+00:00
num_battles: 16231
num_wins: 8233
celo_rating: 1243.42
family_friendly_score: 0.5771999999999999
family_friendly_standard_error: 0.0069862745437035325
submission_type: basic
model_repo: rirv938/llama_8b_multihead_57m_retry
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_8123_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_57m_retry
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-07
win_ratio: 0.5072392335653996
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-8123-v1-mkmlizer
Waiting for job on rirv938-llama-8b-multihe-8123-v1-mkmlizer to finish
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  Version: 0.11.33                                                   ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ║                                                                     ║
rirv938-llama-8b-multihe-8123-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission blend_gerot_2024-10-19: ('http://chaiml-elo-alignment-run-3-v48-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:38184->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
rirv938-llama-8b-multihe-8123-v1-mkmlizer: Downloaded to shared memory in 132.010s
rirv938-llama-8b-multihe-8123-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpf5sm2w19, device:0
rirv938-llama-8b-multihe-8123-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
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-8123-v1-mkmlizer: quantized model in 90.424s
rirv938-llama-8b-multihe-8123-v1-mkmlizer: Processed model rirv938/llama_8b_multihead_57m_retry in 222.435s
rirv938-llama-8b-multihe-8123-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multihe-8123-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multihe-8123-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1
rirv938-llama-8b-multihe-8123-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1/config.json
rirv938-llama-8b-multihe-8123-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1/tokenizer_config.json
rirv938-llama-8b-multihe-8123-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1/special_tokens_map.json
rirv938-llama-8b-multihe-8123-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1/tokenizer.json
rirv938-llama-8b-multihe-8123-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multihe-8123-v1/flywheel_model.0.safetensors
rirv938-llama-8b-multihe-8123-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<01:00,  4.80it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:37,  2.93it/s]
Loading 0:   2%|▏         | 5/291 [00:01<02:10,  2.19it/s]
Loading 0:   3%|▎         | 8/291 [00:02<01:07,  4.21it/s]
Loading 0:   3%|▎         | 9/291 [00:02<01:05,  4.28it/s]
Loading 0:   3%|▎         | 10/291 [00:02<00:57,  4.86it/s]
Loading 0:   4%|▍         | 12/291 [00:03<01:09,  4.04it/s]
Loading 0:   4%|▍         | 13/291 [00:03<01:31,  3.04it/s]
Loading 0:   5%|▍         | 14/291 [00:04<01:55,  2.39it/s]
Loading 0:   6%|▌         | 17/291 [00:04<01:06,  4.13it/s]
Loading 0:   6%|▌         | 18/291 [00:04<01:02,  4.36it/s]
Loading 0:   7%|▋         | 19/291 [00:04<00:54,  4.95it/s]
Loading 0:   7%|▋         | 21/291 [00:05<01:06,  4.07it/s]
Loading 0:   8%|▊         | 22/291 [00:06<01:26,  3.09it/s]
Loading 0:   8%|▊         | 23/291 [00:06<01:49,  2.45it/s]
Loading 0:   9%|▉         | 26/291 [00:07<01:03,  4.17it/s]
Loading 0:   9%|▉         | 27/291 [00:07<01:00,  4.40it/s]
Loading 0:  10%|▉         | 28/291 [00:07<00:53,  4.92it/s]
Loading 0:  10%|█         | 30/291 [00:07<00:43,  6.01it/s]
Loading 0:  11%|█         | 31/291 [00:07<00:43,  5.94it/s]
Loading 0:  11%|█         | 32/291 [00:07<00:39,  6.48it/s]
Loading 0:  11%|█▏        | 33/291 [00:08<00:43,  5.94it/s]
Loading 0:  12%|█▏        | 34/291 [00:08<01:13,  3.52it/s]
Loading 0:  12%|█▏        | 35/291 [00:09<01:35,  2.68it/s]
Loading 0:  12%|█▏        | 36/291 [00:09<01:58,  2.16it/s]
Loading 0:  13%|█▎        | 39/291 [00:10<01:21,  3.09it/s]
Loading 0:  14%|█▎        | 40/291 [00:11<01:36,  2.61it/s]
Loading 0:  14%|█▍        | 41/291 [00:11<01:52,  2.23it/s]
Loading 0:  15%|█▌        | 44/291 [00:12<01:04,  3.84it/s]
Loading 0:  15%|█▌        | 45/291 [00:12<00:59,  4.10it/s]
Loading 0:  16%|█▌        | 46/291 [00:12<00:52,  4.67it/s]
Loading 0:  16%|█▋        | 48/291 [00:12<01:00,  4.03it/s]
Loading 0:  17%|█▋        | 49/291 [00:13<01:18,  3.08it/s]
Loading 0:  17%|█▋        | 50/291 [00:14<01:39,  2.42it/s]
Loading 0:  18%|█▊        | 53/291 [00:14<00:56,  4.18it/s]
Loading 0:  19%|█▊        | 54/291 [00:14<00:53,  4.40it/s]
Loading 0:  19%|█▉        | 55/291 [00:14<00:47,  4.93it/s]
Loading 0:  20%|█▉        | 57/291 [00:15<00:56,  4.15it/s]
Loading 0:  20%|█▉        | 58/291 [00:15<01:14,  3.15it/s]
Loading 0:  20%|██        | 59/291 [00:16<01:33,  2.49it/s]
Loading 0:  21%|██▏       | 62/291 [00:16<00:54,  4.24it/s]
Loading 0:  22%|██▏       | 63/291 [00:17<00:51,  4.46it/s]
Loading 0:  22%|██▏       | 64/291 [00:17<00:45,  5.01it/s]
Loading 0:  23%|██▎       | 66/291 [00:17<00:53,  4.17it/s]
Loading 0:  23%|██▎       | 67/291 [00:18<01:11,  3.15it/s]
Loading 0:  23%|██▎       | 68/291 [00:19<01:29,  2.49it/s]
Loading 0:  24%|██▍       | 71/291 [00:19<00:52,  4.22it/s]
Loading 0:  25%|██▍       | 72/291 [00:19<00:49,  4.45it/s]
Loading 0:  25%|██▌       | 73/291 [00:19<00:43,  5.03it/s]
Loading 0:  25%|██▌       | 74/291 [00:20<01:03,  3.40it/s]
Loading 0:  26%|██▌       | 75/291 [00:20<01:23,  2.57it/s]
Loading 0:  26%|██▋       | 77/291 [00:21<00:57,  3.74it/s]
Loading 0:  27%|██▋       | 78/291 [00:21<00:52,  4.06it/s]
Loading 0:  27%|██▋       | 79/291 [00:21<00:45,  4.68it/s]
Loading 0:  27%|██▋       | 80/291 [00:21<00:44,  4.71it/s]
Loading 0:  28%|██▊       | 81/291 [00:22<01:07,  3.12it/s]
Loading 0:  28%|██▊       | 82/291 [00:22<01:23,  2.51it/s]
Loading 0:  29%|██▊       | 83/291 [00:23<01:39,  2.09it/s]
Loading 0:  30%|██▉       | 86/291 [00:23<00:52,  3.93it/s]
Loading 0:  30%|██▉       | 87/291 [00:23<00:48,  4.21it/s]
Loading 0:  30%|███       | 88/291 [00:23<00:42,  4.83it/s]
Loading 0:  31%|███       | 90/291 [00:24<00:49,  4.07it/s]
Loading 0:  31%|███▏      | 91/291 [00:25<01:04,  3.08it/s]
Loading 0:  32%|███▏      | 92/291 [00:25<01:20,  2.46it/s]
Loading 0:  33%|███▎      | 95/291 [00:25<00:46,  4.21it/s]
Loading 0:  33%|███▎      | 96/291 [00:26<00:43,  4.44it/s]
Loading 0:  33%|███▎      | 97/291 [00:26<00:38,  5.02it/s]
Loading 0:  34%|███▍      | 99/291 [00:26<00:46,  4.17it/s]
Loading 0:  34%|███▍      | 100/291 [00:27<01:00,  3.15it/s]
Loading 0:  35%|███▍      | 101/291 [00:28<01:16,  2.49it/s]
Loading 0:  36%|███▌      | 104/291 [00:28<00:44,  4.24it/s]
Loading 0:  36%|███▌      | 105/291 [00:28<00:41,  4.47it/s]
Loading 0:  36%|███▋      | 106/291 [00:28<00:36,  5.03it/s]
Loading 0:  37%|███▋      | 108/291 [00:29<00:43,  4.18it/s]
Loading 0:  37%|███▋      | 109/291 [00:29<00:57,  3.16it/s]
Loading 0:  38%|███▊      | 110/291 [00:30<01:12,  2.51it/s]
Loading 0:  39%|███▉      | 113/291 [00:30<00:41,  4.27it/s]
Loading 0:  39%|███▉      | 114/291 [00:30<00:39,  4.49it/s]
Loading 0:  40%|███▉      | 115/291 [00:31<00:34,  5.05it/s]
Loading 0:  40%|███▉      | 116/291 [00:31<00:51,  3.39it/s]
Loading 0:  41%|████      | 118/291 [00:31<00:38,  4.52it/s]
Loading 0:  41%|████      | 119/291 [00:32<00:36,  4.72it/s]
Loading 0:  41%|████      | 120/291 [00:32<00:32,  5.28it/s]
Loading 0:  42%|████▏     | 122/291 [00:32<00:40,  4.22it/s]
Loading 0:  43%|████▎     | 125/291 [00:33<00:36,  4.54it/s]
Loading 0:  43%|████▎     | 126/291 [00:33<00:47,  3.46it/s]
Loading 0:  44%|████▎     | 127/291 [00:34<01:00,  2.71it/s]
Loading 0:  45%|████▍     | 130/291 [00:34<00:36,  4.36it/s]
Loading 0:  45%|████▌     | 131/291 [00:35<00:35,  4.56it/s]
Loading 0:  45%|████▌     | 132/291 [00:35<00:31,  5.09it/s]
Loading 0:  46%|████▌     | 133/291 [00:35<00:31,  5.05it/s]
Loading 0:  46%|████▌     | 134/291 [00:35<00:46,  3.36it/s]
Loading 0:  46%|████▋     | 135/291 [00:36<01:01,  2.54it/s]
Loading 0:  47%|████▋     | 138/291 [00:37<00:44,  3.42it/s]
Loading 0:  48%|████▊     | 139/291 [00:37<00:53,  2.82it/s]
Loading 0:  48%|████▊     | 140/291 [00:38<01:04,  2.34it/s]
Loading 0:  49%|████▉     | 143/291 [00:38<00:37,  3.93it/s]
Loading 0:  49%|████▉     | 144/291 [00:38<00:35,  4.17it/s]
Loading 0:  50%|████▉     | 145/291 [00:39<00:30,  4.71it/s]
Loading 0:  51%|█████     | 147/291 [00:39<00:35,  4.05it/s]
Loading 0:  51%|█████     | 148/291 [00:40<00:45,  3.11it/s]
Loading 0:  51%|█████     | 149/291 [00:40<00:57,  2.47it/s]
Loading 0:  52%|█████▏    | 152/291 [00:41<00:32,  4.25it/s]
Loading 0:  53%|█████▎    | 153/291 [00:41<00:30,  4.47it/s]
Loading 0:  53%|█████▎    | 154/291 [00:41<00:27,  5.02it/s]
Loading 0:  54%|█████▎    | 156/291 [00:41<00:32,  4.19it/s]
Loading 0:  54%|█████▍    | 157/291 [00:42<00:42,  3.16it/s]
Loading 0:  54%|█████▍    | 158/291 [00:43<00:53,  2.48it/s]
Loading 0:  55%|█████▌    | 161/291 [00:43<00:31,  4.16it/s]
Loading 0:  56%|█████▌    | 162/291 [00:43<00:29,  4.39it/s]
Loading 0:  56%|█████▌    | 163/291 [00:43<00:25,  4.95it/s]
Loading 0:  57%|█████▋    | 165/291 [00:44<00:30,  4.16it/s]
Loading 0:  57%|█████▋    | 166/291 [00:44<00:39,  3.15it/s]
Loading 0:  57%|█████▋    | 167/291 [00:45<00:49,  2.49it/s]
Loading 0:  58%|█████▊    | 170/291 [00:45<00:28,  4.22it/s]
Loading 0:  59%|█████▉    | 171/291 [00:46<00:26,  4.45it/s]
Loading 0:  59%|█████▉    | 172/291 [00:46<00:23,  4.99it/s]
Loading 0:  60%|█████▉    | 174/291 [00:46<00:28,  4.18it/s]
Loading 0:  60%|██████    | 175/291 [00:47<00:36,  3.16it/s]
Loading 0:  60%|██████    | 176/291 [00:48<00:45,  2.51it/s]
Loading 0:  62%|██████▏   | 179/291 [00:48<00:26,  4.25it/s]
Loading 0:  62%|██████▏   | 180/291 [00:48<00:24,  4.48it/s]
Loading 0:  62%|██████▏   | 181/291 [00:48<00:21,  5.05it/s]
Loading 0:  63%|██████▎   | 183/291 [00:48<00:17,  6.11it/s]
Loading 0:  63%|██████▎   | 184/291 [00:48<00:17,  5.99it/s]
Loading 0:  64%|██████▎   | 185/291 [00:49<00:16,  6.46it/s]
Loading 0:  64%|██████▍   | 186/291 [00:49<00:16,  6.18it/s]
Loading 0:  64%|██████▍   | 187/291 [00:49<00:28,  3.60it/s]
Loading 0:  65%|██████▍   | 188/291 [00:50<00:37,  2.73it/s]
Loading 0:  65%|██████▍   | 189/291 [00:51<00:45,  2.22it/s]
Loading 0:  66%|██████▌   | 192/291 [00:51<00:31,  3.19it/s]
Loading 0:  66%|██████▋   | 193/291 [00:52<00:36,  2.69it/s]
Loading 0:  67%|██████▋   | 194/291 [00:52<00:42,  2.28it/s]
Loading 0:  68%|██████▊   | 197/291 [00:53<00:24,  3.87it/s]
Loading 0:  68%|██████▊   | 198/291 [00:53<00:22,  4.12it/s]
Loading 0:  68%|██████▊   | 199/291 [00:53<00:19,  4.66it/s]
Loading 0:  69%|██████▉   | 201/291 [00:54<00:22,  4.04it/s]
Loading 0:  69%|██████▉   | 202/291 [00:54<00:28,  3.10it/s]
Loading 0:  70%|██████▉   | 203/291 [00:55<00:35,  2.46it/s]
Loading 0:  71%|███████   | 206/291 [00:55<00:20,  4.18it/s]
Loading 0:  71%|███████   | 207/291 [00:55<00:18,  4.42it/s]
Loading 0:  71%|███████▏  | 208/291 [00:55<00:16,  4.97it/s]
Loading 0:  72%|███████▏  | 210/291 [00:56<00:19,  4.18it/s]
Loading 0:  73%|███████▎  | 211/291 [00:57<00:25,  3.16it/s]
Loading 0:  73%|███████▎  | 212/291 [00:57<00:31,  2.52it/s]
Loading 0:  74%|███████▍  | 215/291 [00:57<00:17,  4.26it/s]
Loading 0:  74%|███████▍  | 216/291 [00:58<00:16,  4.49it/s]
Loading 0:  75%|███████▍  | 217/291 [00:58<00:14,  5.04it/s]
Loading 0:  75%|███████▌  | 219/291 [00:58<00:17,  4.21it/s]
Loading 0:  76%|███████▌  | 220/291 [00:59<00:22,  3.18it/s]
Loading 0:  76%|███████▌  | 221/291 [01:00<00:27,  2.52it/s]
Loading 0:  77%|███████▋  | 224/291 [01:00<00:15,  4.25it/s]
Loading 0:  77%|███████▋  | 225/291 [01:00<00:14,  4.47it/s]
Loading 0:  78%|███████▊  | 226/291 [01:00<00:12,  5.00it/s]
Loading 0:  78%|███████▊  | 227/291 [01:01<00:18,  3.38it/s]
Loading 0:  78%|███████▊  | 228/291 [01:01<00:24,  2.57it/s]
Loading 0:  79%|███████▉  | 230/291 [01:02<00:16,  3.68it/s]
Loading 0:  79%|███████▉  | 231/291 [01:02<00:14,  4.01it/s]
Loading 0:  80%|███████▉  | 232/291 [01:02<00:12,  4.66it/s]
Loading 0:  80%|████████  | 233/291 [01:02<00:11,  4.85it/s]
Loading 0:  80%|████████  | 234/291 [01:03<00:17,  3.19it/s]
Loading 0:  81%|████████▏ | 237/291 [01:03<00:13,  3.96it/s]
Loading 0:  82%|████████▏ | 238/291 [01:04<00:17,  3.09it/s]
Loading 0:  82%|████████▏ | 239/291 [01:05<00:20,  2.48it/s]
Loading 0:  83%|████████▎ | 242/291 [01:05<00:11,  4.14it/s]
Loading 0:  84%|████████▎ | 243/291 [01:05<00:10,  4.37it/s]
Loading 0:  84%|████████▍ | 244/291 [01:05<00:09,  4.90it/s]
Loading 0:  85%|████████▍ | 246/291 [01:06<00:10,  4.14it/s]
Loading 0:  85%|████████▍ | 247/291 [01:06<00:13,  3.15it/s]
Loading 0:  85%|████████▌ | 248/291 [01:07<00:17,  2.50it/s]
Loading 0:  86%|████████▋ | 251/291 [01:07<00:09,  4.23it/s]
Loading 0:  87%|████████▋ | 252/291 [01:07<00:08,  4.42it/s]
Loading 0:  87%|████████▋ | 253/291 [01:07<00:07,  4.94it/s]
Loading 0:  88%|████████▊ | 255/291 [01:08<00:08,  4.16it/s]
Loading 0:  88%|████████▊ | 256/291 [01:09<00:11,  3.16it/s]
Loading 0:  88%|████████▊ | 257/291 [01:09<00:13,  2.50it/s]
Loading 0:  89%|████████▉ | 260/291 [01:10<00:07,  4.24it/s]
Loading 0:  90%|████████▉ | 261/291 [01:10<00:06,  4.47it/s]
Loading 0:  90%|█████████ | 262/291 [01:10<00:05,  5.02it/s]
Loading 0:  91%|█████████ | 264/291 [01:10<00:06,  4.19it/s]
Loading 0:  91%|█████████ | 265/291 [01:11<00:08,  3.18it/s]
Loading 0:  91%|█████████▏| 266/291 [01:12<00:09,  2.51it/s]
Loading 0:  92%|█████████▏| 269/291 [01:12<00:05,  4.25it/s]
Loading 0:  93%|█████████▎| 270/291 [01:12<00:04,  4.47it/s]
Loading 0:  93%|█████████▎| 271/291 [01:12<00:04,  4.99it/s]
Loading 0:  94%|█████████▍| 273/291 [01:13<00:04,  4.18it/s]
Loading 0:  94%|█████████▍| 274/291 [01:13<00:05,  3.16it/s]
Loading 0:  95%|█████████▍| 275/291 [01:14<00:06,  2.50it/s]
Loading 0:  96%|█████████▌| 278/291 [01:14<00:03,  4.24it/s]
Loading 0:  96%|█████████▌| 279/291 [01:14<00:02,  4.47it/s]
Loading 0:  96%|█████████▌| 280/291 [01:15<00:02,  4.98it/s]
Loading 0:  97%|█████████▋| 281/291 [01:15<00:02,  3.38it/s]
Loading 0:  97%|█████████▋| 283/291 [01:15<00:01,  4.53it/s]
Loading 0:  98%|█████████▊| 284/291 [01:16<00:01,  4.73it/s]
Loading 0:  98%|█████████▊| 285/291 [01:16<00:01,  5.25it/s]
Loading 0:  98%|█████████▊| 286/291 [01:16<00:00,  5.33it/s]
Loading 0:  99%|█████████▊| 287/291 [01:16<00:01,  3.34it/s]
Loading 0:  99%|█████████▉| 288/291 [01:17<00:01,  2.48it/s]
                                                            
Job rirv938-llama-8b-multihe-8123-v1-mkmlizer completed after 247.41s with status: succeeded
Stopping job with name rirv938-llama-8b-multihe-8123-v1-mkmlizer
Pipeline stage MKMLizer completed in 247.96s
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 rirv938-llama-8b-multihe-8123-v1
Waiting for inference service rirv938-llama-8b-multihe-8123-v1 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
Inference service rirv938-llama-8b-multihe-8123-v1 ready after 170.58933663368225s
Pipeline stage MKMLDeployer completed in 171.16s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.390606164932251s
Received healthy response to inference request in 3.189307689666748s
Received healthy response to inference request in 2.9773733615875244s
Received healthy response to inference request in 1.2245910167694092s
Received healthy response to inference request in 3.1692922115325928s
5 requests
0 failed requests
5th percentile: 1.4577940464019776
10th percentile: 1.6909970760345459
20th percentile: 2.1574031352996825
30th percentile: 2.5079596042633057
40th percentile: 2.742666482925415
50th percentile: 2.9773733615875244
60th percentile: 3.054140901565552
70th percentile: 3.1309084415435793
80th percentile: 3.1732953071594237
90th percentile: 3.181301498413086
95th percentile: 3.185304594039917
99th percentile: 3.188507070541382
mean time: 2.590234088897705
Pipeline stage StressChecker completed in 14.43s
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 6.34s
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 2.94s
Shutdown handler de-registered
rirv938-llama-8b-multihe_8123_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multihe-8123-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-8123-v1-profiler to be ready
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Retrying (%r) after connection broken by '%r': %s
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-8123-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 1.61s
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-8123-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-8123-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-8123-v1-profiler ready after 70.17026710510254s
Pipeline stage MKMLProfilerDeployer completed in 70.47s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mulbf74a76d7c7e3c504b5b3e52967e981d-deplockrmz:/code/chaiverse_profiler_1731025508 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mulbf74a76d7c7e3c504b5b3e52967e981d-deplockrmz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731025508 && 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_1731025508/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mulbf74a76d7c7e3c504b5b3e52967e981d-deplockrmz:/code/chaiverse_profiler_1731027588 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mulbf74a76d7c7e3c504b5b3e52967e981d-deplockrmz --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731027588 && 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_1731027588/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-8123-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-8123-v1-profiler
Service rirv938-llama-8b-multihe-8123-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.78s
Shutdown handler de-registered
rirv938-llama-8b-multihe_8123_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-multihe_8123_v1 status is now torndown due to DeploymentManager action