developer_uid: robert_irvine
submission_id: rirv938-llama-8b-multihe_6884_v1
model_name: rirv938-llama-8b-multihe_6884_v1
model_group: rirv938/llama_8b_multihe
status: torndown
timestamp: 2024-11-14T18:28:03+00:00
num_battles: 18722
num_wins: 9290
celo_rating: 1243.65
family_friendly_score: 0.5784
family_friendly_standard_error: 0.006983601363193635
submission_type: basic
model_repo: rirv938/llama_8b_multihead_204m_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_6884_v1
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_multihead_204m_retry
model_size: 8B
ranking_group: single
us_pacific_date: 2024-11-14
win_ratio: 0.4962076701207136
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-6884-v1-mkmlizer
Waiting for job on rirv938-llama-8b-multihe-6884-v1-mkmlizer to finish
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ _____ __ __ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ /___/ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ Version: 0.11.12 ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ belonging to: ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ Expiration: 2025-01-15 23:59:59 ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ║ ║
rirv938-llama-8b-multihe-6884-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-multihe-6884-v1-mkmlizer: Downloaded to shared memory in 109.195s
rirv938-llama-8b-multihe-6884-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmprcnmoxee, device:0
rirv938-llama-8b-multihe-6884-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
rirv938-llama-8b-multihe-6884-v1-mkmlizer: quantized model in 86.520s
rirv938-llama-8b-multihe-6884-v1-mkmlizer: Processed model rirv938/llama_8b_multihead_204m_retry in 195.715s
rirv938-llama-8b-multihe-6884-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-multihe-6884-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-multihe-6884-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-multihe-6884-v1
rirv938-llama-8b-multihe-6884-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-multihe-6884-v1/tokenizer.json
rirv938-llama-8b-multihe-6884-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-multihe-6884-v1/flywheel_model.0.safetensors
rirv938-llama-8b-multihe-6884-v1-mkmlizer: Loading 0: 0%| | 0/291 [00:00<?, ?it/s] Loading 0: 1%| | 3/291 [00:00<00:58, 4.93it/s] Loading 0: 1%|▏ | 4/291 [00:01<01:35, 3.02it/s] Loading 0: 2%|▏ | 5/291 [00:01<02:07, 2.24it/s] Loading 0: 3%|▎ | 8/291 [00:02<01:06, 4.24it/s] Loading 0: 3%|▎ | 9/291 [00:02<01:05, 4.32it/s] Loading 0: 3%|▎ | 10/291 [00:02<00:57, 4.92it/s] Loading 0: 4%|▍ | 12/291 [00:03<01:07, 4.13it/s] Loading 0: 4%|▍ | 13/291 [00:03<01:29, 3.11it/s] Loading 0: 5%|▍ | 14/291 [00:04<01:52, 2.46it/s] Loading 0: 6%|▌ | 17/291 [00:04<01:04, 4.24it/s] Loading 0: 6%|▌ | 18/291 [00:04<01:00, 4.52it/s] Loading 0: 7%|▋ | 19/291 [00:04<00:53, 5.11it/s] Loading 0: 7%|▋ | 21/291 [00:05<01:03, 4.25it/s] Loading 0: 8%|▊ | 22/291 [00:06<01:24, 3.19it/s] Loading 0: 8%|▊ | 23/291 [00:06<01:46, 2.51it/s] Loading 0: 9%|▉ | 26/291 [00:06<01:01, 4.33it/s] Loading 0: 9%|▉ | 27/291 [00:07<00:57, 4.55it/s] Loading 0: 10%|▉ | 29/291 [00:07<00:43, 6.03it/s] Loading 0: 10%|█ | 30/291 [00:07<00:42, 6.10it/s] Loading 0: 11%|█ | 31/291 [00:07<00:43, 6.01it/s] Loading 0: 11%|█▏ | 33/291 [00:07<00:40, 6.31it/s] Loading 0: 12%|█▏ | 34/291 [00:08<01:05, 3.93it/s] Loading 0: 12%|█▏ | 35/291 [00:09<01:25, 2.99it/s] Loading 0: 12%|█▏ | 36/291 [00:09<01:46, 2.40it/s] Loading 0: 13%|█▎ | 39/291 [00:10<01:16, 3.30it/s] Loading 0: 14%|█▎ | 40/291 [00:10<01:30, 2.77it/s] Loading 0: 14%|█▍ | 41/291 [00:11<01:47, 2.33it/s] Loading 0: 15%|█▌ | 44/291 [00:11<01:03, 3.92it/s] Loading 0: 15%|█▌ | 45/291 [00:11<00:59, 4.16it/s] Loading 0: 16%|█▌ | 46/291 [00:12<00:53, 4.59it/s] Loading 0: 16%|█▋ | 48/291 [00:12<01:00, 4.04it/s] Loading 0: 17%|█▋ | 49/291 [00:13<01:17, 3.12it/s] Loading 0: 17%|█▋ | 50/291 [00:13<01:36, 2.50it/s] Loading 0: 18%|█▊ | 53/291 [00:14<00:55, 4.29it/s] Loading 0: 19%|█▊ | 54/291 [00:14<00:52, 4.51it/s] Loading 0: 19%|█▉ | 55/291 [00:14<00:46, 5.11it/s] Loading 0: 20%|█▉ | 57/291 [00:14<00:54, 4.29it/s] Loading 0: 20%|█▉ | 58/291 [00:15<01:12, 3.24it/s] Loading 0: 20%|██ | 59/291 [00:16<01:31, 2.55it/s] Loading 0: 21%|██▏ | 62/291 [00:16<00:52, 4.32it/s] Loading 0: 22%|██▏ | 63/291 [00:16<00:50, 4.54it/s] Loading 0: 22%|██▏ | 64/291 [00:16<00:44, 5.14it/s] Loading 0: 23%|██▎ | 66/291 [00:17<00:52, 4.28it/s] Loading 0: 23%|██▎ | 67/291 [00:17<01:09, 3.22it/s] Loading 0: 23%|██▎ | 68/291 [00:18<01:27, 2.54it/s] Loading 0: 24%|██▍ | 71/291 [00:18<00:51, 4.30it/s] Loading 0: 25%|██▍ | 72/291 [00:18<00:48, 4.52it/s] Loading 0: 25%|██▌ | 73/291 [00:19<00:42, 5.11it/s] Loading 0: 25%|██▌ | 74/291 [00:19<01:03, 3.43it/s] Loading 0: 26%|██▌ | 75/291 [00:20<01:24, 2.55it/s] Loading 0: 26%|██▋ | 77/291 [00:20<00:57, 3.72it/s] Loading 0: 27%|██▋ | 78/291 [00:20<00:52, 4.05it/s] Loading 0: 27%|██▋ | 79/291 [00:20<00:44, 4.74it/s] Loading 0: 27%|██▋ | 80/291 [00:20<00:42, 4.93it/s] Loading 0: 28%|██▊ | 81/291 [00:21<01:04, 3.26it/s] Loading 0: 28%|██▊ | 82/291 [00:22<01:20, 2.58it/s] Loading 0: 29%|██▊ | 83/291 [00:22<01:37, 2.14it/s] Loading 0: 30%|██▉ | 86/291 [00:23<00:50, 4.05it/s] Loading 0: 30%|██▉ | 87/291 [00:23<00:47, 4.33it/s] Loading 0: 30%|███ | 88/291 [00:23<00:40, 4.97it/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, 2.54it/s] Loading 0: 33%|███▎ | 95/291 [00:25<00:44, 4.41it/s] Loading 0: 33%|███▎ | 96/291 [00:25<00:41, 4.71it/s] Loading 0: 34%|███▍ | 99/291 [00:26<00:42, 4.56it/s] Loading 0: 34%|███▍ | 100/291 [00:26<00:54, 3.52it/s] Loading 0: 35%|███▍ | 101/291 [00:27<01:08, 2.78it/s] Loading 0: 36%|███▌ | 104/291 [00:27<00:41, 4.46it/s] Loading 0: 36%|███▌ | 105/291 [00:27<00:39, 4.67it/s] Loading 0: 36%|███▋ | 106/291 [00:27<00:35, 5.23it/s] Loading 0: 37%|███▋ | 108/291 [00:28<00:41, 4.36it/s] Loading 0: 37%|███▋ | 109/291 [00:29<00:55, 3.29it/s] Loading 0: 38%|███▊ | 110/291 [00:29<01:09, 2.62it/s] Loading 0: 39%|███▉ | 113/291 [00:29<00:40, 4.41it/s] Loading 0: 39%|███▉ | 114/291 [00:30<00:38, 4.63it/s] Loading 0: 40%|███▉ | 115/291 [00:30<00:33, 5.23it/s] Loading 0: 40%|███▉ | 116/291 [00:30<00:49, 3.51it/s] Loading 0: 41%|████ | 118/291 [00:30<00:36, 4.69it/s] Loading 0: 41%|████ | 119/291 [00:31<00:34, 4.92it/s] Loading 0: 41%|████ | 120/291 [00:31<00:30, 5.54it/s] Loading 0: 42%|████▏ | 122/291 [00:31<00:38, 4.41it/s] Loading 0: 43%|████▎ | 125/291 [00:32<00:35, 4.74it/s] Loading 0: 43%|████▎ | 126/291 [00:32<00:45, 3.60it/s] Loading 0: 44%|████▎ | 127/291 [00:33<00:57, 2.83it/s] Loading 0: 45%|████▍ | 130/291 [00:33<00:35, 4.53it/s] Loading 0: 45%|████▌ | 131/291 [00:34<00:33, 4.73it/s] Loading 0: 45%|████▌ | 132/291 [00:34<00:30, 5.29it/s] Loading 0: 46%|████▌ | 133/291 [00:34<00:28, 5.49it/s] Loading 0: 46%|████▌ | 134/291 [00:34<00:43, 3.57it/s] Loading 0: 46%|████▋ | 135/291 [00:35<00:59, 2.64it/s] Loading 0: 47%|████▋ | 138/291 [00:36<00:42, 3.56it/s] Loading 0: 48%|████▊ | 139/291 [00:36<00:51, 2.94it/s] Loading 0: 48%|████▊ | 140/291 [00:37<01:01, 2.46it/s] Loading 0: 49%|████▉ | 143/291 [00:37<00:36, 4.11it/s] Loading 0: 49%|████▉ | 144/291 [00:37<00:33, 4.36it/s] Loading 0: 50%|████▉ | 145/291 [00:37<00:29, 4.94it/s] Loading 0: 51%|█████ | 147/291 [00:38<00:34, 4.23it/s] Loading 0: 51%|█████ | 148/291 [00:38<00:44, 3.23it/s] Loading 0: 51%|█████ | 149/291 [00:39<00:54, 2.59it/s] Loading 0: 52%|█████▏ | 152/291 [00:39<00:31, 4.38it/s] Loading 0: 53%|█████▎ | 153/291 [00:39<00:29, 4.61it/s] Loading 0: 53%|█████▎ | 154/291 [00:40<00:26, 5.21it/s] Loading 0: 54%|█████▎ | 156/291 [00:40<00:31, 4.32it/s] Loading 0: 54%|█████▍ | 157/291 [00:41<00:41, 3.27it/s] Loading 0: 54%|█████▍ | 158/291 [00:41<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 [00:42<00:29, 4.31it/s] Loading 0: 57%|█████▋ | 166/291 [00:43<00:38, 3.27it/s] Loading 0: 57%|█████▋ | 167/291 [00:44<00:47, 2.60it/s] Loading 0: 58%|█████▊ | 170/291 [00:44<00:27, 4.40it/s] Loading 0: 59%|█████▉ | 171/291 [00:44<00:25, 4.63it/s] Loading 0: 60%|█████▉ | 174/291 [00:45<00:25, 4.52it/s] Loading 0: 60%|██████ | 175/291 [00:45<00:33, 3.51it/s] Loading 0: 60%|██████ | 176/291 [00:46<00:41, 2.80it/s] Loading 0: 62%|██████▏ | 179/291 [00:46<00:24, 4.53it/s] Loading 0: 62%|██████▏ | 180/291 [00:46<00:23, 4.74it/s] Loading 0: 63%|██████▎ | 182/291 [00:46<00:17, 6.13it/s] Loading 0: 63%|██████▎ | 183/291 [00:47<00:17, 6.22it/s] Loading 0: 63%|██████▎ | 184/291 [00:47<00:17, 6.16it/s] Loading 0: 64%|██████▎ | 185/291 [00:47<00:15, 6.74it/s] Loading 0: 64%|██████▍ | 186/291 [00:47<00:16, 6.47it/s] Loading 0: 64%|██████▍ | 187/291 [00:48<00:27, 3.73it/s] Loading 0: 65%|██████▍ | 188/291 [00:48<00:36, 2.84it/s] Loading 0: 65%|██████▍ | 189/291 [00:49<00:44, 2.31it/s] Loading 0: 66%|██████▌ | 192/291 [00:49<00:29, 3.33it/s] Loading 0: 66%|██████▋ | 193/291 [00:50<00:34, 2.80it/s] Loading 0: 67%|██████▋ | 194/291 [00:51<00:40, 2.37it/s] Loading 0: 68%|██████▊ | 197/291 [00:51<00:23, 4.04it/s] Loading 0: 68%|██████▊ | 198/291 [00:51<00:21, 4.30it/s] Loading 0: 68%|██████▊ | 199/291 [00:51<00:18, 4.87it/s] Loading 0: 69%|██████▉ | 201/291 [00:52<00:21, 4.20it/s] Loading 0: 69%|██████▉ | 202/291 [00:52<00:27, 3.22it/s] Loading 0: 70%|██████▉ | 203/291 [00:53<00:33, 2.59it/s] Loading 0: 71%|███████ | 206/291 [00:53<00:19, 4.38it/s] Loading 0: 71%|███████ | 207/291 [00:53<00:18, 4.62it/s] Loading 0: 71%|███████▏ | 208/291 [00:53<00:15, 5.19it/s] Loading 0: 72%|███████▏ | 210/291 [00:54<00:18, 4.33it/s] Loading 0: 73%|███████▎ | 211/291 [00:55<00:24, 3.29it/s] Loading 0: 73%|███████▎ | 212/291 [00:55<00:30, 2.62it/s] Loading 0: 74%|███████▍ | 215/291 [00:55<00:17, 4.42it/s] Loading 0: 74%|███████▍ | 216/291 [00:56<00:16, 4.65it/s] Loading 0: 75%|███████▍ | 217/291 [00:56<00:14, 5.21it/s] Loading 0: 75%|███████▌ | 219/291 [00:56<00:16, 4.36it/s] Loading 0: 76%|███████▌ | 220/291 [00:57<00:21, 3.30it/s] Loading 0: 76%|███████▌ | 221/291 [00:58<00:26, 2.63it/s] Loading 0: 77%|███████▋ | 224/291 [00:58<00:15, 4.45it/s] Loading 0: 77%|███████▋ | 225/291 [00:58<00:14, 4.68it/s] Loading 0: 78%|███████▊ | 226/291 [00:58<00:12, 5.24it/s] Loading 0: 78%|███████▊ | 227/291 [00:59<00:18, 3.53it/s] Loading 0: 78%|███████▊ | 228/291 [00:59<00:23, 2.69it/s] Loading 0: 79%|███████▉ | 230/291 [00:59<00:15, 3.84it/s] Loading 0: 79%|███████▉ | 231/291 [01:00<00:14, 4.18it/s] Loading 0: 80%|███████▉ | 232/291 [01:00<00:12, 4.86it/s] Loading 0: 80%|████████ | 233/291 [01:00<00:11, 5.22it/s] Loading 0: 80%|████████ | 234/291 [01:00<00:16, 3.39it/s] Loading 0: 81%|████████▏ | 237/291 [01:01<00:12, 4.19it/s] Loading 0: 82%|████████▏ | 238/291 [01:02<00:16, 3.26it/s] Loading 0: 82%|████████▏ | 239/291 [01:02<00:19, 2.60it/s] Loading 0: 83%|████████▎ | 242/291 [01:02<00:11, 4.34it/s] Loading 0: 84%|████████▎ | 243/291 [01:03<00:10, 4.58it/s] Loading 0: 84%|████████▍ | 244/291 [01:03<00:09, 5.15it/s] Loading 0: 85%|████████▍ | 246/291 [01:03<00:10, 4.35it/s] Loading 0: 85%|████████▍ | 247/291 [01:04<00:13, 3.29it/s] Loading 0: 85%|████████▌ | 248/291 [01:04<00:16, 2.62it/s] Loading 0: 86%|████████▋ | 251/291 [01:05<00:09, 4.44it/s] Loading 0: 87%|████████▋ | 252/291 [01:05<00:08, 4.67it/s] Loading 0: 87%|████████▋ | 253/291 [01:05<00:07, 5.23it/s] Loading 0: 88%|████████▊ | 255/291 [01:06<00:08, 4.36it/s] Loading 0: 88%|████████▊ | 256/291 [01:06<00:10, 3.31it/s] Loading 0: 88%|████████▊ | 257/291 [01:07<00:12, 2.64it/s] Loading 0: 89%|████████▉ | 260/291 [01:07<00:06, 4.47it/s] Loading 0: 90%|████████▉ | 261/291 [01:07<00:06, 4.70it/s] Loading 0: 90%|█████████ | 262/291 [01:07<00:05, 5.30it/s] Loading 0: 91%|█████████ | 264/291 [01:08<00:06, 4.40it/s] Loading 0: 91%|█████████ | 265/291 [01:08<00:07, 3.32it/s] Loading 0: 91%|█████████▏| 266/291 [01:09<00:09, 2.64it/s] Loading 0: 92%|█████████▏| 269/291 [01:09<00:04, 4.47it/s] Loading 0: 93%|█████████▎| 270/291 [01:09<00:04, 4.71it/s] Loading 0: 93%|█████████▎| 271/291 [01:09<00:03, 5.29it/s] Loading 0: 94%|█████████▍| 273/291 [01:10<00:04, 4.41it/s] Loading 0: 94%|█████████▍| 274/291 [01:11<00:05, 3.34it/s] Loading 0: 95%|█████████▍| 275/291 [01:11<00:06, 2.63it/s] Loading 0: 96%|█████████▌| 278/291 [01:11<00:02, 4.53it/s] Loading 0: 96%|█████████▌| 279/291 [01:12<00:02, 4.76it/s] Loading 0: 96%|█████████▌| 280/291 [01:12<00:02, 5.36it/s] Loading 0: 97%|█████████▋| 281/291 [01:12<00:02, 3.59it/s] Loading 0: 97%|█████████▋| 283/291 [01:13<00:01, 4.80it/s] Loading 0: 98%|█████████▊| 284/291 [01:13<00:01, 5.02it/s] Loading 0: 98%|█████████▊| 285/291 [01:13<00:01, 5.69it/s] Loading 0: 98%|█████████▊| 286/291 [01:13<00:00, 5.79it/s] Loading 0: 99%|█████████▊| 287/291 [01:14<00:01, 3.55it/s] Loading 0: 99%|█████████▉| 288/291 [01:14<00:01, 2.63it/s]
Job rirv938-llama-8b-multihe-6884-v1-mkmlizer completed after 217.91s with status: succeeded
Stopping job with name rirv938-llama-8b-multihe-6884-v1-mkmlizer
Pipeline stage MKMLizer completed in 218.52s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-multihe-6884-v1
Waiting for inference service rirv938-llama-8b-multihe-6884-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
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 rirv938-llama-8b-multihe-6884-v1 ready after 191.18295216560364s
Pipeline stage MKMLDeployer completed in 191.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7402358055114746s
Received healthy response to inference request in 3.7749722003936768s
Received healthy response to inference request in 2.8279547691345215s
Received healthy response to inference request in 2.967207670211792s
Received healthy response to inference request in 1.992614507675171s
5 requests
0 failed requests
5th percentile: 2.1421387672424315
10th percentile: 2.2916630268096925
20th percentile: 2.590711545944214
30th percentile: 2.757779598236084
40th percentile: 2.7928671836853027
50th percentile: 2.8279547691345215
60th percentile: 2.8836559295654296
70th percentile: 2.9393570899963377
80th percentile: 3.128760576248169
90th percentile: 3.451866388320923
95th percentile: 3.6134192943573
99th percentile: 3.7426616191864013
mean time: 2.8605969905853272
Pipeline stage StressChecker completed in 16.18s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%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
triggered trigger_guanaco_pipeline args=%s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 6.20s
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 2.46s
Shutdown handler de-registered
rirv938-llama-8b-multihe_6884_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
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 0.14s
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-6884-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-6884-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-6884-v1-profiler ready after 200.5184030532837s
Pipeline stage MKMLProfilerDeployer completed in 200.92s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplolj25p:/code/chaiverse_profiler_1731609550 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplolj25p --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731609550 && 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_1731609550/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplolj25p:/code/chaiverse_profiler_1731612318 --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-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplolj25p:/code/chaiverse_profiler_1731612318 --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-6884-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-6884-v1-profiler
Service rirv938-llama-8b-multihe-6884-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.10s
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-6884-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.18s
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-6884-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-6884-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-6884-v1-profiler ready after 60.18145704269409s
Pipeline stage MKMLProfilerDeployer completed in 60.54s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplos7lsn:/code/chaiverse_profiler_1731612418 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplos7lsn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731612418 && 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_1731612418/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplos7lsn:/code/chaiverse_profiler_1731615141 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplos7lsn --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731615141 && 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_1731615141/summary.json'
Received signal 2, running shutdown handler
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-multihe-6884-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-6884-v1-profiler
Service rirv938-llama-8b-multihe-6884-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.98s
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-6884-v1-profiler is running
Skipping teardown as no inference service was found
Pipeline stage MKMLProfilerDeleter completed in 2.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-multihe-6884-v1-profiler
Waiting for inference service rirv938-llama-8b-multihe-6884-v1-profiler to be ready
Inference service rirv938-llama-8b-multihe-6884-v1-profiler ready after 160.4637405872345s
Pipeline stage MKMLProfilerDeployer completed in 160.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplo6trpm:/code/chaiverse_profiler_1731616145 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplo6trpm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1731616145 && 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_1731616145/summary.json'
%s, retrying in %s seconds...
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplo6trpm:/code/chaiverse_profiler_1731618883 --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-mul82fc6f30dfb8b71035e0d9af15bc71e0-deplo6trpm:/code/chaiverse_profiler_1731618883 --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-6884-v1-profiler is running
Tearing down inference service rirv938-llama-8b-multihe-6884-v1-profiler
Service rirv938-llama-8b-multihe-6884-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.19s
Shutdown handler de-registered
rirv938-llama-8b-multihe_6884_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-multihe_6884_v1 status is now torndown due to DeploymentManager action