rirv938-llama-8b-dpo-vs-_7242

developer_uid: robert_irvine
submission_id: rirv938-llama-8b-dpo-vs-_7242_v2
model_name: rirv938-llama-8b-dpo-vs-_7242_v2
model_group: rirv938/llama_8b_dpo_vs_
status: torndown
timestamp: 2024-09-14T21:17:23+00:00
num_battles: 11348
num_wins: 5641
celo_rating: 1252.74
family_friendly_score: 0.0
submission_type: basic
model_repo: rirv938/llama_8b_dpo_vs_dpo_250k_1560
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 256
max_output_tokens: 1
latencies: [{'batch_size': 1, 'throughput': 0.10588268358637434, 'latency_mean': 9.444117254018783, 'latency_p50': 9.438481569290161, 'latency_p90': 9.568569350242615}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rirv938-llama-8b-dpo-vs-_7242_v2
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_dpo_vs_dpo_250k_1560
model_size: 8B
ranking_group: single
us_pacific_date: 2024-09-14
win_ratio: 0.4970919985900599
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-dpo-vs-7242-v2-mkmlizer
Waiting for job on rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer to finish
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: Downloaded to shared memory in 19.546s
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmpdf_e5ldv, device:0
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: quantized model in 83.379s
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: Processed model rirv938/llama_8b_dpo_vs_dpo_250k_1560 in 102.925s
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2/config.json
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2/special_tokens_map.json
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2/tokenizer_config.json
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2/tokenizer.json
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-7242-v2/flywheel_model.0.safetensors
rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:54,  5.24it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:29,  3.19it/s]
Loading 0:   2%|▏         | 5/291 [00:01<01:59,  2.40it/s]
Loading 0:   3%|▎         | 8/291 [00:01<01:01,  4.58it/s]
Loading 0:   3%|▎         | 9/291 [00:02<01:00,  4.63it/s]
Loading 0:   3%|▎         | 10/291 [00:02<00:53,  5.27it/s]
Loading 0:   4%|▍         | 12/291 [00:02<01:03,  4.38it/s]
Loading 0:   4%|▍         | 13/291 [00:03<01:24,  3.28it/s]
Loading 0:   5%|▍         | 14/291 [00:04<01:46,  2.60it/s]
Loading 0:   6%|▌         | 17/291 [00:04<01:01,  4.44it/s]
Loading 0:   6%|▌         | 18/291 [00:04<00:58,  4.68it/s]
Loading 0:   7%|▋         | 19/291 [00:04<00:51,  5.29it/s]
Loading 0:   7%|▋         | 21/291 [00:05<01:01,  4.42it/s]
Loading 0:   8%|▊         | 22/291 [00:05<01:20,  3.34it/s]
Loading 0:   8%|▊         | 23/291 [00:06<01:41,  2.63it/s]
Loading 0:   9%|▉         | 26/291 [00:06<00:59,  4.47it/s]
Loading 0:   9%|▉         | 27/291 [00:06<00:55,  4.71it/s]
Loading 0:  10%|▉         | 28/291 [00:06<00:49,  5.30it/s]
Loading 0:  10%|█         | 30/291 [00:07<00:58,  4.44it/s]
Loading 0:  11%|█         | 31/291 [00:07<01:17,  3.34it/s]
Loading 0:  11%|█         | 32/291 [00:08<01:38,  2.63it/s]
Loading 0:  12%|█▏        | 35/291 [00:08<00:56,  4.51it/s]
Loading 0:  12%|█▏        | 36/291 [00:08<00:53,  4.75it/s]
Loading 0:  13%|█▎        | 37/291 [00:09<00:47,  5.32it/s]
Loading 0:  13%|█▎        | 39/291 [00:09<00:56,  4.45it/s]
Loading 0:  14%|█▎        | 40/291 [00:10<01:14,  3.35it/s]
Loading 0:  14%|█▍        | 41/291 [00:10<01:34,  2.64it/s]
Loading 0:  15%|█▌        | 44/291 [00:11<00:55,  4.49it/s]
Loading 0:  15%|█▌        | 45/291 [00:11<00:52,  4.73it/s]
Loading 0:  16%|█▋        | 48/291 [00:11<00:52,  4.63it/s]
Loading 0:  17%|█▋        | 49/291 [00:12<01:07,  3.60it/s]
Loading 0:  17%|█▋        | 50/291 [00:13<01:24,  2.85it/s]
Loading 0:  18%|█▊        | 53/291 [00:13<00:52,  4.56it/s]
Loading 0:  19%|█▊        | 54/291 [00:13<00:49,  4.78it/s]
Loading 0:  19%|█▉        | 55/291 [00:13<00:44,  5.34it/s]
Loading 0:  20%|█▉        | 57/291 [00:14<00:52,  4.49it/s]
Loading 0:  20%|█▉        | 58/291 [00:14<01:08,  3.39it/s]
Loading 0:  20%|██        | 59/291 [00:15<01:26,  2.67it/s]
Loading 0:  21%|██▏       | 62/291 [00:15<00:50,  4.50it/s]
Loading 0:  22%|██▏       | 63/291 [00:15<00:48,  4.73it/s]
Loading 0:  23%|██▎       | 66/291 [00:16<00:48,  4.62it/s]
Loading 0:  23%|██▎       | 67/291 [00:16<01:02,  3.60it/s]
Loading 0:  23%|██▎       | 68/291 [00:17<01:18,  2.86it/s]
Loading 0:  24%|██▍       | 71/291 [00:17<00:48,  4.55it/s]
Loading 0:  25%|██▍       | 72/291 [00:17<00:46,  4.75it/s]
Loading 0:  25%|██▌       | 73/291 [00:18<00:41,  5.28it/s]
Loading 0:  26%|██▌       | 75/291 [00:18<00:48,  4.46it/s]
Loading 0:  26%|██▌       | 76/291 [00:19<01:03,  3.39it/s]
Loading 0:  26%|██▋       | 77/291 [00:19<01:19,  2.69it/s]
Loading 0:  27%|██▋       | 80/291 [00:20<00:46,  4.52it/s]
Loading 0:  28%|██▊       | 81/291 [00:20<00:44,  4.76it/s]
Loading 0:  29%|██▊       | 83/291 [00:20<00:37,  5.48it/s]
Loading 0:  29%|██▉       | 84/291 [00:21<00:53,  3.86it/s]
Loading 0:  29%|██▉       | 85/291 [00:21<01:07,  3.06it/s]
Loading 0:  30%|██▉       | 86/291 [00:22<01:22,  2.50it/s]
Loading 0:  31%|███       | 89/291 [00:22<00:46,  4.38it/s]
Loading 0:  31%|███       | 90/291 [00:22<00:43,  4.64it/s]
Loading 0:  32%|███▏      | 93/291 [00:23<00:43,  4.59it/s]
Loading 0:  32%|███▏      | 94/291 [00:23<00:55,  3.57it/s]
Loading 0:  33%|███▎      | 95/291 [00:24<01:08,  2.84it/s]
Loading 0:  34%|███▎      | 98/291 [00:24<00:42,  4.58it/s]
Loading 0:  34%|███▍      | 99/291 [00:24<00:40,  4.80it/s]
Loading 0:  34%|███▍      | 100/291 [00:24<00:35,  5.35it/s]
Loading 0:  35%|███▌      | 102/291 [00:25<00:42,  4.48it/s]
Loading 0:  35%|███▌      | 103/291 [00:26<00:55,  3.39it/s]
Loading 0:  36%|███▌      | 104/291 [00:26<01:10,  2.66it/s]
Loading 0:  37%|███▋      | 107/291 [00:26<00:40,  4.54it/s]
Loading 0:  37%|███▋      | 108/291 [00:27<00:38,  4.77it/s]
Loading 0:  38%|███▊      | 111/291 [00:27<00:38,  4.65it/s]
Loading 0:  38%|███▊      | 112/291 [00:28<00:49,  3.61it/s]
Loading 0:  39%|███▉      | 113/291 [00:28<01:02,  2.86it/s]
Loading 0:  40%|███▉      | 116/291 [00:29<00:37,  4.61it/s]
Loading 0:  40%|████      | 117/291 [00:29<00:36,  4.82it/s]
Loading 0:  41%|████      | 120/291 [00:29<00:36,  4.69it/s]
Loading 0:  42%|████▏     | 121/291 [00:30<00:46,  3.66it/s]
Loading 0:  42%|████▏     | 122/291 [00:31<00:58,  2.88it/s]
Loading 0:  43%|████▎     | 125/291 [00:31<00:36,  4.61it/s]
Loading 0:  43%|████▎     | 126/291 [00:31<00:34,  4.82it/s]
Loading 0:  44%|████▍     | 129/291 [00:32<00:34,  4.69it/s]
Loading 0:  45%|████▍     | 130/291 [00:32<00:44,  3.65it/s]
Loading 0:  45%|████▌     | 131/291 [00:33<00:55,  2.89it/s]
Loading 0:  46%|████▌     | 134/291 [00:33<00:33,  4.63it/s]
Loading 0:  46%|████▋     | 135/291 [00:33<00:32,  4.84it/s]
Loading 0:  47%|████▋     | 136/291 [00:33<00:28,  5.40it/s]
Loading 0:  47%|████▋     | 138/291 [00:34<00:33,  4.51it/s]
Loading 0:  48%|████▊     | 139/291 [00:34<00:44,  3.41it/s]
Loading 0:  48%|████▊     | 140/291 [00:35<00:55,  2.70it/s]
Loading 0:  49%|████▉     | 143/291 [00:35<00:32,  4.54it/s]
Loading 0:  49%|████▉     | 144/291 [00:35<00:30,  4.78it/s]
Loading 0:  51%|█████     | 147/291 [00:36<00:30,  4.66it/s]
Loading 0:  51%|█████     | 148/291 [00:37<00:39,  3.62it/s]
Loading 0:  51%|█████     | 149/291 [00:37<00:49,  2.86it/s]
Loading 0:  52%|█████▏    | 152/291 [00:37<00:30,  4.55it/s]
Loading 0:  53%|█████▎    | 153/291 [00:38<00:28,  4.77it/s]
Loading 0:  54%|█████▎    | 156/291 [00:38<00:28,  4.66it/s]
Loading 0:  54%|█████▍    | 157/291 [00:39<00:36,  3.65it/s]
Loading 0:  54%|█████▍    | 158/291 [00:39<00:45,  2.91it/s]
Loading 0:  55%|█████▌    | 161/291 [00:40<00:27,  4.65it/s]
Loading 0:  56%|█████▌    | 162/291 [00:40<00:26,  4.85it/s]
Loading 0:  57%|█████▋    | 165/291 [00:41<00:26,  4.72it/s]
Loading 0:  57%|█████▋    | 166/291 [00:41<00:33,  3.68it/s]
Loading 0:  57%|█████▋    | 167/291 [00:42<00:42,  2.91it/s]
Loading 0:  58%|█████▊    | 170/291 [00:42<00:26,  4.59it/s]
Loading 0:  59%|█████▉    | 171/291 [00:42<00:24,  4.80it/s]
Loading 0:  59%|█████▉    | 173/291 [00:43<00:29,  4.01it/s]
Loading 0:  60%|██████    | 175/291 [00:43<00:22,  5.05it/s]
Loading 0:  60%|██████    | 176/291 [00:43<00:22,  5.22it/s]
Loading 0:  61%|██████    | 177/291 [00:43<00:20,  5.69it/s]
Loading 0:  62%|██████▏   | 179/291 [00:44<00:24,  4.61it/s]
Loading 0:  62%|██████▏   | 180/291 [00:44<00:32,  3.44it/s]
Loading 0:  62%|██████▏   | 181/291 [00:45<00:40,  2.72it/s]
Loading 0:  63%|██████▎   | 184/291 [00:45<00:23,  4.58it/s]
Loading 0:  64%|██████▎   | 185/291 [00:45<00:22,  4.81it/s]
Loading 0:  64%|██████▍   | 186/291 [00:45<00:19,  5.38it/s]
Loading 0:  64%|██████▍   | 187/291 [00:46<00:18,  5.49it/s]
Loading 0:  65%|██████▍   | 188/291 [00:46<00:28,  3.60it/s]
Loading 0:  65%|██████▍   | 189/291 [00:47<00:37,  2.71it/s]
Loading 0:  66%|██████▌   | 192/291 [00:47<00:26,  3.68it/s]
Loading 0:  66%|██████▋   | 193/291 [00:48<00:32,  3.03it/s]
Loading 0:  67%|██████▋   | 194/291 [00:49<00:38,  2.53it/s]
Loading 0:  68%|██████▊   | 197/291 [00:49<00:22,  4.26it/s]
Loading 0:  68%|██████▊   | 198/291 [00:49<00:20,  4.51it/s]
Loading 0:  68%|██████▊   | 199/291 [00:49<00:18,  5.10it/s]
Loading 0:  69%|██████▉   | 201/291 [00:50<00:20,  4.39it/s]
Loading 0:  69%|██████▉   | 202/291 [00:50<00:26,  3.36it/s]
Loading 0:  70%|██████▉   | 203/291 [00:51<00:32,  2.68it/s]
Loading 0:  71%|███████   | 206/291 [00:51<00:18,  4.52it/s]
Loading 0:  71%|███████   | 207/291 [00:51<00:17,  4.76it/s]
Loading 0:  71%|███████▏  | 208/291 [00:51<00:15,  5.33it/s]
Loading 0:  72%|███████▏  | 210/291 [00:52<00:18,  4.47it/s]
Loading 0:  73%|███████▎  | 211/291 [00:52<00:23,  3.37it/s]
Loading 0:  73%|███████▎  | 212/291 [00:53<00:29,  2.67it/s]
Loading 0:  74%|███████▍  | 215/291 [00:53<00:16,  4.52it/s]
Loading 0:  74%|███████▍  | 216/291 [00:53<00:15,  4.77it/s]
Loading 0:  75%|███████▍  | 218/291 [00:53<00:11,  6.53it/s]
Loading 0:  76%|███████▌  | 220/291 [00:55<00:20,  3.44it/s]
Loading 0:  76%|███████▌  | 221/291 [00:55<00:24,  2.80it/s]
Loading 0:  77%|███████▋  | 224/291 [00:55<00:15,  4.43it/s]
Loading 0:  77%|███████▋  | 225/291 [00:56<00:14,  4.66it/s]
Loading 0:  78%|███████▊  | 226/291 [00:56<00:12,  5.21it/s]
Loading 0:  78%|███████▊  | 228/291 [00:56<00:14,  4.45it/s]
Loading 0:  79%|███████▊  | 229/291 [00:57<00:18,  3.40it/s]
Loading 0:  79%|███████▉  | 230/291 [00:57<00:22,  2.71it/s]
Loading 0:  80%|████████  | 233/291 [00:58<00:12,  4.60it/s]
Loading 0:  80%|████████  | 234/291 [00:58<00:11,  4.83it/s]
Loading 0:  81%|████████▏ | 237/291 [00:58<00:11,  4.69it/s]
Loading 0:  82%|████████▏ | 238/291 [00:59<00:14,  3.63it/s]
Loading 0:  82%|████████▏ | 239/291 [01:00<00:17,  2.89it/s]
Loading 0:  83%|████████▎ | 242/291 [01:00<00:10,  4.65it/s]
Loading 0:  84%|████████▎ | 243/291 [01:00<00:09,  4.86it/s]
Loading 0:  85%|████████▍ | 246/291 [01:01<00:09,  4.70it/s]
Loading 0:  85%|████████▍ | 247/291 [01:01<00:11,  3.67it/s]
Loading 0:  85%|████████▌ | 248/291 [01:02<00:14,  2.93it/s]
Loading 0:  86%|████████▋ | 251/291 [01:02<00:08,  4.67it/s]
Loading 0:  87%|████████▋ | 252/291 [01:02<00:07,  4.88it/s]
Loading 0:  88%|████████▊ | 255/291 [01:03<00:07,  4.71it/s]
Loading 0:  88%|████████▊ | 256/291 [01:03<00:09,  3.68it/s]
Loading 0:  88%|████████▊ | 257/291 [01:04<00:11,  2.94it/s]
Loading 0:  89%|████████▉ | 260/291 [01:04<00:06,  4.69it/s]
Loading 0:  90%|████████▉ | 261/291 [01:04<00:06,  4.90it/s]
Loading 0:  91%|█████████ | 264/291 [01:05<00:05,  4.74it/s]
Loading 0:  91%|█████████ | 265/291 [01:06<00:07,  3.69it/s]
Loading 0:  91%|█████████▏| 266/291 [01:06<00:08,  2.94it/s]
Loading 0:  92%|█████████▏| 269/291 [01:06<00:04,  4.68it/s]
Loading 0:  93%|█████████▎| 270/291 [01:07<00:04,  4.90it/s]
Loading 0:  94%|█████████▍| 273/291 [01:07<00:03,  4.74it/s]
Loading 0:  94%|█████████▍| 274/291 [01:08<00:04,  3.69it/s]
Loading 0:  95%|█████████▍| 275/291 [01:08<00:05,  2.93it/s]
Loading 0:  96%|█████████▌| 278/291 [01:09<00:02,  4.67it/s]
Loading 0:  96%|█████████▌| 279/291 [01:09<00:02,  4.88it/s]
Loading 0:  97%|█████████▋| 281/291 [01:09<00:02,  4.02it/s]
Loading 0:  97%|█████████▋| 282/291 [01:10<00:02,  3.11it/s]
Loading 0:  98%|█████████▊| 284/291 [01:10<00:01,  4.11it/s]
Loading 0:  98%|█████████▊| 285/291 [01:10<00:01,  4.41it/s]
Loading 0:  98%|█████████▊| 286/291 [01:11<00:01,  4.99it/s]
Loading 0:  99%|█████████▊| 287/291 [01:11<00:00,  5.26it/s]
Loading 0:  99%|█████████▉| 288/291 [01:11<00:00,  3.50it/s]
                                                            
Job rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer completed after 129.18s with status: succeeded
Stopping job with name rirv938-llama-8b-dpo-vs-7242-v2-mkmlizer
Pipeline stage MKMLizer completed in 132.65s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-dpo-vs-7242-v2
Waiting for inference service rirv938-llama-8b-dpo-vs-7242-v2 to be ready
Inference service rirv938-llama-8b-dpo-vs-7242-v2 ready after 170.8472034931183s
Pipeline stage MKMLDeployer completed in 171.25s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.385324478149414s
Received healthy response to inference request in 3.713613510131836s
Received healthy response to inference request in 3.8110203742980957s
Received healthy response to inference request in 3.910635471343994s
Received healthy response to inference request in 3.1807830333709717s
5 requests
0 failed requests
5th percentile: 3.2873491287231444
10th percentile: 3.393915224075317
20th percentile: 3.607047414779663
30th percentile: 3.733094882965088
40th percentile: 3.772057628631592
50th percentile: 3.8110203742980957
60th percentile: 3.850866413116455
70th percentile: 3.8907124519348146
80th percentile: 4.005573272705078
90th percentile: 4.195448875427246
95th percentile: 4.29038667678833
99th percentile: 4.366336917877197
mean time: 3.800275373458862
Pipeline stage StressChecker completed in 19.80s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 5.86s
Shutdown handler de-registered
rirv938-llama-8b-dpo-vs-_7242_v2 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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-llama-8b-dpo-vs-7242-v2-profiler
Waiting for inference service rirv938-llama-8b-dpo-vs-7242-v2-profiler to be ready
Inference service rirv938-llama-8b-dpo-vs-7242-v2-profiler ready after 160.46199297904968s
Pipeline stage MKMLProfilerDeployer completed in 164.54s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-dpo721a5e226a02b5c77f81fae581fdf256-deplox5k7g:/code/chaiverse_profiler_1726349190 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-dpo721a5e226a02b5c77f81fae581fdf256-deplox5k7g --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726349190 && 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_1726349190/summary.json'
kubectl exec -it rirv938-llama-8b-dpo721a5e226a02b5c77f81fae581fdf256-deplox5k7g --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726349190/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1899.30s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-dpo-vs-7242-v2-profiler is running
Tearing down inference service rirv938-llama-8b-dpo-vs-7242-v2-profiler
Service rirv938-llama-8b-dpo-vs-7242-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
rirv938-llama-8b-dpo-vs-_7242_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-dpo-vs-_7242_v2 status is now torndown due to DeploymentManager action