rirv938-llama-8b-dpo-vs-_2870

submission_id: rirv938-llama-8b-dpo-vs-_2870_v2
developer_uid: robert_irvine
best_of: 1
celo_rating: 1253.8
display_name: rirv938-llama-8b-dpo-vs-_2870_v2
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', 'truncate_by_message': False}
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}
gpu_counts: {'NVIDIA RTX A5000': 1}
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: rirv938/llama_8b_dpo_vs_dpo_250k_2535
latencies: [{'batch_size': 1, 'throughput': 0.10659064636709366, 'latency_mean': 9.381595573425294, 'latency_p50': 9.38123619556427, 'latency_p90': 9.464583611488342}]
max_input_tokens: 256
max_output_tokens: 1
model_architecture: LlamaForSequenceClassification
model_group: rirv938/llama_8b_dpo_vs_
model_name: rirv938-llama-8b-dpo-vs-_2870_v2
model_num_parameters: 8030261248.0
model_repo: rirv938/llama_8b_dpo_vs_dpo_250k_2535
model_size: 8B
num_battles: 11526
num_wins: 5768
ranking_group: single
status: torndown
submission_type: basic
timestamp: 2024-09-14T17:52:12+00:00
us_pacific_date: 2024-09-14
win_ratio: 0.5004338018393198
Download Preference Data
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-2870-v2-mkmlizer
Waiting for job on rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer to finish
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║       /___/                                                         ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  Version: 0.10.1                                                    ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ║                                                                     ║
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: Downloaded to shared memory in 24.103s
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp0rltsiup, device:0
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission blend_gamub_2024-09-09: ('http://zonemercy-virgo-edit-v1-1e5-v3-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: quantized model in 84.440s
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: Processed model rirv938/llama_8b_dpo_vs_dpo_250k_2535 in 108.543s
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2/special_tokens_map.json
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2/tokenizer_config.json
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2/config.json
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2/tokenizer.json
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-llama-8b-dpo-vs-2870-v2/flywheel_model.0.safetensors
rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/291 [00:00<00:53,  5.37it/s]
Loading 0:   1%|▏         | 4/291 [00:01<01:27,  3.28it/s]
Loading 0:   2%|▏         | 5/291 [00:01<01:59,  2.40it/s]
Loading 0:   3%|▎         | 8/291 [00:01<01:01,  4.60it/s]
Loading 0:   3%|▎         | 9/291 [00:02<01:00,  4.67it/s]
Loading 0:   3%|▎         | 10/291 [00:02<00:53,  5.29it/s]
Loading 0:   4%|▍         | 12/291 [00:02<01:03,  4.41it/s]
Loading 0:   4%|▍         | 13/291 [00:03<01:24,  3.28it/s]
Loading 0:   5%|▍         | 14/291 [00:04<01:47,  2.57it/s]
Loading 0:   6%|▌         | 17/291 [00:04<01:01,  4.43it/s]
Loading 0:   6%|▌         | 18/291 [00:04<00:58,  4.66it/s]
Loading 0:   7%|▋         | 19/291 [00:04<00:52,  5.19it/s]
Loading 0:   7%|▋         | 21/291 [00:05<01:02,  4.35it/s]
Loading 0:   8%|▊         | 22/291 [00:05<01:22,  3.28it/s]
Loading 0:   8%|▊         | 23/291 [00:06<01:43,  2.60it/s]
Loading 0:   9%|▉         | 26/291 [00:06<01:00,  4.40it/s]
Loading 0:   9%|▉         | 27/291 [00:06<00:56,  4.64it/s]
Loading 0:  10%|█         | 30/291 [00:07<00:57,  4.52it/s]
Loading 0:  11%|█         | 31/291 [00:08<01:14,  3.51it/s]
Loading 0:  11%|█         | 32/291 [00:08<01:33,  2.77it/s]
Loading 0:  12%|█▏        | 35/291 [00:08<00:57,  4.44it/s]
Loading 0:  12%|█▏        | 36/291 [00:09<00:54,  4.67it/s]
Loading 0:  13%|█▎        | 37/291 [00:09<00:48,  5.22it/s]
Loading 0:  13%|█▎        | 39/291 [00:09<00:57,  4.36it/s]
Loading 0:  14%|█▎        | 40/291 [00:10<01:16,  3.29it/s]
Loading 0:  14%|█▍        | 41/291 [00:10<01:36,  2.59it/s]
Loading 0:  15%|█▌        | 44/291 [00:11<00:56,  4.38it/s]
Loading 0:  15%|█▌        | 45/291 [00:11<00:53,  4.62it/s]
Loading 0:  16%|█▋        | 48/291 [00:12<00:53,  4.52it/s]
Loading 0:  17%|█▋        | 49/291 [00:12<01:08,  3.51it/s]
Loading 0:  17%|█▋        | 50/291 [00:13<01:26,  2.79it/s]
Loading 0:  18%|█▊        | 53/291 [00:13<00:53,  4.46it/s]
Loading 0:  19%|█▊        | 54/291 [00:13<00:50,  4.69it/s]
Loading 0:  20%|█▉        | 57/291 [00:14<00:51,  4.58it/s]
Loading 0:  20%|█▉        | 58/291 [00:14<01:05,  3.56it/s]
Loading 0:  20%|██        | 59/291 [00:15<01:21,  2.83it/s]
Loading 0:  21%|██▏       | 62/291 [00:15<00:51,  4.49it/s]
Loading 0:  22%|██▏       | 63/291 [00:15<00:48,  4.70it/s]
Loading 0:  23%|██▎       | 66/291 [00:16<00:49,  4.59it/s]
Loading 0:  23%|██▎       | 67/291 [00:17<01:02,  3.58it/s]
Loading 0:  23%|██▎       | 68/291 [00:17<01:19,  2.82it/s]
Loading 0:  24%|██▍       | 71/291 [00:18<00:49,  4.46it/s]
Loading 0:  25%|██▍       | 72/291 [00:18<00:46,  4.68it/s]
Loading 0:  26%|██▌       | 75/291 [00:18<00:47,  4.57it/s]
Loading 0:  26%|██▌       | 76/291 [00:19<01:00,  3.58it/s]
Loading 0:  26%|██▋       | 77/291 [00:20<01:15,  2.85it/s]
Loading 0:  27%|██▋       | 80/291 [00:20<00:46,  4.50it/s]
Loading 0:  28%|██▊       | 81/291 [00:20<00:43,  4.79it/s]
Loading 0:  29%|██▊       | 83/291 [00:20<00:37,  5.55it/s]
Loading 0:  29%|██▉       | 84/291 [00:21<00:53,  3.88it/s]
Loading 0:  29%|██▉       | 85/291 [00:21<01:07,  3.06it/s]
Loading 0:  30%|██▉       | 86/291 [00:22<01:22,  2.48it/s]
Loading 0:  31%|███       | 89/291 [00:22<00:46,  4.31it/s]
Loading 0:  31%|███       | 90/291 [00:22<00:44,  4.57it/s]
Loading 0:  32%|███▏      | 93/291 [00:23<00:43,  4.52it/s]
Loading 0:  32%|███▏      | 94/291 [00:24<00:55,  3.52it/s]
Loading 0:  33%|███▎      | 95/291 [00:24<01:09,  2.82it/s]
Loading 0:  34%|███▎      | 98/291 [00:24<00:42,  4.50it/s]
Loading 0:  34%|███▍      | 99/291 [00:25<00:40,  4.72it/s]
Loading 0:  35%|███▌      | 102/291 [00:25<00:41,  4.61it/s]
Loading 0:  35%|███▌      | 103/291 [00:26<00:52,  3.58it/s]
Loading 0:  36%|███▌      | 104/291 [00:27<01:05,  2.85it/s]
Loading 0:  37%|███▋      | 107/291 [00:27<00:40,  4.51it/s]
Loading 0:  37%|███▋      | 108/291 [00:27<00:38,  4.73it/s]
Loading 0:  38%|███▊      | 111/291 [00:28<00:39,  4.57it/s]
Loading 0:  38%|███▊      | 112/291 [00:28<00:50,  3.51it/s]
Loading 0:  39%|███▉      | 113/291 [00:29<01:03,  2.78it/s]
Loading 0:  40%|███▉      | 116/291 [00:29<00:39,  4.41it/s]
Loading 0:  40%|████      | 117/291 [00:29<00:37,  4.64it/s]
Loading 0:  41%|████      | 118/291 [00:29<00:33,  5.17it/s]
Loading 0:  41%|████      | 120/291 [00:30<00:39,  4.38it/s]
Loading 0:  42%|████▏     | 121/291 [00:30<00:51,  3.32it/s]
Loading 0:  42%|████▏     | 122/291 [00:31<01:03,  2.65it/s]
Loading 0:  43%|████▎     | 125/291 [00:31<00:36,  4.49it/s]
Loading 0:  43%|████▎     | 126/291 [00:31<00:34,  4.72it/s]
Loading 0:  44%|████▍     | 129/291 [00:32<00:35,  4.59it/s]
Loading 0:  45%|████▍     | 130/291 [00:33<00:45,  3.56it/s]
Loading 0:  45%|████▌     | 131/291 [00:33<00:56,  2.84it/s]
Loading 0:  46%|████▌     | 134/291 [00:34<00:34,  4.53it/s]
Loading 0:  46%|████▋     | 135/291 [00:34<00:32,  4.74it/s]
Loading 0:  47%|████▋     | 136/291 [00:34<00:29,  5.28it/s]
Loading 0:  47%|████▋     | 138/291 [00:34<00:34,  4.42it/s]
Loading 0:  48%|████▊     | 139/291 [00:35<00:45,  3.35it/s]
Loading 0:  48%|████▊     | 140/291 [00:36<00:56,  2.65it/s]
Loading 0:  49%|████▉     | 143/291 [00:36<00:33,  4.46it/s]
Loading 0:  49%|████▉     | 144/291 [00:36<00:31,  4.69it/s]
Loading 0:  51%|█████     | 147/291 [00:37<00:31,  4.59it/s]
Loading 0:  51%|█████     | 148/291 [00:37<00:40,  3.55it/s]
Loading 0:  51%|█████     | 149/291 [00:38<00:50,  2.83it/s]
Loading 0:  52%|█████▏    | 152/291 [00:38<00:30,  4.52it/s]
Loading 0:  53%|█████▎    | 153/291 [00:38<00:29,  4.71it/s]
Loading 0:  54%|█████▎    | 156/291 [00:39<00:29,  4.60it/s]
Loading 0:  54%|█████▍    | 157/291 [00:39<00:37,  3.59it/s]
Loading 0:  54%|█████▍    | 158/291 [00:40<00:46,  2.87it/s]
Loading 0:  55%|█████▌    | 161/291 [00:40<00:28,  4.59it/s]
Loading 0:  56%|█████▌    | 162/291 [00:40<00:26,  4.80it/s]
Loading 0:  57%|█████▋    | 165/291 [00:41<00:27,  4.66it/s]
Loading 0:  57%|█████▋    | 166/291 [00:42<00:34,  3.63it/s]
Loading 0:  57%|█████▋    | 167/291 [00:42<00:42,  2.89it/s]
Loading 0:  58%|█████▊    | 170/291 [00:43<00:26,  4.57it/s]
Loading 0:  59%|█████▉    | 171/291 [00:43<00:25,  4.78it/s]
Loading 0:  59%|█████▉    | 173/291 [00:43<00:29,  3.95it/s]
Loading 0:  60%|██████    | 175/291 [00:44<00:23,  4.98it/s]
Loading 0:  60%|██████    | 176/291 [00:44<00:22,  5.15it/s]
Loading 0:  61%|██████    | 177/291 [00:44<00:19,  5.71it/s]
Loading 0:  62%|██████▏   | 179/291 [00:44<00:24,  4.59it/s]
Loading 0:  62%|██████▏   | 180/291 [00:45<00:32,  3.41it/s]
Loading 0:  62%|██████▏   | 181/291 [00:46<00:40,  2.69it/s]
Loading 0:  63%|██████▎   | 184/291 [00:46<00:23,  4.55it/s]
Loading 0:  64%|██████▎   | 185/291 [00:46<00:22,  4.78it/s]
Loading 0:  64%|██████▍   | 187/291 [00:46<00:18,  5.58it/s]
Loading 0:  65%|██████▍   | 188/291 [00:47<00:26,  3.86it/s]
Loading 0:  65%|██████▍   | 189/291 [00:47<00:34,  2.93it/s]
Loading 0:  66%|██████▌   | 192/291 [00:48<00:26,  3.73it/s]
Loading 0:  66%|██████▋   | 193/291 [00:49<00:31,  3.07it/s]
Loading 0:  67%|██████▋   | 194/291 [00:49<00:38,  2.55it/s]
Loading 0:  68%|██████▊   | 197/291 [00:49<00:22,  4.20it/s]
Loading 0:  68%|██████▊   | 198/291 [00:50<00:20,  4.45it/s]
Loading 0:  69%|██████▉   | 201/291 [00:50<00:20,  4.45it/s]
Loading 0:  69%|██████▉   | 202/291 [00:51<00:25,  3.49it/s]
Loading 0:  70%|██████▉   | 203/291 [00:51<00:31,  2.81it/s]
Loading 0:  71%|███████   | 206/291 [00:52<00:19,  4.46it/s]
Loading 0:  71%|███████   | 207/291 [00:52<00:17,  4.69it/s]
Loading 0:  72%|███████▏  | 210/291 [00:53<00:17,  4.60it/s]
Loading 0:  73%|███████▎  | 211/291 [00:53<00:22,  3.58it/s]
Loading 0:  73%|███████▎  | 212/291 [00:54<00:27,  2.87it/s]
Loading 0:  74%|███████▍  | 215/291 [00:54<00:16,  4.52it/s]
Loading 0:  74%|███████▍  | 216/291 [00:54<00:15,  4.74it/s]
Loading 0:  75%|███████▍  | 217/291 [00:54<00:13,  5.30it/s]
Loading 0:  75%|███████▌  | 219/291 [00:55<00:16,  4.44it/s]
Loading 0:  76%|███████▌  | 220/291 [00:55<00:21,  3.37it/s]
Loading 0:  76%|███████▌  | 221/291 [00:56<00:26,  2.68it/s]
Loading 0:  77%|███████▋  | 224/291 [00:56<00:14,  4.56it/s]
Loading 0:  77%|███████▋  | 225/291 [00:56<00:13,  4.79it/s]
Loading 0:  78%|███████▊  | 227/291 [00:56<00:09,  6.54it/s]
Loading 0:  79%|███████▊  | 229/291 [00:58<00:18,  3.40it/s]
Loading 0:  79%|███████▉  | 230/291 [00:58<00:21,  2.78it/s]
Loading 0:  80%|████████  | 233/291 [00:58<00:13,  4.43it/s]
Loading 0:  80%|████████  | 234/291 [00:59<00:12,  4.66it/s]
Loading 0:  81%|████████▏ | 237/291 [00:59<00:11,  4.55it/s]
Loading 0:  82%|████████▏ | 238/291 [01:00<00:14,  3.58it/s]
Loading 0:  82%|████████▏ | 239/291 [01:00<00:18,  2.86it/s]
Loading 0:  83%|████████▎ | 242/291 [01:01<00:10,  4.56it/s]
Loading 0:  84%|████████▎ | 243/291 [01:01<00:10,  4.77it/s]
Loading 0:  84%|████████▍ | 244/291 [01:01<00:08,  5.33it/s]
Loading 0:  85%|████████▍ | 246/291 [01:02<00:10,  4.44it/s]
Loading 0:  85%|████████▍ | 247/291 [01:02<00:13,  3.37it/s]
Loading 0:  85%|████████▌ | 248/291 [01:03<00:16,  2.68it/s]
Loading 0:  86%|████████▋ | 251/291 [01:03<00:08,  4.55it/s]
Loading 0:  87%|████████▋ | 252/291 [01:03<00:08,  4.77it/s]
Loading 0:  88%|████████▊ | 255/291 [01:04<00:07,  4.62it/s]
Loading 0:  88%|████████▊ | 256/291 [01:04<00:09,  3.59it/s]
Loading 0:  88%|████████▊ | 257/291 [01:05<00:11,  2.86it/s]
Loading 0:  89%|████████▉ | 260/291 [01:05<00:06,  4.57it/s]
Loading 0:  90%|████████▉ | 261/291 [01:05<00:06,  4.79it/s]
Loading 0:  91%|█████████ | 264/291 [01:06<00:05,  4.66it/s]
Loading 0:  91%|█████████ | 265/291 [01:07<00:07,  3.64it/s]
Loading 0:  91%|█████████▏| 266/291 [01:07<00:08,  2.90it/s]
Loading 0:  92%|█████████▏| 269/291 [01:07<00:04,  4.60it/s]
Loading 0:  93%|█████████▎| 270/291 [01:08<00:04,  4.82it/s]
Loading 0:  94%|█████████▍| 273/291 [01:08<00:03,  4.66it/s]
Loading 0:  94%|█████████▍| 274/291 [01:09<00:04,  3.62it/s]
Loading 0:  95%|█████████▍| 275/291 [01:09<00:05,  2.90it/s]
Loading 0:  96%|█████████▌| 278/291 [01:10<00:02,  4.64it/s]
Loading 0:  96%|█████████▌| 279/291 [01:10<00:02,  4.85it/s]
Loading 0:  96%|█████████▌| 280/291 [01:10<00:02,  5.41it/s]
Loading 0:  97%|█████████▋| 281/291 [01:10<00:02,  3.67it/s]
Loading 0:  97%|█████████▋| 282/291 [01:11<00:03,  2.77it/s]
Loading 0:  98%|█████████▊| 284/291 [01:11<00:01,  3.92it/s]
Loading 0:  98%|█████████▊| 285/291 [01:11<00:01,  4.27it/s]
Loading 0:  98%|█████████▊| 286/291 [01:12<00:01,  4.94it/s]
Loading 0:  99%|█████████▊| 287/291 [01:12<00:00,  5.21it/s]
Loading 0:  99%|█████████▉| 288/291 [01:12<00:00,  3.40it/s]
                                                            
Job rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer completed after 126.7s with status: succeeded
Stopping job with name rirv938-llama-8b-dpo-vs-2870-v2-mkmlizer
Pipeline stage MKMLizer completed in 127.44s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-llama-8b-dpo-vs-2870-v2
Waiting for inference service rirv938-llama-8b-dpo-vs-2870-v2 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
Inference service rirv938-llama-8b-dpo-vs-2870-v2 ready after 171.26724934577942s
Pipeline stage MKMLDeployer completed in 171.68s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 4.533504486083984s
Received healthy response to inference request in 5.265985727310181s
Received healthy response to inference request in 4.567178964614868s
Received healthy response to inference request in 5.099348306655884s
Received healthy response to inference request in 5.920182704925537s
5 requests
0 failed requests
5th percentile: 4.540239381790161
10th percentile: 4.5469742774963375
20th percentile: 4.560444068908692
30th percentile: 4.673612833023071
40th percentile: 4.8864805698394775
50th percentile: 5.099348306655884
60th percentile: 5.166003274917602
70th percentile: 5.232658243179321
80th percentile: 5.396825122833252
90th percentile: 5.658503913879395
95th percentile: 5.789343309402466
99th percentile: 5.894014825820923
mean time: 5.077240037918091
%s, retrying in %s seconds...
Received healthy response to inference request in 4.374760389328003s
Received healthy response to inference request in 2.070336103439331s
Received healthy response to inference request in 3.151808977127075s
Received healthy response to inference request in 4.1577770709991455s
Received healthy response to inference request in 4.515655755996704s
5 requests
0 failed requests
5th percentile: 2.2866306781768797
10th percentile: 2.502925252914429
20th percentile: 2.9355144023895265
30th percentile: 3.353002595901489
40th percentile: 3.7553898334503173
50th percentile: 4.1577770709991455
60th percentile: 4.244570398330689
70th percentile: 4.331363725662231
80th percentile: 4.4029394626617435
90th percentile: 4.459297609329224
95th percentile: 4.4874766826629635
99th percentile: 4.510019941329956
mean time: 3.6540676593780517
Pipeline stage StressChecker completed in 45.73s
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 4.80s
Shutdown handler de-registered
rirv938-llama-8b-dpo-vs-_2870_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 0.17s
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-2870-v2-profiler
Waiting for inference service rirv938-llama-8b-dpo-vs-2870-v2-profiler to be ready
Inference service rirv938-llama-8b-dpo-vs-2870-v2-profiler ready after 170.4467101097107s
Pipeline stage MKMLProfilerDeployer completed in 170.86s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/rirv938-llama-8b-dpo160bfdd69c35e14610443d6aab6b9023-deplo9rndm:/code/chaiverse_profiler_1726336901 --namespace tenant-chaiml-guanaco
kubectl exec -it rirv938-llama-8b-dpo160bfdd69c35e14610443d6aab6b9023-deplo9rndm --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1726336901 && 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_1726336901/summary.json'
kubectl exec -it rirv938-llama-8b-dpo160bfdd69c35e14610443d6aab6b9023-deplo9rndm --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1726336901/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1884.70s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service rirv938-llama-8b-dpo-vs-2870-v2-profiler is running
Tearing down inference service rirv938-llama-8b-dpo-vs-2870-v2-profiler
Service rirv938-llama-8b-dpo-vs-2870-v2-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.79s
Shutdown handler de-registered
rirv938-llama-8b-dpo-vs-_2870_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-llama-8b-dpo-vs-_2870_v2 status is now torndown due to DeploymentManager action