submission_id: zonemercy-vingt-deux-v0-_4921_v5
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1233.6
display_name: temp-4
family_friendly_score: 0.0
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
generation_params: {'temperature': 0.9, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
gpu_counts: {'NVIDIA RTX A6000': 1}
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v0-1e5ep1
latencies: [{'batch_size': 1, 'throughput': 0.382898543344294, 'latency_mean': 2.611599575281143, 'latency_p50': 2.602728247642517, 'latency_p90': 2.8990391969680784}, {'batch_size': 2, 'throughput': 0.6029787567838029, 'latency_mean': 3.314497298002243, 'latency_p50': 3.33073353767395, 'latency_p90': 3.6354781866073607}, {'batch_size': 3, 'throughput': 0.7620913793424816, 'latency_mean': 3.914365919828415, 'latency_p50': 3.908880352973938, 'latency_p90': 4.2731640338897705}, {'batch_size': 4, 'throughput': 0.889596862024985, 'latency_mean': 4.472989809513092, 'latency_p50': 4.472272634506226, 'latency_p90': 5.021115803718566}, {'batch_size': 5, 'throughput': 0.9740571076158042, 'latency_mean': 5.0913947224617, 'latency_p50': 5.1130406856536865, 'latency_p90': 5.686147618293762}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-v0-
model_name: temp-4
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-v0-1e5ep1
model_size: 22B
num_battles: 52094
num_wins: 25175
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.71
timestamp: 2024-09-23T09:55:43+00:00
us_pacific_date: 2024-09-23
win_ratio: 0.4832610281414366
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
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
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
Starting job with name zonemercy-vingt-deux-v0-4921-v5-mkmlizer
Waiting for job on zonemercy-vingt-deux-v0-4921-v5-mkmlizer to finish
Connection pool is full, discarding connection: %s. Connection pool size: %s
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ _____ __ __ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ /___/ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ Version: 0.10.1 ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ https://mk1.ai ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ The license key for the current software has been verified as ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ belonging to: ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ Chai Research Corp. ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ║ ║
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
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
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: Downloaded to shared memory in 98.681s
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpl2qirc4s, device:0
zonemercy-vingt-deux-v0-4921-v5-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
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: quantized model in 51.714s
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: Processed model zonemercy/Vingt-Deux-v0-1e5ep1 in 150.395s
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-4921-v5/tokenizer_config.json
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-4921-v5/tokenizer.json
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-4921-v5/flywheel_model.1.safetensors
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v0-4921-v5/flywheel_model.0.safetensors
zonemercy-vingt-deux-v0-4921-v5-mkmlizer: Loading 0: 0%| | 0/507 [00:00<?, ?it/s] Loading 0: 1%| | 4/507 [00:00<00:17, 28.19it/s] Loading 0: 1%|▏ | 7/507 [00:00<00:23, 21.27it/s] Loading 0: 2%|▏ | 10/507 [00:00<00:21, 22.70it/s] Loading 0: 3%|▎ | 13/507 [00:00<00:22, 21.53it/s] Loading 0: 3%|▎ | 16/507 [00:00<00:22, 21.78it/s] Loading 0: 4%|▎ | 19/507 [00:00<00:20, 23.63it/s] Loading 0: 4%|▍ | 22/507 [00:00<00:19, 24.85it/s] Loading 0: 5%|▍ | 25/507 [00:01<00:29, 16.29it/s] Loading 0: 6%|▌ | 28/507 [00:01<00:30, 15.68it/s] Loading 0: 6%|▌ | 31/507 [00:01<00:27, 17.10it/s] Loading 0: 7%|▋ | 33/507 [00:01<00:28, 16.47it/s] Loading 0: 7%|▋ | 37/507 [00:01<00:23, 20.27it/s] Loading 0: 8%|▊ | 40/507 [00:02<00:22, 20.79it/s] Loading 0: 8%|▊ | 43/507 [00:02<00:21, 21.62it/s] Loading 0: 9%|▉ | 46/507 [00:02<00:19, 23.57it/s] Loading 0: 10%|▉ | 49/507 [00:02<00:18, 24.76it/s] Loading 0: 10%|█ | 52/507 [00:02<00:25, 17.77it/s] Loading 0: 11%|█ | 55/507 [00:02<00:26, 17.04it/s] Loading 0: 11%|█▏ | 58/507 [00:02<00:24, 18.30it/s] Loading 0: 12%|█▏ | 61/507 [00:03<00:22, 19.57it/s] Loading 0: 13%|█▎ | 66/507 [00:03<00:19, 22.31it/s] Loading 0: 14%|█▎ | 69/507 [00:03<00:21, 20.31it/s] Loading 0: 14%|█▍ | 73/507 [00:03<00:18, 23.95it/s] Loading 0: 15%|█▌ | 77/507 [00:03<00:16, 26.24it/s] Loading 0: 16%|█▌ | 80/507 [00:03<00:23, 18.35it/s] Loading 0: 16%|█▋ | 83/507 [00:04<00:24, 17.44it/s] Loading 0: 17%|█▋ | 87/507 [00:04<00:19, 21.15it/s] Loading 0: 18%|█▊ | 90/507 [00:04<00:18, 22.77it/s] Loading 0: 19%|█▊ | 94/507 [00:04<00:17, 23.39it/s] Loading 0: 19%|█▉ | 97/507 [00:04<00:16, 24.17it/s] Loading 0: 20%|█▉ | 100/507 [00:04<00:21, 18.89it/s] Loading 0: 21%|██ | 105/507 [00:05<00:16, 24.52it/s] Loading 0: 21%|██▏ | 108/507 [00:05<00:24, 16.31it/s] Loading 0: 22%|██▏ | 112/507 [00:05<00:20, 19.12it/s] Loading 0: 23%|██▎ | 115/507 [00:05<00:19, 20.08it/s] Loading 0: 24%|██▎ | 120/507 [00:05<00:16, 22.94it/s] Loading 0: 24%|██▍ | 123/507 [00:05<00:17, 21.37it/s] Loading 0: 25%|██▌ | 127/507 [00:06<00:15, 24.91it/s] Loading 0: 26%|██▌ | 131/507 [00:06<00:13, 27.19it/s] Loading 0: 26%|██▋ | 134/507 [00:06<00:19, 19.23it/s] Loading 0: 27%|██▋ | 137/507 [00:06<00:17, 20.66it/s] Loading 0: 28%|██▊ | 140/507 [00:06<00:20, 17.59it/s] Loading 0: 29%|██▊ | 145/507 [00:06<00:15, 23.28it/s] Loading 0: 29%|██▉ | 148/507 [00:07<00:15, 23.48it/s] Loading 0: 30%|██▉ | 151/507 [00:07<00:14, 23.88it/s] Loading 0: 31%|███ | 155/507 [00:07<00:14, 23.84it/s] Loading 0: 32%|███▏ | 160/507 [00:07<00:15, 21.96it/s] Loading 0: 32%|███▏ | 163/507 [00:07<00:17, 20.05it/s] Loading 0: 33%|███▎ | 166/507 [00:07<00:16, 20.87it/s] Loading 0: 33%|███▎ | 169/507 [00:08<00:15, 21.35it/s] Loading 0: 34%|███▍ | 172/507 [00:08<00:14, 23.09it/s] Loading 0: 35%|███▍ | 175/507 [00:08<00:14, 22.90it/s] Loading 0: 35%|███▌ | 178/507 [00:08<00:14, 22.85it/s] Loading 0: 36%|███▌ | 182/507 [00:08<00:13, 23.53it/s] Loading 0: 37%|███▋ | 186/507 [00:08<00:11, 27.01it/s] Loading 0: 37%|███▋ | 189/507 [00:09<00:18, 17.33it/s] Loading 0: 38%|███▊ | 193/507 [00:09<00:15, 20.51it/s] Loading 0: 39%|███▊ | 196/507 [00:09<00:14, 21.00it/s] Loading 0: 39%|███▉ | 199/507 [00:09<00:13, 22.08it/s] Loading 0: 40%|███▉ | 202/507 [00:09<00:13, 22.47it/s] Loading 0: 40%|████ | 205/507 [00:09<00:13, 22.58it/s] Loading 0: 41%|████ | 209/507 [00:09<00:12, 23.09it/s] Loading 0: 42%|████▏ | 214/507 [00:10<00:13, 21.64it/s] Loading 0: 43%|████▎ | 217/507 [00:10<00:14, 20.36it/s] Loading 0: 43%|████▎ | 220/507 [00:10<00:13, 20.83it/s] Loading 0: 44%|████▍ | 223/507 [00:10<00:13, 21.15it/s] Loading 0: 45%|████▍ | 226/507 [00:10<00:12, 22.76it/s] Loading 0: 45%|████▌ | 229/507 [00:10<00:12, 23.05it/s] Loading 0: 46%|████▌ | 232/507 [00:10<00:11, 23.71it/s] Loading 0: 47%|████▋ | 236/507 [00:11<00:11, 24.19it/s] Loading 0: 47%|████▋ | 240/507 [00:11<00:09, 27.90it/s] Loading 0: 48%|████▊ | 243/507 [00:11<00:14, 17.83it/s] Loading 0: 49%|████▊ | 247/507 [00:11<00:12, 20.82it/s] Loading 0: 49%|████▉ | 250/507 [00:11<00:12, 21.30it/s] Loading 0: 50%|████▉ | 253/507 [00:11<00:11, 22.61it/s] Loading 0: 50%|█████ | 256/507 [00:12<00:11, 22.59it/s] Loading 0: 51%|█████ | 259/507 [00:12<00:11, 22.33it/s] Loading 0: 52%|█████▏ | 262/507 [00:12<00:10, 23.26it/s] Loading 0: 52%|█████▏ | 266/507 [00:12<00:09, 26.13it/s] Loading 0: 53%|█████▎ | 269/507 [00:12<00:12, 18.87it/s] Loading 0: 54%|█████▎ | 272/507 [00:12<00:11, 20.30it/s] Loading 0: 54%|█████▍ | 275/507 [00:13<00:13, 16.92it/s] Loading 0: 55%|█████▌ | 280/507 [00:13<00:09, 22.84it/s] Loading 0: 56%|█████▌ | 283/507 [00:13<00:09, 23.09it/s] Loading 0: 56%|█████▋ | 286/507 [00:13<00:09, 23.51it/s] Loading 0: 57%|█████▋ | 290/507 [00:13<00:09, 23.82it/s] Loading 0: 58%|█████▊ | 294/507 [00:13<00:07, 26.80it/s] Loading 0: 59%|█████▊ | 297/507 [00:13<00:11, 17.64it/s] Loading 0: 59%|█████▉ | 300/507 [00:28<04:35, 1.33s/it] Loading 0: 60%|█████▉ | 302/507 [00:28<03:41, 1.08s/it] Loading 0: 60%|██████ | 306/507 [00:28<02:20, 1.43it/s] Loading 0: 61%|██████ | 309/507 [00:28<01:42, 1.94it/s] Loading 0: 61%|██████▏ | 311/507 [00:29<01:23, 2.35it/s] Loading 0: 62%|██████▏ | 316/507 [00:29<00:47, 3.99it/s] Loading 0: 63%|██████▎ | 320/507 [00:29<00:33, 5.66it/s] Loading 0: 64%|██████▎ | 323/507 [00:29<00:28, 6.48it/s] Loading 0: 64%|██████▍ | 326/507 [00:29<00:22, 8.09it/s] Loading 0: 65%|██████▍ | 329/507 [00:29<00:19, 8.95it/s] Loading 0: 66%|██████▌ | 334/507 [00:29<00:13, 13.28it/s] Loading 0: 66%|██████▋ | 337/507 [00:30<00:11, 15.00it/s] Loading 0: 67%|██████▋ | 340/507 [00:30<00:10, 16.58it/s] Loading 0: 68%|██████▊ | 343/507 [00:30<00:08, 18.28it/s] Loading 0: 68%|██████▊ | 346/507 [00:30<00:07, 20.54it/s] Loading 0: 69%|██████▉ | 349/507 [00:30<00:09, 17.20it/s] Loading 0: 69%|██████▉ | 352/507 [00:30<00:09, 16.97it/s] Loading 0: 70%|███████ | 355/507 [00:31<00:08, 18.40it/s] Loading 0: 71%|███████ | 358/507 [00:31<00:07, 18.91it/s] Loading 0: 71%|███████ | 361/507 [00:31<00:06, 21.13it/s] Loading 0: 72%|███████▏ | 364/507 [00:31<00:06, 21.40it/s] Loading 0: 72%|███████▏ | 367/507 [00:31<00:06, 21.94it/s] Loading 0: 73%|███████▎ | 370/507 [00:31<00:05, 23.64it/s] Loading 0: 74%|███████▍ | 374/507 [00:31<00:05, 26.48it/s] Loading 0: 74%|███████▍ | 377/507 [00:32<00:06, 18.61it/s] Loading 0: 75%|███████▍ | 380/507 [00:32<00:06, 20.09it/s] Loading 0: 76%|███████▌ | 383/507 [00:32<00:07, 16.75it/s] Loading 0: 77%|███████▋ | 388/507 [00:32<00:05, 22.54it/s] Loading 0: 77%|███████▋ | 391/507 [00:32<00:05, 22.87it/s] Loading 0: 78%|███████▊ | 394/507 [00:32<00:04, 23.15it/s] Loading 0: 78%|███████▊ | 397/507 [00:32<00:04, 23.80it/s] Loading 0: 79%|███████▉ | 400/507 [00:32<00:04, 25.16it/s] Loading 0: 79%|███████▉ | 403/507 [00:33<00:05, 18.59it/s] Loading 0: 80%|████████ | 406/507 [00:33<00:05, 17.69it/s] Loading 0: 81%|████████ | 409/507 [00:33<00:05, 18.95it/s] Loading 0: 81%|████████▏ | 412/507 [00:33<00:04, 19.87it/s] Loading 0: 82%|████████▏ | 417/507 [00:33<00:03, 23.22it/s] Loading 0: 83%|████████▎ | 420/507 [00:34<00:04, 21.49it/s] Loading 0: 84%|████████▎ | 424/507 [00:34<00:03, 25.17it/s] Loading 0: 84%|████████▍ | 428/507 [00:34<00:02, 27.37it/s] Loading 0: 85%|████████▌ | 431/507 [00:34<00:03, 19.99it/s] Loading 0: 86%|████████▌ | 434/507 [00:34<00:03, 21.24it/s] Loading 0: 86%|████████▌ | 437/507 [00:34<00:04, 17.33it/s] Loading 0: 87%|████████▋ | 442/507 [00:35<00:02, 22.27it/s] Loading 0: 88%|████████▊ | 445/507 [00:35<00:02, 22.68it/s] Loading 0: 88%|████████▊ | 448/507 [00:35<00:02, 22.79it/s] Loading 0: 89%|████████▉ | 452/507 [00:35<00:02, 23.17it/s] Loading 0: 90%|████████▉ | 456/507 [00:35<00:01, 26.71it/s] Loading 0: 91%|█████████ | 459/507 [00:35<00:02, 17.85it/s] Loading 0: 91%|█████████▏| 463/507 [00:36<00:02, 20.70it/s] Loading 0: 92%|█████████▏| 466/507 [00:36<00:01, 21.06it/s] Loading 0: 93%|█████████▎| 469/507 [00:36<00:01, 22.67it/s] Loading 0: 93%|█████████▎| 472/507 [00:36<00:01, 22.99it/s] Loading 0: 94%|█████████▎| 475/507 [00:36<00:01, 23.19it/s] Loading 0: 94%|█████████▍| 478/507 [00:36<00:01, 24.80it/s] Loading 0: 95%|█████████▌| 482/507 [00:36<00:00, 27.59it/s] Loading 0: 96%|█████████▌| 485/507 [00:38<00:05, 4.26it/s] Loading 0: 96%|█████████▋| 488/507 [00:39<00:03, 5.40it/s] Loading 0: 97%|█████████▋| 491/507 [00:39<00:02, 6.99it/s] Loading 0: 97%|█████████▋| 494/507 [00:39<00:01, 8.78it/s] Loading 0: 98%|█████████▊| 497/507 [00:39<00:00, 10.96it/s] Loading 0: 99%|█████████▊| 500/507 [00:39<00:00, 12.91it/s] Loading 0: 99%|█████████▉| 503/507 [00:39<00:00, 14.76it/s]
Job zonemercy-vingt-deux-v0-4921-v5-mkmlizer completed after 186.53s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v0-4921-v5-mkmlizer
Pipeline stage MKMLizer completed in 188.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v0-4921-v5
Waiting for inference service zonemercy-vingt-deux-v0-4921-v5 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
Failed to get response for submission riverise-mistral-0920-7872_v1: ('http://riverise-mistral-0920-7872-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:51176->127.0.0.1:8080: read: connection reset by peer\n')
Inference service zonemercy-vingt-deux-v0-4921-v5 ready after 191.33506226539612s
Pipeline stage MKMLDeployer completed in 192.17s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.849907398223877s
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
Received healthy response to inference request in 2.4437990188598633s
Received healthy response to inference request in 2.566190481185913s
Received healthy response to inference request in 3.416821241378784s
Received healthy response to inference request in 2.5859296321868896s
5 requests
0 failed requests
5th percentile: 2.4682773113250733
10th percentile: 2.4927556037902834
20th percentile: 2.541712188720703
30th percentile: 2.5701383113861085
40th percentile: 2.578033971786499
50th percentile: 2.5859296321868896
60th percentile: 2.918286275863647
70th percentile: 3.250642919540405
80th percentile: 3.5034384727478027
90th percentile: 3.67667293548584
95th percentile: 3.7632901668548584
99th percentile: 3.832583951950073
mean time: 2.9725295543670653
Pipeline stage StressChecker completed in 17.35s
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 4.81s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-_4921_v5 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zonemercy-vingt-deux-v0-4921-v5-profiler
Waiting for inference service zonemercy-vingt-deux-v0-4921-v5-profiler to be ready
Inference service zonemercy-vingt-deux-v0-4921-v5-profiler ready after 180.41426587104797s
Pipeline stage MKMLProfilerDeployer completed in 180.81s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux861828c24a504dd1e26c47ffd995758a-deplo59cnx:/code/chaiverse_profiler_1727085980 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux861828c24a504dd1e26c47ffd995758a-deplo59cnx --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727085980 && python profiles.py profile --best_of_n 8 --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 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727085980/summary.json'
kubectl exec -it zonemercy-vingt-deux861828c24a504dd1e26c47ffd995758a-deplo59cnx --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727085980/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1551.98s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v0-4921-v5-profiler is running
Tearing down inference service zonemercy-vingt-deux-v0-4921-v5-profiler
Service zonemercy-vingt-deux-v0-4921-v5-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 1.92s
Shutdown handler de-registered
zonemercy-vingt-deux-v0-_4921_v5 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v0-_4921_v5 status is now torndown due to DeploymentManager action