submission_id: zonemercy-vingt-deux-gfv_3432_v1
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1244.72
display_name: temp-8
family_friendly_score: 0.0
formatter: {'memory_template': 'Bot Name: {bot_name}\n####\n', 'prompt_template': '', 'bot_template': 'Bot: {message}\n', 'user_template': 'User: {message}\n', 'response_template': 'Bot:', '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}
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-gfv1v2ep2
latencies: [{'batch_size': 1, 'throughput': 0.3772285132821718, 'latency_mean': 2.650842909812927, 'latency_p50': 2.6685352325439453, 'latency_p90': 2.937673282623291}, {'batch_size': 2, 'throughput': 0.5854907557008859, 'latency_mean': 3.406289758682251, 'latency_p50': 3.4048399925231934, 'latency_p90': 3.7491538763046264}, {'batch_size': 3, 'throughput': 0.7339211998100066, 'latency_mean': 4.085287327766419, 'latency_p50': 4.110352516174316, 'latency_p90': 4.490677833557129}, {'batch_size': 4, 'throughput': 0.850418836453305, 'latency_mean': 4.686221106052399, 'latency_p50': 4.689862370491028, 'latency_p90': 5.215206623077393}, {'batch_size': 5, 'throughput': 0.9383789652735032, 'latency_mean': 5.296363946199417, 'latency_p50': 5.285581588745117, 'latency_p90': 6.012956261634827}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-gfv
model_name: temp-8
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-gfv1v2ep2
model_size: 22B
num_battles: 4837
num_wins: 2366
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.66
timestamp: 2024-09-24T15:39:15+00:00
us_pacific_date: 2024-09-24
win_ratio: 0.48914616497829233
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 zonemercy-vingt-deux-gfv-3432-v1-mkmlizer
Waiting for job on zonemercy-vingt-deux-gfv-3432-v1-mkmlizer to finish
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-gfv-3432-v1-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
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: Downloaded to shared memory in 180.436s
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp7hpxbwvg, device:0
zonemercy-vingt-deux-gfv-3432-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
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/config.json
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/special_tokens_map.json
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/tokenizer_config.json
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/tokenizer.json
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-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/flywheel_model.1.safetensors
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-gfv-3432-v1/flywheel_model.0.safetensors
zonemercy-vingt-deux-gfv-3432-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/507 [00:00<00:15, 33.50it/s]
Loading 0:   2%|▏         | 8/507 [00:00<00:17, 27.84it/s]
Loading 0:   2%|▏         | 12/507 [00:00<00:18, 26.45it/s]
Loading 0:   3%|▎         | 15/507 [00:00<00:21, 22.97it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:18, 25.77it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:16, 28.64it/s]
Loading 0:   5%|▌         | 26/507 [00:01<00:26, 18.35it/s]
Loading 0:   6%|▌         | 29/507 [00:01<00:23, 20.01it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:27, 17.27it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:20, 22.97it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:20, 23.05it/s]
Loading 0:   8%|▊         | 43/507 [00:01<00:19, 23.42it/s]
Loading 0:   9%|▉         | 47/507 [00:02<00:19, 23.69it/s]
Loading 0:  10%|█         | 51/507 [00:02<00:17, 26.81it/s]
Loading 0:  11%|█         | 54/507 [00:02<00:25, 17.66it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:21, 20.96it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:20, 21.68it/s]
Loading 0:  13%|█▎        | 66/507 [00:02<00:18, 24.50it/s]
Loading 0:  14%|█▎        | 69/507 [00:03<00:19, 22.34it/s]
Loading 0:  14%|█▍        | 73/507 [00:03<00:17, 25.23it/s]
Loading 0:  15%|█▌        | 77/507 [00:03<00:15, 27.60it/s]
Loading 0:  16%|█▌        | 80/507 [00:03<00:21, 19.93it/s]
Loading 0:  16%|█▋        | 83/507 [00:03<00:22, 18.92it/s]
Loading 0:  17%|█▋        | 87/507 [00:03<00:18, 22.48it/s]
Loading 0:  18%|█▊        | 91/507 [00:03<00:16, 25.75it/s]
Loading 0:  19%|█▊        | 94/507 [00:04<00:16, 24.72it/s]
Loading 0:  19%|█▉        | 97/507 [00:04<00:16, 25.11it/s]
Loading 0:  20%|█▉        | 100/507 [00:04<00:20, 19.98it/s]
Loading 0:  21%|██        | 105/507 [00:04<00:15, 25.37it/s]
Loading 0:  21%|██▏       | 108/507 [00:04<00:22, 17.42it/s]
Loading 0:  22%|██▏       | 112/507 [00:05<00:19, 20.70it/s]
Loading 0:  23%|██▎       | 115/507 [00:05<00:18, 21.44it/s]
Loading 0:  24%|██▎       | 120/507 [00:05<00:16, 24.14it/s]
Loading 0:  24%|██▍       | 123/507 [00:05<00:17, 22.39it/s]
Loading 0:  25%|██▌       | 127/507 [00:05<00:15, 25.09it/s]
Loading 0:  26%|██▌       | 131/507 [00:05<00:13, 27.71it/s]
Loading 0:  26%|██▋       | 134/507 [00:05<00:18, 20.13it/s]
Loading 0:  27%|██▋       | 137/507 [00:06<00:17, 21.48it/s]
Loading 0:  28%|██▊       | 140/507 [00:06<00:19, 18.37it/s]
Loading 0:  29%|██▊       | 145/507 [00:06<00:15, 23.97it/s]
Loading 0:  29%|██▉       | 148/507 [00:06<00:14, 24.18it/s]
Loading 0:  30%|██▉       | 151/507 [00:06<00:14, 24.20it/s]
Loading 0:  31%|███       | 155/507 [00:06<00:14, 24.35it/s]
Loading 0:  31%|███▏      | 159/507 [00:06<00:12, 27.30it/s]
Loading 0:  32%|███▏      | 162/507 [00:07<00:19, 18.06it/s]
Loading 0:  33%|███▎      | 166/507 [00:07<00:15, 21.37it/s]
Loading 0:  33%|███▎      | 169/507 [00:07<00:15, 22.00it/s]
Loading 0:  34%|███▍      | 172/507 [00:07<00:14, 23.67it/s]
Loading 0:  35%|███▍      | 175/507 [00:07<00:13, 24.08it/s]
Loading 0:  35%|███▌      | 178/507 [00:07<00:13, 23.96it/s]
Loading 0:  36%|███▌      | 181/507 [00:07<00:12, 25.41it/s]
Loading 0:  36%|███▋      | 185/507 [00:08<00:11, 28.59it/s]
Loading 0:  37%|███▋      | 188/507 [00:08<00:16, 19.56it/s]
Loading 0:  38%|███▊      | 191/507 [00:08<00:14, 21.20it/s]
Loading 0:  38%|███▊      | 194/507 [00:08<00:17, 18.09it/s]
Loading 0:  39%|███▉      | 199/507 [00:08<00:12, 23.74it/s]
Loading 0:  40%|███▉      | 202/507 [00:08<00:12, 23.95it/s]
Loading 0:  40%|████      | 205/507 [00:09<00:12, 23.97it/s]
Loading 0:  41%|████      | 208/507 [00:09<00:11, 25.01it/s]
Loading 0:  42%|████▏     | 212/507 [00:09<00:10, 27.46it/s]
Loading 0:  42%|████▏     | 215/507 [00:09<00:14, 19.66it/s]
Loading 0:  43%|████▎     | 218/507 [00:09<00:13, 21.04it/s]
Loading 0:  44%|████▎     | 221/507 [00:09<00:16, 17.86it/s]
Loading 0:  45%|████▍     | 226/507 [00:09<00:12, 23.41it/s]
Loading 0:  45%|████▌     | 229/507 [00:10<00:11, 23.90it/s]
Loading 0:  46%|████▌     | 232/507 [00:10<00:11, 24.07it/s]
Loading 0:  47%|████▋     | 236/507 [00:10<00:11, 24.27it/s]
Loading 0:  47%|████▋     | 240/507 [00:10<00:09, 27.68it/s]
Loading 0:  48%|████▊     | 243/507 [00:10<00:14, 18.38it/s]
Loading 0:  49%|████▊     | 247/507 [00:10<00:11, 21.68it/s]
Loading 0:  49%|████▉     | 250/507 [00:11<00:11, 22.39it/s]
Loading 0:  50%|█████     | 255/507 [00:11<00:10, 24.99it/s]
Loading 0:  51%|█████     | 258/507 [00:11<00:10, 22.94it/s]
Loading 0:  52%|█████▏    | 262/507 [00:11<00:09, 25.62it/s]
Loading 0:  52%|█████▏    | 266/507 [00:11<00:08, 28.23it/s]
Loading 0:  53%|█████▎    | 270/507 [00:11<00:12, 18.49it/s]
Loading 0:  54%|█████▍    | 274/507 [00:12<00:10, 21.44it/s]
Loading 0:  55%|█████▍    | 277/507 [00:12<00:10, 21.90it/s]
Loading 0:  56%|█████▌    | 282/507 [00:12<00:09, 24.47it/s]
Loading 0:  56%|█████▌    | 285/507 [00:12<00:09, 22.71it/s]
Loading 0:  57%|█████▋    | 289/507 [00:12<00:08, 25.80it/s]
Loading 0:  58%|█████▊    | 293/507 [00:12<00:07, 28.26it/s]
Loading 0:  59%|█████▊    | 297/507 [00:13<00:11, 18.80it/s]
Loading 0:  59%|█████▉    | 300/507 [00:27<04:11,  1.22s/it]
Loading 0:  60%|█████▉    | 302/507 [00:27<03:24,  1.00it/s]
Loading 0:  60%|██████    | 306/507 [00:27<02:13,  1.51it/s]
Loading 0:  61%|██████    | 309/507 [00:27<01:38,  2.01it/s]
Loading 0:  62%|██████▏   | 312/507 [00:28<01:12,  2.69it/s]
Loading 0:  62%|██████▏   | 316/507 [00:28<00:48,  3.98it/s]
Loading 0:  63%|██████▎   | 321/507 [00:28<00:31,  5.98it/s]
Loading 0:  64%|██████▍   | 324/507 [00:28<00:27,  6.59it/s]
Loading 0:  65%|██████▍   | 328/507 [00:28<00:20,  8.86it/s]
Loading 0:  65%|██████▌   | 331/507 [00:28<00:16, 10.58it/s]
Loading 0:  66%|██████▋   | 336/507 [00:29<00:12, 14.09it/s]
Loading 0:  67%|██████▋   | 339/507 [00:29<00:11, 14.86it/s]
Loading 0:  68%|██████▊   | 343/507 [00:29<00:08, 18.25it/s]
Loading 0:  68%|██████▊   | 347/507 [00:29<00:07, 21.85it/s]
Loading 0:  69%|██████▉   | 351/507 [00:29<00:09, 16.43it/s]
Loading 0:  70%|███████   | 355/507 [00:29<00:07, 19.50it/s]
Loading 0:  71%|███████   | 358/507 [00:30<00:07, 20.55it/s]
Loading 0:  71%|███████   | 361/507 [00:30<00:06, 22.16it/s]
Loading 0:  72%|███████▏  | 364/507 [00:30<00:06, 22.96it/s]
Loading 0:  72%|███████▏  | 367/507 [00:30<00:05, 23.56it/s]
Loading 0:  73%|███████▎  | 371/507 [00:30<00:05, 24.21it/s]
Loading 0:  74%|███████▍  | 376/507 [00:30<00:05, 23.03it/s]
Loading 0:  75%|███████▍  | 379/507 [00:30<00:06, 21.26it/s]
Loading 0:  75%|███████▌  | 382/507 [00:31<00:05, 22.29it/s]
Loading 0:  76%|███████▌  | 385/507 [00:31<00:05, 22.78it/s]
Loading 0:  77%|███████▋  | 388/507 [00:31<00:04, 24.27it/s]
Loading 0:  77%|███████▋  | 391/507 [00:31<00:04, 24.54it/s]
Loading 0:  78%|███████▊  | 394/507 [00:31<00:04, 24.84it/s]
Loading 0:  79%|███████▊  | 398/507 [00:31<00:04, 24.71it/s]
Loading 0:  79%|███████▉  | 402/507 [00:31<00:03, 27.94it/s]
Loading 0:  80%|███████▉  | 405/507 [00:32<00:05, 18.59it/s]
Loading 0:  81%|████████  | 409/507 [00:32<00:04, 21.69it/s]
Loading 0:  81%|████████▏ | 412/507 [00:32<00:04, 22.38it/s]
Loading 0:  82%|████████▏ | 417/507 [00:32<00:03, 25.03it/s]
Loading 0:  83%|████████▎ | 420/507 [00:32<00:03, 23.09it/s]
Loading 0:  84%|████████▎ | 424/507 [00:32<00:03, 25.98it/s]
Loading 0:  84%|████████▍ | 428/507 [00:32<00:02, 28.61it/s]
Loading 0:  85%|████████▌ | 432/507 [00:33<00:04, 18.48it/s]
Loading 0:  86%|████████▌ | 436/507 [00:33<00:03, 21.46it/s]
Loading 0:  87%|████████▋ | 439/507 [00:33<00:03, 22.09it/s]
Loading 0:  88%|████████▊ | 444/507 [00:33<00:02, 24.51it/s]
Loading 0:  88%|████████▊ | 447/507 [00:33<00:02, 22.14it/s]
Loading 0:  89%|████████▉ | 451/507 [00:34<00:02, 25.40it/s]
Loading 0:  90%|████████▉ | 455/507 [00:34<00:01, 28.39it/s]
Loading 0:  91%|█████████ | 459/507 [00:34<00:02, 19.00it/s]
Loading 0:  91%|█████████▏| 463/507 [00:34<00:01, 22.05it/s]
Loading 0:  92%|█████████▏| 466/507 [00:34<00:01, 22.44it/s]
Loading 0:  93%|█████████▎| 471/507 [00:34<00:01, 24.99it/s]
Loading 0:  93%|█████████▎| 474/507 [00:35<00:01, 21.28it/s]
Loading 0:  94%|█████████▍| 478/507 [00:35<00:01, 23.88it/s]
Loading 0:  95%|█████████▌| 482/507 [00:35<00:00, 26.28it/s]
Loading 0:  96%|█████████▌| 485/507 [00:37<00:04,  4.86it/s]
Loading 0:  96%|█████████▋| 488/507 [00:37<00:03,  5.93it/s]
Loading 0:  97%|█████████▋| 491/507 [00:37<00:02,  7.48it/s]
Loading 0:  97%|█████████▋| 494/507 [00:37<00:01,  9.16it/s]
Loading 0:  98%|█████████▊| 497/507 [00:38<00:00, 11.16it/s]
Loading 0:  99%|█████████▊| 500/507 [00:38<00:00, 13.05it/s]
Loading 0:  99%|█████████▉| 503/507 [00:38<00:00, 14.23it/s]
Loading 0: 100%|█████████▉| 506/507 [00:38<00:00, 16.23it/s]
                                                            

Job zonemercy-vingt-deux-gfv-3432-v1-mkmlizer completed after 269.91s with status: succeeded
Stopping job with name zonemercy-vingt-deux-gfv-3432-v1-mkmlizer
Pipeline stage MKMLizer completed in 270.59s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-gfv-3432-v1
Waiting for inference service zonemercy-vingt-deux-gfv-3432-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
Inference service zonemercy-vingt-deux-gfv-3432-v1 ready after 203.98240542411804s
Pipeline stage MKMLDeployer completed in 204.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.3562071323394775s
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
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 5.154017448425293s
Received healthy response to inference request in 3.1481847763061523s
Received healthy response to inference request in 2.874455690383911s
Received healthy response to inference request in 7.563024282455444s
5 requests
0 failed requests
5th percentile: 2.9292015075683593
10th percentile: 2.9839473247528074
20th percentile: 3.093438959121704
30th percentile: 3.1897892475128176
40th percentile: 3.2729981899261475
50th percentile: 3.3562071323394775
60th percentile: 4.0753312587738035
70th percentile: 4.7944553852081295
80th percentile: 5.635818815231324
90th percentile: 6.5994215488433845
95th percentile: 7.0812229156494135
99th percentile: 7.466664009094238
mean time: 4.419177865982055
%s, retrying in %s seconds...
Received healthy response to inference request in 3.0697453022003174s
Received healthy response to inference request in 2.8511149883270264s
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 2.3666234016418457s
Received healthy response to inference request in 2.5403380393981934s
Received healthy response to inference request in 3.6470096111297607s
5 requests
0 failed requests
5th percentile: 2.4013663291931153
10th percentile: 2.436109256744385
20th percentile: 2.5055951118469237
30th percentile: 2.60249342918396
40th percentile: 2.7268042087554933
50th percentile: 2.8511149883270264
60th percentile: 2.938567113876343
70th percentile: 3.026019239425659
80th percentile: 3.185198163986206
90th percentile: 3.416103887557983
95th percentile: 3.531556749343872
99th percentile: 3.623919038772583
mean time: 2.8949662685394286
Pipeline stage StressChecker completed in 38.52s
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 6.36s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_3432_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 0.17s
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 zonemercy-vingt-deux-gfv-3432-v1-profiler
Waiting for inference service zonemercy-vingt-deux-gfv-3432-v1-profiler to be ready
Inference service zonemercy-vingt-deux-gfv-3432-v1-profiler ready after 330.81877040863037s
Pipeline stage MKMLProfilerDeployer completed in 331.21s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deuxce729853e63fe6b14004c52c84ad81f2-deplovqx7k:/code/chaiverse_profiler_1727193245 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deuxce729853e63fe6b14004c52c84ad81f2-deplovqx7k --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727193245 && 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_1727193245/summary.json'
kubectl exec -it zonemercy-vingt-deuxce729853e63fe6b14004c52c84ad81f2-deplovqx7k --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727193245/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1598.96s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-gfv-3432-v1-profiler is running
Tearing down inference service zonemercy-vingt-deux-gfv-3432-v1-profiler
Service zonemercy-vingt-deux-gfv-3432-v1-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.34s
Shutdown handler de-registered
zonemercy-vingt-deux-gfv_3432_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of zonemercy-vingt-deux-gfv_3432_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
admin requested tearing down of zonemercy-vingt-deux-v1-1e5_v5
Running pipeline stage MKMLDeleter
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
admin requested tearing down of zonemercy-vingt-deux-v1-_8973_v1
run pipeline stage %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-v2-1e5_v1
Running pipeline stage MKMLDeleter
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
admin requested tearing down of zonemercy-vingt-deux-v2-1e5_v2
run pipeline stage %s
%s, retrying in %s seconds...
run pipeline %s
Shutdown handler not registered because Python interpreter is not running in the main thread
Running pipeline stage MKMLDeleter
%s, retrying in %s seconds...
run pipeline stage %s
run pipeline %s
%s, retrying in %s seconds...
%s, retrying in %s seconds...
Running pipeline stage MKMLDeleter
run pipeline stage %s
Checking if service zonemercy-vingt-deux-v1-1e5-v5 is running
Checking if service zonemercy-vingt-deux-gfv-3432-v1 is running
Checking if service zonemercy-vingt-deux-v1-8973-v1 is running
Running pipeline stage MKMLDeleter
Checking if service zonemercy-vingt-deux-v2-1e5-v1 is running
Checking if service zonemercy-vingt-deux-v2-1e5-v2 is running
Tearing down inference service zonemercy-vingt-deux-v1-1e5-v5
Tearing down inference service zonemercy-vingt-deux-v1-8973-v1
Tearing down inference service zonemercy-vingt-deux-gfv-3432-v1
Tearing down inference service zonemercy-vingt-deux-v2-1e5-v2
Service zonemercy-vingt-deux-v1-1e5-v5 has been torndown
Service zonemercy-vingt-deux-v1-8973-v1 has been torndown
Service zonemercy-vingt-deux-gfv-3432-v1 has been torndown
Service zonemercy-vingt-deux-v2-1e5-v2 has been torndown
Pipeline stage MKMLDeleter completed in 4.38s
Pipeline stage MKMLDeleter completed in 3.69s
Tearing down inference service zonemercy-vingt-deux-v2-1e5-v1
Pipeline stage MKMLDeleter completed in 5.43s
Pipeline stage MKMLDeleter completed in 3.43s
run pipeline stage %s
run pipeline stage %s
Service zonemercy-vingt-deux-v2-1e5-v1 has been torndown
run pipeline stage %s
run pipeline stage %s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Pipeline stage MKMLDeleter completed in 4.65s
Running pipeline stage MKMLModelDeleter
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from S3
run pipeline stage %s
Cleaning model data from S3
Cleaning model data from S3
Cleaning model data from model cache
Cleaning model data from model cache
Running pipeline stage MKMLModelDeleter
Cleaning model data from model cache
Cleaning model data from model cache
Cleaning model data from S3
Cleaning model data from model cache
Deleting key zonemercy-vingt-deux-v2-1e5-v1/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-8973-v1/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-8973-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-8973-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/flywheel_model.1.safetensors from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-8973-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/tokenizer.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 6.98s
Deleting key zonemercy-vingt-deux-v1-8973-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/tokenizer.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v1-1e5-v5/tokenizer_config.json from bucket guanaco-mkml-models
Shutdown handler de-registered
Deleting key zonemercy-vingt-deux-v1-8973-v1/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-v2-1e5-v2/tokenizer_config.json from bucket guanaco-mkml-models
Deleting key zonemercy-vingt-deux-gfv-3432-v1/tokenizer_config.json from bucket guanaco-mkml-models
Pipeline stage MKMLModelDeleter completed in 9.17s
zonemercy-vingt-deux-v2-1e5_v1 status is now torndown due to DeploymentManager action
Pipeline stage MKMLModelDeleter completed in 9.44s
Pipeline stage MKMLModelDeleter completed in 9.16s
Shutdown handler de-registered
Pipeline stage MKMLModelDeleter completed in 9.37s
Shutdown handler de-registered
Shutdown handler de-registered
zonemercy-vingt-deux-v1-1e5_v5 status is now torndown due to DeploymentManager action
Shutdown handler de-registered
zonemercy-vingt-deux-v1-_8973_v1 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-1e5_v2 status is now torndown due to DeploymentManager action
zonemercy-vingt-deux-v2-1e5_v2 status is now torndown due to DeploymentManager action