zonemercy-vingt-deux-v2-_1790

submission_id: zonemercy-vingt-deux-v2-_1790_v4
developer_uid: chai_backend_admin
best_of: 8
celo_rating: 1252.65
display_name: temp-7
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}
ineligible_reason: num_battles<5000
is_internal_developer: True
language_model: zonemercy/Vingt-Deux-v2-1e5ep1
latencies: [{'batch_size': 1, 'throughput': 0.3795172200910875, 'latency_mean': 2.6348644387722016, 'latency_p50': 2.634938955307007, 'latency_p90': 2.897043061256409}, {'batch_size': 2, 'throughput': 0.5944968457612515, 'latency_mean': 3.358650405406952, 'latency_p50': 3.3475664854049683, 'latency_p90': 3.6604575395584105}, {'batch_size': 3, 'throughput': 0.7470698134596526, 'latency_mean': 4.000136036872863, 'latency_p50': 3.9834372997283936, 'latency_p90': 4.38957257270813}, {'batch_size': 4, 'throughput': 0.8784275043873477, 'latency_mean': 4.543809641599655, 'latency_p50': 4.547712326049805, 'latency_p90': 5.117617177963257}, {'batch_size': 5, 'throughput': 0.9556154590063612, 'latency_mean': 5.200826135873794, 'latency_p50': 5.232406735420227, 'latency_p90': 5.82054295539856}]
max_input_tokens: 1024
max_output_tokens: 64
model_architecture: MistralForCausalLM
model_group: zonemercy/Vingt-Deux-v2-
model_name: temp-7
model_num_parameters: 22247282688.0
model_repo: zonemercy/Vingt-Deux-v2-1e5ep1
model_size: 22B
num_battles: 3091
num_wins: 1541
ranking_group: single
status: torndown
submission_type: basic
throughput_3p7s: 0.68
timestamp: 2024-09-24T16:23:00+00:00
us_pacific_date: 2024-09-24
win_ratio: 0.49854416046586864
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-v2-1790-v4-mkmlizer
Waiting for job on zonemercy-vingt-deux-v2-1790-v4-mkmlizer to finish
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║     _____            __           __                                ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║       /___/                                                         ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  Version: 0.10.1                                                    ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  https://mk1.ai                                                     ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  belonging to:                                                      ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  Chai Research Corp.                                                ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ║                                                                     ║
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission zonemercy-vingt-deux-v1-_8973_v1: ('http://zonemercy-vingt-deux-v1-8973-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: Downloaded to shared memory in 103.024s
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp1bnedsao, device:0
zonemercy-vingt-deux-v2-1790-v4-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
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: quantized model in 52.509s
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: Processed model zonemercy/Vingt-Deux-v2-1e5ep1 in 155.533s
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: creating bucket guanaco-mkml-models
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/config.json
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/special_tokens_map.json
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/tokenizer_config.json
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/tokenizer.json
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/flywheel_model.1.safetensors
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zonemercy-vingt-deux-v2-1790-v4/flywheel_model.0.safetensors
zonemercy-vingt-deux-v2-1790-v4-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/507 [00:00<00:17, 28.73it/s]
Loading 0:   1%|▏         | 7/507 [00:00<00:21, 23.07it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:21, 23.14it/s]
Loading 0:   3%|▎         | 13/507 [00:00<00:22, 22.35it/s]
Loading 0:   3%|▎         | 16/507 [00:00<00:22, 21.68it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:21, 22.49it/s]
Loading 0:   4%|▍         | 22/507 [00:00<00:20, 24.05it/s]
Loading 0:   5%|▍         | 25/507 [00:01<00:30, 16.01it/s]
Loading 0:   5%|▌         | 27/507 [00:01<00:33, 14.15it/s]
Loading 0:   6%|▌         | 31/507 [00:01<00:26, 17.96it/s]
Loading 0:   7%|▋         | 34/507 [00:01<00:25, 18.79it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:22, 20.98it/s]
Loading 0:   8%|▊         | 40/507 [00:01<00:21, 21.46it/s]
Loading 0:   8%|▊         | 43/507 [00:02<00:21, 21.94it/s]
Loading 0:   9%|▉         | 47/507 [00:02<00:20, 22.47it/s]
Loading 0:  10%|█         | 51/507 [00:02<00:17, 25.69it/s]
Loading 0:  11%|█         | 54/507 [00:02<00:28, 15.80it/s]
Loading 0:  11%|█▏        | 58/507 [00:02<00:24, 18.69it/s]
Loading 0:  12%|█▏        | 61/507 [00:03<00:22, 19.57it/s]
Loading 0:  13%|█▎        | 66/507 [00:03<00:19, 22.61it/s]
Loading 0:  14%|█▎        | 69/507 [00:03<00:21, 20.83it/s]
Loading 0:  14%|█▍        | 73/507 [00:03<00:17, 24.42it/s]
Loading 0:  15%|█▌        | 77/507 [00:03<00:16, 26.70it/s]
Loading 0:  16%|█▌        | 80/507 [00:03<00:22, 18.59it/s]
Loading 0:  16%|█▋        | 83/507 [00:04<00:23, 17.69it/s]
Loading 0:  17%|█▋        | 87/507 [00:04<00:19, 21.30it/s]
Loading 0:  18%|█▊        | 91/507 [00:04<00:17, 24.08it/s]
Loading 0:  19%|█▊        | 94/507 [00:04<00:17, 23.60it/s]
Loading 0:  19%|█▉        | 97/507 [00:04<00:16, 24.43it/s]
Loading 0:  20%|█▉        | 100/507 [00:04<00:21, 19.27it/s]
Loading 0:  21%|██        | 105/507 [00:04<00:16, 25.03it/s]
Loading 0:  21%|██▏       | 108/507 [00:05<00:24, 16.44it/s]
Loading 0:  22%|██▏       | 112/507 [00:05<00:20, 19.32it/s]
Loading 0:  23%|██▎       | 115/507 [00:05<00:19, 20.09it/s]
Loading 0:  24%|██▎       | 120/507 [00:05<00:16, 22.89it/s]
Loading 0:  24%|██▍       | 123/507 [00:05<00:18, 21.16it/s]
Loading 0:  25%|██▌       | 127/507 [00:06<00:15, 24.56it/s]
Loading 0:  26%|██▌       | 131/507 [00:06<00:13, 27.01it/s]
Loading 0:  26%|██▋       | 134/507 [00:06<00:19, 19.33it/s]
Loading 0:  27%|██▋       | 137/507 [00:06<00:17, 20.56it/s]
Loading 0:  28%|██▊       | 140/507 [00:06<00:21, 17.39it/s]
Loading 0:  29%|██▊       | 145/507 [00:06<00:15, 22.99it/s]
Loading 0:  29%|██▉       | 148/507 [00:07<00:15, 23.24it/s]
Loading 0:  30%|██▉       | 151/507 [00:07<00:15, 23.71it/s]
Loading 0:  31%|███       | 155/507 [00:07<00:14, 23.92it/s]
Loading 0:  31%|███▏      | 159/507 [00:07<00:12, 27.32it/s]
Loading 0:  32%|███▏      | 162/507 [00:07<00:19, 17.76it/s]
Loading 0:  33%|███▎      | 166/507 [00:07<00:16, 20.70it/s]
Loading 0:  33%|███▎      | 169/507 [00:08<00:15, 21.32it/s]
Loading 0:  34%|███▍      | 172/507 [00:08<00:14, 22.78it/s]
Loading 0:  35%|███▍      | 175/507 [00:08<00:14, 22.92it/s]
Loading 0:  35%|███▌      | 178/507 [00:08<00:14, 22.96it/s]
Loading 0:  36%|███▌      | 182/507 [00:08<00:13, 23.55it/s]
Loading 0:  37%|███▋      | 186/507 [00:08<00:11, 26.95it/s]
Loading 0:  37%|███▋      | 189/507 [00:08<00:18, 17.32it/s]
Loading 0:  38%|███▊      | 193/507 [00:09<00:15, 20.47it/s]
Loading 0:  39%|███▊      | 196/507 [00:09<00:14, 21.15it/s]
Loading 0:  40%|███▉      | 201/507 [00:09<00:12, 23.62it/s]
Loading 0:  40%|████      | 204/507 [00:09<00:13, 21.68it/s]
Loading 0:  41%|████      | 208/507 [00:09<00:11, 25.17it/s]
Loading 0:  42%|████▏     | 212/507 [00:09<00:10, 27.41it/s]
Loading 0:  42%|████▏     | 215/507 [00:10<00:14, 19.70it/s]
Loading 0:  43%|████▎     | 218/507 [00:10<00:13, 20.91it/s]
Loading 0:  44%|████▎     | 221/507 [00:10<00:16, 17.47it/s]
Loading 0:  45%|████▍     | 226/507 [00:10<00:12, 22.50it/s]
Loading 0:  45%|████▌     | 229/507 [00:10<00:12, 22.80it/s]
Loading 0:  46%|████▌     | 232/507 [00:10<00:11, 22.95it/s]
Loading 0:  47%|████▋     | 236/507 [00:10<00:11, 23.30it/s]
Loading 0:  47%|████▋     | 240/507 [00:11<00:10, 26.36it/s]
Loading 0:  48%|████▊     | 243/507 [00:11<00:15, 17.44it/s]
Loading 0:  49%|████▊     | 247/507 [00:11<00:12, 20.59it/s]
Loading 0:  49%|████▉     | 250/507 [00:11<00:12, 21.20it/s]
Loading 0:  50%|█████     | 255/507 [00:11<00:10, 24.05it/s]
Loading 0:  51%|█████     | 258/507 [00:12<00:11, 22.05it/s]
Loading 0:  52%|█████▏    | 262/507 [00:12<00:09, 25.32it/s]
Loading 0:  52%|█████▏    | 266/507 [00:12<00:08, 27.40it/s]
Loading 0:  53%|█████▎    | 269/507 [00:12<00:11, 19.88it/s]
Loading 0:  54%|█████▎    | 272/507 [00:12<00:11, 21.08it/s]
Loading 0:  54%|█████▍    | 275/507 [00:12<00:13, 17.70it/s]
Loading 0:  55%|█████▌    | 280/507 [00:13<00:09, 23.05it/s]
Loading 0:  56%|█████▌    | 283/507 [00:13<00:09, 23.22it/s]
Loading 0:  56%|█████▋    | 286/507 [00:13<00:09, 23.20it/s]
Loading 0:  57%|█████▋    | 289/507 [00:13<00:08, 24.42it/s]
Loading 0:  58%|█████▊    | 293/507 [00:13<00:07, 27.23it/s]
Loading 0:  58%|█████▊    | 296/507 [00:13<00:11, 18.93it/s]
Loading 0:  59%|█████▉    | 299/507 [00:13<00:10, 20.23it/s]
Loading 0:  59%|█████▉    | 299/507 [00:28<00:10, 20.23it/s]
Loading 0:  59%|█████▉    | 300/507 [00:28<06:07,  1.77s/it]
Loading 0:  60%|█████▉    | 302/507 [00:28<04:39,  1.36s/it]
Loading 0:  60%|██████    | 306/507 [00:29<02:43,  1.23it/s]
Loading 0:  61%|██████    | 309/507 [00:29<01:54,  1.73it/s]
Loading 0:  62%|██████▏   | 312/507 [00:29<01:21,  2.38it/s]
Loading 0:  62%|██████▏   | 316/507 [00:29<00:52,  3.62it/s]
Loading 0:  63%|██████▎   | 320/507 [00:29<00:35,  5.25it/s]
Loading 0:  64%|██████▎   | 323/507 [00:30<00:30,  6.03it/s]
Loading 0:  64%|██████▍   | 326/507 [00:30<00:23,  7.57it/s]
Loading 0:  65%|██████▍   | 329/507 [00:30<00:21,  8.44it/s]
Loading 0:  66%|██████▌   | 334/507 [00:30<00:13, 12.42it/s]
Loading 0:  66%|██████▋   | 337/507 [00:30<00:11, 14.17it/s]
Loading 0:  67%|██████▋   | 340/507 [00:30<00:10, 15.70it/s]
Loading 0:  68%|██████▊   | 343/507 [00:30<00:09, 17.64it/s]
Loading 0:  68%|██████▊   | 347/507 [00:31<00:07, 21.11it/s]
Loading 0:  69%|██████▉   | 350/507 [00:31<00:09, 16.44it/s]
Loading 0:  70%|██████▉   | 353/507 [00:31<00:08, 18.02it/s]
Loading 0:  70%|███████   | 356/507 [00:31<00:09, 16.03it/s]
Loading 0:  71%|███████   | 361/507 [00:31<00:06, 21.69it/s]
Loading 0:  72%|███████▏  | 364/507 [00:31<00:06, 22.13it/s]
Loading 0:  72%|███████▏  | 367/507 [00:32<00:06, 22.31it/s]
Loading 0:  73%|███████▎  | 371/507 [00:32<00:05, 23.02it/s]
Loading 0:  74%|███████▍  | 375/507 [00:32<00:05, 26.39it/s]
Loading 0:  75%|███████▍  | 378/507 [00:32<00:07, 17.12it/s]
Loading 0:  75%|███████▌  | 382/507 [00:32<00:06, 20.22it/s]
Loading 0:  76%|███████▌  | 385/507 [00:32<00:05, 20.76it/s]
Loading 0:  77%|███████▋  | 388/507 [00:33<00:05, 22.23it/s]
Loading 0:  77%|███████▋  | 391/507 [00:33<00:05, 22.55it/s]
Loading 0:  78%|███████▊  | 394/507 [00:33<00:04, 23.01it/s]
Loading 0:  79%|███████▊  | 398/507 [00:33<00:04, 23.62it/s]
Loading 0:  79%|███████▉  | 402/507 [00:33<00:03, 27.05it/s]
Loading 0:  80%|███████▉  | 405/507 [00:33<00:05, 17.62it/s]
Loading 0:  81%|████████  | 409/507 [00:34<00:04, 20.51it/s]
Loading 0:  81%|████████▏ | 412/507 [00:34<00:04, 21.42it/s]
Loading 0:  82%|████████▏ | 417/507 [00:34<00:03, 24.15it/s]
Loading 0:  83%|████████▎ | 420/507 [00:34<00:03, 22.04it/s]
Loading 0:  84%|████████▎ | 424/507 [00:34<00:03, 25.53it/s]
Loading 0:  84%|████████▍ | 428/507 [00:34<00:02, 27.80it/s]
Loading 0:  85%|████████▌ | 432/507 [00:35<00:04, 17.98it/s]
Loading 0:  86%|████████▌ | 436/507 [00:35<00:03, 20.83it/s]
Loading 0:  87%|████████▋ | 439/507 [00:35<00:03, 21.29it/s]
Loading 0:  87%|████████▋ | 442/507 [00:35<00:02, 22.80it/s]
Loading 0:  88%|████████▊ | 445/507 [00:35<00:02, 22.80it/s]
Loading 0:  88%|████████▊ | 448/507 [00:35<00:02, 23.08it/s]
Loading 0:  89%|████████▉ | 452/507 [00:35<00:02, 23.05it/s]
Loading 0:  90%|████████▉ | 456/507 [00:36<00:01, 25.99it/s]
Loading 0:  91%|█████████ | 459/507 [00:36<00:02, 17.18it/s]
Loading 0:  91%|█████████▏| 463/507 [00:36<00:02, 19.97it/s]
Loading 0:  92%|█████████▏| 466/507 [00:36<00:02, 20.18it/s]
Loading 0:  93%|█████████▎| 469/507 [00:36<00:01, 21.84it/s]
Loading 0:  93%|█████████▎| 472/507 [00:36<00:01, 21.86it/s]
Loading 0:  94%|█████████▎| 475/507 [00:37<00:01, 21.95it/s]
Loading 0:  94%|█████████▍| 478/507 [00:37<00:01, 23.61it/s]
Loading 0:  95%|█████████▌| 482/507 [00:37<00:00, 26.30it/s]
Loading 0:  96%|█████████▌| 485/507 [00:39<00:05,  4.23it/s]
Loading 0:  96%|█████████▌| 487/507 [00:39<00:04,  4.86it/s]
Loading 0:  97%|█████████▋| 491/507 [00:39<00:02,  7.15it/s]
Loading 0:  97%|█████████▋| 494/507 [00:39<00:01,  8.98it/s]
Loading 0:  98%|█████████▊| 499/507 [00:40<00:00, 12.48it/s]
Loading 0:  99%|█████████▉| 502/507 [00:40<00:00, 13.37it/s]
Loading 0: 100%|█████████▉| 506/507 [00:40<00:00, 16.88it/s]
                                                            
Job zonemercy-vingt-deux-v2-1790-v4-mkmlizer completed after 199.61s with status: succeeded
Stopping job with name zonemercy-vingt-deux-v2-1790-v4-mkmlizer
Pipeline stage MKMLizer completed in 200.91s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zonemercy-vingt-deux-v2-1790-v4
Waiting for inference service zonemercy-vingt-deux-v2-1790-v4 to be ready
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
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
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 zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v2-1e5_v2: ('http://zonemercy-vingt-deux-v2-1e5-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
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
Failed to get response for submission zonemercy-vingt-deux-v1-_8973_v1: ('http://zonemercy-vingt-deux-v1-8973-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v1-_8973_v1: ('http://zonemercy-vingt-deux-v1-8973-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-v1-_8973_v1: ('http://zonemercy-vingt-deux-v1-8973-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Failed to get response for submission zonemercy-vingt-deux-gfv_3432_v1: ('http://zonemercy-vingt-deux-gfv-3432-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'activator request timeout')
Inference service zonemercy-vingt-deux-v2-1790-v4 ready after 231.1275293827057s
Pipeline stage MKMLDeployer completed in 231.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9030814170837402s
Received healthy response to inference request in 3.821622371673584s
Received healthy response to inference request in 2.746426582336426s
Received healthy response to inference request in 2.7514703273773193s
Received healthy response to inference request in 2.555276870727539s
5 requests
0 failed requests
5th percentile: 2.5935068130493164
10th percentile: 2.6317367553710938
20th percentile: 2.7081966400146484
30th percentile: 2.7474353313446045
40th percentile: 2.749452829360962
50th percentile: 2.7514703273773193
60th percentile: 2.8121147632598875
70th percentile: 2.872759199142456
80th percentile: 3.086789608001709
90th percentile: 3.4542059898376465
95th percentile: 3.6379141807556152
99th percentile: 3.7848807334899903
mean time: 2.9555755138397215
Pipeline stage StressChecker completed in 15.88s
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 4.24s
Shutdown handler de-registered
zonemercy-vingt-deux-v2-_1790_v4 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 0.15s
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 zonemercy-vingt-deux-v2-1790-v4-profiler
Waiting for inference service zonemercy-vingt-deux-v2-1790-v4-profiler to be ready
Inference service zonemercy-vingt-deux-v2-1790-v4-profiler ready after 591.6228861808777s
Pipeline stage MKMLProfilerDeployer completed in 592.03s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/zonemercy-vingt-deux1a749a1a91d72c33db5902964b1e6968-deplowsqzb:/code/chaiverse_profiler_1727196075 --namespace tenant-chaiml-guanaco
kubectl exec -it zonemercy-vingt-deux1a749a1a91d72c33db5902964b1e6968-deplowsqzb --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727196075 && 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_1727196075/summary.json'
kubectl exec -it zonemercy-vingt-deux1a749a1a91d72c33db5902964b1e6968-deplowsqzb --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727196075/summary.json'
Pipeline stage MKMLProfilerRunner completed in 1573.93s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service zonemercy-vingt-deux-v2-1790-v4-profiler is running
Tearing down inference service zonemercy-vingt-deux-v2-1790-v4-profiler
Service zonemercy-vingt-deux-v2-1790-v4-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.25s
Shutdown handler de-registered
zonemercy-vingt-deux-v2-_1790_v4 status is now inactive due to auto deactivation removed underperforming models
zonemercy-vingt-deux-v2-_1790_v4 status is now torndown due to DeploymentManager action