failspy-codestral-22b-v0_8790

developer_uid: zonemercy
submission_id: failspy-codestral-22b-v0_8790_v1
model_name: raifle-acolyte-22b_v1
model_group: failspy/Codestral-22B-v0
status: torndown
timestamp: 2024-10-10T23:01:34+00:00
num_battles: 9128
num_wins: 3728
celo_rating: 1187.71
family_friendly_score: 0.5443739326191586
family_friendly_standard_error: 0.005335361480460363
submission_type: basic
model_repo: failspy/Codestral-22B-v0.1-abliterated-v3
model_architecture: MistralForCausalLM
model_num_parameters: 22247282688.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: raifle-acolyte-22b_v1
is_internal_developer: True
language_model: failspy/Codestral-22B-v0.1-abliterated-v3
model_size: 22B
ranking_group: single
us_pacific_date: 2024-10-10
win_ratio: 0.4084136722173532
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', '</s>', '####', 'Bot:', 'User:', 'You:', '<|im_end|>', '<|eot_id|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
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}
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 failspy-codestral-22b-v0-8790-v1-mkmlizer
Waiting for job on failspy-codestral-22b-v0-8790-v1-mkmlizer to finish
failspy-codestral-22b-v0-8790-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║     _____            __           __                                ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║       /___/                                                         ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║                                                                     ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  https://mk1.ai                                                     ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║                                                                     ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  belonging to:                                                      ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║                                                                     ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  Chai Research Corp.                                                ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ║                                                                     ║
failspy-codestral-22b-v0-8790-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
failspy-codestral-22b-v0-8790-v1-mkmlizer: Downloaded to shared memory in 101.333s
failspy-codestral-22b-v0-8790-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpjuquyqvg, device:0
failspy-codestral-22b-v0-8790-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
failspy-codestral-22b-v0-8790-v1-mkmlizer: quantized model in 50.031s
failspy-codestral-22b-v0-8790-v1-mkmlizer: Processed model failspy/Codestral-22B-v0.1-abliterated-v3 in 151.364s
failspy-codestral-22b-v0-8790-v1-mkmlizer: creating bucket guanaco-mkml-models
failspy-codestral-22b-v0-8790-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
failspy-codestral-22b-v0-8790-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/config.json
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/special_tokens_map.json
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/tokenizer_config.json
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/tokenizer.model
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/tokenizer.json
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/flywheel_model.1.safetensors
failspy-codestral-22b-v0-8790-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/failspy-codestral-22b-v0-8790-v1/flywheel_model.0.safetensors
failspy-codestral-22b-v0-8790-v1-mkmlizer: 
Loading 0:   0%|          | 0/507 [00:00<?, ?it/s]
Loading 0:   1%|          | 5/507 [00:00<00:21, 22.93it/s]
Loading 0:   2%|▏         | 10/507 [00:00<00:15, 31.22it/s]
Loading 0:   3%|▎         | 14/507 [00:00<00:19, 25.81it/s]
Loading 0:   4%|▎         | 19/507 [00:00<00:15, 30.94it/s]
Loading 0:   5%|▍         | 23/507 [00:00<00:18, 26.76it/s]
Loading 0:   6%|▌         | 28/507 [00:00<00:15, 29.97it/s]
Loading 0:   6%|▋         | 32/507 [00:01<00:17, 26.40it/s]
Loading 0:   7%|▋         | 37/507 [00:01<00:15, 30.23it/s]
Loading 0:   8%|▊         | 41/507 [00:01<00:17, 26.15it/s]
Loading 0:   9%|▉         | 46/507 [00:01<00:15, 29.91it/s]
Loading 0:  10%|▉         | 50/507 [00:01<00:16, 27.39it/s]
Loading 0:  10%|█         | 53/507 [00:02<00:23, 19.14it/s]
Loading 0:  11%|█         | 56/507 [00:02<00:24, 18.31it/s]
Loading 0:  12%|█▏        | 61/507 [00:02<00:19, 23.23it/s]
Loading 0:  13%|█▎        | 65/507 [00:02<00:19, 22.36it/s]
Loading 0:  14%|█▍        | 70/507 [00:02<00:16, 26.60it/s]
Loading 0:  15%|█▍        | 74/507 [00:02<00:14, 28.94it/s]
Loading 0:  16%|█▌        | 79/507 [00:02<00:12, 33.37it/s]
Loading 0:  16%|█▋        | 83/507 [00:03<00:13, 31.37it/s]
Loading 0:  17%|█▋        | 87/507 [00:03<00:14, 29.86it/s]
Loading 0:  18%|█▊        | 91/507 [00:03<00:14, 28.57it/s]
Loading 0:  19%|█▊        | 95/507 [00:03<00:13, 30.49it/s]
Loading 0:  20%|█▉        | 99/507 [00:03<00:15, 26.46it/s]
Loading 0:  20%|██        | 103/507 [00:03<00:14, 27.72it/s]
Loading 0:  21%|██        | 107/507 [00:04<00:15, 25.23it/s]
Loading 0:  22%|██▏       | 112/507 [00:04<00:13, 29.15it/s]
Loading 0:  23%|██▎       | 116/507 [00:04<00:20, 18.87it/s]
Loading 0:  24%|██▍       | 122/507 [00:04<00:17, 21.81it/s]
Loading 0:  25%|██▌       | 127/507 [00:04<00:15, 25.24it/s]
Loading 0:  26%|██▌       | 131/507 [00:05<00:15, 24.09it/s]
Loading 0:  27%|██▋       | 136/507 [00:05<00:13, 27.88it/s]
Loading 0:  28%|██▊       | 140/507 [00:05<00:14, 25.54it/s]
Loading 0:  29%|██▊       | 145/507 [00:05<00:12, 29.05it/s]
Loading 0:  29%|██▉       | 149/507 [00:05<00:13, 26.27it/s]
Loading 0:  30%|███       | 154/507 [00:05<00:11, 29.50it/s]
Loading 0:  31%|███       | 158/507 [00:06<00:13, 26.40it/s]
Loading 0:  32%|███▏      | 163/507 [00:06<00:11, 29.67it/s]
Loading 0:  33%|███▎      | 168/507 [00:06<00:11, 30.43it/s]
Loading 0:  34%|███▍      | 172/507 [00:06<00:16, 20.19it/s]
Loading 0:  35%|███▍      | 176/507 [00:06<00:16, 20.24it/s]
Loading 0:  36%|███▌      | 181/507 [00:06<00:13, 23.98it/s]
Loading 0:  36%|███▋      | 185/507 [00:07<00:14, 22.84it/s]
Loading 0:  37%|███▋      | 190/507 [00:07<00:11, 27.09it/s]
Loading 0:  38%|███▊      | 194/507 [00:07<00:12, 24.71it/s]
Loading 0:  39%|███▉      | 199/507 [00:07<00:10, 28.31it/s]
Loading 0:  40%|████      | 203/507 [00:07<00:11, 25.53it/s]
Loading 0:  41%|████      | 208/507 [00:07<00:10, 28.97it/s]
Loading 0:  42%|████▏     | 212/507 [00:08<00:11, 26.03it/s]
Loading 0:  43%|████▎     | 217/507 [00:08<00:09, 29.89it/s]
Loading 0:  44%|████▎     | 221/507 [00:08<00:10, 27.40it/s]
Loading 0:  44%|████▍     | 224/507 [00:08<00:14, 19.00it/s]
Loading 0:  45%|████▌     | 230/507 [00:08<00:12, 21.68it/s]
Loading 0:  46%|████▋     | 235/507 [00:09<00:10, 25.32it/s]
Loading 0:  47%|████▋     | 239/507 [00:09<00:11, 23.50it/s]
Loading 0:  48%|████▊     | 244/507 [00:09<00:09, 27.16it/s]
Loading 0:  49%|████▉     | 248/507 [00:09<00:10, 24.99it/s]
Loading 0:  50%|████▉     | 253/507 [00:09<00:09, 28.22it/s]
Loading 0:  51%|█████     | 257/507 [00:09<00:09, 25.50it/s]
Loading 0:  52%|█████▏    | 262/507 [00:10<00:08, 28.68it/s]
Loading 0:  52%|█████▏    | 266/507 [00:10<00:09, 25.66it/s]
Loading 0:  53%|█████▎    | 271/507 [00:10<00:08, 28.39it/s]
Loading 0:  54%|█████▍    | 275/507 [00:10<00:09, 25.47it/s]
Loading 0:  55%|█████▌    | 280/507 [00:10<00:07, 28.48it/s]
Loading 0:  56%|█████▌    | 284/507 [00:11<00:10, 20.36it/s]
Loading 0:  57%|█████▋    | 287/507 [00:11<00:11, 18.58it/s]
Loading 0:  58%|█████▊    | 293/507 [00:11<00:09, 21.57it/s]
Loading 0:  59%|█████▉    | 298/507 [00:11<00:08, 25.15it/s]
Loading 0:  59%|█████▉    | 301/507 [00:26<03:51,  1.12s/it]
Loading 0:  60%|█████▉    | 302/507 [00:27<03:31,  1.03s/it]
Loading 0:  61%|██████    | 307/507 [00:27<02:07,  1.57it/s]
Loading 0:  61%|██████    | 310/507 [00:27<01:35,  2.05it/s]
Loading 0:  62%|██████▏   | 313/507 [00:27<01:11,  2.72it/s]
Loading 0:  62%|██████▏   | 316/507 [00:27<00:52,  3.61it/s]
Loading 0:  63%|██████▎   | 320/507 [00:27<00:36,  5.06it/s]
Loading 0:  64%|██████▍   | 325/507 [00:27<00:23,  7.60it/s]
Loading 0:  65%|██████▍   | 329/507 [00:28<00:18,  9.41it/s]
Loading 0:  66%|██████▌   | 334/507 [00:28<00:13, 12.88it/s]
Loading 0:  67%|██████▋   | 339/507 [00:28<00:10, 15.89it/s]
Loading 0:  68%|██████▊   | 343/507 [00:28<00:12, 13.62it/s]
Loading 0:  68%|██████▊   | 347/507 [00:29<00:10, 14.79it/s]
Loading 0:  69%|██████▉   | 352/507 [00:29<00:08, 18.68it/s]
Loading 0:  70%|███████   | 356/507 [00:29<00:07, 19.17it/s]
Loading 0:  71%|███████   | 361/507 [00:29<00:06, 22.88it/s]
Loading 0:  72%|███████▏  | 365/507 [00:29<00:06, 21.85it/s]
Loading 0:  73%|███████▎  | 370/507 [00:29<00:05, 25.56it/s]
Loading 0:  74%|███████▍  | 374/507 [00:30<00:05, 23.64it/s]
Loading 0:  75%|███████▍  | 379/507 [00:30<00:04, 25.91it/s]
Loading 0:  76%|███████▌  | 383/507 [00:30<00:05, 24.23it/s]
Loading 0:  77%|███████▋  | 388/507 [00:30<00:04, 27.85it/s]
Loading 0:  77%|███████▋  | 392/507 [00:30<00:04, 25.15it/s]
Loading 0:  78%|███████▊  | 395/507 [00:31<00:06, 17.58it/s]
Loading 0:  79%|███████▉  | 400/507 [00:31<00:04, 22.32it/s]
Loading 0:  79%|███████▉  | 403/507 [00:31<00:04, 22.15it/s]
Loading 0:  80%|████████  | 406/507 [00:31<00:04, 22.72it/s]
Loading 0:  81%|████████  | 410/507 [00:31<00:04, 21.89it/s]
Loading 0:  82%|████████▏ | 415/507 [00:31<00:03, 25.55it/s]
Loading 0:  83%|████████▎ | 419/507 [00:31<00:03, 23.50it/s]
Loading 0:  84%|████████▎ | 424/507 [00:32<00:03, 27.52it/s]
Loading 0:  84%|████████▍ | 428/507 [00:32<00:03, 24.92it/s]
Loading 0:  85%|████████▌ | 433/507 [00:32<00:02, 28.46it/s]
Loading 0:  86%|████████▌ | 437/507 [00:32<00:02, 25.41it/s]
Loading 0:  87%|████████▋ | 442/507 [00:32<00:02, 28.81it/s]
Loading 0:  88%|████████▊ | 446/507 [00:32<00:02, 25.95it/s]
Loading 0:  89%|████████▉ | 451/507 [00:33<00:01, 29.77it/s]
Loading 0:  90%|████████▉ | 455/507 [00:35<00:09,  5.47it/s]
Loading 0:  91%|█████████ | 459/507 [00:35<00:06,  6.95it/s]
Loading 0:  92%|█████████▏| 465/507 [00:35<00:04,  9.84it/s]
Loading 0:  93%|█████████▎| 470/507 [00:35<00:02, 12.96it/s]
Loading 0:  93%|█████████▎| 474/507 [00:36<00:02, 14.59it/s]
Loading 0:  94%|█████████▍| 479/507 [00:36<00:01, 18.41it/s]
Loading 0:  95%|█████████▌| 483/507 [00:36<00:01, 19.52it/s]
Loading 0:  96%|█████████▋| 488/507 [00:36<00:00, 24.21it/s]
Loading 0:  97%|█████████▋| 492/507 [00:36<00:00, 23.51it/s]
Loading 0:  98%|█████████▊| 497/507 [00:36<00:00, 27.91it/s]
Loading 0:  99%|█████████▉| 501/507 [00:36<00:00, 26.32it/s]
Loading 0: 100%|█████████▉| 506/507 [00:37<00:00, 30.04it/s]
                                                            
Job failspy-codestral-22b-v0-8790-v1-mkmlizer completed after 195.98s with status: succeeded
Stopping job with name failspy-codestral-22b-v0-8790-v1-mkmlizer
Pipeline stage MKMLizer completed in 196.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service failspy-codestral-22b-v0-8790-v1
Waiting for inference service failspy-codestral-22b-v0-8790-v1 to be ready
Inference service failspy-codestral-22b-v0-8790-v1 ready after 140.53638911247253s
Pipeline stage MKMLDeployer completed in 141.11s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5721936225891113s
Received healthy response to inference request in 1.4836723804473877s
Received healthy response to inference request in 1.467393398284912s
Received healthy response to inference request in 2.3463940620422363s
Received healthy response to inference request in 2.186163902282715s
5 requests
0 failed requests
5th percentile: 1.4706491947174072
10th percentile: 1.4739049911499023
20th percentile: 1.4804165840148926
30th percentile: 1.5013766288757324
40th percentile: 1.5367851257324219
50th percentile: 1.5721936225891113
60th percentile: 1.8177817344665526
70th percentile: 2.0633698463439942
80th percentile: 2.2182099342346193
90th percentile: 2.282301998138428
95th percentile: 2.314348030090332
99th percentile: 2.3399848556518554
mean time: 1.8111634731292725
Pipeline stage StressChecker completed in 10.65s
Shutdown handler de-registered
failspy-codestral-22b-v0_8790_v1 status is now deployed due to DeploymentManager action
failspy-codestral-22b-v0_8790_v1 status is now inactive due to auto deactivation removed underperforming models
failspy-codestral-22b-v0_8790_v1 status is now torndown due to DeploymentManager action