developer_uid: azuruce
submission_id: chaiml-nemo-20241015-dar_4058_v4
model_name: chaiml-nemo-20241015-dar_4058_v4
model_group: ChaiML/nemo-20241015-dar
status: torndown
timestamp: 2024-10-16T21:32:13+00:00
num_battles: 6873
num_wins: 3694
celo_rating: 1247.28
family_friendly_score: 0.5838797397580564
family_friendly_standard_error: 0.00605962589098782
submission_type: basic
model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v1-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241015-dar_4058_v4
is_internal_developer: True
language_model: ChaiML/nemo-20241015-dare_ties-remerge_v1-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-16
win_ratio: 0.5374654444929434
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', '<|eot_id|>', '<|end_of_text|>', 'You:'], 'max_input_tokens': 1024, 'best_of': 4, 'max_output_tokens': 64}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '### Response:\n{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 chaiml-nemo-20241015-dar-4058-v4-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-4058-v4-mkmlizer to finish
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: Downloaded to shared memory in 30.270s
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplv3z_2xt, device:0
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: quantized model in 36.768s
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v1-albert in 67.038s
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v4
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v4/config.json
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v4/special_tokens_map.json
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v4/tokenizer_config.json
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v4/tokenizer.json
chaiml-nemo-20241015-dar-4058-v4-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:54,  2.98s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:47,  1.24it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:06,  2.78it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.32it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.02it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 10.91it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 14.33it/s]
Loading 0:  10%|█         | 37/363 [00:06<00:17, 18.31it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:20, 16.00it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.67it/s]
Loading 0:  15%|█▍        | 54/363 [00:07<00:12, 25.72it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:10, 29.03it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:09, 31.13it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:10, 26.85it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.08it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 36.07it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:07, 37.87it/s]
Loading 0:  25%|██▌       | 91/363 [00:08<00:06, 39.91it/s]
Loading 0:  26%|██▋       | 96/363 [00:08<00:07, 34.68it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 42.46it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 41.91it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 42.48it/s]
Loading 0:  33%|███▎      | 118/363 [00:09<00:05, 43.32it/s]
Loading 0:  34%|███▍      | 123/363 [00:09<00:09, 26.52it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 33.75it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 35.51it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:06, 36.42it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 39.09it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 33.95it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 40.37it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:05, 38.74it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:05, 38.89it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 40.42it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 35.73it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 43.25it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 41.64it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:03, 43.61it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:03, 41.68it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 29.06it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 34.84it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 36.08it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 37.38it/s]
Loading 0:  62%|██████▏   | 226/363 [00:12<00:03, 40.26it/s]
Loading 0:  64%|██████▎   | 231/363 [00:12<00:03, 33.80it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:03, 37.17it/s]
Loading 0:  66%|██████▋   | 241/363 [00:12<00:03, 34.21it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:03, 34.83it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 33.10it/s]
Loading 0:  71%|███████   | 256/363 [00:12<00:02, 41.22it/s]
Loading 0:  72%|███████▏  | 261/363 [00:13<00:02, 39.66it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 39.17it/s]
Loading 0:  75%|███████▍  | 271/363 [00:13<00:02, 40.23it/s]
Loading 0:  76%|███████▌  | 276/363 [00:13<00:02, 33.68it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 28.94it/s]
Loading 0:  79%|███████▉  | 287/363 [00:13<00:02, 29.62it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 33.15it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 33.37it/s]
Loading 0:  83%|████████▎ | 301/363 [00:14<00:01, 36.29it/s]
Loading 0:  84%|████████▍ | 305/363 [00:14<00:01, 35.17it/s]
Loading 0:  85%|████████▌ | 310/363 [00:14<00:01, 38.03it/s]
Loading 0:  87%|████████▋ | 314/363 [00:14<00:01, 36.59it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 39.45it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:01, 38.70it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 38.66it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 36.79it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 39.33it/s]
Loading 0:  94%|█████████▍| 341/363 [00:15<00:00, 37.26it/s]
Loading 0:  95%|█████████▌| 346/363 [00:15<00:00, 40.09it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 39.75it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 40.58it/s]
Loading 0:  99%|█████████▉| 361/363 [00:15<00:00, 41.26it/s]
                                                            

Job chaiml-nemo-20241015-dar-4058-v4-mkmlizer completed after 96.74s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-4058-v4-mkmlizer
Pipeline stage MKMLizer completed in 98.76s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241015-dar-4058-v4
Waiting for inference service chaiml-nemo-20241015-dar-4058-v4 to be ready
Inference service chaiml-nemo-20241015-dar-4058-v4 ready after 170.60509490966797s
Pipeline stage MKMLDeployer completed in 171.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1951944828033447s
Received healthy response to inference request in 1.461275577545166s
Received healthy response to inference request in 1.6690733432769775s
Received healthy response to inference request in 1.7705259323120117s
Received healthy response to inference request in 1.7571425437927246s
5 requests
0 failed requests
5th percentile: 1.5028351306915284
10th percentile: 1.5443946838378906
20th percentile: 1.6275137901306151
30th percentile: 1.686687183380127
40th percentile: 1.7219148635864259
50th percentile: 1.7571425437927246
60th percentile: 1.7624958992004394
70th percentile: 1.7678492546081543
80th percentile: 1.8554596424102785
90th percentile: 2.0253270626068116
95th percentile: 2.110260772705078
99th percentile: 2.1782077407836913
mean time: 1.770642375946045
Pipeline stage StressChecker completed in 10.03s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_4058_v4 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_4058_v4 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_4058_v4 status is now torndown due to DeploymentManager action