chaiml-nemo-20241009-tie_7091

developer_uid: azuruce
submission_id: chaiml-nemo-20241009-tie_7091_v2
model_name: chaiml-nemo-20241009-tie_7091_v2
model_group: ChaiML/nemo-20241009_tie
status: torndown
timestamp: 2024-10-10T15:45:29+00:00
num_battles: 6240
num_wins: 3168
celo_rating: 1265.11
family_friendly_score: 0.5728992765720645
family_friendly_standard_error: 0.006371717181045074
submission_type: basic
model_repo: ChaiML/nemo-20241009_tier_merge_v4-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241009-tie_7091_v2
is_internal_developer: True
language_model: ChaiML/nemo-20241009_tier_merge_v4-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-10
win_ratio: 0.5076923076923077
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': 8, '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-20241009-tie-7091-v2-mkmlizer
Waiting for job on chaiml-nemo-20241009-tie-7091-v2-mkmlizer to finish
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: Downloaded to shared memory in 47.342s
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprfwsvbry, device:0
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: quantized model in 38.122s
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: Processed model ChaiML/nemo-20241009_tier_merge_v4-albert in 85.464s
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2/config.json
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2/special_tokens_map.json
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2/tokenizer_config.json
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2/tokenizer.json
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-7091-v2/flywheel_model.0.safetensors
chaiml-nemo-20241009-tie-7091-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:06,  3.01s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:08,  2.74it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:22,  4.24it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:50,  6.79it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:37,  8.93it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:23, 14.33it/s]
Loading 0:  10%|▉         | 36/363 [00:06<00:18, 17.78it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.52it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.99it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.48it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.11it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 28.94it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:10, 29.47it/s]
Loading 0:  18%|█▊        | 66/363 [00:08<00:09, 29.85it/s]
Loading 0:  19%|█▉        | 70/363 [00:08<00:10, 29.02it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.67it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 33.64it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 36.57it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:07, 35.00it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 36.61it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 34.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 37.46it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:07, 35.13it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 36.89it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 34.13it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:09, 25.14it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:09, 25.09it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 30.98it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:07, 30.92it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 33.47it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 32.42it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 34.81it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 33.69it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 35.96it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 34.35it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 36.91it/s]
Loading 0:  47%|████▋     | 170/363 [00:11<00:05, 34.81it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 36.52it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 34.15it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.13it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:05, 34.26it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 36.58it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:04, 34.83it/s]
Loading 0:  56%|█████▌    | 202/363 [00:12<00:06, 25.56it/s]
Loading 0:  56%|█████▋    | 205/363 [00:12<00:06, 25.39it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 31.44it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 31.45it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 34.10it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:04, 33.41it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 36.11it/s]
Loading 0:  64%|██████▍   | 233/363 [00:13<00:03, 35.16it/s]
Loading 0:  66%|██████▌   | 238/363 [00:13<00:03, 37.25it/s]
Loading 0:  67%|██████▋   | 242/363 [00:13<00:03, 35.68it/s]
Loading 0:  68%|██████▊   | 246/363 [00:13<00:03, 35.85it/s]
Loading 0:  69%|██████▉   | 250/363 [00:13<00:03, 33.00it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 38.39it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 36.77it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 38.36it/s]
Loading 0:  74%|███████▍  | 269/363 [00:14<00:02, 35.83it/s]
Loading 0:  75%|███████▌  | 274/363 [00:14<00:02, 37.50it/s]
Loading 0:  77%|███████▋  | 278/363 [00:14<00:02, 35.40it/s]
Loading 0:  78%|███████▊  | 283/363 [00:14<00:03, 26.49it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 27.58it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 31.32it/s]
Loading 0:  82%|████████▏ | 296/363 [00:14<00:02, 31.42it/s]
Loading 0:  83%|████████▎ | 301/363 [00:15<00:01, 34.46it/s]
Loading 0:  84%|████████▍ | 305/363 [00:15<00:01, 30.90it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 33.78it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:01, 33.17it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:01, 36.98it/s]
Loading 0:  89%|████████▉ | 323/363 [00:15<00:01, 35.99it/s]
Loading 0:  90%|█████████ | 328/363 [00:15<00:00, 38.24it/s]
Loading 0:  91%|█████████▏| 332/363 [00:15<00:00, 35.27it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:00, 38.08it/s]
Loading 0:  94%|█████████▍| 341/363 [00:16<00:00, 36.44it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 38.72it/s]
Loading 0:  96%|█████████▋| 350/363 [00:16<00:00, 36.62it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 39.27it/s]
Loading 0:  99%|█████████▉| 359/363 [00:16<00:00, 36.29it/s]
                                                            
Job chaiml-nemo-20241009-tie-7091-v2-mkmlizer completed after 134.59s with status: succeeded
Stopping job with name chaiml-nemo-20241009-tie-7091-v2-mkmlizer
Pipeline stage MKMLizer completed in 135.17s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.45s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241009-tie-7091-v2
Waiting for inference service chaiml-nemo-20241009-tie-7091-v2 to be ready
Inference service chaiml-nemo-20241009-tie-7091-v2 ready after 130.5392255783081s
Pipeline stage MKMLDeployer completed in 131.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8919885158538818s
Received healthy response to inference request in 1.5684106349945068s
Received healthy response to inference request in 1.7413110733032227s
Received healthy response to inference request in 1.6264684200286865s
Received healthy response to inference request in 1.6713693141937256s
5 requests
0 failed requests
5th percentile: 1.5800221920013429
10th percentile: 1.5916337490081787
20th percentile: 1.6148568630218505
30th percentile: 1.6354485988616942
40th percentile: 1.65340895652771
50th percentile: 1.6713693141937256
60th percentile: 1.6993460178375244
70th percentile: 1.7273227214813232
80th percentile: 1.7714465618133546
90th percentile: 1.8317175388336182
95th percentile: 1.86185302734375
99th percentile: 1.8859614181518554
mean time: 1.6999095916748046
Pipeline stage StressChecker completed in 10.10s
Shutdown handler de-registered
chaiml-nemo-20241009-tie_7091_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241009-tie_7091_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241009-tie_7091_v2 status is now torndown due to DeploymentManager action