chaiml-nemo-20241015-dar_4058

developer_uid: azuruce
submission_id: chaiml-nemo-20241015-dar_4058_v7
model_name: chaiml-nemo-20241015-dar_4058_v7
model_group: ChaiML/nemo-20241015-dar
status: torndown
timestamp: 2024-10-16T21:38:14+00:00
num_battles: 8330
num_wins: 4583
celo_rating: 1254.16
family_friendly_score: 0.5625847744998305
family_friendly_standard_error: 0.005556888641147437
submission_type: basic
model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v1-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241015-dar_4058_v7
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: 0.5501800720288115
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|>'], '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-20241015-dar-4058-v7-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-4058-v7-mkmlizer to finish
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: Downloaded to shared memory in 29.511s
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3ibvyx4o, device:0
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: quantized model in 36.737s
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v1-albert in 66.248s
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7/config.json
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7/special_tokens_map.json
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7/tokenizer_config.json
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7/tokenizer.json
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v7/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-4058-v7-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:39,  2.93s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:43,  1.26it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:05,  2.81it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:19,  4.35it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:42,  8.08it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:32, 10.32it/s]
Loading 0:   9%|▊         | 31/363 [00:06<00:23, 14.04it/s]
Loading 0:  10%|▉         | 36/363 [00:06<00:18, 17.91it/s]
Loading 0:  11%|█▏        | 41/363 [00:07<00:18, 17.50it/s]
Loading 0:  12%|█▏        | 45/363 [00:07<00:15, 20.25it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.44it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:11, 25.85it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 30.48it/s]
Loading 0:  17%|█▋        | 62/363 [00:07<00:09, 31.10it/s]
Loading 0:  18%|█▊        | 66/363 [00:07<00:08, 33.17it/s]
Loading 0:  19%|█▉        | 70/363 [00:07<00:09, 31.45it/s]
Loading 0:  21%|██        | 76/363 [00:07<00:07, 36.85it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:07, 35.48it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 38.39it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 37.75it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 37.41it/s]
Loading 0:  27%|██▋       | 98/363 [00:08<00:07, 36.08it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:06, 39.43it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:06, 39.29it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:06, 38.78it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:06, 36.83it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 27.12it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:08, 27.73it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:07, 32.02it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:07, 32.47it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:06, 35.57it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:06, 34.74it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:05, 37.67it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 36.14it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:05, 38.30it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:05, 36.51it/s]
Loading 0:  46%|████▌     | 166/363 [00:10<00:05, 39.08it/s]
Loading 0:  47%|████▋     | 170/363 [00:10<00:05, 37.14it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 38.68it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:05, 36.63it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:04, 39.32it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 37.09it/s]
Loading 0:  53%|█████▎    | 193/363 [00:11<00:04, 39.95it/s]
Loading 0:  55%|█████▍    | 198/363 [00:11<00:04, 39.18it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 27.14it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:05, 28.47it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 32.27it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 32.15it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 35.63it/s]
Loading 0:  62%|██████▏   | 224/363 [00:12<00:03, 34.86it/s]
Loading 0:  63%|██████▎   | 229/363 [00:12<00:03, 37.28it/s]
Loading 0:  64%|██████▍   | 233/363 [00:12<00:03, 35.39it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:03, 38.34it/s]
Loading 0:  67%|██████▋   | 242/363 [00:12<00:03, 36.76it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 39.47it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 39.18it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 38.61it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 36.70it/s]
Loading 0:  73%|███████▎  | 265/363 [00:13<00:02, 38.84it/s]
Loading 0:  74%|███████▍  | 269/363 [00:13<00:02, 36.92it/s]
Loading 0:  75%|███████▌  | 274/363 [00:13<00:02, 39.55it/s]
Loading 0:  77%|███████▋  | 278/363 [00:13<00:02, 37.10it/s]
Loading 0:  78%|███████▊  | 283/363 [00:13<00:02, 27.59it/s]
Loading 0:  79%|███████▉  | 287/363 [00:14<00:02, 29.28it/s]
Loading 0:  81%|████████  | 293/363 [00:14<00:02, 34.65it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 35.83it/s]
Loading 0:  83%|████████▎ | 302/363 [00:14<00:01, 37.25it/s]
Loading 0:  84%|████████▍ | 306/363 [00:14<00:01, 36.50it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:01, 38.19it/s]
Loading 0:  87%|████████▋ | 315/363 [00:14<00:01, 37.93it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:01, 39.24it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 41.73it/s]
Loading 0:  91%|█████████ | 330/363 [00:15<00:00, 33.32it/s]
Loading 0:  93%|█████████▎| 337/363 [00:15<00:00, 39.68it/s]
Loading 0:  94%|█████████▍| 342/363 [00:15<00:00, 38.71it/s]
Loading 0:  96%|█████████▌| 347/363 [00:15<00:00, 38.79it/s]
Loading 0:  97%|█████████▋| 352/363 [00:15<00:00, 41.17it/s]
Loading 0:  98%|█████████▊| 357/363 [00:15<00:00, 33.68it/s]
                                                            
Job chaiml-nemo-20241015-dar-4058-v7-mkmlizer completed after 94.15s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-4058-v7-mkmlizer
Pipeline stage MKMLizer completed in 94.69s
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 chaiml-nemo-20241015-dar-4058-v7
Waiting for inference service chaiml-nemo-20241015-dar-4058-v7 to be ready
Inference service chaiml-nemo-20241015-dar-4058-v7 ready after 356.6079204082489s
Pipeline stage MKMLDeployer completed in 357.24s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0228564739227295s
Received healthy response to inference request in 1.469818353652954s
Received healthy response to inference request in 1.5561351776123047s
Received healthy response to inference request in 1.4334743022918701s
Received healthy response to inference request in 1.81589674949646s
5 requests
0 failed requests
5th percentile: 1.4407431125640868
10th percentile: 1.4480119228363038
20th percentile: 1.4625495433807374
30th percentile: 1.4870817184448242
40th percentile: 1.5216084480285645
50th percentile: 1.5561351776123047
60th percentile: 1.6600398063659667
70th percentile: 1.763944435119629
80th percentile: 1.857288694381714
90th percentile: 1.9400725841522217
95th percentile: 1.9814645290374755
99th percentile: 2.0145780849456787
mean time: 1.6596362113952636
Pipeline stage StressChecker completed in 9.83s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_4058_v7 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_4058_v7 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_4058_v7 status is now torndown due to DeploymentManager action