chaiml-nemo-20241015-dar_4058

developer_uid: azuruce

submission_id: chaiml-nemo-20241015-dar_4058_v9

model_name: chaiml-nemo-20241015-dar_4058_v9

model_group: ChaiML/nemo-20241015-dar

status: torndown

timestamp: 2024-10-17T19:14:29+00:00

num_battles: 8145

num_wins: 4002

celo_rating: 1255.54

family_friendly_score: 0.6085246324477689

family_friendly_standard_error: 0.005514188101085395

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_v9

is_internal_developer: True

language_model: ChaiML/nemo-20241015-dare_ties-remerge_v1-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-17

win_ratio: 0.4913443830570902

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-v9-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-4058-v9-mkmlizer to finish
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: Downloaded to shared memory in 43.756s
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp65r6ofh1, device:0
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: quantized model in 35.495s
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v1-albert in 79.252s
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9/config.json
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9/special_tokens_map.json
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9/tokenizer_config.json
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9/tokenizer.json
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-4058-v9/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-4058-v9-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:46,  2.95s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:44,  1.25it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:41,  3.44it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:08,  5.02it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:41,  8.16it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.60it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.74it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.43it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.13it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.48it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 28.13it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.87it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 36.66it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 38.71it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 40.47it/s]
Loading 0:  23%|██▎       | 82/363 [00:07<00:06, 42.79it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:07, 35.09it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 42.67it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 43.27it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 44.53it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 42.45it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:06, 41.29it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:07, 32.32it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 33.41it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.05it/s]
Loading 0:  37%|███▋      | 134/363 [00:09<00:06, 36.06it/s]
Loading 0:  38%|███▊      | 139/363 [00:09<00:05, 38.71it/s]
Loading 0:  40%|███▉      | 144/363 [00:09<00:05, 39.43it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:05, 40.89it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:05, 40.45it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:05, 40.53it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 45.80it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 43.77it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 43.01it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 47.01it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 46.44it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 47.34it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 44.91it/s]
Loading 0:  56%|█████▋    | 205/363 [00:11<00:05, 30.96it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 37.29it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 37.80it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 38.44it/s]
Loading 0:  63%|██████▎   | 229/363 [00:11<00:03, 42.94it/s]
Loading 0:  64%|██████▍   | 234/363 [00:11<00:03, 42.71it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:02, 42.86it/s]
Loading 0:  67%|██████▋   | 244/363 [00:11<00:02, 43.64it/s]
Loading 0:  69%|██████▊   | 249/363 [00:12<00:03, 35.54it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 44.29it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 42.67it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 41.75it/s]
Loading 0:  75%|███████▌  | 274/363 [00:12<00:01, 45.83it/s]
Loading 0:  77%|███████▋  | 279/363 [00:12<00:01, 45.51it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 31.79it/s]
Loading 0:  79%|███████▉  | 288/363 [00:13<00:02, 33.29it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 36.69it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 37.44it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 38.32it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 44.25it/s]
Loading 0:  87%|████████▋ | 317/363 [00:13<00:01, 42.66it/s]
Loading 0:  89%|████████▊ | 322/363 [00:13<00:00, 42.94it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 47.59it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 45.15it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 44.16it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 45.65it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 45.17it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 45.72it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 42.87it/s]
                                                            
Job chaiml-nemo-20241015-dar-4058-v9-mkmlizer completed after 104.62s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-4058-v9-mkmlizer
Pipeline stage MKMLizer completed in 105.19s
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-v9
Waiting for inference service chaiml-nemo-20241015-dar-4058-v9 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-nemo-20241015-dar-4058-v9 ready after 180.6826524734497s
Pipeline stage MKMLDeployer completed in 181.22s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.631164312362671s
Received healthy response to inference request in 1.5880587100982666s
Received healthy response to inference request in 1.778437852859497s
Received healthy response to inference request in 1.5623817443847656s
Received healthy response to inference request in 1.6021721363067627s
5 requests
0 failed requests
5th percentile: 1.567517137527466
10th percentile: 1.572652530670166
20th percentile: 1.5829233169555663
30th percentile: 1.5908813953399659
40th percentile: 1.5965267658233642
50th percentile: 1.6021721363067627
60th percentile: 1.6726784229278564
70th percentile: 1.74318470954895
80th percentile: 1.948983144760132
90th percentile: 2.2900737285614015
95th percentile: 2.460619020462036
99th percentile: 2.597055253982544
mean time: 1.8324429512023925
Pipeline stage StressChecker completed in 10.72s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_4058_v9 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_4058_v9 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_4058_v9 status is now torndown due to DeploymentManager action