chaiml-nemo-20241015-dar_3550

developer_uid: azuruce

submission_id: chaiml-nemo-20241015-dar_3550_v2

model_name: chaiml-nemo-20241015-dar_3550_v2

model_group: ChaiML/nemo-20241015-dar

status: torndown

timestamp: 2024-10-17T04:52:01+00:00

num_battles: 7458

num_wins: 3927

celo_rating: 1275.87

family_friendly_score: 0.5426698959965808

family_friendly_standard_error: 0.00590425627081521

submission_type: basic

model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-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_3550_v2

is_internal_developer: True

language_model: ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-16

win_ratio: 0.5265486725663717

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-3550-v2-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-3550-v2-mkmlizer to finish
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: Downloaded to shared memory in 33.782s
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp02gqisaf, device:0
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: quantized model in 39.132s
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v4_6merge-albert in 72.914s
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2/config.json
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2/special_tokens_map.json
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2/tokenizer_config.json
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2/tokenizer.json
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-3550-v2/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-3550-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:51,  3.13s/it]
Loading 0:   2%|▏         | 6/363 [00:06<05:02,  1.18it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:13,  2.63it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:25,  4.06it/s]
Loading 0:   6%|▌         | 20/363 [00:06<00:52,  6.50it/s]
Loading 0:   7%|▋         | 24/363 [00:07<00:39,  8.52it/s]
Loading 0:   8%|▊         | 29/363 [00:07<00:27, 12.09it/s]
Loading 0:   9%|▉         | 33/363 [00:07<00:23, 14.19it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:17, 18.65it/s]
Loading 0:  12%|█▏        | 42/363 [00:07<00:20, 15.98it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.97it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 24.69it/s]
Loading 0:  16%|█▌        | 58/363 [00:08<00:10, 28.83it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:09, 30.11it/s]
Loading 0:  19%|█▊        | 68/363 [00:08<00:08, 35.12it/s]
Loading 0:  20%|██        | 73/363 [00:08<00:07, 37.36it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 31.18it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 37.36it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:07, 37.53it/s]
Loading 0:  26%|██▌       | 95/363 [00:09<00:06, 38.33it/s]
Loading 0:  28%|██▊       | 100/363 [00:09<00:06, 39.19it/s]
Loading 0:  29%|██▉       | 105/363 [00:09<00:08, 31.53it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 37.26it/s]
Loading 0:  32%|███▏      | 117/363 [00:09<00:06, 35.98it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:09, 25.03it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:09, 25.80it/s]
Loading 0:  36%|███▌      | 129/363 [00:10<00:08, 27.48it/s]
Loading 0:  37%|███▋      | 133/363 [00:10<00:08, 26.13it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:07, 31.71it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 31.53it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 33.67it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:06, 32.42it/s]
Loading 0:  43%|████▎     | 156/363 [00:11<00:06, 33.98it/s]
Loading 0:  44%|████▍     | 160/363 [00:11<00:06, 30.55it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:06, 31.70it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:06, 28.86it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 33.11it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:06, 30.42it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:05, 34.14it/s]
Loading 0:  51%|█████     | 186/363 [00:12<00:05, 31.43it/s]
Loading 0:  53%|█████▎    | 191/363 [00:12<00:04, 35.26it/s]
Loading 0:  54%|█████▎    | 195/363 [00:12<00:05, 31.61it/s]
Loading 0:  56%|█████▌    | 202/363 [00:12<00:05, 27.11it/s]
Loading 0:  57%|█████▋    | 206/363 [00:12<00:05, 28.22it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 31.98it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 31.80it/s]
Loading 0:  61%|██████    | 220/363 [00:13<00:04, 32.75it/s]
Loading 0:  62%|██████▏   | 224/363 [00:13<00:04, 31.99it/s]
Loading 0:  63%|██████▎   | 229/363 [00:13<00:03, 34.52it/s]
Loading 0:  64%|██████▍   | 233/363 [00:13<00:03, 33.09it/s]
Loading 0:  65%|██████▌   | 237/363 [00:13<00:03, 34.71it/s]
Loading 0:  66%|██████▋   | 241/363 [00:13<00:03, 31.14it/s]
Loading 0:  67%|██████▋   | 245/363 [00:13<00:03, 33.17it/s]
Loading 0:  69%|██████▊   | 249/363 [00:14<00:03, 30.30it/s]
Loading 0:  71%|███████   | 256/363 [00:14<00:02, 37.56it/s]
Loading 0:  72%|███████▏  | 260/363 [00:14<00:02, 35.08it/s]
Loading 0:  73%|███████▎  | 265/363 [00:14<00:02, 37.41it/s]
Loading 0:  74%|███████▍  | 269/363 [00:14<00:02, 35.17it/s]
Loading 0:  75%|███████▌  | 274/363 [00:14<00:02, 36.71it/s]
Loading 0:  77%|███████▋  | 278/363 [00:14<00:02, 34.52it/s]
Loading 0:  78%|███████▊  | 283/363 [00:15<00:03, 24.56it/s]
Loading 0:  79%|███████▉  | 286/363 [00:15<00:03, 24.80it/s]
Loading 0:  80%|████████  | 292/363 [00:15<00:02, 30.50it/s]
Loading 0:  82%|████████▏ | 296/363 [00:15<00:02, 30.52it/s]
Loading 0:  83%|████████▎ | 301/363 [00:15<00:01, 32.82it/s]
Loading 0:  84%|████████▍ | 305/363 [00:15<00:01, 32.99it/s]
Loading 0:  85%|████████▌ | 310/363 [00:15<00:01, 36.89it/s]
Loading 0:  87%|████████▋ | 314/363 [00:15<00:01, 36.55it/s]
Loading 0:  88%|████████▊ | 319/363 [00:16<00:01, 37.31it/s]
Loading 0:  89%|████████▉ | 323/363 [00:16<00:01, 36.04it/s]
Loading 0:  91%|█████████ | 329/363 [00:16<00:00, 40.53it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:00, 40.43it/s]
Loading 0:  94%|█████████▎| 340/363 [00:16<00:00, 39.98it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 45.08it/s]
Loading 0:  97%|█████████▋| 353/363 [00:16<00:00, 43.55it/s]
Loading 0:  99%|█████████▊| 358/363 [00:16<00:00, 42.44it/s]
                                                            
Job chaiml-nemo-20241015-dar-3550-v2-mkmlizer completed after 104.01s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-3550-v2-mkmlizer
Pipeline stage MKMLizer completed in 104.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241015-dar-3550-v2
Waiting for inference service chaiml-nemo-20241015-dar-3550-v2 to be ready
Retrying (%r) after connection broken by '%r': %s
Inference service chaiml-nemo-20241015-dar-3550-v2 ready after 219.07441973686218s
Pipeline stage MKMLDeployer completed in 219.64s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.403333902359009s
Received healthy response to inference request in 1.5276970863342285s
Received healthy response to inference request in 1.813002347946167s
Received healthy response to inference request in 1.4246852397918701s
Received healthy response to inference request in 1.4407215118408203s
5 requests
0 failed requests
5th percentile: 1.4278924942016602
10th percentile: 1.4310997486114503
20th percentile: 1.4375142574310302
30th percentile: 1.458116626739502
40th percentile: 1.4929068565368653
50th percentile: 1.5276970863342285
60th percentile: 1.6418191909790039
70th percentile: 1.7559412956237792
80th percentile: 1.9310686588287354
90th percentile: 2.167201280593872
95th percentile: 2.2852675914764404
99th percentile: 2.3797206401824953
mean time: 1.721888017654419
Pipeline stage StressChecker completed in 10.11s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_3550_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_3550_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_3550_v2 status is now torndown due to DeploymentManager action