chaiml-nemo-20241015-dar_8071

developer_uid: azuruce

submission_id: chaiml-nemo-20241015-dar_8071_v2

model_name: chaiml-nemo-20241015-dar_8071_v2

model_group: ChaiML/nemo-20241015-dar

status: torndown

timestamp: 2024-10-17T00:43:52+00:00

num_battles: 7299

num_wins: 3258

celo_rating: 1217.04

family_friendly_score: 0.5788655788655789

family_friendly_standard_error: 0.005916451112560808

submission_type: basic

model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v2_half_viral-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_8071_v2

is_internal_developer: True

language_model: ChaiML/nemo-20241015-dare_ties-remerge_v2_half_viral-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-16

win_ratio: 0.44636251541307026

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-8071-v2-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-8071-v2-mkmlizer to finish
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: Downloaded to shared memory in 32.720s
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpacn7vzdj, device:0
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: quantized model in 36.365s
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v2_half_viral-albert in 69.085s
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2/config.json
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2/special_tokens_map.json
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2/tokenizer_config.json
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2/tokenizer.json
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-8071-v2/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-8071-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:31,  3.08s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:55,  1.21it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:45,  3.33it/s]
Loading 0:   5%|▌         | 19/363 [00:06<01:00,  5.71it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:42,  7.95it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:25, 13.08it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:19, 16.89it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:19, 16.82it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 22.66it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 26.58it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:10, 29.53it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 33.97it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 36.53it/s]
Loading 0:  21%|██        | 77/363 [00:07<00:07, 39.47it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:06, 40.13it/s]
Loading 0:  24%|██▍       | 88/363 [00:08<00:06, 41.09it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:05, 46.13it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:05, 45.53it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:05, 44.90it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 48.47it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 46.41it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:07, 31.98it/s]
Loading 0:  36%|███▌      | 130/363 [00:09<00:06, 36.98it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:05, 39.18it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 41.48it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:05, 41.81it/s]
Loading 0:  42%|████▏     | 151/363 [00:09<00:05, 41.14it/s]
Loading 0:  43%|████▎     | 157/363 [00:09<00:04, 45.68it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:04, 44.13it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 44.81it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 43.15it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 41.19it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 46.04it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:03, 44.36it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:04, 41.71it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:04, 32.59it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 32.18it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 35.08it/s]
Loading 0:  59%|█████▉    | 215/363 [00:11<00:04, 35.55it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 39.39it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 39.55it/s]
Loading 0:  64%|██████▍   | 232/363 [00:11<00:03, 38.64it/s]
Loading 0:  66%|██████▌   | 238/363 [00:11<00:02, 43.16it/s]
Loading 0:  67%|██████▋   | 243/363 [00:11<00:02, 43.34it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 43.90it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 45.42it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 37.37it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 44.36it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 44.06it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:02, 43.14it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:01, 44.40it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:03, 24.86it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 32.29it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 34.80it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 36.58it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 38.17it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 38.42it/s]
Loading 0:  88%|████████▊ | 319/363 [00:13<00:01, 41.59it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 42.04it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 42.93it/s]
Loading 0:  92%|█████████▏| 335/363 [00:14<00:00, 41.34it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 38.78it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 43.69it/s]
Loading 0:  97%|█████████▋| 351/363 [00:14<00:00, 44.02it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 43.44it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 44.16it/s]
                                                            
Job chaiml-nemo-20241015-dar-8071-v2-mkmlizer completed after 94.5s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-8071-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.06s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241015-dar-8071-v2
Waiting for inference service chaiml-nemo-20241015-dar-8071-v2 to be ready
Inference service chaiml-nemo-20241015-dar-8071-v2 ready after 170.60641646385193s
Pipeline stage MKMLDeployer completed in 171.32s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.082200765609741s
Received healthy response to inference request in 1.565317153930664s
Received healthy response to inference request in 1.469691276550293s
Received healthy response to inference request in 1.346858263015747s
Received healthy response to inference request in 1.3574481010437012s
5 requests
0 failed requests
5th percentile: 1.348976230621338
10th percentile: 1.3510941982269287
20th percentile: 1.3553301334381103
30th percentile: 1.3798967361450196
40th percentile: 1.4247940063476563
50th percentile: 1.469691276550293
60th percentile: 1.5079416275024413
70th percentile: 1.5461919784545899
80th percentile: 1.6686938762664796
90th percentile: 1.8754473209381104
95th percentile: 1.9788240432739257
99th percentile: 2.061525421142578
mean time: 1.5643031120300293
Pipeline stage StressChecker completed in 9.26s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_8071_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_8071_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_8071_v2 status is now torndown due to DeploymentManager action