chaiml-nemo-20241009-tie_2881

developer_uid: azuruce

submission_id: chaiml-nemo-20241009-tie_2881_v2

model_name: chaiml-nemo-20241009-tie_2881_v2

model_group: ChaiML/nemo-20241009-tie

status: torndown

timestamp: 2024-10-11T22:01:44+00:00

num_battles: 8502

num_wins: 4506

celo_rating: 1270.21

family_friendly_score: 0.5350460564191135

family_friendly_standard_error: 0.005509158793711739

submission_type: basic

model_repo: ChaiML/nemo-20241009-ties-v7-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_2881_v2

is_internal_developer: True

language_model: ChaiML/nemo-20241009-ties-v7-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-11

win_ratio: 0.5299929428369795

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-2881-v2-mkmlizer
Waiting for job on chaiml-nemo-20241009-tie-2881-v2-mkmlizer to finish
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: Downloaded to shared memory in 31.876s
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpo9p3nais, device:0
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: quantized model in 36.099s
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: Processed model ChaiML/nemo-20241009-ties-v7-albert in 67.975s
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2/config.json
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2/special_tokens_map.json
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2/tokenizer_config.json
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2/tokenizer.json
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-2881-v2/flywheel_model.0.safetensors
chaiml-nemo-20241009-tie-2881-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<17:52,  2.97s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:47,  1.24it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:06,  2.79it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:19,  4.37it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:41,  8.17it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:30, 11.12it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.72it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:16, 19.23it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:17, 17.87it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.28it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:10, 27.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:07<00:09, 30.24it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 36.54it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:07, 37.27it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 37.01it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:06, 41.73it/s]
Loading 0:  25%|██▍       | 90/363 [00:08<00:06, 42.15it/s]
Loading 0:  26%|██▌       | 95/363 [00:08<00:06, 43.29it/s]
Loading 0:  28%|██▊       | 101/363 [00:08<00:06, 42.35it/s]
Loading 0:  29%|██▉       | 106/363 [00:08<00:06, 41.79it/s]
Loading 0:  31%|███       | 112/363 [00:08<00:05, 45.98it/s]
Loading 0:  32%|███▏      | 117/363 [00:08<00:05, 45.65it/s]
Loading 0:  34%|███▎      | 122/363 [00:09<00:07, 31.40it/s]
Loading 0:  35%|███▍      | 126/363 [00:09<00:07, 32.58it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 36.04it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 37.92it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 38.20it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:04, 43.70it/s]
Loading 0:  43%|████▎     | 155/363 [00:09<00:04, 42.79it/s]
Loading 0:  44%|████▍     | 160/363 [00:09<00:04, 42.25it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 46.89it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:04, 45.34it/s]
Loading 0:  49%|████▉     | 178/363 [00:10<00:04, 42.57it/s]
Loading 0:  51%|█████     | 184/363 [00:10<00:03, 46.54it/s]
Loading 0:  52%|█████▏    | 189/363 [00:10<00:03, 44.73it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 45.30it/s]
Loading 0:  55%|█████▍    | 199/363 [00:10<00:03, 44.78it/s]
Loading 0:  56%|█████▌    | 204/363 [00:11<00:06, 26.06it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 32.51it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:04, 33.74it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:04, 34.45it/s]
Loading 0:  62%|██████▏   | 225/363 [00:11<00:04, 34.44it/s]
Loading 0:  63%|██████▎   | 229/363 [00:11<00:03, 35.65it/s]
Loading 0:  64%|██████▍   | 233/363 [00:11<00:03, 36.44it/s]
Loading 0:  66%|██████▌   | 239/363 [00:11<00:03, 41.11it/s]
Loading 0:  67%|██████▋   | 245/363 [00:12<00:02, 40.47it/s]
Loading 0:  69%|██████▉   | 250/363 [00:12<00:02, 40.41it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 46.20it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 44.31it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 42.71it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 47.53it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:01, 47.33it/s]
Loading 0:  79%|███████▊  | 285/363 [00:13<00:02, 26.96it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.29it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 36.85it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.61it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:01, 39.01it/s]
Loading 0:  86%|████████▌ | 313/363 [00:13<00:01, 39.93it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:00, 45.51it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:00, 45.50it/s]
Loading 0:  91%|█████████ | 330/363 [00:14<00:00, 38.77it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.82it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 45.36it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 43.48it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 48.17it/s]
Loading 0:  99%|█████████▉| 361/363 [00:14<00:00, 48.09it/s]
                                                            
Job chaiml-nemo-20241009-tie-2881-v2-mkmlizer completed after 94.71s with status: succeeded
Stopping job with name chaiml-nemo-20241009-tie-2881-v2-mkmlizer
Pipeline stage MKMLizer completed in 95.19s
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-20241009-tie-2881-v2
Waiting for inference service chaiml-nemo-20241009-tie-2881-v2 to be ready
Inference service chaiml-nemo-20241009-tie-2881-v2 ready after 150.55486726760864s
Pipeline stage MKMLDeployer completed in 151.02s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.953233003616333s
Received healthy response to inference request in 1.6040287017822266s
Received healthy response to inference request in 1.4902565479278564s
Received healthy response to inference request in 1.7156102657318115s
Received healthy response to inference request in 1.830411672592163s
5 requests
0 failed requests
5th percentile: 1.5130109786987305
10th percentile: 1.5357654094696045
20th percentile: 1.5812742710113525
30th percentile: 1.6263450145721436
40th percentile: 1.6709776401519776
50th percentile: 1.7156102657318115
60th percentile: 1.761530828475952
70th percentile: 1.8074513912200927
80th percentile: 1.854975938796997
90th percentile: 1.904104471206665
95th percentile: 1.928668737411499
99th percentile: 1.9483201503753662
mean time: 1.7187080383300781
Pipeline stage StressChecker completed in 10.22s
Shutdown handler de-registered
chaiml-nemo-20241009-tie_2881_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241009-tie_2881_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241009-tie_2881_v2 status is now torndown due to DeploymentManager action