chaiml-nemo-20241017-dar_6728

developer_uid: azuruce
submission_id: chaiml-nemo-20241017-dar_6728_v1
model_name: chaiml-nemo-20241017-dar_6728_v1
model_group: ChaiML/nemo-20241017-dar
status: torndown
timestamp: 2024-10-18T15:55:10+00:00
num_battles: 5635
num_wins: 2833
celo_rating: 1253.58
family_friendly_score: 0.5917018542316872
family_friendly_standard_error: 0.006632520256274645
submission_type: basic
model_repo: ChaiML/nemo-20241017-dare_linear-remerge_v2_5merge-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 4
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241017-dar_6728_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241017-dare_linear-remerge_v2_5merge-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-18
win_ratio: 0.5027506654835847
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-20241017-dar-6728-v1-mkmlizer
Waiting for job on chaiml-nemo-20241017-dar-6728-v1-mkmlizer to finish
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: Downloaded to shared memory in 48.925s
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp01kcw7eg, device:0
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: quantized model in 39.303s
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: Processed model ChaiML/nemo-20241017-dare_linear-remerge_v2_5merge-albert in 88.228s
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-6728-v1
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-6728-v1/config.json
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-6728-v1/special_tokens_map.json
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-6728-v1/tokenizer_config.json
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-dar-6728-v1/tokenizer.json
chaiml-nemo-20241017-dar-6728-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:27,  3.07s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:56,  1.20it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:10,  2.69it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.18it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.81it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.72it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:23, 13.94it/s]
Loading 0:  10%|▉         | 36/363 [00:07<00:19, 16.49it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:21, 15.21it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:19, 16.53it/s]
Loading 0:  13%|█▎        | 47/363 [00:07<00:15, 20.06it/s]
Loading 0:  14%|█▍        | 51/363 [00:07<00:14, 21.73it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 29.57it/s]
Loading 0:  17%|█▋        | 62/363 [00:08<00:10, 29.67it/s]
Loading 0:  18%|█▊        | 67/363 [00:08<00:09, 32.45it/s]
Loading 0:  20%|█▉        | 71/363 [00:08<00:09, 31.68it/s]
Loading 0:  21%|██        | 76/363 [00:08<00:08, 34.06it/s]
Loading 0:  22%|██▏       | 80/363 [00:08<00:08, 32.24it/s]
Loading 0:  23%|██▎       | 85/363 [00:08<00:07, 34.84it/s]
Loading 0:  25%|██▍       | 89/363 [00:08<00:08, 34.02it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 36.98it/s]
Loading 0:  27%|██▋       | 98/363 [00:09<00:07, 34.96it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:07, 36.89it/s]
Loading 0:  29%|██▉       | 107/363 [00:09<00:07, 34.93it/s]
Loading 0:  31%|███       | 111/363 [00:09<00:06, 36.18it/s]
Loading 0:  32%|███▏      | 115/363 [00:09<00:07, 32.32it/s]
Loading 0:  33%|███▎      | 119/363 [00:09<00:07, 33.83it/s]
Loading 0:  34%|███▍      | 123/363 [00:10<00:11, 21.47it/s]
Loading 0:  35%|███▌      | 128/363 [00:10<00:08, 26.30it/s]
Loading 0:  36%|███▋      | 132/363 [00:10<00:09, 24.90it/s]
Loading 0:  38%|███▊      | 137/363 [00:10<00:07, 29.65it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:07, 27.94it/s]
Loading 0:  40%|████      | 146/363 [00:10<00:06, 32.30it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:07, 29.75it/s]
Loading 0:  43%|████▎     | 155/363 [00:10<00:06, 33.62it/s]
Loading 0:  44%|████▍     | 159/363 [00:11<00:06, 30.45it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:05, 34.21it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:06, 30.68it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 33.75it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:06, 30.86it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:05, 34.39it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:05, 30.72it/s]
Loading 0:  53%|█████▎    | 191/363 [00:12<00:04, 34.63it/s]
Loading 0:  54%|█████▎    | 195/363 [00:12<00:05, 30.07it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:04, 34.07it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:07, 21.65it/s]
Loading 0:  58%|█████▊    | 209/363 [00:12<00:05, 26.15it/s]
Loading 0:  59%|█████▊    | 213/363 [00:12<00:05, 25.10it/s]
Loading 0:  60%|██████    | 218/363 [00:13<00:04, 29.05it/s]
Loading 0:  61%|██████    | 222/363 [00:13<00:05, 27.15it/s]
Loading 0:  63%|██████▎   | 227/363 [00:13<00:04, 31.05it/s]
Loading 0:  64%|██████▎   | 231/363 [00:13<00:04, 28.58it/s]
Loading 0:  65%|██████▌   | 236/363 [00:13<00:03, 32.53it/s]
Loading 0:  66%|██████▌   | 240/363 [00:13<00:04, 29.87it/s]
Loading 0:  67%|██████▋   | 245/363 [00:13<00:03, 33.15it/s]
Loading 0:  69%|██████▊   | 249/363 [00:14<00:03, 30.71it/s]
Loading 0:  70%|██████▉   | 254/363 [00:14<00:03, 34.49it/s]
Loading 0:  71%|███████   | 258/363 [00:14<00:03, 31.36it/s]
Loading 0:  72%|███████▏  | 263/363 [00:14<00:02, 34.88it/s]
Loading 0:  74%|███████▎  | 267/363 [00:14<00:03, 31.84it/s]
Loading 0:  75%|███████▍  | 272/363 [00:14<00:02, 35.98it/s]
Loading 0:  76%|███████▌  | 276/363 [00:14<00:02, 32.85it/s]
Loading 0:  77%|███████▋  | 281/363 [00:14<00:02, 36.96it/s]
Loading 0:  79%|███████▊  | 285/363 [00:15<00:03, 23.86it/s]
Loading 0:  80%|███████▉  | 290/363 [00:15<00:02, 28.59it/s]
Loading 0:  81%|████████  | 294/363 [00:15<00:02, 27.60it/s]
Loading 0:  82%|████████▏ | 299/363 [00:15<00:02, 31.58it/s]
Loading 0:  83%|████████▎ | 303/363 [00:15<00:01, 30.22it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:01, 33.28it/s]
Loading 0:  86%|████████▌ | 312/363 [00:16<00:01, 29.82it/s]
Loading 0:  87%|████████▋ | 317/363 [00:16<00:01, 33.23it/s]
Loading 0:  88%|████████▊ | 321/363 [00:16<00:01, 29.54it/s]
Loading 0:  90%|████████▉ | 326/363 [00:16<00:01, 33.05it/s]
Loading 0:  91%|█████████ | 330/363 [00:16<00:01, 30.36it/s]
Loading 0:  92%|█████████▏| 335/363 [00:16<00:00, 32.66it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:00, 30.86it/s]
Loading 0:  95%|█████████▍| 344/363 [00:17<00:00, 33.94it/s]
Loading 0:  96%|█████████▌| 348/363 [00:17<00:00, 29.94it/s]
Loading 0:  97%|█████████▋| 353/363 [00:17<00:00, 34.14it/s]
Loading 0:  98%|█████████▊| 357/363 [00:17<00:00, 32.24it/s]
                                                            
Job chaiml-nemo-20241017-dar-6728-v1-mkmlizer completed after 113.92s with status: succeeded
Stopping job with name chaiml-nemo-20241017-dar-6728-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-dar-6728-v1
Waiting for inference service chaiml-nemo-20241017-dar-6728-v1 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service chaiml-nemo-20241017-dar-6728-v1 ready after 160.60951256752014s
Pipeline stage MKMLDeployer completed in 161.51s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8220674991607666s
Received healthy response to inference request in 1.7974927425384521s
Received healthy response to inference request in 1.3803880214691162s
Received healthy response to inference request in 1.800873041152954s
Received healthy response to inference request in 1.3717501163482666s
5 requests
0 failed requests
5th percentile: 1.3734776973724365
10th percentile: 1.3752052783966064
20th percentile: 1.3786604404449463
30th percentile: 1.4638089656829834
40th percentile: 1.6306508541107179
50th percentile: 1.7974927425384521
60th percentile: 1.798844861984253
70th percentile: 1.8001969814300538
80th percentile: 1.8051119327545166
90th percentile: 1.8135897159576415
95th percentile: 1.817828607559204
99th percentile: 1.8212197208404541
mean time: 1.634514284133911
Pipeline stage StressChecker completed in 9.42s
Shutdown handler de-registered
chaiml-nemo-20241017-dar_6728_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241017-dar_6728_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-dar_6728_v1 status is now torndown due to DeploymentManager action