developer_uid: azuruce
submission_id: chaiml-nemo-20241015-dar_5690_v2
model_name: chaiml-nemo-20241015-dar_5690_v2
model_group: ChaiML/nemo-20241015-dar
status: torndown
timestamp: 2024-10-17T03:28:11+00:00
num_battles: 9510
num_wins: 5010
celo_rating: 1274.72
family_friendly_score: 0.55787954262425
family_friendly_standard_error: 0.005245505618400978
submission_type: basic
model_repo: ChaiML/nemo-20241015-dare_ties-remerge_v3_half_viral-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_5690_v2
is_internal_developer: True
language_model: ChaiML/nemo-20241015-dare_ties-remerge_v3_half_viral-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-16
win_ratio: 0.526813880126183
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-5690-v2-mkmlizer
Waiting for job on chaiml-nemo-20241015-dar-5690-v2-mkmlizer to finish
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: Downloaded to shared memory in 34.374s
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpnimz1bsa, device:0
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: quantized model in 38.435s
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: Processed model ChaiML/nemo-20241015-dare_ties-remerge_v3_half_viral-albert in 72.810s
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2/special_tokens_map.json
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2/config.json
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2/tokenizer_config.json
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2/tokenizer.json
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241015-dar-5690-v2/flywheel_model.0.safetensors
chaiml-nemo-20241015-dar-5690-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:37,  3.10s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:59,  1.19it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:13,  2.64it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:25,  4.09it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:44,  7.65it/s]
Loading 0:   7%|▋         | 26/363 [00:06<00:34,  9.83it/s]
Loading 0:   9%|▊         | 31/363 [00:07<00:24, 13.44it/s]
Loading 0:  10%|▉         | 35/363 [00:07<00:20, 15.86it/s]
Loading 0:  11%|█         | 39/363 [00:07<00:17, 18.57it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:21, 15.04it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:15, 20.28it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:14, 22.00it/s]
Loading 0:  16%|█▌        | 57/363 [00:08<00:12, 24.50it/s]
Loading 0:  17%|█▋        | 61/363 [00:08<00:12, 23.92it/s]
Loading 0:  18%|█▊        | 65/363 [00:08<00:11, 26.83it/s]
Loading 0:  19%|█▉        | 69/363 [00:08<00:11, 26.24it/s]
Loading 0:  20%|██        | 74/363 [00:08<00:09, 31.08it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:09, 29.50it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:08, 32.77it/s]
Loading 0:  24%|██▍       | 87/363 [00:09<00:09, 30.29it/s]
Loading 0:  25%|██▌       | 92/363 [00:09<00:07, 34.23it/s]
Loading 0:  26%|██▋       | 96/363 [00:09<00:08, 31.02it/s]
Loading 0:  28%|██▊       | 103/363 [00:09<00:06, 38.24it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:06, 38.23it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:06, 38.61it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:06, 36.70it/s]
Loading 0:  33%|███▎      | 121/363 [00:10<00:08, 27.07it/s]
Loading 0:  34%|███▍      | 125/363 [00:10<00:08, 28.08it/s]
Loading 0:  36%|███▌      | 130/363 [00:10<00:07, 31.60it/s]
Loading 0:  37%|███▋      | 134/363 [00:10<00:07, 31.75it/s]
Loading 0:  38%|███▊      | 139/363 [00:10<00:06, 35.06it/s]
Loading 0:  39%|███▉      | 143/363 [00:10<00:06, 33.47it/s]
Loading 0:  41%|████      | 148/363 [00:10<00:06, 35.71it/s]
Loading 0:  42%|████▏     | 152/363 [00:10<00:05, 35.42it/s]
Loading 0:  43%|████▎     | 157/363 [00:11<00:05, 37.80it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:05, 36.55it/s]
Loading 0:  46%|████▌     | 166/363 [00:11<00:04, 39.43it/s]
Loading 0:  47%|████▋     | 171/363 [00:11<00:05, 38.17it/s]
Loading 0:  48%|████▊     | 175/363 [00:11<00:05, 37.18it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:05, 34.72it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 36.85it/s]
Loading 0:  52%|█████▏    | 188/363 [00:11<00:04, 36.79it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 40.89it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:03, 42.38it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:06, 24.42it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 30.77it/s]
Loading 0:  59%|█████▉    | 215/363 [00:12<00:04, 30.76it/s]
Loading 0:  61%|██████    | 220/363 [00:12<00:04, 33.26it/s]
Loading 0:  62%|██████▏   | 224/363 [00:13<00:04, 33.02it/s]
Loading 0:  63%|██████▎   | 229/363 [00:13<00:03, 36.19it/s]
Loading 0:  64%|██████▍   | 233/363 [00:13<00:03, 35.44it/s]
Loading 0:  66%|██████▌   | 238/363 [00:13<00:03, 38.75it/s]
Loading 0:  67%|██████▋   | 243/363 [00:13<00:03, 37.55it/s]
Loading 0:  68%|██████▊   | 247/363 [00:13<00:03, 36.30it/s]
Loading 0:  69%|██████▉   | 251/363 [00:13<00:03, 35.02it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 38.44it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 37.35it/s]
Loading 0:  73%|███████▎  | 266/363 [00:14<00:02, 41.22it/s]
Loading 0:  75%|███████▍  | 271/363 [00:14<00:02, 43.19it/s]
Loading 0:  76%|███████▌  | 276/363 [00:14<00:02, 32.67it/s]
Loading 0:  77%|███████▋  | 281/363 [00:14<00:02, 36.11it/s]
Loading 0:  79%|███████▉  | 286/363 [00:14<00:03, 24.72it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 30.60it/s]
Loading 0:  82%|████████▏ | 296/363 [00:15<00:02, 32.05it/s]
Loading 0:  83%|████████▎ | 302/363 [00:15<00:01, 36.65it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:01, 39.33it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:01, 34.49it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:01, 42.71it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:00, 41.11it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:00, 38.82it/s]
Loading 0:  93%|█████████▎| 337/363 [00:16<00:00, 43.53it/s]
Loading 0:  94%|█████████▍| 342/363 [00:16<00:00, 43.72it/s]
Loading 0:  96%|█████████▌| 347/363 [00:16<00:00, 43.38it/s]
Loading 0:  97%|█████████▋| 353/363 [00:16<00:00, 41.79it/s]
Loading 0:  99%|█████████▊| 358/363 [00:16<00:00, 41.12it/s]
                                                            

Job chaiml-nemo-20241015-dar-5690-v2-mkmlizer completed after 94.09s with status: succeeded
Stopping job with name chaiml-nemo-20241015-dar-5690-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.58s
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-20241015-dar-5690-v2
Waiting for inference service chaiml-nemo-20241015-dar-5690-v2 to be ready
Inference service chaiml-nemo-20241015-dar-5690-v2 ready after 170.59165811538696s
Pipeline stage MKMLDeployer completed in 171.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0156257152557373s
Received healthy response to inference request in 1.655426263809204s
Received healthy response to inference request in 1.803164005279541s
Received healthy response to inference request in 1.5008103847503662s
Received healthy response to inference request in 1.409045696258545s
5 requests
0 failed requests
5th percentile: 1.4273986339569091
10th percentile: 1.4457515716552733
20th percentile: 1.482457447052002
30th percentile: 1.5317335605621338
40th percentile: 1.5935799121856689
50th percentile: 1.655426263809204
60th percentile: 1.7145213603973388
70th percentile: 1.7736164569854735
80th percentile: 1.8456563472747802
90th percentile: 1.9306410312652589
95th percentile: 1.973133373260498
99th percentile: 2.0071272468566894
mean time: 1.6768144130706788
Pipeline stage StressChecker completed in 9.74s
Shutdown handler de-registered
chaiml-nemo-20241015-dar_5690_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241015-dar_5690_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241015-dar_5690_v2 status is now torndown due to DeploymentManager action