chaiml-nemo-20241010-tie_9292

developer_uid: azuruce
submission_id: chaiml-nemo-20241010-tie_9292_v1
model_name: chaiml-nemo-20241010-tie_9292_v1
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-10T21:25:19+00:00
num_battles: 6073
num_wins: 3175
celo_rating: 1271.99
family_friendly_score: 0.548038200437234
family_friendly_standard_error: 0.006505016874882422
submission_type: basic
model_repo: ChaiML/nemo-20241010_tier_merge_v2-albert
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: chaiml-nemo-20241010-tie_9292_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v2-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-10
win_ratio: 0.522805862012185
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.05, 'top_k': 1000, '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-20241010-tie-9292-v1-mkmlizer
Waiting for job on chaiml-nemo-20241010-tie-9292-v1-mkmlizer to finish
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: Downloaded to shared memory in 59.964s
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmprq00_j0w, device:0
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: quantized model in 36.336s
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v2-albert in 96.300s
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1/config.json
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1/special_tokens_map.json
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1/tokenizer_config.json
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1/tokenizer.json
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-9292-v1/flywheel_model.0.safetensors
chaiml-nemo-20241010-tie-9292-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:06,  3.01s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:07,  2.76it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:20,  4.32it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:39,  8.56it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:28, 11.90it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:21, 15.21it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.92it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 19.15it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.55it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.76it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 31.10it/s]
Loading 0:  18%|█▊        | 65/363 [00:07<00:08, 33.36it/s]
Loading 0:  19%|█▉        | 70/363 [00:07<00:08, 34.02it/s]
Loading 0:  21%|██        | 76/363 [00:07<00:07, 38.78it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 39.90it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 41.26it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 40.08it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.38it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 44.04it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 44.06it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 44.18it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:05, 42.31it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:08, 29.08it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.50it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:05, 38.44it/s]
Loading 0:  39%|███▉      | 141/363 [00:09<00:06, 33.26it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 40.19it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:05, 40.62it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 41.69it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:04, 40.55it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 40.44it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 44.59it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 44.47it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 44.88it/s]
Loading 0:  52%|█████▏    | 190/363 [00:10<00:03, 44.92it/s]
Loading 0:  54%|█████▎    | 195/363 [00:10<00:04, 37.28it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 31.22it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 31.69it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 36.11it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 36.97it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:03, 35.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 43.93it/s]
Loading 0:  65%|██████▍   | 235/363 [00:11<00:02, 44.65it/s]
Loading 0:  66%|██████▌   | 240/363 [00:12<00:03, 37.04it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 44.86it/s]
Loading 0:  70%|██████▉   | 254/363 [00:12<00:02, 43.23it/s]
Loading 0:  71%|███████▏  | 259/363 [00:12<00:02, 41.90it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 46.07it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 46.02it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 46.37it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 43.76it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 30.16it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:01, 35.63it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 37.46it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 39.34it/s]
Loading 0:  85%|████████▍ | 307/363 [00:13<00:01, 41.71it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:01, 36.34it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:00, 44.38it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:00, 42.61it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:00, 41.76it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:00, 46.05it/s]
Loading 0:  94%|█████████▍| 342/363 [00:14<00:00, 44.05it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 43.65it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 42.13it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 41.83it/s]
                                                            
Job chaiml-nemo-20241010-tie-9292-v1-mkmlizer completed after 124.58s with status: succeeded
Stopping job with name chaiml-nemo-20241010-tie-9292-v1-mkmlizer
Pipeline stage MKMLizer completed in 125.15s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-tie-9292-v1
Waiting for inference service chaiml-nemo-20241010-tie-9292-v1 to be ready
Inference service chaiml-nemo-20241010-tie-9292-v1 ready after 140.50556445121765s
Pipeline stage MKMLDeployer completed in 141.28s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2417988777160645s
Received healthy response to inference request in 1.4546175003051758s
Received healthy response to inference request in 2.081477403640747s
Received healthy response to inference request in 1.560767650604248s
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
5 requests
1 failed requests
5th percentile: 1.4758475303649903
10th percentile: 1.4970775604248048
20th percentile: 1.5395376205444335
30th percentile: 1.6649096012115479
40th percentile: 1.8731935024261475
50th percentile: 2.081477403640747
60th percentile: 2.145605993270874
70th percentile: 2.209734582901001
80th percentile: 5.851178264617923
90th percentile: 13.069937038421632
95th percentile: 16.679316425323485
99th percentile: 19.566819934844972
mean time: 5.525471448898315
%s, retrying in %s seconds...
Received healthy response to inference request in 1.9350199699401855s
Received healthy response to inference request in 1.8001046180725098s
Received healthy response to inference request in 1.716111660003662s
Received healthy response to inference request in 2.1566390991210938s
Received healthy response to inference request in 1.4997961521148682s
5 requests
0 failed requests
5th percentile: 1.5430592536926269
10th percentile: 1.5863223552703858
20th percentile: 1.6728485584259034
30th percentile: 1.7329102516174317
40th percentile: 1.7665074348449707
50th percentile: 1.8001046180725098
60th percentile: 1.8540707588195802
70th percentile: 1.9080368995666503
80th percentile: 1.9793437957763673
90th percentile: 2.0679914474487306
95th percentile: 2.112315273284912
99th percentile: 2.1477743339538575
mean time: 1.8215342998504638
Pipeline stage StressChecker completed in 39.81s
Shutdown handler de-registered
chaiml-nemo-20241010-tie_9292_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-tie_9292_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-tie_9292_v1 status is now torndown due to DeploymentManager action