developer_uid: azuruce
submission_id: chaiml-nemo-20241010-tie_3480_v1
model_name: chaiml-nemo-20241010-tie_3480_v1
model_group: ChaiML/nemo-20241010_tie
status: torndown
timestamp: 2024-10-11T00:48:36+00:00
num_battles: 7293
num_wins: 3781
celo_rating: 1261.8
family_friendly_score: 0.5516455818913286
family_friendly_standard_error: 0.005957636950598832
submission_type: basic
model_repo: ChaiML/nemo-20241010_tier_merge_v6-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_3480_v1
is_internal_developer: True
language_model: ChaiML/nemo-20241010_tier_merge_v6-albert
model_size: 13B
ranking_group: single
us_pacific_date: 2024-10-10
win_ratio: 0.5184423419717538
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-20241010-tie-3480-v1-mkmlizer
Waiting for job on chaiml-nemo-20241010-tie-3480-v1-mkmlizer to finish
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: Downloaded to shared memory in 68.429s
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmps0fdn2zw, device:0
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: quantized model in 36.094s
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v6-albert in 104.523s
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1/config.json
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1/special_tokens_map.json
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1/tokenizer_config.json
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1/tokenizer.json
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-tie-3480-v1/flywheel_model.0.safetensors
chaiml-nemo-20241010-tie-3480-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:08,  3.01s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:50,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.38it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.94it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  8.05it/s]
Loading 0:   8%|▊         | 29/363 [00:06<00:29, 11.49it/s]
Loading 0:   9%|▉         | 34/363 [00:06<00:22, 14.84it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.66it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.93it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 23.16it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 25.53it/s]
Loading 0:  16%|█▋        | 59/363 [00:07<00:09, 31.01it/s]
Loading 0:  18%|█▊        | 64/363 [00:07<00:08, 34.67it/s]
Loading 0:  19%|█▉        | 69/363 [00:07<00:09, 30.98it/s]
Loading 0:  21%|██        | 76/363 [00:07<00:07, 38.62it/s]
Loading 0:  22%|██▏       | 81/363 [00:08<00:07, 40.28it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 41.74it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 40.47it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.60it/s]
Loading 0:  28%|██▊       | 103/363 [00:08<00:05, 44.31it/s]
Loading 0:  30%|██▉       | 108/363 [00:08<00:05, 43.16it/s]
Loading 0:  31%|███       | 113/363 [00:08<00:05, 41.76it/s]
Loading 0:  33%|███▎      | 119/363 [00:08<00:06, 40.19it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:08, 28.18it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 34.64it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:06, 35.79it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:06, 36.70it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:05, 41.38it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:05, 40.82it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:04, 41.19it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:04, 43.37it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:05, 37.32it/s]
Loading 0:  48%|████▊     | 175/363 [00:10<00:04, 44.52it/s]
Loading 0:  50%|████▉     | 180/363 [00:10<00:04, 44.70it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:03, 45.26it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:04, 42.33it/s]
Loading 0:  54%|█████▍    | 196/363 [00:10<00:03, 41.81it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 30.90it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 32.08it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:04, 36.84it/s]
Loading 0:  60%|█████▉    | 217/363 [00:11<00:03, 39.18it/s]
Loading 0:  61%|██████    | 222/363 [00:11<00:04, 34.70it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 42.96it/s]
Loading 0:  65%|██████▌   | 236/363 [00:12<00:03, 41.89it/s]
Loading 0:  66%|██████▋   | 241/363 [00:12<00:02, 41.40it/s]
Loading 0:  68%|██████▊   | 247/363 [00:12<00:02, 45.56it/s]
Loading 0:  69%|██████▉   | 252/363 [00:12<00:02, 43.28it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 43.58it/s]
Loading 0:  72%|███████▏  | 263/363 [00:12<00:02, 41.95it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:02, 41.29it/s]
Loading 0:  75%|███████▌  | 274/363 [00:12<00:01, 45.85it/s]
Loading 0:  77%|███████▋  | 279/363 [00:12<00:01, 45.27it/s]
Loading 0:  78%|███████▊  | 284/363 [00:13<00:02, 31.27it/s]
Loading 0:  80%|███████▉  | 289/363 [00:13<00:02, 35.04it/s]
Loading 0:  81%|████████  | 294/363 [00:13<00:02, 32.48it/s]
Loading 0:  83%|████████▎ | 301/363 [00:13<00:01, 40.03it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:01, 40.74it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 42.08it/s]
Loading 0:  87%|████████▋ | 317/363 [00:14<00:01, 41.33it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:00, 41.67it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:00, 45.90it/s]
Loading 0:  92%|█████████▏| 333/363 [00:14<00:00, 45.88it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:00, 46.42it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 43.88it/s]
Loading 0:  96%|█████████▌| 349/363 [00:14<00:00, 42.37it/s]
Loading 0:  98%|█████████▊| 355/363 [00:14<00:00, 46.42it/s]
Loading 0:  99%|█████████▉| 360/363 [00:14<00:00, 44.19it/s]
                                                            

Job chaiml-nemo-20241010-tie-3480-v1-mkmlizer completed after 124.2s with status: succeeded
Stopping job with name chaiml-nemo-20241010-tie-3480-v1-mkmlizer
Pipeline stage MKMLizer completed in 124.78s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241010-tie-3480-v1
Waiting for inference service chaiml-nemo-20241010-tie-3480-v1 to be ready
Failed to get response for submission chaiml-elo-alignment-run-3_v34: ('http://chaiml-elo-alignment-run-3-v34-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '{"error":"ValueError : [TypeError(\\"\'numpy.int64\' object is not iterable\\"), TypeError(\'vars() argument must have __dict__ attribute\')]"}')
Inference service chaiml-nemo-20241010-tie-3480-v1 ready after 150.66323328018188s
Pipeline stage MKMLDeployer completed in 151.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3382089138031006s
Received healthy response to inference request in 1.9461371898651123s
Received healthy response to inference request in 1.5260894298553467s
Received healthy response to inference request in 1.5128486156463623s
Received healthy response to inference request in 1.7777459621429443s
5 requests
0 failed requests
5th percentile: 1.5154967784881592
10th percentile: 1.5181449413299561
20th percentile: 1.5234412670135498
30th percentile: 1.5764207363128662
40th percentile: 1.6770833492279054
50th percentile: 1.7777459621429443
60th percentile: 1.8451024532318114
70th percentile: 1.9124589443206788
80th percentile: 2.02455153465271
90th percentile: 2.1813802242279055
95th percentile: 2.259794569015503
99th percentile: 2.322526044845581
mean time: 1.8202060222625733
Pipeline stage StressChecker completed in 10.56s
Shutdown handler de-registered
chaiml-nemo-20241010-tie_3480_v1 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-tie_3480_v1 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-tie_3480_v1 status is now torndown due to DeploymentManager action