chaiml-nemo-20241009-tie_3924

developer_uid: azuruce

submission_id: chaiml-nemo-20241009-tie_3924_v3

model_name: chaiml-nemo-20241009-tie_3924_v3

model_group: ChaiML/nemo-20241009-tie

status: torndown

timestamp: 2024-10-10T19:46:16+00:00

num_battles: 5986

num_wins: 3176

celo_rating: 1277.68

family_friendly_score: 0.583463158502106

family_friendly_standard_error: 0.006467104137967231

submission_type: basic

model_repo: ChaiML/nemo-20241009-ties-v5-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_3924_v3

is_internal_developer: True

language_model: ChaiML/nemo-20241009-ties-v5-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-10

win_ratio: 0.5305713331105913

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-3924-v3-mkmlizer
Waiting for job on chaiml-nemo-20241009-tie-3924-v3-mkmlizer to finish
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ║                                                                     ║
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: Downloaded to shared memory in 29.715s
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_0_1mlqq, device:0
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: quantized model in 36.174s
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: Processed model ChaiML/nemo-20241009-ties-v5-albert in 65.889s
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3/config.json
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3/special_tokens_map.json
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3/tokenizer_config.json
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3/tokenizer.json
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241009-tie-3924-v3/flywheel_model.0.safetensors
chaiml-nemo-20241009-tie-3924-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:13,  3.03s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:51,  1.22it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:44,  3.36it/s]
Loading 0:   5%|▍         | 17/363 [00:06<01:10,  4.90it/s]
Loading 0:   6%|▋         | 23/363 [00:06<00:42,  7.95it/s]
Loading 0:   8%|▊         | 28/363 [00:06<00:30, 11.08it/s]
Loading 0:   9%|▉         | 33/363 [00:06<00:24, 13.58it/s]
Loading 0:  11%|█         | 40/363 [00:07<00:19, 16.49it/s]
Loading 0:  12%|█▏        | 44/363 [00:07<00:16, 18.97it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:12, 24.15it/s]
Loading 0:  15%|█▌        | 56/363 [00:07<00:11, 27.38it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:10, 27.95it/s]
Loading 0:  18%|█▊        | 67/363 [00:07<00:08, 35.26it/s]
Loading 0:  20%|█▉        | 72/363 [00:07<00:07, 36.92it/s]
Loading 0:  21%|██        | 77/363 [00:08<00:07, 37.94it/s]
Loading 0:  23%|██▎       | 82/363 [00:08<00:07, 39.99it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 33.73it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:06, 40.28it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 41.09it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:06, 42.21it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:06, 40.97it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:06, 39.68it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:08, 29.80it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:07, 31.13it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:06, 35.68it/s]
Loading 0:  37%|███▋      | 135/363 [00:09<00:06, 35.51it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:05, 37.22it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:05, 40.23it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:06, 34.87it/s]
Loading 0:  43%|████▎     | 157/363 [00:10<00:04, 41.97it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:04, 42.24it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:04, 42.33it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:04, 43.04it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:05, 35.18it/s]
Loading 0:  51%|█████     | 185/363 [00:10<00:04, 43.39it/s]
Loading 0:  53%|█████▎    | 191/363 [00:10<00:04, 41.95it/s]
Loading 0:  54%|█████▍    | 196/363 [00:11<00:04, 40.79it/s]
Loading 0:  56%|█████▌    | 202/363 [00:11<00:05, 31.78it/s]
Loading 0:  57%|█████▋    | 206/363 [00:11<00:04, 32.83it/s]
Loading 0:  58%|█████▊    | 211/363 [00:11<00:04, 36.23it/s]
Loading 0:  60%|█████▉    | 216/363 [00:11<00:03, 38.51it/s]
Loading 0:  61%|██████    | 221/363 [00:11<00:03, 40.36it/s]
Loading 0:  63%|██████▎   | 227/363 [00:11<00:03, 39.83it/s]
Loading 0:  64%|██████▍   | 232/363 [00:12<00:03, 38.66it/s]
Loading 0:  66%|██████▌   | 238/363 [00:12<00:02, 42.92it/s]
Loading 0:  67%|██████▋   | 243/363 [00:12<00:02, 42.94it/s]
Loading 0:  68%|██████▊   | 248/363 [00:12<00:02, 42.45it/s]
Loading 0:  70%|██████▉   | 253/363 [00:12<00:02, 44.34it/s]
Loading 0:  71%|███████   | 258/363 [00:12<00:02, 37.09it/s]
Loading 0:  73%|███████▎  | 265/363 [00:12<00:02, 44.69it/s]
Loading 0:  74%|███████▍  | 270/363 [00:12<00:02, 44.89it/s]
Loading 0:  76%|███████▌  | 275/363 [00:13<00:01, 45.23it/s]
Loading 0:  77%|███████▋  | 281/363 [00:13<00:01, 43.06it/s]
Loading 0:  79%|███████▉  | 286/363 [00:13<00:02, 29.07it/s]
Loading 0:  80%|████████  | 292/363 [00:13<00:02, 34.87it/s]
Loading 0:  82%|████████▏ | 297/363 [00:13<00:01, 37.04it/s]
Loading 0:  83%|████████▎ | 302/363 [00:13<00:01, 38.93it/s]
Loading 0:  85%|████████▍ | 308/363 [00:14<00:01, 38.82it/s]
Loading 0:  86%|████████▌ | 313/363 [00:14<00:01, 38.44it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 41.90it/s]
Loading 0:  89%|████████▉ | 324/363 [00:14<00:00, 42.15it/s]
Loading 0:  91%|█████████ | 329/363 [00:14<00:00, 41.96it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:00, 43.52it/s]
Loading 0:  93%|█████████▎| 339/363 [00:14<00:00, 37.48it/s]
Loading 0:  95%|█████████▌| 346/363 [00:14<00:00, 44.94it/s]
Loading 0:  97%|█████████▋| 351/363 [00:15<00:00, 44.96it/s]
Loading 0:  98%|█████████▊| 356/363 [00:15<00:00, 45.55it/s]
Loading 0: 100%|█████████▉| 362/363 [00:15<00:00, 42.96it/s]
                                                            
Job chaiml-nemo-20241009-tie-3924-v3-mkmlizer completed after 93.98s with status: succeeded
Stopping job with name chaiml-nemo-20241009-tie-3924-v3-mkmlizer
Pipeline stage MKMLizer completed in 94.51s
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-20241009-tie-3924-v3
Waiting for inference service chaiml-nemo-20241009-tie-3924-v3 to be ready
Inference service chaiml-nemo-20241009-tie-3924-v3 ready after 140.48781085014343s
Pipeline stage MKMLDeployer completed in 140.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0118117332458496s
Received healthy response to inference request in 1.5616426467895508s
Received healthy response to inference request in 1.4983344078063965s
Received healthy response to inference request in 1.867424488067627s
Received healthy response to inference request in 1.6106998920440674s
5 requests
0 failed requests
5th percentile: 1.5109960556030273
10th percentile: 1.5236577033996581
20th percentile: 1.54898099899292
30th percentile: 1.5714540958404541
40th percentile: 1.5910769939422607
50th percentile: 1.6106998920440674
60th percentile: 1.7133897304534913
70th percentile: 1.816079568862915
80th percentile: 1.8963019371032714
90th percentile: 1.9540568351745606
95th percentile: 1.9829342842102051
99th percentile: 2.0060362434387207
mean time: 1.7099826335906982
Pipeline stage StressChecker completed in 10.13s
Shutdown handler de-registered
chaiml-nemo-20241009-tie_3924_v3 status is now deployed due to DeploymentManager action
chaiml-nemo-20241009-tie_3924_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241009-tie_3924_v3 status is now torndown due to DeploymentManager action