chaiml-nemo-20241010-ti_5991

developer_uid: chai_backend_admin

submission_id: chaiml-nemo-20241010-ti_5991_v92

model_name: chaiml-nemo-20241010-ti_5991_v92

model_group: ChaiML/nemo-20241010_tie

status: torndown

timestamp: 2024-10-14T04:00:40+00:00

num_battles: 8583

num_wins: 4334

celo_rating: 1263.44

family_friendly_score: 0.5921818857638459

family_friendly_standard_error: 0.0054327165473641035

submission_type: basic

model_repo: ChaiML/nemo-20241010_tier_merge_v4-albert

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-nemo-20241010-ti_5991_v92

is_internal_developer: True

language_model: ChaiML/nemo-20241010_tier_merge_v4-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-13

win_ratio: 0.5049516486077129

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-20241010-ti-5991-v92-mkmlizer
Waiting for job on chaiml-nemo-20241010-ti-5991-v92-mkmlizer to finish
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ║                                                                     ║
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: Downloaded to shared memory in 28.785s
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi8topn7i, device:0
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: quantized model in 35.507s
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: Processed model ChaiML/nemo-20241010_tier_merge_v4-albert in 64.292s
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v92
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v92/special_tokens_map.json
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v92/config.json
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v92/tokenizer_config.json
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241010-ti-5991-v92/flywheel_model.0.safetensors
chaiml-nemo-20241010-ti-5991-v92-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:05<18:00,  2.99s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:49,  1.23it/s]
Loading 0:   4%|▎         | 13/363 [00:06<01:43,  3.39it/s]
Loading 0:   5%|▍         | 18/363 [00:06<01:04,  5.38it/s]
Loading 0:   7%|▋         | 24/363 [00:06<00:41,  8.21it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:24, 13.39it/s]
Loading 0:  10%|█         | 38/363 [00:06<00:18, 17.34it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:18, 16.92it/s]
Loading 0:  14%|█▍        | 50/363 [00:07<00:13, 22.56it/s]
Loading 0:  15%|█▌        | 55/363 [00:07<00:12, 25.50it/s]
Loading 0:  17%|█▋        | 60/363 [00:07<00:11, 25.87it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 34.15it/s]
Loading 0:  20%|██        | 74/363 [00:07<00:08, 36.03it/s]
Loading 0:  22%|██▏       | 79/363 [00:07<00:07, 37.05it/s]
Loading 0:  24%|██▎       | 86/363 [00:08<00:06, 42.33it/s]
Loading 0:  25%|██▌       | 92/363 [00:08<00:06, 39.91it/s]
Loading 0:  27%|██▋       | 97/363 [00:08<00:06, 39.49it/s]
Loading 0:  29%|██▊       | 104/363 [00:08<00:05, 45.41it/s]
Loading 0:  30%|███       | 110/363 [00:08<00:05, 45.14it/s]
Loading 0:  32%|███▏      | 115/363 [00:08<00:05, 44.61it/s]
Loading 0:  33%|███▎      | 121/363 [00:08<00:06, 34.76it/s]
Loading 0:  34%|███▍      | 125/363 [00:09<00:06, 35.14it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:05, 39.87it/s]
Loading 0:  38%|███▊      | 137/363 [00:09<00:05, 40.24it/s]
Loading 0:  39%|███▉      | 142/363 [00:09<00:05, 39.93it/s]
Loading 0:  41%|████      | 148/363 [00:09<00:04, 44.58it/s]
Loading 0:  42%|████▏     | 153/363 [00:09<00:04, 43.54it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:04, 44.92it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:04, 44.96it/s]
Loading 0:  47%|████▋     | 169/363 [00:10<00:04, 44.09it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:03, 48.82it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:03, 47.65it/s]
Loading 0:  52%|█████▏    | 187/363 [00:10<00:03, 46.81it/s]
Loading 0:  53%|█████▎    | 194/363 [00:10<00:03, 51.43it/s]
Loading 0:  55%|█████▌    | 200/363 [00:10<00:03, 49.35it/s]
Loading 0:  56%|█████▋    | 205/363 [00:10<00:04, 32.27it/s]
Loading 0:  58%|█████▊    | 212/363 [00:11<00:03, 38.57it/s]
Loading 0:  60%|██████    | 218/363 [00:11<00:03, 38.94it/s]
Loading 0:  61%|██████▏   | 223/363 [00:11<00:03, 39.25it/s]
Loading 0:  63%|██████▎   | 230/363 [00:11<00:03, 43.97it/s]
Loading 0:  65%|██████▌   | 236/363 [00:11<00:02, 42.82it/s]
Loading 0:  66%|██████▋   | 241/363 [00:11<00:02, 41.97it/s]
Loading 0:  68%|██████▊   | 247/363 [00:11<00:02, 46.02it/s]
Loading 0:  69%|██████▉   | 252/363 [00:11<00:02, 44.57it/s]
Loading 0:  71%|███████   | 257/363 [00:12<00:02, 45.65it/s]
Loading 0:  72%|███████▏  | 262/363 [00:12<00:02, 45.64it/s]
Loading 0:  74%|███████▎  | 267/363 [00:12<00:02, 38.53it/s]
Loading 0:  76%|███████▌  | 275/363 [00:12<00:01, 47.22it/s]
Loading 0:  77%|███████▋  | 281/363 [00:12<00:01, 45.87it/s]
Loading 0:  79%|███████▉  | 286/363 [00:12<00:02, 31.72it/s]
Loading 0:  81%|████████  | 293/363 [00:13<00:01, 38.28it/s]
Loading 0:  82%|████████▏ | 299/363 [00:13<00:01, 39.54it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:01, 40.35it/s]
Loading 0:  86%|████████▌ | 311/363 [00:13<00:01, 45.50it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 44.83it/s]
Loading 0:  88%|████████▊ | 321/363 [00:13<00:01, 38.78it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:00, 46.70it/s]
Loading 0:  92%|█████████▏| 335/363 [00:13<00:00, 46.04it/s]
Loading 0:  94%|█████████▎| 340/363 [00:14<00:00, 45.17it/s]
Loading 0:  96%|█████████▌| 347/363 [00:14<00:00, 49.48it/s]
Loading 0:  97%|█████████▋| 353/363 [00:14<00:00, 48.10it/s]
Loading 0:  99%|█████████▊| 358/363 [00:14<00:00, 47.19it/s]
                                                            
Job chaiml-nemo-20241010-ti-5991-v92-mkmlizer completed after 83.78s with status: succeeded
Stopping job with name chaiml-nemo-20241010-ti-5991-v92-mkmlizer
Pipeline stage MKMLizer completed in 84.36s
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-ti-5991-v92
Waiting for inference service chaiml-nemo-20241010-ti-5991-v92 to be ready
Inference service chaiml-nemo-20241010-ti-5991-v92 ready after 180.95600605010986s
Pipeline stage MKMLDeployer completed in 181.56s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.799882173538208s
Received healthy response to inference request in 1.4502007961273193s
Received healthy response to inference request in 1.4204370975494385s
Received healthy response to inference request in 1.5519657135009766s
Received healthy response to inference request in 1.5828979015350342s
5 requests
0 failed requests
5th percentile: 1.4263898372650146
10th percentile: 1.4323425769805909
20th percentile: 1.4442480564117433
30th percentile: 1.4705537796020507
40th percentile: 1.5112597465515136
50th percentile: 1.5519657135009766
60th percentile: 1.5643385887145995
70th percentile: 1.5767114639282227
80th percentile: 1.626294755935669
90th percentile: 1.7130884647369384
95th percentile: 1.756485319137573
99th percentile: 1.791202802658081
mean time: 1.5610767364501954
Pipeline stage StressChecker completed in 9.18s
Shutdown handler de-registered
chaiml-nemo-20241010-ti_5991_v92 status is now deployed due to DeploymentManager action
chaiml-nemo-20241010-ti_5991_v92 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241010-ti_5991_v92 status is now torndown due to DeploymentManager action