chaiml-nemo-20241017-tie_8098

developer_uid: azuruce

submission_id: chaiml-nemo-20241017-tie_8098_v2

model_name: chaiml-nemo-20241017-tie_8098_v2

model_group: ChaiML/nemo-20241017-tie

status: torndown

timestamp: 2024-10-18T16:02:10+00:00

num_battles: 8511

num_wins: 4262

celo_rating: 1252.55

family_friendly_score: 0.6151325222235877

family_friendly_standard_error: 0.005368875049392797

submission_type: basic

model_repo: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 4

max_input_tokens: 1024

max_output_tokens: 64

display_name: chaiml-nemo-20241017-tie_8098_v2

is_internal_developer: True

language_model: ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert

model_size: 13B

ranking_group: single

us_pacific_date: 2024-10-18

win_ratio: 0.5007637175420044

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-20241017-tie-8098-v2-mkmlizer
Waiting for job on chaiml-nemo-20241017-tie-8098-v2-mkmlizer to finish
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║       /___/                                                         ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  Version: 0.11.12                                                   ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║  Expiration: 2025-01-15 23:59:59                                    ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ║                                                                     ║
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: Downloaded to shared memory in 34.373s
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpj8kgx7sb, device:0
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: quantized model in 38.573s
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: Processed model ChaiML/nemo-20241017-ties-remerge_v2_5merge-albert in 72.947s
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2/config.json
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2/special_tokens_map.json
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2/tokenizer_config.json
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2/tokenizer.json
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-nemo-20241017-tie-8098-v2/flywheel_model.0.safetensors
chaiml-nemo-20241017-tie-8098-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 2/363 [00:06<18:41,  3.11s/it]
Loading 0:   2%|▏         | 6/363 [00:06<04:59,  1.19it/s]
Loading 0:   3%|▎         | 11/363 [00:06<02:11,  2.68it/s]
Loading 0:   4%|▍         | 15/363 [00:06<01:23,  4.17it/s]
Loading 0:   6%|▌         | 22/363 [00:06<00:43,  7.79it/s]
Loading 0:   7%|▋         | 27/363 [00:06<00:31, 10.77it/s]
Loading 0:   9%|▉         | 32/363 [00:06<00:22, 14.40it/s]
Loading 0:  10%|█         | 38/363 [00:07<00:17, 18.70it/s]
Loading 0:  12%|█▏        | 43/363 [00:07<00:17, 17.85it/s]
Loading 0:  13%|█▎        | 49/363 [00:07<00:13, 22.76it/s]
Loading 0:  15%|█▍        | 53/363 [00:07<00:12, 24.85it/s]
Loading 0:  16%|█▌        | 58/363 [00:07<00:10, 29.31it/s]
Loading 0:  17%|█▋        | 63/363 [00:07<00:09, 31.99it/s]
Loading 0:  19%|█▊        | 68/363 [00:07<00:08, 34.78it/s]
Loading 0:  20%|██        | 73/363 [00:08<00:07, 36.33it/s]
Loading 0:  21%|██▏       | 78/363 [00:08<00:10, 27.88it/s]
Loading 0:  23%|██▎       | 83/363 [00:08<00:08, 31.98it/s]
Loading 0:  24%|██▍       | 87/363 [00:08<00:08, 30.72it/s]
Loading 0:  26%|██▌       | 94/363 [00:08<00:07, 37.93it/s]
Loading 0:  27%|██▋       | 99/363 [00:08<00:06, 37.89it/s]
Loading 0:  29%|██▊       | 104/363 [00:09<00:06, 37.48it/s]
Loading 0:  30%|██▉       | 108/363 [00:09<00:07, 34.90it/s]
Loading 0:  31%|███       | 112/363 [00:09<00:07, 33.58it/s]
Loading 0:  32%|███▏      | 116/363 [00:09<00:07, 32.49it/s]
Loading 0:  33%|███▎      | 121/363 [00:09<00:09, 25.08it/s]
Loading 0:  34%|███▍      | 124/363 [00:09<00:10, 23.67it/s]
Loading 0:  35%|███▌      | 128/363 [00:09<00:09, 25.94it/s]
Loading 0:  36%|███▋      | 132/363 [00:10<00:09, 23.88it/s]
Loading 0:  38%|███▊      | 137/363 [00:10<00:08, 28.20it/s]
Loading 0:  39%|███▉      | 141/363 [00:10<00:08, 27.50it/s]
Loading 0:  40%|████      | 146/363 [00:10<00:06, 31.89it/s]
Loading 0:  41%|████▏     | 150/363 [00:10<00:07, 29.56it/s]
Loading 0:  43%|████▎     | 155/363 [00:10<00:06, 33.48it/s]
Loading 0:  44%|████▍     | 159/363 [00:11<00:06, 30.02it/s]
Loading 0:  45%|████▌     | 164/363 [00:11<00:05, 33.85it/s]
Loading 0:  46%|████▋     | 168/363 [00:11<00:06, 30.92it/s]
Loading 0:  48%|████▊     | 173/363 [00:11<00:05, 35.03it/s]
Loading 0:  49%|████▉     | 177/363 [00:11<00:05, 32.56it/s]
Loading 0:  51%|█████     | 184/363 [00:11<00:04, 39.04it/s]
Loading 0:  52%|█████▏    | 189/363 [00:11<00:04, 39.51it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:04, 40.86it/s]
Loading 0:  55%|█████▍    | 199/363 [00:12<00:03, 42.91it/s]
Loading 0:  56%|█████▌    | 204/363 [00:12<00:06, 25.63it/s]
Loading 0:  58%|█████▊    | 211/363 [00:12<00:04, 32.73it/s]
Loading 0:  60%|█████▉    | 216/363 [00:12<00:04, 33.62it/s]
Loading 0:  61%|██████    | 221/363 [00:12<00:04, 34.97it/s]
Loading 0:  62%|██████▏   | 226/363 [00:12<00:03, 37.66it/s]
Loading 0:  64%|██████▎   | 231/363 [00:13<00:04, 33.00it/s]
Loading 0:  66%|██████▌   | 238/363 [00:13<00:03, 38.57it/s]
Loading 0:  67%|██████▋   | 243/363 [00:13<00:03, 38.30it/s]
Loading 0:  68%|██████▊   | 248/363 [00:13<00:03, 37.96it/s]
Loading 0:  69%|██████▉   | 252/363 [00:13<00:02, 37.27it/s]
Loading 0:  71%|███████   | 256/363 [00:13<00:02, 36.58it/s]
Loading 0:  72%|███████▏  | 260/363 [00:13<00:02, 36.04it/s]
Loading 0:  73%|███████▎  | 266/363 [00:13<00:02, 40.27it/s]
Loading 0:  75%|███████▍  | 272/363 [00:14<00:02, 39.96it/s]
Loading 0:  76%|███████▋  | 277/363 [00:14<00:02, 38.47it/s]
Loading 0:  77%|███████▋  | 281/363 [00:14<00:02, 38.82it/s]
Loading 0:  79%|███████▊  | 285/363 [00:14<00:03, 24.45it/s]
Loading 0:  80%|████████  | 292/363 [00:14<00:02, 32.30it/s]
Loading 0:  82%|████████▏ | 297/363 [00:14<00:01, 33.59it/s]
Loading 0:  83%|████████▎ | 302/363 [00:15<00:01, 36.08it/s]
Loading 0:  85%|████████▍ | 308/363 [00:15<00:01, 37.05it/s]
Loading 0:  86%|████████▌ | 313/363 [00:15<00:01, 36.48it/s]
Loading 0:  88%|████████▊ | 320/363 [00:15<00:01, 42.26it/s]
Loading 0:  90%|████████▉ | 326/363 [00:15<00:00, 41.16it/s]
Loading 0:  91%|█████████ | 331/363 [00:15<00:00, 40.02it/s]
Loading 0:  93%|█████████▎| 338/363 [00:15<00:00, 45.19it/s]
Loading 0:  95%|█████████▍| 344/363 [00:15<00:00, 43.17it/s]
Loading 0:  96%|█████████▌| 349/363 [00:16<00:00, 40.95it/s]
Loading 0:  98%|█████████▊| 355/363 [00:16<00:00, 44.47it/s]
Loading 0:  99%|█████████▉| 360/363 [00:16<00:00, 44.28it/s]
                                                            
Job chaiml-nemo-20241017-tie-8098-v2-mkmlizer completed after 93.97s with status: succeeded
Stopping job with name chaiml-nemo-20241017-tie-8098-v2-mkmlizer
Pipeline stage MKMLizer completed in 94.55s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-nemo-20241017-tie-8098-v2
Waiting for inference service chaiml-nemo-20241017-tie-8098-v2 to be ready
Inference service chaiml-nemo-20241017-tie-8098-v2 ready after 170.86289739608765s
Pipeline stage MKMLDeployer completed in 171.50s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.8561816215515137s
Received healthy response to inference request in 1.9035060405731201s
Received healthy response to inference request in 1.5737993717193604s
Received healthy response to inference request in 1.9733858108520508s
Received healthy response to inference request in 1.530203104019165s
5 requests
0 failed requests
5th percentile: 1.5389223575592041
10th percentile: 1.5476416110992433
20th percentile: 1.5650801181793212
30th percentile: 1.630275821685791
40th percentile: 1.7432287216186524
50th percentile: 1.8561816215515137
60th percentile: 1.8751113891601563
70th percentile: 1.894041156768799
80th percentile: 1.9174819946289063
90th percentile: 1.9454339027404786
95th percentile: 1.9594098567962646
99th percentile: 1.9705906200408936
mean time: 1.767415189743042
Pipeline stage StressChecker completed in 10.12s
Shutdown handler de-registered
chaiml-nemo-20241017-tie_8098_v2 status is now deployed due to DeploymentManager action
chaiml-nemo-20241017-tie_8098_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-nemo-20241017-tie_8098_v2 status is now torndown due to DeploymentManager action