jic062-dpo-v3-0-nemo-e2

submission_id: jic062-dpo-v3-0-nemo-e2_v1

developer_uid: chace9580

best_of: 8

celo_rating: 1271.16

display_name: jic062-dpo-v3-0-nemo-e2_v1

family_friendly_score: 0.5877130219851698

family_friendly_standard_error: 0.005579546993510403

formatter: {'memory_template': '[INST]system\n{memory}[/INST]\n', 'prompt_template': '[INST]user\n{prompt}[/INST]\n', 'bot_template': '[INST]assistant\n{bot_name}: {message}[/INST]\n', 'user_template': '[INST]user\n{user_name}: {message}[/INST]\n', 'response_template': '[INST]assistant\n{bot_name}:', 'truncate_by_message': False}

generation_params: {'temperature': 1.0, 'top_p': 0.9, 'min_p': 0.05, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

is_internal_developer: False

language_model: jic062/dpo-v3.0-Nemo-e2

max_input_tokens: 1024

max_output_tokens: 64

model_architecture: MistralForCausalLM

model_group: jic062/dpo-v3.0-Nemo-e2

model_name: jic062-dpo-v3-0-nemo-e2_v1

model_num_parameters: 12772070400.0

model_repo: jic062/dpo-v3.0-Nemo-e2

model_size: 13B

num_battles: 8215

num_wins: 4271

ranking_group: single

status: torndown

submission_type: basic

timestamp: 2024-10-14T04:12:37+00:00

us_pacific_date: 2024-10-13

win_ratio: 0.5199026171637249

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 jic062-dpo-v3-0-nemo-e2-v1-mkmlizer
Waiting for job on jic062-dpo-v3-0-nemo-e2-v1-mkmlizer to finish
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║     _____            __           __                                ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║       /___/                                                         ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  belonging to:                                                      ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ║                                                                     ║
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: Downloaded to shared memory in 51.134s
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8k4hb9sz, device:0
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: quantized model in 35.383s
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: Processed model jic062/dpo-v3.0-Nemo-e2 in 86.517s
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: creating bucket guanaco-mkml-models
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1/config.json
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1/special_tokens_map.json
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1/tokenizer_config.json
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1/tokenizer.json
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/jic062-dpo-v3-0-nemo-e2-v1/flywheel_model.0.safetensors
jic062-dpo-v3-0-nemo-e2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.22it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.40it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 48.19it/s]
Loading 0:   7%|▋         | 25/363 [00:00<00:06, 49.69it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 52.30it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 50.18it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 51.19it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:05, 53.25it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 47.05it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.10it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.22it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.01it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 41.88it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 42.22it/s]
Loading 0:  25%|██▍       | 90/363 [00:01<00:05, 47.36it/s]
Loading 0:  26%|██▌       | 95/363 [00:02<00:05, 47.93it/s]
Loading 0:  28%|██▊       | 100/363 [00:02<00:06, 39.52it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 49.00it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.38it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 43.82it/s]
Loading 0:  35%|███▍      | 126/363 [00:02<00:04, 48.45it/s]
Loading 0:  36%|███▋      | 132/363 [00:02<00:04, 47.45it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:04, 46.44it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:06, 35.07it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 35.35it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 34.45it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 40.02it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 39.45it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:04, 40.74it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 40.48it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 40.85it/s]
Loading 0:  51%|█████     | 184/363 [00:04<00:03, 46.13it/s]
Loading 0:  52%|█████▏    | 190/363 [00:04<00:03, 44.50it/s]
Loading 0:  54%|█████▎    | 195/363 [00:04<00:04, 41.72it/s]
Loading 0:  55%|█████▌    | 201/363 [00:04<00:03, 45.53it/s]
Loading 0:  57%|█████▋    | 206/363 [00:04<00:03, 45.86it/s]
Loading 0:  58%|█████▊    | 211/363 [00:04<00:03, 46.59it/s]
Loading 0:  60%|█████▉    | 217/363 [00:04<00:03, 44.81it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 33.42it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:03, 34.14it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:03, 33.12it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 39.14it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:02, 41.62it/s]
Loading 0:  68%|██████▊   | 247/363 [00:05<00:02, 42.96it/s]
Loading 0:  70%|██████▉   | 253/363 [00:05<00:02, 43.44it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 43.25it/s]
Loading 0:  73%|███████▎  | 265/363 [00:06<00:02, 48.11it/s]
Loading 0:  75%|███████▍  | 271/363 [00:06<00:02, 45.37it/s]
Loading 0:  76%|███████▌  | 276/363 [00:06<00:02, 41.54it/s]
Loading 0:  78%|███████▊  | 282/363 [00:06<00:01, 45.41it/s]
Loading 0:  79%|███████▉  | 287/363 [00:06<00:01, 43.48it/s]
Loading 0:  80%|████████  | 292/363 [00:06<00:01, 44.18it/s]
Loading 0:  82%|████████▏ | 298/363 [00:06<00:01, 43.50it/s]
Loading 0:  84%|████████▎ | 304/363 [00:13<00:21,  2.68it/s]
Loading 0:  85%|████████▍ | 308/363 [00:13<00:16,  3.41it/s]
Loading 0:  86%|████████▌ | 312/363 [00:13<00:11,  4.39it/s]
Loading 0:  88%|████████▊ | 320/363 [00:14<00:05,  7.22it/s]
Loading 0:  90%|████████▉ | 326/363 [00:14<00:03,  9.77it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:02, 12.39it/s]
Loading 0:  93%|█████████▎| 338/363 [00:14<00:01, 17.34it/s]
Loading 0:  95%|█████████▍| 344/363 [00:14<00:00, 21.40it/s]
Loading 0:  96%|█████████▋| 350/363 [00:14<00:00, 25.94it/s]
Loading 0:  98%|█████████▊| 356/363 [00:14<00:00, 30.83it/s]
Loading 0: 100%|█████████▉| 362/363 [00:14<00:00, 33.16it/s]
                                                            
Job jic062-dpo-v3-0-nemo-e2-v1-mkmlizer completed after 114.3s with status: succeeded
Stopping job with name jic062-dpo-v3-0-nemo-e2-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.86s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service jic062-dpo-v3-0-nemo-e2-v1
Waiting for inference service jic062-dpo-v3-0-nemo-e2-v1 to be ready
Inference service jic062-dpo-v3-0-nemo-e2-v1 ready after 180.65301036834717s
Pipeline stage MKMLDeployer completed in 181.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.340045690536499s
Received healthy response to inference request in 1.735445261001587s
Received healthy response to inference request in 1.9521591663360596s
Received healthy response to inference request in 2.288198709487915s
Received healthy response to inference request in 1.8333139419555664s
5 requests
0 failed requests
5th percentile: 1.7550189971923829
10th percentile: 1.7745927333831788
20th percentile: 1.8137402057647705
30th percentile: 1.857082986831665
40th percentile: 1.9046210765838623
50th percentile: 1.9521591663360596
60th percentile: 2.086574983596802
70th percentile: 2.220990800857544
80th percentile: 2.298568105697632
90th percentile: 2.3193068981170653
95th percentile: 2.329676294326782
99th percentile: 2.3379718112945556
mean time: 2.0298325538635256
Pipeline stage StressChecker completed in 11.71s
Shutdown handler de-registered
jic062-dpo-v3-0-nemo-e2_v1 status is now deployed due to DeploymentManager action
jic062-dpo-v3-0-nemo-e2_v1 status is now inactive due to auto deactivation removed underperforming models
jic062-dpo-v3-0-nemo-e2_v1 status is now torndown due to DeploymentManager action