developer_uid: azuruce
submission_id: probemedicalyonseimaila_97469_v1
model_name: medical
model_group: ProbeMedicalYonseiMAILab
status: torndown
timestamp: 2025-01-19T04:16:40+00:00
num_battles: 14125
num_wins: 5282
celo_rating: 1180.51
family_friendly_score: 0.607
family_friendly_standard_error: 0.006907257053273753
submission_type: basic
model_repo: ProbeMedicalYonseiMAILab/medllama3-v20
model_architecture: LlamaForCausalLM
model_num_parameters: 8030261248.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
display_name: medical
is_internal_developer: True
language_model: ProbeMedicalYonseiMAILab/medllama3-v20
model_size: 8B
ranking_group: single
us_pacific_date: 2025-01-18
win_ratio: 0.37394690265486724
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 100, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n', '</s>', '####', 'Bot:', 'User:', 'You:', 'Me', '<|im_end|>', '<|eot_id|>'], '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': '{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 probemedicalyonseimaila-97469-v1-mkmlizer
Waiting for job on probemedicalyonseimaila-97469-v1-mkmlizer to finish
probemedicalyonseimaila-97469-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
probemedicalyonseimaila-97469-v1-mkmlizer: ║     _____            __           __                                ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║       /___/                                                         ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║                                                                     ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  Version: 0.11.12                                                   ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  https://mk1.ai                                                     ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║                                                                     ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  belonging to:                                                      ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║                                                                     ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  Chai Research Corp.                                                ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
probemedicalyonseimaila-97469-v1-mkmlizer: ║                                                                     ║
probemedicalyonseimaila-97469-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
probemedicalyonseimaila-97469-v1-mkmlizer: Downloaded to shared memory in 45.062s
probemedicalyonseimaila-97469-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3_6_ldx_, device:0
probemedicalyonseimaila-97469-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
probemedicalyonseimaila-97469-v1-mkmlizer: quantized model in 25.751s
probemedicalyonseimaila-97469-v1-mkmlizer: Processed model ProbeMedicalYonseiMAILab/medllama3-v20 in 70.813s
probemedicalyonseimaila-97469-v1-mkmlizer: creating bucket guanaco-mkml-models
probemedicalyonseimaila-97469-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
probemedicalyonseimaila-97469-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/probemedicalyonseimaila-97469-v1
probemedicalyonseimaila-97469-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/probemedicalyonseimaila-97469-v1/tokenizer.json
probemedicalyonseimaila-97469-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/probemedicalyonseimaila-97469-v1/flywheel_model.0.safetensors
probemedicalyonseimaila-97469-v1-mkmlizer: 
Loading 0:   0%|          | 0/291 [00:00<?, ?it/s]
Loading 0:   2%|▏         | 5/291 [00:00<00:09, 29.04it/s]
Loading 0:   5%|▍         | 14/291 [00:00<00:06, 43.69it/s]
Loading 0:   8%|▊         | 23/291 [00:00<00:05, 47.74it/s]
Loading 0:  11%|█         | 31/291 [00:00<00:04, 56.62it/s]
Loading 0:  13%|█▎        | 38/291 [00:00<00:04, 55.66it/s]
Loading 0:  15%|█▌        | 44/291 [00:00<00:04, 55.62it/s]
Loading 0:  17%|█▋        | 50/291 [00:01<00:04, 49.01it/s]
Loading 0:  20%|█▉        | 57/291 [00:01<00:04, 48.98it/s]
Loading 0:  22%|██▏       | 63/291 [00:01<00:05, 40.46it/s]
Loading 0:  23%|██▎       | 68/291 [00:01<00:05, 41.74it/s]
Loading 0:  25%|██▌       | 74/291 [00:01<00:05, 40.89it/s]
Loading 0:  29%|██▊       | 83/291 [00:01<00:04, 45.55it/s]
Loading 0:  32%|███▏      | 92/291 [00:01<00:04, 47.59it/s]
Loading 0:  34%|███▍      | 100/291 [00:02<00:03, 53.74it/s]
Loading 0:  36%|███▋      | 106/291 [00:02<00:03, 51.32it/s]
Loading 0:  38%|███▊      | 112/291 [00:02<00:03, 48.30it/s]
Loading 0:  41%|████      | 119/291 [00:02<00:03, 50.79it/s]
Loading 0:  44%|████▍     | 128/291 [00:02<00:03, 52.02it/s]
Loading 0:  47%|████▋     | 136/291 [00:02<00:02, 57.91it/s]
Loading 0:  49%|████▉     | 142/291 [00:02<00:02, 54.15it/s]
Loading 0:  51%|█████     | 148/291 [00:03<00:03, 45.56it/s]
Loading 0:  53%|█████▎    | 154/291 [00:03<00:03, 44.57it/s]
Loading 0:  55%|█████▍    | 159/291 [00:03<00:02, 45.33it/s]
Loading 0:  57%|█████▋    | 167/291 [00:03<00:02, 45.98it/s]
Loading 0:  60%|██████    | 176/291 [00:03<00:02, 48.58it/s]
Loading 0:  63%|██████▎   | 184/291 [00:03<00:01, 54.95it/s]
Loading 0:  65%|██████▌   | 190/291 [00:03<00:01, 52.04it/s]
Loading 0:  67%|██████▋   | 196/291 [00:03<00:01, 52.42it/s]
Loading 0:  69%|██████▉   | 202/291 [00:04<00:01, 54.09it/s]
Loading 0:  71%|███████▏  | 208/291 [00:04<00:01, 50.12it/s]
Loading 0:  74%|███████▎  | 214/291 [00:04<00:01, 51.66it/s]
Loading 0:  76%|███████▌  | 220/291 [00:04<00:01, 46.50it/s]
Loading 0:  77%|███████▋  | 225/291 [00:04<00:01, 38.10it/s]
Loading 0:  79%|███████▉  | 230/291 [00:04<00:01, 39.54it/s]
Loading 0:  82%|████████▏ | 238/291 [00:04<00:01, 47.66it/s]
Loading 0:  84%|████████▍ | 244/291 [00:05<00:01, 45.68it/s]
Loading 0:  86%|████████▌ | 249/291 [00:05<00:00, 46.29it/s]
Loading 0:  88%|████████▊ | 256/291 [00:05<00:00, 51.87it/s]
Loading 0:  90%|█████████ | 262/291 [00:05<00:00, 48.90it/s]
Loading 0:  92%|█████████▏| 268/291 [00:05<00:00, 49.92it/s]
Loading 0:  95%|█████████▍| 275/291 [00:05<00:00, 47.16it/s]
Loading 0:  98%|█████████▊| 284/291 [00:05<00:00, 49.34it/s]
Loading 0: 100%|██████████| 291/291 [00:11<00:00,  4.18it/s]
                                                            

Job probemedicalyonseimaila-97469-v1-mkmlizer completed after 93.77s with status: succeeded
Stopping job with name probemedicalyonseimaila-97469-v1-mkmlizer
Pipeline stage MKMLizer completed in 94.24s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service probemedicalyonseimaila-97469-v1
Waiting for inference service probemedicalyonseimaila-97469-v1 to be ready
Inference service probemedicalyonseimaila-97469-v1 ready after 110.38238477706909s
Pipeline stage MKMLDeployer completed in 110.96s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5393803119659424s
Received healthy response to inference request in 1.09421706199646s
Received healthy response to inference request in 1.1421740055084229s
Received healthy response to inference request in 1.1590816974639893s
Received healthy response to inference request in 1.0572731494903564s
5 requests
0 failed requests
5th percentile: 1.064661931991577
10th percentile: 1.0720507144927978
20th percentile: 1.0868282794952393
30th percentile: 1.1038084506988526
40th percentile: 1.1229912281036376
50th percentile: 1.1421740055084229
60th percentile: 1.1489370822906495
70th percentile: 1.155700159072876
80th percentile: 1.23514142036438
90th percentile: 1.387260866165161
95th percentile: 1.4633205890655516
99th percentile: 1.5241683673858641
mean time: 1.1984252452850341
Pipeline stage StressChecker completed in 7.51s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyTriggerPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage OfflineFamilyFriendlyTriggerPipeline completed in 0.69s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
triggered trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 0.66s
Shutdown handler de-registered
probemedicalyonseimaila_97469_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage OfflineFamilyFriendlyScorer
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 2150.13s
Shutdown handler de-registered
probemedicalyonseimaila_97469_v1 status is now inactive due to auto deactivation removed underperforming models
probemedicalyonseimaila_97469_v1 status is now torndown due to DeploymentManager action
ChatRequest
Generation Params
Prompt Formatter
Chat History
ChatMessage 1