developer_uid: BBChicago
submission_id: bbchicago-tang82mv-dpo-ep3_v1
model_name: tang82mv-dpo-ep3
model_group: BBChicago/tang82mv-dpo-e
status: torndown
timestamp: 2025-04-30T02:45:43+00:00
num_battles: 6093
num_wins: 2987
celo_rating: 1284.21
family_friendly_score: 0.4972
family_friendly_standard_error: 0.0070709569366529165
submission_type: basic
model_repo: BBChicago/tang82mv-dpo-ep3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6080734573724393, 'latency_mean': 1.64446484208107, 'latency_p50': 1.645024061203003, 'latency_p90': 1.7876240015029907}, {'batch_size': 3, 'throughput': 1.1124760190139191, 'latency_mean': 2.688703478574753, 'latency_p50': 2.688292980194092, 'latency_p90': 2.909965491294861}, {'batch_size': 5, 'throughput': 1.3334002358837862, 'latency_mean': 3.7341887021064757, 'latency_p50': 3.753862142562866, 'latency_p90': 4.080150699615478}, {'batch_size': 6, 'throughput': 1.40704153217958, 'latency_mean': 4.247304466962814, 'latency_p50': 4.287616014480591, 'latency_p90': 4.7343837976455685}, {'batch_size': 8, 'throughput': 1.4681017124664022, 'latency_mean': 5.4148732900619505, 'latency_p50': 5.3839415311813354, 'latency_p90': 6.068496513366699}, {'batch_size': 10, 'throughput': 1.5196131682958367, 'latency_mean': 6.5331070256233215, 'latency_p50': 6.477184176445007, 'latency_p90': 7.5060707330703735}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tang82mv-dpo-ep3
is_internal_developer: False
language_model: BBChicago/tang82mv-dpo-ep3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.33
us_pacific_date: 2025-04-29
win_ratio: 0.4902346955522731
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', '<', '>', '[INST]', '[\\INST]'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', '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 bbchicago-tang82mv-dpo-ep3-v1-mkmlizer
Waiting for job on bbchicago-tang82mv-dpo-ep3-v1-mkmlizer to finish
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║     _____            __           __                                ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║       /___/                                                         ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║                                                                     ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║                                                                     ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  belonging to:                                                      ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║                                                                     ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ║                                                                     ║
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: Downloaded to shared memory in 50.233s
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv8l9ipc6, device:0
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: quantized model in 35.628s
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: Processed model BBChicago/tang82mv-dpo-ep3 in 85.861s
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1/config.json
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1/special_tokens_map.json
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1/tokenizer_config.json
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1/tokenizer.json
bbchicago-tang82mv-dpo-ep3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-tang82mv-dpo-ep3-v1/flywheel_model.0.safetensors
Job bbchicago-tang82mv-dpo-ep3-v1-mkmlizer completed after 114.25s with status: succeeded
Stopping job with name bbchicago-tang82mv-dpo-ep3-v1-mkmlizer
Pipeline stage MKMLizer completed in 114.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service bbchicago-tang82mv-dpo-ep3-v1
Waiting for inference service bbchicago-tang82mv-dpo-ep3-v1 to be ready
Inference service bbchicago-tang82mv-dpo-ep3-v1 ready after 140.48203015327454s
Pipeline stage MKMLDeployer completed in 140.92s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4245216846466064s
Received healthy response to inference request in 1.6001627445220947s
Received healthy response to inference request in 1.5519368648529053s
Received healthy response to inference request in 1.8428840637207031s
Received healthy response to inference request in 1.0093824863433838s
5 requests
0 failed requests
5th percentile: 1.117893362045288
10th percentile: 1.2264042377471924
20th percentile: 1.443425989151001
30th percentile: 1.5615820407867431
40th percentile: 1.580872392654419
50th percentile: 1.6001627445220947
60th percentile: 1.697251272201538
70th percentile: 1.7943397998809814
80th percentile: 1.9592115879058838
90th percentile: 2.191866636276245
95th percentile: 2.308194160461426
99th percentile: 2.4012561798095704
mean time: 1.6857775688171386
Pipeline stage StressChecker completed in 10.08s
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 0.72s
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 0.65s
Shutdown handler de-registered
bbchicago-tang82mv-dpo-ep3_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 2710.40s
Shutdown handler de-registered
bbchicago-tang82mv-dpo-ep3_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-tang82mv-dpo-ep3_v1 status is now torndown due to DeploymentManager action