developer_uid: BBChicago
submission_id: bbchicago-tang82mv-flpc_27672_v1
model_name: tang82mv-flpchatai-591k-dpo-ep1
model_group: BBChicago/tang82mv-flpch
status: torndown
timestamp: 2025-05-12T03:20:34+00:00
num_battles: 8852
num_wins: 4436
celo_rating: 1287.4
family_friendly_score: 0.5402
family_friendly_standard_error: 0.0070481765017627075
submission_type: basic
model_repo: BBChicago/tang82mv-flpchatai-591k-dpo-ep1
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.6068546137486523, 'latency_mean': 1.6477827441692352, 'latency_p50': 1.6479640007019043, 'latency_p90': 1.8089656591415406}, {'batch_size': 3, 'throughput': 1.1173429828185057, 'latency_mean': 2.673573701381683, 'latency_p50': 2.6672959327697754, 'latency_p90': 2.9479082107543944}, {'batch_size': 5, 'throughput': 1.3604171590381686, 'latency_mean': 3.653688939809799, 'latency_p50': 3.6595876216888428, 'latency_p90': 4.156456446647644}, {'batch_size': 6, 'throughput': 1.4223812919019512, 'latency_mean': 4.188548406362534, 'latency_p50': 4.171956181526184, 'latency_p90': 4.645461940765381}, {'batch_size': 8, 'throughput': 1.4829123270067641, 'latency_mean': 5.351911736726761, 'latency_p50': 5.399008274078369, 'latency_p90': 5.943493461608886}, {'batch_size': 10, 'throughput': 1.517515399078021, 'latency_mean': 6.538589595556259, 'latency_p50': 6.497731328010559, 'latency_p90': 7.40040922164917}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: tang82mv-flpchatai-591k-dpo-ep1
is_internal_developer: False
language_model: BBChicago/tang82mv-flpchatai-591k-dpo-ep1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.37
us_pacific_date: 2025-05-11
win_ratio: 0.5011296882060551
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-flpc-27672-v1-mkmlizer
Waiting for job on bbchicago-tang82mv-flpc-27672-v1-mkmlizer to finish
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ _____ __ __ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ /___/ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ Version: 0.12.8 ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ https://mk1.ai ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ The license key for the current software has been verified as ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ belonging to: ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ Chai Research Corp. ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ║ ║
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: Downloaded to shared memory in 40.798s
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv4dv0e4l, device:0
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: quantized model in 35.892s
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: Processed model BBChicago/tang82mv-flpchatai-591k-dpo-ep1 in 76.690s
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: creating bucket guanaco-mkml-models
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1/config.json
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1/special_tokens_map.json
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1/tokenizer_config.json
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1/tokenizer.json
bbchicago-tang82mv-flpc-27672-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/bbchicago-tang82mv-flpc-27672-v1/flywheel_model.0.safetensors
Job bbchicago-tang82mv-flpc-27672-v1-mkmlizer completed after 103.91s with status: succeeded
Stopping job with name bbchicago-tang82mv-flpc-27672-v1-mkmlizer
Pipeline stage MKMLizer completed in 104.41s
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-flpc-27672-v1
Waiting for inference service bbchicago-tang82mv-flpc-27672-v1 to be ready
Failed to get response for submission blend_ruhas_2025-04-28: HTTPConnectionPool(host='blend-ropob-2025-04-04-predictor.tenant-chaiml-guanaco.k2.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service bbchicago-tang82mv-flpc-27672-v1 ready after 120.59880924224854s
Pipeline stage MKMLDeployer completed in 121.03s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.272970199584961s
Received healthy response to inference request in 1.5122489929199219s
Received healthy response to inference request in 1.5755233764648438s
Received healthy response to inference request in 1.8835153579711914s
Received healthy response to inference request in 1.699113368988037s
5 requests
0 failed requests
5th percentile: 1.5249038696289063
10th percentile: 1.5375587463378906
20th percentile: 1.5628684997558593
30th percentile: 1.6002413749694824
40th percentile: 1.6496773719787599
50th percentile: 1.699113368988037
60th percentile: 1.7728741645812989
70th percentile: 1.8466349601745604
80th percentile: 1.9614063262939454
90th percentile: 2.117188262939453
95th percentile: 2.195079231262207
99th percentile: 2.2573920059204102
mean time: 1.788674259185791
Pipeline stage StressChecker completed in 10.20s
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 0.75s
Shutdown handler de-registered
bbchicago-tang82mv-flpc_27672_v1 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service bbchicago-tang82mv-flpc-27672-v1-profiler
Waiting for inference service bbchicago-tang82mv-flpc-27672-v1-profiler to be ready
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 2737.44s
Shutdown handler de-registered
bbchicago-tang82mv-flpc_27672_v1 status is now inactive due to auto deactivation removed underperforming models
bbchicago-tang82mv-flpc_27672_v1 status is now torndown due to DeploymentManager action