developer_uid: NischayDnk
submission_id: deepseek-ai-deepseek-r1_28051_v8
model_name: deepseek-ai-deepseek-r1_28051_v8
model_group: deepseek-ai/DeepSeek-R1-
status: torndown
timestamp: 2025-05-16T16:42:11+00:00
num_battles: 12322
num_wins: 5419
celo_rating: 1242.6
family_friendly_score: 0.6508
family_friendly_standard_error: 0.006741800353021439
submission_type: basic
model_repo: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
model_architecture: Qwen2ForCausalLM
model_num_parameters: 14769689600.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.46578038445056275, 'latency_mean': 2.1468610632419587, 'latency_p50': 2.160458564758301, 'latency_p90': 2.3683591365814207}, {'batch_size': 3, 'throughput': 0.8640776427213077, 'latency_mean': 3.465353630781174, 'latency_p50': 3.469200015068054, 'latency_p90': 3.7659432888031006}, {'batch_size': 5, 'throughput': 1.0648071833236106, 'latency_mean': 4.675830492973327, 'latency_p50': 4.669639945030212, 'latency_p90': 5.3231768131256105}, {'batch_size': 6, 'throughput': 1.1143653188301734, 'latency_mean': 5.343588485717773, 'latency_p50': 5.318568110466003, 'latency_p90': 6.014267778396606}, {'batch_size': 10, 'throughput': 1.1997113601851226, 'latency_mean': 8.273019086122513, 'latency_p50': 8.340372204780579, 'latency_p90': 9.292841982841491}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: deepseek-ai-deepseek-r1_28051_v8
is_internal_developer: False
language_model: deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
model_size: 15B
ranking_group: single
throughput_3p7s: 0.92
us_pacific_date: 2025-05-16
win_ratio: 0.43978250284044795
generation_params: {'temperature': 0.85, 'top_p': 0.94, 'min_p': 0.02, 'top_k': 40, 'presence_penalty': 0.1, 'frequency_penalty': 0.1, 'stopping_words': ['\n', '<|im_end|>'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|system|>Family Friendly{memory}\n', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 deepseek-ai-deepseek-r1-28051-v8-mkmlizer
Waiting for job on deepseek-ai-deepseek-r1-28051-v8-mkmlizer to finish
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║     _____            __           __                                ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║       /___/                                                         ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║                                                                     ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  Version: 0.12.8                                                    ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  https://mk1.ai                                                     ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║                                                                     ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  The license key for the current software has been verified as      ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  belonging to:                                                      ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║                                                                     ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  Chai Research Corp.                                                ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ║                                                                     ║
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: Downloaded to shared memory in 30.596s
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp459wsn76, device:0
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: Saving flywheel model at /dev/shm/model_cache
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: quantized model in 36.459s
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: Processed model deepseek-ai/DeepSeek-R1-Distill-Qwen-14B in 67.056s
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: creating bucket guanaco-mkml-models
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/config.json
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/special_tokens_map.json
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/tokenizer_config.json
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/tokenizer.json
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/flywheel_model.1.safetensors
deepseek-ai-deepseek-r1-28051-v8-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/deepseek-ai-deepseek-r1-28051-v8/flywheel_model.0.safetensors
Job deepseek-ai-deepseek-r1-28051-v8-mkmlizer completed after 94.25s with status: succeeded
Stopping job with name deepseek-ai-deepseek-r1-28051-v8-mkmlizer
Pipeline stage MKMLizer completed in 94.77s
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 deepseek-ai-deepseek-r1-28051-v8
Waiting for inference service deepseek-ai-deepseek-r1-28051-v8 to be ready
Inference service deepseek-ai-deepseek-r1-28051-v8 ready after 140.6136486530304s
Pipeline stage MKMLDeployer completed in 141.20s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.519965887069702s
Received healthy response to inference request in 2.526017665863037s
Received healthy response to inference request in 1.9404776096343994s
Received healthy response to inference request in 2.056901454925537s
Received healthy response to inference request in 2.0473783016204834s
5 requests
0 failed requests
5th percentile: 1.9618577480316162
10th percentile: 1.983237886428833
20th percentile: 2.0259981632232664
30th percentile: 2.049282932281494
40th percentile: 2.053092193603516
50th percentile: 2.056901454925537
60th percentile: 2.242127227783203
70th percentile: 2.4273530006408692
80th percentile: 2.521176242828369
90th percentile: 2.5235969543457033
95th percentile: 2.52480731010437
99th percentile: 2.5257755947113036
mean time: 2.218148183822632
Pipeline stage StressChecker completed in 12.50s
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 0.74s
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 0.67s
Shutdown handler de-registered
deepseek-ai-deepseek-r1_28051_v8 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 3944.06s
Shutdown handler de-registered
deepseek-ai-deepseek-r1_28051_v8 status is now inactive due to auto deactivation removed underperforming models
deepseek-ai-deepseek-r1_28051_v8 status is now torndown due to DeploymentManager action