developer_uid: NischayDnk
submission_id: chaiml-mistral31-24b-dp_19604_v2
model_name: chaiml-mistral31-24b-dp_19604_v2
model_group: ChaiML/mistral31-24b-dpo
status: torndown
timestamp: 2025-05-11T19:32:49+00:00
num_battles: 21281
num_wins: 11545
celo_rating: 1314.79
family_friendly_score: 0.5287999999999999
family_friendly_standard_error: 0.007059328013345179
submission_type: basic
model_repo: ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-1
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.563489772139049, 'latency_mean': 1.7745956766605377, 'latency_p50': 1.7660586833953857, 'latency_p90': 1.98231201171875}, {'batch_size': 3, 'throughput': 1.1852149751089691, 'latency_mean': 2.5175482487678527, 'latency_p50': 2.4820003509521484, 'latency_p90': 2.775683307647705}, {'batch_size': 5, 'throughput': 1.5410781148155597, 'latency_mean': 3.2162610197067263, 'latency_p50': 3.2314035892486572, 'latency_p90': 3.546865940093994}, {'batch_size': 6, 'throughput': 1.679139935921074, 'latency_mean': 3.5458313381671904, 'latency_p50': 3.541421413421631, 'latency_p90': 3.9781904458999633}, {'batch_size': 8, 'throughput': 1.8689446074786842, 'latency_mean': 4.232041094303131, 'latency_p50': 4.213136315345764, 'latency_p90': 4.741670155525208}, {'batch_size': 10, 'throughput': 1.9733984282404409, 'latency_mean': 5.014989577531814, 'latency_p50': 5.059955358505249, 'latency_p90': 5.634912443161011}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral31-24b-dp_19604_v2
is_internal_developer: False
language_model: ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-1
model_size: 24B
ranking_group: single
throughput_3p7s: 1.74
us_pacific_date: 2025-05-11
win_ratio: 0.5425027019406983
generation_params: {'temperature': 0.45, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 60, 'presence_penalty': 0.4, 'frequency_penalty': 0.4, 'stopping_words': ['<|im_start|>', '<|im_end|>', '\n'], 'max_input_tokens': 768, '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 chaiml-mistral31-24b-dp-19604-v2-mkmlizer
Waiting for job on chaiml-mistral31-24b-dp-19604-v2-mkmlizer to finish
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: Downloaded to shared memory in 60.640s
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp8t6b6bj3, device:0
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: quantized model in 54.236s
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: Processed model ChaiML/mistral31-24b-dpoexp1-s1-new-sft-retryv2top20lex-1 in 114.876s
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/config.json
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/special_tokens_map.json
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/tokenizer_config.json
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/tokenizer.json
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/flywheel_model.1.safetensors
chaiml-mistral31-24b-dp-19604-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-dp-19604-v2/flywheel_model.0.safetensors
Job chaiml-mistral31-24b-dp-19604-v2-mkmlizer completed after 145.63s with status: succeeded
Stopping job with name chaiml-mistral31-24b-dp-19604-v2-mkmlizer
Pipeline stage MKMLizer completed in 146.11s
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 chaiml-mistral31-24b-dp-19604-v2
Waiting for inference service chaiml-mistral31-24b-dp-19604-v2 to be ready
Inference service chaiml-mistral31-24b-dp-19604-v2 ready after 110.43278574943542s
Pipeline stage MKMLDeployer completed in 110.94s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.717931032180786s
Received healthy response to inference request in 1.8900928497314453s
Received healthy response to inference request in 1.965130090713501s
Received healthy response to inference request in 2.0159385204315186s
Received healthy response to inference request in 1.9597370624542236s
5 requests
0 failed requests
5th percentile: 1.904021692276001
10th percentile: 1.9179505348205566
20th percentile: 1.945808219909668
30th percentile: 1.960815668106079
40th percentile: 1.96297287940979
50th percentile: 1.965130090713501
60th percentile: 1.985453462600708
70th percentile: 2.005776834487915
80th percentile: 2.156337022781372
90th percentile: 2.437134027481079
95th percentile: 2.5775325298309326
99th percentile: 2.6898513317108153
mean time: 2.109765911102295
Pipeline stage StressChecker completed in 11.72s
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 0.81s
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 0.71s
Shutdown handler de-registered
chaiml-mistral31-24b-dp_19604_v2 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 2827.97s
Shutdown handler de-registered
chaiml-mistral31-24b-dp_19604_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-dp_19604_v2 status is now torndown due to DeploymentManager action