developer_uid: NischayDnk
submission_id: chaiml-mistral31-ff4kex_21721_v3
model_name: chaiml-mistral31-ff4kex_21721_v3
model_group: ChaiML/mistral31-ff4kexp
status: torndown
timestamp: 2025-04-11T20:22:06+00:00
num_battles: 5902
num_wins: 3348
celo_rating: 1315.27
family_friendly_score: 0.5024
family_friendly_standard_error: 0.007070986352695075
submission_type: basic
model_repo: ChaiML/mistral31-ff4kexp1-simpo-v1-data31prefpubv1
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.3707136266745696, 'latency_mean': 2.6974000799655915, 'latency_p50': 2.6997835636138916, 'latency_p90': 2.993265080451965}, {'batch_size': 2, 'throughput': 0.5749827207527719, 'latency_mean': 3.4681171584129333, 'latency_p50': 3.4739264249801636, 'latency_p90': 3.8379795789718627}, {'batch_size': 3, 'throughput': 0.7289020602947199, 'latency_mean': 4.102143545150756, 'latency_p50': 4.103667140007019, 'latency_p90': 4.4898048639297485}, {'batch_size': 4, 'throughput': 0.8504268509462286, 'latency_mean': 4.681440197229385, 'latency_p50': 4.687289237976074, 'latency_p90': 5.1800330638885494}, {'batch_size': 5, 'throughput': 0.9399108252415674, 'latency_mean': 5.283356003761291, 'latency_p50': 5.276484251022339, 'latency_p90': 5.894684910774231}]
gpu_counts: {'NVIDIA RTX A6000': 1}
display_name: chaiml-mistral31-ff4kex_21721_v3
is_internal_developer: False
language_model: ChaiML/mistral31-ff4kexp1-simpo-v1-data31prefpubv1
model_size: 24B
ranking_group: single
throughput_3p7s: 0.64
us_pacific_date: 2025-04-11
win_ratio: 0.5672653337851575
generation_params: {'temperature': 0.4, 'top_p': 0.95, 'min_p': 0.025, 'top_k': 40, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['\n', '<|im_start|>', '<|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 chaiml-mistral31-ff4kex-21721-v3-mkmlizer
Waiting for job on chaiml-mistral31-ff4kex-21721-v3-mkmlizer to finish
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║  Expiration: 2025-04-15 23:59:59                                    ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: Downloaded to shared memory in 60.006s
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpsag_bzn4, device:0
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: quantized model in 53.615s
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: Processed model ChaiML/mistral31-ff4kexp1-simpo-v1-data31prefpubv1 in 113.621s
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/config.json
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/special_tokens_map.json
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/tokenizer_config.json
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/tokenizer.json
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/flywheel_model.1.safetensors
chaiml-mistral31-ff4kex-21721-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-ff4kex-21721-v3/flywheel_model.0.safetensors
Job chaiml-mistral31-ff4kex-21721-v3-mkmlizer completed after 146.91s with status: succeeded
Stopping job with name chaiml-mistral31-ff4kex-21721-v3-mkmlizer
Pipeline stage MKMLizer completed in 147.38s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-ff4kex-21721-v3
Waiting for inference service chaiml-mistral31-ff4kex-21721-v3 to be ready
Inference service chaiml-mistral31-ff4kex-21721-v3 ready after 110.41776299476624s
Pipeline stage MKMLDeployer completed in 110.80s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.148607015609741s
Received healthy response to inference request in 2.910007953643799s
Received healthy response to inference request in 2.7452733516693115s
Received healthy response to inference request in 2.6431243419647217s
Received healthy response to inference request in 2.639247179031372s
5 requests
0 failed requests
5th percentile: 2.640022611618042
10th percentile: 2.640798044204712
20th percentile: 2.6423489093780517
30th percentile: 2.66355414390564
40th percentile: 2.7044137477874757
50th percentile: 2.7452733516693115
60th percentile: 2.8111671924591066
70th percentile: 2.8770610332489013
80th percentile: 2.9577277660369874
90th percentile: 3.053167390823364
95th percentile: 3.1008872032165526
99th percentile: 3.1390630531311037
mean time: 2.817251968383789
Pipeline stage StressChecker completed in 15.34s
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 0.61s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_21721_v3 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 0.09s
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 chaiml-mistral31-ff4kex-21721-v3-profiler
Waiting for inference service chaiml-mistral31-ff4kex-21721-v3-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 2969.68s
Shutdown handler de-registered
chaiml-mistral31-ff4kex_21721_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-ff4kex_21721_v3 status is now torndown due to DeploymentManager action