developer_uid: rirv938
submission_id: chaiml-mistral31-24b-s_69496_v18
model_name: chaiml-mistral31-24b-s_69496_v18
model_group: ChaiML/mistral31-24b-sim
status: torndown
timestamp: 2025-07-08T15:29:50+00:00
num_battles: 9984
num_wins: 4979
celo_rating: 1296.91
family_friendly_score: 0.5127999999999999
family_friendly_standard_error: 0.007068750384615374
submission_type: basic
model_repo: ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e
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': 0.5415385839930704, 'latency_mean': 1.8464696276187897, 'latency_p50': 1.838247537612915, 'latency_p90': 2.0626537084579466}, {'batch_size': 3, 'throughput': 1.1348713416097014, 'latency_mean': 2.634616878032684, 'latency_p50': 2.627373695373535, 'latency_p90': 2.905923938751221}, {'batch_size': 5, 'throughput': 1.470443780407193, 'latency_mean': 3.3847634398937227, 'latency_p50': 3.3952897787094116, 'latency_p90': 3.7179580688476563}, {'batch_size': 6, 'throughput': 1.611946964877839, 'latency_mean': 3.6933257710933685, 'latency_p50': 3.699577212333679, 'latency_p90': 4.1574866771698}, {'batch_size': 8, 'throughput': 1.7769888229276325, 'latency_mean': 4.479634644985199, 'latency_p50': 4.499890089035034, 'latency_p90': 5.080727124214173}, {'batch_size': 10, 'throughput': 1.8825482063479484, 'latency_mean': 5.267234356403351, 'latency_p50': 5.251821994781494, 'latency_p90': 5.973697137832642}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral31-24b-s_69496_v18
is_internal_developer: True
language_model: ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e
model_size: 24B
ranking_group: single
throughput_3p7s: 1.63
us_pacific_date: 2025-07-08
win_ratio: 0.4986979166666667
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_end|>', '\n', '<|im_start|>'], '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-s-69496-v18-mkmlizer
Waiting for job on chaiml-mistral31-24b-s-69496-v18-mkmlizer to finish
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-s-69496-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-s-69496-v18-mkmlizer: Downloaded to shared memory in 104.941s
chaiml-mistral31-24b-s-69496-v18-mkmlizer: Checking if ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e already exists in ChaiML
chaiml-mistral31-24b-s-69496-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp9zilow1c, device:0
chaiml-mistral31-24b-s-69496-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-s-69496-v18-mkmlizer: quantized model in 48.147s
chaiml-mistral31-24b-s-69496-v18-mkmlizer: Processed model ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e in 153.089s
chaiml-mistral31-24b-s-69496-v18-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-s-69496-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-s-69496-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/config.json
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/special_tokens_map.json
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/tokenizer_config.json
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/tokenizer.json
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/flywheel_model.1.safetensors
chaiml-mistral31-24b-s-69496-v18-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v18/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral31-24b-s-69496-v18-mkmlizer completed after 188.86s with status: succeeded
Stopping job with name chaiml-mistral31-24b-s-69496-v18-mkmlizer
Pipeline stage MKMLizer completed in 189.48s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-24b-s-69496-v18
Waiting for inference service chaiml-mistral31-24b-s-69496-v18 to be ready
Inference service chaiml-mistral31-24b-s-69496-v18 ready after 201.27474665641785s
Pipeline stage MKMLDeployer completed in 201.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6699278354644775s
Received healthy response to inference request in 3.1844749450683594s
Received healthy response to inference request in 2.276235342025757s
Received healthy response to inference request in 2.165658473968506s
Received healthy response to inference request in 1.980879545211792s
5 requests
0 failed requests
5th percentile: 2.017835330963135
10th percentile: 2.0547911167144775
20th percentile: 2.128702688217163
30th percentile: 2.187773847579956
40th percentile: 2.2320045948028566
50th percentile: 2.276235342025757
60th percentile: 2.433712339401245
70th percentile: 2.591189336776733
80th percentile: 2.772837257385254
90th percentile: 2.9786561012268065
95th percentile: 3.081565523147583
99th percentile: 3.163893060684204
mean time: 2.4554352283477785
Pipeline stage StressChecker completed in 13.61s
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 0.71s
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-s_69496_v18 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 3330.89s
Shutdown handler de-registered
chaiml-mistral31-24b-s_69496_v18 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-s_69496_v18 status is now torndown due to DeploymentManager action