developer_uid: zonemercy
submission_id: chaiml-mistral31-24b-s_69496_v45
model_name: chaiml-mistral31-24b-s_69496_v45
model_group: ChaiML/mistral31-24b-sim
status: torndown
timestamp: 2025-10-06T05:01:32+00:00
num_battles: 5595
num_wins: 2745
celo_rating: 1281.11
family_friendly_score: 0.486
family_friendly_standard_error: 0.00706829540978587
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': 0.5709998994015751, 'latency_mean': 1.751194874048233, 'latency_p50': 1.7475440502166748, 'latency_p90': 1.9574816703796387}, {'batch_size': 3, 'throughput': 1.1943844943018804, 'latency_mean': 2.500675164461136, 'latency_p50': 2.509539484977722, 'latency_p90': 2.776189184188843}, {'batch_size': 5, 'throughput': 1.556951436684542, 'latency_mean': 3.191820421218872, 'latency_p50': 3.180591106414795, 'latency_p90': 3.587801218032837}, {'batch_size': 6, 'throughput': 1.6960228020167647, 'latency_mean': 3.506363346576691, 'latency_p50': 3.496796727180481, 'latency_p90': 4.0028208017349245}, {'batch_size': 8, 'throughput': 1.8961644510399722, 'latency_mean': 4.196727609634399, 'latency_p50': 4.182517647743225, 'latency_p90': 4.79485547542572}, {'batch_size': 10, 'throughput': 1.9798207821848455, 'latency_mean': 5.027265059947967, 'latency_p50': 5.056712031364441, 'latency_p90': 5.773900699615479}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mistral31-24b-s_69496_v45
is_internal_developer: True
language_model: ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e
model_size: 24B
ranking_group: single
throughput_3p7s: 1.77
us_pacific_date: 2025-10-05
win_ratio: 0.4906166219839142
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': ['\n', '<|im_end|>', '<|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-v45-mkmlizer
Waiting for job on chaiml-mistral31-24b-s-69496-v45-mkmlizer to finish
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Version: 0.30.2 ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ https://mk1.ai ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ belonging to: ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Chai Research Corp. ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ║ ║
chaiml-mistral31-24b-s-69496-v45-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-s-69496-v45-mkmlizer: Downloaded to shared memory in 47.134s
chaiml-mistral31-24b-s-69496-v45-mkmlizer: Checking if ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e already exists in ChaiML
chaiml-mistral31-24b-s-69496-v45-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmp9deneltq, device:0
chaiml-mistral31-24b-s-69496-v45-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-s-69496-v45-mkmlizer: quantized model in 286.323s
chaiml-mistral31-24b-s-69496-v45-mkmlizer: Processed model ChaiML/mistral31-24b-simpoexp1-s1-new-sft-retryv2top20lex-2e in 333.458s
chaiml-mistral31-24b-s-69496-v45-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-s-69496-v45-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-s-69496-v45-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/special_tokens_map.json
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/config.json
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/tokenizer_config.json
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/tokenizer.json
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/flywheel_model.1.safetensors
chaiml-mistral31-24b-s-69496-v45-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-s-69496-v45/nvidia/flywheel_model.0.safetensors
Job chaiml-mistral31-24b-s-69496-v45-mkmlizer completed after 468.32s with status: succeeded
Stopping job with name chaiml-mistral31-24b-s-69496-v45-mkmlizer
Pipeline stage MKMLizer completed in 468.81s
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-mistral31-24b-s-69496-v45
Waiting for inference service chaiml-mistral31-24b-s-69496-v45 to be ready
Inference service chaiml-mistral31-24b-s-69496-v45 ready after 30.147428512573242s
Pipeline stage MKMLDeployer completed in 31.85s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0871665477752686s
Received healthy response to inference request in 1.9177591800689697s
Received healthy response to inference request in 1.878650188446045s
Received healthy response to inference request in 2.505666732788086s
Received healthy response to inference request in 1.8248100280761719s
5 requests
0 failed requests
5th percentile: 1.8355780601501466
10th percentile: 1.846346092224121
20th percentile: 1.8678821563720702
30th percentile: 1.8864719867706299
40th percentile: 1.9021155834197998
50th percentile: 1.9177591800689697
60th percentile: 1.9855221271514893
70th percentile: 2.053285074234009
80th percentile: 2.170866584777832
90th percentile: 2.338266658782959
95th percentile: 2.4219666957855224
99th percentile: 2.4889267253875733
mean time: 2.0428105354309083
Pipeline stage StressChecker completed in 11.45s
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 0.62s
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-mistral31-24b-s_69496_v45 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 0.07s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mistral31-24b-s-69496-v45-profiler
Waiting for inference service chaiml-mistral31-24b-s-69496-v45-profiler to be ready
Inference service chaiml-mistral31-24b-s-69496-v45-profiler ready after 60.47505283355713s
Pipeline stage MKMLProfilerDeployer completed in 61.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/chaiml-mistral31-24b60bb73829909dc26c6f6d303a7e51a4a-deplopkrsf:/code/chaiverse_profiler_1759727564 --namespace tenant-chaiml-guanaco
kubectl --kubeconfig /code/guanaco/guanaco_services/resources/kchai_coreweave_us_east_04a.yaml exec -it chaiml-mistral31-24b60bb73829909dc26c6f6d303a7e51a4a-deplopkrsf --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1759727564 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 768 --output_tokens 64 --summary /code/chaiverse_profiler_1759727564/summary.json'
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 2363.26s
Shutdown handler de-registered
chaiml-mistral31-24b-s_69496_v45 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-s_69496_v45 status is now torndown due to DeploymentManager action