developer_uid: NischayDnk
submission_id: chaiml-mistral31-24b-sf_86012_v2
model_name: chaiml-mistral31-24b-sf_86012_v2
model_group: ChaiML/mistral31-24b-sft
status: torndown
timestamp: 2025-05-07T07:55:28+00:00
num_battles: 7515
num_wins: 3705
celo_rating: 1281.88
family_friendly_score: 0.5833999999999999
family_friendly_standard_error: 0.006972007458401059
submission_type: basic
model_repo: ChaiML/mistral31-24b-sftmorelora-retryv1full-fullnomask
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': 0.5339336814798779, 'latency_mean': 1.872831835746765, 'latency_p50': 1.8639639616012573, 'latency_p90': 2.086688780784607}, {'batch_size': 3, 'throughput': 1.101401482616594, 'latency_mean': 2.7166931319236753, 'latency_p50': 2.713261127471924, 'latency_p90': 3.0587942361831666}, {'batch_size': 5, 'throughput': 1.4032387963752198, 'latency_mean': 3.5480035197734834, 'latency_p50': 3.527842164039612, 'latency_p90': 3.987359809875488}, {'batch_size': 6, 'throughput': 1.5318822464792312, 'latency_mean': 3.8873071134090424, 'latency_p50': 3.8880876302719116, 'latency_p90': 4.393873405456543}, {'batch_size': 8, 'throughput': 1.6447714172152166, 'latency_mean': 4.837806169986725, 'latency_p50': 4.821183443069458, 'latency_p90': 5.402816033363342}, {'batch_size': 10, 'throughput': 1.7516988848567654, 'latency_mean': 5.668888028860092, 'latency_p50': 5.687739849090576, 'latency_p90': 6.359915471076965}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral31-24b-sf_86012_v2
is_internal_developer: False
language_model: ChaiML/mistral31-24b-sftmorelora-retryv1full-fullnomask
model_size: 24B
ranking_group: single
throughput_3p7s: 1.47
us_pacific_date: 2025-05-07
win_ratio: 0.4930139720558882
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|>', '<|im_start|>', '\n'], '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-mistral31-24b-sf-86012-v2-mkmlizer
Waiting for job on chaiml-mistral31-24b-sf-86012-v2-mkmlizer to finish
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║     _____            __           __                                ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║       /___/                                                         ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ║                                                                     ║
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: Downloaded to shared memory in 82.221s
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpivr2zb6g, device:0
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: quantized model in 52.931s
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: Processed model ChaiML/mistral31-24b-sftmorelora-retryv1full-fullnomask in 135.153s
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/config.json
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/special_tokens_map.json
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/tokenizer_config.json
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/tokenizer.json
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/flywheel_model.1.safetensors
chaiml-mistral31-24b-sf-86012-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-24b-sf-86012-v2/flywheel_model.0.safetensors
Job chaiml-mistral31-24b-sf-86012-v2-mkmlizer completed after 165.92s with status: succeeded
Stopping job with name chaiml-mistral31-24b-sf-86012-v2-mkmlizer
Pipeline stage MKMLizer completed in 166.41s
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-sf-86012-v2
Waiting for inference service chaiml-mistral31-24b-sf-86012-v2 to be ready
Inference service chaiml-mistral31-24b-sf-86012-v2 ready after 150.57422494888306s
Pipeline stage MKMLDeployer completed in 151.15s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5713346004486084s
Received healthy response to inference request in 2.2296292781829834s
Received healthy response to inference request in 2.0447535514831543s
Received healthy response to inference request in 2.2938222885131836s
Received healthy response to inference request in 2.128394603729248s
5 requests
0 failed requests
5th percentile: 2.061481761932373
10th percentile: 2.078209972381592
20th percentile: 2.1116663932800295
30th percentile: 2.1486415386199953
40th percentile: 2.1891354084014893
50th percentile: 2.2296292781829834
60th percentile: 2.2553064823150635
70th percentile: 2.2809836864471436
80th percentile: 2.349324750900269
90th percentile: 2.4603296756744384
95th percentile: 2.515832138061523
99th percentile: 2.5602341079711914
mean time: 2.2535868644714356
Pipeline stage StressChecker completed in 12.62s
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 0.69s
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 0.84s
Shutdown handler de-registered
chaiml-mistral31-24b-sf_86012_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 2857.19s
Shutdown handler de-registered
chaiml-mistral31-24b-sf_86012_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-24b-sf_86012_v2 status is now torndown due to DeploymentManager action