developer_uid: NischayDnk
submission_id: chaiml-mistral31-cpos1-e_9084_v3
model_name: chaiml-mistral31-cpos1-e_9084_v3
model_group: ChaiML/mistral31-cpos1-e
status: torndown
timestamp: 2025-06-24T17:46:08+00:00
num_battles: 8755
num_wins: 4603
celo_rating: 1313.03
family_friendly_score: 0.4476
family_friendly_standard_error: 0.007032129691636808
submission_type: basic
model_repo: ChaiML/mistral31-cpos1-exp1-sft1306-6kpref-1024-lowlr
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 4
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.45564729936080983, 'latency_mean': 2.1945833313465117, 'latency_p50': 2.1903700828552246, 'latency_p90': 2.39912428855896}, {'batch_size': 3, 'throughput': 0.864477323133919, 'latency_mean': 3.461233088970184, 'latency_p50': 3.4443068504333496, 'latency_p90': 3.7220271110534666}, {'batch_size': 5, 'throughput': 1.0795417329509434, 'latency_mean': 4.616803939342499, 'latency_p50': 4.588110685348511, 'latency_p90': 5.272599077224731}, {'batch_size': 6, 'throughput': 1.1516917632381334, 'latency_mean': 5.181302274465561, 'latency_p50': 5.2107216119766235, 'latency_p90': 5.823297429084778}, {'batch_size': 10, 'throughput': 1.3001017379862052, 'latency_mean': 7.637263259887695, 'latency_p50': 7.64477014541626, 'latency_p90': 8.746834468841552}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: chaiml-mistral31-cpos1-e_9084_v3
is_internal_developer: False
language_model: ChaiML/mistral31-cpos1-exp1-sft1306-6kpref-1024-lowlr
model_size: 24B
ranking_group: single
throughput_3p7s: 0.92
us_pacific_date: 2025-06-24
win_ratio: 0.5257567104511708
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': 2048, 'best_of': 4, '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-cpos1-e-9084-v3-mkmlizer
Waiting for job on chaiml-mistral31-cpos1-e-9084-v3-mkmlizer to finish
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Version: 0.29.3                                                    ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ║                                                                     ║
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: Downloaded to shared memory in 118.987s
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: Checking if ChaiML/mistral31-cpos1-exp1-sft1306-6kpref-1024-lowlr already exists in ChaiML
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpk7azrl3k, device:0
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: quantized model in 49.111s
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: Processed model ChaiML/mistral31-cpos1-exp1-sft1306-6kpref-1024-lowlr in 168.099s
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3/config.json
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3/special_tokens_map.json
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3/tokenizer_config.json
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3/flywheel_model.1.safetensors
chaiml-mistral31-cpos1-e-9084-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mistral31-cpos1-e-9084-v3/flywheel_model.0.safetensors
Job chaiml-mistral31-cpos1-e-9084-v3-mkmlizer completed after 198.95s with status: succeeded
Stopping job with name chaiml-mistral31-cpos1-e-9084-v3-mkmlizer
Pipeline stage MKMLizer completed in 199.67s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-mistral31-cpos1-e-9084-v3
Waiting for inference service chaiml-mistral31-cpos1-e-9084-v3 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service chaiml-mistral31-cpos1-e-9084-v3 ready after 130.5038571357727s
Pipeline stage MKMLDeployer completed in 131.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.725031852722168s
Received healthy response to inference request in 1.905289649963379s
Received healthy response to inference request in 1.8368492126464844s
Received healthy response to inference request in 1.8042781352996826s
Received healthy response to inference request in 1.7396628856658936s
5 requests
0 failed requests
5th percentile: 1.7525859355926514
10th percentile: 1.7655089855194093
20th percentile: 1.7913550853729248
30th percentile: 1.8107923507690429
40th percentile: 1.8238207817077636
50th percentile: 1.8368492126464844
60th percentile: 1.8642253875732422
70th percentile: 1.8916015625
80th percentile: 2.069238090515137
90th percentile: 2.3971349716186525
95th percentile: 2.56108341217041
99th percentile: 2.6922421646118164
mean time: 2.0022223472595213
Pipeline stage StressChecker completed in 11.29s
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 0.92s
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 0.68s
Shutdown handler de-registered
chaiml-mistral31-cpos1-e_9084_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 4894.93s
Shutdown handler de-registered
chaiml-mistral31-cpos1-e_9084_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-mistral31-cpos1-e_9084_v3 status is now torndown due to DeploymentManager action