developer_uid: zonemercy
submission_id: chaiml-ir-v4-1-dpo-irv1_27949_v5
model_name: test
model_group: ChaiML/ir-v4-1-dpo_irv13
status: torndown
timestamp: 2025-11-03T02:01:33+00:00
num_battles: 5921
num_wins: 3102
celo_rating: 1306.21
family_friendly_score: 0.4736
family_friendly_standard_error: 0.007061204429840564
submission_type: basic
model_repo: ChaiML/ir-v4-1-dpo_irv13-lr5e6b01
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 2048
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.47237759020842546, 'latency_mean': 2.1168468475341795, 'latency_p50': 2.1017274856567383, 'latency_p90': 2.315536546707153}, {'batch_size': 2, 'throughput': 0.6792147159582651, 'latency_mean': 2.9381996381282804, 'latency_p50': 2.9522875547409058, 'latency_p90': 3.160139632225037}, {'batch_size': 3, 'throughput': 0.8268423659119084, 'latency_mean': 3.6134419620037077, 'latency_p50': 3.6000925302505493, 'latency_p90': 4.108573317527771}, {'batch_size': 4, 'throughput': 0.9144229837759851, 'latency_mean': 4.360030455589294, 'latency_p50': 4.3697768449783325, 'latency_p90': 4.886740016937256}, {'batch_size': 5, 'throughput': 0.9853694819693474, 'latency_mean': 5.05808438539505, 'latency_p50': 5.041763544082642, 'latency_p90': 5.866796159744263}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: test
is_internal_developer: True
language_model: ChaiML/ir-v4-1-dpo_irv13-lr5e6b01
model_size: 24B
ranking_group: single
throughput_3p7s: 0.84
us_pacific_date: 2025-10-30
win_ratio: 0.5238979902043573
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['User:', 'You:', '</s>'], 'max_input_tokens': 2048, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s persona: {memory}", 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': 'You: {message}\n', 'response_template': '####\n{bot_name}:', 'truncate_by_message': True}
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-ir-v4-1-dpo-irv1-27949-v5-mkmlizer
Waiting for job on chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer to finish
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  belonging to:                                                      ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ║                                                                     ║
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: Downloaded to shared memory in 50.709s
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: Checking if ChaiML/ir-v4-1-dpo_irv13-lr5e6b01 already exists in ChaiML
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmpucckzkgo, device:0
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: quantized model in 294.204s
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: Processed model ChaiML/ir-v4-1-dpo_irv13-lr5e6b01 in 344.914s
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: creating bucket guanaco-mkml-models
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/config.json
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/special_tokens_map.json
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/tokenizer_config.json
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/tokenizer.json
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/flywheel_model.1.safetensors
chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-ir-v4-1-dpo-irv1-27949-v5/nvidia/flywheel_model.0.safetensors
Job chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer completed after 390.12s with status: succeeded
Stopping job with name chaiml-ir-v4-1-dpo-irv1-27949-v5-mkmlizer
Pipeline stage MKMLizer completed in 390.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-ir-v4-1-dpo-irv1-27949-v5
Waiting for inference service chaiml-ir-v4-1-dpo-irv1-27949-v5 to be ready
Inference service chaiml-ir-v4-1-dpo-irv1-27949-v5 ready after 131.4045307636261s
Pipeline stage MKMLDeployer completed in 132.00s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.226752281188965s
Received healthy response to inference request in 2.326110363006592s
Received healthy response to inference request in 1.7945635318756104s
Received healthy response to inference request in 1.6512863636016846s
Received healthy response to inference request in 1.8807697296142578s
5 requests
0 failed requests
5th percentile: 1.6799417972564696
10th percentile: 1.708597230911255
20th percentile: 1.7659080982208253
30th percentile: 1.8118047714233398
40th percentile: 1.8462872505187988
50th percentile: 1.8807697296142578
60th percentile: 2.0191627502441407
70th percentile: 2.157555770874023
80th percentile: 2.24662389755249
90th percentile: 2.286367130279541
95th percentile: 2.3062387466430665
99th percentile: 2.322136039733887
mean time: 1.975896453857422
Pipeline stage StressChecker completed in 11.49s
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 0.67s
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 0.72s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv1_27949_v5 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 2907.30s
Shutdown handler de-registered
chaiml-ir-v4-1-dpo-irv1_27949_v5 status is now inactive due to auto deactivation removed underperforming models
chaiml-ir-v4-1-dpo-irv1_27949_v5 status is now torndown due to DeploymentManager action