developer_uid: ChaiHarshitSheoran
submission_id: chaiml-mn24b-v2preferwi_76149_v2
model_name: chaiml-mn24b-v2preferwi_76149_v2
model_group: ChaiML/mn24b_v2preferwin
status: torndown
timestamp: 2025-09-19T22:54:08+00:00
num_battles: 5739
num_wins: 3134
celo_rating: 1285.47
family_friendly_score: 0.5698
family_friendly_standard_error: 0.007001827761377739
submission_type: basic
model_repo: ChaiML/mn24b_v2preferwin2_qwen_bo16_valfiltbef_tune4
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': 0.5548316652247633, 'latency_mean': 1.8022477519512177, 'latency_p50': 1.7824921607971191, 'latency_p90': 2.0058260440826414}, {'batch_size': 3, 'throughput': 1.1165635518827306, 'latency_mean': 2.6784988701343537, 'latency_p50': 2.6897201538085938, 'latency_p90': 2.9929256439208984}, {'batch_size': 5, 'throughput': 1.4418297887817626, 'latency_mean': 3.444855579137802, 'latency_p50': 3.4384552240371704, 'latency_p90': 3.865722107887268}, {'batch_size': 6, 'throughput': 1.5485733885103625, 'latency_mean': 3.857417894601822, 'latency_p50': 3.876498579978943, 'latency_p90': 4.359054279327393}, {'batch_size': 8, 'throughput': 1.708618657110893, 'latency_mean': 4.653946561813354, 'latency_p50': 4.604179382324219, 'latency_p90': 5.304329824447632}, {'batch_size': 10, 'throughput': 1.7735473493792893, 'latency_mean': 5.5951440250873565, 'latency_p50': 5.6987844705581665, 'latency_p90': 6.436064982414245}]
gpu_counts: {'NVIDIA L40S': 1}
display_name: chaiml-mn24b-v2preferwi_76149_v2
is_internal_developer: False
language_model: ChaiML/mn24b_v2preferwin2_qwen_bo16_valfiltbef_tune4
model_size: 24B
ranking_group: single
throughput_3p7s: 1.52
us_pacific_date: 2025-09-19
win_ratio: 0.5460881686705001
generation_params: {'temperature': 0.65, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{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-mn24b-v2preferwi-76149-v2-mkmlizer
Waiting for job on chaiml-mn24b-v2preferwi-76149-v2-mkmlizer to finish
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Version: 0.30.2                                                    ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  belonging to:                                                      ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ║                                                                     ║
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: Downloaded to shared memory in 54.927s
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: Checking if ChaiML/mn24b_v2preferwin2_qwen_bo16_valfiltbef_tune4 already exists in ChaiML
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:q4, folder:/tmp/tmphp05errn, device:0
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
Failed to get response for submission mistralai-mistral-nem_93303_v569: ('http://mistralai-mistral-nem-93303-v569-predictor.tenant-chaiml-guanaco.k2.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: quantized model in 288.791s
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: Processed model ChaiML/mn24b_v2preferwin2_qwen_bo16_valfiltbef_tune4 in 343.719s
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: creating bucket guanaco-mkml-models
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia/special_tokens_map.json
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia/config.json
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia/tokenizer_config.json
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia/flywheel_model.1.safetensors
chaiml-mn24b-v2preferwi-76149-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-mn24b-v2preferwi-76149-v2/nvidia/flywheel_model.0.safetensors
Job chaiml-mn24b-v2preferwi-76149-v2-mkmlizer completed after 430.88s with status: succeeded
Stopping job with name chaiml-mn24b-v2preferwi-76149-v2-mkmlizer
Pipeline stage MKMLizer completed in 431.40s
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-mn24b-v2preferwi-76149-v2
Waiting for inference service chaiml-mn24b-v2preferwi-76149-v2 to be ready
Failed to get response for submission rirv938-llama-0-9b-user_33111_v2: HTTPConnectionPool(host='rirv938-llama-0-9b-user-33111-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Max retries exceeded with url: /v1/models/GPT-J-6B-lit-v2:predict (Caused by ConnectTimeoutError(<urllib3.connection.HTTPConnection object at 0x7f5b8863a010>, 'Connection to rirv938-llama-0-9b-user-33111-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com timed out. (connect timeout=12.0)'))
Inference service chaiml-mn24b-v2preferwi-76149-v2 ready after 70.34268116950989s
Pipeline stage MKMLDeployer completed in 70.87s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0078115463256836s
Received healthy response to inference request in 1.8665707111358643s
Received healthy response to inference request in 2.1119306087493896s
Received healthy response to inference request in 1.7906897068023682s
Received healthy response to inference request in 2.0249269008636475s
5 requests
0 failed requests
5th percentile: 1.8058659076690673
10th percentile: 1.8210421085357666
20th percentile: 1.8513945102691651
30th percentile: 1.8948188781738282
40th percentile: 1.951315212249756
50th percentile: 2.0078115463256836
60th percentile: 2.0146576881408693
70th percentile: 2.0215038299560546
80th percentile: 2.042327642440796
90th percentile: 2.0771291255950928
95th percentile: 2.094529867172241
99th percentile: 2.10845046043396
mean time: 1.9603858947753907
Pipeline stage StressChecker completed in 11.40s
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 0.72s
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-mn24b-v2preferwi_76149_v2 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 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.08s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service chaiml-mn24b-v2preferwi-76149-v2-profiler
Waiting for inference service chaiml-mn24b-v2preferwi-76149-v2-profiler to be ready
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 2512.68s
Shutdown handler de-registered
chaiml-mn24b-v2preferwi_76149_v2 status is now inactive due to auto deactivation removed underperforming models
chaiml-mn24b-v2preferwi_76149_v2 status is now torndown due to DeploymentManager action