developer_uid: rirv938
submission_id: chaiml-20250411-rob-ava-_6550_v3
model_name: chaiml-20250411-rob-ava-_6550_v3
model_group: ChaiML/20250411_rob_ava_
status: torndown
timestamp: 2025-05-30T08:05:22+00:00
num_battles: 5820
num_wins: 3054
celo_rating: 1306.4
family_friendly_score: 0.5218
family_friendly_standard_error: 0.007064343706247595
submission_type: basic
model_repo: ChaiML/20250411_rob_ava_reward_300k_safety_threshold_1_2
model_architecture: LlamaForSequenceClassification
model_num_parameters: 8030261248.0
best_of: 1
max_input_tokens: 512
max_output_tokens: 1
reward_model: default
display_name: chaiml-20250411-rob-ava-_6550_v3
ineligible_reason: max_output_tokens!=64
is_internal_developer: True
language_model: ChaiML/20250411_rob_ava_reward_300k_safety_threshold_1_2
model_size: 8B
ranking_group: single
us_pacific_date: 2025-05-30
win_ratio: 0.5247422680412371
generation_params: {'temperature': 1.0, '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': 512, 'best_of': 1, 'max_output_tokens': 1}
formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '', '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-20250411-rob-ava-6550-v3-mkmlizer
Waiting for job on chaiml-20250411-rob-ava-6550-v3-mkmlizer to finish
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║                                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║                                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Version: 0.27.1+vampire_v3                                         ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║                                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║                                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ║                                                                     ║
chaiml-20250411-rob-ava-6550-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-20250411-rob-ava-6550-v3-mkmlizer: Downloaded to shared memory in 24.085s
chaiml-20250411-rob-ava-6550-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:t0, folder:/tmp/tmp695_e8bh, device:0
chaiml-20250411-rob-ava-6550-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-20250411-rob-ava-6550-v3-mkmlizer: quantized model in 19.398s
chaiml-20250411-rob-ava-6550-v3-mkmlizer: Processed model ChaiML/20250411_rob_ava_reward_300k_safety_threshold_1_2 in 43.484s
chaiml-20250411-rob-ava-6550-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-20250411-rob-ava-6550-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-20250411-rob-ava-6550-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3
chaiml-20250411-rob-ava-6550-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3/config.json
chaiml-20250411-rob-ava-6550-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3/special_tokens_map.json
chaiml-20250411-rob-ava-6550-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3/tokenizer_config.json
chaiml-20250411-rob-ava-6550-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3/tokenizer.json
chaiml-20250411-rob-ava-6550-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-20250411-rob-ava-6550-v3/flywheel_model.0.safetensors
Job chaiml-20250411-rob-ava-6550-v3-mkmlizer completed after 73.92s with status: succeeded
Stopping job with name chaiml-20250411-rob-ava-6550-v3-mkmlizer
Pipeline stage MKMLizer completed in 74.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-20250411-rob-ava-6550-v3
Waiting for inference service chaiml-20250411-rob-ava-6550-v3 to be ready
Inference service chaiml-20250411-rob-ava-6550-v3 ready after 150.60527563095093s
Pipeline stage MKMLDeployer completed in 151.15s
run pipeline stage %s
Running pipeline stage StressChecker
Retrying (%r) after connection broken by '%r': %s
Received healthy response to inference request in 5.180418491363525s
Received healthy response to inference request in 3.128857135772705s
Received healthy response to inference request in 3.6436305046081543s
Received healthy response to inference request in 4.043033838272095s
Received healthy response to inference request in 3.165933132171631s
5 requests
0 failed requests
5th percentile: 3.13627233505249
10th percentile: 3.143687534332275
20th percentile: 3.158517932891846
30th percentile: 3.2614726066589355
40th percentile: 3.452551555633545
50th percentile: 3.6436305046081543
60th percentile: 3.8033918380737304
70th percentile: 3.9631531715393065
80th percentile: 4.270510768890381
90th percentile: 4.725464630126953
95th percentile: 4.952941560745239
99th percentile: 5.134923105239868
mean time: 3.832374620437622
%s, retrying in %s seconds...
Received healthy response to inference request in 2.5997228622436523s
Received healthy response to inference request in 2.2333312034606934s
Received healthy response to inference request in 3.4873247146606445s
Received healthy response to inference request in 2.313645362854004s
Received healthy response to inference request in 2.8898396492004395s
5 requests
0 failed requests
5th percentile: 2.2493940353393556
10th percentile: 2.2654568672180178
20th percentile: 2.2975825309753417
30th percentile: 2.3708608627319334
40th percentile: 2.485291862487793
50th percentile: 2.5997228622436523
60th percentile: 2.715769577026367
70th percentile: 2.831816291809082
80th percentile: 3.0093366622924806
90th percentile: 3.2483306884765626
95th percentile: 3.3678277015686033
99th percentile: 3.4634253120422365
mean time: 2.7047727584838865
Pipeline stage StressChecker completed in 34.99s
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 0.66s
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 0.67s
Shutdown handler de-registered
chaiml-20250411-rob-ava-_6550_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3850.40s
Shutdown handler de-registered
chaiml-20250411-rob-ava-_6550_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-20250411-rob-ava-_6550_v3 status is now torndown due to DeploymentManager action