developer_uid: rica40325
submission_id: rica40325-filter-feedbackv3_v2
model_name: rica40325-filter-feedbackv3_v1
model_group: rica40325/filter-feedbac
status: torndown
timestamp: 2025-06-24T12:36:14+00:00
num_battles: 7854
num_wins: 3705
celo_rating: 1266.63
family_friendly_score: 0.5802
family_friendly_standard_error: 0.006979512303879119
submission_type: basic
model_repo: rica40325/filter-feedbackv3
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5967488174295892, 'latency_mean': 1.6756281125545502, 'latency_p50': 1.683400273323059, 'latency_p90': 1.844738984107971}, {'batch_size': 3, 'throughput': 1.0885808792216163, 'latency_mean': 2.7431788301467894, 'latency_p50': 2.7276222705841064, 'latency_p90': 3.016599154472351}, {'batch_size': 5, 'throughput': 1.298193433382488, 'latency_mean': 3.8314346301555635, 'latency_p50': 3.8719035387039185, 'latency_p90': 4.203841018676758}, {'batch_size': 6, 'throughput': 1.3710837756231762, 'latency_mean': 4.359070600271225, 'latency_p50': 4.368979573249817, 'latency_p90': 4.840160894393921}, {'batch_size': 8, 'throughput': 1.4448704285181455, 'latency_mean': 5.501663618087768, 'latency_p50': 5.515318274497986, 'latency_p90': 6.157961702346801}, {'batch_size': 10, 'throughput': 1.4808372819641915, 'latency_mean': 6.699473925828934, 'latency_p50': 6.686452507972717, 'latency_p90': 7.583392024040222}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-filter-feedbackv3_v1
is_internal_developer: False
language_model: rica40325/filter-feedbackv3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.29
us_pacific_date: 2025-06-24
win_ratio: 0.4717341482047364
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': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': '<|im_start|>system\n{memory}<|im_end|>\n', 'prompt_template': '<|im_start|>user\n{prompt}<|im_end|>\n', 'bot_template': '<|im_start|>assistant\n{bot_name}: {message}<|im_end|>\n', 'user_template': '<|im_start|>user\n{user_name}: {message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n{bot_name}:', '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 rica40325-filter-feedbackv3-v2-mkmlizer
Waiting for job on rica40325-filter-feedbackv3-v2-mkmlizer to finish
rica40325-filter-feedbackv3-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-feedbackv3-v2-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-feedbackv3-v2-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-feedbackv3-v2-mkmlizer: Downloaded to shared memory in 44.911s
rica40325-filter-feedbackv3-v2-mkmlizer: Checking if rica40325/filter-feedbackv3 already exists in ChaiML
rica40325-filter-feedbackv3-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi_grog80, device:0
rica40325-filter-feedbackv3-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-feedbackv3-v2-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-feedbackv3-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-feedbackv3-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2
rica40325-filter-feedbackv3-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2/config.json
rica40325-filter-feedbackv3-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2/special_tokens_map.json
rica40325-filter-feedbackv3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2/tokenizer_config.json
rica40325-filter-feedbackv3-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2/tokenizer.json
rica40325-filter-feedbackv3-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v2/flywheel_model.0.safetensors
Job rica40325-filter-feedbackv3-v2-mkmlizer completed after 104.55s with status: succeeded
Stopping job with name rica40325-filter-feedbackv3-v2-mkmlizer
Pipeline stage MKMLizer completed in 105.06s
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 rica40325-filter-feedbackv3-v2
Waiting for inference service rica40325-filter-feedbackv3-v2 to be ready
Inference service rica40325-filter-feedbackv3-v2 ready after 130.45877981185913s
Pipeline stage MKMLDeployer completed in 131.01s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4123692512512207s
Received healthy response to inference request in 1.913649320602417s
Received healthy response to inference request in 1.9858431816101074s
Received healthy response to inference request in 1.7612593173980713s
Received healthy response to inference request in 1.7709670066833496s
5 requests
0 failed requests
5th percentile: 1.763200855255127
10th percentile: 1.7651423931121826
20th percentile: 1.7690254688262939
30th percentile: 1.799503469467163
40th percentile: 1.85657639503479
50th percentile: 1.913649320602417
60th percentile: 1.9425268650054932
70th percentile: 1.9714044094085694
80th percentile: 2.07114839553833
90th percentile: 2.2417588233947754
95th percentile: 2.327064037322998
99th percentile: 2.3953082084655763
mean time: 1.9688176155090331
Pipeline stage StressChecker completed in 12.04s
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 0.70s
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 0.93s
Shutdown handler de-registered
rica40325-filter-feedbackv3_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 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-filter-feedbackv3-v2-profiler
Waiting for inference service rica40325-filter-feedbackv3-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5279.22s
Shutdown handler de-registered
rica40325-filter-feedbackv3_v2 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-feedbackv3_v2 status is now torndown due to DeploymentManager action