developer_uid: zmeeks
submission_id: zmeeks-capitanito-50_v3
model_name: capitanito_t10__z50__ppmmp
model_group: zmeeks/capitanito__50
status: torndown
timestamp: 2025-07-16T14:04:32+00:00
num_battles: 10127
num_wins: 4769
celo_rating: 1257.88
family_friendly_score: 0.5708
family_friendly_standard_error: 0.006999819426242366
submission_type: basic
model_repo: zmeeks/capitanito__50
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': 0.5997670911688673, 'latency_mean': 1.667210990190506, 'latency_p50': 1.657795786857605, 'latency_p90': 1.8370197296142579}, {'batch_size': 3, 'throughput': 1.0804502298764314, 'latency_mean': 2.766143954992294, 'latency_p50': 2.7559813261032104, 'latency_p90': 3.1090461015701294}, {'batch_size': 5, 'throughput': 1.2817744369277961, 'latency_mean': 3.8872485542297364, 'latency_p50': 3.9058961868286133, 'latency_p90': 4.335092639923095}, {'batch_size': 6, 'throughput': 1.3490637887219845, 'latency_mean': 4.425120606422424, 'latency_p50': 4.417688250541687, 'latency_p90': 4.929051375389099}, {'batch_size': 8, 'throughput': 1.4138912799714671, 'latency_mean': 5.618009946346283, 'latency_p50': 5.6062188148498535, 'latency_p90': 6.253026485443115}, {'batch_size': 10, 'throughput': 1.4345104959995465, 'latency_mean': 6.90616731762886, 'latency_p50': 6.957292079925537, 'latency_p90': 7.686287593841553}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: capitanito_t10__z50__ppmmp
is_internal_developer: False
language_model: zmeeks/capitanito__50
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-07-16
win_ratio: 0.4709193245778612
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 25, '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': '{prompt}\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 zmeeks-capitanito-50-v3-mkmlizer
Waiting for job on zmeeks-capitanito-50-v3-mkmlizer to finish
zmeeks-capitanito-50-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zmeeks-capitanito-50-v3-mkmlizer: ║                                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
zmeeks-capitanito-50-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
zmeeks-capitanito-50-v3-mkmlizer: ║                                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
zmeeks-capitanito-50-v3-mkmlizer: ║  https://mk1.ai                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ║                                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
zmeeks-capitanito-50-v3-mkmlizer: ║  belonging to:                                                      ║
zmeeks-capitanito-50-v3-mkmlizer: ║                                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Chai Research Corp.                                                ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zmeeks-capitanito-50-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
zmeeks-capitanito-50-v3-mkmlizer: ║                                                                     ║
zmeeks-capitanito-50-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zmeeks-capitanito-50-v3-mkmlizer: Downloaded to shared memory in 31.902s
zmeeks-capitanito-50-v3-mkmlizer: Checking if zmeeks/capitanito__50 already exists in ChaiML
zmeeks-capitanito-50-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3x_r3p6_, device:0
zmeeks-capitanito-50-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zmeeks-capitanito-50-v3-mkmlizer: quantized model in 32.221s
zmeeks-capitanito-50-v3-mkmlizer: Processed model zmeeks/capitanito__50 in 64.269s
zmeeks-capitanito-50-v3-mkmlizer: creating bucket guanaco-mkml-models
zmeeks-capitanito-50-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zmeeks-capitanito-50-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zmeeks-capitanito-50-v3/nvidia
zmeeks-capitanito-50-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zmeeks-capitanito-50-v3/nvidia/config.json
zmeeks-capitanito-50-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zmeeks-capitanito-50-v3/nvidia/special_tokens_map.json
zmeeks-capitanito-50-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zmeeks-capitanito-50-v3/nvidia/tokenizer_config.json
zmeeks-capitanito-50-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zmeeks-capitanito-50-v3/nvidia/tokenizer.json
Job zmeeks-capitanito-50-v3-mkmlizer completed after 102.85s with status: succeeded
Stopping job with name zmeeks-capitanito-50-v3-mkmlizer
Pipeline stage MKMLizer completed in 103.62s
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 zmeeks-capitanito-50-v3
Waiting for inference service zmeeks-capitanito-50-v3 to be ready
Failed to get response for submission junhua024-chai-02-full-061_v1: HTTPConnectionPool(host='junhua024-chai-02-full-061-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-02-full-061_v1: HTTPConnectionPool(host='junhua024-chai-02-full-061-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Failed to get response for submission junhua024-chai-02-full-061_v1: HTTPConnectionPool(host='junhua024-chai-02-full-061-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service zmeeks-capitanito-50-v3 ready after 271.62386751174927s
Pipeline stage MKMLDeployer completed in 272.04s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6063458919525146s
Received healthy response to inference request in 2.5383710861206055s
Received healthy response to inference request in 1.8946020603179932s
Received healthy response to inference request in 2.050912618637085s
Received healthy response to inference request in 1.9075226783752441s
5 requests
0 failed requests
5th percentile: 1.8971861839294433
10th percentile: 1.8997703075408936
20th percentile: 1.904938554763794
30th percentile: 1.9362006664276123
40th percentile: 1.9935566425323485
50th percentile: 2.050912618637085
60th percentile: 2.245896005630493
70th percentile: 2.440879392623901
80th percentile: 2.5519660472869874
90th percentile: 2.579155969619751
95th percentile: 2.5927509307861327
99th percentile: 2.6036268997192384
mean time: 2.1995508670806885
Pipeline stage StressChecker completed in 12.68s
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 0.68s
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
zmeeks-capitanito-50_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
clean up pipeline due to error=DeploymentChecksError('None: None')
Shutdown handler de-registered
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 3370.29s
Shutdown handler de-registered
zmeeks-capitanito-50_v3 status is now inactive due to auto deactivation removed underperforming models
zmeeks-capitanito-50_v3 status is now torndown due to DeploymentManager action
zmeeks-capitanito-50_v3 status is now torndown due to DeploymentManager action