developer_uid: zmeeks
submission_id: zmeeks-capitanito-29_v13
model_name: capitanito_t10_k20__29__ppmmp
model_group: zmeeks/capitanito__29
status: torndown
timestamp: 2025-07-13T01:19:56+00:00
num_battles: 12308
num_wins: 5680
celo_rating: 1254.75
family_friendly_score: 0.5751999999999999
family_friendly_standard_error: 0.0069906360225661865
submission_type: basic
model_repo: zmeeks/capitanito__29
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': 0.6036362842092697, 'latency_mean': 1.656496331691742, 'latency_p50': 1.6707179546356201, 'latency_p90': 1.8180307865142822}, {'batch_size': 3, 'throughput': 1.0937307620079595, 'latency_mean': 2.741129461526871, 'latency_p50': 2.7501920461654663, 'latency_p90': 3.008913850784302}, {'batch_size': 5, 'throughput': 1.3240438532957148, 'latency_mean': 3.7631808590888975, 'latency_p50': 3.78205144405365, 'latency_p90': 4.2346944332122805}, {'batch_size': 6, 'throughput': 1.3963133540834296, 'latency_mean': 4.260484545230866, 'latency_p50': 4.282878756523132, 'latency_p90': 4.797792768478393}, {'batch_size': 8, 'throughput': 1.4567579444722176, 'latency_mean': 5.450896221399307, 'latency_p50': 5.4720693826675415, 'latency_p90': 5.9861749649047855}, {'batch_size': 10, 'throughput': 1.4938102569206773, 'latency_mean': 6.640229929685592, 'latency_p50': 6.6581807136535645, 'latency_p90': 7.52831757068634}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: capitanito_t10_k20__29__ppmmp
is_internal_developer: False
language_model: zmeeks/capitanito__29
model_size: 13B
ranking_group: single
throughput_3p7s: 1.32
us_pacific_date: 2025-07-12
win_ratio: 0.4614884627884303
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 20, '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': 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 zmeeks-capitanito-29-v13-mkmlizer
Waiting for job on zmeeks-capitanito-29-v13-mkmlizer to finish
zmeeks-capitanito-29-v13-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zmeeks-capitanito-29-v13-mkmlizer: ║                                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
zmeeks-capitanito-29-v13-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
zmeeks-capitanito-29-v13-mkmlizer: ║                                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Version: 0.29.15                                                   ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
zmeeks-capitanito-29-v13-mkmlizer: ║  https://mk1.ai                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ║                                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ║  The license key for the current software has been verified as      ║
zmeeks-capitanito-29-v13-mkmlizer: ║  belonging to:                                                      ║
zmeeks-capitanito-29-v13-mkmlizer: ║                                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Chai Research Corp.                                                ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zmeeks-capitanito-29-v13-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
zmeeks-capitanito-29-v13-mkmlizer: ║                                                                     ║
zmeeks-capitanito-29-v13-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zmeeks-capitanito-29-v13-mkmlizer: Downloaded to shared memory in 37.322s
zmeeks-capitanito-29-v13-mkmlizer: Checking if zmeeks/capitanito__29 already exists in ChaiML
zmeeks-capitanito-29-v13-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkgx_fr_d, device:0
zmeeks-capitanito-29-v13-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zmeeks-capitanito-29-v13-mkmlizer: quantized model in 29.913s
zmeeks-capitanito-29-v13-mkmlizer: Processed model zmeeks/capitanito__29 in 67.315s
zmeeks-capitanito-29-v13-mkmlizer: creating bucket guanaco-mkml-models
zmeeks-capitanito-29-v13-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zmeeks-capitanito-29-v13-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia
zmeeks-capitanito-29-v13-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia/config.json
zmeeks-capitanito-29-v13-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia/special_tokens_map.json
zmeeks-capitanito-29-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia/tokenizer_config.json
zmeeks-capitanito-29-v13-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia/tokenizer.json
zmeeks-capitanito-29-v13-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zmeeks-capitanito-29-v13/nvidia/flywheel_model.0.safetensors
Job zmeeks-capitanito-29-v13-mkmlizer completed after 95.02s with status: succeeded
Stopping job with name zmeeks-capitanito-29-v13-mkmlizer
Pipeline stage MKMLizer completed in 95.84s
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-29-v13
Waiting for inference service zmeeks-capitanito-29-v13 to be ready
Inference service zmeeks-capitanito-29-v13 ready after 221.43889474868774s
Pipeline stage MKMLDeployer completed in 221.91s
run pipeline stage %s
Running pipeline stage StressChecker
HTTPConnectionPool(host='guanaco-submitter.guanaco-backend.k2.chaiverse.com', port=80): Read timed out. (read timeout=20)
Received unhealthy response to inference request!
Received healthy response to inference request in 2.196904420852661s
Received healthy response to inference request in 1.6260297298431396s
Received healthy response to inference request in 1.6397173404693604s
Received healthy response to inference request in 1.6736786365509033s
5 requests
1 failed requests
5th percentile: 1.6287672519683838
10th percentile: 1.631504774093628
20th percentile: 1.6369798183441162
30th percentile: 1.646509599685669
40th percentile: 1.6600941181182862
50th percentile: 1.6736786365509033
60th percentile: 1.8829689502716065
70th percentile: 2.0922592639923097
80th percentile: 5.785823822021488
90th percentile: 12.963662624359133
95th percentile: 16.55258202552795
99th percentile: 19.423717546463013
mean time: 5.455566310882569
%s, retrying in %s seconds...
Received healthy response to inference request in 2.0522334575653076s
Received healthy response to inference request in 1.723146915435791s
Received healthy response to inference request in 1.692889928817749s
Received healthy response to inference request in 1.453927755355835s
Received healthy response to inference request in 1.7931182384490967s
5 requests
0 failed requests
5th percentile: 1.5017201900482178
10th percentile: 1.5495126247406006
20th percentile: 1.6450974941253662
30th percentile: 1.6989413261413575
40th percentile: 1.7110441207885743
50th percentile: 1.723146915435791
60th percentile: 1.7511354446411134
70th percentile: 1.7791239738464355
80th percentile: 1.844941282272339
90th percentile: 1.9485873699188232
95th percentile: 2.0004104137420655
99th percentile: 2.041868848800659
mean time: 1.743063259124756
Pipeline stage StressChecker completed in 38.64s
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 0.99s
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 0.68s
Shutdown handler de-registered
zmeeks-capitanito-29_v13 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 3206.24s
Shutdown handler de-registered
zmeeks-capitanito-29_v13 status is now inactive due to auto deactivation removed underperforming models
zmeeks-capitanito-29_v13 status is now torndown due to DeploymentManager action