developer_uid: zmeeks
submission_id: zmeeks-capitanito-53-1600_v4
model_name: capitanito_t11__z53-1600__ppmmp
model_group: zmeeks/capitanito__53-16
status: torndown
timestamp: 2025-07-17T01:12:41+00:00
num_battles: 5880
num_wins: 2856
celo_rating: 1263.78
family_friendly_score: 0.5706
family_friendly_standard_error: 0.007000223425005805
submission_type: basic
model_repo: zmeeks/capitanito__53-1600
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': 0.5964896421072529, 'latency_mean': 1.676295179128647, 'latency_p50': 1.6731276512145996, 'latency_p90': 1.8500017881393434}, {'batch_size': 3, 'throughput': 1.0749243784065676, 'latency_mean': 2.7882576322555543, 'latency_p50': 2.784657597541809, 'latency_p90': 3.0106933832168576}, {'batch_size': 5, 'throughput': 1.2934965377999008, 'latency_mean': 3.853067810535431, 'latency_p50': 3.856335997581482, 'latency_p90': 4.310402941703797}, {'batch_size': 6, 'throughput': 1.343134442733209, 'latency_mean': 4.445931924581528, 'latency_p50': 4.465345025062561, 'latency_p90': 4.9565101146698}, {'batch_size': 8, 'throughput': 1.4163913339065497, 'latency_mean': 5.592583223581314, 'latency_p50': 5.624091863632202, 'latency_p90': 6.254927444458008}, {'batch_size': 10, 'throughput': 1.4508119853282209, 'latency_mean': 6.831022815704346, 'latency_p50': 6.840661525726318, 'latency_p90': 7.670665287971496}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: capitanito_t11__z53-1600__ppmmp
is_internal_developer: False
language_model: zmeeks/capitanito__53-1600
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-16
win_ratio: 0.4857142857142857
generation_params: {'temperature': 1.1, '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-53-1600-v4-mkmlizer
Waiting for job on zmeeks-capitanito-53-1600-v4-mkmlizer to finish
zmeeks-capitanito-53-1600-v4-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zmeeks-capitanito-53-1600-v4-mkmlizer: ║                                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║                                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Version: 0.29.15                                                   ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  https://mk1.ai                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║                                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  The license key for the current software has been verified as      ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  belonging to:                                                      ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║                                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Chai Research Corp.                                                ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ║                                                                     ║
zmeeks-capitanito-53-1600-v4-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zmeeks-capitanito-53-1600-v4-mkmlizer: Downloaded to shared memory in 37.312s
zmeeks-capitanito-53-1600-v4-mkmlizer: Checking if zmeeks/capitanito__53-1600 already exists in ChaiML
zmeeks-capitanito-53-1600-v4-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy2d8wqgq, device:0
zmeeks-capitanito-53-1600-v4-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zmeeks-capitanito-53-1600-v4-mkmlizer: quantized model in 31.373s
zmeeks-capitanito-53-1600-v4-mkmlizer: Processed model zmeeks/capitanito__53-1600 in 68.777s
zmeeks-capitanito-53-1600-v4-mkmlizer: creating bucket guanaco-mkml-models
zmeeks-capitanito-53-1600-v4-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zmeeks-capitanito-53-1600-v4-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zmeeks-capitanito-53-1600-v4/nvidia
zmeeks-capitanito-53-1600-v4-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zmeeks-capitanito-53-1600-v4/nvidia/config.json
zmeeks-capitanito-53-1600-v4-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zmeeks-capitanito-53-1600-v4/nvidia/special_tokens_map.json
zmeeks-capitanito-53-1600-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zmeeks-capitanito-53-1600-v4/nvidia/tokenizer_config.json
zmeeks-capitanito-53-1600-v4-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zmeeks-capitanito-53-1600-v4/nvidia/tokenizer.json
Job zmeeks-capitanito-53-1600-v4-mkmlizer completed after 96.55s with status: succeeded
Stopping job with name zmeeks-capitanito-53-1600-v4-mkmlizer
Pipeline stage MKMLizer completed in 97.50s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.21s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service zmeeks-capitanito-53-1600-v4
Waiting for inference service zmeeks-capitanito-53-1600-v4 to be ready
Failed to get response for submission chaiml-cogito32b-dpos2-_39363_v4: ('http://chaiml-cogito32b-dpos2-39363-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:49470->127.0.0.1:8080: read: connection reset by peer\n')
Inference service zmeeks-capitanito-53-1600-v4 ready after 270.9056270122528s
Pipeline stage MKMLDeployer completed in 271.57s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 1.5537903308868408s
Received healthy response to inference request in 1.4765620231628418s
Received healthy response to inference request in 2.010976791381836s
Received healthy response to inference request in 1.4916658401489258s
Received healthy response to inference request in 1.5924859046936035s
5 requests
0 failed requests
5th percentile: 1.4795827865600586
10th percentile: 1.4826035499572754
20th percentile: 1.488645076751709
30th percentile: 1.5040907382965087
40th percentile: 1.528940534591675
50th percentile: 1.5537903308868408
60th percentile: 1.569268560409546
70th percentile: 1.584746789932251
80th percentile: 1.6761840820312501
90th percentile: 1.843580436706543
95th percentile: 1.9272786140441893
99th percentile: 1.9942371559143066
mean time: 1.6250961780548097
Pipeline stage StressChecker completed in 9.41s
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 0.67s
Shutdown handler de-registered
zmeeks-capitanito-53-1600_v4 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 0.12s
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 zmeeks-capitanito-53-1600-v4-profiler
Waiting for inference service zmeeks-capitanito-53-1600-v4-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 3076.77s
Shutdown handler de-registered
zmeeks-capitanito-53-1600_v4 status is now inactive due to auto deactivation removed underperforming models
zmeeks-capitanito-53-1600_v4 status is now torndown due to DeploymentManager action
zmeeks-capitanito-53-1600_v4 status is now torndown due to DeploymentManager action