developer_uid: zmeeks
submission_id: zmeeks-capitanito-1_v1
model_name: capitanito__1
model_group: zmeeks/capitanito__1
status: torndown
timestamp: 2025-07-11T00:58:03+00:00
num_battles: 7081
num_wins: 2837
celo_rating: 1214.03
family_friendly_score: 0.5588
family_friendly_standard_error: 0.007022001993733695
submission_type: basic
model_repo: zmeeks/capitanito__1
model_architecture: MistralForCausalLM
model_num_parameters: 12772080640.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
reward_model: default
latencies: [{'batch_size': 1, 'throughput': 0.5970906536166478, 'latency_mean': 1.6746566367149354, 'latency_p50': 1.654834508895874, 'latency_p90': 1.853646206855774}, {'batch_size': 3, 'throughput': 1.0791850163494456, 'latency_mean': 2.7649015128612517, 'latency_p50': 2.7486575841903687, 'latency_p90': 3.016515278816223}, {'batch_size': 5, 'throughput': 1.2898857155364938, 'latency_mean': 3.8563221526145934, 'latency_p50': 3.873061180114746, 'latency_p90': 4.33355131149292}, {'batch_size': 6, 'throughput': 1.3584759923937335, 'latency_mean': 4.3948824810981755, 'latency_p50': 4.426706314086914, 'latency_p90': 4.904406309127808}, {'batch_size': 8, 'throughput': 1.413415790001411, 'latency_mean': 5.624707053899765, 'latency_p50': 5.667349338531494, 'latency_p90': 6.3058289051055905}, {'batch_size': 10, 'throughput': 1.4592338157219138, 'latency_mean': 6.802047071456909, 'latency_p50': 6.756876707077026, 'latency_p90': 7.782580900192261}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: capitanito__1
is_internal_developer: False
language_model: zmeeks/capitanito__1
model_size: 13B
ranking_group: single
throughput_3p7s: 1.27
us_pacific_date: 2025-07-10
win_ratio: 0.4006496257590736
generation_params: {'temperature': 1.2, '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': 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-1-v1-mkmlizer
Waiting for job on zmeeks-capitanito-1-v1-mkmlizer to finish
zmeeks-capitanito-1-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zmeeks-capitanito-1-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
zmeeks-capitanito-1-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
zmeeks-capitanito-1-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
zmeeks-capitanito-1-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zmeeks-capitanito-1-v1-mkmlizer: ║  belonging to:                                                      ║
zmeeks-capitanito-1-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zmeeks-capitanito-1-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
zmeeks-capitanito-1-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-1-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zmeeks-capitanito-1-v1-mkmlizer: Downloaded to shared memory in 44.260s
zmeeks-capitanito-1-v1-mkmlizer: Checking if zmeeks/capitanito__1 already exists in ChaiML
zmeeks-capitanito-1-v1-mkmlizer: Creating repo ChaiML/capitanito__1 and uploading /tmp/tmp3iyu0hmr to it
zmeeks-capitanito-1-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:05<00:26,  5.30s/it]
 33%|███▎      | 2/6 [00:12<00:26,  6.70s/it]
 50%|█████     | 3/6 [00:17<00:17,  5.69s/it]
 67%|██████▋   | 4/6 [00:24<00:12,  6.39s/it]
 83%|████████▎ | 5/6 [00:28<00:05,  5.42s/it]
100%|██████████| 6/6 [00:29<00:00,  3.97s/it]
100%|██████████| 6/6 [00:29<00:00,  4.96s/it]
zmeeks-capitanito-1-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3iyu0hmr, device:0
zmeeks-capitanito-1-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zmeeks-capitanito-1-v1-mkmlizer: quantized model in 30.705s
zmeeks-capitanito-1-v1-mkmlizer: Processed model zmeeks/capitanito__1 in 130.127s
zmeeks-capitanito-1-v1-mkmlizer: creating bucket guanaco-mkml-models
zmeeks-capitanito-1-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zmeeks-capitanito-1-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia
zmeeks-capitanito-1-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia/config.json
zmeeks-capitanito-1-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia/special_tokens_map.json
zmeeks-capitanito-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia/tokenizer_config.json
zmeeks-capitanito-1-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia/tokenizer.json
zmeeks-capitanito-1-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zmeeks-capitanito-1-v1/nvidia/flywheel_model.0.safetensors
Job zmeeks-capitanito-1-v1-mkmlizer completed after 157.78s with status: succeeded
Stopping job with name zmeeks-capitanito-1-v1-mkmlizer
Pipeline stage MKMLizer completed in 158.25s
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 zmeeks-capitanito-1-v1
Waiting for inference service zmeeks-capitanito-1-v1 to be ready
Inference service zmeeks-capitanito-1-v1 ready after 191.38614130020142s
Pipeline stage MKMLDeployer completed in 192.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.211369752883911s
Received healthy response to inference request in 1.5664033889770508s
Received healthy response to inference request in 1.5241320133209229s
Received healthy response to inference request in 1.422229528427124s
Received healthy response to inference request in 1.734860897064209s
5 requests
0 failed requests
5th percentile: 1.4426100254058838
10th percentile: 1.4629905223846436
20th percentile: 1.503751516342163
30th percentile: 1.5325862884521484
40th percentile: 1.5494948387145997
50th percentile: 1.5664033889770508
60th percentile: 1.633786392211914
70th percentile: 1.7011693954467773
80th percentile: 1.8301626682281495
90th percentile: 2.0207662105560305
95th percentile: 2.116067981719971
99th percentile: 2.192309398651123
mean time: 1.6917991161346435
Pipeline stage StressChecker completed in 9.95s
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 1.09s
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 0.82s
Shutdown handler de-registered
zmeeks-capitanito-1_v1 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 zmeeks-capitanito-1-v1-profiler
Waiting for inference service zmeeks-capitanito-1-v1-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 5202.42s
Shutdown handler de-registered
zmeeks-capitanito-1_v1 status is now inactive due to auto deactivation removed underperforming models
zmeeks-capitanito-1_v1 status is now torndown due to DeploymentManager action