zmeeks-capitanito-48-s3

developer_uid: zmeeks

submission_id: zmeeks-capitanito-48-s3_v1

model_name: capitanito_t10__48-s3__ppmmp

model_group: zmeeks/capitanito__48-s3

status: torndown

timestamp: 2025-07-15T12:44:23+00:00

num_battles: 6938

num_wins: 3256

celo_rating: 1253.36

family_friendly_score: 0.571

family_friendly_standard_error: 0.006999414261207862

submission_type: basic

model_repo: zmeeks/capitanito__48-s3

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': 0.5914807516329919, 'latency_mean': 1.6904779362678528, 'latency_p50': 1.691398024559021, 'latency_p90': 1.8517066478729247}, {'batch_size': 3, 'throughput': 1.0563605253813872, 'latency_mean': 2.8274283981323243, 'latency_p50': 2.8253284692764282, 'latency_p90': 3.0919881105422973}, {'batch_size': 5, 'throughput': 1.2442306600672657, 'latency_mean': 4.003166552782059, 'latency_p50': 4.009807348251343, 'latency_p90': 4.437666249275208}, {'batch_size': 6, 'throughput': 1.3117999721220488, 'latency_mean': 4.543518097400665, 'latency_p50': 4.541678428649902, 'latency_p90': 5.012520718574524}, {'batch_size': 8, 'throughput': 1.3731837762592152, 'latency_mean': 5.800864763259888, 'latency_p50': 5.807567715644836, 'latency_p90': 6.502523303031921}, {'batch_size': 10, 'throughput': 1.3905024967490658, 'latency_mean': 7.138094805479049, 'latency_p50': 7.163720726966858, 'latency_p90': 7.933311319351196}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: capitanito_t10__48-s3__ppmmp

is_internal_developer: False

language_model: zmeeks/capitanito__48-s3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.21

us_pacific_date: 2025-07-15

win_ratio: 0.4692995099452292

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': 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-48-s3-v1-mkmlizer
Waiting for job on zmeeks-capitanito-48-s3-v1-mkmlizer to finish
zmeeks-capitanito-48-s3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
zmeeks-capitanito-48-s3-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  belonging to:                                                      ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ║                                                                     ║
zmeeks-capitanito-48-s3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
zmeeks-capitanito-48-s3-v1-mkmlizer: Downloaded to shared memory in 42.161s
zmeeks-capitanito-48-s3-v1-mkmlizer: Checking if zmeeks/capitanito__48-s3 already exists in ChaiML
zmeeks-capitanito-48-s3-v1-mkmlizer: Creating repo ChaiML/capitanito__48-s3 and uploading /tmp/tmpbfhuouz7 to it
zmeeks-capitanito-48-s3-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:05<00:29,  5.90s/it]
 33%|███▎      | 2/6 [00:09<00:18,  4.59s/it]
 50%|█████     | 3/6 [00:17<00:18,  6.16s/it]
 67%|██████▋   | 4/6 [00:21<00:10,  5.46s/it]
 83%|████████▎ | 5/6 [00:27<00:05,  5.47s/it]
100%|██████████| 6/6 [00:28<00:00,  3.96s/it]
100%|██████████| 6/6 [00:28<00:00,  4.75s/it]
zmeeks-capitanito-48-s3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpbfhuouz7, device:0
zmeeks-capitanito-48-s3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
zmeeks-capitanito-48-s3-v1-mkmlizer: quantized model in 30.085s
zmeeks-capitanito-48-s3-v1-mkmlizer: Processed model zmeeks/capitanito__48-s3 in 125.697s
zmeeks-capitanito-48-s3-v1-mkmlizer: creating bucket guanaco-mkml-models
zmeeks-capitanito-48-s3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
zmeeks-capitanito-48-s3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia
zmeeks-capitanito-48-s3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia/config.json
zmeeks-capitanito-48-s3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia/special_tokens_map.json
zmeeks-capitanito-48-s3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia/tokenizer_config.json
zmeeks-capitanito-48-s3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia/tokenizer.json
zmeeks-capitanito-48-s3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/zmeeks-capitanito-48-s3-v1/nvidia/flywheel_model.0.safetensors
zmeeks-capitanito-48-s3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 32.22it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 50.69it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.65it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.04it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.39it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.51it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.27it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 47.97it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.34it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:09, 33.50it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.82it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:07, 37.96it/s]
Loading 0:  21%|██        | 76/363 [00:01<00:07, 38.24it/s]
Loading 0:  22%|██▏       | 81/363 [00:01<00:07, 39.46it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:06, 41.61it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:07, 35.25it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 42.72it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 42.52it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 44.16it/s]
Loading 0:  31%|███       | 113/363 [00:02<00:06, 37.72it/s]
Loading 0:  33%|███▎      | 118/363 [00:02<00:06, 37.91it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 43.96it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 42.86it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.01it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:04, 44.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.94it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.08it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 34.83it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 36.59it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.96it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.02it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 33.51it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 40.66it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 40.34it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 40.23it/s]
Loading 0:  55%|█████▍    | 198/363 [00:05<00:03, 41.66it/s]
Loading 0:  56%|█████▌    | 203/363 [00:05<00:04, 34.57it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 40.51it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 40.31it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 41.26it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 26.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 28.94it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.87it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 37.70it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.02it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 40.90it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:03, 34.23it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 41.30it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 41.96it/s]
Loading 0:  75%|███████▌  | 274/363 [00:07<00:02, 40.74it/s]
Loading 0:  77%|███████▋  | 279/363 [00:07<00:01, 42.26it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 35.81it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 42.52it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 41.48it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.20it/s]
Loading 0:  84%|████████▍ | 306/363 [00:08<00:02, 24.90it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 25.84it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 28.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.71it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.16it/s]
Loading 0:  91%|█████████ | 330/363 [00:08<00:00, 34.61it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.57it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 42.53it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 43.59it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 45.06it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 35.59it/s]
                                                            
Job zmeeks-capitanito-48-s3-v1-mkmlizer completed after 148.05s with status: succeeded
Stopping job with name zmeeks-capitanito-48-s3-v1-mkmlizer
Pipeline stage MKMLizer completed in 148.54s
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-48-s3-v1
Waiting for inference service zmeeks-capitanito-48-s3-v1 to be ready
Inference service zmeeks-capitanito-48-s3-v1 ready after 240.93819975852966s
Pipeline stage MKMLDeployer completed in 241.38s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.3797712326049805s
Received healthy response to inference request in 1.7078335285186768s
Received healthy response to inference request in 1.8689546585083008s
Received healthy response to inference request in 1.6633594036102295s
Received healthy response to inference request in 1.8890459537506104s
5 requests
0 failed requests
5th percentile: 1.6722542285919189
10th percentile: 1.6811490535736084
20th percentile: 1.6989387035369874
30th percentile: 1.7400577545166016
40th percentile: 1.804506206512451
50th percentile: 1.8689546585083008
60th percentile: 1.8769911766052245
70th percentile: 1.8850276947021485
80th percentile: 1.9871910095214844
90th percentile: 2.1834811210632323
95th percentile: 2.281626176834106
99th percentile: 2.3601422214508054
mean time: 1.9017929553985595
Pipeline stage StressChecker completed in 10.81s
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 0.67s
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 0.66s
Shutdown handler de-registered
zmeeks-capitanito-48-s3_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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service zmeeks-capitanito-48-s3-v1-profiler
Waiting for inference service zmeeks-capitanito-48-s3-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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3601.82s
Shutdown handler de-registered
zmeeks-capitanito-48-s3_v1 status is now inactive due to auto deactivation removed underperforming models
zmeeks-capitanito-48-s3_v1 status is now torndown due to DeploymentManager action
Cleaning model data from S3
zmeeks-capitanito-48-s3_v1 status is now torndown due to DeploymentManager action