riverise-captain-filter_96811

developer_uid: Riverise

submission_id: riverise-captain-filter_96811_v1

model_name: riverise-captain-filter_96811_v1

model_group: Riverise/captain_filter_

status: torndown

timestamp: 2025-06-25T13:55:46+00:00

num_battles: 7511

num_wins: 3696

celo_rating: 1273.27

family_friendly_score: 0.5628

family_friendly_standard_error: 0.007015071774401171

submission_type: basic

model_repo: Riverise/captain_filter_0622_checkpoint-1250

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': 0.5937521582384813, 'latency_mean': 1.6840924406051636, 'latency_p50': 1.674647331237793, 'latency_p90': 1.8590476036071777}, {'batch_size': 3, 'throughput': 1.0630048612499294, 'latency_mean': 2.8180436956882478, 'latency_p50': 2.833067297935486, 'latency_p90': 3.1336931705474855}, {'batch_size': 5, 'throughput': 1.2819864177667994, 'latency_mean': 3.8785726153850555, 'latency_p50': 3.8708300590515137, 'latency_p90': 4.389821290969849}, {'batch_size': 6, 'throughput': 1.3378319589865888, 'latency_mean': 4.4698248541355134, 'latency_p50': 4.486003756523132, 'latency_p90': 4.932292461395264}, {'batch_size': 8, 'throughput': 1.3925602756522344, 'latency_mean': 5.706278749704361, 'latency_p50': 5.676637649536133, 'latency_p90': 6.432095670700074}, {'batch_size': 10, 'throughput': 1.4328528851089466, 'latency_mean': 6.904891269207001, 'latency_p50': 6.942264795303345, 'latency_p90': 7.8230209112167355}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: riverise-captain-filter_96811_v1

is_internal_developer: False

language_model: Riverise/captain_filter_0622_checkpoint-1250

model_size: 13B

ranking_group: single

throughput_3p7s: 1.26

us_pacific_date: 2025-06-25

win_ratio: 0.49207828518173347

generation_params: {'temperature': 0.95, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, '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 riverise-captain-filter-96811-v1-mkmlizer
Waiting for job on riverise-captain-filter-96811-v1-mkmlizer to finish
riverise-captain-filter-96811-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
riverise-captain-filter-96811-v1-mkmlizer: ║                                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
riverise-captain-filter-96811-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
riverise-captain-filter-96811-v1-mkmlizer: ║                                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
riverise-captain-filter-96811-v1-mkmlizer: ║  https://mk1.ai                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ║                                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
riverise-captain-filter-96811-v1-mkmlizer: ║  belonging to:                                                      ║
riverise-captain-filter-96811-v1-mkmlizer: ║                                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Chai Research Corp.                                                ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
riverise-captain-filter-96811-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
riverise-captain-filter-96811-v1-mkmlizer: ║                                                                     ║
riverise-captain-filter-96811-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
riverise-captain-filter-96811-v1-mkmlizer: Downloaded to shared memory in 41.153s
riverise-captain-filter-96811-v1-mkmlizer: Checking if Riverise/captain_filter_0622_checkpoint-1250 already exists in ChaiML
riverise-captain-filter-96811-v1-mkmlizer: Creating repo ChaiML/captain_filter_0622_checkpoint-1250 and uploading /tmp/tmp__te_2yh to it
riverise-captain-filter-96811-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:04<00:20,  4.11s/it]
 33%|███▎      | 2/6 [00:07<00:15,  3.75s/it]
 50%|█████     | 3/6 [00:11<00:10,  3.65s/it]
 67%|██████▋   | 4/6 [00:18<00:10,  5.08s/it]
 83%|████████▎ | 5/6 [00:22<00:04,  4.61s/it]
100%|██████████| 6/6 [00:23<00:00,  3.43s/it]
100%|██████████| 6/6 [00:23<00:00,  3.89s/it]
riverise-captain-filter-96811-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp__te_2yh, device:0
riverise-captain-filter-96811-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
riverise-captain-filter-96811-v1-mkmlizer: quantized model in 30.600s
riverise-captain-filter-96811-v1-mkmlizer: Processed model Riverise/captain_filter_0622_checkpoint-1250 in 120.966s
riverise-captain-filter-96811-v1-mkmlizer: creating bucket guanaco-mkml-models
riverise-captain-filter-96811-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
riverise-captain-filter-96811-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/riverise-captain-filter-96811-v1
riverise-captain-filter-96811-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/riverise-captain-filter-96811-v1/config.json
riverise-captain-filter-96811-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/riverise-captain-filter-96811-v1/special_tokens_map.json
riverise-captain-filter-96811-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/riverise-captain-filter-96811-v1/tokenizer_config.json
riverise-captain-filter-96811-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/riverise-captain-filter-96811-v1/tokenizer.json
riverise-captain-filter-96811-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/riverise-captain-filter-96811-v1/flywheel_model.0.safetensors
riverise-captain-filter-96811-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 30.29it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:07, 48.39it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 44.66it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.01it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 48.81it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 44.92it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 43.44it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 48.41it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 44.86it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 33.80it/s]
Loading 0:  18%|█▊        | 65/363 [00:01<00:09, 32.53it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 38.55it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 38.83it/s]
Loading 0:  23%|██▎       | 83/363 [00:02<00:07, 38.37it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 42.94it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 42.29it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 43.18it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 44.51it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 42.75it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 43.00it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 41.30it/s]
Loading 0:  35%|███▍      | 126/363 [00:03<00:05, 44.08it/s]
Loading 0:  36%|███▋      | 132/363 [00:03<00:05, 41.81it/s]
Loading 0:  38%|███▊      | 137/363 [00:03<00:05, 39.72it/s]
Loading 0:  39%|███▉      | 142/363 [00:03<00:07, 30.54it/s]
Loading 0:  40%|████      | 146/363 [00:03<00:06, 31.45it/s]
Loading 0:  41%|████▏     | 150/363 [00:03<00:06, 30.59it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 36.56it/s]
Loading 0:  44%|████▍     | 160/363 [00:04<00:05, 36.61it/s]
Loading 0:  45%|████▌     | 165/363 [00:04<00:04, 39.88it/s]
Loading 0:  47%|████▋     | 170/363 [00:04<00:04, 39.74it/s]
Loading 0:  48%|████▊     | 175/363 [00:04<00:04, 40.80it/s]
Loading 0:  50%|████▉     | 180/363 [00:04<00:04, 42.60it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:04, 35.93it/s]
Loading 0:  53%|█████▎    | 192/363 [00:04<00:03, 43.06it/s]
Loading 0:  54%|█████▍    | 197/363 [00:04<00:03, 43.27it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:03, 43.69it/s]
Loading 0:  57%|█████▋    | 207/363 [00:05<00:03, 44.67it/s]
Loading 0:  58%|█████▊    | 212/363 [00:05<00:04, 37.15it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:03, 41.71it/s]
Loading 0:  61%|██████▏   | 223/363 [00:05<00:04, 31.77it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 31.95it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.68it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 36.29it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 35.88it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.60it/s]
Loading 0:  69%|██████▉   | 251/363 [00:06<00:02, 39.56it/s]
Loading 0:  71%|███████   | 256/363 [00:06<00:02, 40.40it/s]
Loading 0:  72%|███████▏  | 261/363 [00:06<00:02, 42.48it/s]
Loading 0:  73%|███████▎  | 266/363 [00:06<00:02, 34.20it/s]
Loading 0:  75%|███████▌  | 273/363 [00:06<00:02, 41.40it/s]
Loading 0:  77%|███████▋  | 278/363 [00:07<00:02, 40.81it/s]
Loading 0:  78%|███████▊  | 283/363 [00:07<00:01, 41.33it/s]
Loading 0:  79%|███████▉  | 288/363 [00:07<00:01, 43.42it/s]
Loading 0:  81%|████████  | 293/363 [00:07<00:01, 36.66it/s]
Loading 0:  82%|████████▏ | 299/363 [00:07<00:01, 40.53it/s]
Loading 0:  84%|████████▎ | 304/363 [00:08<00:02, 22.34it/s]
Loading 0:  85%|████████▍ | 308/363 [00:08<00:02, 24.46it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 24.51it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.86it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.87it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 36.86it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 42.27it/s]
Loading 0:  94%|█████████▍| 343/363 [00:08<00:00, 43.67it/s]
Loading 0:  96%|█████████▌| 348/363 [00:09<00:00, 38.00it/s]
Loading 0:  98%|█████████▊| 355/363 [00:09<00:00, 44.96it/s]
Loading 0:  99%|█████████▉| 360/363 [00:09<00:00, 44.54it/s]
                                                            
Job riverise-captain-filter-96811-v1-mkmlizer completed after 145.12s with status: succeeded
Stopping job with name riverise-captain-filter-96811-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.61s
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 riverise-captain-filter-96811-v1
Waiting for inference service riverise-captain-filter-96811-v1 to be ready
Inference service riverise-captain-filter-96811-v1 ready after 150.80367064476013s
Pipeline stage MKMLDeployer completed in 151.35s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2244269847869873s
Received healthy response to inference request in 1.6463286876678467s
Received healthy response to inference request in 1.6525120735168457s
Received healthy response to inference request in 1.3720741271972656s
Received healthy response to inference request in 2.1566009521484375s
5 requests
0 failed requests
5th percentile: 1.426925039291382
10th percentile: 1.481775951385498
20th percentile: 1.5914777755737304
30th percentile: 1.6475653648376465
40th percentile: 1.650038719177246
50th percentile: 1.6525120735168457
60th percentile: 1.8541476249694824
70th percentile: 2.055783176422119
80th percentile: 2.1701661586761474
90th percentile: 2.1972965717315676
95th percentile: 2.2108617782592774
99th percentile: 2.2217139434814452
mean time: 1.8103885650634766
Pipeline stage StressChecker completed in 10.42s
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 0.70s
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 0.77s
Shutdown handler de-registered
riverise-captain-filter_96811_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 0.17s
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 riverise-captain-filter-96811-v1-profiler
Waiting for inference service riverise-captain-filter-96811-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 3018.68s
Shutdown handler de-registered
riverise-captain-filter_96811_v1 status is now inactive due to auto deactivation removed underperforming models
riverise-captain-filter_96811_v1 status is now torndown due to DeploymentManager action