rica40325-filter-feedbackv3-2

developer_uid: rica40325

submission_id: rica40325-filter-feedbackv3-2_v1

model_name: rica40325-filter-feedbackv3-2_v1

model_group: rica40325/filter-feedbac

status: torndown

timestamp: 2025-06-26T06:19:13+00:00

num_battles: 8362

num_wins: 3958

celo_rating: 1268.58

family_friendly_score: 0.571

family_friendly_standard_error: 0.006999414261207862

submission_type: basic

model_repo: rica40325/filter-feedbackv3.2

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': 0.5975693284173792, 'latency_mean': 1.6733179593086243, 'latency_p50': 1.6787161827087402, 'latency_p90': 1.8404604196548462}, {'batch_size': 3, 'throughput': 1.0849684904942956, 'latency_mean': 2.754786821603775, 'latency_p50': 2.7431355714797974, 'latency_p90': 3.0208630084991452}, {'batch_size': 5, 'throughput': 1.3163630819300316, 'latency_mean': 3.774681830406189, 'latency_p50': 3.8059052228927612, 'latency_p90': 4.179959058761597}, {'batch_size': 6, 'throughput': 1.379449255073035, 'latency_mean': 4.329446054697037, 'latency_p50': 4.333159327507019, 'latency_p90': 4.830634641647339}, {'batch_size': 8, 'throughput': 1.444214393665029, 'latency_mean': 5.500085756778717, 'latency_p50': 5.480615019798279, 'latency_p90': 6.160862588882446}, {'batch_size': 10, 'throughput': 1.473685239438593, 'latency_mean': 6.738850064277649, 'latency_p50': 6.794699311256409, 'latency_p90': 7.600349068641663}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-filter-feedbackv3-2_v1

is_internal_developer: False

language_model: rica40325/filter-feedbackv3.2

model_size: 13B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-06-25

win_ratio: 0.47333173881846446

generation_params: {'temperature': 1.0, '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 rica40325-filter-feedbackv3-2-v1-mkmlizer
Waiting for job on rica40325-filter-feedbackv3-2-v1-mkmlizer to finish
rica40325-filter-feedbackv3-2-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-2-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-feedbackv3-2-v1-mkmlizer: Downloaded to shared memory in 40.849s
rica40325-filter-feedbackv3-2-v1-mkmlizer: Checking if rica40325/filter-feedbackv3.2 already exists in ChaiML
rica40325-filter-feedbackv3-2-v1-mkmlizer: Creating repo ChaiML/filter-feedbackv3.2 and uploading /tmp/tmp28crgvnz to it
Failed to get response for submission chaiml-llama8b-retune7-_53337_v1: HTTPConnectionPool(host='chaiml-llama8b-retune7-53337-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rica40325-filter-feedbackv3-2-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:07<00:36,  7.31s/it]
 33%|███▎      | 2/6 [00:11<00:21,  5.41s/it]
 50%|█████     | 3/6 [00:18<00:18,  6.29s/it]
 67%|██████▋   | 4/6 [00:22<00:10,  5.37s/it]
 83%|████████▎ | 5/6 [00:26<00:04,  4.71s/it]
100%|██████████| 6/6 [00:27<00:00,  3.50s/it]
100%|██████████| 6/6 [00:27<00:00,  4.56s/it]
rica40325-filter-feedbackv3-2-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp28crgvnz, device:0
rica40325-filter-feedbackv3-2-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-feedbackv3-2-v1-mkmlizer: quantized model in 29.874s
rica40325-filter-feedbackv3-2-v1-mkmlizer: Processed model rica40325/filter-feedbackv3.2 in 123.568s
rica40325-filter-feedbackv3-2-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-feedbackv3-2-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-feedbackv3-2-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1
rica40325-filter-feedbackv3-2-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1/config.json
rica40325-filter-feedbackv3-2-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1/special_tokens_map.json
rica40325-filter-feedbackv3-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1/tokenizer_config.json
rica40325-filter-feedbackv3-2-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1/tokenizer.json
rica40325-filter-feedbackv3-2-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-feedbackv3-2-v1/flywheel_model.0.safetensors
rica40325-filter-feedbackv3-2-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:11, 31.78it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.89it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 47.18it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 45.29it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 51.91it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:06, 49.15it/s]
Loading 0:  12%|█▏        | 43/363 [00:00<00:06, 49.42it/s]
Loading 0:  13%|█▎        | 49/363 [00:00<00:06, 51.72it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 48.93it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.32it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.63it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 41.03it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:06, 40.80it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 41.02it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:05, 46.20it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 43.02it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 42.02it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:05, 48.18it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:05, 44.07it/s]
Loading 0:  33%|███▎      | 119/363 [00:02<00:05, 42.90it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 46.91it/s]
Loading 0:  36%|███▌      | 130/363 [00:02<00:05, 44.84it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 43.82it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.59it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.37it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.00it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 37.40it/s]
Loading 0:  46%|████▌     | 166/363 [00:03<00:05, 38.87it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.17it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.65it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 42.42it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 41.44it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:04, 42.41it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 41.32it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 40.04it/s]
Loading 0:  58%|█████▊    | 211/363 [00:05<00:03, 45.01it/s]
Loading 0:  60%|█████▉    | 217/363 [00:05<00:03, 43.51it/s]
Loading 0:  61%|██████    | 222/363 [00:05<00:03, 44.41it/s]
Loading 0:  63%|██████▎   | 227/363 [00:05<00:04, 30.12it/s]
Loading 0:  64%|██████▎   | 231/363 [00:05<00:04, 30.57it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 36.34it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 38.59it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 40.28it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 42.72it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 36.41it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.22it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.94it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 44.39it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 45.73it/s]
Loading 0:  78%|███████▊  | 284/363 [00:06<00:02, 37.86it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 44.78it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.00it/s]
Loading 0:  83%|████████▎ | 302/363 [00:07<00:01, 46.69it/s]
Loading 0:  85%|████████▍ | 307/363 [00:07<00:02, 22.25it/s]
Loading 0:  86%|████████▌ | 312/363 [00:07<00:02, 24.58it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 33.23it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.01it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 35.92it/s]
Loading 0:  93%|█████████▎| 338/363 [00:08<00:00, 41.84it/s]
Loading 0:  95%|█████████▍| 344/363 [00:08<00:00, 41.17it/s]
Loading 0:  96%|█████████▌| 349/363 [00:08<00:00, 40.80it/s]
Loading 0:  98%|█████████▊| 356/363 [00:08<00:00, 46.29it/s]
Loading 0: 100%|█████████▉| 362/363 [00:09<00:00, 44.42it/s]
                                                            
Job rica40325-filter-feedbackv3-2-v1-mkmlizer completed after 145.22s with status: succeeded
Stopping job with name rica40325-filter-feedbackv3-2-v1-mkmlizer
Pipeline stage MKMLizer completed in 145.79s
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 rica40325-filter-feedbackv3-2-v1
Waiting for inference service rica40325-filter-feedbackv3-2-v1 to be ready
Inference service rica40325-filter-feedbackv3-2-v1 ready after 150.72391963005066s
Pipeline stage MKMLDeployer completed in 151.30s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.7507312297821045s
Received healthy response to inference request in 1.6258673667907715s
Received healthy response to inference request in 1.8788704872131348s
Received healthy response to inference request in 1.7260239124298096s
Received healthy response to inference request in 1.5556731224060059s
5 requests
0 failed requests
5th percentile: 1.569711971282959
10th percentile: 1.5837508201599122
20th percentile: 1.6118285179138183
30th percentile: 1.6458986759185792
40th percentile: 1.6859612941741944
50th percentile: 1.7260239124298096
60th percentile: 1.7871625423431396
70th percentile: 1.8483011722564697
80th percentile: 2.053242635726929
90th percentile: 2.4019869327545167
95th percentile: 2.5763590812683104
99th percentile: 2.7158568000793455
mean time: 1.9074332237243652
Pipeline stage StressChecker completed in 11.07s
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 0.82s
Shutdown handler de-registered
rica40325-filter-feedbackv3-2_v1 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
%s, retrying in %s seconds...
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 7741.19s
Shutdown handler de-registered
rica40325-filter-feedbackv3-2_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-feedbackv3-2_v1 status is now torndown due to DeploymentManager action