developer_uid: rica40325
submission_id: rica40325-feedbackv4-filter_v1
model_name: rica40325-feedbackv4-filter_v1
model_group: rica40325/feedbackv4_fil
status: torndown
timestamp: 2025-07-15T18:04:58+00:00
num_battles: 11456
num_wins: 5495
celo_rating: 1279.52
family_friendly_score: 0.5708
family_friendly_standard_error: 0.006999819426242366
submission_type: basic
model_repo: rica40325/feedbackv4_filter
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': 0.5935569882697505, 'latency_mean': 1.6846524238586427, 'latency_p50': 1.6905356645584106, 'latency_p90': 1.8558335065841676}, {'batch_size': 3, 'throughput': 1.0573439107151348, 'latency_mean': 2.831928894519806, 'latency_p50': 2.8401800394058228, 'latency_p90': 3.1484896659851076}, {'batch_size': 5, 'throughput': 1.2648275581474084, 'latency_mean': 3.9333789098262786, 'latency_p50': 3.9243937730789185, 'latency_p90': 4.409088373184204}, {'batch_size': 6, 'throughput': 1.3171082445818156, 'latency_mean': 4.518050255775452, 'latency_p50': 4.52446722984314, 'latency_p90': 5.104549980163574}, {'batch_size': 8, 'throughput': 1.368940084944311, 'latency_mean': 5.808618748188019, 'latency_p50': 5.8358190059661865, 'latency_p90': 6.580887722969055}, {'batch_size': 10, 'throughput': 1.4183298827001591, 'latency_mean': 7.003302326202393, 'latency_p50': 7.038915991783142, 'latency_p90': 7.771187782287598}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-feedbackv4-filter_v1
is_internal_developer: False
language_model: rica40325/feedbackv4_filter
model_size: 13B
ranking_group: single
throughput_3p7s: 1.24
us_pacific_date: 2025-07-15
win_ratio: 0.479661312849162
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-feedbackv4-filter-v1-mkmlizer
Waiting for job on rica40325-feedbackv4-filter-v1-mkmlizer to finish
rica40325-feedbackv4-filter-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-feedbackv4-filter-v1-mkmlizer: ║                                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║                                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║                                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║                                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-feedbackv4-filter-v1-mkmlizer: ║                                                                     ║
rica40325-feedbackv4-filter-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-feedbackv4-filter-v1-mkmlizer: Downloaded to shared memory in 34.764s
rica40325-feedbackv4-filter-v1-mkmlizer: Checking if rica40325/feedbackv4_filter already exists in ChaiML
rica40325-feedbackv4-filter-v1-mkmlizer: Creating repo ChaiML/feedbackv4_filter and uploading /tmp/tmplgfvtj7b to it
rica40325-feedbackv4-filter-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:04<00:22,  4.43s/it]
 33%|███▎      | 2/6 [00:09<00:20,  5.04s/it]
 50%|█████     | 3/6 [00:14<00:14,  4.75s/it]
 67%|██████▋   | 4/6 [00:18<00:09,  4.57s/it]
 83%|████████▎ | 5/6 [00:22<00:04,  4.34s/it]
100%|██████████| 6/6 [00:23<00:00,  3.31s/it]
100%|██████████| 6/6 [00:23<00:00,  3.98s/it]
rica40325-feedbackv4-filter-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmplgfvtj7b, device:0
rica40325-feedbackv4-filter-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-feedbackv4-filter-v1-mkmlizer: quantized model in 31.062s
rica40325-feedbackv4-filter-v1-mkmlizer: Processed model rica40325/feedbackv4_filter in 116.012s
rica40325-feedbackv4-filter-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-feedbackv4-filter-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-feedbackv4-filter-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia
rica40325-feedbackv4-filter-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia/config.json
rica40325-feedbackv4-filter-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia/special_tokens_map.json
rica40325-feedbackv4-filter-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia/tokenizer_config.json
rica40325-feedbackv4-filter-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia/tokenizer.json
rica40325-feedbackv4-filter-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-feedbackv4-filter-v1/nvidia/flywheel_model.0.safetensors
rica40325-feedbackv4-filter-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.11it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.13it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.36it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 43.71it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.24it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 46.02it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.69it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.83it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.51it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 35.52it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 36.72it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.88it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 40.06it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:07, 39.84it/s]
Loading 0:  25%|██▍       | 90/363 [00:02<00:06, 44.97it/s]
Loading 0:  26%|██▋       | 96/363 [00:02<00:06, 42.78it/s]
Loading 0:  28%|██▊       | 101/363 [00:02<00:06, 41.72it/s]
Loading 0:  29%|██▉       | 106/363 [00:02<00:05, 43.09it/s]
Loading 0:  31%|███       | 112/363 [00:02<00:05, 44.42it/s]
Loading 0:  32%|███▏      | 117/363 [00:02<00:05, 42.19it/s]
Loading 0:  34%|███▎      | 122/363 [00:02<00:05, 43.94it/s]
Loading 0:  35%|███▍      | 127/363 [00:03<00:06, 37.50it/s]
Loading 0:  37%|███▋      | 134/363 [00:03<00:05, 44.67it/s]
Loading 0:  38%|███▊      | 139/363 [00:03<00:05, 44.42it/s]
Loading 0:  40%|███▉      | 144/363 [00:03<00:07, 28.66it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:06, 31.12it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 37.46it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 38.80it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:04, 40.48it/s]
Loading 0:  47%|████▋     | 172/363 [00:04<00:04, 39.92it/s]
Loading 0:  49%|████▉     | 177/363 [00:04<00:04, 39.11it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 43.55it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:03, 44.02it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 44.36it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:03, 41.93it/s]
Loading 0:  56%|█████▌    | 204/363 [00:04<00:03, 41.00it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 45.25it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 44.48it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 45.84it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:04, 28.94it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.74it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 38.38it/s]
Loading 0:  67%|██████▋   | 242/363 [00:05<00:03, 40.20it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 41.87it/s]
Loading 0:  69%|██████▉   | 252/363 [00:06<00:02, 43.78it/s]
Loading 0:  71%|███████   | 257/363 [00:06<00:02, 37.12it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 44.60it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 44.71it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.75it/s]
Loading 0:  77%|███████▋  | 280/363 [00:06<00:01, 41.80it/s]
Loading 0:  79%|███████▊  | 285/363 [00:06<00:01, 41.41it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 45.54it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 44.74it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 45.97it/s]
Loading 0:  84%|████████▍ | 306/363 [00:07<00:02, 24.69it/s]
Loading 0:  85%|████████▌ | 310/363 [00:07<00:02, 25.94it/s]
Loading 0:  87%|████████▋ | 315/363 [00:07<00:01, 30.14it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.11it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 36.09it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 37.48it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.68it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 43.32it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 43.94it/s]
Loading 0:  97%|█████████▋| 353/363 [00:08<00:00, 41.94it/s]
Loading 0:  99%|█████████▊| 358/363 [00:08<00:00, 41.69it/s]
                                                            

Job rica40325-feedbackv4-filter-v1-mkmlizer completed after 149.06s with status: succeeded
Stopping job with name rica40325-feedbackv4-filter-v1-mkmlizer
Pipeline stage MKMLizer completed in 149.92s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-feedbackv4-filter-v1
Waiting for inference service rica40325-feedbackv4-filter-v1 to be ready
Inference service rica40325-feedbackv4-filter-v1 ready after 251.5000970363617s
Pipeline stage MKMLDeployer completed in 252.08s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5999584197998047s
Received healthy response to inference request in 1.610994815826416s
Received healthy response to inference request in 1.6483571529388428s
Received healthy response to inference request in 1.684194564819336s
Received healthy response to inference request in 1.8879027366638184s
5 requests
0 failed requests
5th percentile: 1.6184672832489013
10th percentile: 1.6259397506713866
20th percentile: 1.6408846855163575
30th percentile: 1.6555246353149413
40th percentile: 1.6698596000671386
50th percentile: 1.684194564819336
60th percentile: 1.7656778335571288
70th percentile: 1.847161102294922
80th percentile: 2.030313873291016
90th percentile: 2.3151361465454103
95th percentile: 2.457547283172607
99th percentile: 2.571476192474365
mean time: 1.8862815380096436
Pipeline stage StressChecker completed in 11.50s
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 0.93s
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 0.72s
Shutdown handler de-registered
rica40325-feedbackv4-filter_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 4465.71s
Shutdown handler de-registered
rica40325-feedbackv4-filter_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-feedbackv4-filter_v1 status is now torndown due to DeploymentManager action
rica40325-feedbackv4-filter_v1 status is now torndown due to DeploymentManager action