developer_uid: rica40325
submission_id: rica40325-filter65k-v6-100_v1
model_name: rica40325-filter65k-v6-100_v1
model_group: rica40325/filter65k-v6-1
status: torndown
timestamp: 2025-06-21T04:38:13+00:00
num_battles: 9696
num_wins: 4570
celo_rating: 1267.86
family_friendly_score: 0.5654
family_friendly_standard_error: 0.007010318680345424
submission_type: basic
model_repo: rica40325/filter65k-v6-100
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': 0.5953790396101232, 'latency_mean': 1.679478381872177, 'latency_p50': 1.680463433265686, 'latency_p90': 1.8508296489715577}, {'batch_size': 3, 'throughput': 1.0618765533518482, 'latency_mean': 2.814410675764084, 'latency_p50': 2.8157745599746704, 'latency_p90': 3.1563188791275025}, {'batch_size': 5, 'throughput': 1.3014492604054566, 'latency_mean': 3.8251314580440523, 'latency_p50': 3.828023314476013, 'latency_p90': 4.229801416397095}, {'batch_size': 6, 'throughput': 1.3677588301110701, 'latency_mean': 4.362013845443726, 'latency_p50': 4.346398949623108, 'latency_p90': 4.830417895317078}, {'batch_size': 8, 'throughput': 1.4246872172900145, 'latency_mean': 5.574307457208634, 'latency_p50': 5.577343940734863, 'latency_p90': 6.301927638053894}, {'batch_size': 10, 'throughput': 1.454734905103827, 'latency_mean': 6.820823975801468, 'latency_p50': 6.835426449775696, 'latency_p90': 7.6068687915802}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-filter65k-v6-100_v1
is_internal_developer: False
language_model: rica40325/filter65k-v6-100
model_size: 13B
ranking_group: single
throughput_3p7s: 1.28
us_pacific_date: 2025-06-20
win_ratio: 0.4713283828382838
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-filter65k-v6-100-v1-mkmlizer
Waiting for job on rica40325-filter65k-v6-100-v1-mkmlizer to finish
rica40325-filter65k-v6-100-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter65k-v6-100-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter65k-v6-100-v1-mkmlizer: ║                                                                     ║
rica40325-filter65k-v6-100-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter65k-v6-100-v1-mkmlizer: Downloaded to shared memory in 41.943s
rica40325-filter65k-v6-100-v1-mkmlizer: Checking if rica40325/filter65k-v6-100 already exists in ChaiML
rica40325-filter65k-v6-100-v1-mkmlizer: Creating repo ChaiML/filter65k-v6-100 and uploading /tmp/tmpv7m42kz2 to it
rica40325-filter65k-v6-100-v1-mkmlizer: 
  0%|          | 0/7 [00:00<?, ?it/s]
 14%|█▍        | 1/7 [00:03<00:21,  3.64s/it]
 29%|██▊       | 2/7 [00:12<00:32,  6.45s/it]
 43%|████▎     | 3/7 [00:18<00:26,  6.63s/it]
 57%|█████▋    | 4/7 [00:26<00:20,  7.00s/it]
 71%|███████▏  | 5/7 [00:30<00:11,  5.80s/it]
 86%|████████▌ | 6/7 [00:31<00:04,  4.25s/it]
100%|██████████| 7/7 [00:31<00:00,  3.06s/it]
100%|██████████| 7/7 [00:31<00:00,  4.57s/it]
rica40325-filter65k-v6-100-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpv7m42kz2, device:0
rica40325-filter65k-v6-100-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter65k-v6-100-v1-mkmlizer: quantized model in 31.129s
rica40325-filter65k-v6-100-v1-mkmlizer: Processed model rica40325/filter65k-v6-100 in 130.942s
rica40325-filter65k-v6-100-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter65k-v6-100-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter65k-v6-100-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1
rica40325-filter65k-v6-100-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1/config.json
rica40325-filter65k-v6-100-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1/special_tokens_map.json
rica40325-filter65k-v6-100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1/tokenizer_config.json
rica40325-filter65k-v6-100-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1/tokenizer.json
rica40325-filter65k-v6-100-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter65k-v6-100-v1/flywheel_model.0.safetensors
rica40325-filter65k-v6-100-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:12, 27.61it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 45.41it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 46.84it/s]
Loading 0:   6%|▋         | 23/363 [00:00<00:09, 36.42it/s]
Loading 0:   8%|▊         | 30/363 [00:00<00:07, 45.27it/s]
Loading 0:  10%|▉         | 36/363 [00:00<00:07, 45.68it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:08, 37.23it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:07, 44.63it/s]
Loading 0:  15%|█▍        | 54/363 [00:01<00:06, 45.54it/s]
Loading 0:  16%|█▋        | 59/363 [00:01<00:06, 46.32it/s]
Loading 0:  18%|█▊        | 64/363 [00:01<00:12, 24.46it/s]
Loading 0:  20%|█▉        | 71/363 [00:01<00:09, 31.73it/s]
Loading 0:  21%|██        | 76/363 [00:02<00:08, 33.46it/s]
Loading 0:  22%|██▏       | 81/363 [00:02<00:07, 35.32it/s]
Loading 0:  24%|██▎       | 86/363 [00:02<00:07, 37.21it/s]
Loading 0:  25%|██▌       | 91/363 [00:02<00:08, 31.74it/s]
Loading 0:  27%|██▋       | 98/363 [00:02<00:06, 38.78it/s]
Loading 0:  28%|██▊       | 103/363 [00:02<00:06, 39.09it/s]
Loading 0:  30%|██▉       | 108/363 [00:02<00:06, 41.37it/s]
Loading 0:  31%|███       | 113/363 [00:03<00:06, 35.88it/s]
Loading 0:  33%|███▎      | 118/363 [00:03<00:06, 35.74it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 42.28it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.82it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 40.76it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.38it/s]
Loading 0:  40%|███▉      | 145/363 [00:04<00:08, 24.68it/s]
Loading 0:  41%|████      | 149/363 [00:04<00:08, 25.23it/s]
Loading 0:  42%|████▏     | 154/363 [00:04<00:07, 29.58it/s]
Loading 0:  44%|████▎     | 158/363 [00:04<00:07, 28.61it/s]
Loading 0:  45%|████▌     | 164/363 [00:04<00:05, 35.19it/s]
Loading 0:  47%|████▋     | 169/363 [00:04<00:05, 34.77it/s]
Loading 0:  48%|████▊     | 174/363 [00:04<00:05, 36.96it/s]
Loading 0:  49%|████▉     | 179/363 [00:04<00:04, 37.35it/s]
Loading 0:  50%|█████     | 183/363 [00:05<00:04, 37.65it/s]
Loading 0:  52%|█████▏    | 187/363 [00:05<00:04, 36.50it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.65it/s]
Loading 0:  54%|█████▍    | 196/363 [00:05<00:04, 37.04it/s]
Loading 0:  55%|█████▌    | 201/363 [00:05<00:04, 39.49it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 39.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 37.18it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 35.42it/s]
Loading 0:  60%|██████    | 218/363 [00:06<00:04, 35.45it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 25.61it/s]
Loading 0:  62%|██████▏   | 226/363 [00:06<00:05, 25.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:06<00:04, 27.21it/s]
Loading 0:  65%|██████▌   | 237/363 [00:06<00:03, 35.53it/s]
Loading 0:  66%|██████▋   | 241/363 [00:06<00:03, 35.33it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 38.13it/s]
Loading 0:  69%|██████▉   | 251/363 [00:07<00:02, 38.73it/s]
Loading 0:  71%|███████   | 256/363 [00:07<00:02, 38.59it/s]
Loading 0:  72%|███████▏  | 260/363 [00:07<00:02, 38.87it/s]
Loading 0:  73%|███████▎  | 265/363 [00:07<00:02, 39.87it/s]
Loading 0:  74%|███████▍  | 270/363 [00:07<00:02, 42.00it/s]
Loading 0:  76%|███████▌  | 275/363 [00:07<00:02, 34.55it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:01, 41.82it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 41.44it/s]
Loading 0:  80%|████████  | 292/363 [00:08<00:01, 39.55it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 41.39it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 42.80it/s]
Loading 0:  85%|████████▍ | 307/363 [00:08<00:02, 20.41it/s]
Loading 0:  86%|████████▌ | 312/363 [00:08<00:02, 22.89it/s]
Loading 0:  88%|████████▊ | 320/363 [00:09<00:01, 31.14it/s]
Loading 0:  90%|████████▉ | 325/363 [00:09<00:01, 34.52it/s]
Loading 0:  91%|█████████ | 330/363 [00:09<00:01, 31.35it/s]
Loading 0:  93%|█████████▎| 337/363 [00:09<00:00, 38.65it/s]
Loading 0:  94%|█████████▍| 342/363 [00:09<00:00, 39.51it/s]
Loading 0:  96%|█████████▌| 347/363 [00:09<00:00, 40.82it/s]
Loading 0:  97%|█████████▋| 352/363 [00:09<00:00, 42.46it/s]
Loading 0:  98%|█████████▊| 357/363 [00:10<00:00, 34.40it/s]
                                                            

Job rica40325-filter65k-v6-100-v1-mkmlizer completed after 155.84s with status: succeeded
Stopping job with name rica40325-filter65k-v6-100-v1-mkmlizer
Pipeline stage MKMLizer completed in 156.34s
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-filter65k-v6-100-v1
Waiting for inference service rica40325-filter65k-v6-100-v1 to be ready
Inference service rica40325-filter65k-v6-100-v1 ready after 110.40964865684509s
Pipeline stage MKMLDeployer completed in 111.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.202077627182007s
Received healthy response to inference request in 2.022681474685669s
Received healthy response to inference request in 1.8521692752838135s
Received healthy response to inference request in 1.6608633995056152s
Received healthy response to inference request in 1.5706722736358643s
5 requests
0 failed requests
5th percentile: 1.5887104988098144
10th percentile: 1.6067487239837646
20th percentile: 1.642825174331665
30th percentile: 1.6991245746612549
40th percentile: 1.7756469249725342
50th percentile: 1.8521692752838135
60th percentile: 1.9203741550445557
70th percentile: 1.9885790348052979
80th percentile: 2.0585607051849366
90th percentile: 2.1303191661834715
95th percentile: 2.166198396682739
99th percentile: 2.1949017810821534
mean time: 1.8616928100585937
Pipeline stage StressChecker completed in 10.67s
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 0.68s
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 0.65s
Shutdown handler de-registered
rica40325-filter65k-v6-100_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 3131.66s
Shutdown handler de-registered
rica40325-filter65k-v6-100_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter65k-v6-100_v1 status is now torndown due to DeploymentManager action