rica40325-filterv3

developer_uid: rica40325

submission_id: rica40325-filterv3_v1

model_name: rica40325-filter-16a4b-v1_v1

model_group: rica40325/filterv3

status: torndown

timestamp: 2025-04-23T02:44:13+00:00

num_battles: 5972

num_wins: 2921

celo_rating: 1273.72

family_friendly_score: 0.608

family_friendly_standard_error: 0.006904143683325254

submission_type: basic

model_repo: rica40325/filterv3

model_architecture: MistralForCausalLM

model_num_parameters: 12772070400.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

latencies: [{'batch_size': 1, 'throughput': 0.602844787531116, 'latency_mean': 1.658731141090393, 'latency_p50': 1.6596590280532837, 'latency_p90': 1.8282819747924806}, {'batch_size': 3, 'throughput': 1.1213844461264912, 'latency_mean': 2.665455094575882, 'latency_p50': 2.6612266302108765, 'latency_p90': 2.9177811622619627}, {'batch_size': 5, 'throughput': 1.3616740227797495, 'latency_mean': 3.6575895416736603, 'latency_p50': 3.6446073055267334, 'latency_p90': 4.03023374080658}, {'batch_size': 6, 'throughput': 1.4425000396495398, 'latency_mean': 4.137514743804932, 'latency_p50': 4.118344187736511, 'latency_p90': 4.676629948616028}, {'batch_size': 8, 'throughput': 1.503169978648864, 'latency_mean': 5.277992463111877, 'latency_p50': 5.289721846580505, 'latency_p90': 6.0021364212036135}, {'batch_size': 10, 'throughput': 1.5445721302123552, 'latency_mean': 6.427381783723831, 'latency_p50': 6.447277545928955, 'latency_p90': 7.31404492855072}]

gpu_counts: {'NVIDIA RTX A5000': 1}

display_name: rica40325-filter-16a4b-v1_v1

is_internal_developer: False

language_model: rica40325/filterv3

model_size: 13B

ranking_group: single

throughput_3p7s: 1.38

us_pacific_date: 2025-04-22

win_ratio: 0.4891158740790355

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-filterv3-v1-mkmlizer
Waiting for job on rica40325-filterv3-v1-mkmlizer to finish
rica40325-filterv3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filterv3-v1-mkmlizer: ║     _____            __           __                                ║
rica40325-filterv3-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rica40325-filterv3-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rica40325-filterv3-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rica40325-filterv3-v1-mkmlizer: ║       /___/                                                         ║
rica40325-filterv3-v1-mkmlizer: ║                                                                     ║
rica40325-filterv3-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rica40325-filterv3-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rica40325-filterv3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filterv3-v1-mkmlizer: ║                                                                     ║
rica40325-filterv3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filterv3-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filterv3-v1-mkmlizer: ║                                                                     ║
rica40325-filterv3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filterv3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filterv3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filterv3-v1-mkmlizer: ║                                                                     ║
rica40325-filterv3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filterv3-v1-mkmlizer: Downloaded to shared memory in 38.443s
rica40325-filterv3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmporxwl0lp, device:0
rica40325-filterv3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filterv3-v1-mkmlizer: quantized model in 37.832s
rica40325-filterv3-v1-mkmlizer: Processed model rica40325/filterv3 in 76.275s
rica40325-filterv3-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filterv3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filterv3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filterv3-v1
rica40325-filterv3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filterv3-v1/config.json
rica40325-filterv3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filterv3-v1/special_tokens_map.json
rica40325-filterv3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filterv3-v1/tokenizer_config.json
rica40325-filterv3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filterv3-v1/tokenizer.json
rica40325-filterv3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filterv3-v1/flywheel_model.0.safetensors
rica40325-filterv3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:13, 26.06it/s]
Loading 0:   3%|▎         | 12/363 [00:00<00:07, 44.69it/s]
Loading 0:   5%|▍         | 18/363 [00:00<00:07, 47.09it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:08, 39.52it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:07, 45.27it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 42.19it/s]
Loading 0:  12%|█▏        | 42/363 [00:01<00:07, 41.02it/s]
Loading 0:  13%|█▎        | 48/363 [00:01<00:06, 45.44it/s]
Loading 0:  15%|█▍        | 53/363 [00:01<00:06, 44.85it/s]
Loading 0:  16%|█▌        | 58/363 [00:01<00:06, 46.17it/s]
Loading 0:  17%|█▋        | 63/363 [00:01<00:09, 31.09it/s]
Loading 0:  18%|█▊        | 67/363 [00:01<00:09, 32.52it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:08, 35.31it/s]
Loading 0:  21%|██        | 77/363 [00:01<00:07, 38.31it/s]
Loading 0:  23%|██▎       | 82/363 [00:02<00:08, 33.45it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 41.24it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 41.46it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:06, 41.98it/s]
Loading 0:  29%|██▊       | 104/363 [00:02<00:05, 43.49it/s]
Loading 0:  30%|███       | 109/363 [00:02<00:05, 45.08it/s]
Loading 0:  31%|███▏      | 114/363 [00:02<00:06, 37.58it/s]
Loading 0:  33%|███▎      | 119/363 [00:03<00:06, 37.31it/s]
Loading 0:  34%|███▍      | 125/363 [00:03<00:05, 40.89it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 40.89it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.18it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 42.99it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.34it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 27.85it/s]
Loading 0:  43%|████▎     | 156/363 [00:04<00:05, 34.74it/s]
Loading 0:  44%|████▍     | 161/363 [00:04<00:05, 35.83it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 37.09it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 38.65it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:06, 30.82it/s]
Loading 0:  50%|████▉     | 181/363 [00:04<00:05, 33.79it/s]
Loading 0:  51%|█████     | 185/363 [00:04<00:05, 32.03it/s]
Loading 0:  53%|█████▎    | 192/363 [00:05<00:04, 38.57it/s]
Loading 0:  54%|█████▍    | 197/363 [00:05<00:04, 38.78it/s]
Loading 0:  56%|█████▌    | 202/363 [00:05<00:04, 38.27it/s]
Loading 0:  57%|█████▋    | 206/363 [00:05<00:04, 38.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:04, 37.74it/s]
Loading 0:  59%|█████▉    | 214/363 [00:05<00:04, 35.60it/s]
Loading 0:  60%|██████    | 218/363 [00:05<00:04, 35.33it/s]
Loading 0:  61%|██████▏   | 223/363 [00:06<00:05, 26.50it/s]
Loading 0:  63%|██████▎   | 227/363 [00:06<00:04, 27.28it/s]
Loading 0:  64%|██████▎   | 231/363 [00:06<00:04, 27.07it/s]
Loading 0:  65%|██████▍   | 235/363 [00:06<00:04, 29.69it/s]
Loading 0:  66%|██████▌   | 239/363 [00:06<00:04, 28.63it/s]
Loading 0:  68%|██████▊   | 246/363 [00:06<00:03, 36.28it/s]
Loading 0:  69%|██████▉   | 250/363 [00:06<00:03, 35.10it/s]
Loading 0:  70%|███████   | 255/363 [00:06<00:02, 36.95it/s]
Loading 0:  71%|███████▏  | 259/363 [00:07<00:02, 35.55it/s]
Loading 0:  73%|███████▎  | 264/363 [00:07<00:02, 37.53it/s]
Loading 0:  74%|███████▍  | 268/363 [00:07<00:02, 36.14it/s]
Loading 0:  75%|███████▌  | 273/363 [00:07<00:02, 38.10it/s]
Loading 0:  76%|███████▋  | 277/363 [00:07<00:02, 36.74it/s]
Loading 0:  78%|███████▊  | 282/363 [00:07<00:02, 39.72it/s]
Loading 0:  79%|███████▉  | 287/363 [00:07<00:01, 40.04it/s]
Loading 0:  80%|████████  | 292/363 [00:07<00:01, 40.26it/s]
Loading 0:  82%|████████▏ | 297/363 [00:08<00:01, 41.73it/s]
Loading 0:  83%|████████▎ | 302/363 [00:08<00:01, 43.02it/s]
Loading 0:  85%|████████▍ | 307/363 [00:15<00:25,  2.24it/s]
Loading 0:  86%|████████▌ | 312/363 [00:15<00:16,  3.12it/s]
Loading 0:  88%|████████▊ | 319/363 [00:15<00:09,  4.87it/s]
Loading 0:  89%|████████▉ | 324/363 [00:15<00:06,  6.46it/s]
Loading 0:  91%|█████████ | 329/363 [00:15<00:03,  8.51it/s]
Loading 0:  92%|█████████▏| 334/363 [00:15<00:02, 11.15it/s]
Loading 0:  93%|█████████▎| 339/363 [00:16<00:01, 13.27it/s]
Loading 0:  95%|█████████▌| 346/363 [00:16<00:00, 18.80it/s]
Loading 0:  97%|█████████▋| 351/363 [00:16<00:00, 22.01it/s]
Loading 0:  98%|█████████▊| 356/363 [00:16<00:00, 25.25it/s]
Loading 0:  99%|█████████▉| 361/363 [00:16<00:00, 28.96it/s]
                                                            
Job rica40325-filterv3-v1-mkmlizer completed after 104.51s with status: succeeded
Stopping job with name rica40325-filterv3-v1-mkmlizer
Pipeline stage MKMLizer completed in 105.02s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.20s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-filterv3-v1
Waiting for inference service rica40325-filterv3-v1 to be ready
Inference service rica40325-filterv3-v1 ready after 130.7070186138153s
Pipeline stage MKMLDeployer completed in 131.26s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.548818349838257s
Received healthy response to inference request in 1.6148681640625s
Received healthy response to inference request in 1.8085026741027832s
Received healthy response to inference request in 1.6565871238708496s
Received healthy response to inference request in 1.7280311584472656s
5 requests
0 failed requests
5th percentile: 1.62321195602417
10th percentile: 1.6315557479858398
20th percentile: 1.6482433319091796
30th percentile: 1.6708759307861327
40th percentile: 1.6994535446166992
50th percentile: 1.7280311584472656
60th percentile: 1.7602197647094726
70th percentile: 1.7924083709716796
80th percentile: 1.956565809249878
90th percentile: 2.2526920795440675
95th percentile: 2.400755214691162
99th percentile: 2.519205722808838
mean time: 1.871361494064331
Pipeline stage StressChecker completed in 10.75s
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 0.76s
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 0.69s
Shutdown handler de-registered
rica40325-filterv3_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rica40325-filterv3-v1-profiler
Waiting for inference service rica40325-filterv3-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 2707.88s
Shutdown handler de-registered
rica40325-filterv3_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filterv3_v1 status is now torndown due to DeploymentManager action