developer_uid: rica40325
submission_id: rica40325-filter-feedbackv3_v1
model_name: rica40325-filter-feedbackv3_v1
model_group: rica40325/filter-feedbac
status: torndown
timestamp: 2025-06-24T11:23:09+00:00
num_battles: 8739
num_wins: 4194
celo_rating: 1272.32
family_friendly_score: 0.5726
family_friendly_standard_error: 0.006996130930735931
submission_type: basic
model_repo: rica40325/filter-feedbackv3
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': 0.5923147383564513, 'latency_mean': 1.6881771278381348, 'latency_p50': 1.6984063386917114, 'latency_p90': 1.851989984512329}, {'batch_size': 3, 'throughput': 1.0564564294055767, 'latency_mean': 2.830328245162964, 'latency_p50': 2.8546382188796997, 'latency_p90': 3.0832259893417358}, {'batch_size': 5, 'throughput': 1.284465329964789, 'latency_mean': 3.8751346325874327, 'latency_p50': 3.8515583276748657, 'latency_p90': 4.32672655582428}, {'batch_size': 6, 'throughput': 1.3388074331438364, 'latency_mean': 4.453692911863327, 'latency_p50': 4.4598482847213745, 'latency_p90': 4.958812522888183}, {'batch_size': 8, 'throughput': 1.4072594140580075, 'latency_mean': 5.6487165808677675, 'latency_p50': 5.661367058753967, 'latency_p90': 6.391954445838929}, {'batch_size': 10, 'throughput': 1.431927963307365, 'latency_mean': 6.926728751659393, 'latency_p50': 6.932467699050903, 'latency_p90': 7.9001609802246096}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: rica40325-filter-feedbackv3_v1
is_internal_developer: False
language_model: rica40325/filter-feedbackv3
model_size: 13B
ranking_group: single
throughput_3p7s: 1.26
us_pacific_date: 2025-06-24
win_ratio: 0.4799176107106076
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-v1-mkmlizer
Waiting for job on rica40325-filter-feedbackv3-v1-mkmlizer to finish
rica40325-filter-feedbackv3-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rica40325-filter-feedbackv3-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  belonging to:                                                      ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rica40325-filter-feedbackv3-v1-mkmlizer: ║                                                                     ║
rica40325-filter-feedbackv3-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rica40325-filter-feedbackv3-v1-mkmlizer: Downloaded to shared memory in 41.073s
rica40325-filter-feedbackv3-v1-mkmlizer: Checking if rica40325/filter-feedbackv3 already exists in ChaiML
rica40325-filter-feedbackv3-v1-mkmlizer: Creating repo ChaiML/filter-feedbackv3 and uploading /tmp/tmpi2g7nais to it
rica40325-filter-feedbackv3-v1-mkmlizer: 
  0%|          | 0/6 [00:00<?, ?it/s]
 17%|█▋        | 1/6 [00:08<00:41,  8.22s/it]
 33%|███▎      | 2/6 [00:12<00:23,  5.79s/it]
 50%|█████     | 3/6 [00:16<00:15,  5.16s/it]
 67%|██████▋   | 4/6 [00:20<00:09,  4.63s/it]
 83%|████████▎ | 5/6 [00:24<00:04,  4.44s/it]
100%|██████████| 6/6 [00:25<00:00,  3.30s/it]
100%|██████████| 6/6 [00:25<00:00,  4.29s/it]
rica40325-filter-feedbackv3-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpi2g7nais, device:0
rica40325-filter-feedbackv3-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rica40325-filter-feedbackv3-v1-mkmlizer: quantized model in 31.069s
rica40325-filter-feedbackv3-v1-mkmlizer: Processed model rica40325/filter-feedbackv3 in 123.313s
rica40325-filter-feedbackv3-v1-mkmlizer: creating bucket guanaco-mkml-models
rica40325-filter-feedbackv3-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rica40325-filter-feedbackv3-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1
rica40325-filter-feedbackv3-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1/config.json
rica40325-filter-feedbackv3-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1/special_tokens_map.json
rica40325-filter-feedbackv3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1/tokenizer_config.json
rica40325-filter-feedbackv3-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1/tokenizer.json
rica40325-filter-feedbackv3-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rica40325-filter-feedbackv3-v1/flywheel_model.0.safetensors
rica40325-filter-feedbackv3-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:10, 33.41it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:06, 52.64it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:07, 45.36it/s]
Loading 0:   7%|▋         | 24/363 [00:00<00:07, 44.16it/s]
Loading 0:   9%|▊         | 31/363 [00:00<00:06, 49.98it/s]
Loading 0:  10%|█         | 37/363 [00:00<00:07, 45.96it/s]
Loading 0:  12%|█▏        | 42/363 [00:00<00:07, 44.62it/s]
Loading 0:  13%|█▎        | 49/363 [00:01<00:06, 49.67it/s]
Loading 0:  15%|█▌        | 55/363 [00:01<00:06, 46.11it/s]
Loading 0:  17%|█▋        | 61/363 [00:01<00:08, 36.13it/s]
Loading 0:  18%|█▊        | 66/363 [00:01<00:08, 37.03it/s]
Loading 0:  20%|█▉        | 72/363 [00:01<00:07, 40.89it/s]
Loading 0:  21%|██▏       | 78/363 [00:01<00:07, 39.90it/s]
Loading 0:  23%|██▎       | 83/363 [00:01<00:06, 40.18it/s]
Loading 0:  25%|██▍       | 89/363 [00:02<00:06, 43.97it/s]
Loading 0:  26%|██▌       | 94/363 [00:02<00:06, 43.67it/s]
Loading 0:  27%|██▋       | 99/363 [00:02<00:05, 44.11it/s]
Loading 0:  29%|██▉       | 105/363 [00:02<00:06, 41.61it/s]
Loading 0:  30%|███       | 110/363 [00:02<00:05, 43.14it/s]
Loading 0:  32%|███▏      | 115/363 [00:02<00:05, 43.03it/s]
Loading 0:  33%|███▎      | 120/363 [00:02<00:05, 40.77it/s]
Loading 0:  34%|███▍      | 125/363 [00:02<00:05, 42.50it/s]
Loading 0:  36%|███▌      | 130/363 [00:03<00:05, 41.88it/s]
Loading 0:  37%|███▋      | 135/363 [00:03<00:05, 41.99it/s]
Loading 0:  39%|███▊      | 140/363 [00:03<00:05, 43.58it/s]
Loading 0:  40%|███▉      | 145/363 [00:03<00:07, 27.45it/s]
Loading 0:  41%|████      | 149/363 [00:03<00:07, 28.33it/s]
Loading 0:  43%|████▎     | 156/363 [00:03<00:05, 35.75it/s]
Loading 0:  44%|████▍     | 161/363 [00:03<00:05, 36.97it/s]
Loading 0:  46%|████▌     | 166/363 [00:04<00:05, 38.58it/s]
Loading 0:  47%|████▋     | 171/363 [00:04<00:04, 40.93it/s]
Loading 0:  48%|████▊     | 176/363 [00:04<00:05, 34.82it/s]
Loading 0:  50%|█████     | 183/363 [00:04<00:04, 41.93it/s]
Loading 0:  52%|█████▏    | 188/363 [00:04<00:04, 42.02it/s]
Loading 0:  53%|█████▎    | 193/363 [00:04<00:03, 42.81it/s]
Loading 0:  55%|█████▍    | 199/363 [00:04<00:04, 40.72it/s]
Loading 0:  56%|█████▌    | 204/363 [00:05<00:03, 39.97it/s]
Loading 0:  58%|█████▊    | 210/363 [00:05<00:03, 43.82it/s]
Loading 0:  59%|█████▉    | 215/363 [00:05<00:03, 43.41it/s]
Loading 0:  61%|██████    | 220/363 [00:05<00:03, 44.41it/s]
Loading 0:  62%|██████▏   | 225/363 [00:05<00:05, 27.49it/s]
Loading 0:  63%|██████▎   | 230/363 [00:05<00:04, 30.05it/s]
Loading 0:  65%|██████▌   | 237/363 [00:05<00:03, 37.24it/s]
Loading 0:  67%|██████▋   | 242/363 [00:06<00:03, 38.53it/s]
Loading 0:  68%|██████▊   | 247/363 [00:06<00:02, 39.54it/s]
Loading 0:  70%|██████▉   | 253/363 [00:06<00:02, 39.08it/s]
Loading 0:  71%|███████   | 258/363 [00:06<00:02, 38.77it/s]
Loading 0:  73%|███████▎  | 264/363 [00:06<00:02, 42.25it/s]
Loading 0:  74%|███████▍  | 269/363 [00:06<00:02, 42.35it/s]
Loading 0:  75%|███████▌  | 274/363 [00:06<00:02, 43.00it/s]
Loading 0:  77%|███████▋  | 279/363 [00:06<00:01, 44.37it/s]
Loading 0:  78%|███████▊  | 284/363 [00:07<00:02, 36.43it/s]
Loading 0:  80%|████████  | 291/363 [00:07<00:01, 43.35it/s]
Loading 0:  82%|████████▏ | 296/363 [00:07<00:01, 43.45it/s]
Loading 0:  83%|████████▎ | 301/363 [00:07<00:01, 43.97it/s]
Loading 0:  84%|████████▍ | 306/363 [00:07<00:02, 24.25it/s]
Loading 0:  85%|████████▌ | 310/363 [00:08<00:02, 25.56it/s]
Loading 0:  87%|████████▋ | 314/363 [00:08<00:01, 28.12it/s]
Loading 0:  88%|████████▊ | 320/363 [00:08<00:01, 34.17it/s]
Loading 0:  90%|████████▉ | 326/363 [00:08<00:01, 35.89it/s]
Loading 0:  91%|█████████ | 331/363 [00:08<00:00, 37.46it/s]
Loading 0:  93%|█████████▎| 337/363 [00:08<00:00, 42.28it/s]
Loading 0:  94%|█████████▍| 342/363 [00:08<00:00, 42.16it/s]
Loading 0:  96%|█████████▌| 347/363 [00:08<00:00, 43.13it/s]
Loading 0:  97%|█████████▋| 352/363 [00:08<00:00, 44.89it/s]
Loading 0:  98%|█████████▊| 357/363 [00:09<00:00, 38.18it/s]
                                                            

Job rica40325-filter-feedbackv3-v1-mkmlizer completed after 145.86s with status: succeeded
Stopping job with name rica40325-filter-feedbackv3-v1-mkmlizer
Pipeline stage MKMLizer completed in 146.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.42s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rica40325-filter-feedbackv3-v1
Waiting for inference service rica40325-filter-feedbackv3-v1 to be ready
Failed to get response for submission chaiml-giyu-disabled-hu_13897_v2: ('http://chaiml-giyu-disabled-hu-13897-v2-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Inference service rica40325-filter-feedbackv3-v1 ready after 130.63499689102173s
Pipeline stage MKMLDeployer completed in 131.39s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4194772243499756s
Received healthy response to inference request in 1.8184373378753662s
Received healthy response to inference request in 2.1514828205108643s
Received healthy response to inference request in 1.8222599029541016s
Received healthy response to inference request in 1.6653156280517578s
5 requests
0 failed requests
5th percentile: 1.6959399700164794
10th percentile: 1.726564311981201
20th percentile: 1.7878129959106446
30th percentile: 1.8192018508911132
40th percentile: 1.8207308769226074
50th percentile: 1.8222599029541016
60th percentile: 1.9539490699768067
70th percentile: 2.0856382369995115
80th percentile: 2.2050817012786865
90th percentile: 2.312279462814331
95th percentile: 2.3658783435821533
99th percentile: 2.408757448196411
mean time: 1.9753945827484132
Pipeline stage StressChecker completed in 11.30s
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 0.76s
Shutdown handler de-registered
rica40325-filter-feedbackv3_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
Pipeline stage OfflineFamilyFriendlyScorer completed in 4273.37s
Shutdown handler de-registered
rica40325-filter-feedbackv3_v1 status is now inactive due to auto deactivation removed underperforming models
rica40325-filter-feedbackv3_v1 status is now torndown due to DeploymentManager action