rirv938-yautja-cp312-98_44860

developer_uid: rirv938

submission_id: rirv938-yautja-cp312-98_44860_v1

model_name: rirv938-yautja-cp312-98_44860_v1

model_group: rirv938/yautja_cp312_98f

status: torndown

timestamp: 2025-07-08T19:53:18+00:00

num_battles: 6419

num_wins: 3257

celo_rating: 1293.81

family_friendly_score: 0.5726

family_friendly_standard_error: 0.006996130930735931

submission_type: basic

model_repo: rirv938/yautja_cp312_98ff_b35_r1_reformat_high_quality_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5116708876262187, 'latency_mean': 1.9542860281467438, 'latency_p50': 1.9784598350524902, 'latency_p90': 2.150825595855713}, {'batch_size': 3, 'throughput': 1.0407007029686735, 'latency_mean': 2.8708889973163605, 'latency_p50': 2.887291669845581, 'latency_p90': 3.176371669769287}, {'batch_size': 5, 'throughput': 1.3201341613585766, 'latency_mean': 3.768367649316788, 'latency_p50': 3.8057353496551514, 'latency_p90': 4.1993766784667965}, {'batch_size': 6, 'throughput': 1.4123310226867143, 'latency_mean': 4.228004418611526, 'latency_p50': 4.232929825782776, 'latency_p90': 4.699475908279419}, {'batch_size': 8, 'throughput': 1.539630256254295, 'latency_mean': 5.150737127065659, 'latency_p50': 5.178256273269653, 'latency_p90': 5.909256768226624}, {'batch_size': 10, 'throughput': 1.614005703438104, 'latency_mean': 6.128730708360672, 'latency_p50': 6.079362511634827, 'latency_p90': 6.907727575302124}]

gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}

display_name: rirv938-yautja-cp312-98_44860_v1

is_internal_developer: True

language_model: rirv938/yautja_cp312_98ff_b35_r1_reformat_high_quality_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.31

us_pacific_date: 2025-07-08

win_ratio: 0.5073999065274964

generation_params: {'temperature': 1.0, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['###', '</s>', 'You:', '\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', '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 rirv938-yautja-cp312-98-44860-v1-mkmlizer
Waiting for job on rirv938-yautja-cp312-98-44860-v1-mkmlizer to finish
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║                                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║                                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║                                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║                                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ║                                                                     ║
rirv938-yautja-cp312-98-44860-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-yautja-cp312-98-44860-v1-mkmlizer: Downloaded to shared memory in 300.685s
rirv938-yautja-cp312-98-44860-v1-mkmlizer: Checking if rirv938/yautja_cp312_98ff_b35_r1_reformat_high_quality_merged already exists in ChaiML
rirv938-yautja-cp312-98-44860-v1-mkmlizer: Creating repo ChaiML/yautja_cp312_98ff_b35_r1_reformat_high_quality_merged and uploading /tmp/tmpr9d3y5_1 to it
rirv938-yautja-cp312-98-44860-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:06<02:08,  6.13s/it]
  9%|▉         | 2/22 [00:11<01:58,  5.92s/it]
 14%|█▎        | 3/22 [00:20<02:11,  6.93s/it]
 18%|█▊        | 4/22 [00:28<02:13,  7.44s/it]
 23%|██▎       | 5/22 [00:35<02:05,  7.38s/it]
 27%|██▋       | 6/22 [00:40<01:45,  6.58s/it]
 32%|███▏      | 7/22 [00:47<01:39,  6.62s/it]
 36%|███▋      | 8/22 [00:52<01:28,  6.31s/it]
 41%|████      | 9/22 [00:59<01:23,  6.45s/it]
 45%|████▌     | 10/22 [01:03<01:08,  5.67s/it]
 50%|█████     | 11/22 [01:06<00:54,  4.97s/it]
 55%|█████▍    | 12/22 [01:13<00:55,  5.53s/it]
 59%|█████▉    | 13/22 [01:19<00:51,  5.73s/it]
 64%|██████▎   | 14/22 [01:27<00:49,  6.15s/it]
 68%|██████▊   | 15/22 [01:33<00:44,  6.36s/it]
 73%|███████▎  | 16/22 [01:40<00:39,  6.54s/it]
 77%|███████▋  | 17/22 [01:44<00:28,  5.77s/it]
 82%|████████▏ | 18/22 [01:48<00:20,  5.11s/it]
 86%|████████▋ | 19/22 [01:53<00:15,  5.24s/it]
 91%|█████████ | 20/22 [01:58<00:10,  5.11s/it]
 95%|█████████▌| 21/22 [02:02<00:04,  4.66s/it]
100%|██████████| 22/22 [02:03<00:00,  3.57s/it]
100%|██████████| 22/22 [02:03<00:00,  5.61s/it]
rirv938-yautja-cp312-98-44860-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpr9d3y5_1, device:0
rirv938-yautja-cp312-98-44860-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-yautja-cp312-98-44860-v1-mkmlizer: quantized model in 58.419s
rirv938-yautja-cp312-98-44860-v1-mkmlizer: Processed model rirv938/yautja_cp312_98ff_b35_r1_reformat_high_quality_merged in 577.747s
rirv938-yautja-cp312-98-44860-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/config.json
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/special_tokens_map.json
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/tokenizer_config.json
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/tokenizer.json
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/flywheel_model.1.safetensors
rirv938-yautja-cp312-98-44860-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-yautja-cp312-98-44860-v1/nvidia/flywheel_model.0.safetensors
rirv938-yautja-cp312-98-44860-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 27.81it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.71it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.06it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.07it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.73it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 16.13it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 12.95it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.57it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.16it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.07it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 15.34it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:27, 11.85it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 16.72it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 20.02it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.54it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:20, 15.14it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:25, 12.05it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:17, 17.03it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.32it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.77it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.45it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:23, 12.22it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.27it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.65it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.67it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:18, 15.02it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.34it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.05it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 18.94it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.42it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:20, 12.22it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:21, 11.96it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:19, 12.98it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 10.88it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.27it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.04it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.81it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:15, 15.57it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.32it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 17.07it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 20.34it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:14, 15.25it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.70it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.36it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.48it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.07it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.32it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.79it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.55it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.69it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:08, 21.27it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:13, 13.89it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:11, 15.75it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.30it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:09, 18.01it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:07, 21.76it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.31it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.94it/s]
Loading 0:  56%|█████▌    | 203/363 [00:28<03:53,  1.46s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<02:30,  1.04it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:49,  1.39it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:21,  1.83it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:02,  2.34it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:45,  3.19it/s]
Loading 0:  61%|██████    | 222/363 [00:29<00:35,  4.02it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:23,  5.90it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:16,  8.15it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.24it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:13,  9.56it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:13,  9.49it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:12,  9.90it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 13.87it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 17.90it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.39it/s]
Loading 0:  70%|██████▉   | 254/363 [00:31<00:07, 14.30it/s]
Loading 0:  71%|███████   | 256/363 [00:31<00:08, 12.87it/s]
Loading 0:  71%|███████   | 258/363 [00:31<00:08, 12.58it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.21it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.50it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:06, 14.93it/s]
Loading 0:  75%|███████▍  | 272/363 [00:32<00:05, 15.54it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:07, 12.07it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.32it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.66it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.31it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.10it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.13it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.21it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.78it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 15.12it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 15.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 11.98it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 16.89it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 20.22it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 14.80it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 15.15it/s]
Loading 0:  91%|█████████ | 329/363 [00:36<00:02, 12.05it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 16.81it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 20.19it/s]
Loading 0:  94%|█████████▍| 341/363 [00:36<00:01, 14.95it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.44it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 12.05it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 16.88it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 20.02it/s]
Loading 0:  99%|█████████▉| 359/363 [00:38<00:00, 10.85it/s]
Loading 0: 100%|█████████▉| 362/363 [00:38<00:00, 10.92it/s]
                                                            
Job rirv938-yautja-cp312-98-44860-v1-mkmlizer completed after 610.64s with status: succeeded
Stopping job with name rirv938-yautja-cp312-98-44860-v1-mkmlizer
Pipeline stage MKMLizer completed in 611.37s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.15s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-yautja-cp312-98-44860-v1
Waiting for inference service rirv938-yautja-cp312-98-44860-v1 to be ready
Inference service rirv938-yautja-cp312-98-44860-v1 ready after 191.01704168319702s
Pipeline stage MKMLDeployer completed in 191.59s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.643878221511841s
Received healthy response to inference request in 1.9723827838897705s
Received healthy response to inference request in 2.4387319087982178s
Received healthy response to inference request in 1.866591215133667s
Received healthy response to inference request in 1.9084889888763428s
5 requests
0 failed requests
5th percentile: 1.8749707698822022
10th percentile: 1.8833503246307373
20th percentile: 1.9001094341278075
30th percentile: 1.9212677478790283
40th percentile: 1.9468252658843994
50th percentile: 1.9723827838897705
60th percentile: 2.1589224338531494
70th percentile: 2.3454620838165283
80th percentile: 2.479761171340942
90th percentile: 2.5618196964263915
95th percentile: 2.6028489589691164
99th percentile: 2.635672369003296
mean time: 2.166014623641968
Pipeline stage StressChecker completed in 12.26s
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 0.63s
Shutdown handler de-registered
rirv938-yautja-cp312-98_44860_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 8114.00s
Shutdown handler de-registered
rirv938-yautja-cp312-98_44860_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-yautja-cp312-98_44860_v1 status is now torndown due to DeploymentManager action