rirv938-prefgrok-cp312-_47258

developer_uid: rirv938

submission_id: rirv938-prefgrok-cp312-_47258_v1

model_name: rirv938-prefgrok-cp312-_47258_v1

model_group: rirv938/prefgrok_cp312_9

status: torndown

timestamp: 2025-07-08T03:12:54+00:00

num_battles: 6975

num_wins: 3561

celo_rating: 1297.89

family_friendly_score: 0.5740000000000001

family_friendly_standard_error: 0.006993196693930466

submission_type: basic

model_repo: rirv938/prefgrok_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': 0.5207147172950745, 'latency_mean': 1.9202421188354493, 'latency_p50': 1.9199541807174683, 'latency_p90': 2.1214576721191407}, {'batch_size': 3, 'throughput': 1.0550544935390345, 'latency_mean': 2.8301633620262145, 'latency_p50': 2.827998399734497, 'latency_p90': 3.1348973751068114}, {'batch_size': 5, 'throughput': 1.327765502913323, 'latency_mean': 3.7584677016735077, 'latency_p50': 3.750988245010376, 'latency_p90': 4.155819320678711}, {'batch_size': 6, 'throughput': 1.4501922886825536, 'latency_mean': 4.1090248477458955, 'latency_p50': 4.0875256061553955, 'latency_p90': 4.717459702491761}, {'batch_size': 8, 'throughput': 1.5840842449362558, 'latency_mean': 5.012435845136642, 'latency_p50': 5.039191722869873, 'latency_p90': 5.609656739234924}, {'batch_size': 10, 'throughput': 1.6424718191657757, 'latency_mean': 6.0490942275524135, 'latency_p50': 6.055216073989868, 'latency_p90': 6.772023892402649}]

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

display_name: rirv938-prefgrok-cp312-_47258_v1

is_internal_developer: True

language_model: rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-07

win_ratio: 0.5105376344086021

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': ['###', 'You:', '\n', '</s>'], '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-prefgrok-cp312-47258-v1-mkmlizer
Waiting for job on rirv938-prefgrok-cp312-47258-v1-mkmlizer to finish
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Downloaded to shared memory in 228.888s
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Checking if rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged already exists in ChaiML
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Creating repo ChaiML/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged and uploading /tmp/tmpxw6nk7yz to it
rirv938-prefgrok-cp312-47258-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:03<01:16,  3.64s/it]
  9%|▉         | 2/22 [00:07<01:20,  4.02s/it]
 14%|█▎        | 3/22 [00:14<01:39,  5.22s/it]
 18%|█▊        | 4/22 [00:17<01:20,  4.50s/it]
 23%|██▎       | 5/22 [00:25<01:37,  5.72s/it]
 27%|██▋       | 6/22 [00:30<01:25,  5.36s/it]
 32%|███▏      | 7/22 [00:33<01:09,  4.66s/it]
 36%|███▋      | 8/22 [00:39<01:09,  4.94s/it]
 41%|████      | 9/22 [00:42<00:57,  4.41s/it]
 45%|████▌     | 10/22 [00:50<01:06,  5.55s/it]
 50%|█████     | 11/22 [00:56<01:01,  5.57s/it]
 55%|█████▍    | 12/22 [01:02<00:59,  5.93s/it]
 59%|█████▉    | 13/22 [01:10<00:56,  6.31s/it]
 64%|██████▎   | 14/22 [01:13<00:43,  5.43s/it]
 68%|██████▊   | 15/22 [01:16<00:33,  4.81s/it]
 73%|███████▎  | 16/22 [01:21<00:28,  4.76s/it]
 77%|███████▋  | 17/22 [01:25<00:23,  4.61s/it]
 82%|████████▏ | 18/22 [01:30<00:17,  4.49s/it]
 86%|████████▋ | 19/22 [01:36<00:15,  5.12s/it]
 91%|█████████ | 20/22 [02:19<00:32, 16.47s/it]
 95%|█████████▌| 21/22 [02:23<00:12, 12.61s/it]
100%|██████████| 22/22 [02:24<00:00,  9.26s/it]
100%|██████████| 22/22 [02:24<00:00,  6.57s/it]
rirv938-prefgrok-cp312-47258-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxw6nk7yz, device:0
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-prefgrok-cp312-47258-v1-mkmlizer: quantized model in 58.451s
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Processed model rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged in 525.363s
rirv938-prefgrok-cp312-47258-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-prefgrok-cp312-47258-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-prefgrok-cp312-47258-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/special_tokens_map.json
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/config.json
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/tokenizer_config.json
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/tokenizer.json
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/flywheel_model.1.safetensors
rirv938-prefgrok-cp312-47258-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v1/nvidia/flywheel_model.0.safetensors
rirv938-prefgrok-cp312-47258-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.80it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 17.89it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.84it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.28it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.09it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.55it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.39it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.33it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.61it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 15.80it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.42it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 12.95it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.13it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.56it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.49it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 16.04it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.80it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.76it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.14it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.42it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.20it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.99it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 17.95it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.45it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.67it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.04it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 20.00it/s]
Loading 0:  28%|██▊       | 101/363 [00:05<00:11, 22.13it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.33it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:17, 14.35it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 14.07it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.76it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:20, 12.44it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.66it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.27it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.78it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.50it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.59it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.70it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.67it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.33it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 13.06it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.16it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.52it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.82it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 16.67it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.24it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.50it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.85it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 15.92it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.76it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.26it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.45it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.82it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.97it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.64it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:53,  1.46s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:30,  1.03it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:50,  1.39it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:22,  1.83it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:02,  2.36it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:44,  3.21it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:34,  4.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  5.98it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.34it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.54it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12, 10.09it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:12,  9.60it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 14.07it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.32it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.89it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.10it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.66it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.59it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.07it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.40it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.77it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:07, 12.03it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 16.76it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 19.94it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:05, 13.91it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 14.86it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 11.99it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 16.82it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:03, 19.96it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.70it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.45it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.66it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.50it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.42it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.23it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 16.12it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.92it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.83it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.05it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.51it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.38it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 13.09it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.03it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.18it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.73it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.86it/s]
                                                            
Job rirv938-prefgrok-cp312-47258-v1-mkmlizer completed after 556.75s with status: succeeded
Stopping job with name rirv938-prefgrok-cp312-47258-v1-mkmlizer
Pipeline stage MKMLizer completed in 557.50s
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-prefgrok-cp312-47258-v1
Waiting for inference service rirv938-prefgrok-cp312-47258-v1 to be ready
Inference service rirv938-prefgrok-cp312-47258-v1 ready after 190.6805136203766s
Pipeline stage MKMLDeployer completed in 191.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.905707597732544s
Received healthy response to inference request in 2.146768808364868s
Received healthy response to inference request in 1.9217920303344727s
Received healthy response to inference request in 1.882399082183838s
Received healthy response to inference request in 2.3414623737335205s
5 requests
0 failed requests
5th percentile: 1.8902776718139649
10th percentile: 1.8981562614440919
20th percentile: 1.9139134407043457
30th percentile: 1.9667873859405518
40th percentile: 2.05677809715271
50th percentile: 2.146768808364868
60th percentile: 2.224646234512329
70th percentile: 2.30252366065979
80th percentile: 2.4543114185333255
90th percentile: 2.6800095081329345
95th percentile: 2.792858552932739
99th percentile: 2.883137788772583
mean time: 2.2396259784698485
Pipeline stage StressChecker completed in 12.40s
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 0.63s
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-prefgrok-cp312-_47258_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 3218.97s
Shutdown handler de-registered
rirv938-prefgrok-cp312-_47258_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-prefgrok-cp312-_47258_v1 status is now torndown due to DeploymentManager action