rirv938-prefgrok-cp624-_38902

developer_uid: rirv938

submission_id: rirv938-prefgrok-cp624-_38902_v1

model_name: rirv938-prefgrok-cp624-_38902_v1

model_group: rirv938/prefgrok_cp624_9

status: torndown

timestamp: 2025-07-08T03:54:43+00:00

num_battles: 7969

num_wins: 4076

celo_rating: 1297.14

family_friendly_score: 0.573

family_friendly_standard_error: 0.006995298421082549

submission_type: basic

model_repo: rirv938/prefgrok_cp624_98ff_b35_r1_reformat_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': 0.5133060405505486, 'latency_mean': 1.9480313909053804, 'latency_p50': 1.9618569612503052, 'latency_p90': 2.148884582519531}, {'batch_size': 3, 'throughput': 1.0336114038119386, 'latency_mean': 2.894945594072342, 'latency_p50': 2.9081135988235474, 'latency_p90': 3.2118653059005737}, {'batch_size': 5, 'throughput': 1.310592442494933, 'latency_mean': 3.801007525920868, 'latency_p50': 3.7682164907455444, 'latency_p90': 4.244332790374756}, {'batch_size': 6, 'throughput': 1.4047551927710173, 'latency_mean': 4.233913481235504, 'latency_p50': 4.245859742164612, 'latency_p90': 4.795722818374633}, {'batch_size': 8, 'throughput': 1.5271045266534626, 'latency_mean': 5.193231990337372, 'latency_p50': 5.210110068321228, 'latency_p90': 5.832296085357666}, {'batch_size': 10, 'throughput': 1.627263917903572, 'latency_mean': 6.099389617443085, 'latency_p50': 6.11952531337738, 'latency_p90': 6.921280336380005}]

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

display_name: rirv938-prefgrok-cp624-_38902_v1

is_internal_developer: True

language_model: rirv938/prefgrok_cp624_98ff_b35_r1_reformat_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.29

us_pacific_date: 2025-07-07

win_ratio: 0.511481992721797

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-prefgrok-cp624-38902-v1-mkmlizer
Waiting for job on rirv938-prefgrok-cp624-38902-v1-mkmlizer to finish
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp624-38902-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Downloaded to shared memory in 155.438s
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Checking if rirv938/prefgrok_cp624_98ff_b35_r1_reformat_merged already exists in ChaiML
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Creating repo ChaiML/prefgrok_cp624_98ff_b35_r1_reformat_merged and uploading /tmp/tmp2v88fbf4 to it
rirv938-prefgrok-cp624-38902-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:03<01:18,  3.75s/it]
  9%|▉         | 2/22 [00:11<02:01,  6.07s/it]
 14%|█▎        | 3/22 [00:19<02:12,  6.99s/it]
 18%|█▊        | 4/22 [00:23<01:43,  5.76s/it]
 23%|██▎       | 5/22 [00:26<01:23,  4.89s/it]
 27%|██▋       | 6/22 [00:34<01:32,  5.81s/it]
 32%|███▏      | 7/22 [00:37<01:14,  4.98s/it]
 36%|███▋      | 8/22 [00:40<01:02,  4.46s/it]
 41%|████      | 9/22 [00:45<00:57,  4.40s/it]
 45%|████▌     | 10/22 [00:48<00:49,  4.08s/it]
 50%|█████     | 11/22 [00:51<00:42,  3.87s/it]
 55%|█████▍    | 12/22 [00:55<00:37,  3.71s/it]
 59%|█████▉    | 13/22 [01:03<00:45,  5.05s/it]
 64%|██████▎   | 14/22 [01:07<00:38,  4.75s/it]
 68%|██████▊   | 15/22 [01:10<00:30,  4.33s/it]
 73%|███████▎  | 16/22 [01:16<00:29,  4.86s/it]
 77%|███████▋  | 17/22 [01:23<00:27,  5.43s/it]
 82%|████████▏ | 18/22 [01:31<00:24,  6.22s/it]
 86%|████████▋ | 19/22 [01:38<00:19,  6.42s/it]
 91%|█████████ | 20/22 [01:44<00:12,  6.15s/it]
 95%|█████████▌| 21/22 [03:58<00:44, 44.60s/it]
100%|██████████| 22/22 [03:59<00:00, 31.55s/it]
100%|██████████| 22/22 [03:59<00:00, 10.89s/it]
rirv938-prefgrok-cp624-38902-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2v88fbf4, device:0
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-prefgrok-cp624-38902-v1-mkmlizer: quantized model in 57.218s
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Processed model rirv938/prefgrok_cp624_98ff_b35_r1_reformat_merged in 544.139s
rirv938-prefgrok-cp624-38902-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-prefgrok-cp624-38902-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-prefgrok-cp624-38902-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/config.json
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/special_tokens_map.json
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/tokenizer_config.json
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/tokenizer.json
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/flywheel_model.1.safetensors
rirv938-prefgrok-cp624-38902-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp624-38902-v1/nvidia/flywheel_model.0.safetensors
rirv938-prefgrok-cp624-38902-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.66it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.58it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.97it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.51it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.07it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:21, 16.17it/s]
Loading 0:   6%|▌         | 22/363 [00:01<00:21, 15.57it/s]
Loading 0:   7%|▋         | 24/363 [00:01<00:23, 14.70it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.50it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 23.51it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.50it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.30it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.71it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.91it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.10it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.16it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.65it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.44it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.04it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 20.25it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.01it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.76it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.61it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.65it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.05it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.49it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 15.95it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.65it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.55it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.70it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 15.10it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.79it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.28it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.17it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.64it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.02it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.71it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.10it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:15, 15.58it/s]
Loading 0:  36%|███▌      | 130/363 [00:08<00:16, 13.94it/s]
Loading 0:  36%|███▋      | 132/363 [00:08<00:16, 13.60it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 18.23it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:09, 22.33it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.41it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.12it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.61it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.74it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.92it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.14it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.91it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.68it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.82it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.21it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.39it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 16.06it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.69it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.57it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.79it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.20it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.10it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:50,  1.44s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:29,  1.05it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:48,  1.41it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:20,  1.86it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:01,  2.39it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:44,  3.25it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:34,  4.12it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.03it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:15,  8.38it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.50it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12, 10.00it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.51it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 13.99it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 17.36it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.92it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.95it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.36it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.31it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.66it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.47it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.14it/s]
Loading 0:  76%|███████▌  | 275/363 [00:32<00:06, 13.13it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 18.23it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.74it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 16.19it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.82it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 13.16it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.29it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.65it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.73it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.51it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:03, 13.01it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.85it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.87it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.43it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.08it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.81it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.74it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.77it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.15it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 16.01it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.97it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.94it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.16it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.69it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.79it/s]
                                                            
Job rirv938-prefgrok-cp624-38902-v1-mkmlizer completed after 576.94s with status: succeeded
Stopping job with name rirv938-prefgrok-cp624-38902-v1-mkmlizer
Pipeline stage MKMLizer completed in 577.64s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-prefgrok-cp624-38902-v1
Waiting for inference service rirv938-prefgrok-cp624-38902-v1 to be ready
Inference service rirv938-prefgrok-cp624-38902-v1 ready after 181.03058004379272s
Pipeline stage MKMLDeployer completed in 181.77s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4548230171203613s
Received healthy response to inference request in 1.9248292446136475s
Received healthy response to inference request in 2.160811424255371s
Received healthy response to inference request in 1.925360918045044s
Received healthy response to inference request in 1.893477201461792s
5 requests
0 failed requests
5th percentile: 1.899747610092163
10th percentile: 1.9060180187225342
20th percentile: 1.9185588359832764
30th percentile: 1.9249355792999268
40th percentile: 1.9251482486724854
50th percentile: 1.925360918045044
60th percentile: 2.019541120529175
70th percentile: 2.113721323013306
80th percentile: 2.2196137428283693
90th percentile: 2.3372183799743653
95th percentile: 2.396020698547363
99th percentile: 2.4430625534057615
mean time: 2.071860361099243
Pipeline stage StressChecker completed in 11.65s
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 0.84s
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 0.88s
Shutdown handler de-registered
rirv938-prefgrok-cp624-_38902_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 3220.29s
Shutdown handler de-registered
rirv938-prefgrok-cp624-_38902_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-prefgrok-cp624-_38902_v1 status is now torndown due to DeploymentManager action