rirv938-prefgrok-cp312-_47258

developer_uid: rirv938

submission_id: rirv938-prefgrok-cp312-_47258_v2

model_name: rirv938-prefgrok-cp312-_47258_v2

model_group: rirv938/prefgrok_cp312_9

status: torndown

timestamp: 2025-07-08T03:16:25+00:00

num_battles: 6897

num_wins: 3477

celo_rating: 1291.89

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': 0.5206049157731266, 'latency_mean': 1.920742653608322, 'latency_p50': 1.9268054962158203, 'latency_p90': 2.1188695669174193}, {'batch_size': 3, 'throughput': 1.0483794734048641, 'latency_mean': 2.8530299353599546, 'latency_p50': 2.845577836036682, 'latency_p90': 3.1330612659454347}, {'batch_size': 5, 'throughput': 1.3380489643466869, 'latency_mean': 3.7177755570411684, 'latency_p50': 3.7086398601531982, 'latency_p90': 4.084887146949768}, {'batch_size': 6, 'throughput': 1.4422108299683312, 'latency_mean': 4.132575228214264, 'latency_p50': 4.132449984550476, 'latency_p90': 4.581862497329712}, {'batch_size': 8, 'throughput': 1.5726693919919248, 'latency_mean': 5.037752950191498, 'latency_p50': 5.052253484725952, 'latency_p90': 5.6434815406799315}, {'batch_size': 10, 'throughput': 1.6559703107385864, 'latency_mean': 5.978239257335662, 'latency_p50': 6.020376443862915, 'latency_p90': 6.678397369384766}]

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

display_name: rirv938-prefgrok-cp312-_47258_v2

is_internal_developer: True

language_model: rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-07

win_ratio: 0.5041322314049587

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': '<|system|>{bot_name}memory:{memory}\n', '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-v2-mkmlizer
Waiting for job on rirv938-prefgrok-cp312-47258-v2-mkmlizer to finish
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-cp312-47258-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-prefgrok-cp312-47258-v2-mkmlizer: Downloaded to shared memory in 134.205s
rirv938-prefgrok-cp312-47258-v2-mkmlizer: Checking if rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged already exists in ChaiML
rirv938-prefgrok-cp312-47258-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpq3cvmc5a, device:0
rirv938-prefgrok-cp312-47258-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-prefgrok-cp312-47258-v2-mkmlizer: quantized model in 59.655s
rirv938-prefgrok-cp312-47258-v2-mkmlizer: Processed model rirv938/prefgrok_cp312_98ff_b35_r1_reformat_high_quality_merged in 193.935s
rirv938-prefgrok-cp312-47258-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-prefgrok-cp312-47258-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-prefgrok-cp312-47258-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/config.json
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/special_tokens_map.json
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/tokenizer_config.json
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/tokenizer.json
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/flywheel_model.1.safetensors
rirv938-prefgrok-cp312-47258-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-cp312-47258-v2/nvidia/flywheel_model.0.safetensors
rirv938-prefgrok-cp312-47258-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:13, 27.36it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 13.81it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.17it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 12.94it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.64it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.55it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.83it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:28, 11.84it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.09it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.28it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:23, 14.13it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:21, 14.80it/s]
Loading 0:  11%|█         | 40/363 [00:02<00:24, 13.17it/s]
Loading 0:  12%|█▏        | 42/363 [00:02<00:25, 12.69it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.38it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.81it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.57it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:23, 13.29it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:21, 14.32it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:25, 11.97it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:16, 17.92it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.57it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.12it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.67it/s]
Loading 0:  21%|██        | 76/363 [00:05<00:20, 14.11it/s]
Loading 0:  21%|██▏       | 78/363 [00:05<00:20, 13.61it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.75it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.59it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.09it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.85it/s]
Loading 0:  26%|██▋       | 96/363 [00:06<00:13, 19.92it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:11, 21.99it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.80it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.13it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.48it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.33it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.07it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 16.78it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:12, 19.84it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:17, 13.82it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.26it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 13.99it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:20, 11.27it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:13, 16.70it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:11, 19.32it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:15, 14.03it/s]
Loading 0:  40%|███▉      | 145/363 [00:09<00:16, 13.60it/s]
Loading 0:  40%|████      | 147/363 [00:09<00:14, 14.60it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:18, 11.84it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.68it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:09, 20.65it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:14, 13.94it/s]
Loading 0:  45%|████▍     | 163/363 [00:10<00:15, 13.23it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:14, 14.07it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:17, 11.34it/s]
Loading 0:  47%|████▋     | 172/363 [00:11<00:11, 16.76it/s]
Loading 0:  48%|████▊     | 176/363 [00:11<00:09, 20.38it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:13, 14.08it/s]
Loading 0:  50%|████▉     | 181/363 [00:11<00:13, 13.44it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 14.16it/s]
Loading 0:  51%|█████     | 185/363 [00:12<00:15, 11.67it/s]
Loading 0:  52%|█████▏    | 190/363 [00:12<00:10, 17.23it/s]
Loading 0:  53%|█████▎    | 194/363 [00:12<00:08, 20.60it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.56it/s]
Loading 0:  55%|█████▍    | 199/363 [00:13<00:11, 14.18it/s]
Loading 0:  55%|█████▌    | 201/363 [00:27<04:39,  1.73s/it]
Loading 0:  56%|█████▌    | 202/363 [00:27<04:01,  1.50s/it]
Loading 0:  56%|█████▌    | 204/363 [00:28<02:54,  1.10s/it]
Loading 0:  57%|█████▋    | 207/363 [00:28<01:48,  1.44it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:11,  2.14it/s]
Loading 0:  58%|█████▊    | 212/363 [00:28<00:55,  2.73it/s]
Loading 0:  59%|█████▉    | 214/363 [00:28<00:45,  3.26it/s]
Loading 0:  60%|█████▉    | 216/363 [00:29<00:38,  3.86it/s]
Loading 0:  60%|██████    | 219/363 [00:29<00:25,  5.67it/s]
Loading 0:  61%|██████    | 221/363 [00:29<00:23,  6.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:13, 10.32it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:09, 13.52it/s]
Loading 0:  64%|██████▍   | 233/363 [00:30<00:11, 11.41it/s]
Loading 0:  65%|██████▌   | 236/363 [00:30<00:10, 12.58it/s]
Loading 0:  66%|██████▌   | 238/363 [00:30<00:10, 11.86it/s]
Loading 0:  66%|██████▌   | 240/363 [00:30<00:10, 11.50it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:07, 15.39it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 18.99it/s]
Loading 0:  69%|██████▉   | 251/363 [00:31<00:08, 13.52it/s]
Loading 0:  70%|██████▉   | 253/363 [00:31<00:08, 13.00it/s]
Loading 0:  70%|███████   | 255/363 [00:31<00:07, 13.56it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:09, 11.07it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:06, 16.60it/s]
Loading 0:  73%|███████▎  | 266/363 [00:32<00:04, 19.65it/s]
Loading 0:  74%|███████▍  | 269/363 [00:32<00:07, 13.41it/s]
Loading 0:  75%|███████▍  | 271/363 [00:32<00:07, 13.01it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:06, 13.98it/s]
Loading 0:  76%|███████▌  | 275/363 [00:33<00:07, 11.61it/s]
Loading 0:  77%|███████▋  | 280/363 [00:33<00:04, 17.40it/s]
Loading 0:  78%|███████▊  | 284/363 [00:33<00:03, 21.00it/s]
Loading 0:  79%|███████▉  | 287/363 [00:33<00:05, 14.85it/s]
Loading 0:  80%|███████▉  | 290/363 [00:33<00:04, 15.58it/s]
Loading 0:  80%|████████  | 292/363 [00:34<00:05, 14.02it/s]
Loading 0:  81%|████████  | 294/363 [00:34<00:05, 13.57it/s]
Loading 0:  82%|████████▏ | 298/363 [00:34<00:03, 17.62it/s]
Loading 0:  83%|████████▎ | 302/363 [00:34<00:02, 20.94it/s]
Loading 0:  84%|████████▍ | 305/363 [00:34<00:03, 14.63it/s]
Loading 0:  85%|████████▍ | 307/363 [00:34<00:03, 14.05it/s]
Loading 0:  85%|████████▌ | 309/363 [00:35<00:03, 14.99it/s]
Loading 0:  86%|████████▌ | 311/363 [00:35<00:04, 12.16it/s]
Loading 0:  87%|████████▋ | 316/363 [00:35<00:02, 18.17it/s]
Loading 0:  88%|████████▊ | 320/363 [00:35<00:02, 21.46it/s]
Loading 0:  89%|████████▉ | 323/363 [00:35<00:02, 15.02it/s]
Loading 0:  90%|████████▉ | 326/363 [00:36<00:02, 15.79it/s]
Loading 0:  90%|█████████ | 328/363 [00:36<00:02, 14.02it/s]
Loading 0:  91%|█████████ | 330/363 [00:36<00:02, 13.55it/s]
Loading 0:  92%|█████████▏| 334/363 [00:36<00:01, 17.85it/s]
Loading 0:  93%|█████████▎| 338/363 [00:36<00:01, 21.39it/s]
Loading 0:  94%|█████████▍| 341/363 [00:37<00:01, 14.66it/s]
Loading 0:  94%|█████████▍| 343/363 [00:37<00:01, 13.98it/s]
Loading 0:  95%|█████████▌| 345/363 [00:37<00:01, 14.87it/s]
Loading 0:  96%|█████████▌| 347/363 [00:37<00:01, 11.98it/s]
Loading 0:  97%|█████████▋| 352/363 [00:37<00:00, 17.63it/s]
Loading 0:  98%|█████████▊| 356/363 [00:37<00:00, 20.33it/s]
Loading 0:  99%|█████████▉| 359/363 [00:38<00:00,  9.51it/s]
Loading 0:  99%|█████████▉| 361/363 [00:38<00:00,  8.81it/s]
                                                            
Job rirv938-prefgrok-cp312-47258-v2-mkmlizer completed after 228.69s with status: succeeded
Stopping job with name rirv938-prefgrok-cp312-47258-v2-mkmlizer
Pipeline stage MKMLizer completed in 229.23s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-prefgrok-cp312-47258-v2
Waiting for inference service rirv938-prefgrok-cp312-47258-v2 to be ready
Inference service rirv938-prefgrok-cp312-47258-v2 ready after 191.14691829681396s
Pipeline stage MKMLDeployer completed in 191.67s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.4169414043426514s
Received healthy response to inference request in 2.088852882385254s
Received healthy response to inference request in 1.9617280960083008s
Received healthy response to inference request in 2.0201046466827393s
Received healthy response to inference request in 1.8992018699645996s
5 requests
0 failed requests
5th percentile: 1.9117071151733398
10th percentile: 1.92421236038208
20th percentile: 1.9492228507995606
30th percentile: 1.9734034061431884
40th percentile: 1.996754026412964
50th percentile: 2.0201046466827393
60th percentile: 2.047603940963745
70th percentile: 2.075103235244751
80th percentile: 2.1544705867767333
90th percentile: 2.2857059955596926
95th percentile: 2.351323699951172
99th percentile: 2.4038178634643557
mean time: 2.077365779876709
Pipeline stage StressChecker completed in 11.77s
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 0.67s
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 1.02s
Shutdown handler de-registered
rirv938-prefgrok-cp312-_47258_v2 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 0.15s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-prefgrok-cp312-47258-v2-profiler
Waiting for inference service rirv938-prefgrok-cp312-47258-v2-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 3178.62s
Shutdown handler de-registered
rirv938-prefgrok-cp312-_47258_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-prefgrok-cp312-_47258_v2 status is now torndown due to DeploymentManager action