developer_uid: rirv938
submission_id: rirv938-prefgrok-r2-cp6_85163_v1
model_name: rirv938-prefgrok-r2-cp6_85163_v1
model_group: rirv938/prefgrok_r2_cp62
status: torndown
timestamp: 2025-07-09T14:22:17+00:00
num_battles: 6994
num_wins: 3637
celo_rating: 1305.89
family_friendly_score: 0.5666
family_friendly_standard_error: 0.0070080587897077455
submission_type: basic
model_repo: rirv938/prefgrok_r2_cp624_98ff_b5_v2_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': 0.5204056857657282, 'latency_mean': 1.9214498269557954, 'latency_p50': 1.9045981168746948, 'latency_p90': 2.1355282068252563}, {'batch_size': 3, 'throughput': 1.039974774232485, 'latency_mean': 2.8835809135437014, 'latency_p50': 2.85212242603302, 'latency_p90': 3.231964182853699}, {'batch_size': 5, 'throughput': 1.3184464857602831, 'latency_mean': 3.773481991291046, 'latency_p50': 3.7785381078720093, 'latency_p90': 4.2494988441467285}, {'batch_size': 6, 'throughput': 1.409401629016456, 'latency_mean': 4.223396993875504, 'latency_p50': 4.213966369628906, 'latency_p90': 4.846129631996154}, {'batch_size': 8, 'throughput': 1.5250967192214877, 'latency_mean': 5.2017278683185575, 'latency_p50': 5.243237257003784, 'latency_p90': 5.8049968957901}, {'batch_size': 10, 'throughput': 1.6214277681736644, 'latency_mean': 6.114314106702804, 'latency_p50': 6.115529775619507, 'latency_p90': 6.897277164459228}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-prefgrok-r2-cp6_85163_v1
is_internal_developer: True
language_model: rirv938/prefgrok_r2_cp624_98ff_b5_v2_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.31
us_pacific_date: 2025-07-09
win_ratio: 0.520017157563626
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-r2-cp6-85163-v1-mkmlizer
Waiting for job on rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer to finish
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Downloaded to shared memory in 162.947s
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Checking if rirv938/prefgrok_r2_cp624_98ff_b5_v2_merged already exists in ChaiML
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Creating repo ChaiML/prefgrok_r2_cp624_98ff_b5_v2_merged and uploading /tmp/tmpqbd72vnf to it
Failed to get response for submission chaiml-gy-exp129-dpo-ex_61642_v4: HTTPConnectionPool(host='chaiml-gy-exp129-dpo-ex-61642-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:08<02:48,  8.02s/it]
  9%|▉         | 2/22 [00:11<01:45,  5.29s/it]
 14%|█▎        | 3/22 [00:16<01:35,  5.05s/it]
 18%|█▊        | 4/22 [00:19<01:20,  4.46s/it]
 23%|██▎       | 5/22 [00:26<01:29,  5.24s/it]
 27%|██▋       | 6/22 [00:32<01:31,  5.72s/it]
 32%|███▏      | 7/22 [00:36<01:14,  4.94s/it]
 36%|███▋      | 8/22 [00:42<01:13,  5.28s/it]
 41%|████      | 9/22 [00:50<01:20,  6.19s/it]
 45%|████▌     | 10/22 [00:56<01:13,  6.15s/it]
 50%|█████     | 11/22 [01:02<01:07,  6.15s/it]
 55%|█████▍    | 12/22 [01:07<00:56,  5.64s/it]
 59%|█████▉    | 13/22 [01:15<00:57,  6.39s/it]
 64%|██████▎   | 14/22 [01:23<00:54,  6.82s/it]
 68%|██████▊   | 15/22 [01:27<00:42,  6.09s/it]
 73%|███████▎  | 16/22 [01:30<00:31,  5.26s/it]
 77%|███████▋  | 17/22 [01:37<00:28,  5.69s/it]
 82%|████████▏ | 18/22 [01:42<00:21,  5.47s/it]
 86%|████████▋ | 19/22 [01:46<00:14,  4.99s/it]
 91%|█████████ | 20/22 [01:54<00:11,  5.92s/it]
 95%|█████████▌| 21/22 [02:04<00:07,  7.27s/it]
100%|██████████| 22/22 [02:06<00:00,  5.48s/it]
100%|██████████| 22/22 [02:06<00:00,  5.74s/it]
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpqbd72vnf, device:0
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: quantized model in 57.723s
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Processed model rirv938/prefgrok_r2_cp624_98ff_b5_v2_merged in 439.228s
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/config.json
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/special_tokens_map.json
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/tokenizer_config.json
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/tokenizer.json
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/flywheel_model.1.safetensors
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp6-85163-v1/nvidia/flywheel_model.0.safetensors
rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.60it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.41it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.08it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:27, 12.75it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.61it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.99it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:26, 13.00it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.90it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.52it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.18it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 16.11it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.79it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.35it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 20.97it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.11it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.92it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.78it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 21.01it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 15.00it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.87it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.67it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.07it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.10it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.63it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.47it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:12, 21.65it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 18.02it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.81it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.57it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.33it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.88it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.76it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.50it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.19it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.05it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.78it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.78it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.13it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.26it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.13it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.77it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.92it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.67it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.08it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.05it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.93it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.08it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.53it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.76it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:10, 16.55it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.18it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.15it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.25it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.40it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.27it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:54,  1.47s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:31,  1.03it/s]
Loading 0:  58%|█████▊    | 210/363 [00:28<01:50,  1.38it/s]
Loading 0:  59%|█████▊    | 213/363 [00:28<01:22,  1.82it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:02,  2.35it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:44,  3.20it/s]
Loading 0:  61%|██████    | 222/363 [00:29<00:34,  4.09it/s]
Loading 0:  62%|██████▏   | 226/363 [00:29<00:22,  6.00it/s]
Loading 0:  63%|██████▎   | 230/363 [00:29<00:15,  8.39it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.50it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12,  9.99it/s]
Loading 0:  66%|██████▌   | 239/363 [00:30<00:12,  9.63it/s]
Loading 0:  67%|██████▋   | 244/363 [00:30<00:08, 14.13it/s]
Loading 0:  68%|██████▊   | 248/363 [00:30<00:06, 17.53it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.10it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.29it/s]
Loading 0:  71%|███████   | 257/363 [00:31<00:08, 12.62it/s]
Loading 0:  72%|███████▏  | 262/363 [00:31<00:05, 17.81it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.29it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:06, 13.41it/s]
Loading 0:  75%|███████▌  | 273/363 [00:32<00:05, 15.52it/s]
Loading 0:  76%|███████▌  | 276/363 [00:32<00:05, 14.56it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 18.06it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.73it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 16.12it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.84it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 13.39it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.60it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 21.89it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 16.09it/s]
Loading 0:  85%|████████▍ | 308/363 [00:34<00:03, 16.80it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:03, 13.26it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 18.35it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.78it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 16.00it/s]
Loading 0:  90%|████████▉ | 326/363 [00:35<00:02, 16.77it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 13.41it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 18.67it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 22.04it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 16.16it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 17.00it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 13.71it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.95it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 22.42it/s]
Loading 0:  99%|█████████▉| 360/363 [00:37<00:00, 12.23it/s]
Loading 0: 100%|██████████| 363/363 [00:37<00:00, 13.52it/s]
                                                            

Job rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer completed after 476.2s with status: succeeded
Stopping job with name rirv938-prefgrok-r2-cp6-85163-v1-mkmlizer
Pipeline stage MKMLizer completed in 476.71s
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-r2-cp6-85163-v1
Waiting for inference service rirv938-prefgrok-r2-cp6-85163-v1 to be ready
Failed to get response for submission chaiml-gy-exp129-dpo-ex_61642_v4: HTTPConnectionPool(host='chaiml-gy-exp129-dpo-ex-61642-v4-predictor.tenant-chaiml-guanaco.k.chaiverse.com', port=80): Read timed out. (read timeout=12.0)
Inference service rirv938-prefgrok-r2-cp6-85163-v1 ready after 200.88600492477417s
Pipeline stage MKMLDeployer completed in 201.41s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.639878034591675s
Received healthy response to inference request in 1.9040272235870361s
Received healthy response to inference request in 1.848254680633545s
Received healthy response to inference request in 2.329972267150879s
Received healthy response to inference request in 2.071211099624634s
5 requests
0 failed requests
5th percentile: 1.8594091892242433
10th percentile: 1.8705636978149414
20th percentile: 1.8928727149963378
30th percentile: 1.9374639987945557
40th percentile: 2.0043375492095947
50th percentile: 2.071211099624634
60th percentile: 2.1747155666351317
70th percentile: 2.27822003364563
80th percentile: 2.3919534206390383
90th percentile: 2.5159157276153565
95th percentile: 2.5778968811035154
99th percentile: 2.627481803894043
mean time: 2.1586686611175536
Pipeline stage StressChecker completed in 12.04s
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 0.64s
Shutdown handler de-registered
rirv938-prefgrok-r2-cp6_85163_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 3286.04s
Shutdown handler de-registered
rirv938-prefgrok-r2-cp6_85163_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-prefgrok-r2-cp6_85163_v1 status is now torndown due to DeploymentManager action