rirv938-prefgrok-r2-cp3_29730

developer_uid: rirv938

submission_id: rirv938-prefgrok-r2-cp3_29730_v2

model_name: rirv938-prefgrok-r2-cp3_29730_v2

model_group: rirv938/prefgrok_r2_cp31

status: torndown

timestamp: 2025-07-09T14:22:13+00:00

num_battles: 7825

num_wins: 4025

celo_rating: 1302.31

family_friendly_score: 0.5720000000000001

family_friendly_standard_error: 0.00699737093485832

submission_type: basic

model_repo: rirv938/prefgrok_r2_cp312_98ff_b5_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': 0.5171589844094988, 'latency_mean': 1.9335362708568573, 'latency_p50': 1.945791244506836, 'latency_p90': 2.140089273452759}, {'batch_size': 3, 'throughput': 1.050947164069465, 'latency_mean': 2.83954372048378, 'latency_p50': 2.848116159439087, 'latency_p90': 3.1239968299865724}, {'batch_size': 5, 'throughput': 1.3450669055260516, 'latency_mean': 3.6903369104862214, 'latency_p50': 3.672423481941223, 'latency_p90': 4.1448187828063965}, {'batch_size': 6, 'throughput': 1.4541846825162892, 'latency_mean': 4.10141047000885, 'latency_p50': 4.091861009597778, 'latency_p90': 4.583688235282898}, {'batch_size': 8, 'throughput': 1.589101948247057, 'latency_mean': 4.988377310037613, 'latency_p50': 4.963876008987427, 'latency_p90': 5.675579714775085}, {'batch_size': 10, 'throughput': 1.6608828488551501, 'latency_mean': 5.9457130372524265, 'latency_p50': 5.971495628356934, 'latency_p90': 6.722448825836182}]

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

display_name: rirv938-prefgrok-r2-cp3_29730_v2

is_internal_developer: True

language_model: rirv938/prefgrok_r2_cp312_98ff_b5_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.36

us_pacific_date: 2025-07-09

win_ratio: 0.5143769968051118

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>', '\n', 'You:'], '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-cp3-29730-v2-mkmlizer
Waiting for job on rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer to finish
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ║                                                                     ║
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Retrying (%r) after connection broken by '%r': %s
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: Downloaded to shared memory in 154.954s
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: Checking if rirv938/prefgrok_r2_cp312_98ff_b5_merged already exists in ChaiML
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpkg456w1e, device:0
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: quantized model in 57.055s
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: Processed model rirv938/prefgrok_r2_cp312_98ff_b5_merged in 212.091s
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/config.json
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/special_tokens_map.json
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/tokenizer_config.json
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/tokenizer.json
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/flywheel_model.1.safetensors
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-prefgrok-r2-cp3-29730-v2/nvidia/flywheel_model.0.safetensors
rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.79it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.12it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.36it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.49it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.12it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.70it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.45it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.35it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.71it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.34it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 16.13it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.68it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.26it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:15, 20.02it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:21, 14.63it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.43it/s]
Loading 0:  16%|█▌        | 58/363 [00:03<00:22, 13.85it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:22, 13.34it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.61it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.39it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.71it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.41it/s]
Loading 0:  21%|██        | 76/363 [00:04<00:20, 13.77it/s]
Loading 0:  21%|██▏       | 78/363 [00:04<00:21, 13.44it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.88it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 21.15it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 14.55it/s]
Loading 0:  25%|██▌       | 91/363 [00:05<00:19, 14.03it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.05it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.58it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.67it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.55it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.40it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.17it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:18, 13.97it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.71it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.23it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 22.13it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.36it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.78it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.49it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.72it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.45it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.25it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 13.16it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.22it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.64it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 15.98it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 16.57it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.30it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.30it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.43it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.49it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.99it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.67it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.52it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.63it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.29it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.05it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:45,  1.41s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:26,  1.07it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:46,  1.43it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:19,  1.88it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<01:00,  2.41it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:43,  3.27it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:38,  3.71it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.53it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:15,  8.51it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12,  9.89it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.44it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 13.84it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.13it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.69it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.85it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.36it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.34it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 20.64it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.45it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.13it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.89it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.84it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 20.71it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.38it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.05it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.71it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 17.41it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.35it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 15.16it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.86it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 12.69it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.62it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.78it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.42it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.12it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.76it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.67it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.99it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.58it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.21it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.81it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.81it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.19it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.66it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.67it/s]
                                                            
Job rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer completed after 239.16s with status: succeeded
Stopping job with name rirv938-prefgrok-r2-cp3-29730-v2-mkmlizer
Pipeline stage MKMLizer completed in 239.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-prefgrok-r2-cp3-29730-v2
Waiting for inference service rirv938-prefgrok-r2-cp3-29730-v2 to be ready
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service rirv938-prefgrok-r2-cp3-29730-v2 ready after 210.84847450256348s
Pipeline stage MKMLDeployer completed in 211.62s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.874854564666748s
Received healthy response to inference request in 2.4214797019958496s
Received healthy response to inference request in 1.9033424854278564s
Received healthy response to inference request in 2.967674732208252s
Received healthy response to inference request in 1.8846893310546875s
5 requests
0 failed requests
5th percentile: 1.8884199619293214
10th percentile: 1.892150592803955
20th percentile: 1.8996118545532226
30th percentile: 2.006969928741455
40th percentile: 2.2142248153686523
50th percentile: 2.4214797019958496
60th percentile: 2.602829647064209
70th percentile: 2.7841795921325683
80th percentile: 2.8934185981750487
90th percentile: 2.9305466651916503
95th percentile: 2.9491106986999513
99th percentile: 2.9639619255065917
mean time: 2.4104081630706786
Pipeline stage StressChecker completed in 13.50s
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 0.76s
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 0.75s
Shutdown handler de-registered
rirv938-prefgrok-r2-cp3_29730_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 0.14s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.11s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-prefgrok-r2-cp3-29730-v2-profiler
Waiting for inference service rirv938-prefgrok-r2-cp3-29730-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
%s, retrying in %s seconds...
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 6370.87s
Shutdown handler de-registered
rirv938-prefgrok-r2-cp3_29730_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-prefgrok-r2-cp3_29730_v2 status is now torndown due to DeploymentManager action