chaiml-grok-payloads-gr_12038

developer_uid: rirv938

submission_id: chaiml-grok-payloads-gr_12038_v3

model_name: chaiml-grok-payloads-gr_12038_v3

model_group: ChaiML/grok_payloads_grp

status: torndown

timestamp: 2025-07-09T18:20:20+00:00

num_battles: 7356

num_wins: 3922

celo_rating: 1315.95

family_friendly_score: 0.5316000000000001

family_friendly_standard_error: 0.007056931911248684

submission_type: basic

model_repo: ChaiML/grok_payloads_grpo_cp312_98ff_b35_r1_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': 0.5190195628214644, 'latency_mean': 1.9265841901302339, 'latency_p50': 1.926439642906189, 'latency_p90': 2.1430891275405886}, {'batch_size': 3, 'throughput': 1.0462478565743054, 'latency_mean': 2.8555327641963957, 'latency_p50': 2.8510836362838745, 'latency_p90': 3.1618786334991453}, {'batch_size': 5, 'throughput': 1.3286934774957782, 'latency_mean': 3.7476963698863983, 'latency_p50': 3.736752510070801, 'latency_p90': 4.179577755928039}, {'batch_size': 6, 'throughput': 1.432043005648191, 'latency_mean': 4.158286565542221, 'latency_p50': 4.141102433204651, 'latency_p90': 4.640650129318237}, {'batch_size': 8, 'throughput': 1.5719469497287326, 'latency_mean': 5.057961399555206, 'latency_p50': 5.031152606010437, 'latency_p90': 5.6833358049392695}, {'batch_size': 10, 'throughput': 1.6387557540298918, 'latency_mean': 6.0389502441883085, 'latency_p50': 6.035779118537903, 'latency_p90': 6.759004306793213}]

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

display_name: chaiml-grok-payloads-gr_12038_v3

is_internal_developer: True

language_model: ChaiML/grok_payloads_grpo_cp312_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.32

us_pacific_date: 2025-07-09

win_ratio: 0.5331702011963023

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': True}

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 chaiml-grok-payloads-gr-12038-v3-mkmlizer
Waiting for job on chaiml-grok-payloads-gr-12038-v3-mkmlizer to finish
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║                                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║                                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  https://mk1.ai                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║                                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  belonging to:                                                      ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║                                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Chai Research Corp.                                                ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ║                                                                     ║
chaiml-grok-payloads-gr-12038-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
chaiml-grok-payloads-gr-12038-v3-mkmlizer: Downloaded to shared memory in 136.753s
chaiml-grok-payloads-gr-12038-v3-mkmlizer: Checking if ChaiML/grok_payloads_grpo_cp312_98ff_b35_r1_merged already exists in ChaiML
chaiml-grok-payloads-gr-12038-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpy5o__ub9, device:0
chaiml-grok-payloads-gr-12038-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-grok-payloads-gr-12038-v3-mkmlizer: creating bucket guanaco-mkml-models
chaiml-grok-payloads-gr-12038-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-grok-payloads-gr-12038-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/config.json
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/special_tokens_map.json
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/tokenizer_config.json
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/tokenizer.json
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/flywheel_model.1.safetensors
chaiml-grok-payloads-gr-12038-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-grok-payloads-gr-12038-v3/nvidia/flywheel_model.0.safetensors
chaiml-grok-payloads-gr-12038-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:18, 19.27it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:39,  9.18it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:18, 19.46it/s]
Loading 0:   4%|▍         | 14/363 [00:01<00:27, 12.65it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:28, 12.37it/s]
Loading 0:   5%|▌         | 19/363 [00:01<00:22, 15.16it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 15.60it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:27, 12.17it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.43it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.26it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:22, 14.27it/s]
Loading 0:  10%|█         | 37/363 [00:02<00:24, 13.40it/s]
Loading 0:  11%|█         | 39/363 [00:02<00:22, 14.22it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:28, 11.23it/s]
Loading 0:  13%|█▎        | 46/363 [00:03<00:19, 16.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:03<00:15, 19.77it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:22, 13.59it/s]
Loading 0:  15%|█▌        | 55/363 [00:03<00:24, 12.68it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:22, 13.35it/s]
Loading 0:  16%|█▋        | 59/363 [00:04<00:28, 10.80it/s]
Loading 0:  18%|█▊        | 64/363 [00:04<00:18, 15.80it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:15, 18.54it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:22, 13.07it/s]
Loading 0:  20%|██        | 73/363 [00:05<00:23, 12.10it/s]
Loading 0:  21%|██        | 75/363 [00:05<00:22, 12.70it/s]
Loading 0:  21%|██        | 77/363 [00:05<00:27, 10.23it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:18, 15.61it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 18.89it/s]
Loading 0:  25%|██▍       | 89/363 [00:06<00:19, 13.82it/s]
Loading 0:  25%|██▌       | 91/363 [00:06<00:20, 13.43it/s]
Loading 0:  26%|██▌       | 95/363 [00:06<00:15, 17.55it/s]
Loading 0:  27%|██▋       | 99/363 [00:06<00:12, 21.22it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.21it/s]
Loading 0:  29%|██▉       | 105/363 [00:07<00:18, 14.22it/s]
Loading 0:  29%|██▉       | 107/363 [00:07<00:19, 12.95it/s]
Loading 0:  30%|███       | 109/363 [00:07<00:20, 12.42it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.40it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:22, 11.12it/s]
Loading 0:  33%|███▎      | 118/363 [00:08<00:14, 17.12it/s]
Loading 0:  34%|███▎      | 122/363 [00:08<00:11, 20.51it/s]
Loading 0:  34%|███▍      | 125/363 [00:08<00:16, 14.21it/s]
Loading 0:  35%|███▍      | 127/363 [00:08<00:17, 13.48it/s]
Loading 0:  36%|███▌      | 129/363 [00:08<00:16, 14.36it/s]
Loading 0:  36%|███▌      | 131/363 [00:09<00:20, 11.41it/s]
Loading 0:  37%|███▋      | 136/363 [00:09<00:13, 16.88it/s]
Loading 0:  39%|███▊      | 140/363 [00:09<00:11, 19.79it/s]
Loading 0:  39%|███▉      | 143/363 [00:09<00:16, 13.67it/s]
Loading 0:  40%|███▉      | 145/363 [00:10<00:17, 12.62it/s]
Loading 0:  40%|████      | 147/363 [00:10<00:16, 13.21it/s]
Loading 0:  41%|████      | 149/363 [00:10<00:21, 10.15it/s]
Loading 0:  42%|████▏     | 154/363 [00:10<00:14, 14.76it/s]
Loading 0:  44%|████▎     | 158/363 [00:10<00:11, 17.19it/s]
Loading 0:  44%|████▍     | 161/363 [00:11<00:17, 11.81it/s]
Loading 0:  45%|████▍     | 163/363 [00:11<00:17, 11.29it/s]
Loading 0:  45%|████▌     | 165/363 [00:11<00:16, 12.23it/s]
Loading 0:  46%|████▌     | 167/363 [00:11<00:20,  9.76it/s]
Loading 0:  47%|████▋     | 172/363 [00:12<00:13, 14.35it/s]
Loading 0:  48%|████▊     | 176/363 [00:12<00:10, 17.33it/s]
Loading 0:  49%|████▉     | 179/363 [00:12<00:14, 13.13it/s]
Loading 0:  50%|████▉     | 181/363 [00:12<00:14, 12.96it/s]
Loading 0:  50%|█████     | 183/363 [00:12<00:12, 13.94it/s]
Loading 0:  51%|█████     | 185/363 [00:13<00:15, 11.66it/s]
Loading 0:  52%|█████▏    | 190/363 [00:13<00:09, 17.72it/s]
Loading 0:  53%|█████▎    | 194/363 [00:13<00:07, 21.57it/s]
Loading 0:  54%|█████▍    | 197/363 [00:13<00:10, 15.22it/s]
Loading 0:  55%|█████▌    | 200/363 [00:13<00:10, 15.67it/s]
Loading 0:  56%|█████▌    | 203/363 [00:29<04:08,  1.55s/it]
Loading 0:  57%|█████▋    | 207/363 [00:29<02:38,  1.02s/it]
Loading 0:  58%|█████▊    | 210/363 [00:30<01:54,  1.33it/s]
Loading 0:  59%|█████▊    | 213/363 [00:30<01:25,  1.75it/s]
Loading 0:  59%|█████▉    | 215/363 [00:30<01:10,  2.10it/s]
Loading 0:  60%|█████▉    | 217/363 [00:30<00:57,  2.56it/s]
Loading 0:  60%|██████    | 219/363 [00:30<00:44,  3.23it/s]
Loading 0:  61%|██████    | 221/363 [00:31<00:38,  3.66it/s]
Loading 0:  62%|██████▏   | 226/363 [00:31<00:21,  6.50it/s]
Loading 0:  63%|██████▎   | 230/363 [00:31<00:14,  8.95it/s]
Loading 0:  64%|██████▍   | 233/363 [00:31<00:15,  8.26it/s]
Loading 0:  65%|██████▍   | 235/363 [00:32<00:14,  8.64it/s]
Loading 0:  65%|██████▌   | 237/363 [00:32<00:12,  9.76it/s]
Loading 0:  66%|██████▌   | 239/363 [00:32<00:13,  8.91it/s]
Loading 0:  67%|██████▋   | 244/363 [00:32<00:08, 14.04it/s]
Loading 0:  68%|██████▊   | 248/363 [00:32<00:06, 17.53it/s]
Loading 0:  69%|██████▉   | 251/363 [00:33<00:08, 13.34it/s]
Loading 0:  70%|██████▉   | 253/363 [00:33<00:08, 13.03it/s]
Loading 0:  70%|███████   | 255/363 [00:33<00:07, 13.94it/s]
Loading 0:  71%|███████   | 257/363 [00:33<00:09, 11.56it/s]
Loading 0:  72%|███████▏  | 262/363 [00:33<00:05, 17.49it/s]
Loading 0:  73%|███████▎  | 266/363 [00:33<00:04, 20.67it/s]
Loading 0:  74%|███████▍  | 269/363 [00:34<00:06, 13.97it/s]
Loading 0:  75%|███████▍  | 272/363 [00:34<00:06, 14.65it/s]
Loading 0:  75%|███████▌  | 274/363 [00:34<00:06, 13.18it/s]
Loading 0:  76%|███████▌  | 276/363 [00:34<00:06, 12.71it/s]
Loading 0:  77%|███████▋  | 280/363 [00:35<00:04, 16.63it/s]
Loading 0:  78%|███████▊  | 284/363 [00:35<00:03, 20.15it/s]
Loading 0:  79%|███████▉  | 287/363 [00:35<00:05, 14.15it/s]
Loading 0:  80%|███████▉  | 289/363 [00:35<00:05, 13.62it/s]
Loading 0:  80%|████████  | 291/363 [00:35<00:05, 14.29it/s]
Loading 0:  81%|████████  | 293/363 [00:36<00:06, 10.68it/s]
Loading 0:  82%|████████▏ | 298/363 [00:36<00:04, 16.11it/s]
Loading 0:  83%|████████▎ | 302/363 [00:36<00:03, 19.59it/s]
Loading 0:  84%|████████▍ | 305/363 [00:36<00:04, 14.30it/s]
Loading 0:  85%|████████▍ | 307/363 [00:36<00:04, 13.53it/s]
Loading 0:  85%|████████▌ | 309/363 [00:37<00:03, 14.35it/s]
Loading 0:  86%|████████▌ | 311/363 [00:37<00:04, 11.65it/s]
Loading 0:  87%|████████▋ | 316/363 [00:37<00:02, 17.61it/s]
Loading 0:  88%|████████▊ | 320/363 [00:37<00:02, 21.23it/s]
Loading 0:  89%|████████▉ | 323/363 [00:37<00:02, 15.00it/s]
Loading 0:  90%|████████▉ | 326/363 [00:38<00:02, 15.54it/s]
Loading 0:  90%|█████████ | 328/363 [00:38<00:02, 13.65it/s]
Loading 0:  91%|█████████ | 330/363 [00:38<00:02, 13.10it/s]
Loading 0:  92%|█████████▏| 334/363 [00:38<00:01, 17.27it/s]
Loading 0:  93%|█████████▎| 338/363 [00:38<00:01, 20.84it/s]
Loading 0:  94%|█████████▍| 341/363 [00:39<00:01, 14.56it/s]
Loading 0:  94%|█████████▍| 343/363 [00:39<00:01, 13.86it/s]
Loading 0:  95%|█████████▌| 345/363 [00:39<00:01, 14.61it/s]
Loading 0:  96%|█████████▌| 347/363 [00:39<00:01, 11.50it/s]
Loading 0:  97%|█████████▋| 352/363 [00:39<00:00, 17.15it/s]
Loading 0:  98%|█████████▊| 356/363 [00:39<00:00, 20.49it/s]
Loading 0:  99%|█████████▉| 359/363 [00:40<00:00, 10.30it/s]
Loading 0:  99%|█████████▉| 361/363 [00:40<00:00,  9.41it/s]
                                                            
Job chaiml-grok-payloads-gr-12038-v3-mkmlizer completed after 354.4s with status: succeeded
Stopping job with name chaiml-grok-payloads-gr-12038-v3-mkmlizer
Pipeline stage MKMLizer completed in 355.34s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.23s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service chaiml-grok-payloads-gr-12038-v3
Waiting for inference service chaiml-grok-payloads-gr-12038-v3 to be ready
Inference service chaiml-grok-payloads-gr-12038-v3 ready after 211.69129729270935s
Pipeline stage MKMLDeployer completed in 212.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 3.2717456817626953s
Received healthy response to inference request in 2.953047275543213s
Received healthy response to inference request in 2.1703708171844482s
Received healthy response to inference request in 2.069171667098999s
Received healthy response to inference request in 2.336779832839966s
5 requests
0 failed requests
5th percentile: 2.089411497116089
10th percentile: 2.1096513271331787
20th percentile: 2.1501309871673584
30th percentile: 2.2036526203155518
40th percentile: 2.270216226577759
50th percentile: 2.336779832839966
60th percentile: 2.5832868099212645
70th percentile: 2.8297937870025636
80th percentile: 3.0167869567871093
90th percentile: 3.1442663192749025
95th percentile: 3.208006000518799
99th percentile: 3.258997745513916
mean time: 2.5602230548858644
Pipeline stage StressChecker completed in 14.55s
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 0.83s
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 1.07s
Shutdown handler de-registered
chaiml-grok-payloads-gr_12038_v3 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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5839.43s
Shutdown handler de-registered
chaiml-grok-payloads-gr_12038_v3 status is now inactive due to auto deactivation removed underperforming models
chaiml-grok-payloads-gr_12038_v3 status is now torndown due to DeploymentManager action