rirv938-groksyn-grpo-cp_67088

developer_uid: rirv938

submission_id: rirv938-groksyn-grpo-cp_67088_v1

model_name: rirv938-groksyn-grpo-cp_67088_v1

model_group: rirv938/groksyn_grpo_cp3

status: torndown

timestamp: 2025-07-04T02:08:31+00:00

num_battles: 6005

num_wins: 3001

celo_rating: 1289.67

family_friendly_score: 0.5344

family_friendly_standard_error: 0.007054312723433801

submission_type: basic

model_repo: rirv938/groksyn_grpo_cp312_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 768

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5442839994611953, 'latency_mean': 1.8371750795841217, 'latency_p50': 1.833587408065796, 'latency_p90': 2.0524515867233277}, {'batch_size': 3, 'throughput': 1.1368589910019484, 'latency_mean': 2.6260291492938994, 'latency_p50': 2.6219974756240845, 'latency_p90': 2.933555340766907}, {'batch_size': 5, 'throughput': 1.4774820769033425, 'latency_mean': 3.3616284275054933, 'latency_p50': 3.3563015460968018, 'latency_p90': 3.768356156349182}, {'batch_size': 6, 'throughput': 1.610595630185931, 'latency_mean': 3.6928582870960236, 'latency_p50': 3.708861827850342, 'latency_p90': 4.119208669662475}, {'batch_size': 8, 'throughput': 1.7923153617385754, 'latency_mean': 4.42775955915451, 'latency_p50': 4.433256149291992, 'latency_p90': 5.008806753158569}, {'batch_size': 10, 'throughput': 1.887019274812971, 'latency_mean': 5.224240727424622, 'latency_p50': 5.205143451690674, 'latency_p90': 5.911608719825745}]

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

display_name: rirv938-groksyn-grpo-cp_67088_v1

is_internal_developer: True

language_model: rirv938/groksyn_grpo_cp312_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.63

us_pacific_date: 2025-07-03

win_ratio: 0.49975020815986676

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': 768, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', '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-groksyn-grpo-cp-67088-v1-mkmlizer
Waiting for job on rirv938-groksyn-grpo-cp-67088-v1-mkmlizer to finish
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ║                                                                     ║
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Downloaded to shared memory in 166.175s
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Checking if rirv938/groksyn_grpo_cp312_98ff_b35_r1_merged already exists in ChaiML
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Creating repo ChaiML/groksyn_grpo_cp312_98ff_b35_r1_merged and uploading /tmp/tmpov2vdp_f to it
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:04<01:40,  4.79s/it]
  9%|▉         | 2/22 [00:08<01:25,  4.28s/it]
 14%|█▎        | 3/22 [00:14<01:33,  4.94s/it]
 18%|█▊        | 4/22 [00:22<01:51,  6.21s/it]
 23%|██▎       | 5/22 [00:30<01:58,  6.96s/it]
 27%|██▋       | 6/22 [00:39<01:57,  7.37s/it]
 32%|███▏      | 7/22 [00:43<01:34,  6.32s/it]
 36%|███▋      | 8/22 [00:46<01:16,  5.44s/it]
 41%|████      | 9/22 [00:50<01:02,  4.82s/it]
 45%|████▌     | 10/22 [00:53<00:52,  4.38s/it]
 50%|█████     | 11/22 [00:57<00:45,  4.12s/it]
 55%|█████▍    | 12/22 [01:01<00:41,  4.15s/it]
 59%|█████▉    | 13/22 [01:09<00:48,  5.37s/it]
 64%|██████▎   | 14/22 [01:13<00:39,  4.90s/it]
 68%|██████▊   | 15/22 [01:18<00:34,  4.95s/it]
 73%|███████▎  | 16/22 [01:21<00:27,  4.51s/it]
 77%|███████▋  | 17/22 [01:25<00:21,  4.23s/it]
 82%|████████▏ | 18/22 [01:29<00:16,  4.22s/it]
 86%|████████▋ | 19/22 [01:33<00:11,  3.99s/it]
 91%|█████████ | 20/22 [01:41<00:10,  5.26s/it]
 95%|█████████▌| 21/22 [01:46<00:05,  5.18s/it]
100%|██████████| 22/22 [01:47<00:00,  4.05s/it]
100%|██████████| 22/22 [01:47<00:00,  4.90s/it]
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpov2vdp_f, device:0
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: quantized model in 56.199s
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Processed model rirv938/groksyn_grpo_cp312_98ff_b35_r1_merged in 422.071s
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/config.json
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/special_tokens_map.json
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/tokenizer_config.json
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/tokenizer.json
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/flywheel_model.1.safetensors
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-groksyn-grpo-cp-67088-v1/nvidia/flywheel_model.0.safetensors
rirv938-groksyn-grpo-cp-67088-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.38it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:24, 14.41it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.98it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.59it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 13.05it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.63it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.49it/s]
Loading 0:   8%|▊         | 29/363 [00:01<00:15, 20.97it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:15, 21.97it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 14.99it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.72it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:26, 12.35it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.28it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:22, 13.86it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 15.83it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:20, 14.45it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.27it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.98it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.79it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.43it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.93it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.33it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.85it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:19, 13.92it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.84it/s]
Loading 0:  28%|██▊       | 100/363 [00:05<00:11, 22.97it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:14, 17.92it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.19it/s]
Loading 0:  30%|███       | 110/363 [00:06<00:16, 15.07it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:20, 12.38it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.01it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 20.09it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 14.88it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:15, 15.58it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.69it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.85it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.43it/s]
Loading 0:  40%|███▉      | 144/363 [00:08<00:15, 13.99it/s]
Loading 0:  40%|████      | 147/363 [00:08<00:13, 15.87it/s]
Loading 0:  41%|████▏     | 150/363 [00:09<00:14, 14.57it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.35it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:10, 19.21it/s]
Loading 0:  45%|████▍     | 162/363 [00:09<00:13, 14.79it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:11, 16.74it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:12, 15.12it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 19.03it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 22.82it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.32it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.86it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 12.97it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.02it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.96it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 15.41it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.17it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:43,  1.40s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:24,  1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:45,  1.45it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.91it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<01:00,  2.44it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:43,  3.31it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:33,  4.19it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.14it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.59it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:14,  8.67it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.18it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.51it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 14.08it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.66it/s]
Loading 0:  69%|██████▉   | 252/363 [00:29<00:08, 12.87it/s]
Loading 0:  70%|███████   | 255/363 [00:30<00:07, 14.86it/s]
Loading 0:  71%|███████   | 258/363 [00:30<00:07, 13.89it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.70it/s]
Loading 0:  74%|███████▎  | 267/363 [00:30<00:05, 18.32it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:06, 14.33it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 16.46it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:05, 14.90it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.89it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 22.68it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 16.11it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.80it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.89it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 17.99it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.09it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.99it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 16.61it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:03, 13.09it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.30it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:01, 21.90it/s]
Loading 0:  89%|████████▉ | 324/363 [00:34<00:02, 14.10it/s]
Loading 0:  90%|█████████ | 327/363 [00:34<00:02, 16.22it/s]
Loading 0:  91%|█████████ | 330/363 [00:34<00:02, 14.61it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.16it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 21.53it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.76it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.39it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 12.97it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.05it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.53it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00, 11.79it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 11.70it/s]
                                                            
Job rirv938-groksyn-grpo-cp-67088-v1-mkmlizer completed after 456.7s with status: succeeded
Stopping job with name rirv938-groksyn-grpo-cp-67088-v1-mkmlizer
Pipeline stage MKMLizer completed in 457.57s
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-groksyn-grpo-cp-67088-v1
Waiting for inference service rirv938-groksyn-grpo-cp-67088-v1 to be ready
Inference service rirv938-groksyn-grpo-cp-67088-v1 ready after 221.21329593658447s
Pipeline stage MKMLDeployer completed in 221.76s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6032626628875732s
Received healthy response to inference request in 1.8756659030914307s
Received healthy response to inference request in 2.0255284309387207s
Received healthy response to inference request in 1.153198003768921s
Received healthy response to inference request in 1.3274297714233398s
5 requests
0 failed requests
5th percentile: 1.1880443572998047
10th percentile: 1.2228907108306886
20th percentile: 1.292583417892456
30th percentile: 1.437076997756958
40th percentile: 1.6563714504241944
50th percentile: 1.8756659030914307
60th percentile: 1.9356109142303466
70th percentile: 1.9955559253692627
80th percentile: 2.141075277328491
90th percentile: 2.3721689701080324
95th percentile: 2.487715816497803
99th percentile: 2.580153293609619
mean time: 1.7970169544219972
Pipeline stage StressChecker completed in 11.06s
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 0.72s
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 0.80s
Shutdown handler de-registered
rirv938-groksyn-grpo-cp_67088_v1 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 0.16s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.10s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-groksyn-grpo-cp-67088-v1-profiler
Waiting for inference service rirv938-groksyn-grpo-cp-67088-v1-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 3367.78s
Shutdown handler de-registered
rirv938-groksyn-grpo-cp_67088_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-groksyn-grpo-cp_67088_v1 status is now torndown due to DeploymentManager action