rirv938-simp-grpo-cp312_84936

developer_uid: rirv938

submission_id: rirv938-simp-grpo-cp312_84936_v1

model_name: rirv938-simp-grpo-cp312_84936_v1

model_group: rirv938/simp_grpo_cp312_

status: torndown

timestamp: 2025-07-02T17:21:06+00:00

num_battles: 6254

num_wins: 3250

celo_rating: 1299.28

family_friendly_score: 0.4878

family_friendly_standard_error: 0.007068962583010325

submission_type: basic

model_repo: rirv938/simp_grpo_cp312_2ff_b35_r1_ava_rm_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': 0.5442478716208329, 'latency_mean': 1.837293223142624, 'latency_p50': 1.8481155633926392, 'latency_p90': 2.039307475090027}, {'batch_size': 3, 'throughput': 1.1444355152444161, 'latency_mean': 2.6109991347789765, 'latency_p50': 2.6222500801086426, 'latency_p90': 2.8704611539840696}, {'batch_size': 5, 'throughput': 1.4718406866533982, 'latency_mean': 3.378688534498215, 'latency_p50': 3.4078348875045776, 'latency_p90': 3.784842109680176}, {'batch_size': 6, 'throughput': 1.6059085094046515, 'latency_mean': 3.6979370772838593, 'latency_p50': 3.676754593849182, 'latency_p90': 4.1479713201522825}, {'batch_size': 8, 'throughput': 1.7946263262026345, 'latency_mean': 4.417666158676147, 'latency_p50': 4.418113589286804, 'latency_p90': 4.985701990127564}, {'batch_size': 10, 'throughput': 1.8987044345717863, 'latency_mean': 5.21827491402626, 'latency_p50': 5.224866628646851, 'latency_p90': 5.860755348205567}]

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

display_name: rirv938-simp-grpo-cp312_84936_v1

is_internal_developer: True

language_model: rirv938/simp_grpo_cp312_2ff_b35_r1_ava_rm_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-07-02

win_ratio: 0.5196674128557723

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:', '</s>', '###', '\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-simp-grpo-cp312-84936-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp312-84936-v1-mkmlizer to finish
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Version: 0.29.8                                                    ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Downloaded to shared memory in 167.641s
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Checking if rirv938/simp_grpo_cp312_2ff_b35_r1_ava_rm_merged already exists in ChaiML
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp312_2ff_b35_r1_ava_rm_merged and uploading /tmp/tmphwua5dwu to it
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:04<01:44,  4.96s/it]
  9%|▉         | 2/22 [00:13<02:19,  6.99s/it]
 14%|█▎        | 3/22 [00:18<01:58,  6.25s/it]
 18%|█▊        | 4/22 [00:22<01:32,  5.13s/it]
 23%|██▎       | 5/22 [00:25<01:17,  4.54s/it]
 27%|██▋       | 6/22 [00:33<01:32,  5.76s/it]
 32%|███▏      | 7/22 [00:38<01:19,  5.32s/it]
 36%|███▋      | 8/22 [00:41<01:07,  4.83s/it]
 41%|████      | 9/22 [00:45<00:58,  4.51s/it]
 45%|████▌     | 10/22 [00:49<00:50,  4.20s/it]
 50%|█████     | 11/22 [00:53<00:45,  4.16s/it]
 55%|█████▍    | 12/22 [00:58<00:45,  4.55s/it]
 59%|█████▉    | 13/22 [01:03<00:42,  4.74s/it]
 64%|██████▎   | 14/22 [01:12<00:45,  5.74s/it]
 68%|██████▊   | 15/22 [01:15<00:35,  5.06s/it]
 73%|███████▎  | 16/22 [01:23<00:35,  5.99s/it]
 77%|███████▋  | 17/22 [01:27<00:27,  5.40s/it]
 82%|████████▏ | 18/22 [01:35<00:24,  6.22s/it]
 86%|████████▋ | 19/22 [01:42<00:19,  6.45s/it]
 91%|█████████ | 20/22 [01:49<00:13,  6.58s/it]
 95%|█████████▌| 21/22 [01:55<00:06,  6.33s/it]
100%|██████████| 22/22 [01:56<00:00,  4.86s/it]
100%|██████████| 22/22 [01:56<00:00,  5.31s/it]
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmphwua5dwu, device:0
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: quantized model in 57.454s
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Processed model rirv938/simp_grpo_cp312_2ff_b35_r1_ava_rm_merged in 433.836s
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/config.json
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/special_tokens_map.json
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/tokenizer_config.json
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/tokenizer.json
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/flywheel_model.1.safetensors
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-84936-v1/nvidia/flywheel_model.0.safetensors
rirv938-simp-grpo-cp312-84936-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:17, 20.97it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 17.90it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.30it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.92it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.45it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.89it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.41it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.34it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.74it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.04it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.38it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.58it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.67it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 20.94it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.26it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 16.00it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:24, 12.45it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:17, 17.47it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:14, 20.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.75it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.48it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:23, 12.28it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 16.72it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:14, 19.66it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.11it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.49it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:15, 17.81it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.43it/s]
Loading 0:  28%|██▊       | 102/363 [00:06<00:13, 19.64it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:17, 14.82it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 13.57it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.25it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.22it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.41it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.92it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 21.96it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.70it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.41it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.52it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.77it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.11it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.01it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:14, 15.12it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:17, 12.17it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:12, 17.23it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 20.63it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:13, 15.28it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.82it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.57it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.62it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.14it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:11, 15.54it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.95it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.65it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.52it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.93it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.56it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.18it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:41,  1.39s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:23,  1.09it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:44,  1.46it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.92it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:59,  2.46it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:43,  3.34it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:33,  4.22it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.17it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.55it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:15,  8.63it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12, 10.09it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.43it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 13.63it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 16.89it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:08, 13.76it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.66it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.12it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.22it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.55it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 15.23it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 16.01it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.74it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.74it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 21.25it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.39it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 15.34it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 11.85it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:04, 16.07it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:03, 18.49it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:04, 13.63it/s]
Loading 0:  85%|████████▍ | 307/363 [00:33<00:04, 12.87it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 13.54it/s]
Loading 0:  86%|████████▌ | 311/363 [00:34<00:04, 11.02it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 16.04it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 18.85it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 13.52it/s]
Loading 0:  90%|████████▉ | 325/363 [00:34<00:02, 13.01it/s]
Loading 0:  90%|█████████ | 327/363 [00:35<00:02, 14.01it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 11.55it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.38it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 20.95it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.02it/s]
Loading 0:  95%|█████████▍| 344/363 [00:36<00:01, 15.32it/s]
Loading 0:  95%|█████████▌| 346/363 [00:36<00:01, 13.20it/s]
Loading 0:  96%|█████████▌| 348/363 [00:36<00:01, 12.21it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 15.74it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 18.58it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00,  9.58it/s]
Loading 0:  99%|█████████▉| 361/363 [00:37<00:00,  8.82it/s]
                                                            
Job rirv938-simp-grpo-cp312-84936-v1-mkmlizer completed after 515.32s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp312-84936-v1-mkmlizer
Pipeline stage MKMLizer completed in 515.87s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.37s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-simp-grpo-cp312-84936-v1
Waiting for inference service rirv938-simp-grpo-cp312-84936-v1 to be ready
Inference service rirv938-simp-grpo-cp312-84936-v1 ready after 210.80242037773132s
Pipeline stage MKMLDeployer completed in 211.47s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.9363155364990234s
Received healthy response to inference request in 2.1612396240234375s
Received healthy response to inference request in 2.448362350463867s
Received healthy response to inference request in 2.2584166526794434s
Received healthy response to inference request in 2.076979875564575s
5 requests
0 failed requests
5th percentile: 2.0938318252563475
10th percentile: 2.11068377494812
20th percentile: 2.144387674331665
30th percentile: 2.1806750297546387
40th percentile: 2.219545841217041
50th percentile: 2.2584166526794434
60th percentile: 2.334394931793213
70th percentile: 2.4103732109069824
80th percentile: 2.5459529876708986
90th percentile: 2.741134262084961
95th percentile: 2.838724899291992
99th percentile: 2.916797409057617
mean time: 2.3762628078460692
Pipeline stage StressChecker completed in 13.35s
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 0.79s
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 0.89s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_84936_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 3205.11s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_84936_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp312_84936_v1 status is now torndown due to DeploymentManager action