rirv938-simp-grpo-cp624_96435

developer_uid: rirv938

submission_id: rirv938-simp-grpo-cp624_96435_v1

model_name: rirv938-simp-grpo-cp624_96435_v1

model_group: rirv938/simp_grpo_cp624_

status: torndown

timestamp: 2025-06-30T20:30:20+00:00

num_battles: 9118

num_wins: 4779

celo_rating: 1302.03

family_friendly_score: 0.4858

family_friendly_standard_error: 0.0070682156164056

submission_type: basic

model_repo: rirv938/simp_grpo_cp624_96ff_b3_r1_12m_US_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': 0.5507420156658491, 'latency_mean': 1.8156158244609832, 'latency_p50': 1.788088083267212, 'latency_p90': 2.0306756496429443}, {'batch_size': 3, 'throughput': 1.1361501850042726, 'latency_mean': 2.6282697677612306, 'latency_p50': 2.643708825111389, 'latency_p90': 2.9245172500610352}, {'batch_size': 5, 'throughput': 1.4852971007639457, 'latency_mean': 3.3444335877895357, 'latency_p50': 3.354040741920471, 'latency_p90': 3.7022752523422238}, {'batch_size': 6, 'throughput': 1.6085667790666796, 'latency_mean': 3.709936598539352, 'latency_p50': 3.709652304649353, 'latency_p90': 4.185380220413208}, {'batch_size': 8, 'throughput': 1.7668127625193586, 'latency_mean': 4.474188247919082, 'latency_p50': 4.469796180725098, 'latency_p90': 5.009371900558471}, {'batch_size': 10, 'throughput': 1.8883262276176935, 'latency_mean': 5.221636025905609, 'latency_p50': 5.184547424316406, 'latency_p90': 5.917107057571411}]

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

display_name: rirv938-simp-grpo-cp624_96435_v1

is_internal_developer: True

language_model: rirv938/simp_grpo_cp624_96ff_b3_r1_12m_US_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.61

us_pacific_date: 2025-06-30

win_ratio: 0.5241280982671639

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': ['\n', '</s>', 'You:', '###'], '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-cp624-96435-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp624-96435-v1-mkmlizer to finish
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Downloaded to shared memory in 152.499s
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Checking if rirv938/simp_grpo_cp624_96ff_b3_r1_12m_US_merged already exists in ChaiML
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp624_96ff_b3_r1_12m_US_merged and uploading /tmp/tmp4k9_rkxj to it
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: 
  0%|          | 0/22 [00:00<?, ?it/s]
  5%|▍         | 1/22 [00:04<01:29,  4.28s/it]
  9%|▉         | 2/22 [00:09<01:30,  4.54s/it]
 14%|█▎        | 3/22 [00:12<01:15,  4.00s/it]
 18%|█▊        | 4/22 [00:17<01:22,  4.59s/it]
 23%|██▎       | 5/22 [00:21<01:13,  4.33s/it]
 27%|██▋       | 6/22 [00:25<01:07,  4.24s/it]
 32%|███▏      | 7/22 [00:29<01:00,  4.06s/it]
 36%|███▋      | 8/22 [00:37<01:12,  5.18s/it]
 41%|████      | 9/22 [00:45<01:19,  6.09s/it]
 45%|████▌     | 10/22 [00:49<01:07,  5.66s/it]
 50%|█████     | 11/22 [00:54<00:57,  5.23s/it]
 55%|█████▍    | 12/22 [01:00<00:54,  5.48s/it]
 59%|█████▉    | 13/22 [01:08<00:56,  6.27s/it]
 64%|██████▎   | 14/22 [01:11<00:42,  5.36s/it]
 68%|██████▊   | 15/22 [01:15<00:33,  4.85s/it]
 73%|███████▎  | 16/22 [01:18<00:26,  4.44s/it]
 77%|███████▋  | 17/22 [01:23<00:22,  4.50s/it]
 82%|████████▏ | 18/22 [01:29<00:20,  5.15s/it]
 86%|████████▋ | 19/22 [01:33<00:14,  4.76s/it]
 91%|█████████ | 20/22 [01:41<00:11,  5.77s/it]
 95%|█████████▌| 21/22 [01:45<00:05,  5.08s/it]
100%|██████████| 22/22 [01:46<00:00,  3.98s/it]
100%|██████████| 22/22 [01:46<00:00,  4.86s/it]
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp4k9_rkxj, device:0
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: quantized model in 56.254s
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Processed model rirv938/simp_grpo_cp624_96ff_b3_r1_12m_US_merged in 408.376s
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/config.json
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/special_tokens_map.json
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/tokenizer_config.json
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/tokenizer.json
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/flywheel_model.1.safetensors
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp624-96435-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp624-96435-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:16, 21.82it/s]
Loading 0:   2%|▏         | 7/363 [00:00<00:19, 18.33it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:15, 22.48it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:25, 13.80it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:25, 13.52it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:19, 17.22it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.57it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 19.41it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.80it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:20, 16.02it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:19, 16.84it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:24, 13.31it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 18.58it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.86it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:19, 15.92it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:18, 16.66it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:22, 13.23it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 18.11it/s]
Loading 0:  19%|█▊        | 68/363 [00:03<00:13, 21.35it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.90it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.71it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:21, 13.21it/s]
Loading 0:  23%|██▎       | 82/363 [00:04<00:15, 18.31it/s]
Loading 0:  24%|██▎       | 86/363 [00:04<00:12, 21.36it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:17, 15.34it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:16, 16.02it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.81it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.54it/s]
Loading 0:  28%|██▊       | 102/363 [00:05<00:12, 20.30it/s]
Loading 0:  29%|██▉       | 105/363 [00:06<00:16, 15.61it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:18, 14.22it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:18, 13.53it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:17, 14.52it/s]
Loading 0:  31%|███       | 113/363 [00:06<00:21, 11.84it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 18.14it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:10, 21.96it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.57it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 16.44it/s]
Loading 0:  36%|███▌      | 131/363 [00:07<00:18, 12.84it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.97it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.34it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.62it/s]
Loading 0:  40%|████      | 146/363 [00:08<00:13, 16.45it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 13.26it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 18.47it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.70it/s]
Loading 0:  44%|████▍     | 161/363 [00:09<00:12, 16.16it/s]
Loading 0:  45%|████▌     | 164/363 [00:09<00:11, 16.89it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:14, 13.45it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 18.57it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 21.90it/s]
Loading 0:  49%|████▉     | 179/363 [00:10<00:11, 16.16it/s]
Loading 0:  50%|█████     | 182/363 [00:10<00:10, 16.91it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:13, 13.39it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.55it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.76it/s]
Loading 0:  54%|█████▍    | 197/363 [00:11<00:10, 16.15it/s]
Loading 0:  55%|█████▌    | 200/363 [00:11<00:09, 16.76it/s]
Loading 0:  56%|█████▌    | 203/363 [00:26<03:42,  1.39s/it]
Loading 0:  57%|█████▋    | 207/363 [00:26<02:24,  1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [00:26<01:45,  1.45it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.91it/s]
Loading 0:  60%|█████▉    | 216/363 [00:27<00:59,  2.46it/s]
Loading 0:  60%|██████    | 219/363 [00:27<00:43,  3.34it/s]
Loading 0:  61%|██████    | 222/363 [00:27<00:33,  4.24it/s]
Loading 0:  62%|██████▏   | 226/363 [00:27<00:22,  6.18it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.56it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:14,  8.68it/s]
Loading 0:  65%|██████▌   | 236/363 [00:28<00:12, 10.13it/s]
Loading 0:  66%|██████▌   | 239/363 [00:28<00:12,  9.55it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 13.96it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 17.15it/s]
Loading 0:  69%|██████▉   | 251/363 [00:29<00:08, 13.90it/s]
Loading 0:  70%|██████▉   | 254/363 [00:29<00:07, 15.04it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.44it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.49it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.80it/s]
Loading 0:  74%|███████▍  | 269/363 [00:30<00:06, 15.66it/s]
Loading 0:  75%|███████▍  | 272/363 [00:30<00:05, 16.47it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 13.07it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 18.10it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 21.27it/s]
Loading 0:  79%|███████▉  | 287/363 [00:31<00:04, 15.79it/s]
Loading 0:  80%|███████▉  | 290/363 [00:31<00:04, 16.51it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 13.18it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 18.12it/s]
Loading 0:  83%|████████▎ | 302/363 [00:32<00:02, 21.38it/s]
Loading 0:  84%|████████▍ | 305/363 [00:32<00:03, 15.99it/s]
Loading 0:  85%|████████▍ | 308/363 [00:32<00:03, 16.65it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:03, 13.24it/s]
Loading 0:  87%|████████▋ | 316/363 [00:33<00:02, 18.32it/s]
Loading 0:  88%|████████▊ | 320/363 [00:33<00:01, 21.55it/s]
Loading 0:  89%|████████▉ | 323/363 [00:33<00:02, 15.95it/s]
Loading 0:  90%|████████▉ | 326/363 [00:33<00:02, 16.44it/s]
Loading 0:  91%|█████████ | 329/363 [00:34<00:02, 13.14it/s]
Loading 0:  92%|█████████▏| 334/363 [00:34<00:01, 18.29it/s]
Loading 0:  93%|█████████▎| 338/363 [00:34<00:01, 21.49it/s]
Loading 0:  94%|█████████▍| 341/363 [00:34<00:01, 15.97it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.62it/s]
Loading 0:  96%|█████████▌| 347/363 [00:35<00:01, 13.38it/s]
Loading 0:  97%|█████████▋| 352/363 [00:35<00:00, 18.40it/s]
Loading 0:  98%|█████████▊| 356/363 [00:35<00:00, 21.62it/s]
Loading 0:  99%|█████████▉| 359/363 [00:36<00:00, 11.94it/s]
Loading 0: 100%|█████████▉| 362/363 [00:36<00:00, 11.97it/s]
                                                            
Job rirv938-simp-grpo-cp624-96435-v1-mkmlizer completed after 433.35s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp624-96435-v1-mkmlizer
Pipeline stage MKMLizer completed in 433.85s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.47s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-simp-grpo-cp624-96435-v1
Waiting for inference service rirv938-simp-grpo-cp624-96435-v1 to be ready
Inference service rirv938-simp-grpo-cp624-96435-v1 ready after 210.87941122055054s
Pipeline stage MKMLDeployer completed in 211.44s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.769404888153076s
Received healthy response to inference request in 2.09420108795166s
Received healthy response to inference request in 1.9349727630615234s
Received healthy response to inference request in 1.8091561794281006s
Received healthy response to inference request in 1.8711333274841309s
5 requests
0 failed requests
5th percentile: 1.8215516090393067
10th percentile: 1.8339470386505128
20th percentile: 1.8587378978729248
30th percentile: 1.8839012145996095
40th percentile: 1.9094369888305665
50th percentile: 1.9349727630615234
60th percentile: 1.998664093017578
70th percentile: 2.0623554229736327
80th percentile: 2.2292418479919434
90th percentile: 2.4993233680725098
95th percentile: 2.634364128112793
99th percentile: 2.7423967361450194
mean time: 2.0957736492156984
Pipeline stage StressChecker completed in 11.71s
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 0.68s
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 0.69s
Shutdown handler de-registered
rirv938-simp-grpo-cp624_96435_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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 6036.05s
Shutdown handler de-registered
rirv938-simp-grpo-cp624_96435_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp624_96435_v1 status is now torndown due to DeploymentManager action