developer_uid: rirv938
submission_id: rirv938-simp-grpo-cp312_25497_v1
model_name: rirv938-simp-grpo-cp312_25497_v1
model_group: rirv938/simp_grpo_cp312_
status: torndown
timestamp: 2025-06-30T20:30:16+00:00
num_battles: 8492
num_wins: 4543
celo_rating: 1307.46
family_friendly_score: 0.4908
family_friendly_standard_error: 0.007069870720175865
submission_type: basic
model_repo: rirv938/simp_grpo_cp312_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': 0.5122844920523066, 'latency_mean': 1.9518843984603882, 'latency_p50': 1.958839774131775, 'latency_p90': 2.1700257778167726}, {'batch_size': 3, 'throughput': 1.0403380132195055, 'latency_mean': 2.869705003499985, 'latency_p50': 2.869490623474121, 'latency_p90': 3.1684336423873902}, {'batch_size': 5, 'throughput': 1.3612225122433643, 'latency_mean': 3.6455839395523073, 'latency_p50': 3.6581268310546875, 'latency_p90': 4.0701792478561405}, {'batch_size': 6, 'throughput': 1.4559919872785934, 'latency_mean': 4.0871614074707034, 'latency_p50': 4.057814598083496, 'latency_p90': 4.613384103775024}, {'batch_size': 8, 'throughput': 1.6062985470725057, 'latency_mean': 4.935116884708404, 'latency_p50': 4.937439203262329, 'latency_p90': 5.556915426254272}, {'batch_size': 10, 'throughput': 1.6717094674148083, 'latency_mean': 5.9216601753234865, 'latency_p50': 5.959613919258118, 'latency_p90': 6.541982245445251}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-simp-grpo-cp312_25497_v1
is_internal_developer: True
language_model: rirv938/simp_grpo_cp312_96ff_b3_r1_12m_US_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.38
us_pacific_date: 2025-06-30
win_ratio: 0.5349740932642487
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-cp312-25497-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp312-25497-v1-mkmlizer to finish
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Version: 0.29.3 ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ belonging to: ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Downloaded to shared memory in 156.069s
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Checking if rirv938/simp_grpo_cp312_96ff_b3_r1_12m_US_merged already exists in ChaiML
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp312_96ff_b3_r1_12m_US_merged and uploading /tmp/tmp2vd3q3nk to it
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:05<01:55, 5.50s/it] 9%|▉ | 2/22 [00:09<01:28, 4.44s/it] 14%|█▎ | 3/22 [00:13<01:18, 4.15s/it] 18%|█▊ | 4/22 [00:16<01:13, 4.08s/it] 23%|██▎ | 5/22 [00:21<01:10, 4.18s/it] 27%|██▋ | 6/22 [00:28<01:21, 5.11s/it] 32%|███▏ | 7/22 [00:31<01:08, 4.58s/it] 36%|███▋ | 8/22 [00:35<01:00, 4.32s/it] 41%|████ | 9/22 [00:40<00:58, 4.54s/it] 45%|████▌ | 10/22 [00:46<00:58, 4.85s/it] 50%|█████ | 11/22 [00:50<00:51, 4.65s/it] 55%|█████▍ | 12/22 [00:54<00:43, 4.39s/it] 59%|█████▉ | 13/22 [00:57<00:37, 4.11s/it] 64%|██████▎ | 14/22 [01:01<00:31, 3.96s/it] 68%|██████▊ | 15/22 [01:04<00:26, 3.83s/it] 73%|███████▎ | 16/22 [01:08<00:22, 3.73s/it] 77%|███████▋ | 17/22 [01:12<00:19, 3.87s/it] 82%|████████▏ | 18/22 [01:16<00:15, 3.96s/it] 86%|████████▋ | 19/22 [01:24<00:15, 5.27s/it] 91%|█████████ | 20/22 [01:31<00:11, 5.76s/it] 95%|█████████▌| 21/22 [01:38<00:06, 6.04s/it] 100%|██████████| 22/22 [01:39<00:00, 4.55s/it] 100%|██████████| 22/22 [01:39<00:00, 4.52s/it]
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp2vd3q3nk, device:0
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: quantized model in 57.290s
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Processed model rirv938/simp_grpo_cp312_96ff_b3_r1_12m_US_merged in 404.441s
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-25497-v1/config.json
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-25497-v1/special_tokens_map.json
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-25497-v1/tokenizer_config.json
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-25497-v1/tokenizer.json
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-25497-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp312-25497-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 3/363 [00:00<00:12, 28.81it/s] Loading 0: 2%|▏ | 6/363 [00:00<00:25, 13.98it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:16, 21.49it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:27, 12.65it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:28, 12.14it/s] Loading 0: 5%|▌ | 19/363 [00:01<00:22, 15.20it/s] Loading 0: 6%|▌ | 22/363 [00:01<00:23, 14.72it/s] Loading 0: 7%|▋ | 24/363 [00:01<00:24, 14.01it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 18.62it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.18it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:23, 13.88it/s] Loading 0: 10%|█ | 38/363 [00:02<00:22, 14.69it/s] Loading 0: 11%|█ | 40/363 [00:02<00:24, 13.00it/s] Loading 0: 12%|█▏ | 42/363 [00:02<00:25, 12.63it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 16.88it/s] Loading 0: 14%|█▍ | 50/363 [00:03<00:15, 20.76it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:21, 14.36it/s] Loading 0: 15%|█▌ | 55/363 [00:03<00:22, 13.86it/s] Loading 0: 16%|█▌ | 57/363 [00:03<00:20, 14.74it/s] Loading 0: 16%|█▋ | 59/363 [00:04<00:26, 11.63it/s] Loading 0: 18%|█▊ | 64/363 [00:04<00:17, 17.43it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 21.04it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:20, 14.48it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.43it/s] Loading 0: 21%|██ | 76/363 [00:05<00:20, 13.82it/s] Loading 0: 21%|██▏ | 78/363 [00:05<00:21, 13.49it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:15, 17.93it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:12, 21.89it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 15.13it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.67it/s] Loading 0: 26%|██▋ | 96/363 [00:06<00:13, 19.66it/s] Loading 0: 27%|██▋ | 99/363 [00:06<00:12, 21.62it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 19.55it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:17, 14.57it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:19, 13.35it/s] Loading 0: 30%|███ | 109/363 [00:07<00:19, 13.10it/s] Loading 0: 31%|███ | 111/363 [00:07<00:18, 13.98it/s] Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.42it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.88it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.72it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 14.90it/s] Loading 0: 35%|███▌ | 128/363 [00:08<00:14, 15.72it/s] Loading 0: 36%|███▌ | 131/363 [00:08<00:18, 12.44it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 17.61it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 20.96it/s] Loading 0: 39%|███▉ | 143/363 [00:09<00:14, 15.17it/s] Loading 0: 40%|████ | 146/363 [00:09<00:13, 15.89it/s] Loading 0: 41%|████ | 149/363 [00:09<00:17, 12.43it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:12, 17.34it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 20.59it/s] Loading 0: 44%|████▍ | 161/363 [00:10<00:13, 15.08it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 15.80it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:15, 12.55it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 17.58it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:09, 20.76it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:12, 15.20it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 15.91it/s] Loading 0: 51%|█████ | 185/363 [00:11<00:14, 12.59it/s] Loading 0: 52%|█████▏ | 190/363 [00:11<00:09, 17.54it/s] Loading 0: 53%|█████▎ | 194/363 [00:12<00:08, 20.62it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:11, 14.90it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 15.70it/s] Loading 0: 55%|█████▌ | 200/363 [00:27<00:10, 15.70it/s] Loading 0: 55%|█████▌ | 201/363 [00:27<04:31, 1.68s/it] Loading 0: 56%|█████▌ | 203/363 [00:27<03:28, 1.30s/it] Loading 0: 57%|█████▋ | 207/363 [00:27<02:02, 1.28it/s] Loading 0: 58%|█████▊ | 210/363 [00:27<01:25, 1.79it/s] Loading 0: 59%|█████▊ | 213/363 [00:27<01:02, 2.39it/s] Loading 0: 59%|█████▉ | 215/363 [00:28<00:51, 2.89it/s] Loading 0: 60%|█████▉ | 217/363 [00:28<00:41, 3.55it/s] Loading 0: 60%|██████ | 219/363 [00:28<00:32, 4.47it/s] Loading 0: 61%|██████ | 221/363 [00:28<00:28, 5.06it/s] Loading 0: 62%|██████▏ | 226/363 [00:28<00:15, 8.93it/s] Loading 0: 63%|██████▎ | 230/363 [00:28<00:10, 12.20it/s] Loading 0: 64%|██████▍ | 233/363 [00:29<00:11, 10.85it/s] Loading 0: 65%|██████▌ | 236/363 [00:29<00:10, 12.34it/s] Loading 0: 66%|██████▌ | 239/363 [00:29<00:11, 10.78it/s] Loading 0: 67%|██████▋ | 244/363 [00:29<00:07, 15.55it/s] Loading 0: 68%|██████▊ | 248/363 [00:30<00:06, 18.91it/s] Loading 0: 69%|██████▉ | 251/363 [00:30<00:07, 14.33it/s] Loading 0: 70%|██████▉ | 254/363 [00:30<00:07, 15.21it/s] Loading 0: 71%|███████ | 257/363 [00:30<00:08, 12.16it/s] Loading 0: 72%|███████▏ | 262/363 [00:31<00:05, 17.11it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 20.38it/s] Loading 0: 74%|███████▍ | 269/363 [00:31<00:06, 15.17it/s] Loading 0: 75%|███████▍ | 272/363 [00:31<00:05, 16.00it/s] Loading 0: 76%|███████▌ | 275/363 [00:32<00:07, 12.54it/s] Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 17.51it/s] Loading 0: 78%|███████▊ | 284/363 [00:32<00:03, 20.75it/s] Loading 0: 79%|███████▉ | 287/363 [00:32<00:04, 15.38it/s] Loading 0: 80%|███████▉ | 290/363 [00:32<00:04, 15.98it/s] Loading 0: 81%|████████ | 293/363 [00:33<00:05, 12.68it/s] Loading 0: 82%|████████▏ | 298/363 [00:33<00:03, 17.56it/s] Loading 0: 83%|████████▎ | 302/363 [00:33<00:02, 20.84it/s] Loading 0: 84%|████████▍ | 305/363 [00:33<00:03, 15.24it/s] Loading 0: 85%|████████▍ | 308/363 [00:33<00:03, 16.06it/s] Loading 0: 86%|████████▌ | 311/363 [00:34<00:04, 12.83it/s] Loading 0: 87%|████████▋ | 316/363 [00:34<00:02, 17.87it/s] Loading 0: 88%|████████▊ | 320/363 [00:34<00:02, 21.06it/s] Loading 0: 89%|████████▉ | 323/363 [00:34<00:02, 15.49it/s] Loading 0: 90%|████████▉ | 326/363 [00:34<00:02, 16.19it/s] Loading 0: 91%|█████████ | 329/363 [00:35<00:02, 12.90it/s] Loading 0: 92%|█████████▏| 334/363 [00:35<00:01, 17.83it/s] Loading 0: 93%|█████████▎| 338/363 [00:35<00:01, 21.14it/s] Loading 0: 94%|█████████▍| 341/363 [00:35<00:01, 15.52it/s] Loading 0: 95%|█████████▍| 344/363 [00:36<00:01, 16.21it/s] Loading 0: 96%|█████████▌| 347/363 [00:36<00:01, 12.80it/s] Loading 0: 97%|█████████▋| 352/363 [00:36<00:00, 17.83it/s] Loading 0: 98%|█████████▊| 356/363 [00:36<00:00, 21.16it/s] Loading 0: 99%|█████████▉| 359/363 [00:37<00:00, 11.36it/s] Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.53it/s]
Job rirv938-simp-grpo-cp312-25497-v1-mkmlizer completed after 434.41s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp312-25497-v1-mkmlizer
Pipeline stage MKMLizer completed in 435.00s
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-simp-grpo-cp312-25497-v1
Waiting for inference service rirv938-simp-grpo-cp312-25497-v1 to be ready
Inference service rirv938-simp-grpo-cp312-25497-v1 ready after 201.2779746055603s
Pipeline stage MKMLDeployer completed in 201.83s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.6312501430511475s
Received healthy response to inference request in 2.144921064376831s
Received healthy response to inference request in 2.075854778289795s
Received healthy response to inference request in 2.3955540657043457s
Received healthy response to inference request in 2.240021228790283s
5 requests
0 failed requests
5th percentile: 2.089668035507202
10th percentile: 2.1034812927246094
20th percentile: 2.131107807159424
30th percentile: 2.1639410972595217
40th percentile: 2.2019811630249024
50th percentile: 2.240021228790283
60th percentile: 2.3022343635559084
70th percentile: 2.364447498321533
80th percentile: 2.442693281173706
90th percentile: 2.5369717121124267
95th percentile: 2.5841109275817873
99th percentile: 2.6218222999572753
mean time: 2.2975202560424806
Pipeline stage StressChecker completed in 12.87s
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 0.89s
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 0.65s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_25497_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 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-simp-grpo-cp312-25497-v1-profiler
Waiting for inference service rirv938-simp-grpo-cp312-25497-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 3364.41s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_25497_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp312_25497_v1 status is now torndown due to DeploymentManager action