developer_uid: rirv938
submission_id: rirv938-simp-grpo-cp312-_8272_v1
model_name: rirv938-simp-grpo-cp312-_8272_v1
model_group: rirv938/simp_grpo_cp312_
status: torndown
timestamp: 2025-07-01T02:06:20+00:00
num_battles: 9866
num_wins: 5090
celo_rating: 1299.59
family_friendly_score: 0.4942
family_friendly_standard_error: 0.007070592054418074
submission_type: basic
model_repo: rirv938/simp_grpo_cp312_98ff_b3_r2_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': 0.5422701499472823, 'latency_mean': 1.8439810180664062, 'latency_p50': 1.8601669073104858, 'latency_p90': 2.0467966079711912}, {'batch_size': 3, 'throughput': 1.1385995158957345, 'latency_mean': 2.632238507270813, 'latency_p50': 2.6351691484451294, 'latency_p90': 2.908034634590149}, {'batch_size': 5, 'throughput': 1.467502179825407, 'latency_mean': 3.381138631105423, 'latency_p50': 3.3772783279418945, 'latency_p90': 3.7347443819046022}, {'batch_size': 6, 'throughput': 1.6032591736048358, 'latency_mean': 3.7006522035598755, 'latency_p50': 3.667320489883423, 'latency_p90': 4.1358069896698}, {'batch_size': 8, 'throughput': 1.7590173557912088, 'latency_mean': 4.514506351947785, 'latency_p50': 4.47449517250061, 'latency_p90': 5.0897475481033325}, {'batch_size': 10, 'throughput': 1.8972796162869514, 'latency_mean': 5.2097963774204255, 'latency_p50': 5.161553621292114, 'latency_p90': 5.864894556999206}]
gpu_counts: {'NVIDIA A100-SXM4-80GB': 1}
display_name: rirv938-simp-grpo-cp312-_8272_v1
is_internal_developer: True
language_model: rirv938/simp_grpo_cp312_98ff_b3_r2_12m_US_merged
model_size: 24B
ranking_group: single
throughput_3p7s: 1.62
us_pacific_date: 2025-06-30
win_ratio: 0.5159132373809041
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-cp312-8272-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp312-8272-v1-mkmlizer to finish
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ██████ ██████ █████ ████ ████ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░░██████ ██████ ░░███ ███░ ░░███ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░███░█████░███ ░███ ███ ░███ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░███░░███ ░███ ░███████ ░███ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░███ ░░░ ░███ ░███░░███ ░███ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░███ ░███ ░███ ░░███ ░███ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ █████ █████ █████ ░░████ █████ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ░░░░░ ░░░░░ ░░░░░ ░░░░ ░░░░░ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Version: 0.29.3 ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Features: FLYWHEEL, CUDA ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Copyright 2023-2025 MK ONE TECHNOLOGIES Inc. ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ https://mk1.ai ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ The license key for the current software has been verified as ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ belonging to: ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Chai Research Corp. ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ Expiration: 2028-03-31 23:59:59 ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ║ ║
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Downloaded to shared memory in 174.264s
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Checking if rirv938/simp_grpo_cp312_98ff_b3_r2_12m_US_merged already exists in ChaiML
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp312_98ff_b3_r2_12m_US_merged and uploading /tmp/tmpyn7yq047 to it
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: 0%| | 0/22 [00:00<?, ?it/s] 5%|▍ | 1/22 [00:03<01:20, 3.83s/it] 9%|▉ | 2/22 [00:10<01:51, 5.55s/it] 14%|█▎ | 3/22 [00:15<01:39, 5.25s/it] 18%|█▊ | 4/22 [00:21<01:39, 5.53s/it] 23%|██▎ | 5/22 [00:27<01:38, 5.79s/it] 27%|██▋ | 6/22 [00:31<01:19, 4.99s/it] 32%|███▏ | 7/22 [00:34<01:07, 4.51s/it] 36%|███▋ | 8/22 [00:38<00:58, 4.15s/it] 41%|████ | 9/22 [00:42<00:56, 4.32s/it] 45%|████▌ | 10/22 [00:46<00:48, 4.04s/it] 50%|█████ | 11/22 [00:50<00:44, 4.08s/it] 55%|█████▍ | 12/22 [00:54<00:41, 4.19s/it] 59%|█████▉ | 13/22 [00:59<00:39, 4.36s/it] 64%|██████▎ | 14/22 [01:03<00:33, 4.23s/it] 68%|██████▊ | 15/22 [01:10<00:34, 4.94s/it] 73%|███████▎ | 16/22 [01:13<00:27, 4.65s/it] 77%|███████▋ | 17/22 [01:17<00:21, 4.32s/it] 82%|████████▏ | 18/22 [01:21<00:17, 4.33s/it] 86%|████████▋ | 19/22 [01:25<00:12, 4.18s/it] 91%|█████████ | 20/22 [01:33<00:10, 5.36s/it] 95%|█████████▌| 21/22 [01:39<00:05, 5.46s/it] 100%|██████████| 22/22 [01:40<00:00, 4.24s/it] 100%|██████████| 22/22 [01:40<00:00, 4.59s/it]
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpyn7yq047, device:0
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: quantized model in 57.631s
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Processed model rirv938/simp_grpo_cp312_98ff_b3_r2_12m_US_merged in 424.475s
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/config.json
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/special_tokens_map.json
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/tokenizer_config.json
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/tokenizer.json
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/flywheel_model.1.safetensors
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-8272-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp312-8272-v1-mkmlizer: Loading 0: 0%| | 0/363 [00:00<?, ?it/s] Loading 0: 1%| | 4/363 [00:00<00:17, 20.88it/s] Loading 0: 2%|▏ | 7/363 [00:00<00:19, 17.81it/s] Loading 0: 3%|▎ | 11/363 [00:00<00:16, 21.75it/s] Loading 0: 4%|▍ | 14/363 [00:00<00:25, 13.43it/s] Loading 0: 4%|▍ | 16/363 [00:01<00:26, 13.10it/s] Loading 0: 6%|▌ | 21/363 [00:01<00:20, 16.63it/s] Loading 0: 6%|▋ | 23/363 [00:01<00:25, 13.31it/s] Loading 0: 8%|▊ | 28/363 [00:01<00:17, 18.93it/s] Loading 0: 9%|▉ | 32/363 [00:01<00:14, 22.16it/s] Loading 0: 10%|▉ | 35/363 [00:02<00:21, 15.43it/s] Loading 0: 10%|█ | 38/363 [00:02<00:20, 15.99it/s] Loading 0: 11%|█▏ | 41/363 [00:02<00:25, 12.62it/s] Loading 0: 13%|█▎ | 46/363 [00:02<00:18, 17.61it/s] Loading 0: 14%|█▍ | 50/363 [00:02<00:15, 20.68it/s] Loading 0: 15%|█▍ | 53/363 [00:03<00:20, 15.10it/s] Loading 0: 15%|█▌ | 56/363 [00:03<00:19, 15.69it/s] Loading 0: 16%|█▋ | 59/363 [00:03<00:24, 12.45it/s] Loading 0: 18%|█▊ | 64/363 [00:03<00:17, 17.28it/s] Loading 0: 19%|█▊ | 68/363 [00:04<00:14, 20.16it/s] Loading 0: 20%|█▉ | 71/363 [00:04<00:19, 14.80it/s] Loading 0: 20%|██ | 74/363 [00:04<00:18, 15.51it/s] Loading 0: 21%|██ | 77/363 [00:04<00:23, 12.23it/s] Loading 0: 23%|██▎ | 82/363 [00:05<00:16, 16.89it/s] Loading 0: 24%|██▎ | 86/363 [00:05<00:13, 20.09it/s] Loading 0: 25%|██▍ | 89/363 [00:05<00:18, 14.78it/s] Loading 0: 25%|██▌ | 92/363 [00:05<00:17, 15.35it/s] Loading 0: 26%|██▋ | 96/363 [00:05<00:14, 19.03it/s] Loading 0: 27%|██▋ | 99/363 [00:05<00:12, 21.05it/s] Loading 0: 28%|██▊ | 102/363 [00:06<00:13, 19.35it/s] Loading 0: 29%|██▉ | 105/363 [00:06<00:17, 14.88it/s] Loading 0: 29%|██▉ | 107/363 [00:06<00:18, 13.66it/s] Loading 0: 30%|███ | 109/363 [00:06<00:19, 13.17it/s] Loading 0: 31%|███ | 111/363 [00:06<00:17, 14.16it/s] Loading 0: 31%|███ | 113/363 [00:07<00:21, 11.61it/s] Loading 0: 33%|███▎ | 118/363 [00:07<00:13, 17.98it/s] Loading 0: 34%|███▎ | 122/363 [00:07<00:11, 21.62it/s] Loading 0: 34%|███▍ | 125/363 [00:07<00:15, 15.36it/s] Loading 0: 35%|███▌ | 128/363 [00:07<00:14, 16.07it/s] Loading 0: 36%|███▌ | 131/363 [00:08<00:18, 12.74it/s] Loading 0: 37%|███▋ | 136/363 [00:08<00:12, 17.84it/s] Loading 0: 39%|███▊ | 140/363 [00:08<00:10, 21.24it/s] Loading 0: 39%|███▉ | 143/363 [00:08<00:14, 15.61it/s] Loading 0: 40%|████ | 146/363 [00:09<00:13, 16.30it/s] Loading 0: 41%|████ | 149/363 [00:09<00:16, 12.83it/s] Loading 0: 42%|████▏ | 154/363 [00:09<00:11, 17.83it/s] Loading 0: 44%|████▎ | 158/363 [00:09<00:09, 21.14it/s] Loading 0: 44%|████▍ | 161/363 [00:09<00:13, 15.42it/s] Loading 0: 45%|████▌ | 164/363 [00:10<00:12, 16.11it/s] Loading 0: 46%|████▌ | 167/363 [00:10<00:15, 12.89it/s] Loading 0: 47%|████▋ | 172/363 [00:10<00:10, 17.43it/s] Loading 0: 48%|████▊ | 176/363 [00:10<00:09, 20.55it/s] Loading 0: 49%|████▉ | 179/363 [00:11<00:11, 15.35it/s] Loading 0: 50%|█████ | 182/363 [00:11<00:11, 16.04it/s] Loading 0: 51%|█████ | 185/363 [00:11<00:13, 12.82it/s] Loading 0: 52%|█████▏ | 190/363 [00:11<00:09, 17.70it/s] Loading 0: 53%|█████▎ | 194/363 [00:11<00:08, 20.69it/s] Loading 0: 54%|█████▍ | 197/363 [00:12<00:10, 15.26it/s] Loading 0: 55%|█████▌ | 200/363 [00:12<00:10, 16.03it/s] Loading 0: 56%|█████▌ | 203/363 [00:27<03:45, 1.41s/it] Loading 0: 57%|█████▋ | 207/363 [00:27<02:25, 1.07it/s] Loading 0: 58%|█████▊ | 210/363 [00:27<01:46, 1.43it/s] Loading 0: 59%|█████▊ | 213/363 [00:27<01:19, 1.89it/s] Loading 0: 60%|█████▉ | 216/363 [00:28<01:00, 2.42it/s] Loading 0: 60%|██████ | 219/363 [00:28<00:43, 3.29it/s] Loading 0: 61%|██████ | 222/363 [00:28<00:33, 4.16it/s] Loading 0: 62%|██████▏ | 226/363 [00:28<00:22, 6.07it/s] Loading 0: 63%|██████▎ | 230/363 [00:28<00:15, 8.42it/s] Loading 0: 64%|██████▍ | 233/363 [00:29<00:15, 8.49it/s] Loading 0: 65%|██████▌ | 236/363 [00:29<00:12, 9.97it/s] Loading 0: 66%|██████▌ | 239/363 [00:29<00:13, 9.39it/s] Loading 0: 67%|██████▋ | 244/363 [00:29<00:08, 13.58it/s] Loading 0: 68%|██████▊ | 248/363 [00:29<00:06, 16.79it/s] Loading 0: 69%|██████▉ | 251/363 [00:30<00:08, 13.64it/s] Loading 0: 70%|██████▉ | 254/363 [00:30<00:07, 14.68it/s] Loading 0: 71%|███████ | 257/363 [00:30<00:08, 12.15it/s] Loading 0: 72%|███████▏ | 262/363 [00:30<00:06, 16.75it/s] Loading 0: 73%|███████▎ | 266/363 [00:31<00:04, 19.84it/s] Loading 0: 74%|███████▍ | 269/363 [00:31<00:06, 14.99it/s] Loading 0: 75%|███████▍ | 272/363 [00:31<00:05, 15.84it/s] Loading 0: 76%|███████▌ | 275/363 [00:31<00:06, 12.71it/s] Loading 0: 77%|███████▋ | 280/363 [00:32<00:04, 17.56it/s] Loading 0: 78%|███████▊ | 284/363 [00:32<00:03, 20.67it/s] Loading 0: 79%|███████▉ | 287/363 [00:32<00:04, 15.37it/s] Loading 0: 80%|███████▉ | 290/363 [00:32<00:04, 15.94it/s] Loading 0: 81%|████████ | 293/363 [00:32<00:05, 12.70it/s] Loading 0: 82%|████████▏ | 298/363 [00:33<00:03, 17.57it/s] Loading 0: 83%|████████▎ | 302/363 [00:33<00:02, 20.48it/s] Loading 0: 84%|████████▍ | 305/363 [00:33<00:03, 15.10it/s] Loading 0: 85%|████████▍ | 308/363 [00:33<00:03, 15.74it/s] Loading 0: 86%|████████▌ | 311/363 [00:34<00:04, 12.40it/s] Loading 0: 87%|████████▋ | 316/363 [00:34<00:02, 17.20it/s] Loading 0: 88%|████████▊ | 320/363 [00:34<00:02, 20.47it/s] Loading 0: 89%|████████▉ | 323/363 [00:34<00:02, 15.14it/s] Loading 0: 90%|████████▉ | 326/363 [00:34<00:02, 15.82it/s] Loading 0: 91%|█████████ | 329/363 [00:35<00:02, 12.51it/s] Loading 0: 92%|█████████▏| 334/363 [00:35<00:01, 17.31it/s] Loading 0: 93%|█████████▎| 338/363 [00:35<00:01, 20.42it/s] Loading 0: 94%|█████████▍| 341/363 [00:35<00:01, 15.23it/s] Loading 0: 95%|█████████▍| 344/363 [00:36<00:01, 15.99it/s] Loading 0: 96%|█████████▌| 347/363 [00:36<00:01, 12.79it/s] Loading 0: 97%|█████████▋| 352/363 [00:36<00:00, 17.57it/s] Loading 0: 98%|█████████▊| 356/363 [00:36<00:00, 20.51it/s] Loading 0: 99%|█████████▉| 359/363 [00:37<00:00, 11.26it/s] Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.41it/s]
Job rirv938-simp-grpo-cp312-8272-v1-mkmlizer completed after 464.32s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp312-8272-v1-mkmlizer
Pipeline stage MKMLizer completed in 464.99s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.18s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-simp-grpo-cp312-8272-v1
Waiting for inference service rirv938-simp-grpo-cp312-8272-v1 to be ready
Inference service rirv938-simp-grpo-cp312-8272-v1 ready after 221.01552629470825s
Pipeline stage MKMLDeployer completed in 221.97s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.5888044834136963s
Received healthy response to inference request in 1.9316797256469727s
Received healthy response to inference request in 2.053783655166626s
Received healthy response to inference request in 2.1507537364959717s
Received healthy response to inference request in 2.0599536895751953s
5 requests
0 failed requests
5th percentile: 1.9561005115509034
10th percentile: 1.980521297454834
20th percentile: 2.0293628692626955
30th percentile: 2.05501766204834
40th percentile: 2.0574856758117677
50th percentile: 2.0599536895751953
60th percentile: 2.0962737083435057
70th percentile: 2.1325937271118165
80th percentile: 2.2383638858795165
90th percentile: 2.4135841846466066
95th percentile: 2.5011943340301515
99th percentile: 2.571282453536987
mean time: 2.1569950580596924
Pipeline stage StressChecker completed in 12.72s
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 0.81s
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 0.84s
Shutdown handler de-registered
rirv938-simp-grpo-cp312-_8272_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 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.09s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service rirv938-simp-grpo-cp312-8272-v1-profiler
Waiting for inference service rirv938-simp-grpo-cp312-8272-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
%s, retrying in %s seconds...
Evaluating %s Family Friendly Score with %s threads
Pipeline stage OfflineFamilyFriendlyScorer completed in 5686.21s
Shutdown handler de-registered
rirv938-simp-grpo-cp312-_8272_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp312-_8272_v1 status is now torndown due to DeploymentManager action