rirv938-simp-grpo-cp156_13555

developer_uid: rirv938

submission_id: rirv938-simp-grpo-cp156_13555_v1

model_name: rirv938-simp-grpo-cp156_13555_v1

model_group: rirv938/simp_grpo_cp156_

status: torndown

timestamp: 2025-07-01T05:28:15+00:00

num_battles: 8595

num_wins: 4381

celo_rating: 1296.46

family_friendly_score: 0.48819999999999997

family_friendly_standard_error: 0.007069098386640265

submission_type: basic

model_repo: rirv938/simp_grpo_cp156_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': 0.5400313134945866, 'latency_mean': 1.851645565032959, 'latency_p50': 1.8639030456542969, 'latency_p90': 2.058797264099121}, {'batch_size': 3, 'throughput': 1.1457721399384435, 'latency_mean': 2.6130715572834013, 'latency_p50': 2.6443203687667847, 'latency_p90': 2.9040812492370605}, {'batch_size': 5, 'throughput': 1.4910127411330574, 'latency_mean': 3.341018280982971, 'latency_p50': 3.333831310272217, 'latency_p90': 3.802466535568237}, {'batch_size': 6, 'throughput': 1.6137690182591693, 'latency_mean': 3.6987722766399385, 'latency_p50': 3.7179712057113647, 'latency_p90': 4.204629230499267}, {'batch_size': 8, 'throughput': 1.7899474609973902, 'latency_mean': 4.425954259634018, 'latency_p50': 4.411089062690735, 'latency_p90': 5.007139706611634}, {'batch_size': 10, 'throughput': 1.8787166451043118, 'latency_mean': 5.281259453296661, 'latency_p50': 5.297902345657349, 'latency_p90': 5.885782718658447}]

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

display_name: rirv938-simp-grpo-cp156_13555_v1

is_internal_developer: True

language_model: rirv938/simp_grpo_cp156_96ff_b3_r1_12m_US_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.62

us_pacific_date: 2025-06-30

win_ratio: 0.5097149505526469

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-cp156-13555-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp156-13555-v1-mkmlizer to finish
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Version: 0.29.3                                                    ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Downloaded to shared memory in 162.785s
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Checking if rirv938/simp_grpo_cp156_96ff_b3_r1_12m_US_merged already exists in ChaiML
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Creating repo ChaiML/simp_grpo_cp156_96ff_b3_r1_12m_US_merged and uploading /tmp/tmp3z5_set4 to it
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp3z5_set4, device:0
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: quantized model in 56.832s
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Processed model rirv938/simp_grpo_cp156_96ff_b3_r1_12m_US_merged in 415.713s
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/config.json
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/special_tokens_map.json
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/tokenizer_config.json
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/tokenizer.json
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/flywheel_model.1.safetensors
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp156-13555-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp156-13555-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 28.49it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:25, 14.07it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:16, 21.60it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:26, 13.01it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:26, 12.86it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:20, 16.31it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.24it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.95it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.11it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.13it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.97it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.64it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:17, 17.80it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:14, 21.13it/s]
Loading 0:  15%|█▍        | 53/363 [00:03<00:20, 15.11it/s]
Loading 0:  15%|█▌        | 56/363 [00:03<00:19, 15.95it/s]
Loading 0:  16%|█▋        | 59/363 [00:03<00:23, 12.75it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.78it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:14, 21.05it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:18, 15.41it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:17, 16.12it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.48it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:16, 17.39it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:13, 20.64it/s]
Loading 0:  25%|██▍       | 89/363 [00:05<00:18, 15.07it/s]
Loading 0:  25%|██▌       | 92/363 [00:05<00:17, 15.58it/s]
Loading 0:  26%|██▋       | 96/363 [00:05<00:13, 19.30it/s]
Loading 0:  28%|██▊       | 101/363 [00:06<00:12, 21.26it/s]
Loading 0:  29%|██▊       | 104/363 [00:06<00:15, 16.52it/s]
Loading 0:  29%|██▉       | 107/363 [00:06<00:19, 13.08it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 12.94it/s]
Loading 0:  31%|███       | 111/363 [00:06<00:18, 13.71it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.65it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:13, 17.67it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.39it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.10it/s]
Loading 0:  35%|███▌      | 128/363 [00:07<00:14, 15.93it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.75it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.58it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.17it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.53it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 16.06it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.73it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.71it/s]
Loading 0:  44%|████▎     | 158/363 [00:09<00:09, 21.08it/s]
Loading 0:  44%|████▍     | 161/363 [00:10<00:13, 15.27it/s]
Loading 0:  45%|████▌     | 164/363 [00:10<00:12, 15.98it/s]
Loading 0:  46%|████▌     | 167/363 [00:10<00:15, 12.59it/s]
Loading 0:  47%|████▋     | 172/363 [00:10<00:10, 17.54it/s]
Loading 0:  48%|████▊     | 176/363 [00:10<00:08, 20.84it/s]
Loading 0:  49%|████▉     | 179/363 [00:11<00:12, 15.02it/s]
Loading 0:  50%|█████     | 182/363 [00:11<00:11, 15.73it/s]
Loading 0:  51%|█████     | 185/363 [00:11<00:14, 12.43it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 17.34it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:08, 20.48it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:11, 14.67it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 15.56it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:42,  1.39s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:23,  1.08it/s]
Loading 0:  58%|█████▊    | 210/363 [00:27<01:45,  1.46it/s]
Loading 0:  59%|█████▊    | 213/363 [00:27<01:18,  1.91it/s]
Loading 0:  60%|█████▉    | 216/363 [00:28<00:59,  2.45it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:43,  3.32it/s]
Loading 0:  61%|██████    | 222/363 [00:28<00:33,  4.21it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:22,  6.16it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:15,  8.56it/s]
Loading 0:  64%|██████▍   | 233/363 [00:28<00:15,  8.66it/s]
Loading 0:  65%|██████▌   | 236/363 [00:29<00:12, 10.16it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:13,  9.52it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:08, 13.69it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:06, 16.78it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:08, 13.19it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 14.34it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 11.93it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:06, 16.81it/s]
Loading 0:  73%|███████▎  | 266/363 [00:30<00:04, 20.10it/s]
Loading 0:  74%|███████▍  | 269/363 [00:31<00:06, 14.99it/s]
Loading 0:  75%|███████▍  | 272/363 [00:31<00:05, 15.73it/s]
Loading 0:  76%|███████▌  | 275/363 [00:31<00:06, 12.63it/s]
Loading 0:  77%|███████▋  | 280/363 [00:31<00:04, 17.62it/s]
Loading 0:  78%|███████▊  | 284/363 [00:31<00:03, 20.81it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.30it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.05it/s]
Loading 0:  81%|████████  | 293/363 [00:32<00:05, 12.73it/s]
Loading 0:  82%|████████▏ | 298/363 [00:32<00:03, 17.52it/s]
Loading 0:  83%|████████▎ | 302/363 [00:33<00:02, 20.47it/s]
Loading 0:  84%|████████▍ | 305/363 [00:33<00:03, 14.85it/s]
Loading 0:  85%|████████▍ | 308/363 [00:33<00:03, 15.73it/s]
Loading 0:  86%|████████▌ | 311/363 [00:33<00:04, 12.67it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.62it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:02, 20.69it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.37it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.13it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.98it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.90it/s]
Loading 0:  93%|█████████▎| 338/363 [00:35<00:01, 21.06it/s]
Loading 0:  94%|█████████▍| 341/363 [00:35<00:01, 15.31it/s]
Loading 0:  95%|█████████▍| 344/363 [00:35<00:01, 16.11it/s]
Loading 0:  96%|█████████▌| 347/363 [00:36<00:01, 12.54it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 17.54it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 20.83it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.27it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.42it/s]
                                                            
Job rirv938-simp-grpo-cp156-13555-v1-mkmlizer completed after 449.38s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp156-13555-v1-mkmlizer
Pipeline stage MKMLizer completed in 450.42s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.27s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-simp-grpo-cp156-13555-v1
Waiting for inference service rirv938-simp-grpo-cp156-13555-v1 to be ready
Inference service rirv938-simp-grpo-cp156-13555-v1 ready after 210.8152813911438s
Pipeline stage MKMLDeployer completed in 211.81s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.640505790710449s
Received healthy response to inference request in 2.0443711280822754s
Received healthy response to inference request in 2.0132484436035156s
Received healthy response to inference request in 2.1415998935699463s
Received healthy response to inference request in 2.0952959060668945s
5 requests
0 failed requests
5th percentile: 2.0194729804992675
10th percentile: 2.0256975173950194
20th percentile: 2.0381465911865235
30th percentile: 2.0545560836791994
40th percentile: 2.074925994873047
50th percentile: 2.0952959060668945
60th percentile: 2.113817501068115
70th percentile: 2.132339096069336
80th percentile: 2.241381072998047
90th percentile: 2.4409434318542482
95th percentile: 2.5407246112823487
99th percentile: 2.620549554824829
mean time: 2.187004232406616
Pipeline stage StressChecker completed in 14.37s
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 1.34s
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 1.08s
Shutdown handler de-registered
rirv938-simp-grpo-cp156_13555_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 3239.17s
Shutdown handler de-registered
rirv938-simp-grpo-cp156_13555_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp156_13555_v1 status is now torndown due to DeploymentManager action