rirv938-simp-grpo-cp312_57442

developer_uid: rirv938
submission_id: rirv938-simp-grpo-cp312_57442_v1
model_name: rirv938-simp-grpo-cp312_57442_v1
model_group: rirv938/simp_grpo_cp312_
status: torndown
timestamp: 2025-06-11T03:59:24+00:00
num_battles: 8659
num_wins: 4524
celo_rating: 1300.75
family_friendly_score: 0.4998
family_friendly_standard_error: 0.007071067246180028
submission_type: basic
model_repo: rirv938/simp_grpo_cp312_96ff_b1_r1_merged
model_architecture: MistralForCausalLM
model_num_parameters: 24096691200.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: rirv938-simp-grpo-cp312_57442_v1
is_internal_developer: True
language_model: rirv938/simp_grpo_cp312_96ff_b1_r1_merged
model_size: 24B
ranking_group: single
us_pacific_date: 2025-06-10
win_ratio: 0.5224621780806098
generation_params: {'temperature': 0.9, 'top_p': 0.95, 'min_p': 0.05, 'top_k': 80, 'presence_penalty': 0.45, 'frequency_penalty': 0.45, 'stopping_words': ['</s>', 'You:', '###', '\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-cp312-57442-v1-mkmlizer
Waiting for job on rirv938-simp-grpo-cp312-57442-v1-mkmlizer to finish
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Version: 0.27.1+vampire_v3                                         ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ║                                                                     ║
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: Downloaded to shared memory in 161.331s
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpxbhn3v7v, device:0
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: quantized model in 84.581s
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: Processed model rirv938/simp_grpo_cp312_96ff_b1_r1_merged in 245.924s
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: creating bucket guanaco-mkml-models
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1/config.json
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1/special_tokens_map.json
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1/tokenizer_config.json
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1/flywheel_model.1.safetensors
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-simp-grpo-cp312-57442-v1/flywheel_model.0.safetensors
rirv938-simp-grpo-cp312-57442-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:01<02:43,  2.21it/s]
Loading 0:   1%|          | 4/363 [00:02<04:33,  1.31it/s]
Loading 0:   1%|▏         | 5/363 [00:04<05:58,  1.00s/it]
Loading 0:   2%|▏         | 8/363 [00:04<02:46,  2.14it/s]
Loading 0:   2%|▏         | 9/363 [00:04<02:22,  2.48it/s]
Loading 0:   3%|▎         | 10/363 [00:04<01:58,  2.99it/s]
Loading 0:   3%|▎         | 11/363 [00:04<01:44,  3.38it/s]
Loading 0:   3%|▎         | 12/363 [00:05<01:30,  3.90it/s]
Loading 0:   4%|▎         | 13/363 [00:06<03:23,  1.72it/s]
Loading 0:   4%|▍         | 14/363 [00:08<04:49,  1.21it/s]
Loading 0:   4%|▍         | 15/363 [00:09<05:52,  1.01s/it]
Loading 0:   5%|▍         | 18/363 [00:09<02:50,  2.03it/s]
Loading 0:   5%|▌         | 19/363 [00:09<02:22,  2.41it/s]
Loading 0:   6%|▌         | 21/363 [00:11<02:57,  1.93it/s]
Loading 0:   6%|▌         | 22/363 [00:12<03:20,  1.70it/s]
Loading 0:   6%|▋         | 23/363 [00:12<03:25,  1.66it/s]
Loading 0:   7%|▋         | 27/363 [00:12<01:35,  3.53it/s]
Loading 0:   8%|▊         | 29/363 [00:12<01:12,  4.60it/s]
Loading 0:   9%|▊         | 31/363 [00:13<00:57,  5.75it/s]
Loading 0:   9%|▉         | 33/363 [00:13<00:50,  6.49it/s]
Loading 0:  10%|▉         | 35/363 [00:14<01:33,  3.50it/s]
Loading 0:  10%|▉         | 36/363 [00:15<01:59,  2.75it/s]
Loading 0:  11%|█         | 39/363 [00:15<01:37,  3.32it/s]
Loading 0:  11%|█         | 40/363 [00:16<01:54,  2.83it/s]
Loading 0:  11%|█▏        | 41/363 [00:17<02:16,  2.36it/s]
Loading 0:  12%|█▏        | 44/363 [00:17<01:18,  4.06it/s]
Loading 0:  13%|█▎        | 46/363 [00:17<01:03,  5.02it/s]
Loading 0:  13%|█▎        | 48/363 [00:17<00:48,  6.49it/s]
Loading 0:  14%|█▍        | 50/363 [00:17<00:42,  7.44it/s]
Loading 0:  14%|█▍        | 52/363 [00:18<01:06,  4.71it/s]
Loading 0:  15%|█▍        | 53/363 [00:19<01:29,  3.46it/s]
Loading 0:  15%|█▍        | 54/363 [00:19<01:57,  2.63it/s]
Loading 0:  16%|█▌        | 57/363 [00:20<01:34,  3.25it/s]
Loading 0:  16%|█▌        | 58/363 [00:21<01:52,  2.71it/s]
Loading 0:  16%|█▋        | 59/363 [00:22<02:14,  2.26it/s]
Loading 0:  17%|█▋        | 62/363 [00:22<01:16,  3.95it/s]
Loading 0:  18%|█▊        | 64/363 [00:22<01:01,  4.90it/s]
Loading 0:  18%|█▊        | 66/363 [00:22<00:47,  6.32it/s]
Loading 0:  19%|█▊        | 68/363 [00:22<00:40,  7.22it/s]
Loading 0:  19%|█▉        | 70/363 [00:23<01:04,  4.53it/s]
Loading 0:  20%|█▉        | 71/363 [00:24<01:26,  3.36it/s]
Loading 0:  20%|█▉        | 72/363 [00:24<01:52,  2.59it/s]
Loading 0:  21%|██        | 75/363 [00:25<01:16,  3.77it/s]
Loading 0:  21%|██        | 77/363 [00:25<01:04,  4.42it/s]
Loading 0:  23%|██▎       | 82/363 [00:25<00:34,  8.22it/s]
Loading 0:  24%|██▎       | 86/363 [00:25<00:24, 11.28it/s]
Loading 0:  25%|██▍       | 89/363 [00:26<00:26, 10.24it/s]
Loading 0:  25%|██▌       | 91/363 [00:26<00:25, 10.47it/s]
Loading 0:  26%|██▌       | 95/363 [00:26<00:18, 14.12it/s]
Loading 0:  27%|██▋       | 99/363 [00:26<00:15, 17.57it/s]
Loading 0:  28%|██▊       | 102/363 [00:26<00:15, 16.90it/s]
Loading 0:  29%|██▉       | 105/363 [00:27<00:19, 13.37it/s]
Loading 0:  29%|██▉       | 107/363 [00:27<00:20, 12.53it/s]
Loading 0:  30%|███       | 109/363 [00:27<00:20, 12.31it/s]
Loading 0:  31%|███       | 111/363 [00:27<00:18, 13.28it/s]
Loading 0:  31%|███       | 113/363 [00:27<00:22, 10.97it/s]
Loading 0:  33%|███▎      | 118/363 [00:27<00:14, 17.04it/s]
Loading 0:  34%|███▎      | 122/363 [00:28<00:11, 20.99it/s]
Loading 0:  34%|███▍      | 125/363 [00:28<00:16, 14.83it/s]
Loading 0:  35%|███▌      | 128/363 [00:28<00:15, 15.45it/s]
Loading 0:  36%|███▌      | 130/363 [00:28<00:17, 13.69it/s]
Loading 0:  36%|███▋      | 132/363 [00:28<00:17, 13.04it/s]
Loading 0:  37%|███▋      | 136/363 [00:29<00:13, 17.14it/s]
Loading 0:  39%|███▊      | 140/363 [00:29<00:10, 20.76it/s]
Loading 0:  39%|███▉      | 143/363 [00:29<00:15, 14.56it/s]
Loading 0:  40%|███▉      | 145/363 [00:29<00:15, 13.68it/s]
Loading 0:  40%|████      | 147/363 [00:29<00:15, 14.35it/s]
Loading 0:  41%|████      | 149/363 [00:30<00:18, 11.62it/s]
Loading 0:  42%|████▏     | 154/363 [00:30<00:12, 17.38it/s]
Loading 0:  44%|████▎     | 158/363 [00:30<00:09, 21.00it/s]
Loading 0:  44%|████▍     | 161/363 [00:30<00:13, 14.79it/s]
Loading 0:  45%|████▌     | 164/363 [00:30<00:12, 15.43it/s]
Loading 0:  46%|████▌     | 166/363 [00:31<00:14, 13.74it/s]
Loading 0:  46%|████▋     | 168/363 [00:31<00:14, 13.07it/s]
Loading 0:  47%|████▋     | 172/363 [00:31<00:11, 17.07it/s]
Loading 0:  48%|████▊     | 176/363 [00:31<00:09, 20.46it/s]
Loading 0:  49%|████▉     | 179/363 [00:31<00:12, 14.42it/s]
Loading 0:  50%|████▉     | 181/363 [00:32<00:13, 13.65it/s]
Loading 0:  50%|█████     | 183/363 [00:32<00:12, 14.44it/s]
Loading 0:  51%|█████     | 185/363 [00:32<00:15, 11.45it/s]
Loading 0:  52%|█████▏    | 190/363 [00:32<00:10, 17.14it/s]
Loading 0:  53%|█████▎    | 194/363 [00:32<00:08, 20.35it/s]
Loading 0:  54%|█████▍    | 197/363 [00:33<00:11, 14.58it/s]
Loading 0:  55%|█████▍    | 199/363 [00:33<00:11, 13.72it/s]
Loading 0:  55%|█████▌    | 201/363 [00:48<04:49,  1.79s/it]
Loading 0:  56%|█████▌    | 203/363 [00:48<03:41,  1.38s/it]
Loading 0:  57%|█████▋    | 207/363 [00:48<02:08,  1.21it/s]
Loading 0:  58%|█████▊    | 210/363 [00:49<01:29,  1.70it/s]
Loading 0:  59%|█████▊    | 213/363 [00:49<01:06,  2.25it/s]
Loading 0:  59%|█████▉    | 215/363 [00:49<00:54,  2.73it/s]
Loading 0:  60%|█████▉    | 217/363 [00:49<00:43,  3.36it/s]
Loading 0:  60%|██████    | 219/363 [00:49<00:33,  4.25it/s]
Loading 0:  61%|██████    | 221/363 [00:50<00:29,  4.81it/s]
Loading 0:  62%|██████▏   | 226/363 [00:50<00:16,  8.44it/s]
Loading 0:  63%|██████▎   | 230/363 [00:50<00:11, 11.48it/s]
Loading 0:  64%|██████▍   | 233/363 [00:50<00:12, 10.41it/s]
Loading 0:  65%|██████▍   | 235/363 [00:50<00:12, 10.66it/s]
Loading 0:  65%|██████▌   | 237/363 [00:51<00:10, 11.81it/s]
Loading 0:  66%|██████▌   | 239/363 [00:51<00:12, 10.33it/s]
Loading 0:  67%|██████▋   | 244/363 [00:51<00:07, 15.85it/s]
Loading 0:  68%|██████▊   | 248/363 [00:51<00:05, 19.35it/s]
Loading 0:  69%|██████▉   | 251/363 [00:51<00:07, 14.57it/s]
Loading 0:  70%|██████▉   | 254/363 [00:52<00:07, 15.24it/s]
Loading 0:  71%|███████   | 256/363 [00:52<00:07, 13.71it/s]
Loading 0:  71%|███████   | 258/363 [00:52<00:07, 13.13it/s]
Loading 0:  72%|███████▏  | 262/363 [00:52<00:05, 17.17it/s]
Loading 0:  73%|███████▎  | 266/363 [00:52<00:04, 20.70it/s]
Loading 0:  74%|███████▍  | 269/363 [00:53<00:06, 14.68it/s]
Loading 0:  75%|███████▍  | 271/363 [00:53<00:06, 13.72it/s]
Loading 0:  75%|███████▌  | 273/363 [00:53<00:06, 14.38it/s]
Loading 0:  76%|███████▌  | 275/363 [00:53<00:07, 11.58it/s]
Loading 0:  77%|███████▋  | 280/363 [00:53<00:04, 17.27it/s]
Loading 0:  78%|███████▊  | 284/363 [00:53<00:03, 20.57it/s]
Loading 0:  79%|███████▉  | 287/363 [00:54<00:05, 14.47it/s]
Loading 0:  80%|███████▉  | 289/363 [00:54<00:05, 13.66it/s]
Loading 0:  80%|████████  | 291/363 [00:54<00:05, 14.39it/s]
Loading 0:  81%|████████  | 293/363 [00:54<00:06, 11.50it/s]
Loading 0:  82%|████████▏ | 298/363 [00:54<00:03, 17.14it/s]
Loading 0:  83%|████████▎ | 302/363 [00:55<00:02, 20.34it/s]
Loading 0:  84%|████████▍ | 305/363 [00:55<00:04, 14.12it/s]
Loading 0:  85%|████████▍ | 307/363 [00:55<00:04, 13.33it/s]
Loading 0:  85%|████████▌ | 309/363 [00:55<00:03, 14.15it/s]
Loading 0:  86%|████████▌ | 311/363 [00:56<00:04, 11.36it/s]
Loading 0:  87%|████████▋ | 316/363 [00:56<00:02, 16.92it/s]
Loading 0:  88%|████████▊ | 320/363 [00:56<00:02, 20.05it/s]
Loading 0:  89%|████████▉ | 323/363 [00:56<00:02, 13.90it/s]
Loading 0:  90%|████████▉ | 325/363 [00:56<00:02, 13.21it/s]
Loading 0:  90%|█████████ | 327/363 [00:56<00:02, 13.96it/s]
Loading 0:  91%|█████████ | 329/363 [00:57<00:03, 11.27it/s]
Loading 0:  92%|█████████▏| 334/363 [00:57<00:01, 16.86it/s]
Loading 0:  93%|█████████▎| 338/363 [00:57<00:01, 20.36it/s]
Loading 0:  94%|█████████▍| 341/363 [00:57<00:01, 14.12it/s]
Loading 0:  94%|█████████▍| 343/363 [00:58<00:01, 13.39it/s]
Loading 0:  95%|█████████▌| 345/363 [00:58<00:01, 14.15it/s]
Loading 0:  96%|█████████▌| 347/363 [00:58<00:01, 11.53it/s]
Loading 0:  97%|█████████▋| 352/363 [00:58<00:00, 17.26it/s]
Loading 0:  98%|█████████▊| 356/363 [00:58<00:00, 20.59it/s]
Loading 0:  99%|█████████▉| 359/363 [00:59<00:00, 10.21it/s]
Loading 0:  99%|█████████▉| 361/363 [00:59<00:00,  9.39it/s]
                                                            
Job rirv938-simp-grpo-cp312-57442-v1-mkmlizer completed after 279.97s with status: succeeded
Stopping job with name rirv938-simp-grpo-cp312-57442-v1-mkmlizer
Pipeline stage MKMLizer completed in 280.51s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.34s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-simp-grpo-cp312-57442-v1
Waiting for inference service rirv938-simp-grpo-cp312-57442-v1 to be ready
Inference service rirv938-simp-grpo-cp312-57442-v1 ready after 100.41070318222046s
Pipeline stage MKMLDeployer completed in 100.99s
run pipeline stage %s
Running pipeline stage StressChecker
Failed to get response for submission chaiml-cyndonia24b-cpos_11400_v1: ('http://chaiml-cyndonia24b-cpos-11400-v1-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', '')
Received healthy response to inference request in 2.893407106399536s
Received healthy response to inference request in 1.987668514251709s
Received healthy response to inference request in 2.2926125526428223s
Received healthy response to inference request in 1.9066293239593506s
Received healthy response to inference request in 2.05637788772583s
5 requests
0 failed requests
5th percentile: 1.9228371620178222
10th percentile: 1.939045000076294
20th percentile: 1.9714606761932374
30th percentile: 2.001410388946533
40th percentile: 2.028894138336182
50th percentile: 2.05637788772583
60th percentile: 2.150871753692627
70th percentile: 2.245365619659424
80th percentile: 2.412771463394165
90th percentile: 2.6530892848968506
95th percentile: 2.7732481956481934
99th percentile: 2.8693753242492677
mean time: 2.2273390769958494
Pipeline stage StressChecker completed in 12.56s
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 0.80s
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 0.75s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_57442_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 2757.59s
Shutdown handler de-registered
rirv938-simp-grpo-cp312_57442_v1 status is now inactive due to auto deactivation removed underperforming models
rirv938-simp-grpo-cp312_57442_v1 status is now torndown due to DeploymentManager action