rirv938-gy-grpo-cp624-9_14536

developer_uid: rirv938

submission_id: rirv938-gy-grpo-cp624-9_14536_v3

model_name: rirv938-gy-grpo-cp624-9_14536_v3

model_group: rirv938/gy_grpo_cp624_98

status: torndown

timestamp: 2025-07-09T16:43:58+00:00

num_battles: 7332

num_wins: 3895

celo_rating: 1309.82

family_friendly_score: 0.5064

family_friendly_standard_error: 0.007070488526261817

submission_type: basic

model_repo: rirv938/gy_grpo_cp624_98ff_b35_r1_merged

model_architecture: MistralForCausalLM

model_num_parameters: 24096691200.0

best_of: 8

max_input_tokens: 1024

max_output_tokens: 64

reward_model: default

latencies: [{'batch_size': 1, 'throughput': 0.5226576726151674, 'latency_mean': 1.9131997895240784, 'latency_p50': 1.8984781503677368, 'latency_p90': 2.1324461936950683}, {'batch_size': 3, 'throughput': 1.0514324739163499, 'latency_mean': 2.835710881948471, 'latency_p50': 2.8245667219161987, 'latency_p90': 3.151325058937073}, {'batch_size': 5, 'throughput': 1.33828153602488, 'latency_mean': 3.710835498571396, 'latency_p50': 3.7086085081100464, 'latency_p90': 4.146710586547852}, {'batch_size': 6, 'throughput': 1.444124460699365, 'latency_mean': 4.111164892911911, 'latency_p50': 4.09285569190979, 'latency_p90': 4.679732537269592}, {'batch_size': 8, 'throughput': 1.5764915227587832, 'latency_mean': 5.032036859989166, 'latency_p50': 5.037081241607666, 'latency_p90': 5.721074438095092}, {'batch_size': 10, 'throughput': 1.6643251671231973, 'latency_mean': 5.954547154903412, 'latency_p50': 5.9680163860321045, 'latency_p90': 6.760630583763122}]

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

display_name: rirv938-gy-grpo-cp624-9_14536_v3

is_internal_developer: True

language_model: rirv938/gy_grpo_cp624_98ff_b35_r1_merged

model_size: 24B

ranking_group: single

throughput_3p7s: 1.34

us_pacific_date: 2025-07-09

win_ratio: 0.5312329514457174

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': 1024, 'best_of': 8, 'max_output_tokens': 64}

formatter: {'memory_template': '', 'prompt_template': '', 'bot_template': '<|im_start|>assistant\n{message}<|im_end|>\n', 'user_template': '<|im_start|>user\nYou:{message}<|im_end|>\n', 'response_template': '<|im_start|>assistant\n', 'truncate_by_message': True}

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-gy-grpo-cp624-9-14536-v3-mkmlizer
Waiting for job on rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer to finish
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   ██████   ██████  █████   ████  ████                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  ░░██████ ██████  ░░███   ███░  ░░███                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   ░███░█████░███   ░███  ███     ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   ░███░░███ ░███   ░███████      ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   ░███ ░░░  ░███   ░███░░███     ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   ░███      ░███   ░███ ░░███    ░███                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║   █████     █████  █████ ░░████  █████                              ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  ░░░░░     ░░░░░  ░░░░░   ░░░░  ░░░░░                               ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Version: 0.29.15                                                   ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Features: FLYWHEEL, CUDA                                           ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Copyright 2023-2025 MK ONE TECHNOLOGIES Inc.                       ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  belonging to:                                                      ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ║                                                                     ║
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: Downloaded to shared memory in 112.848s
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: Checking if rirv938/gy_grpo_cp624_98ff_b35_r1_merged already exists in ChaiML
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmptij1yz9u, device:0
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: quantized model in 56.817s
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: Processed model rirv938/gy_grpo_cp624_98ff_b35_r1_merged in 169.745s
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: creating bucket guanaco-mkml-models
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/config.json
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/special_tokens_map.json
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/tokenizer_config.json
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/tokenizer.json
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.1.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/flywheel_model.1.safetensors
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-gy-grpo-cp624-9-14536-v3/nvidia/flywheel_model.0.safetensors
rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 3/363 [00:00<00:12, 29.39it/s]
Loading 0:   2%|▏         | 6/363 [00:00<00:26, 13.57it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:17, 20.74it/s]
Loading 0:   4%|▎         | 13/363 [00:00<00:25, 13.61it/s]
Loading 0:   4%|▍         | 16/363 [00:01<00:27, 12.72it/s]
Loading 0:   6%|▌         | 21/363 [00:01<00:21, 16.14it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:25, 13.19it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:17, 18.92it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:14, 22.40it/s]
Loading 0:  10%|▉         | 35/363 [00:02<00:21, 15.27it/s]
Loading 0:  10%|█         | 38/363 [00:02<00:20, 15.69it/s]
Loading 0:  11%|█▏        | 41/363 [00:02<00:25, 12.40it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:18, 17.46it/s]
Loading 0:  14%|█▍        | 51/363 [00:03<00:17, 17.93it/s]
Loading 0:  15%|█▍        | 54/363 [00:03<00:22, 13.82it/s]
Loading 0:  16%|█▌        | 57/363 [00:03<00:19, 15.75it/s]
Loading 0:  17%|█▋        | 60/363 [00:03<00:21, 14.21it/s]
Loading 0:  18%|█▊        | 64/363 [00:03<00:16, 17.82it/s]
Loading 0:  19%|█▊        | 68/363 [00:04<00:13, 21.44it/s]
Loading 0:  20%|█▉        | 71/363 [00:04<00:19, 14.87it/s]
Loading 0:  20%|██        | 74/363 [00:04<00:18, 15.64it/s]
Loading 0:  21%|██        | 77/363 [00:04<00:22, 12.60it/s]
Loading 0:  23%|██▎       | 82/363 [00:05<00:15, 17.82it/s]
Loading 0:  24%|██▎       | 86/363 [00:05<00:12, 21.47it/s]
Loading 0:  25%|██▍       | 90/363 [00:05<00:19, 13.66it/s]
Loading 0:  26%|██▌       | 95/363 [00:05<00:14, 18.25it/s]
Loading 0:  27%|██▋       | 99/363 [00:05<00:12, 21.19it/s]
Loading 0:  28%|██▊       | 103/363 [00:06<00:15, 16.25it/s]
Loading 0:  29%|██▉       | 106/363 [00:06<00:18, 14.19it/s]
Loading 0:  30%|███       | 109/363 [00:06<00:19, 13.32it/s]
Loading 0:  31%|███       | 111/363 [00:07<00:18, 13.98it/s]
Loading 0:  31%|███       | 113/363 [00:07<00:21, 11.75it/s]
Loading 0:  33%|███▎      | 118/363 [00:07<00:14, 17.44it/s]
Loading 0:  34%|███▎      | 122/363 [00:07<00:11, 21.03it/s]
Loading 0:  34%|███▍      | 125/363 [00:07<00:15, 15.16it/s]
Loading 0:  35%|███▌      | 128/363 [00:08<00:14, 15.84it/s]
Loading 0:  36%|███▌      | 131/363 [00:08<00:18, 12.47it/s]
Loading 0:  37%|███▋      | 136/363 [00:08<00:12, 17.73it/s]
Loading 0:  39%|███▊      | 140/363 [00:08<00:10, 21.15it/s]
Loading 0:  39%|███▉      | 143/363 [00:08<00:14, 15.40it/s]
Loading 0:  40%|████      | 146/363 [00:09<00:13, 15.98it/s]
Loading 0:  41%|████      | 149/363 [00:09<00:16, 12.60it/s]
Loading 0:  42%|████▏     | 154/363 [00:09<00:11, 17.82it/s]
Loading 0:  44%|████▍     | 159/363 [00:09<00:11, 18.44it/s]
Loading 0:  45%|████▍     | 162/363 [00:10<00:14, 14.21it/s]
Loading 0:  45%|████▌     | 165/363 [00:10<00:12, 16.24it/s]
Loading 0:  46%|████▋     | 168/363 [00:10<00:13, 14.71it/s]
Loading 0:  48%|████▊     | 173/363 [00:10<00:09, 19.93it/s]
Loading 0:  49%|████▉     | 177/363 [00:10<00:10, 18.33it/s]
Loading 0:  50%|████▉     | 180/363 [00:11<00:12, 14.14it/s]
Loading 0:  50%|█████     | 183/363 [00:11<00:11, 16.08it/s]
Loading 0:  51%|█████     | 186/363 [00:11<00:12, 14.52it/s]
Loading 0:  52%|█████▏    | 190/363 [00:11<00:09, 18.29it/s]
Loading 0:  53%|█████▎    | 194/363 [00:11<00:07, 21.89it/s]
Loading 0:  54%|█████▍    | 197/363 [00:12<00:10, 15.39it/s]
Loading 0:  55%|█████▌    | 200/363 [00:12<00:10, 16.12it/s]
Loading 0:  56%|█████▌    | 203/363 [00:27<03:47,  1.42s/it]
Loading 0:  57%|█████▋    | 207/363 [00:27<02:26,  1.06it/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:  59%|█████▉    | 215/363 [00:28<01:05,  2.27it/s]
Loading 0:  60%|█████▉    | 217/363 [00:28<00:52,  2.79it/s]
Loading 0:  60%|██████    | 219/363 [00:28<00:40,  3.53it/s]
Loading 0:  61%|██████    | 221/363 [00:28<00:34,  4.07it/s]
Loading 0:  62%|██████▏   | 226/363 [00:28<00:18,  7.23it/s]
Loading 0:  63%|██████▎   | 230/363 [00:28<00:13,  9.86it/s]
Loading 0:  64%|██████▍   | 233/363 [00:29<00:13,  9.41it/s]
Loading 0:  65%|██████▍   | 235/363 [00:29<00:12,  9.86it/s]
Loading 0:  65%|██████▌   | 237/363 [00:29<00:11, 11.07it/s]
Loading 0:  66%|██████▌   | 239/363 [00:29<00:12,  9.89it/s]
Loading 0:  67%|██████▋   | 244/363 [00:29<00:07, 15.69it/s]
Loading 0:  68%|██████▊   | 248/363 [00:29<00:05, 19.85it/s]
Loading 0:  69%|██████▉   | 251/363 [00:30<00:07, 14.50it/s]
Loading 0:  70%|██████▉   | 254/363 [00:30<00:07, 15.42it/s]
Loading 0:  71%|███████   | 257/363 [00:30<00:08, 12.36it/s]
Loading 0:  72%|███████▏  | 262/363 [00:30<00:05, 17.73it/s]
Loading 0:  73%|███████▎  | 266/363 [00:31<00:04, 21.39it/s]
Loading 0:  74%|███████▍  | 270/363 [00:31<00:06, 13.71it/s]
Loading 0:  75%|███████▌  | 273/363 [00:31<00:05, 15.66it/s]
Loading 0:  76%|███████▌  | 276/363 [00:31<00:06, 14.15it/s]
Loading 0:  77%|███████▋  | 280/363 [00:32<00:04, 17.86it/s]
Loading 0:  78%|███████▊  | 284/363 [00:32<00:03, 21.53it/s]
Loading 0:  79%|███████▉  | 287/363 [00:32<00:04, 15.45it/s]
Loading 0:  80%|███████▉  | 290/363 [00:32<00:04, 16.23it/s]
Loading 0:  81%|████████  | 293/363 [00:33<00:05, 12.77it/s]
Loading 0:  82%|████████▏ | 298/363 [00:33<00:03, 18.08it/s]
Loading 0:  83%|████████▎ | 303/363 [00:33<00:03, 18.59it/s]
Loading 0:  84%|████████▍ | 306/363 [00:33<00:03, 14.42it/s]
Loading 0:  85%|████████▌ | 309/363 [00:33<00:03, 16.44it/s]
Loading 0:  86%|████████▌ | 312/363 [00:34<00:03, 14.56it/s]
Loading 0:  87%|████████▋ | 316/363 [00:34<00:02, 17.94it/s]
Loading 0:  88%|████████▊ | 320/363 [00:34<00:01, 21.78it/s]
Loading 0:  89%|████████▉ | 323/363 [00:34<00:02, 15.56it/s]
Loading 0:  90%|████████▉ | 326/363 [00:34<00:02, 16.28it/s]
Loading 0:  91%|█████████ | 329/363 [00:35<00:02, 12.55it/s]
Loading 0:  92%|█████████▏| 334/363 [00:35<00:01, 17.80it/s]
Loading 0:  93%|█████████▎| 339/363 [00:35<00:01, 18.47it/s]
Loading 0:  94%|█████████▍| 342/363 [00:35<00:01, 14.50it/s]
Loading 0:  95%|█████████▌| 345/363 [00:36<00:01, 16.34it/s]
Loading 0:  96%|█████████▌| 348/363 [00:36<00:01, 14.49it/s]
Loading 0:  97%|█████████▋| 352/363 [00:36<00:00, 18.25it/s]
Loading 0:  98%|█████████▊| 356/363 [00:36<00:00, 21.98it/s]
Loading 0:  99%|█████████▉| 359/363 [00:37<00:00, 11.41it/s]
Loading 0: 100%|█████████▉| 362/363 [00:37<00:00, 11.47it/s]
                                                            
Job rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer completed after 197.57s with status: succeeded
Stopping job with name rirv938-gy-grpo-cp624-9-14536-v3-mkmlizer
Pipeline stage MKMLizer completed in 198.16s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.19s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-gy-grpo-cp624-9-14536-v3
Waiting for inference service rirv938-gy-grpo-cp624-9-14536-v3 to be ready
Inference service rirv938-gy-grpo-cp624-9-14536-v3 ready after 200.9168815612793s
Pipeline stage MKMLDeployer completed in 201.63s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.663071393966675s
Received healthy response to inference request in 2.4845476150512695s
Received healthy response to inference request in 2.043459415435791s
Received healthy response to inference request in 2.026209831237793s
Received healthy response to inference request in 2.062842607498169s
5 requests
0 failed requests
5th percentile: 2.0296597480773926
10th percentile: 2.033109664916992
20th percentile: 2.0400094985961914
30th percentile: 2.047336053848267
40th percentile: 2.055089330673218
50th percentile: 2.062842607498169
60th percentile: 2.231524610519409
70th percentile: 2.4002066135406492
80th percentile: 2.5202523708343505
90th percentile: 2.591661882400513
95th percentile: 2.627366638183594
99th percentile: 2.6559304428100585
mean time: 2.2560261726379394
Pipeline stage StressChecker completed in 12.63s
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 0.66s
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 0.67s
Shutdown handler de-registered
rirv938-gy-grpo-cp624-9_14536_v3 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
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 3393.34s
Shutdown handler de-registered
rirv938-gy-grpo-cp624-9_14536_v3 status is now inactive due to auto deactivation removed underperforming models
rirv938-gy-grpo-cp624-9_14536_v3 status is now torndown due to DeploymentManager action