rirv938-anthropic-grpo-_34483

developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_34483_v2
model_name: rirv938-anthropic-grpo-_34483_v2
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-20T15:07:09+00:00
num_battles: 6504
num_wins: 3624
celo_rating: 1339.33
family_friendly_score: 0.5664
family_friendly_standard_error: 0.007008438342455472
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp2184_96ff_new_rm_merged
model_architecture: MistralForCausalLM
model_num_parameters: 12772070400.0
best_of: 8
max_input_tokens: 768
max_output_tokens: 64
reward_model: default
display_name: rirv938-anthropic-grpo-_34483_v2
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp2184_96ff_new_rm_merged
model_size: 13B
ranking_group: single
us_pacific_date: 2025-05-20
win_ratio: 0.5571955719557196
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 80, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['</s>', '\n', '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-anthropic-grpo-34483-v2-mkmlizer
Waiting for job on rirv938-anthropic-grpo-34483-v2-mkmlizer to finish
rirv938-anthropic-grpo-34483-v2-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-34483-v2-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-34483-v2-mkmlizer: Downloaded to shared memory in 59.951s
rirv938-anthropic-grpo-34483-v2-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmpn0636vdp, device:0
rirv938-anthropic-grpo-34483-v2-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-34483-v2-mkmlizer: quantized model in 45.809s
rirv938-anthropic-grpo-34483-v2-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp2184_96ff_new_rm_merged in 105.761s
rirv938-anthropic-grpo-34483-v2-mkmlizer: creating bucket guanaco-mkml-models
rirv938-anthropic-grpo-34483-v2-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-34483-v2-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2
rirv938-anthropic-grpo-34483-v2-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2/config.json
rirv938-anthropic-grpo-34483-v2-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2/special_tokens_map.json
rirv938-anthropic-grpo-34483-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2/tokenizer_config.json
rirv938-anthropic-grpo-34483-v2-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2/tokenizer.json
rirv938-anthropic-grpo-34483-v2-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-34483-v2/flywheel_model.0.safetensors
rirv938-anthropic-grpo-34483-v2-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|          | 4/363 [00:00<00:09, 39.85it/s]
Loading 0:   2%|▏         | 8/363 [00:00<00:15, 23.28it/s]
Loading 0:   3%|▎         | 11/363 [00:00<00:14, 24.41it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:18, 18.82it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:13, 25.00it/s]
Loading 0:   6%|▌         | 22/363 [00:00<00:13, 26.08it/s]
Loading 0:   7%|▋         | 25/363 [00:01<00:19, 17.29it/s]
Loading 0:   8%|▊         | 28/363 [00:01<00:18, 18.31it/s]
Loading 0:   9%|▉         | 32/363 [00:01<00:18, 18.27it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 23.38it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 21.53it/s]
Loading 0:  13%|█▎        | 46/363 [00:02<00:12, 25.89it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.05it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.30it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 27.86it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:17, 17.52it/s]
Loading 0:  19%|█▉        | 69/363 [00:03<00:13, 21.46it/s]
Loading 0:  20%|█▉        | 72/363 [00:03<00:14, 20.02it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 20.68it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:11, 24.66it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:12, 22.12it/s]
Loading 0:  25%|██▌       | 91/363 [00:04<00:10, 25.75it/s]
Loading 0:  26%|██▌       | 94/363 [00:04<00:10, 26.47it/s]
Loading 0:  27%|██▋       | 97/363 [00:04<00:10, 24.98it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:10, 25.16it/s]
Loading 0:  28%|██▊       | 103/363 [00:04<00:14, 17.34it/s]
Loading 0:  29%|██▉       | 106/363 [00:04<00:14, 18.26it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:12, 19.77it/s]
Loading 0:  31%|███       | 112/363 [00:05<00:11, 21.71it/s]
Loading 0:  32%|███▏      | 115/363 [00:05<00:11, 21.62it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:10, 22.87it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:11, 20.49it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:09, 25.40it/s]
Loading 0:  36%|███▌      | 130/363 [00:05<00:08, 26.39it/s]
Loading 0:  37%|███▋      | 133/363 [00:05<00:09, 24.69it/s]
Loading 0:  37%|███▋      | 136/363 [00:06<00:09, 24.67it/s]
Loading 0:  39%|███▉      | 141/363 [00:06<00:08, 25.74it/s]
Loading 0:  40%|███▉      | 144/363 [00:06<00:13, 15.77it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:12, 17.40it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:09, 21.39it/s]
Loading 0:  43%|████▎     | 157/363 [00:07<00:09, 22.84it/s]
Loading 0:  44%|████▍     | 160/363 [00:07<00:08, 22.62it/s]
Loading 0:  45%|████▍     | 163/363 [00:07<00:08, 23.37it/s]
Loading 0:  46%|████▌     | 166/363 [00:07<00:07, 24.85it/s]
Loading 0:  47%|████▋     | 169/363 [00:07<00:08, 23.71it/s]
Loading 0:  47%|████▋     | 172/363 [00:07<00:07, 24.32it/s]
Loading 0:  48%|████▊     | 175/363 [00:07<00:07, 25.61it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:07, 24.20it/s]
Loading 0:  50%|████▉     | 181/363 [00:08<00:07, 24.49it/s]
Loading 0:  51%|█████     | 184/363 [00:08<00:10, 16.77it/s]
Loading 0:  52%|█████▏    | 187/363 [00:08<00:09, 17.63it/s]
Loading 0:  52%|█████▏    | 190/363 [00:08<00:08, 19.57it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:08, 19.05it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:06, 24.46it/s]
Loading 0:  56%|█████▌    | 203/363 [00:09<00:07, 22.11it/s]
Loading 0:  57%|█████▋    | 208/363 [00:09<00:05, 26.91it/s]
Loading 0:  58%|█████▊    | 212/363 [00:09<00:06, 23.68it/s]
Loading 0:  60%|█████▉    | 217/363 [00:09<00:05, 28.34it/s]
Loading 0:  61%|██████    | 222/363 [00:09<00:04, 29.01it/s]
Loading 0:  62%|██████▏   | 226/363 [00:10<00:06, 19.75it/s]
Loading 0:  63%|██████▎   | 230/363 [00:10<00:06, 19.33it/s]
Loading 0:  65%|██████▍   | 235/363 [00:10<00:05, 23.46it/s]
Loading 0:  66%|██████▌   | 238/363 [00:10<00:05, 24.58it/s]
Loading 0:  66%|██████▋   | 241/363 [00:10<00:05, 23.72it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 24.34it/s]
Loading 0:  68%|██████▊   | 248/363 [00:11<00:05, 21.59it/s]
Loading 0:  70%|██████▉   | 253/363 [00:11<00:04, 26.03it/s]
Loading 0:  71%|███████   | 257/363 [00:11<00:04, 22.69it/s]
Loading 0:  72%|███████▏  | 262/363 [00:11<00:03, 26.65it/s]
Loading 0:  73%|███████▎  | 265/363 [00:11<00:05, 18.84it/s]
Loading 0:  74%|███████▍  | 268/363 [00:12<00:05, 18.88it/s]
Loading 0:  75%|███████▍  | 271/363 [00:12<00:04, 19.40it/s]
Loading 0:  75%|███████▌  | 274/363 [00:12<00:04, 21.45it/s]
Loading 0:  76%|███████▋  | 277/363 [00:12<00:03, 21.56it/s]
Loading 0:  77%|███████▋  | 280/363 [00:12<00:03, 22.71it/s]
Loading 0:  78%|███████▊  | 284/363 [00:12<00:03, 20.76it/s]
Loading 0:  80%|███████▉  | 289/363 [00:12<00:02, 25.84it/s]
Loading 0:  80%|████████  | 292/363 [00:12<00:02, 26.56it/s]
Loading 0:  81%|████████▏ | 295/363 [00:13<00:02, 23.86it/s]
Loading 0:  82%|████████▏ | 298/363 [00:13<00:02, 24.49it/s]
Loading 0:  83%|████████▎ | 303/363 [00:13<00:02, 26.19it/s]
Loading 0:  84%|████████▍ | 306/363 [00:13<00:03, 16.60it/s]
Loading 0:  86%|████████▌ | 311/363 [00:14<00:02, 18.22it/s]
Loading 0:  87%|████████▋ | 316/363 [00:14<00:02, 22.53it/s]
Loading 0:  88%|████████▊ | 319/363 [00:14<00:01, 23.89it/s]
Loading 0:  89%|████████▊ | 322/363 [00:14<00:01, 23.28it/s]
Loading 0:  90%|████████▉ | 325/363 [00:14<00:01, 23.90it/s]
Loading 0:  90%|█████████ | 328/363 [00:14<00:01, 25.20it/s]
Loading 0:  91%|█████████ | 331/363 [00:14<00:01, 23.99it/s]
Loading 0:  92%|█████████▏| 334/363 [00:14<00:01, 24.39it/s]
Loading 0:  93%|█████████▎| 337/363 [00:14<00:01, 25.07it/s]
Loading 0:  94%|█████████▎| 340/363 [00:15<00:00, 23.94it/s]
Loading 0:  94%|█████████▍| 343/363 [00:15<00:00, 24.46it/s]
Loading 0:  95%|█████████▌| 346/363 [00:22<00:12,  1.37it/s]
Loading 0:  96%|█████████▌| 348/363 [00:22<00:08,  1.70it/s]
Loading 0:  97%|█████████▋| 353/363 [00:22<00:03,  2.90it/s]
Loading 0:  98%|█████████▊| 357/363 [00:22<00:01,  4.03it/s]
Loading 0: 100%|█████████▉| 362/363 [00:23<00:00,  6.07it/s]
                                                            
Job rirv938-anthropic-grpo-34483-v2-mkmlizer completed after 155.79s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-34483-v2-mkmlizer
Pipeline stage MKMLizer completed in 156.27s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.14s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-34483-v2
Waiting for inference service rirv938-anthropic-grpo-34483-v2 to be ready
Inference service rirv938-anthropic-grpo-34483-v2 ready after 150.80096197128296s
Pipeline stage MKMLDeployer completed in 151.31s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.1698668003082275s
Received healthy response to inference request in 1.706512451171875s
Received healthy response to inference request in 2.0561423301696777s
Received healthy response to inference request in 1.5612096786499023s
Received healthy response to inference request in 1.7425851821899414s
5 requests
0 failed requests
5th percentile: 1.5902702331542968
10th percentile: 1.6193307876586913
20th percentile: 1.6774518966674805
30th percentile: 1.7137269973754883
40th percentile: 1.7281560897827148
50th percentile: 1.7425851821899414
60th percentile: 1.8680080413818358
70th percentile: 1.9934309005737305
80th percentile: 2.0788872241973877
90th percentile: 2.1243770122528076
95th percentile: 2.1471219062805176
99th percentile: 2.1653178215026854
mean time: 1.8472632884979248
Pipeline stage StressChecker completed in 10.60s
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 0.71s
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 0.66s
Shutdown handler de-registered
rirv938-anthropic-grpo-_34483_v2 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 2743.28s
Shutdown handler de-registered
rirv938-anthropic-grpo-_34483_v2 status is now inactive due to auto deactivation removed underperforming models
rirv938-anthropic-grpo-_34483_v2 status is now torndown due to DeploymentManager action