rirv938-anthropic-grpo-_29039

developer_uid: rirv938
submission_id: rirv938-anthropic-grpo-_29039_v1
model_name: rirv938-anthropic-grpo-_29039_v1
model_group: rirv938/anthropic_grpo_4
status: torndown
timestamp: 2025-05-20T15:07:14+00:00
num_battles: 6562
num_wins: 3661
celo_rating: 1342.77
family_friendly_score: 0.5746
family_friendly_standard_error: 0.006991921624274688
submission_type: basic
model_repo: rirv938/anthropic_grpo_40k_cp1248_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-_29039_v1
is_internal_developer: True
language_model: rirv938/anthropic_grpo_40k_cp1248_96ff_new_rm_merged
model_size: 13B
ranking_group: single
us_pacific_date: 2025-05-20
win_ratio: 0.5579091740323072
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-29039-v1-mkmlizer
Waiting for job on rirv938-anthropic-grpo-29039-v1-mkmlizer to finish
rirv938-anthropic-grpo-29039-v1-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║     _____            __           __                                ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║       /___/                                                         ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  Version: 0.12.8                                                    ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  https://mk1.ai                                                     ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  The license key for the current software has been verified as      ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  belonging to:                                                      ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  Chai Research Corp.                                                ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║  Expiration: 2028-03-31 23:59:59                                    ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ║                                                                     ║
rirv938-anthropic-grpo-29039-v1-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
rirv938-anthropic-grpo-29039-v1-mkmlizer: Downloaded to shared memory in 88.583s
rirv938-anthropic-grpo-29039-v1-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp35zdz5kd, device:0
rirv938-anthropic-grpo-29039-v1-mkmlizer: Saving flywheel model at /dev/shm/model_cache
rirv938-anthropic-grpo-29039-v1-mkmlizer: quantized model in 43.653s
rirv938-anthropic-grpo-29039-v1-mkmlizer: Processed model rirv938/anthropic_grpo_40k_cp1248_96ff_new_rm_merged in 132.237s
rirv938-anthropic-grpo-29039-v1-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
rirv938-anthropic-grpo-29039-v1-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1
rirv938-anthropic-grpo-29039-v1-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1/config.json
rirv938-anthropic-grpo-29039-v1-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1/special_tokens_map.json
rirv938-anthropic-grpo-29039-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1/tokenizer_config.json
rirv938-anthropic-grpo-29039-v1-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1/tokenizer.json
rirv938-anthropic-grpo-29039-v1-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/rirv938-anthropic-grpo-29039-v1/flywheel_model.0.safetensors
rirv938-anthropic-grpo-29039-v1-mkmlizer: 
Loading 0:   0%|          | 0/363 [00:00<?, ?it/s]
Loading 0:   1%|▏         | 5/363 [00:00<00:17, 19.94it/s]
Loading 0:   3%|▎         | 10/363 [00:00<00:14, 24.92it/s]
Loading 0:   4%|▍         | 14/363 [00:00<00:15, 22.09it/s]
Loading 0:   5%|▌         | 19/363 [00:00<00:12, 27.80it/s]
Loading 0:   6%|▋         | 23/363 [00:01<00:16, 20.02it/s]
Loading 0:   7%|▋         | 26/363 [00:01<00:18, 18.11it/s]
Loading 0:   9%|▊         | 31/363 [00:01<00:14, 23.35it/s]
Loading 0:   9%|▉         | 34/363 [00:01<00:14, 23.25it/s]
Loading 0:  10%|█         | 37/363 [00:01<00:13, 24.45it/s]
Loading 0:  11%|█▏        | 41/363 [00:01<00:14, 22.15it/s]
Loading 0:  13%|█▎        | 46/363 [00:01<00:11, 27.09it/s]
Loading 0:  14%|█▍        | 50/363 [00:02<00:13, 23.75it/s]
Loading 0:  15%|█▌        | 55/363 [00:02<00:11, 27.92it/s]
Loading 0:  17%|█▋        | 60/363 [00:02<00:10, 28.60it/s]
Loading 0:  18%|█▊        | 64/363 [00:02<00:16, 18.62it/s]
Loading 0:  19%|█▉        | 69/363 [00:02<00:12, 23.06it/s]
Loading 0:  20%|██        | 73/363 [00:03<00:12, 23.46it/s]
Loading 0:  21%|██        | 77/363 [00:03<00:13, 21.89it/s]
Loading 0:  23%|██▎       | 82/363 [00:03<00:10, 26.38it/s]
Loading 0:  24%|██▎       | 86/363 [00:03<00:11, 23.41it/s]
Loading 0:  25%|██▌       | 91/363 [00:03<00:10, 26.87it/s]
Loading 0:  26%|██▌       | 95/363 [00:04<00:11, 23.94it/s]
Loading 0:  28%|██▊       | 100/363 [00:04<00:09, 28.39it/s]
Loading 0:  29%|██▊       | 104/363 [00:04<00:13, 19.19it/s]
Loading 0:  30%|███       | 109/363 [00:04<00:10, 23.49it/s]
Loading 0:  31%|███       | 113/363 [00:04<00:12, 20.61it/s]
Loading 0:  33%|███▎      | 118/363 [00:05<00:09, 25.35it/s]
Loading 0:  34%|███▎      | 122/363 [00:05<00:10, 23.60it/s]
Loading 0:  35%|███▍      | 127/363 [00:05<00:08, 28.37it/s]
Loading 0:  36%|███▌      | 131/363 [00:05<00:09, 25.32it/s]
Loading 0:  37%|███▋      | 136/363 [00:05<00:07, 29.95it/s]
Loading 0:  39%|███▉      | 141/363 [00:05<00:07, 30.70it/s]
Loading 0:  40%|███▉      | 145/363 [00:06<00:10, 21.41it/s]
Loading 0:  41%|████      | 149/363 [00:06<00:10, 20.90it/s]
Loading 0:  42%|████▏     | 154/363 [00:06<00:08, 25.19it/s]
Loading 0:  44%|████▎     | 158/363 [00:06<00:08, 23.61it/s]
Loading 0:  45%|████▍     | 163/363 [00:06<00:07, 28.53it/s]
Loading 0:  46%|████▌     | 167/363 [00:06<00:07, 25.72it/s]
Loading 0:  48%|████▊     | 174/363 [00:07<00:05, 31.52it/s]
Loading 0:  49%|████▉     | 178/363 [00:07<00:06, 29.70it/s]
Loading 0:  50%|█████     | 182/363 [00:07<00:07, 23.77it/s]
Loading 0:  51%|█████     | 185/363 [00:07<00:08, 20.14it/s]
Loading 0:  52%|█████▏    | 190/363 [00:07<00:07, 24.69it/s]
Loading 0:  53%|█████▎    | 194/363 [00:08<00:07, 23.01it/s]
Loading 0:  55%|█████▍    | 199/363 [00:08<00:05, 27.89it/s]
Loading 0:  56%|█████▌    | 203/363 [00:08<00:06, 25.13it/s]
Loading 0:  57%|█████▋    | 208/363 [00:08<00:05, 29.32it/s]
Loading 0:  58%|█████▊    | 212/363 [00:08<00:06, 24.93it/s]
Loading 0:  60%|█████▉    | 217/363 [00:08<00:05, 28.03it/s]
Loading 0:  61%|██████    | 222/363 [00:08<00:04, 28.89it/s]
Loading 0:  62%|██████▏   | 226/363 [00:09<00:06, 19.91it/s]
Loading 0:  63%|██████▎   | 230/363 [00:09<00:06, 19.46it/s]
Loading 0:  65%|██████▍   | 235/363 [00:09<00:05, 23.46it/s]
Loading 0:  66%|██████▌   | 239/363 [00:09<00:05, 22.01it/s]
Loading 0:  67%|██████▋   | 244/363 [00:10<00:04, 26.23it/s]
Loading 0:  68%|██████▊   | 248/363 [00:10<00:04, 23.96it/s]
Loading 0:  70%|██████▉   | 253/363 [00:10<00:03, 27.89it/s]
Loading 0:  71%|███████   | 257/363 [00:10<00:04, 24.54it/s]
Loading 0:  72%|███████▏  | 262/363 [00:10<00:03, 28.69it/s]
Loading 0:  73%|███████▎  | 266/363 [00:11<00:05, 18.85it/s]
Loading 0:  75%|███████▍  | 271/363 [00:11<00:04, 22.95it/s]
Loading 0:  76%|███████▌  | 275/363 [00:11<00:04, 21.47it/s]
Loading 0:  77%|███████▋  | 280/363 [00:11<00:03, 25.62it/s]
Loading 0:  78%|███████▊  | 284/363 [00:11<00:03, 23.10it/s]
Loading 0:  80%|███████▉  | 289/363 [00:11<00:02, 27.43it/s]
Loading 0:  81%|████████  | 293/363 [00:12<00:02, 24.20it/s]
Loading 0:  82%|████████▏ | 298/363 [00:12<00:02, 28.20it/s]
Loading 0:  83%|████████▎ | 303/363 [00:12<00:02, 28.46it/s]
Loading 0:  85%|████████▍ | 307/363 [00:12<00:02, 19.50it/s]
Loading 0:  86%|████████▌ | 311/363 [00:12<00:02, 19.52it/s]
Loading 0:  87%|████████▋ | 316/363 [00:13<00:01, 23.92it/s]
Loading 0:  88%|████████▊ | 320/363 [00:13<00:01, 22.38it/s]
Loading 0:  90%|████████▉ | 325/363 [00:13<00:01, 27.21it/s]
Loading 0:  91%|█████████ | 329/363 [00:13<00:01, 24.22it/s]
Loading 0:  92%|█████████▏| 334/363 [00:13<00:00, 29.05it/s]
Loading 0:  93%|█████████▎| 338/363 [00:13<00:00, 25.68it/s]
Loading 0:  94%|█████████▍| 343/363 [00:14<00:00, 29.34it/s]
Loading 0:  96%|█████████▌| 347/363 [00:21<00:08,  1.96it/s]
Loading 0:  96%|█████████▋| 350/363 [00:21<00:05,  2.47it/s]
Loading 0:  97%|█████████▋| 353/363 [00:21<00:03,  3.16it/s]
Loading 0:  98%|█████████▊| 357/363 [00:21<00:01,  4.35it/s]
                                                            
Job rirv938-anthropic-grpo-29039-v1-mkmlizer completed after 166.11s with status: succeeded
Stopping job with name rirv938-anthropic-grpo-29039-v1-mkmlizer
Pipeline stage MKMLizer completed in 166.61s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.16s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service rirv938-anthropic-grpo-29039-v1
Waiting for inference service rirv938-anthropic-grpo-29039-v1 to be ready
Inference service rirv938-anthropic-grpo-29039-v1 ready after 140.97561597824097s
Pipeline stage MKMLDeployer completed in 141.55s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.0661497116088867s
Received healthy response to inference request in 1.6991572380065918s
Received healthy response to inference request in 1.913027048110962s
Received healthy response to inference request in 1.5860929489135742s
Received healthy response to inference request in 1.565476894378662s
5 requests
0 failed requests
5th percentile: 1.5696001052856445
10th percentile: 1.573723316192627
20th percentile: 1.5819697380065918
30th percentile: 1.6087058067321778
40th percentile: 1.6539315223693847
50th percentile: 1.6991572380065918
60th percentile: 1.7847051620483398
70th percentile: 1.870253086090088
80th percentile: 1.943651580810547
90th percentile: 2.004900646209717
95th percentile: 2.035525178909302
99th percentile: 2.0600248050689696
mean time: 1.7659807682037354
Pipeline stage StressChecker completed in 9.98s
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 0.68s
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 0.73s
Shutdown handler de-registered
rirv938-anthropic-grpo-_29039_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 2664.44s
Shutdown handler de-registered
rirv938-anthropic-grpo-_29039_v1 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of rirv938-anthropic-grpo-_29039_v1
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLDeleter
Checking if service rirv938-anthropic-grpo-29039-v1 is running
rirv938-anthropic-grpo-_29039_v1 status is now torndown due to DeploymentManager action