Transformers
Safetensors
trl
grpo
arabic-poetry
classical-arabic
lora
Shaer-adapters-grpo / train.log
AhmadAbbass's picture
Final adapter for shaer_grpo_20260411_223409
45def9d verified
2026-04-11 22:34:16,606 | INFO | train_grpo_train | mode=train
2026-04-11 22:36:48,374 | INFO | train_grpo_train | dataset_id=Shaer-AI/ashaar-enhanced-desc-baseform-final-sft-lte20-min500-splits-grpo-meter-count-v1 train_size=24897 eval_size=104
2026-04-11 22:36:48,375 | INFO | train_grpo_train | source_dataset_id=Shaer-AI/ashaar-with-enhanced-descriptions-baseform-final-sft-lte20-min500-splits test_size=204 hard_diagnostic_size=3126
2026-04-11 22:36:48,375 | INFO | train_grpo_train | active_rewards=['meter', 'count_adherence', 'arabic_clean', 'repeat_penalty', 'total_composite']
2026-04-11 22:36:48,375 | INFO | train_grpo_train | reward_weights={'meter': 0.0, 'count_adherence': 0.0, 'arabic_clean': 0.0, 'repeat_penalty': 0.0, 'total_composite': 1.0}
2026-04-11 22:36:48,375 | INFO | train_grpo_train | output_repo=Shaer-AI/Shaer-adapters-grpo
2026-04-11 22:36:48,375 | INFO | train_grpo_train | train_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_drop_trio/cap_3000/selected_manifest.csv
2026-04-11 22:36:48,375 | INFO | train_grpo_train | hard_diagnostic_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_drop_trio/hard_diagnostic_cap_256/selected_manifest.csv
2026-04-11 22:36:48,375 | INFO | train_grpo_train | trainable_params=159907840 total_params=7160467456 trainable_ratio=0.022332
2026-04-11 22:36:48,375 | INFO | train_grpo_train | resume_decision={"timestamp_utc": "2026-04-11T22:36:28Z", "resume_mode": "from_path", "requested_spec": "/root/workspace/Shaer/grpo/outputs/train/shaer_grpo_20260411_192107/checkpoint-650", "result": "resume", "reason": "explicit_local_path", "local_resume_path": "/root/workspace/Shaer/grpo/outputs/train/shaer_grpo_20260411_192107/checkpoint-650", "remote_repo": null, "remote_prefix": null, "compatibility": "fingerprint_mismatch", "config_fingerprint": "dddf85cc86110a84f67b563540177d5e59b5c500695e99fe984dfc39dac36c3f"}
2026-04-11 22:36:48,375 | INFO | train_grpo_train | starting trainer.train()
2026-04-11 22:36:55,674 | INFO | train_grpo_train | metrics_logged mode=train step=651
2026-04-11 22:37:05,537 | INFO | train_grpo_train | metrics_logged mode=train step=652
2026-04-11 22:37:15,021 | INFO | train_grpo_train | metrics_logged mode=train step=653
2026-04-11 22:37:21,300 | INFO | train_grpo_train | metrics_logged mode=train step=654
2026-04-11 22:37:30,818 | INFO | train_grpo_train | metrics_logged mode=train step=655
2026-04-11 22:37:35,310 | INFO | train_grpo_train | metrics_logged mode=train step=656
2026-04-11 22:37:41,214 | INFO | train_grpo_train | metrics_logged mode=train step=657
2026-04-11 22:37:51,192 | INFO | train_grpo_train | metrics_logged mode=train step=658
2026-04-11 22:38:00,609 | INFO | train_grpo_train | metrics_logged mode=train step=659
2026-04-11 22:38:05,980 | INFO | train_grpo_train | metrics_logged mode=train step=660
2026-04-11 22:38:15,702 | INFO | train_grpo_train | metrics_logged mode=train step=661
2026-04-11 22:38:25,178 | INFO | train_grpo_train | metrics_logged mode=train step=662
2026-04-11 22:38:30,408 | INFO | train_grpo_train | metrics_logged mode=train step=663
2026-04-11 22:38:35,095 | INFO | train_grpo_train | metrics_logged mode=train step=664
2026-04-11 22:38:39,704 | INFO | train_grpo_train | metrics_logged mode=train step=665
2026-04-11 22:38:44,973 | INFO | train_grpo_train | metrics_logged mode=train step=666
2026-04-11 22:38:50,134 | INFO | train_grpo_train | metrics_logged mode=train step=667
2026-04-11 22:38:59,869 | INFO | train_grpo_train | metrics_logged mode=train step=668
2026-04-11 22:39:09,370 | INFO | train_grpo_train | metrics_logged mode=train step=669
2026-04-11 22:39:18,932 | INFO | train_grpo_train | metrics_logged mode=train step=670
2026-04-11 22:39:28,672 | INFO | train_grpo_train | metrics_logged mode=train step=671
2026-04-11 22:39:38,378 | INFO | train_grpo_train | metrics_logged mode=train step=672
2026-04-11 22:39:48,402 | INFO | train_grpo_train | metrics_logged mode=train step=673
2026-04-11 22:39:58,064 | INFO | train_grpo_train | metrics_logged mode=train step=674
2026-04-11 22:40:08,021 | INFO | train_grpo_train | metrics_logged mode=train step=675
2026-04-11 22:40:12,622 | INFO | train_grpo_train | metrics_logged mode=train step=676
2026-04-11 22:40:17,256 | INFO | train_grpo_train | metrics_logged mode=train step=677
2026-04-11 22:40:27,014 | INFO | train_grpo_train | metrics_logged mode=train step=678
2026-04-11 22:40:31,362 | INFO | train_grpo_train | metrics_logged mode=train step=679
2026-04-11 22:40:36,613 | INFO | train_grpo_train | metrics_logged mode=train step=680
2026-04-11 22:40:41,212 | INFO | train_grpo_train | metrics_logged mode=train step=681
2026-04-11 22:40:50,664 | INFO | train_grpo_train | metrics_logged mode=train step=682
2026-04-11 22:40:55,073 | INFO | train_grpo_train | metrics_logged mode=train step=683
2026-04-11 22:40:59,778 | INFO | train_grpo_train | metrics_logged mode=train step=684
2026-04-11 22:41:05,613 | INFO | train_grpo_train | metrics_logged mode=train step=685
2026-04-11 22:41:15,153 | INFO | train_grpo_train | metrics_logged mode=train step=686
2026-04-11 22:41:19,695 | INFO | train_grpo_train | metrics_logged mode=train step=687
2026-04-11 22:41:24,297 | INFO | train_grpo_train | metrics_logged mode=train step=688
2026-04-11 22:41:30,466 | INFO | train_grpo_train | metrics_logged mode=train step=689
2026-04-11 22:41:39,021 | INFO | train_grpo_train | metrics_logged mode=train step=690
2026-04-11 22:41:43,353 | INFO | train_grpo_train | metrics_logged mode=train step=691
2026-04-11 22:41:47,992 | INFO | train_grpo_train | metrics_logged mode=train step=692
2026-04-11 22:41:52,274 | INFO | train_grpo_train | metrics_logged mode=train step=693
2026-04-11 22:41:56,868 | INFO | train_grpo_train | metrics_logged mode=train step=694
2026-04-11 22:42:01,718 | INFO | train_grpo_train | metrics_logged mode=train step=695
2026-04-11 22:42:06,942 | INFO | train_grpo_train | metrics_logged mode=train step=696
2026-04-11 22:42:11,562 | INFO | train_grpo_train | metrics_logged mode=train step=697
2026-04-11 22:42:21,335 | INFO | train_grpo_train | metrics_logged mode=train step=698
2026-04-11 22:42:25,978 | INFO | train_grpo_train | metrics_logged mode=train step=699
2026-04-11 22:42:35,107 | INFO | train_grpo_train | metrics_logged mode=train step=700
2026-04-11 22:44:02,860 | INFO | train_grpo_train | metrics_logged mode=eval step=700
2026-04-11 22:44:17,868 | INFO | train_grpo_train | metrics_logged mode=train step=701
2026-04-11 22:44:27,579 | INFO | train_grpo_train | metrics_logged mode=train step=702
2026-04-11 22:44:34,512 | INFO | train_grpo_train | metrics_logged mode=train step=703
2026-04-11 22:44:44,432 | INFO | train_grpo_train | metrics_logged mode=train step=704
2026-04-11 22:44:49,210 | INFO | train_grpo_train | metrics_logged mode=train step=705
2026-04-11 22:44:53,518 | INFO | train_grpo_train | metrics_logged mode=train step=706
2026-04-11 22:44:59,164 | INFO | train_grpo_train | metrics_logged mode=train step=707
2026-04-11 22:45:07,606 | INFO | train_grpo_train | metrics_logged mode=train step=708
2026-04-11 22:45:17,886 | INFO | train_grpo_train | metrics_logged mode=train step=709
2026-04-11 22:45:28,484 | INFO | train_grpo_train | metrics_logged mode=train step=710
2026-04-11 22:45:38,315 | INFO | train_grpo_train | metrics_logged mode=train step=711
2026-04-11 22:45:44,126 | INFO | train_grpo_train | metrics_logged mode=train step=712
2026-04-11 22:45:54,507 | INFO | train_grpo_train | metrics_logged mode=train step=713
2026-04-11 22:46:02,571 | INFO | train_grpo_train | metrics_logged mode=train step=714
2026-04-11 22:46:08,015 | INFO | train_grpo_train | metrics_logged mode=train step=715
2026-04-11 22:46:14,590 | INFO | train_grpo_train | metrics_logged mode=train step=716
2026-04-11 22:46:24,724 | INFO | train_grpo_train | metrics_logged mode=train step=717
2026-04-11 22:46:29,518 | INFO | train_grpo_train | metrics_logged mode=train step=718
2026-04-11 22:46:39,931 | INFO | train_grpo_train | metrics_logged mode=train step=719
2026-04-11 22:46:47,370 | INFO | train_grpo_train | metrics_logged mode=train step=720
2026-04-11 22:46:52,602 | INFO | train_grpo_train | metrics_logged mode=train step=721
2026-04-11 22:46:57,829 | INFO | train_grpo_train | metrics_logged mode=train step=722
2026-04-11 22:47:08,396 | INFO | train_grpo_train | metrics_logged mode=train step=723
2026-04-11 22:47:17,111 | INFO | train_grpo_train | metrics_logged mode=train step=724
2026-04-11 22:47:26,708 | INFO | train_grpo_train | metrics_logged mode=train step=725
2026-04-11 22:47:32,040 | INFO | train_grpo_train | metrics_logged mode=train step=726
2026-04-11 22:47:37,119 | INFO | train_grpo_train | metrics_logged mode=train step=727
2026-04-11 22:47:46,907 | INFO | train_grpo_train | metrics_logged mode=train step=728
2026-04-11 22:47:56,457 | INFO | train_grpo_train | metrics_logged mode=train step=729
2026-04-11 22:48:01,350 | INFO | train_grpo_train | metrics_logged mode=train step=730
2026-04-11 22:48:11,574 | INFO | train_grpo_train | metrics_logged mode=train step=731
2026-04-11 22:48:21,879 | INFO | train_grpo_train | metrics_logged mode=train step=732
2026-04-11 22:48:26,636 | INFO | train_grpo_train | metrics_logged mode=train step=733
2026-04-11 22:48:31,729 | INFO | train_grpo_train | metrics_logged mode=train step=734
2026-04-11 22:48:36,599 | INFO | train_grpo_train | metrics_logged mode=train step=735
2026-04-11 22:48:44,408 | INFO | train_grpo_train | metrics_logged mode=train step=736
2026-04-11 22:48:54,111 | INFO | train_grpo_train | metrics_logged mode=train step=737
2026-04-11 22:49:04,357 | INFO | train_grpo_train | metrics_logged mode=train step=738
2026-04-11 22:49:13,995 | INFO | train_grpo_train | metrics_logged mode=train step=739
2026-04-11 22:49:19,488 | INFO | train_grpo_train | metrics_logged mode=train step=740
2026-04-11 22:49:24,303 | INFO | train_grpo_train | metrics_logged mode=train step=741
2026-04-11 22:49:29,687 | INFO | train_grpo_train | metrics_logged mode=train step=742
2026-04-11 22:49:39,985 | INFO | train_grpo_train | metrics_logged mode=train step=743
2026-04-11 22:49:44,710 | INFO | train_grpo_train | metrics_logged mode=train step=744
2026-04-11 22:49:49,418 | INFO | train_grpo_train | metrics_logged mode=train step=745
2026-04-11 22:49:56,400 | INFO | train_grpo_train | metrics_logged mode=train step=746
2026-04-11 22:50:00,789 | INFO | train_grpo_train | metrics_logged mode=train step=747
2026-04-11 22:50:05,630 | INFO | train_grpo_train | metrics_logged mode=train step=748
2026-04-11 22:50:10,654 | INFO | train_grpo_train | metrics_logged mode=train step=749
2026-04-11 22:50:15,387 | INFO | train_grpo_train | metrics_logged mode=train step=750
2026-04-11 22:51:48,561 | INFO | train_grpo_train | metrics_logged mode=eval step=750
2026-04-11 22:51:55,376 | INFO | train_grpo_train | metrics_logged mode=train step=751
2026-04-11 22:52:00,240 | INFO | train_grpo_train | metrics_logged mode=train step=752
2026-04-11 22:52:04,693 | INFO | train_grpo_train | metrics_logged mode=train step=753
2026-04-11 22:52:09,269 | INFO | train_grpo_train | metrics_logged mode=train step=754
2026-04-11 22:52:13,683 | INFO | train_grpo_train | metrics_logged mode=train step=755
2026-04-11 22:52:19,323 | INFO | train_grpo_train | metrics_logged mode=train step=756
2026-04-11 22:52:26,901 | INFO | train_grpo_train | metrics_logged mode=train step=757
2026-04-11 22:52:37,283 | INFO | train_grpo_train | metrics_logged mode=train step=758
2026-04-11 22:52:42,145 | INFO | train_grpo_train | metrics_logged mode=train step=759
2026-04-11 22:52:46,717 | INFO | train_grpo_train | metrics_logged mode=train step=760
2026-04-11 22:52:51,308 | INFO | train_grpo_train | metrics_logged mode=train step=761
2026-04-11 22:52:56,217 | INFO | train_grpo_train | metrics_logged mode=train step=762
2026-04-11 22:53:06,584 | INFO | train_grpo_train | metrics_logged mode=train step=763
2026-04-11 22:53:11,381 | INFO | train_grpo_train | metrics_logged mode=train step=764
2026-04-11 22:53:16,287 | INFO | train_grpo_train | metrics_logged mode=train step=765
2026-04-11 22:53:21,082 | INFO | train_grpo_train | metrics_logged mode=train step=766
2026-04-11 22:53:26,017 | INFO | train_grpo_train | metrics_logged mode=train step=767
2026-04-11 22:53:31,167 | INFO | train_grpo_train | metrics_logged mode=train step=768
2026-04-11 22:53:37,094 | INFO | train_grpo_train | metrics_logged mode=train step=769
2026-04-11 22:53:47,440 | INFO | train_grpo_train | metrics_logged mode=train step=770
2026-04-11 22:53:54,481 | INFO | train_grpo_train | metrics_logged mode=train step=771
2026-04-11 22:54:00,203 | INFO | train_grpo_train | metrics_logged mode=train step=772
2026-04-11 22:54:10,006 | INFO | train_grpo_train | metrics_logged mode=train step=773
2026-04-11 22:54:14,783 | INFO | train_grpo_train | metrics_logged mode=train step=774
2026-04-11 22:54:20,807 | INFO | train_grpo_train | metrics_logged mode=train step=775
2026-04-11 22:54:25,331 | INFO | train_grpo_train | metrics_logged mode=train step=776
2026-04-11 22:54:29,668 | INFO | train_grpo_train | metrics_logged mode=train step=777
2026-04-11 22:54:34,404 | INFO | train_grpo_train | metrics_logged mode=train step=778
2026-04-11 22:54:45,494 | INFO | train_grpo_train | metrics_logged mode=train step=779
2026-04-11 22:54:56,084 | INFO | train_grpo_train | metrics_logged mode=train step=780
2026-04-11 22:55:01,108 | INFO | train_grpo_train | metrics_logged mode=train step=781
2026-04-11 22:55:10,832 | INFO | train_grpo_train | metrics_logged mode=train step=782
2026-04-11 22:55:15,776 | INFO | train_grpo_train | metrics_logged mode=train step=783
2026-04-11 22:55:20,422 | INFO | train_grpo_train | metrics_logged mode=train step=784
2026-04-11 22:55:25,740 | INFO | train_grpo_train | metrics_logged mode=train step=785
2026-04-11 22:55:34,483 | INFO | train_grpo_train | metrics_logged mode=train step=786
2026-04-11 22:55:40,304 | INFO | train_grpo_train | metrics_logged mode=train step=787
2026-04-11 22:55:44,938 | INFO | train_grpo_train | metrics_logged mode=train step=788
2026-04-11 22:55:49,240 | INFO | train_grpo_train | metrics_logged mode=train step=789
2026-04-11 22:55:54,287 | INFO | train_grpo_train | metrics_logged mode=train step=790
2026-04-11 22:56:01,250 | INFO | train_grpo_train | metrics_logged mode=train step=791
2026-04-11 22:56:07,007 | INFO | train_grpo_train | metrics_logged mode=train step=792
2026-04-11 22:56:11,714 | INFO | train_grpo_train | metrics_logged mode=train step=793
2026-04-11 22:56:16,556 | INFO | train_grpo_train | metrics_logged mode=train step=794
2026-04-11 22:56:21,313 | INFO | train_grpo_train | metrics_logged mode=train step=795
2026-04-11 22:56:28,688 | INFO | train_grpo_train | metrics_logged mode=train step=796
2026-04-11 22:56:33,682 | INFO | train_grpo_train | metrics_logged mode=train step=797
2026-04-11 22:56:38,447 | INFO | train_grpo_train | metrics_logged mode=train step=798
2026-04-11 22:56:45,214 | INFO | train_grpo_train | metrics_logged mode=train step=799
2026-04-11 22:56:50,658 | INFO | train_grpo_train | metrics_logged mode=train step=800
2026-04-11 22:58:16,586 | INFO | train_grpo_train | metrics_logged mode=eval step=800
2026-04-11 22:58:23,384 | INFO | train_grpo_train | metrics_logged mode=train step=801
2026-04-11 22:58:28,067 | INFO | train_grpo_train | metrics_logged mode=train step=802
2026-04-11 22:58:32,953 | INFO | train_grpo_train | metrics_logged mode=train step=803
2026-04-11 22:58:44,019 | INFO | train_grpo_train | metrics_logged mode=train step=804
2026-04-11 22:58:48,788 | INFO | train_grpo_train | metrics_logged mode=train step=805
2026-04-11 22:58:53,432 | INFO | train_grpo_train | metrics_logged mode=train step=806
2026-04-11 22:58:58,329 | INFO | train_grpo_train | metrics_logged mode=train step=807
2026-04-11 22:59:02,599 | INFO | train_grpo_train | metrics_logged mode=train step=808
2026-04-11 22:59:09,234 | INFO | train_grpo_train | metrics_logged mode=train step=809
2026-04-11 22:59:14,111 | INFO | train_grpo_train | metrics_logged mode=train step=810
2026-04-11 22:59:20,864 | INFO | train_grpo_train | metrics_logged mode=train step=811
2026-04-11 22:59:25,914 | INFO | train_grpo_train | metrics_logged mode=train step=812
2026-04-11 22:59:34,169 | INFO | train_grpo_train | metrics_logged mode=train step=813
2026-04-11 22:59:40,099 | INFO | train_grpo_train | metrics_logged mode=train step=814
2026-04-11 22:59:44,842 | INFO | train_grpo_train | metrics_logged mode=train step=815
2026-04-11 22:59:49,253 | INFO | train_grpo_train | metrics_logged mode=train step=816
2026-04-11 22:59:54,485 | INFO | train_grpo_train | metrics_logged mode=train step=817
2026-04-11 23:00:03,172 | INFO | train_grpo_train | metrics_logged mode=train step=818
2026-04-11 23:00:08,137 | INFO | train_grpo_train | metrics_logged mode=train step=819
2026-04-11 23:00:14,131 | INFO | train_grpo_train | metrics_logged mode=train step=820
2026-04-11 23:00:23,670 | INFO | train_grpo_train | metrics_logged mode=train step=821
2026-04-11 23:00:28,575 | INFO | train_grpo_train | metrics_logged mode=train step=822
2026-04-11 23:00:36,010 | INFO | train_grpo_train | metrics_logged mode=train step=823
2026-04-11 23:00:40,825 | INFO | train_grpo_train | metrics_logged mode=train step=824
2026-04-11 23:00:45,630 | INFO | train_grpo_train | metrics_logged mode=train step=825
2026-04-11 23:00:54,663 | INFO | train_grpo_train | metrics_logged mode=train step=826
2026-04-11 23:00:59,364 | INFO | train_grpo_train | metrics_logged mode=train step=827
2026-04-11 23:01:04,067 | INFO | train_grpo_train | metrics_logged mode=train step=828
2026-04-11 23:01:10,094 | INFO | train_grpo_train | metrics_logged mode=train step=829
2026-04-11 23:01:15,715 | INFO | train_grpo_train | metrics_logged mode=train step=830
2026-04-11 23:01:21,586 | INFO | train_grpo_train | metrics_logged mode=train step=831
2026-04-11 23:01:32,020 | INFO | train_grpo_train | metrics_logged mode=train step=832
2026-04-11 23:01:36,282 | INFO | train_grpo_train | metrics_logged mode=train step=833
2026-04-11 23:01:41,068 | INFO | train_grpo_train | metrics_logged mode=train step=834
2026-04-11 23:01:46,843 | INFO | train_grpo_train | metrics_logged mode=train step=835
2026-04-11 23:01:52,569 | INFO | train_grpo_train | metrics_logged mode=train step=836
2026-04-11 23:01:56,759 | INFO | train_grpo_train | metrics_logged mode=train step=837
2026-04-11 23:02:04,669 | INFO | train_grpo_train | metrics_logged mode=train step=838
2026-04-11 23:02:09,984 | INFO | train_grpo_train | metrics_logged mode=train step=839
2026-04-11 23:02:14,773 | INFO | train_grpo_train | metrics_logged mode=train step=840
2026-04-11 23:02:19,615 | INFO | train_grpo_train | metrics_logged mode=train step=841
2026-04-11 23:02:24,014 | INFO | train_grpo_train | metrics_logged mode=train step=842
2026-04-11 23:02:33,646 | INFO | train_grpo_train | metrics_logged mode=train step=843
2026-04-11 23:02:39,436 | INFO | train_grpo_train | metrics_logged mode=train step=844
2026-04-11 23:02:44,722 | INFO | train_grpo_train | metrics_logged mode=train step=845
2026-04-11 23:02:52,881 | INFO | train_grpo_train | metrics_logged mode=train step=846
2026-04-11 23:02:57,786 | INFO | train_grpo_train | metrics_logged mode=train step=847
2026-04-11 23:03:02,988 | INFO | train_grpo_train | metrics_logged mode=train step=848
2026-04-11 23:03:10,319 | INFO | train_grpo_train | metrics_logged mode=train step=849
2026-04-11 23:03:15,274 | INFO | train_grpo_train | metrics_logged mode=train step=850
2026-04-11 23:04:30,996 | INFO | train_grpo_train | metrics_logged mode=eval step=850
2026-04-11 23:04:39,430 | INFO | train_grpo_train | metrics_logged mode=train step=851
2026-04-11 23:04:44,534 | INFO | train_grpo_train | metrics_logged mode=train step=852
2026-04-11 23:04:53,386 | INFO | train_grpo_train | metrics_logged mode=train step=853
2026-04-11 23:04:58,988 | INFO | train_grpo_train | metrics_logged mode=train step=854
2026-04-11 23:05:03,700 | INFO | train_grpo_train | metrics_logged mode=train step=855
2026-04-11 23:05:08,294 | INFO | train_grpo_train | metrics_logged mode=train step=856
2026-04-11 23:05:13,157 | INFO | train_grpo_train | metrics_logged mode=train step=857
2026-04-11 23:05:20,276 | INFO | train_grpo_train | metrics_logged mode=train step=858
2026-04-11 23:05:25,840 | INFO | train_grpo_train | metrics_logged mode=train step=859
2026-04-11 23:05:31,474 | INFO | train_grpo_train | metrics_logged mode=train step=860
2026-04-11 23:05:36,945 | INFO | train_grpo_train | metrics_logged mode=train step=861
2026-04-11 23:05:42,523 | INFO | train_grpo_train | metrics_logged mode=train step=862
2026-04-11 23:05:48,245 | INFO | train_grpo_train | metrics_logged mode=train step=863
2026-04-11 23:05:53,074 | INFO | train_grpo_train | metrics_logged mode=train step=864
2026-04-11 23:05:58,076 | INFO | train_grpo_train | metrics_logged mode=train step=865
2026-04-11 23:06:03,287 | INFO | train_grpo_train | metrics_logged mode=train step=866
2026-04-11 23:06:08,522 | INFO | train_grpo_train | metrics_logged mode=train step=867
2026-04-11 23:06:13,770 | INFO | train_grpo_train | metrics_logged mode=train step=868
2026-04-11 23:06:19,110 | INFO | train_grpo_train | metrics_logged mode=train step=869
2026-04-11 23:06:25,197 | INFO | train_grpo_train | metrics_logged mode=train step=870
2026-04-11 23:06:31,440 | INFO | train_grpo_train | metrics_logged mode=train step=871
2026-04-11 23:06:37,233 | INFO | train_grpo_train | metrics_logged mode=train step=872
2026-04-11 23:06:41,943 | INFO | train_grpo_train | metrics_logged mode=train step=873
2026-04-11 23:06:47,396 | INFO | train_grpo_train | metrics_logged mode=train step=874
2026-04-11 23:06:52,612 | INFO | train_grpo_train | metrics_logged mode=train step=875
2026-04-11 23:06:59,628 | INFO | train_grpo_train | metrics_logged mode=train step=876
2026-04-11 23:07:04,683 | INFO | train_grpo_train | metrics_logged mode=train step=877
2026-04-11 23:07:09,412 | INFO | train_grpo_train | metrics_logged mode=train step=878
2026-04-11 23:07:14,017 | INFO | train_grpo_train | metrics_logged mode=train step=879
2026-04-11 23:07:19,062 | INFO | train_grpo_train | metrics_logged mode=train step=880
2026-04-11 23:07:27,069 | INFO | train_grpo_train | metrics_logged mode=train step=881
2026-04-11 23:07:33,182 | INFO | train_grpo_train | metrics_logged mode=train step=882
2026-04-11 23:07:37,961 | INFO | train_grpo_train | metrics_logged mode=train step=883
2026-04-11 23:07:44,365 | INFO | train_grpo_train | metrics_logged mode=train step=884
2026-04-11 23:07:49,107 | INFO | train_grpo_train | metrics_logged mode=train step=885
2026-04-11 23:07:56,775 | INFO | train_grpo_train | metrics_logged mode=train step=886
2026-04-11 23:08:01,963 | INFO | train_grpo_train | metrics_logged mode=train step=887
2026-04-11 23:08:06,598 | INFO | train_grpo_train | metrics_logged mode=train step=888
2026-04-11 23:08:11,444 | INFO | train_grpo_train | metrics_logged mode=train step=889
2026-04-11 23:08:17,513 | INFO | train_grpo_train | metrics_logged mode=train step=890
2026-04-11 23:08:22,354 | INFO | train_grpo_train | metrics_logged mode=train step=891
2026-04-11 23:08:27,590 | INFO | train_grpo_train | metrics_logged mode=train step=892
2026-04-11 23:08:33,512 | INFO | train_grpo_train | metrics_logged mode=train step=893
2026-04-11 23:08:38,152 | INFO | train_grpo_train | metrics_logged mode=train step=894
2026-04-11 23:08:43,368 | INFO | train_grpo_train | metrics_logged mode=train step=895
2026-04-11 23:08:48,060 | INFO | train_grpo_train | metrics_logged mode=train step=896
2026-04-11 23:08:53,092 | INFO | train_grpo_train | metrics_logged mode=train step=897
2026-04-11 23:08:57,770 | INFO | train_grpo_train | metrics_logged mode=train step=898
2026-04-11 23:09:03,113 | INFO | train_grpo_train | metrics_logged mode=train step=899
2026-04-11 23:09:07,869 | INFO | train_grpo_train | metrics_logged mode=train step=900
2026-04-11 23:10:24,266 | INFO | train_grpo_train | metrics_logged mode=eval step=900
2026-04-11 23:10:32,590 | INFO | train_grpo_train | metrics_logged mode=train step=901
2026-04-11 23:10:38,021 | INFO | train_grpo_train | metrics_logged mode=train step=902
2026-04-11 23:10:43,333 | INFO | train_grpo_train | metrics_logged mode=train step=903
2026-04-11 23:10:53,208 | INFO | train_grpo_train | metrics_logged mode=train step=904
2026-04-11 23:10:59,112 | INFO | train_grpo_train | metrics_logged mode=train step=905
2026-04-11 23:11:08,735 | INFO | train_grpo_train | metrics_logged mode=train step=906
2026-04-11 23:11:16,708 | INFO | train_grpo_train | metrics_logged mode=train step=907
2026-04-11 23:11:26,409 | INFO | train_grpo_train | metrics_logged mode=train step=908
2026-04-11 23:11:32,202 | INFO | train_grpo_train | metrics_logged mode=train step=909
2026-04-11 23:11:40,044 | INFO | train_grpo_train | metrics_logged mode=train step=910
2026-04-11 23:11:49,603 | INFO | train_grpo_train | metrics_logged mode=train step=911
2026-04-11 23:11:59,356 | INFO | train_grpo_train | metrics_logged mode=train step=912
2026-04-11 23:12:09,203 | INFO | train_grpo_train | metrics_logged mode=train step=913
2026-04-11 23:12:14,063 | INFO | train_grpo_train | metrics_logged mode=train step=914
2026-04-11 23:12:24,030 | INFO | train_grpo_train | metrics_logged mode=train step=915
2026-04-11 23:12:28,716 | INFO | train_grpo_train | metrics_logged mode=train step=916
2026-04-11 23:12:33,742 | INFO | train_grpo_train | metrics_logged mode=train step=917
2026-04-11 23:12:38,217 | INFO | train_grpo_train | metrics_logged mode=train step=918
2026-04-11 23:12:43,104 | INFO | train_grpo_train | metrics_logged mode=train step=919
2026-04-11 23:12:50,916 | INFO | train_grpo_train | metrics_logged mode=train step=920
2026-04-11 23:13:01,582 | INFO | train_grpo_train | metrics_logged mode=train step=921
2026-04-11 23:13:08,752 | INFO | train_grpo_train | metrics_logged mode=train step=922
2026-04-11 23:13:13,476 | INFO | train_grpo_train | metrics_logged mode=train step=923
2026-04-11 23:13:23,504 | INFO | train_grpo_train | metrics_logged mode=train step=924
2026-04-11 23:13:28,605 | INFO | train_grpo_train | metrics_logged mode=train step=925
2026-04-11 23:13:33,441 | INFO | train_grpo_train | metrics_logged mode=train step=926
2026-04-11 23:13:42,865 | INFO | train_grpo_train | metrics_logged mode=train step=927
2026-04-11 23:13:49,242 | INFO | train_grpo_train | metrics_logged mode=train step=928
2026-04-11 23:13:55,124 | INFO | train_grpo_train | metrics_logged mode=train step=929
2026-04-11 23:14:00,050 | INFO | train_grpo_train | metrics_logged mode=train step=930
2026-04-11 23:14:07,882 | INFO | train_grpo_train | metrics_logged mode=train step=931
2026-04-11 23:14:13,565 | INFO | train_grpo_train | metrics_logged mode=train step=932
2026-04-11 23:14:18,330 | INFO | train_grpo_train | metrics_logged mode=train step=933
2026-04-11 23:14:23,236 | INFO | train_grpo_train | metrics_logged mode=train step=934
2026-04-11 23:14:27,536 | INFO | train_grpo_train | metrics_logged mode=train step=935
2026-04-11 23:14:32,514 | INFO | train_grpo_train | metrics_logged mode=train step=936
2026-04-11 23:14:37,398 | INFO | train_grpo_train | metrics_logged mode=train step=937
2026-04-11 23:14:43,170 | INFO | train_grpo_train | metrics_logged mode=train step=938
2026-04-11 23:14:47,726 | INFO | train_grpo_train | metrics_logged mode=train step=939
2026-04-11 23:14:53,156 | INFO | train_grpo_train | metrics_logged mode=train step=940
2026-04-11 23:14:58,016 | INFO | train_grpo_train | metrics_logged mode=train step=941
2026-04-11 23:15:02,442 | INFO | train_grpo_train | metrics_logged mode=train step=942
2026-04-11 23:15:06,889 | INFO | train_grpo_train | metrics_logged mode=train step=943
2026-04-11 23:15:12,355 | INFO | train_grpo_train | metrics_logged mode=train step=944
2026-04-11 23:15:18,158 | INFO | train_grpo_train | metrics_logged mode=train step=945
2026-04-11 23:15:24,021 | INFO | train_grpo_train | metrics_logged mode=train step=946
2026-04-11 23:15:31,305 | INFO | train_grpo_train | metrics_logged mode=train step=947
2026-04-11 23:15:35,808 | INFO | train_grpo_train | metrics_logged mode=train step=948
2026-04-11 23:15:40,254 | INFO | train_grpo_train | metrics_logged mode=train step=949
2026-04-11 23:15:45,378 | INFO | train_grpo_train | metrics_logged mode=train step=950
2026-04-11 23:16:56,665 | INFO | train_grpo_train | metrics_logged mode=eval step=950
2026-04-11 23:17:03,908 | INFO | train_grpo_train | metrics_logged mode=train step=951
2026-04-11 23:17:13,628 | INFO | train_grpo_train | metrics_logged mode=train step=952
2026-04-11 23:17:18,566 | INFO | train_grpo_train | metrics_logged mode=train step=953
2026-04-11 23:17:23,815 | INFO | train_grpo_train | metrics_logged mode=train step=954
2026-04-11 23:17:29,113 | INFO | train_grpo_train | metrics_logged mode=train step=955
2026-04-11 23:17:34,277 | INFO | train_grpo_train | metrics_logged mode=train step=956
2026-04-11 23:17:38,927 | INFO | train_grpo_train | metrics_logged mode=train step=957
2026-04-11 23:17:43,219 | INFO | train_grpo_train | metrics_logged mode=train step=958
2026-04-11 23:17:50,835 | INFO | train_grpo_train | metrics_logged mode=train step=959
2026-04-11 23:17:56,620 | INFO | train_grpo_train | metrics_logged mode=train step=960
2026-04-11 23:18:01,282 | INFO | train_grpo_train | metrics_logged mode=train step=961
2026-04-11 23:18:05,963 | INFO | train_grpo_train | metrics_logged mode=train step=962
2026-04-11 23:18:15,471 | INFO | train_grpo_train | metrics_logged mode=train step=963
2026-04-11 23:18:22,389 | INFO | train_grpo_train | metrics_logged mode=train step=964
2026-04-11 23:18:27,196 | INFO | train_grpo_train | metrics_logged mode=train step=965
2026-04-11 23:18:31,827 | INFO | train_grpo_train | metrics_logged mode=train step=966
2026-04-11 23:18:38,296 | INFO | train_grpo_train | metrics_logged mode=train step=967
2026-04-11 23:18:43,190 | INFO | train_grpo_train | metrics_logged mode=train step=968
2026-04-11 23:18:48,470 | INFO | train_grpo_train | metrics_logged mode=train step=969
2026-04-11 23:18:53,277 | INFO | train_grpo_train | metrics_logged mode=train step=970
2026-04-11 23:18:59,365 | INFO | train_grpo_train | metrics_logged mode=train step=971
2026-04-11 23:19:06,465 | INFO | train_grpo_train | metrics_logged mode=train step=972
2026-04-11 23:19:11,053 | INFO | train_grpo_train | metrics_logged mode=train step=973
2026-04-11 23:19:15,848 | INFO | train_grpo_train | metrics_logged mode=train step=974
2026-04-11 23:19:20,807 | INFO | train_grpo_train | metrics_logged mode=train step=975
2026-04-11 23:19:25,364 | INFO | train_grpo_train | metrics_logged mode=train step=976
2026-04-11 23:19:30,161 | INFO | train_grpo_train | metrics_logged mode=train step=977
2026-04-11 23:19:35,038 | INFO | train_grpo_train | metrics_logged mode=train step=978
2026-04-11 23:19:39,855 | INFO | train_grpo_train | metrics_logged mode=train step=979
2026-04-11 23:19:45,176 | INFO | train_grpo_train | metrics_logged mode=train step=980
2026-04-11 23:19:49,840 | INFO | train_grpo_train | metrics_logged mode=train step=981
2026-04-11 23:19:54,364 | INFO | train_grpo_train | metrics_logged mode=train step=982
2026-04-11 23:19:59,289 | INFO | train_grpo_train | metrics_logged mode=train step=983
2026-04-11 23:20:03,674 | INFO | train_grpo_train | metrics_logged mode=train step=984
2026-04-11 23:20:08,412 | INFO | train_grpo_train | metrics_logged mode=train step=985
2026-04-11 23:20:13,749 | INFO | train_grpo_train | metrics_logged mode=train step=986
2026-04-11 23:20:18,608 | INFO | train_grpo_train | metrics_logged mode=train step=987
2026-04-11 23:20:23,643 | INFO | train_grpo_train | metrics_logged mode=train step=988
2026-04-11 23:20:28,398 | INFO | train_grpo_train | metrics_logged mode=train step=989
2026-04-11 23:20:33,101 | INFO | train_grpo_train | metrics_logged mode=train step=990
2026-04-11 23:20:42,071 | INFO | train_grpo_train | metrics_logged mode=train step=991
2026-04-11 23:20:51,306 | INFO | train_grpo_train | metrics_logged mode=train step=992
2026-04-11 23:20:55,999 | INFO | train_grpo_train | metrics_logged mode=train step=993
2026-04-11 23:21:06,235 | INFO | train_grpo_train | metrics_logged mode=train step=994
2026-04-11 23:21:11,117 | INFO | train_grpo_train | metrics_logged mode=train step=995
2026-04-11 23:21:15,975 | INFO | train_grpo_train | metrics_logged mode=train step=996
2026-04-11 23:21:20,949 | INFO | train_grpo_train | metrics_logged mode=train step=997
2026-04-11 23:21:25,331 | INFO | train_grpo_train | metrics_logged mode=train step=998
2026-04-11 23:21:30,338 | INFO | train_grpo_train | metrics_logged mode=train step=999
2026-04-11 23:21:35,326 | INFO | train_grpo_train | metrics_logged mode=train step=1000
2026-04-11 23:22:59,015 | INFO | train_grpo_train | metrics_logged mode=eval step=1000
2026-04-11 23:23:06,473 | INFO | train_grpo_train | metrics_logged mode=train step=1001
2026-04-11 23:23:11,231 | INFO | train_grpo_train | metrics_logged mode=train step=1002
2026-04-11 23:23:16,517 | INFO | train_grpo_train | metrics_logged mode=train step=1003
2026-04-11 23:23:21,176 | INFO | train_grpo_train | metrics_logged mode=train step=1004
2026-04-11 23:23:27,553 | INFO | train_grpo_train | metrics_logged mode=train step=1005
2026-04-11 23:23:32,597 | INFO | train_grpo_train | metrics_logged mode=train step=1006
2026-04-11 23:23:37,276 | INFO | train_grpo_train | metrics_logged mode=train step=1007
2026-04-11 23:23:46,939 | INFO | train_grpo_train | metrics_logged mode=train step=1008
2026-04-11 23:23:52,080 | INFO | train_grpo_train | metrics_logged mode=train step=1009
2026-04-11 23:23:56,857 | INFO | train_grpo_train | metrics_logged mode=train step=1010
2026-04-11 23:24:01,667 | INFO | train_grpo_train | metrics_logged mode=train step=1011
2026-04-11 23:24:06,814 | INFO | train_grpo_train | metrics_logged mode=train step=1012
2026-04-11 23:24:12,139 | INFO | train_grpo_train | metrics_logged mode=train step=1013
2026-04-11 23:24:17,043 | INFO | train_grpo_train | metrics_logged mode=train step=1014
2026-04-11 23:24:21,443 | INFO | train_grpo_train | metrics_logged mode=train step=1015
2026-04-11 23:24:31,610 | INFO | train_grpo_train | metrics_logged mode=train step=1016
2026-04-11 23:24:36,509 | INFO | train_grpo_train | metrics_logged mode=train step=1017
2026-04-11 23:24:41,195 | INFO | train_grpo_train | metrics_logged mode=train step=1018
2026-04-11 23:24:46,172 | INFO | train_grpo_train | metrics_logged mode=train step=1019
2026-04-11 23:24:51,892 | INFO | train_grpo_train | metrics_logged mode=train step=1020
2026-04-11 23:24:56,979 | INFO | train_grpo_train | metrics_logged mode=train step=1021
2026-04-11 23:25:01,839 | INFO | train_grpo_train | metrics_logged mode=train step=1022
2026-04-11 23:25:06,781 | INFO | train_grpo_train | metrics_logged mode=train step=1023
2026-04-11 23:25:15,764 | INFO | train_grpo_train | metrics_logged mode=train step=1024
2026-04-11 23:25:20,841 | INFO | train_grpo_train | metrics_logged mode=train step=1025
2026-04-11 23:25:25,396 | INFO | train_grpo_train | metrics_logged mode=train step=1026
2026-04-11 23:25:30,353 | INFO | train_grpo_train | metrics_logged mode=train step=1027
2026-04-11 23:25:34,928 | INFO | train_grpo_train | metrics_logged mode=train step=1028
2026-04-11 23:25:39,311 | INFO | train_grpo_train | metrics_logged mode=train step=1029
2026-04-11 23:25:43,999 | INFO | train_grpo_train | metrics_logged mode=train step=1030
2026-04-11 23:25:53,564 | INFO | train_grpo_train | metrics_logged mode=train step=1031
2026-04-11 23:26:03,461 | INFO | train_grpo_train | metrics_logged mode=train step=1032
2026-04-11 23:26:08,004 | INFO | train_grpo_train | metrics_logged mode=train step=1033
2026-04-11 23:26:12,756 | INFO | train_grpo_train | metrics_logged mode=train step=1034
2026-04-11 23:26:17,723 | INFO | train_grpo_train | metrics_logged mode=train step=1035
2026-04-11 23:26:21,974 | INFO | train_grpo_train | metrics_logged mode=train step=1036
2026-04-11 23:26:27,680 | INFO | train_grpo_train | metrics_logged mode=train step=1037
2026-04-11 23:26:32,002 | INFO | train_grpo_train | metrics_logged mode=train step=1038
2026-04-11 23:26:36,712 | INFO | train_grpo_train | metrics_logged mode=train step=1039
2026-04-11 23:26:42,729 | INFO | train_grpo_train | metrics_logged mode=train step=1040
2026-04-11 23:26:46,939 | INFO | train_grpo_train | metrics_logged mode=train step=1041
2026-04-11 23:26:52,468 | INFO | train_grpo_train | metrics_logged mode=train step=1042
2026-04-11 23:26:57,146 | INFO | train_grpo_train | metrics_logged mode=train step=1043
2026-04-11 23:27:02,338 | INFO | train_grpo_train | metrics_logged mode=train step=1044
2026-04-11 23:27:07,775 | INFO | train_grpo_train | metrics_logged mode=train step=1045
2026-04-11 23:27:12,443 | INFO | train_grpo_train | metrics_logged mode=train step=1046
2026-04-11 23:27:22,064 | INFO | train_grpo_train | metrics_logged mode=train step=1047
2026-04-11 23:27:26,811 | INFO | train_grpo_train | metrics_logged mode=train step=1048
2026-04-11 23:27:32,348 | INFO | train_grpo_train | metrics_logged mode=train step=1049
2026-04-11 23:27:37,202 | INFO | train_grpo_train | metrics_logged mode=train step=1050
2026-04-11 23:28:52,133 | INFO | train_grpo_train | metrics_logged mode=eval step=1050
2026-04-11 23:29:01,593 | INFO | train_grpo_train | metrics_logged mode=train step=1051
2026-04-11 23:29:06,661 | INFO | train_grpo_train | metrics_logged mode=train step=1052
2026-04-11 23:29:12,178 | INFO | train_grpo_train | metrics_logged mode=train step=1053
2026-04-11 23:29:17,666 | INFO | train_grpo_train | metrics_logged mode=train step=1054
2026-04-11 23:29:23,697 | INFO | train_grpo_train | metrics_logged mode=train step=1055
2026-04-11 23:29:28,576 | INFO | train_grpo_train | metrics_logged mode=train step=1056
2026-04-11 23:29:37,092 | INFO | train_grpo_train | metrics_logged mode=train step=1057
2026-04-11 23:29:45,389 | INFO | train_grpo_train | metrics_logged mode=train step=1058
2026-04-11 23:29:50,243 | INFO | train_grpo_train | metrics_logged mode=train step=1059
2026-04-11 23:30:00,136 | INFO | train_grpo_train | metrics_logged mode=train step=1060
2026-04-11 23:30:07,922 | INFO | train_grpo_train | metrics_logged mode=train step=1061
2026-04-11 23:30:14,247 | INFO | train_grpo_train | metrics_logged mode=train step=1062
2026-04-11 23:30:19,359 | INFO | train_grpo_train | metrics_logged mode=train step=1063
2026-04-11 23:30:25,259 | INFO | train_grpo_train | metrics_logged mode=train step=1064
2026-04-11 23:30:29,838 | INFO | train_grpo_train | metrics_logged mode=train step=1065
2026-04-11 23:30:34,635 | INFO | train_grpo_train | metrics_logged mode=train step=1066
2026-04-11 23:30:39,081 | INFO | train_grpo_train | metrics_logged mode=train step=1067
2026-04-11 23:30:43,586 | INFO | train_grpo_train | metrics_logged mode=train step=1068
2026-04-11 23:30:53,708 | INFO | train_grpo_train | metrics_logged mode=train step=1069
2026-04-11 23:30:58,215 | INFO | train_grpo_train | metrics_logged mode=train step=1070
2026-04-11 23:31:05,439 | INFO | train_grpo_train | metrics_logged mode=train step=1071
2026-04-11 23:31:10,573 | INFO | train_grpo_train | metrics_logged mode=train step=1072
2026-04-11 23:31:16,099 | INFO | train_grpo_train | metrics_logged mode=train step=1073
2026-04-11 23:31:23,473 | INFO | train_grpo_train | metrics_logged mode=train step=1074
2026-04-11 23:31:31,119 | INFO | train_grpo_train | metrics_logged mode=train step=1075
2026-04-11 23:31:37,317 | INFO | train_grpo_train | metrics_logged mode=train step=1076
2026-04-11 23:31:41,878 | INFO | train_grpo_train | metrics_logged mode=train step=1077
2026-04-11 23:31:50,972 | INFO | train_grpo_train | metrics_logged mode=train step=1078
2026-04-11 23:31:55,883 | INFO | train_grpo_train | metrics_logged mode=train step=1079
2026-04-11 23:32:00,640 | INFO | train_grpo_train | metrics_logged mode=train step=1080
2026-04-11 23:32:05,562 | INFO | train_grpo_train | metrics_logged mode=train step=1081
2026-04-11 23:32:10,651 | INFO | train_grpo_train | metrics_logged mode=train step=1082
2026-04-11 23:32:16,377 | INFO | train_grpo_train | metrics_logged mode=train step=1083
2026-04-11 23:32:21,678 | INFO | train_grpo_train | metrics_logged mode=train step=1084
2026-04-11 23:32:30,685 | INFO | train_grpo_train | metrics_logged mode=train step=1085
2026-04-11 23:32:39,822 | INFO | train_grpo_train | metrics_logged mode=train step=1086
2026-04-11 23:32:44,463 | INFO | train_grpo_train | metrics_logged mode=train step=1087
2026-04-11 23:32:48,581 | INFO | train_grpo_train | metrics_logged mode=train step=1088
2026-04-11 23:32:53,922 | INFO | train_grpo_train | metrics_logged mode=train step=1089
2026-04-11 23:33:01,002 | INFO | train_grpo_train | metrics_logged mode=train step=1090
2026-04-11 23:33:05,411 | INFO | train_grpo_train | metrics_logged mode=train step=1091
2026-04-11 23:33:09,947 | INFO | train_grpo_train | metrics_logged mode=train step=1092
2026-04-11 23:33:14,388 | INFO | train_grpo_train | metrics_logged mode=train step=1093
2026-04-11 23:33:19,702 | INFO | train_grpo_train | metrics_logged mode=train step=1094
2026-04-11 23:33:24,112 | INFO | train_grpo_train | metrics_logged mode=train step=1095
2026-04-11 23:33:29,560 | INFO | train_grpo_train | metrics_logged mode=train step=1096
2026-04-11 23:33:37,226 | INFO | train_grpo_train | metrics_logged mode=train step=1097
2026-04-11 23:33:41,786 | INFO | train_grpo_train | metrics_logged mode=train step=1098
2026-04-11 23:33:48,066 | INFO | train_grpo_train | metrics_logged mode=train step=1099
2026-04-11 23:33:55,901 | INFO | train_grpo_train | metrics_logged mode=train step=1100
2026-04-11 23:34:59,623 | INFO | train_grpo_train | metrics_logged mode=eval step=1100
2026-04-11 23:35:07,116 | INFO | train_grpo_train | metrics_logged mode=train step=1101
2026-04-11 23:35:15,155 | INFO | train_grpo_train | metrics_logged mode=train step=1102
2026-04-11 23:35:20,128 | INFO | train_grpo_train | metrics_logged mode=train step=1103
2026-04-11 23:35:25,516 | INFO | train_grpo_train | metrics_logged mode=train step=1104
2026-04-11 23:35:30,708 | INFO | train_grpo_train | metrics_logged mode=train step=1105
2026-04-11 23:35:38,171 | INFO | train_grpo_train | metrics_logged mode=train step=1106
2026-04-11 23:35:42,493 | INFO | train_grpo_train | metrics_logged mode=train step=1107
2026-04-11 23:35:47,288 | INFO | train_grpo_train | metrics_logged mode=train step=1108
2026-04-11 23:35:51,654 | INFO | train_grpo_train | metrics_logged mode=train step=1109
2026-04-11 23:35:57,284 | INFO | train_grpo_train | metrics_logged mode=train step=1110
2026-04-11 23:36:01,900 | INFO | train_grpo_train | metrics_logged mode=train step=1111
2026-04-11 23:36:06,885 | INFO | train_grpo_train | metrics_logged mode=train step=1112
2026-04-11 23:36:10,966 | INFO | train_grpo_train | metrics_logged mode=train step=1113
2026-04-11 23:36:15,298 | INFO | train_grpo_train | metrics_logged mode=train step=1114
2026-04-11 23:36:19,897 | INFO | train_grpo_train | metrics_logged mode=train step=1115
2026-04-11 23:36:24,608 | INFO | train_grpo_train | metrics_logged mode=train step=1116
2026-04-11 23:36:32,701 | INFO | train_grpo_train | metrics_logged mode=train step=1117
2026-04-11 23:36:38,069 | INFO | train_grpo_train | metrics_logged mode=train step=1118
2026-04-11 23:36:42,689 | INFO | train_grpo_train | metrics_logged mode=train step=1119
2026-04-11 23:36:47,248 | INFO | train_grpo_train | metrics_logged mode=train step=1120
2026-04-11 23:36:51,847 | INFO | train_grpo_train | metrics_logged mode=train step=1121
2026-04-11 23:36:56,426 | INFO | train_grpo_train | metrics_logged mode=train step=1122
2026-04-11 23:37:01,072 | INFO | train_grpo_train | metrics_logged mode=train step=1123
2026-04-11 23:37:05,665 | INFO | train_grpo_train | metrics_logged mode=train step=1124
2026-04-11 23:37:11,173 | INFO | train_grpo_train | metrics_logged mode=train step=1125
2026-04-11 23:37:16,153 | INFO | train_grpo_train | metrics_logged mode=train step=1126
2026-04-11 23:37:20,958 | INFO | train_grpo_train | metrics_logged mode=train step=1127
2026-04-11 23:37:25,463 | INFO | train_grpo_train | metrics_logged mode=train step=1128
2026-04-11 23:37:35,230 | INFO | train_grpo_train | metrics_logged mode=train step=1129
2026-04-11 23:37:44,658 | INFO | train_grpo_train | metrics_logged mode=train step=1130
2026-04-11 23:37:49,070 | INFO | train_grpo_train | metrics_logged mode=train step=1131
2026-04-11 23:37:53,319 | INFO | train_grpo_train | metrics_logged mode=train step=1132
2026-04-11 23:37:58,469 | INFO | train_grpo_train | metrics_logged mode=train step=1133
2026-04-11 23:38:03,461 | INFO | train_grpo_train | metrics_logged mode=train step=1134
2026-04-11 23:38:08,475 | INFO | train_grpo_train | metrics_logged mode=train step=1135
2026-04-11 23:38:17,754 | INFO | train_grpo_train | metrics_logged mode=train step=1136
2026-04-11 23:38:23,280 | INFO | train_grpo_train | metrics_logged mode=train step=1137
2026-04-11 23:38:28,504 | INFO | train_grpo_train | metrics_logged mode=train step=1138
2026-04-11 23:38:33,938 | INFO | train_grpo_train | metrics_logged mode=train step=1139
2026-04-11 23:38:38,754 | INFO | train_grpo_train | metrics_logged mode=train step=1140
2026-04-11 23:38:43,675 | INFO | train_grpo_train | metrics_logged mode=train step=1141
2026-04-11 23:38:48,405 | INFO | train_grpo_train | metrics_logged mode=train step=1142
2026-04-11 23:38:58,946 | INFO | train_grpo_train | metrics_logged mode=train step=1143
2026-04-11 23:39:08,491 | INFO | train_grpo_train | metrics_logged mode=train step=1144
2026-04-11 23:39:13,197 | INFO | train_grpo_train | metrics_logged mode=train step=1145
2026-04-11 23:39:18,075 | INFO | train_grpo_train | metrics_logged mode=train step=1146
2026-04-11 23:39:24,079 | INFO | train_grpo_train | metrics_logged mode=train step=1147
2026-04-11 23:39:28,652 | INFO | train_grpo_train | metrics_logged mode=train step=1148
2026-04-11 23:39:33,829 | INFO | train_grpo_train | metrics_logged mode=train step=1149
2026-04-11 23:39:40,406 | INFO | train_grpo_train | metrics_logged mode=train step=1150
2026-04-11 23:40:50,084 | INFO | train_grpo_train | metrics_logged mode=eval step=1150
2026-04-11 23:40:58,755 | INFO | train_grpo_train | metrics_logged mode=train step=1151
2026-04-11 23:41:03,519 | INFO | train_grpo_train | metrics_logged mode=train step=1152
2026-04-11 23:41:08,898 | INFO | train_grpo_train | metrics_logged mode=train step=1153
2026-04-11 23:41:13,116 | INFO | train_grpo_train | metrics_logged mode=train step=1154
2026-04-11 23:41:19,913 | INFO | train_grpo_train | metrics_logged mode=train step=1155
2026-04-11 23:41:24,345 | INFO | train_grpo_train | metrics_logged mode=train step=1156
2026-04-11 23:41:28,917 | INFO | train_grpo_train | metrics_logged mode=train step=1157
2026-04-11 23:41:33,383 | INFO | train_grpo_train | metrics_logged mode=train step=1158
2026-04-11 23:41:37,605 | INFO | train_grpo_train | metrics_logged mode=train step=1159
2026-04-11 23:41:41,949 | INFO | train_grpo_train | metrics_logged mode=train step=1160
2026-04-11 23:41:46,170 | INFO | train_grpo_train | metrics_logged mode=train step=1161
2026-04-11 23:41:51,353 | INFO | train_grpo_train | metrics_logged mode=train step=1162
2026-04-11 23:41:57,817 | INFO | train_grpo_train | metrics_logged mode=train step=1163
2026-04-11 23:42:02,410 | INFO | train_grpo_train | metrics_logged mode=train step=1164
2026-04-11 23:42:06,610 | INFO | train_grpo_train | metrics_logged mode=train step=1165
2026-04-11 23:42:11,056 | INFO | train_grpo_train | metrics_logged mode=train step=1166
2026-04-11 23:42:17,201 | INFO | train_grpo_train | metrics_logged mode=train step=1167
2026-04-11 23:42:21,958 | INFO | train_grpo_train | metrics_logged mode=train step=1168
2026-04-11 23:42:29,127 | INFO | train_grpo_train | metrics_logged mode=train step=1169
2026-04-11 23:42:33,750 | INFO | train_grpo_train | metrics_logged mode=train step=1170
2026-04-11 23:42:38,453 | INFO | train_grpo_train | metrics_logged mode=train step=1171
2026-04-11 23:42:43,583 | INFO | train_grpo_train | metrics_logged mode=train step=1172
2026-04-11 23:42:48,277 | INFO | train_grpo_train | metrics_logged mode=train step=1173
2026-04-11 23:42:52,959 | INFO | train_grpo_train | metrics_logged mode=train step=1174
2026-04-11 23:42:57,864 | INFO | train_grpo_train | metrics_logged mode=train step=1175
2026-04-11 23:43:05,834 | INFO | train_grpo_train | metrics_logged mode=train step=1176
2026-04-11 23:43:10,336 | INFO | train_grpo_train | metrics_logged mode=train step=1177
2026-04-11 23:43:19,967 | INFO | train_grpo_train | metrics_logged mode=train step=1178
2026-04-11 23:43:24,504 | INFO | train_grpo_train | metrics_logged mode=train step=1179
2026-04-11 23:43:28,958 | INFO | train_grpo_train | metrics_logged mode=train step=1180
2026-04-11 23:43:37,343 | INFO | train_grpo_train | metrics_logged mode=train step=1181
2026-04-11 23:43:41,959 | INFO | train_grpo_train | metrics_logged mode=train step=1182
2026-04-11 23:43:45,921 | INFO | train_grpo_train | metrics_logged mode=train step=1183
2026-04-11 23:43:50,877 | INFO | train_grpo_train | metrics_logged mode=train step=1184
2026-04-11 23:43:55,500 | INFO | train_grpo_train | metrics_logged mode=train step=1185
2026-04-11 23:44:01,980 | INFO | train_grpo_train | metrics_logged mode=train step=1186
2026-04-11 23:44:10,278 | INFO | train_grpo_train | metrics_logged mode=train step=1187
2026-04-11 23:44:18,325 | INFO | train_grpo_train | metrics_logged mode=train step=1188
2026-04-11 23:44:22,737 | INFO | train_grpo_train | metrics_logged mode=train step=1189
2026-04-11 23:44:27,747 | INFO | train_grpo_train | metrics_logged mode=train step=1190
2026-04-11 23:44:32,824 | INFO | train_grpo_train | metrics_logged mode=train step=1191
2026-04-11 23:44:37,340 | INFO | train_grpo_train | metrics_logged mode=train step=1192
2026-04-11 23:44:41,852 | INFO | train_grpo_train | metrics_logged mode=train step=1193
2026-04-11 23:44:46,565 | INFO | train_grpo_train | metrics_logged mode=train step=1194
2026-04-11 23:44:50,879 | INFO | train_grpo_train | metrics_logged mode=train step=1195
2026-04-11 23:44:55,682 | INFO | train_grpo_train | metrics_logged mode=train step=1196
2026-04-11 23:45:05,099 | INFO | train_grpo_train | metrics_logged mode=train step=1197
2026-04-11 23:45:09,436 | INFO | train_grpo_train | metrics_logged mode=train step=1198
2026-04-11 23:45:14,079 | INFO | train_grpo_train | metrics_logged mode=train step=1199
2026-04-11 23:45:18,446 | INFO | train_grpo_train | metrics_logged mode=train step=1200
2026-04-11 23:46:28,030 | INFO | train_grpo_train | metrics_logged mode=eval step=1200
2026-04-11 23:46:35,713 | INFO | train_grpo_train | metrics_logged mode=train step=1201
2026-04-11 23:46:40,467 | INFO | train_grpo_train | metrics_logged mode=train step=1202
2026-04-11 23:46:45,480 | INFO | train_grpo_train | metrics_logged mode=train step=1203
2026-04-11 23:46:50,778 | INFO | train_grpo_train | metrics_logged mode=train step=1204
2026-04-11 23:46:55,747 | INFO | train_grpo_train | metrics_logged mode=train step=1205
2026-04-11 23:47:00,725 | INFO | train_grpo_train | metrics_logged mode=train step=1206
2026-04-11 23:47:06,149 | INFO | train_grpo_train | metrics_logged mode=train step=1207
2026-04-11 23:47:10,896 | INFO | train_grpo_train | metrics_logged mode=train step=1208
2026-04-11 23:47:18,111 | INFO | train_grpo_train | metrics_logged mode=train step=1209
2026-04-11 23:47:24,988 | INFO | train_grpo_train | metrics_logged mode=train step=1210
2026-04-11 23:47:32,808 | INFO | train_grpo_train | metrics_logged mode=train step=1211
2026-04-11 23:47:38,201 | INFO | train_grpo_train | metrics_logged mode=train step=1212
2026-04-11 23:47:43,654 | INFO | train_grpo_train | metrics_logged mode=train step=1213
2026-04-11 23:47:52,918 | INFO | train_grpo_train | metrics_logged mode=train step=1214
2026-04-11 23:48:00,478 | INFO | train_grpo_train | metrics_logged mode=train step=1215
2026-04-11 23:48:06,768 | INFO | train_grpo_train | metrics_logged mode=train step=1216
2026-04-11 23:48:12,760 | INFO | train_grpo_train | metrics_logged mode=train step=1217
2026-04-11 23:48:19,051 | INFO | train_grpo_train | metrics_logged mode=train step=1218
2026-04-11 23:48:25,068 | INFO | train_grpo_train | metrics_logged mode=train step=1219
2026-04-11 23:48:29,421 | INFO | train_grpo_train | metrics_logged mode=train step=1220
2026-04-11 23:48:36,892 | INFO | train_grpo_train | metrics_logged mode=train step=1221
2026-04-11 23:48:44,589 | INFO | train_grpo_train | metrics_logged mode=train step=1222
2026-04-11 23:48:49,203 | INFO | train_grpo_train | metrics_logged mode=train step=1223
2026-04-11 23:48:54,188 | INFO | train_grpo_train | metrics_logged mode=train step=1224
2026-04-11 23:49:00,703 | INFO | train_grpo_train | metrics_logged mode=train step=1225
2026-04-11 23:49:05,568 | INFO | train_grpo_train | metrics_logged mode=train step=1226
2026-04-11 23:49:09,947 | INFO | train_grpo_train | metrics_logged mode=train step=1227
2026-04-11 23:49:15,584 | INFO | train_grpo_train | metrics_logged mode=train step=1228
2026-04-11 23:49:20,327 | INFO | train_grpo_train | metrics_logged mode=train step=1229
2026-04-11 23:49:24,853 | INFO | train_grpo_train | metrics_logged mode=train step=1230
2026-04-11 23:49:29,709 | INFO | train_grpo_train | metrics_logged mode=train step=1231
2026-04-11 23:49:34,717 | INFO | train_grpo_train | metrics_logged mode=train step=1232
2026-04-11 23:49:41,537 | INFO | train_grpo_train | metrics_logged mode=train step=1233
2026-04-11 23:49:48,675 | INFO | train_grpo_train | metrics_logged mode=train step=1234
2026-04-11 23:49:53,590 | INFO | train_grpo_train | metrics_logged mode=train step=1235
2026-04-11 23:49:59,829 | INFO | train_grpo_train | metrics_logged mode=train step=1236
2026-04-11 23:50:04,580 | INFO | train_grpo_train | metrics_logged mode=train step=1237
2026-04-11 23:50:09,809 | INFO | train_grpo_train | metrics_logged mode=train step=1238
2026-04-11 23:50:14,294 | INFO | train_grpo_train | metrics_logged mode=train step=1239
2026-04-11 23:50:19,083 | INFO | train_grpo_train | metrics_logged mode=train step=1240
2026-04-11 23:50:24,783 | INFO | train_grpo_train | metrics_logged mode=train step=1241
2026-04-11 23:50:29,660 | INFO | train_grpo_train | metrics_logged mode=train step=1242
2026-04-11 23:50:34,531 | INFO | train_grpo_train | metrics_logged mode=train step=1243
2026-04-11 23:50:40,279 | INFO | train_grpo_train | metrics_logged mode=train step=1244
2026-04-11 23:50:47,230 | INFO | train_grpo_train | metrics_logged mode=train step=1245
2026-04-11 23:50:52,193 | INFO | train_grpo_train | metrics_logged mode=train step=1246
2026-04-11 23:50:57,453 | INFO | train_grpo_train | metrics_logged mode=train step=1247
2026-04-11 23:51:02,467 | INFO | train_grpo_train | metrics_logged mode=train step=1248
2026-04-11 23:51:07,657 | INFO | train_grpo_train | metrics_logged mode=train step=1249
2026-04-11 23:51:12,607 | INFO | train_grpo_train | metrics_logged mode=train step=1250
2026-04-11 23:52:09,004 | INFO | train_grpo_train | metrics_logged mode=eval step=1250
2026-04-11 23:52:17,273 | INFO | train_grpo_train | metrics_logged mode=train step=1251
2026-04-11 23:52:23,795 | INFO | train_grpo_train | metrics_logged mode=train step=1252
2026-04-11 23:52:31,647 | INFO | train_grpo_train | metrics_logged mode=train step=1253
2026-04-11 23:52:36,691 | INFO | train_grpo_train | metrics_logged mode=train step=1254
2026-04-11 23:52:42,005 | INFO | train_grpo_train | metrics_logged mode=train step=1255
2026-04-11 23:52:46,873 | INFO | train_grpo_train | metrics_logged mode=train step=1256
2026-04-11 23:52:51,437 | INFO | train_grpo_train | metrics_logged mode=train step=1257
2026-04-11 23:52:58,758 | INFO | train_grpo_train | metrics_logged mode=train step=1258
2026-04-11 23:53:03,944 | INFO | train_grpo_train | metrics_logged mode=train step=1259
2026-04-11 23:53:08,301 | INFO | train_grpo_train | metrics_logged mode=train step=1260
2026-04-11 23:53:13,980 | INFO | train_grpo_train | metrics_logged mode=train step=1261
2026-04-11 23:53:19,832 | INFO | train_grpo_train | metrics_logged mode=train step=1262
2026-04-11 23:53:27,151 | INFO | train_grpo_train | metrics_logged mode=train step=1263
2026-04-11 23:53:31,728 | INFO | train_grpo_train | metrics_logged mode=train step=1264
2026-04-11 23:53:36,075 | INFO | train_grpo_train | metrics_logged mode=train step=1265
2026-04-11 23:53:40,894 | INFO | train_grpo_train | metrics_logged mode=train step=1266
2026-04-11 23:53:45,590 | INFO | train_grpo_train | metrics_logged mode=train step=1267
2026-04-11 23:53:50,410 | INFO | train_grpo_train | metrics_logged mode=train step=1268
2026-04-11 23:53:55,223 | INFO | train_grpo_train | metrics_logged mode=train step=1269
2026-04-11 23:54:03,948 | INFO | train_grpo_train | metrics_logged mode=train step=1270
2026-04-11 23:54:08,790 | INFO | train_grpo_train | metrics_logged mode=train step=1271
2026-04-11 23:54:13,520 | INFO | train_grpo_train | metrics_logged mode=train step=1272
2026-04-11 23:54:19,210 | INFO | train_grpo_train | metrics_logged mode=train step=1273
2026-04-11 23:54:23,586 | INFO | train_grpo_train | metrics_logged mode=train step=1274
2026-04-11 23:54:29,099 | INFO | train_grpo_train | metrics_logged mode=train step=1275
2026-04-11 23:54:34,130 | INFO | train_grpo_train | metrics_logged mode=train step=1276
2026-04-11 23:54:40,227 | INFO | train_grpo_train | metrics_logged mode=train step=1277
2026-04-11 23:54:44,794 | INFO | train_grpo_train | metrics_logged mode=train step=1278
2026-04-11 23:54:49,847 | INFO | train_grpo_train | metrics_logged mode=train step=1279
2026-04-11 23:54:55,035 | INFO | train_grpo_train | metrics_logged mode=train step=1280
2026-04-11 23:54:59,791 | INFO | train_grpo_train | metrics_logged mode=train step=1281
2026-04-11 23:55:07,468 | INFO | train_grpo_train | metrics_logged mode=train step=1282
2026-04-11 23:55:12,363 | INFO | train_grpo_train | metrics_logged mode=train step=1283
2026-04-11 23:55:16,775 | INFO | train_grpo_train | metrics_logged mode=train step=1284
2026-04-11 23:55:22,307 | INFO | train_grpo_train | metrics_logged mode=train step=1285
2026-04-11 23:55:29,062 | INFO | train_grpo_train | metrics_logged mode=train step=1286
2026-04-11 23:55:35,396 | INFO | train_grpo_train | metrics_logged mode=train step=1287
2026-04-11 23:55:42,622 | INFO | train_grpo_train | metrics_logged mode=train step=1288
2026-04-11 23:55:47,458 | INFO | train_grpo_train | metrics_logged mode=train step=1289
2026-04-11 23:55:54,578 | INFO | train_grpo_train | metrics_logged mode=train step=1290
2026-04-11 23:55:59,727 | INFO | train_grpo_train | metrics_logged mode=train step=1291
2026-04-11 23:56:04,580 | INFO | train_grpo_train | metrics_logged mode=train step=1292
2026-04-11 23:56:09,513 | INFO | train_grpo_train | metrics_logged mode=train step=1293
2026-04-11 23:56:14,641 | INFO | train_grpo_train | metrics_logged mode=train step=1294
2026-04-11 23:56:19,444 | INFO | train_grpo_train | metrics_logged mode=train step=1295
2026-04-11 23:56:24,672 | INFO | train_grpo_train | metrics_logged mode=train step=1296
2026-04-11 23:56:29,515 | INFO | train_grpo_train | metrics_logged mode=train step=1297
2026-04-11 23:56:33,873 | INFO | train_grpo_train | metrics_logged mode=train step=1298
2026-04-11 23:56:38,894 | INFO | train_grpo_train | metrics_logged mode=train step=1299
2026-04-11 23:56:43,328 | INFO | train_grpo_train | metrics_logged mode=train step=1300
2026-04-11 23:57:39,339 | INFO | train_grpo_train | metrics_logged mode=eval step=1300
2026-04-11 23:57:47,205 | INFO | train_grpo_train | metrics_logged mode=train step=1301
2026-04-11 23:57:55,387 | INFO | train_grpo_train | metrics_logged mode=train step=1302
2026-04-11 23:58:01,018 | INFO | train_grpo_train | metrics_logged mode=train step=1303
2026-04-11 23:58:08,377 | INFO | train_grpo_train | metrics_logged mode=train step=1304
2026-04-11 23:58:14,401 | INFO | train_grpo_train | metrics_logged mode=train step=1305
2026-04-11 23:58:19,329 | INFO | train_grpo_train | metrics_logged mode=train step=1306
2026-04-11 23:58:24,354 | INFO | train_grpo_train | metrics_logged mode=train step=1307
2026-04-11 23:58:28,852 | INFO | train_grpo_train | metrics_logged mode=train step=1308
2026-04-11 23:58:32,921 | INFO | train_grpo_train | metrics_logged mode=train step=1309
2026-04-11 23:58:37,393 | INFO | train_grpo_train | metrics_logged mode=train step=1310
2026-04-11 23:58:42,655 | INFO | train_grpo_train | metrics_logged mode=train step=1311
2026-04-11 23:58:47,005 | INFO | train_grpo_train | metrics_logged mode=train step=1312
2026-04-11 23:58:52,975 | INFO | train_grpo_train | metrics_logged mode=train step=1313
2026-04-11 23:58:57,792 | INFO | train_grpo_train | metrics_logged mode=train step=1314
2026-04-11 23:59:02,925 | INFO | train_grpo_train | metrics_logged mode=train step=1315
2026-04-11 23:59:07,611 | INFO | train_grpo_train | metrics_logged mode=train step=1316
2026-04-11 23:59:12,325 | INFO | train_grpo_train | metrics_logged mode=train step=1317
2026-04-11 23:59:16,689 | INFO | train_grpo_train | metrics_logged mode=train step=1318
2026-04-11 23:59:23,653 | INFO | train_grpo_train | metrics_logged mode=train step=1319
2026-04-11 23:59:28,182 | INFO | train_grpo_train | metrics_logged mode=train step=1320
2026-04-11 23:59:32,793 | INFO | train_grpo_train | metrics_logged mode=train step=1321
2026-04-11 23:59:37,024 | INFO | train_grpo_train | metrics_logged mode=train step=1322
2026-04-11 23:59:41,602 | INFO | train_grpo_train | metrics_logged mode=train step=1323
2026-04-11 23:59:45,810 | INFO | train_grpo_train | metrics_logged mode=train step=1324
2026-04-11 23:59:50,980 | INFO | train_grpo_train | metrics_logged mode=train step=1325
2026-04-11 23:59:58,042 | INFO | train_grpo_train | metrics_logged mode=train step=1326
2026-04-12 00:00:03,437 | INFO | train_grpo_train | metrics_logged mode=train step=1327
2026-04-12 00:00:08,062 | INFO | train_grpo_train | metrics_logged mode=train step=1328
2026-04-12 00:00:13,070 | INFO | train_grpo_train | metrics_logged mode=train step=1329
2026-04-12 00:00:17,888 | INFO | train_grpo_train | metrics_logged mode=train step=1330
2026-04-12 00:00:23,584 | INFO | train_grpo_train | metrics_logged mode=train step=1331
2026-04-12 00:00:29,472 | INFO | train_grpo_train | metrics_logged mode=train step=1332
2026-04-12 00:00:34,217 | INFO | train_grpo_train | metrics_logged mode=train step=1333
2026-04-12 00:00:39,673 | INFO | train_grpo_train | metrics_logged mode=train step=1334
2026-04-12 00:00:45,545 | INFO | train_grpo_train | metrics_logged mode=train step=1335
2026-04-12 00:00:52,981 | INFO | train_grpo_train | metrics_logged mode=train step=1336
2026-04-12 00:01:00,820 | INFO | train_grpo_train | metrics_logged mode=train step=1337
2026-04-12 00:01:05,390 | INFO | train_grpo_train | metrics_logged mode=train step=1338
2026-04-12 00:01:10,669 | INFO | train_grpo_train | metrics_logged mode=train step=1339
2026-04-12 00:01:15,660 | INFO | train_grpo_train | metrics_logged mode=train step=1340
2026-04-12 00:01:20,368 | INFO | train_grpo_train | metrics_logged mode=train step=1341
2026-04-12 00:01:25,962 | INFO | train_grpo_train | metrics_logged mode=train step=1342
2026-04-12 00:01:30,795 | INFO | train_grpo_train | metrics_logged mode=train step=1343
2026-04-12 00:01:36,322 | INFO | train_grpo_train | metrics_logged mode=train step=1344
2026-04-12 00:01:40,951 | INFO | train_grpo_train | metrics_logged mode=train step=1345
2026-04-12 00:01:46,495 | INFO | train_grpo_train | metrics_logged mode=train step=1346
2026-04-12 00:01:51,730 | INFO | train_grpo_train | metrics_logged mode=train step=1347
2026-04-12 00:01:56,380 | INFO | train_grpo_train | metrics_logged mode=train step=1348
2026-04-12 00:02:01,213 | INFO | train_grpo_train | metrics_logged mode=train step=1349
2026-04-12 00:02:05,826 | INFO | train_grpo_train | metrics_logged mode=train step=1350
2026-04-12 00:03:04,968 | INFO | train_grpo_train | metrics_logged mode=eval step=1350
2026-04-12 00:03:13,228 | INFO | train_grpo_train | metrics_logged mode=train step=1351
2026-04-12 00:03:17,448 | INFO | train_grpo_train | metrics_logged mode=train step=1352
2026-04-12 00:03:22,117 | INFO | train_grpo_train | metrics_logged mode=train step=1353
2026-04-12 00:03:27,418 | INFO | train_grpo_train | metrics_logged mode=train step=1354
2026-04-12 00:03:31,725 | INFO | train_grpo_train | metrics_logged mode=train step=1355
2026-04-12 00:03:35,740 | INFO | train_grpo_train | metrics_logged mode=train step=1356
2026-04-12 00:03:40,117 | INFO | train_grpo_train | metrics_logged mode=train step=1357
2026-04-12 00:03:44,754 | INFO | train_grpo_train | metrics_logged mode=train step=1358
2026-04-12 00:03:49,376 | INFO | train_grpo_train | metrics_logged mode=train step=1359
2026-04-12 00:03:54,712 | INFO | train_grpo_train | metrics_logged mode=train step=1360
2026-04-12 00:03:58,946 | INFO | train_grpo_train | metrics_logged mode=train step=1361
2026-04-12 00:04:03,573 | INFO | train_grpo_train | metrics_logged mode=train step=1362
2026-04-12 00:04:07,816 | INFO | train_grpo_train | metrics_logged mode=train step=1363
2026-04-12 00:04:12,485 | INFO | train_grpo_train | metrics_logged mode=train step=1364
2026-04-12 00:04:17,442 | INFO | train_grpo_train | metrics_logged mode=train step=1365
2026-04-12 00:04:22,295 | INFO | train_grpo_train | metrics_logged mode=train step=1366
2026-04-12 00:04:26,998 | INFO | train_grpo_train | metrics_logged mode=train step=1367
2026-04-12 00:04:33,512 | INFO | train_grpo_train | metrics_logged mode=train step=1368
2026-04-12 00:04:38,814 | INFO | train_grpo_train | metrics_logged mode=train step=1369
2026-04-12 00:04:44,571 | INFO | train_grpo_train | metrics_logged mode=train step=1370
2026-04-12 00:04:49,934 | INFO | train_grpo_train | metrics_logged mode=train step=1371
2026-04-12 00:04:55,631 | INFO | train_grpo_train | metrics_logged mode=train step=1372
2026-04-12 00:05:02,791 | INFO | train_grpo_train | metrics_logged mode=train step=1373
2026-04-12 00:05:07,339 | INFO | train_grpo_train | metrics_logged mode=train step=1374
2026-04-12 00:05:11,568 | INFO | train_grpo_train | metrics_logged mode=train step=1375
2026-04-12 00:05:18,411 | INFO | train_grpo_train | metrics_logged mode=train step=1376
2026-04-12 00:05:23,164 | INFO | train_grpo_train | metrics_logged mode=train step=1377
2026-04-12 00:05:29,234 | INFO | train_grpo_train | metrics_logged mode=train step=1378
2026-04-12 00:05:35,971 | INFO | train_grpo_train | metrics_logged mode=train step=1379
2026-04-12 00:05:40,431 | INFO | train_grpo_train | metrics_logged mode=train step=1380
2026-04-12 00:05:45,515 | INFO | train_grpo_train | metrics_logged mode=train step=1381
2026-04-12 00:05:51,006 | INFO | train_grpo_train | metrics_logged mode=train step=1382
2026-04-12 00:05:55,976 | INFO | train_grpo_train | metrics_logged mode=train step=1383
2026-04-12 00:06:00,642 | INFO | train_grpo_train | metrics_logged mode=train step=1384
2026-04-12 00:06:04,971 | INFO | train_grpo_train | metrics_logged mode=train step=1385
2026-04-12 00:06:09,589 | INFO | train_grpo_train | metrics_logged mode=train step=1386
2026-04-12 00:06:16,288 | INFO | train_grpo_train | metrics_logged mode=train step=1387
2026-04-12 00:06:21,012 | INFO | train_grpo_train | metrics_logged mode=train step=1388
2026-04-12 00:06:28,393 | INFO | train_grpo_train | metrics_logged mode=train step=1389
2026-04-12 00:06:33,070 | INFO | train_grpo_train | metrics_logged mode=train step=1390
2026-04-12 00:06:37,835 | INFO | train_grpo_train | metrics_logged mode=train step=1391
2026-04-12 00:06:42,406 | INFO | train_grpo_train | metrics_logged mode=train step=1392
2026-04-12 00:06:46,912 | INFO | train_grpo_train | metrics_logged mode=train step=1393
2026-04-12 00:06:51,704 | INFO | train_grpo_train | metrics_logged mode=train step=1394
2026-04-12 00:06:56,346 | INFO | train_grpo_train | metrics_logged mode=train step=1395
2026-04-12 00:07:04,286 | INFO | train_grpo_train | metrics_logged mode=train step=1396
2026-04-12 00:07:08,945 | INFO | train_grpo_train | metrics_logged mode=train step=1397
2026-04-12 00:07:13,486 | INFO | train_grpo_train | metrics_logged mode=train step=1398
2026-04-12 00:07:18,023 | INFO | train_grpo_train | metrics_logged mode=train step=1399
2026-04-12 00:07:23,715 | INFO | train_grpo_train | metrics_logged mode=train step=1400
2026-04-12 00:08:18,842 | INFO | train_grpo_train | metrics_logged mode=eval step=1400
2026-04-12 00:08:25,828 | INFO | train_grpo_train | metrics_logged mode=train step=1401
2026-04-12 00:08:31,677 | INFO | train_grpo_train | metrics_logged mode=train step=1402
2026-04-12 00:08:37,927 | INFO | train_grpo_train | metrics_logged mode=train step=1403
2026-04-12 00:08:42,836 | INFO | train_grpo_train | metrics_logged mode=train step=1404
2026-04-12 00:08:47,499 | INFO | train_grpo_train | metrics_logged mode=train step=1405
2026-04-12 00:08:52,060 | INFO | train_grpo_train | metrics_logged mode=train step=1406
2026-04-12 00:08:57,203 | INFO | train_grpo_train | metrics_logged mode=train step=1407
2026-04-12 00:09:01,485 | INFO | train_grpo_train | metrics_logged mode=train step=1408
2026-04-12 00:09:06,010 | INFO | train_grpo_train | metrics_logged mode=train step=1409
2026-04-12 00:09:10,756 | INFO | train_grpo_train | metrics_logged mode=train step=1410
2026-04-12 00:09:15,420 | INFO | train_grpo_train | metrics_logged mode=train step=1411
2026-04-12 00:09:20,753 | INFO | train_grpo_train | metrics_logged mode=train step=1412
2026-04-12 00:09:26,350 | INFO | train_grpo_train | metrics_logged mode=train step=1413
2026-04-12 00:09:30,905 | INFO | train_grpo_train | metrics_logged mode=train step=1414
2026-04-12 00:09:35,217 | INFO | train_grpo_train | metrics_logged mode=train step=1415
2026-04-12 00:09:41,207 | INFO | train_grpo_train | metrics_logged mode=train step=1416
2026-04-12 00:09:45,857 | INFO | train_grpo_train | metrics_logged mode=train step=1417
2026-04-12 00:09:50,789 | INFO | train_grpo_train | metrics_logged mode=train step=1418
2026-04-12 00:09:54,957 | INFO | train_grpo_train | metrics_logged mode=train step=1419
2026-04-12 00:10:00,230 | INFO | train_grpo_train | metrics_logged mode=train step=1420
2026-04-12 00:10:04,762 | INFO | train_grpo_train | metrics_logged mode=train step=1421
2026-04-12 00:10:09,216 | INFO | train_grpo_train | metrics_logged mode=train step=1422
2026-04-12 00:10:13,603 | INFO | train_grpo_train | metrics_logged mode=train step=1423
2026-04-12 00:10:18,400 | INFO | train_grpo_train | metrics_logged mode=train step=1424
2026-04-12 00:10:26,540 | INFO | train_grpo_train | metrics_logged mode=train step=1425
2026-04-12 00:10:31,233 | INFO | train_grpo_train | metrics_logged mode=train step=1426
2026-04-12 00:10:36,230 | INFO | train_grpo_train | metrics_logged mode=train step=1427
2026-04-12 00:10:43,329 | INFO | train_grpo_train | metrics_logged mode=train step=1428
2026-04-12 00:10:48,654 | INFO | train_grpo_train | metrics_logged mode=train step=1429
2026-04-12 00:10:53,253 | INFO | train_grpo_train | metrics_logged mode=train step=1430
2026-04-12 00:10:58,295 | INFO | train_grpo_train | metrics_logged mode=train step=1431
2026-04-12 00:11:03,550 | INFO | train_grpo_train | metrics_logged mode=train step=1432
2026-04-12 00:11:08,309 | INFO | train_grpo_train | metrics_logged mode=train step=1433
2026-04-12 00:11:13,006 | INFO | train_grpo_train | metrics_logged mode=train step=1434
2026-04-12 00:11:17,504 | INFO | train_grpo_train | metrics_logged mode=train step=1435
2026-04-12 00:11:22,183 | INFO | train_grpo_train | metrics_logged mode=train step=1436
2026-04-12 00:11:26,881 | INFO | train_grpo_train | metrics_logged mode=train step=1437
2026-04-12 00:11:31,472 | INFO | train_grpo_train | metrics_logged mode=train step=1438
2026-04-12 00:11:36,153 | INFO | train_grpo_train | metrics_logged mode=train step=1439
2026-04-12 00:11:42,483 | INFO | train_grpo_train | metrics_logged mode=train step=1440
2026-04-12 00:11:46,993 | INFO | train_grpo_train | metrics_logged mode=train step=1441
2026-04-12 00:11:53,009 | INFO | train_grpo_train | metrics_logged mode=train step=1442
2026-04-12 00:12:00,303 | INFO | train_grpo_train | metrics_logged mode=train step=1443
2026-04-12 00:12:05,910 | INFO | train_grpo_train | metrics_logged mode=train step=1444
2026-04-12 00:12:12,079 | INFO | train_grpo_train | metrics_logged mode=train step=1445
2026-04-12 00:12:16,785 | INFO | train_grpo_train | metrics_logged mode=train step=1446
2026-04-12 00:12:21,062 | INFO | train_grpo_train | metrics_logged mode=train step=1447
2026-04-12 00:12:26,298 | INFO | train_grpo_train | metrics_logged mode=train step=1448
2026-04-12 00:12:32,214 | INFO | train_grpo_train | metrics_logged mode=train step=1449
2026-04-12 00:12:38,380 | INFO | train_grpo_train | metrics_logged mode=train step=1450
2026-04-12 00:13:33,718 | INFO | train_grpo_train | metrics_logged mode=eval step=1450
2026-04-12 00:13:41,035 | INFO | train_grpo_train | metrics_logged mode=train step=1451
2026-04-12 00:13:46,350 | INFO | train_grpo_train | metrics_logged mode=train step=1452
2026-04-12 00:13:51,031 | INFO | train_grpo_train | metrics_logged mode=train step=1453
2026-04-12 00:13:55,673 | INFO | train_grpo_train | metrics_logged mode=train step=1454
2026-04-12 00:14:00,030 | INFO | train_grpo_train | metrics_logged mode=train step=1455
2026-04-12 00:14:07,209 | INFO | train_grpo_train | metrics_logged mode=train step=1456
2026-04-12 00:14:12,385 | INFO | train_grpo_train | metrics_logged mode=train step=1457
2026-04-12 00:14:17,423 | INFO | train_grpo_train | metrics_logged mode=train step=1458
2026-04-12 00:14:25,062 | INFO | train_grpo_train | metrics_logged mode=train step=1459
2026-04-12 00:14:29,807 | INFO | train_grpo_train | metrics_logged mode=train step=1460
2026-04-12 00:14:34,584 | INFO | train_grpo_train | metrics_logged mode=train step=1461
2026-04-12 00:14:39,292 | INFO | train_grpo_train | metrics_logged mode=train step=1462
2026-04-12 00:14:43,916 | INFO | train_grpo_train | metrics_logged mode=train step=1463
2026-04-12 00:14:48,549 | INFO | train_grpo_train | metrics_logged mode=train step=1464
2026-04-12 00:14:53,290 | INFO | train_grpo_train | metrics_logged mode=train step=1465
2026-04-12 00:14:57,924 | INFO | train_grpo_train | metrics_logged mode=train step=1466
2026-04-12 00:15:04,606 | INFO | train_grpo_train | metrics_logged mode=train step=1467
2026-04-12 00:15:09,319 | INFO | train_grpo_train | metrics_logged mode=train step=1468
2026-04-12 00:15:14,333 | INFO | train_grpo_train | metrics_logged mode=train step=1469
2026-04-12 00:15:19,098 | INFO | train_grpo_train | metrics_logged mode=train step=1470
2026-04-12 00:15:23,652 | INFO | train_grpo_train | metrics_logged mode=train step=1471
2026-04-12 00:15:29,458 | INFO | train_grpo_train | metrics_logged mode=train step=1472
2026-04-12 00:15:35,618 | INFO | train_grpo_train | metrics_logged mode=train step=1473
2026-04-12 00:15:41,415 | INFO | train_grpo_train | metrics_logged mode=train step=1474
2026-04-12 00:15:46,502 | INFO | train_grpo_train | metrics_logged mode=train step=1475
2026-04-12 00:15:51,796 | INFO | train_grpo_train | metrics_logged mode=train step=1476
2026-04-12 00:15:56,493 | INFO | train_grpo_train | metrics_logged mode=train step=1477
2026-04-12 00:16:00,707 | INFO | train_grpo_train | metrics_logged mode=train step=1478
2026-04-12 00:16:05,368 | INFO | train_grpo_train | metrics_logged mode=train step=1479
2026-04-12 00:16:09,681 | INFO | train_grpo_train | metrics_logged mode=train step=1480
2026-04-12 00:16:17,404 | INFO | train_grpo_train | metrics_logged mode=train step=1481
2026-04-12 00:16:24,506 | INFO | train_grpo_train | metrics_logged mode=train step=1482
2026-04-12 00:16:30,425 | INFO | train_grpo_train | metrics_logged mode=train step=1483
2026-04-12 00:16:34,990 | INFO | train_grpo_train | metrics_logged mode=train step=1484
2026-04-12 00:16:40,342 | INFO | train_grpo_train | metrics_logged mode=train step=1485
2026-04-12 00:16:45,547 | INFO | train_grpo_train | metrics_logged mode=train step=1486
2026-04-12 00:16:50,666 | INFO | train_grpo_train | metrics_logged mode=train step=1487
2026-04-12 00:16:55,876 | INFO | train_grpo_train | metrics_logged mode=train step=1488
2026-04-12 00:17:01,241 | INFO | train_grpo_train | metrics_logged mode=train step=1489
2026-04-12 00:17:07,364 | INFO | train_grpo_train | metrics_logged mode=train step=1490
2026-04-12 00:17:12,282 | INFO | train_grpo_train | metrics_logged mode=train step=1491
2026-04-12 00:17:16,912 | INFO | train_grpo_train | metrics_logged mode=train step=1492
2026-04-12 00:17:23,793 | INFO | train_grpo_train | metrics_logged mode=train step=1493
2026-04-12 00:17:28,824 | INFO | train_grpo_train | metrics_logged mode=train step=1494
2026-04-12 00:17:33,580 | INFO | train_grpo_train | metrics_logged mode=train step=1495
2026-04-12 00:17:38,432 | INFO | train_grpo_train | metrics_logged mode=train step=1496
2026-04-12 00:17:43,395 | INFO | train_grpo_train | metrics_logged mode=train step=1497
2026-04-12 00:17:47,695 | INFO | train_grpo_train | metrics_logged mode=train step=1498
2026-04-12 00:17:53,134 | INFO | train_grpo_train | metrics_logged mode=train step=1499
2026-04-12 00:17:57,999 | INFO | train_grpo_train | metrics_logged mode=train step=1500
2026-04-12 00:18:57,302 | INFO | train_grpo_train | metrics_logged mode=eval step=1500
2026-04-12 00:19:04,123 | INFO | train_grpo_train | metrics_logged mode=train step=1501
2026-04-12 00:19:09,429 | INFO | train_grpo_train | metrics_logged mode=train step=1502
2026-04-12 00:19:14,304 | INFO | train_grpo_train | metrics_logged mode=train step=1503
2026-04-12 00:19:23,374 | INFO | train_grpo_train | metrics_logged mode=train step=1504
2026-04-12 00:19:30,600 | INFO | train_grpo_train | metrics_logged mode=train step=1505
2026-04-12 00:19:35,183 | INFO | train_grpo_train | metrics_logged mode=train step=1506
2026-04-12 00:19:41,780 | INFO | train_grpo_train | metrics_logged mode=train step=1507
2026-04-12 00:19:48,094 | INFO | train_grpo_train | metrics_logged mode=train step=1508
2026-04-12 00:19:53,318 | INFO | train_grpo_train | metrics_logged mode=train step=1509
2026-04-12 00:19:58,139 | INFO | train_grpo_train | metrics_logged mode=train step=1510
2026-04-12 00:20:07,597 | INFO | train_grpo_train | metrics_logged mode=train step=1511
2026-04-12 00:20:17,625 | INFO | train_grpo_train | metrics_logged mode=train step=1512
2026-04-12 00:20:22,254 | INFO | train_grpo_train | metrics_logged mode=train step=1513
2026-04-12 00:20:28,984 | INFO | train_grpo_train | metrics_logged mode=train step=1514
2026-04-12 00:20:33,671 | INFO | train_grpo_train | metrics_logged mode=train step=1515
2026-04-12 00:20:38,466 | INFO | train_grpo_train | metrics_logged mode=train step=1516
2026-04-12 00:20:42,956 | INFO | train_grpo_train | metrics_logged mode=train step=1517
2026-04-12 00:20:47,557 | INFO | train_grpo_train | metrics_logged mode=train step=1518
2026-04-12 00:20:55,127 | INFO | train_grpo_train | metrics_logged mode=train step=1519
2026-04-12 00:21:00,070 | INFO | train_grpo_train | metrics_logged mode=train step=1520
2026-04-12 00:21:04,881 | INFO | train_grpo_train | metrics_logged mode=train step=1521
2026-04-12 00:21:09,634 | INFO | train_grpo_train | metrics_logged mode=train step=1522
2026-04-12 00:21:14,037 | INFO | train_grpo_train | metrics_logged mode=train step=1523
2026-04-12 00:21:19,242 | INFO | train_grpo_train | metrics_logged mode=train step=1524
2026-04-12 00:21:24,148 | INFO | train_grpo_train | metrics_logged mode=train step=1525
2026-04-12 00:21:29,196 | INFO | train_grpo_train | metrics_logged mode=train step=1526
2026-04-12 00:21:34,968 | INFO | train_grpo_train | metrics_logged mode=train step=1527
2026-04-12 00:21:39,992 | INFO | train_grpo_train | metrics_logged mode=train step=1528
2026-04-12 00:21:44,227 | INFO | train_grpo_train | metrics_logged mode=train step=1529
2026-04-12 00:21:48,965 | INFO | train_grpo_train | metrics_logged mode=train step=1530
2026-04-12 00:21:54,118 | INFO | train_grpo_train | metrics_logged mode=train step=1531
2026-04-12 00:21:59,927 | INFO | train_grpo_train | metrics_logged mode=train step=1532
2026-04-12 00:22:04,343 | INFO | train_grpo_train | metrics_logged mode=train step=1533
2026-04-12 00:22:13,858 | INFO | train_grpo_train | metrics_logged mode=train step=1534
2026-04-12 00:22:19,911 | INFO | train_grpo_train | metrics_logged mode=train step=1535
2026-04-12 00:22:24,637 | INFO | train_grpo_train | metrics_logged mode=train step=1536
2026-04-12 00:22:28,885 | INFO | train_grpo_train | metrics_logged mode=train step=1537
2026-04-12 00:22:33,548 | INFO | train_grpo_train | metrics_logged mode=train step=1538
2026-04-12 00:22:38,476 | INFO | train_grpo_train | metrics_logged mode=train step=1539
2026-04-12 00:22:42,898 | INFO | train_grpo_train | metrics_logged mode=train step=1540
2026-04-12 00:22:47,555 | INFO | train_grpo_train | metrics_logged mode=train step=1541
2026-04-12 00:22:53,039 | INFO | train_grpo_train | metrics_logged mode=train step=1542
2026-04-12 00:22:58,190 | INFO | train_grpo_train | metrics_logged mode=train step=1543
2026-04-12 00:23:02,988 | INFO | train_grpo_train | metrics_logged mode=train step=1544
2026-04-12 00:23:07,690 | INFO | train_grpo_train | metrics_logged mode=train step=1545
2026-04-12 00:23:13,218 | INFO | train_grpo_train | metrics_logged mode=train step=1546
2026-04-12 00:23:17,933 | INFO | train_grpo_train | metrics_logged mode=train step=1547
2026-04-12 00:23:22,341 | INFO | train_grpo_train | metrics_logged mode=train step=1548
2026-04-12 00:23:26,561 | INFO | train_grpo_train | metrics_logged mode=train step=1549
2026-04-12 00:23:31,213 | INFO | train_grpo_train | metrics_logged mode=train step=1550
2026-04-12 00:24:30,693 | INFO | train_grpo_train | metrics_logged mode=eval step=1550
2026-04-12 00:24:39,113 | INFO | train_grpo_train | metrics_logged mode=train step=1551
2026-04-12 00:24:45,876 | INFO | train_grpo_train | metrics_logged mode=train step=1552
2026-04-12 00:24:50,864 | INFO | train_grpo_train | metrics_logged mode=train step=1553
2026-04-12 00:24:58,094 | INFO | train_grpo_train | metrics_logged mode=train step=1554
2026-04-12 00:25:04,452 | INFO | train_grpo_train | metrics_logged mode=train step=1555
2026-04-12 00:25:09,575 | INFO | train_grpo_train | metrics_logged mode=train step=1556
2026-04-12 00:25:14,145 | INFO | train_grpo_train | metrics_logged mode=train step=1557
2026-04-12 00:25:18,382 | INFO | train_grpo_train | metrics_logged mode=train step=1558
2026-04-12 00:25:23,774 | INFO | train_grpo_train | metrics_logged mode=train step=1559
2026-04-12 00:25:29,734 | INFO | train_grpo_train | metrics_logged mode=train step=1560
2026-04-12 00:25:35,623 | INFO | train_grpo_train | metrics_logged mode=train step=1561
2026-04-12 00:25:40,414 | INFO | train_grpo_train | metrics_logged mode=train step=1562
2026-04-12 00:25:46,033 | INFO | train_grpo_train | metrics_logged mode=train step=1563
2026-04-12 00:25:51,606 | INFO | train_grpo_train | metrics_logged mode=train step=1564
2026-04-12 00:25:56,364 | INFO | train_grpo_train | metrics_logged mode=train step=1565
2026-04-12 00:26:01,091 | INFO | train_grpo_train | metrics_logged mode=train step=1566
2026-04-12 00:26:05,754 | INFO | train_grpo_train | metrics_logged mode=train step=1567
2026-04-12 00:26:10,831 | INFO | train_grpo_train | metrics_logged mode=train step=1568
2026-04-12 00:26:15,581 | INFO | train_grpo_train | metrics_logged mode=train step=1569
2026-04-12 00:26:20,503 | INFO | train_grpo_train | metrics_logged mode=train step=1570
2026-04-12 00:26:26,707 | INFO | train_grpo_train | metrics_logged mode=train step=1571
2026-04-12 00:26:36,563 | INFO | train_grpo_train | metrics_logged mode=train step=1572
2026-04-12 00:26:41,344 | INFO | train_grpo_train | metrics_logged mode=train step=1573
2026-04-12 00:26:46,549 | INFO | train_grpo_train | metrics_logged mode=train step=1574
2026-04-12 00:26:51,756 | INFO | train_grpo_train | metrics_logged mode=train step=1575
2026-04-12 00:26:57,087 | INFO | train_grpo_train | metrics_logged mode=train step=1576
2026-04-12 00:27:02,514 | INFO | train_grpo_train | metrics_logged mode=train step=1577
2026-04-12 00:27:09,188 | INFO | train_grpo_train | metrics_logged mode=train step=1578
2026-04-12 00:27:14,582 | INFO | train_grpo_train | metrics_logged mode=train step=1579
2026-04-12 00:27:21,540 | INFO | train_grpo_train | metrics_logged mode=train step=1580
2026-04-12 00:27:28,492 | INFO | train_grpo_train | metrics_logged mode=train step=1581
2026-04-12 00:27:33,780 | INFO | train_grpo_train | metrics_logged mode=train step=1582
2026-04-12 00:27:38,567 | INFO | train_grpo_train | metrics_logged mode=train step=1583
2026-04-12 00:27:43,288 | INFO | train_grpo_train | metrics_logged mode=train step=1584
2026-04-12 00:27:48,840 | INFO | train_grpo_train | metrics_logged mode=train step=1585
2026-04-12 00:27:53,671 | INFO | train_grpo_train | metrics_logged mode=train step=1586
2026-04-12 00:27:58,402 | INFO | train_grpo_train | metrics_logged mode=train step=1587
2026-04-12 00:28:03,557 | INFO | train_grpo_train | metrics_logged mode=train step=1588
2026-04-12 00:28:08,224 | INFO | train_grpo_train | metrics_logged mode=train step=1589
2026-04-12 00:28:15,420 | INFO | train_grpo_train | metrics_logged mode=train step=1590
2026-04-12 00:28:20,008 | INFO | train_grpo_train | metrics_logged mode=train step=1591
2026-04-12 00:28:24,762 | INFO | train_grpo_train | metrics_logged mode=train step=1592
2026-04-12 00:28:29,739 | INFO | train_grpo_train | metrics_logged mode=train step=1593
2026-04-12 00:28:36,553 | INFO | train_grpo_train | metrics_logged mode=train step=1594
2026-04-12 00:28:42,793 | INFO | train_grpo_train | metrics_logged mode=train step=1595
2026-04-12 00:28:47,642 | INFO | train_grpo_train | metrics_logged mode=train step=1596
2026-04-12 00:28:52,862 | INFO | train_grpo_train | metrics_logged mode=train step=1597
2026-04-12 00:28:57,570 | INFO | train_grpo_train | metrics_logged mode=train step=1598
2026-04-12 00:29:01,981 | INFO | train_grpo_train | metrics_logged mode=train step=1599
2026-04-12 00:29:06,496 | INFO | train_grpo_train | metrics_logged mode=train step=1600
2026-04-12 00:30:12,823 | INFO | train_grpo_train | metrics_logged mode=eval step=1600
2026-04-12 00:30:21,365 | INFO | train_grpo_train | metrics_logged mode=train step=1601
2026-04-12 00:30:27,272 | INFO | train_grpo_train | metrics_logged mode=train step=1602
2026-04-12 00:30:33,210 | INFO | train_grpo_train | metrics_logged mode=train step=1603
2026-04-12 00:30:39,145 | INFO | train_grpo_train | metrics_logged mode=train step=1604
2026-04-12 00:30:44,311 | INFO | train_grpo_train | metrics_logged mode=train step=1605
2026-04-12 00:30:50,114 | INFO | train_grpo_train | metrics_logged mode=train step=1606
2026-04-12 00:30:56,158 | INFO | train_grpo_train | metrics_logged mode=train step=1607
2026-04-12 00:31:02,799 | INFO | train_grpo_train | metrics_logged mode=train step=1608
2026-04-12 00:31:07,334 | INFO | train_grpo_train | metrics_logged mode=train step=1609
2026-04-12 00:31:11,893 | INFO | train_grpo_train | metrics_logged mode=train step=1610
2026-04-12 00:31:17,532 | INFO | train_grpo_train | metrics_logged mode=train step=1611
2026-04-12 00:31:22,031 | INFO | train_grpo_train | metrics_logged mode=train step=1612
2026-04-12 00:31:27,082 | INFO | train_grpo_train | metrics_logged mode=train step=1613
2026-04-12 00:31:33,170 | INFO | train_grpo_train | metrics_logged mode=train step=1614
2026-04-12 00:31:38,016 | INFO | train_grpo_train | metrics_logged mode=train step=1615
2026-04-12 00:31:42,813 | INFO | train_grpo_train | metrics_logged mode=train step=1616
2026-04-12 00:31:53,769 | INFO | train_grpo_train | metrics_logged mode=train step=1617
2026-04-12 00:32:02,728 | INFO | train_grpo_train | metrics_logged mode=train step=1618
2026-04-12 00:32:07,265 | INFO | train_grpo_train | metrics_logged mode=train step=1619
2026-04-12 00:32:12,214 | INFO | train_grpo_train | metrics_logged mode=train step=1620
2026-04-12 00:32:17,046 | INFO | train_grpo_train | metrics_logged mode=train step=1621
2026-04-12 00:32:21,989 | INFO | train_grpo_train | metrics_logged mode=train step=1622
2026-04-12 00:32:26,775 | INFO | train_grpo_train | metrics_logged mode=train step=1623
2026-04-12 00:32:35,637 | INFO | train_grpo_train | metrics_logged mode=train step=1624
2026-04-12 00:32:41,819 | INFO | train_grpo_train | metrics_logged mode=train step=1625
2026-04-12 00:32:46,905 | INFO | train_grpo_train | metrics_logged mode=train step=1626
2026-04-12 00:32:51,561 | INFO | train_grpo_train | metrics_logged mode=train step=1627
2026-04-12 00:32:55,797 | INFO | train_grpo_train | metrics_logged mode=train step=1628
2026-04-12 00:33:03,902 | INFO | train_grpo_train | metrics_logged mode=train step=1629
2026-04-12 00:33:12,786 | INFO | train_grpo_train | metrics_logged mode=train step=1630
2026-04-12 00:33:18,042 | INFO | train_grpo_train | metrics_logged mode=train step=1631
2026-04-12 00:33:22,743 | INFO | train_grpo_train | metrics_logged mode=train step=1632
2026-04-12 00:33:26,782 | INFO | train_grpo_train | metrics_logged mode=train step=1633
2026-04-12 00:33:31,901 | INFO | train_grpo_train | metrics_logged mode=train step=1634
2026-04-12 00:33:37,598 | INFO | train_grpo_train | metrics_logged mode=train step=1635
2026-04-12 00:33:42,635 | INFO | train_grpo_train | metrics_logged mode=train step=1636
2026-04-12 00:33:49,029 | INFO | train_grpo_train | metrics_logged mode=train step=1637
2026-04-12 00:33:53,981 | INFO | train_grpo_train | metrics_logged mode=train step=1638
2026-04-12 00:33:58,454 | INFO | train_grpo_train | metrics_logged mode=train step=1639
2026-04-12 00:34:03,068 | INFO | train_grpo_train | metrics_logged mode=train step=1640
2026-04-12 00:34:07,823 | INFO | train_grpo_train | metrics_logged mode=train step=1641
2026-04-12 00:34:12,210 | INFO | train_grpo_train | metrics_logged mode=train step=1642
2026-04-12 00:34:18,750 | INFO | train_grpo_train | metrics_logged mode=train step=1643
2026-04-12 00:34:24,641 | INFO | train_grpo_train | metrics_logged mode=train step=1644
2026-04-12 00:34:29,372 | INFO | train_grpo_train | metrics_logged mode=train step=1645
2026-04-12 00:34:33,720 | INFO | train_grpo_train | metrics_logged mode=train step=1646
2026-04-12 00:34:38,957 | INFO | train_grpo_train | metrics_logged mode=train step=1647
2026-04-12 00:34:43,982 | INFO | train_grpo_train | metrics_logged mode=train step=1648
2026-04-12 00:34:48,078 | INFO | train_grpo_train | metrics_logged mode=train step=1649
2026-04-12 00:34:52,587 | INFO | train_grpo_train | metrics_logged mode=train step=1650
2026-04-12 00:36:11,915 | INFO | train_grpo_train | metrics_logged mode=eval step=1650
2026-04-12 00:36:18,953 | INFO | train_grpo_train | metrics_logged mode=train step=1651
2026-04-12 00:36:23,827 | INFO | train_grpo_train | metrics_logged mode=train step=1652
2026-04-12 00:36:34,429 | INFO | train_grpo_train | metrics_logged mode=train step=1653
2026-04-12 00:36:39,336 | INFO | train_grpo_train | metrics_logged mode=train step=1654
2026-04-12 00:36:44,220 | INFO | train_grpo_train | metrics_logged mode=train step=1655
2026-04-12 00:36:54,226 | INFO | train_grpo_train | metrics_logged mode=train step=1656
2026-04-12 00:36:59,038 | INFO | train_grpo_train | metrics_logged mode=train step=1657
2026-04-12 00:37:03,875 | INFO | train_grpo_train | metrics_logged mode=train step=1658
2026-04-12 00:37:08,691 | INFO | train_grpo_train | metrics_logged mode=train step=1659
2026-04-12 00:37:14,304 | INFO | train_grpo_train | metrics_logged mode=train step=1660
2026-04-12 00:37:19,117 | INFO | train_grpo_train | metrics_logged mode=train step=1661
2026-04-12 00:37:23,818 | INFO | train_grpo_train | metrics_logged mode=train step=1662
2026-04-12 00:37:28,774 | INFO | train_grpo_train | metrics_logged mode=train step=1663
2026-04-12 00:37:34,070 | INFO | train_grpo_train | metrics_logged mode=train step=1664
2026-04-12 00:37:42,436 | INFO | train_grpo_train | metrics_logged mode=train step=1665
2026-04-12 00:37:50,127 | INFO | train_grpo_train | metrics_logged mode=train step=1666
2026-04-12 00:37:55,200 | INFO | train_grpo_train | metrics_logged mode=train step=1667
2026-04-12 00:38:00,486 | INFO | train_grpo_train | metrics_logged mode=train step=1668
2026-04-12 00:38:05,155 | INFO | train_grpo_train | metrics_logged mode=train step=1669
2026-04-12 00:38:09,920 | INFO | train_grpo_train | metrics_logged mode=train step=1670
2026-04-12 00:38:14,972 | INFO | train_grpo_train | metrics_logged mode=train step=1671
2026-04-12 00:38:19,299 | INFO | train_grpo_train | metrics_logged mode=train step=1672
2026-04-12 00:38:24,588 | INFO | train_grpo_train | metrics_logged mode=train step=1673
2026-04-12 00:38:29,109 | INFO | train_grpo_train | metrics_logged mode=train step=1674
2026-04-12 00:38:33,974 | INFO | train_grpo_train | metrics_logged mode=train step=1675
2026-04-12 00:38:39,129 | INFO | train_grpo_train | metrics_logged mode=train step=1676
2026-04-12 00:38:43,677 | INFO | train_grpo_train | metrics_logged mode=train step=1677
2026-04-12 00:38:48,767 | INFO | train_grpo_train | metrics_logged mode=train step=1678
2026-04-12 00:38:55,369 | INFO | train_grpo_train | metrics_logged mode=train step=1679
2026-04-12 00:39:04,775 | INFO | train_grpo_train | metrics_logged mode=train step=1680
2026-04-12 00:39:08,830 | INFO | train_grpo_train | metrics_logged mode=train step=1681
2026-04-12 00:39:13,415 | INFO | train_grpo_train | metrics_logged mode=train step=1682
2026-04-12 00:39:17,816 | INFO | train_grpo_train | metrics_logged mode=train step=1683
2026-04-12 00:39:23,628 | INFO | train_grpo_train | metrics_logged mode=train step=1684
2026-04-12 00:39:28,182 | INFO | train_grpo_train | metrics_logged mode=train step=1685
2026-04-12 00:39:32,757 | INFO | train_grpo_train | metrics_logged mode=train step=1686
2026-04-12 00:39:36,832 | INFO | train_grpo_train | metrics_logged mode=train step=1687
2026-04-12 00:39:40,989 | INFO | train_grpo_train | metrics_logged mode=train step=1688
2026-04-12 00:39:45,297 | INFO | train_grpo_train | metrics_logged mode=train step=1689
2026-04-12 00:39:49,451 | INFO | train_grpo_train | metrics_logged mode=train step=1690
2026-04-12 00:39:54,873 | INFO | train_grpo_train | metrics_logged mode=train step=1691
2026-04-12 00:40:00,382 | INFO | train_grpo_train | metrics_logged mode=train step=1692
2026-04-12 00:40:04,901 | INFO | train_grpo_train | metrics_logged mode=train step=1693
2026-04-12 00:40:10,720 | INFO | train_grpo_train | metrics_logged mode=train step=1694
2026-04-12 00:40:15,163 | INFO | train_grpo_train | metrics_logged mode=train step=1695
2026-04-12 00:40:20,213 | INFO | train_grpo_train | metrics_logged mode=train step=1696
2026-04-12 00:40:24,826 | INFO | train_grpo_train | metrics_logged mode=train step=1697
2026-04-12 00:40:34,369 | INFO | train_grpo_train | metrics_logged mode=train step=1698
2026-04-12 00:40:38,984 | INFO | train_grpo_train | metrics_logged mode=train step=1699
2026-04-12 00:40:44,699 | INFO | train_grpo_train | metrics_logged mode=train step=1700
2026-04-12 00:41:57,403 | INFO | train_grpo_train | metrics_logged mode=eval step=1700
2026-04-12 00:42:06,476 | INFO | train_grpo_train | metrics_logged mode=train step=1701
2026-04-12 00:42:11,625 | INFO | train_grpo_train | metrics_logged mode=train step=1702
2026-04-12 00:42:19,642 | INFO | train_grpo_train | metrics_logged mode=train step=1703
2026-04-12 00:42:25,317 | INFO | train_grpo_train | metrics_logged mode=train step=1704
2026-04-12 00:42:29,985 | INFO | train_grpo_train | metrics_logged mode=train step=1705
2026-04-12 00:42:37,488 | INFO | train_grpo_train | metrics_logged mode=train step=1706
2026-04-12 00:42:41,896 | INFO | train_grpo_train | metrics_logged mode=train step=1707
2026-04-12 00:42:46,545 | INFO | train_grpo_train | metrics_logged mode=train step=1708
2026-04-12 00:42:51,314 | INFO | train_grpo_train | metrics_logged mode=train step=1709
2026-04-12 00:42:56,306 | INFO | train_grpo_train | metrics_logged mode=train step=1710
2026-04-12 00:43:00,756 | INFO | train_grpo_train | metrics_logged mode=train step=1711
2026-04-12 00:43:04,895 | INFO | train_grpo_train | metrics_logged mode=train step=1712
2026-04-12 00:43:09,513 | INFO | train_grpo_train | metrics_logged mode=train step=1713
2026-04-12 00:43:13,830 | INFO | train_grpo_train | metrics_logged mode=train step=1714
2026-04-12 00:43:18,285 | INFO | train_grpo_train | metrics_logged mode=train step=1715
2026-04-12 00:43:22,945 | INFO | train_grpo_train | metrics_logged mode=train step=1716
2026-04-12 00:43:32,147 | INFO | train_grpo_train | metrics_logged mode=train step=1717
2026-04-12 00:43:36,800 | INFO | train_grpo_train | metrics_logged mode=train step=1718
2026-04-12 00:43:44,458 | INFO | train_grpo_train | metrics_logged mode=train step=1719
2026-04-12 00:43:53,491 | INFO | train_grpo_train | metrics_logged mode=train step=1720
2026-04-12 00:43:58,373 | INFO | train_grpo_train | metrics_logged mode=train step=1721
2026-04-12 00:44:06,359 | INFO | train_grpo_train | metrics_logged mode=train step=1722
2026-04-12 00:44:10,769 | INFO | train_grpo_train | metrics_logged mode=train step=1723
2026-04-12 00:44:16,343 | INFO | train_grpo_train | metrics_logged mode=train step=1724
2026-04-12 00:44:20,951 | INFO | train_grpo_train | metrics_logged mode=train step=1725
2026-04-12 00:44:26,467 | INFO | train_grpo_train | metrics_logged mode=train step=1726
2026-04-12 00:44:31,217 | INFO | train_grpo_train | metrics_logged mode=train step=1727
2026-04-12 00:44:36,252 | INFO | train_grpo_train | metrics_logged mode=train step=1728
2026-04-12 00:44:43,412 | INFO | train_grpo_train | metrics_logged mode=train step=1729
2026-04-12 00:44:50,542 | INFO | train_grpo_train | metrics_logged mode=train step=1730
2026-04-12 00:44:56,820 | INFO | train_grpo_train | metrics_logged mode=train step=1731
2026-04-12 00:45:01,705 | INFO | train_grpo_train | metrics_logged mode=train step=1732
2026-04-12 00:45:06,160 | INFO | train_grpo_train | metrics_logged mode=train step=1733
2026-04-12 00:45:10,572 | INFO | train_grpo_train | metrics_logged mode=train step=1734
2026-04-12 00:45:14,992 | INFO | train_grpo_train | metrics_logged mode=train step=1735
2026-04-12 00:45:19,576 | INFO | train_grpo_train | metrics_logged mode=train step=1736
2026-04-12 00:45:24,899 | INFO | train_grpo_train | metrics_logged mode=train step=1737
2026-04-12 00:45:30,655 | INFO | train_grpo_train | metrics_logged mode=train step=1738
2026-04-12 00:45:35,411 | INFO | train_grpo_train | metrics_logged mode=train step=1739
2026-04-12 00:45:39,681 | INFO | train_grpo_train | metrics_logged mode=train step=1740
2026-04-12 00:45:47,281 | INFO | train_grpo_train | metrics_logged mode=train step=1741
2026-04-12 00:45:52,438 | INFO | train_grpo_train | metrics_logged mode=train step=1742
2026-04-12 00:45:57,560 | INFO | train_grpo_train | metrics_logged mode=train step=1743
2026-04-12 00:46:02,689 | INFO | train_grpo_train | metrics_logged mode=train step=1744
2026-04-12 00:46:07,258 | INFO | train_grpo_train | metrics_logged mode=train step=1745
2026-04-12 00:46:12,601 | INFO | train_grpo_train | metrics_logged mode=train step=1746
2026-04-12 00:46:18,420 | INFO | train_grpo_train | metrics_logged mode=train step=1747
2026-04-12 00:46:23,394 | INFO | train_grpo_train | metrics_logged mode=train step=1748
2026-04-12 00:46:28,325 | INFO | train_grpo_train | metrics_logged mode=train step=1749
2026-04-12 00:46:33,295 | INFO | train_grpo_train | metrics_logged mode=train step=1750
2026-04-12 00:47:39,804 | INFO | train_grpo_train | metrics_logged mode=eval step=1750
2026-04-12 00:47:47,173 | INFO | train_grpo_train | metrics_logged mode=train step=1751
2026-04-12 00:47:52,390 | INFO | train_grpo_train | metrics_logged mode=train step=1752
2026-04-12 00:47:56,928 | INFO | train_grpo_train | metrics_logged mode=train step=1753
2026-04-12 00:48:01,741 | INFO | train_grpo_train | metrics_logged mode=train step=1754
2026-04-12 00:48:07,013 | INFO | train_grpo_train | metrics_logged mode=train step=1755
2026-04-12 00:48:11,214 | INFO | train_grpo_train | metrics_logged mode=train step=1756
2026-04-12 00:48:16,749 | INFO | train_grpo_train | metrics_logged mode=train step=1757
2026-04-12 00:48:21,501 | INFO | train_grpo_train | metrics_logged mode=train step=1758
2026-04-12 00:48:25,733 | INFO | train_grpo_train | metrics_logged mode=train step=1759
2026-04-12 00:48:31,251 | INFO | train_grpo_train | metrics_logged mode=train step=1760
2026-04-12 00:48:35,642 | INFO | train_grpo_train | metrics_logged mode=train step=1761
2026-04-12 00:48:40,453 | INFO | train_grpo_train | metrics_logged mode=train step=1762
2026-04-12 00:48:48,391 | INFO | train_grpo_train | metrics_logged mode=train step=1763
2026-04-12 00:48:52,575 | INFO | train_grpo_train | metrics_logged mode=train step=1764
2026-04-12 00:49:01,433 | INFO | train_grpo_train | metrics_logged mode=train step=1765
2026-04-12 00:49:06,553 | INFO | train_grpo_train | metrics_logged mode=train step=1766
2026-04-12 00:49:11,014 | INFO | train_grpo_train | metrics_logged mode=train step=1767
2026-04-12 00:49:15,442 | INFO | train_grpo_train | metrics_logged mode=train step=1768
2026-04-12 00:49:19,803 | INFO | train_grpo_train | metrics_logged mode=train step=1769
2026-04-12 00:49:24,857 | INFO | train_grpo_train | metrics_logged mode=train step=1770
2026-04-12 00:49:29,520 | INFO | train_grpo_train | metrics_logged mode=train step=1771
2026-04-12 00:49:33,851 | INFO | train_grpo_train | metrics_logged mode=train step=1772
2026-04-12 00:49:40,220 | INFO | train_grpo_train | metrics_logged mode=train step=1773
2026-04-12 00:49:45,441 | INFO | train_grpo_train | metrics_logged mode=train step=1774
2026-04-12 00:49:50,087 | INFO | train_grpo_train | metrics_logged mode=train step=1775
2026-04-12 00:49:54,628 | INFO | train_grpo_train | metrics_logged mode=train step=1776
2026-04-12 00:49:59,306 | INFO | train_grpo_train | metrics_logged mode=train step=1777
2026-04-12 00:50:05,432 | INFO | train_grpo_train | metrics_logged mode=train step=1778
2026-04-12 00:50:10,692 | INFO | train_grpo_train | metrics_logged mode=train step=1779
2026-04-12 00:50:18,122 | INFO | train_grpo_train | metrics_logged mode=train step=1780
2026-04-12 00:50:22,340 | INFO | train_grpo_train | metrics_logged mode=train step=1781
2026-04-12 00:50:27,042 | INFO | train_grpo_train | metrics_logged mode=train step=1782
2026-04-12 00:50:32,456 | INFO | train_grpo_train | metrics_logged mode=train step=1783
2026-04-12 00:50:37,011 | INFO | train_grpo_train | metrics_logged mode=train step=1784
2026-04-12 00:50:41,578 | INFO | train_grpo_train | metrics_logged mode=train step=1785
2026-04-12 00:50:47,330 | INFO | train_grpo_train | metrics_logged mode=train step=1786
2026-04-12 00:50:52,247 | INFO | train_grpo_train | metrics_logged mode=train step=1787
2026-04-12 00:50:58,229 | INFO | train_grpo_train | metrics_logged mode=train step=1788
2026-04-12 00:51:02,811 | INFO | train_grpo_train | metrics_logged mode=train step=1789
2026-04-12 00:51:08,107 | INFO | train_grpo_train | metrics_logged mode=train step=1790
2026-04-12 00:51:15,525 | INFO | train_grpo_train | metrics_logged mode=train step=1791
2026-04-12 00:51:20,255 | INFO | train_grpo_train | metrics_logged mode=train step=1792
2026-04-12 00:51:25,255 | INFO | train_grpo_train | metrics_logged mode=train step=1793
2026-04-12 00:51:31,804 | INFO | train_grpo_train | metrics_logged mode=train step=1794
2026-04-12 00:51:37,313 | INFO | train_grpo_train | metrics_logged mode=train step=1795
2026-04-12 00:51:43,623 | INFO | train_grpo_train | metrics_logged mode=train step=1796
2026-04-12 00:51:53,032 | INFO | train_grpo_train | metrics_logged mode=train step=1797
2026-04-12 00:51:59,230 | INFO | train_grpo_train | metrics_logged mode=train step=1798
2026-04-12 00:52:04,075 | INFO | train_grpo_train | metrics_logged mode=train step=1799
2026-04-12 00:52:08,382 | INFO | train_grpo_train | metrics_logged mode=train step=1800
2026-04-12 00:53:14,465 | INFO | train_grpo_train | metrics_logged mode=eval step=1800
2026-04-12 00:53:23,808 | INFO | train_grpo_train | metrics_logged mode=train step=1801
2026-04-12 00:53:29,102 | INFO | train_grpo_train | metrics_logged mode=train step=1802
2026-04-12 00:53:33,374 | INFO | train_grpo_train | metrics_logged mode=train step=1803
2026-04-12 00:53:38,265 | INFO | train_grpo_train | metrics_logged mode=train step=1804
2026-04-12 00:53:42,657 | INFO | train_grpo_train | metrics_logged mode=train step=1805
2026-04-12 00:53:47,490 | INFO | train_grpo_train | metrics_logged mode=train step=1806
2026-04-12 00:53:51,947 | INFO | train_grpo_train | metrics_logged mode=train step=1807
2026-04-12 00:53:57,722 | INFO | train_grpo_train | metrics_logged mode=train step=1808
2026-04-12 00:54:03,520 | INFO | train_grpo_train | metrics_logged mode=train step=1809
2026-04-12 00:54:08,952 | INFO | train_grpo_train | metrics_logged mode=train step=1810
2026-04-12 00:54:14,044 | INFO | train_grpo_train | metrics_logged mode=train step=1811
2026-04-12 00:54:18,703 | INFO | train_grpo_train | metrics_logged mode=train step=1812
2026-04-12 00:54:24,766 | INFO | train_grpo_train | metrics_logged mode=train step=1813
2026-04-12 00:54:29,708 | INFO | train_grpo_train | metrics_logged mode=train step=1814
2026-04-12 00:54:35,595 | INFO | train_grpo_train | metrics_logged mode=train step=1815
2026-04-12 00:54:40,216 | INFO | train_grpo_train | metrics_logged mode=train step=1816
2026-04-12 00:54:44,888 | INFO | train_grpo_train | metrics_logged mode=train step=1817
2026-04-12 00:54:49,746 | INFO | train_grpo_train | metrics_logged mode=train step=1818
2026-04-12 00:54:54,675 | INFO | train_grpo_train | metrics_logged mode=train step=1819
2026-04-12 00:54:59,149 | INFO | train_grpo_train | metrics_logged mode=train step=1820
2026-04-12 00:55:03,793 | INFO | train_grpo_train | metrics_logged mode=train step=1821
2026-04-12 00:55:08,402 | INFO | train_grpo_train | metrics_logged mode=train step=1822
2026-04-12 00:55:12,903 | INFO | train_grpo_train | metrics_logged mode=train step=1823
2026-04-12 00:55:17,248 | INFO | train_grpo_train | metrics_logged mode=train step=1824
2026-04-12 00:55:22,192 | INFO | train_grpo_train | metrics_logged mode=train step=1825
2026-04-12 00:55:27,100 | INFO | train_grpo_train | metrics_logged mode=train step=1826
2026-04-12 00:55:32,079 | INFO | train_grpo_train | metrics_logged mode=train step=1827
2026-04-12 00:55:36,984 | INFO | train_grpo_train | metrics_logged mode=train step=1828
2026-04-12 00:55:43,022 | INFO | train_grpo_train | metrics_logged mode=train step=1829
2026-04-12 00:55:47,960 | INFO | train_grpo_train | metrics_logged mode=train step=1830
2026-04-12 00:55:53,354 | INFO | train_grpo_train | metrics_logged mode=train step=1831
2026-04-12 00:55:58,082 | INFO | train_grpo_train | metrics_logged mode=train step=1832
2026-04-12 00:56:02,761 | INFO | train_grpo_train | metrics_logged mode=train step=1833
2026-04-12 00:56:08,092 | INFO | train_grpo_train | metrics_logged mode=train step=1834
2026-04-12 00:56:12,622 | INFO | train_grpo_train | metrics_logged mode=train step=1835
2026-04-12 00:56:17,816 | INFO | train_grpo_train | metrics_logged mode=train step=1836
2026-04-12 00:56:23,448 | INFO | train_grpo_train | metrics_logged mode=train step=1837
2026-04-12 00:56:30,001 | INFO | train_grpo_train | metrics_logged mode=train step=1838
2026-04-12 00:56:34,743 | INFO | train_grpo_train | metrics_logged mode=train step=1839
2026-04-12 00:56:39,079 | INFO | train_grpo_train | metrics_logged mode=train step=1840
2026-04-12 00:56:44,241 | INFO | train_grpo_train | metrics_logged mode=train step=1841
2026-04-12 00:56:48,796 | INFO | train_grpo_train | metrics_logged mode=train step=1842
2026-04-12 00:56:53,349 | INFO | train_grpo_train | metrics_logged mode=train step=1843
2026-04-12 00:56:58,201 | INFO | train_grpo_train | metrics_logged mode=train step=1844
2026-04-12 00:57:02,794 | INFO | train_grpo_train | metrics_logged mode=train step=1845
2026-04-12 00:57:08,389 | INFO | train_grpo_train | metrics_logged mode=train step=1846
2026-04-12 00:57:13,734 | INFO | train_grpo_train | metrics_logged mode=train step=1847
2026-04-12 00:57:20,229 | INFO | train_grpo_train | metrics_logged mode=train step=1848
2026-04-12 00:57:25,086 | INFO | train_grpo_train | metrics_logged mode=train step=1849
2026-04-12 00:57:29,546 | INFO | train_grpo_train | metrics_logged mode=train step=1850
2026-04-12 00:58:32,306 | INFO | train_grpo_train | metrics_logged mode=eval step=1850
2026-04-12 00:58:40,290 | INFO | train_grpo_train | metrics_logged mode=train step=1851
2026-04-12 00:58:47,559 | INFO | train_grpo_train | metrics_logged mode=train step=1852
2026-04-12 00:58:52,045 | INFO | train_grpo_train | metrics_logged mode=train step=1853
2026-04-12 00:58:57,235 | INFO | train_grpo_train | metrics_logged mode=train step=1854
2026-04-12 00:59:01,706 | INFO | train_grpo_train | metrics_logged mode=train step=1855
2026-04-12 00:59:06,833 | INFO | train_grpo_train | metrics_logged mode=train step=1856
2026-04-12 00:59:11,405 | INFO | train_grpo_train | metrics_logged mode=train step=1857
2026-04-12 00:59:16,250 | INFO | train_grpo_train | metrics_logged mode=train step=1858
2026-04-12 00:59:20,822 | INFO | train_grpo_train | metrics_logged mode=train step=1859
2026-04-12 00:59:26,289 | INFO | train_grpo_train | metrics_logged mode=train step=1860
2026-04-12 00:59:31,341 | INFO | train_grpo_train | metrics_logged mode=train step=1861
2026-04-12 00:59:37,840 | INFO | train_grpo_train | metrics_logged mode=train step=1862
2026-04-12 00:59:42,521 | INFO | train_grpo_train | metrics_logged mode=train step=1863
2026-04-12 00:59:47,279 | INFO | train_grpo_train | metrics_logged mode=train step=1864
2026-04-12 00:59:51,931 | INFO | train_grpo_train | metrics_logged mode=train step=1865
2026-04-12 00:59:56,931 | INFO | train_grpo_train | metrics_logged mode=train step=1866
2026-04-12 01:00:05,391 | INFO | train_grpo_train | metrics_logged mode=train step=1867
2026-04-12 01:00:10,233 | INFO | train_grpo_train | metrics_logged mode=train step=1868
2026-04-12 01:00:15,239 | INFO | train_grpo_train | metrics_logged mode=train step=1869
2026-04-12 01:00:20,060 | INFO | train_grpo_train | metrics_logged mode=train step=1870
2026-04-12 01:00:24,636 | INFO | train_grpo_train | metrics_logged mode=train step=1871
2026-04-12 01:00:34,221 | INFO | train_grpo_train | metrics_logged mode=train step=1872
2026-04-12 01:00:43,858 | INFO | train_grpo_train | metrics_logged mode=train step=1873
2026-04-12 01:00:49,077 | INFO | train_grpo_train | metrics_logged mode=train step=1874
2026-04-12 01:00:55,548 | INFO | train_grpo_train | metrics_logged mode=train step=1875
2026-04-12 01:01:00,263 | INFO | train_grpo_train | metrics_logged mode=train step=1876
2026-04-12 01:01:06,842 | INFO | train_grpo_train | metrics_logged mode=train step=1877
2026-04-12 01:01:16,816 | INFO | train_grpo_train | metrics_logged mode=train step=1878
2026-04-12 01:01:26,568 | INFO | train_grpo_train | metrics_logged mode=train step=1879
2026-04-12 01:01:31,275 | INFO | train_grpo_train | metrics_logged mode=train step=1880
2026-04-12 01:01:35,876 | INFO | train_grpo_train | metrics_logged mode=train step=1881
2026-04-12 01:01:40,245 | INFO | train_grpo_train | metrics_logged mode=train step=1882
2026-04-12 01:01:46,008 | INFO | train_grpo_train | metrics_logged mode=train step=1883
2026-04-12 01:01:50,674 | INFO | train_grpo_train | metrics_logged mode=train step=1884
2026-04-12 01:01:57,572 | INFO | train_grpo_train | metrics_logged mode=train step=1885
2026-04-12 01:02:03,998 | INFO | train_grpo_train | metrics_logged mode=train step=1886
2026-04-12 01:02:09,491 | INFO | train_grpo_train | metrics_logged mode=train step=1887
2026-04-12 01:02:17,051 | INFO | train_grpo_train | metrics_logged mode=train step=1888
2026-04-12 01:02:24,873 | INFO | train_grpo_train | metrics_logged mode=train step=1889
2026-04-12 01:02:29,321 | INFO | train_grpo_train | metrics_logged mode=train step=1890
2026-04-12 01:02:33,638 | INFO | train_grpo_train | metrics_logged mode=train step=1891
2026-04-12 01:02:37,814 | INFO | train_grpo_train | metrics_logged mode=train step=1892
2026-04-12 01:02:43,342 | INFO | train_grpo_train | metrics_logged mode=train step=1893
2026-04-12 01:02:49,268 | INFO | train_grpo_train | metrics_logged mode=train step=1894
2026-04-12 01:02:55,477 | INFO | train_grpo_train | metrics_logged mode=train step=1895
2026-04-12 01:03:01,053 | INFO | train_grpo_train | metrics_logged mode=train step=1896
2026-04-12 01:03:06,593 | INFO | train_grpo_train | metrics_logged mode=train step=1897
2026-04-12 01:03:11,773 | INFO | train_grpo_train | metrics_logged mode=train step=1898
2026-04-12 01:03:16,326 | INFO | train_grpo_train | metrics_logged mode=train step=1899
2026-04-12 01:03:21,203 | INFO | train_grpo_train | metrics_logged mode=train step=1900
2026-04-12 01:04:25,446 | INFO | train_grpo_train | metrics_logged mode=eval step=1900
2026-04-12 01:04:32,305 | INFO | train_grpo_train | metrics_logged mode=train step=1901
2026-04-12 01:04:36,917 | INFO | train_grpo_train | metrics_logged mode=train step=1902
2026-04-12 01:04:42,160 | INFO | train_grpo_train | metrics_logged mode=train step=1903
2026-04-12 01:04:46,845 | INFO | train_grpo_train | metrics_logged mode=train step=1904
2026-04-12 01:04:51,938 | INFO | train_grpo_train | metrics_logged mode=train step=1905
2026-04-12 01:04:56,420 | INFO | train_grpo_train | metrics_logged mode=train step=1906
2026-04-12 01:05:03,307 | INFO | train_grpo_train | metrics_logged mode=train step=1907
2026-04-12 01:05:07,958 | INFO | train_grpo_train | metrics_logged mode=train step=1908
2026-04-12 01:05:12,912 | INFO | train_grpo_train | metrics_logged mode=train step=1909
2026-04-12 01:05:20,410 | INFO | train_grpo_train | metrics_logged mode=train step=1910
2026-04-12 01:05:24,934 | INFO | train_grpo_train | metrics_logged mode=train step=1911
2026-04-12 01:05:29,386 | INFO | train_grpo_train | metrics_logged mode=train step=1912
2026-04-12 01:05:33,710 | INFO | train_grpo_train | metrics_logged mode=train step=1913
2026-04-12 01:05:38,169 | INFO | train_grpo_train | metrics_logged mode=train step=1914
2026-04-12 01:05:43,187 | INFO | train_grpo_train | metrics_logged mode=train step=1915
2026-04-12 01:05:48,298 | INFO | train_grpo_train | metrics_logged mode=train step=1916
2026-04-12 01:05:53,323 | INFO | train_grpo_train | metrics_logged mode=train step=1917
2026-04-12 01:05:57,964 | INFO | train_grpo_train | metrics_logged mode=train step=1918
2026-04-12 01:06:02,450 | INFO | train_grpo_train | metrics_logged mode=train step=1919
2026-04-12 01:06:07,683 | INFO | train_grpo_train | metrics_logged mode=train step=1920
2026-04-12 01:06:12,793 | INFO | train_grpo_train | metrics_logged mode=train step=1921
2026-04-12 01:06:17,318 | INFO | train_grpo_train | metrics_logged mode=train step=1922
2026-04-12 01:06:23,396 | INFO | train_grpo_train | metrics_logged mode=train step=1923
2026-04-12 01:06:28,411 | INFO | train_grpo_train | metrics_logged mode=train step=1924
2026-04-12 01:06:32,807 | INFO | train_grpo_train | metrics_logged mode=train step=1925
2026-04-12 01:06:40,286 | INFO | train_grpo_train | metrics_logged mode=train step=1926
2026-04-12 01:06:45,160 | INFO | train_grpo_train | metrics_logged mode=train step=1927
2026-04-12 01:06:49,696 | INFO | train_grpo_train | metrics_logged mode=train step=1928
2026-04-12 01:06:54,593 | INFO | train_grpo_train | metrics_logged mode=train step=1929
2026-04-12 01:06:59,163 | INFO | train_grpo_train | metrics_logged mode=train step=1930
2026-04-12 01:07:03,652 | INFO | train_grpo_train | metrics_logged mode=train step=1931
2026-04-12 01:07:08,440 | INFO | train_grpo_train | metrics_logged mode=train step=1932
2026-04-12 01:07:13,173 | INFO | train_grpo_train | metrics_logged mode=train step=1933
2026-04-12 01:07:19,802 | INFO | train_grpo_train | metrics_logged mode=train step=1934
2026-04-12 01:07:24,563 | INFO | train_grpo_train | metrics_logged mode=train step=1935
2026-04-12 01:07:29,580 | INFO | train_grpo_train | metrics_logged mode=train step=1936
2026-04-12 01:07:33,989 | INFO | train_grpo_train | metrics_logged mode=train step=1937
2026-04-12 01:07:38,783 | INFO | train_grpo_train | metrics_logged mode=train step=1938
2026-04-12 01:07:43,538 | INFO | train_grpo_train | metrics_logged mode=train step=1939
2026-04-12 01:07:48,131 | INFO | train_grpo_train | metrics_logged mode=train step=1940
2026-04-12 01:07:58,181 | INFO | train_grpo_train | metrics_logged mode=train step=1941
2026-04-12 01:08:02,924 | INFO | train_grpo_train | metrics_logged mode=train step=1942
2026-04-12 01:08:07,931 | INFO | train_grpo_train | metrics_logged mode=train step=1943
2026-04-12 01:08:12,453 | INFO | train_grpo_train | metrics_logged mode=train step=1944
2026-04-12 01:08:17,006 | INFO | train_grpo_train | metrics_logged mode=train step=1945
2026-04-12 01:08:21,842 | INFO | train_grpo_train | metrics_logged mode=train step=1946
2026-04-12 01:08:26,567 | INFO | train_grpo_train | metrics_logged mode=train step=1947
2026-04-12 01:08:31,376 | INFO | train_grpo_train | metrics_logged mode=train step=1948
2026-04-12 01:08:37,024 | INFO | train_grpo_train | metrics_logged mode=train step=1949
2026-04-12 01:08:42,259 | INFO | train_grpo_train | metrics_logged mode=train step=1950
2026-04-12 01:09:56,474 | INFO | train_grpo_train | metrics_logged mode=eval step=1950
2026-04-12 01:10:04,883 | INFO | train_grpo_train | metrics_logged mode=train step=1951
2026-04-12 01:10:10,405 | INFO | train_grpo_train | metrics_logged mode=train step=1952
2026-04-12 01:10:15,533 | INFO | train_grpo_train | metrics_logged mode=train step=1953
2026-04-12 01:10:20,472 | INFO | train_grpo_train | metrics_logged mode=train step=1954
2026-04-12 01:10:28,354 | INFO | train_grpo_train | metrics_logged mode=train step=1955
2026-04-12 01:10:32,890 | INFO | train_grpo_train | metrics_logged mode=train step=1956
2026-04-12 01:10:38,334 | INFO | train_grpo_train | metrics_logged mode=train step=1957
2026-04-12 01:10:42,440 | INFO | train_grpo_train | metrics_logged mode=train step=1958
2026-04-12 01:10:47,293 | INFO | train_grpo_train | metrics_logged mode=train step=1959
2026-04-12 01:10:51,902 | INFO | train_grpo_train | metrics_logged mode=train step=1960
2026-04-12 01:10:56,483 | INFO | train_grpo_train | metrics_logged mode=train step=1961
2026-04-12 01:11:01,262 | INFO | train_grpo_train | metrics_logged mode=train step=1962
2026-04-12 01:11:06,085 | INFO | train_grpo_train | metrics_logged mode=train step=1963
2026-04-12 01:11:12,161 | INFO | train_grpo_train | metrics_logged mode=train step=1964
2026-04-12 01:11:17,143 | INFO | train_grpo_train | metrics_logged mode=train step=1965
2026-04-12 01:11:22,420 | INFO | train_grpo_train | metrics_logged mode=train step=1966
2026-04-12 01:11:27,182 | INFO | train_grpo_train | metrics_logged mode=train step=1967
2026-04-12 01:11:31,549 | INFO | train_grpo_train | metrics_logged mode=train step=1968
2026-04-12 01:11:36,284 | INFO | train_grpo_train | metrics_logged mode=train step=1969
2026-04-12 01:11:41,232 | INFO | train_grpo_train | metrics_logged mode=train step=1970
2026-04-12 01:11:45,898 | INFO | train_grpo_train | metrics_logged mode=train step=1971
2026-04-12 01:11:50,879 | INFO | train_grpo_train | metrics_logged mode=train step=1972
2026-04-12 01:11:56,277 | INFO | train_grpo_train | metrics_logged mode=train step=1973
2026-04-12 01:12:01,525 | INFO | train_grpo_train | metrics_logged mode=train step=1974
2026-04-12 01:12:06,278 | INFO | train_grpo_train | metrics_logged mode=train step=1975
2026-04-12 01:12:12,873 | INFO | train_grpo_train | metrics_logged mode=train step=1976
2026-04-12 01:12:19,093 | INFO | train_grpo_train | metrics_logged mode=train step=1977
2026-04-12 01:12:23,975 | INFO | train_grpo_train | metrics_logged mode=train step=1978
2026-04-12 01:12:28,741 | INFO | train_grpo_train | metrics_logged mode=train step=1979
2026-04-12 01:12:35,341 | INFO | train_grpo_train | metrics_logged mode=train step=1980
2026-04-12 01:12:40,237 | INFO | train_grpo_train | metrics_logged mode=train step=1981
2026-04-12 01:12:45,291 | INFO | train_grpo_train | metrics_logged mode=train step=1982
2026-04-12 01:12:49,588 | INFO | train_grpo_train | metrics_logged mode=train step=1983
2026-04-12 01:12:54,462 | INFO | train_grpo_train | metrics_logged mode=train step=1984
2026-04-12 01:12:59,133 | INFO | train_grpo_train | metrics_logged mode=train step=1985
2026-04-12 01:13:03,613 | INFO | train_grpo_train | metrics_logged mode=train step=1986
2026-04-12 01:13:09,346 | INFO | train_grpo_train | metrics_logged mode=train step=1987
2026-04-12 01:13:14,206 | INFO | train_grpo_train | metrics_logged mode=train step=1988
2026-04-12 01:13:19,000 | INFO | train_grpo_train | metrics_logged mode=train step=1989
2026-04-12 01:13:25,508 | INFO | train_grpo_train | metrics_logged mode=train step=1990
2026-04-12 01:13:33,138 | INFO | train_grpo_train | metrics_logged mode=train step=1991
2026-04-12 01:13:38,874 | INFO | train_grpo_train | metrics_logged mode=train step=1992
2026-04-12 01:13:43,628 | INFO | train_grpo_train | metrics_logged mode=train step=1993
2026-04-12 01:13:49,430 | INFO | train_grpo_train | metrics_logged mode=train step=1994
2026-04-12 01:13:53,663 | INFO | train_grpo_train | metrics_logged mode=train step=1995
2026-04-12 01:13:57,966 | INFO | train_grpo_train | metrics_logged mode=train step=1996
2026-04-12 01:14:02,610 | INFO | train_grpo_train | metrics_logged mode=train step=1997
2026-04-12 01:14:06,810 | INFO | train_grpo_train | metrics_logged mode=train step=1998
2026-04-12 01:14:11,592 | INFO | train_grpo_train | metrics_logged mode=train step=1999
2026-04-12 01:14:17,496 | INFO | train_grpo_train | metrics_logged mode=train step=2000
2026-04-12 01:15:25,463 | INFO | train_grpo_train | metrics_logged mode=eval step=2000
2026-04-12 01:15:33,199 | INFO | train_grpo_train | metrics_logged mode=train step=2001
2026-04-12 01:15:37,687 | INFO | train_grpo_train | metrics_logged mode=train step=2002
2026-04-12 01:15:42,936 | INFO | train_grpo_train | metrics_logged mode=train step=2003
2026-04-12 01:15:47,292 | INFO | train_grpo_train | metrics_logged mode=train step=2004
2026-04-12 01:15:52,627 | INFO | train_grpo_train | metrics_logged mode=train step=2005
2026-04-12 01:15:56,845 | INFO | train_grpo_train | metrics_logged mode=train step=2006
2026-04-12 01:16:01,682 | INFO | train_grpo_train | metrics_logged mode=train step=2007
2026-04-12 01:16:09,656 | INFO | train_grpo_train | metrics_logged mode=train step=2008
2026-04-12 01:16:14,199 | INFO | train_grpo_train | metrics_logged mode=train step=2009
2026-04-12 01:16:19,442 | INFO | train_grpo_train | metrics_logged mode=train step=2010
2026-04-12 01:16:24,262 | INFO | train_grpo_train | metrics_logged mode=train step=2011
2026-04-12 01:16:28,533 | INFO | train_grpo_train | metrics_logged mode=train step=2012
2026-04-12 01:16:33,510 | INFO | train_grpo_train | metrics_logged mode=train step=2013
2026-04-12 01:16:38,018 | INFO | train_grpo_train | metrics_logged mode=train step=2014
2026-04-12 01:16:42,990 | INFO | train_grpo_train | metrics_logged mode=train step=2015
2026-04-12 01:16:47,334 | INFO | train_grpo_train | metrics_logged mode=train step=2016
2026-04-12 01:16:52,557 | INFO | train_grpo_train | metrics_logged mode=train step=2017
2026-04-12 01:16:57,461 | INFO | train_grpo_train | metrics_logged mode=train step=2018
2026-04-12 01:17:02,909 | INFO | train_grpo_train | metrics_logged mode=train step=2019
2026-04-12 01:17:08,875 | INFO | train_grpo_train | metrics_logged mode=train step=2020
2026-04-12 01:17:14,357 | INFO | train_grpo_train | metrics_logged mode=train step=2021
2026-04-12 01:17:18,724 | INFO | train_grpo_train | metrics_logged mode=train step=2022
2026-04-12 01:17:23,510 | INFO | train_grpo_train | metrics_logged mode=train step=2023
2026-04-12 01:17:28,646 | INFO | train_grpo_train | metrics_logged mode=train step=2024
2026-04-12 01:17:34,446 | INFO | train_grpo_train | metrics_logged mode=train step=2025
2026-04-12 01:17:39,101 | INFO | train_grpo_train | metrics_logged mode=train step=2026
2026-04-12 01:17:47,654 | INFO | train_grpo_train | metrics_logged mode=train step=2027
2026-04-12 01:17:52,419 | INFO | train_grpo_train | metrics_logged mode=train step=2028
2026-04-12 01:17:57,492 | INFO | train_grpo_train | metrics_logged mode=train step=2029
2026-04-12 01:18:02,331 | INFO | train_grpo_train | metrics_logged mode=train step=2030
2026-04-12 01:18:07,833 | INFO | train_grpo_train | metrics_logged mode=train step=2031
2026-04-12 01:18:12,741 | INFO | train_grpo_train | metrics_logged mode=train step=2032
2026-04-12 01:18:18,705 | INFO | train_grpo_train | metrics_logged mode=train step=2033
2026-04-12 01:18:23,328 | INFO | train_grpo_train | metrics_logged mode=train step=2034
2026-04-12 01:18:28,295 | INFO | train_grpo_train | metrics_logged mode=train step=2035
2026-04-12 01:18:33,609 | INFO | train_grpo_train | metrics_logged mode=train step=2036
2026-04-12 01:18:38,265 | INFO | train_grpo_train | metrics_logged mode=train step=2037
2026-04-12 01:18:43,367 | INFO | train_grpo_train | metrics_logged mode=train step=2038
2026-04-12 01:18:48,701 | INFO | train_grpo_train | metrics_logged mode=train step=2039
2026-04-12 01:18:53,417 | INFO | train_grpo_train | metrics_logged mode=train step=2040
2026-04-12 01:18:58,046 | INFO | train_grpo_train | metrics_logged mode=train step=2041
2026-04-12 01:19:02,595 | INFO | train_grpo_train | metrics_logged mode=train step=2042
2026-04-12 01:19:11,293 | INFO | train_grpo_train | metrics_logged mode=train step=2043
2026-04-12 01:19:16,156 | INFO | train_grpo_train | metrics_logged mode=train step=2044
2026-04-12 01:19:21,740 | INFO | train_grpo_train | metrics_logged mode=train step=2045
2026-04-12 01:19:26,424 | INFO | train_grpo_train | metrics_logged mode=train step=2046
2026-04-12 01:19:31,115 | INFO | train_grpo_train | metrics_logged mode=train step=2047
2026-04-12 01:19:37,807 | INFO | train_grpo_train | metrics_logged mode=train step=2048
2026-04-12 01:19:42,641 | INFO | train_grpo_train | metrics_logged mode=train step=2049
2026-04-12 01:19:47,355 | INFO | train_grpo_train | metrics_logged mode=train step=2050
2026-04-12 01:20:55,009 | INFO | train_grpo_train | metrics_logged mode=eval step=2050
2026-04-12 01:21:05,885 | INFO | train_grpo_train | metrics_logged mode=train step=2051
2026-04-12 01:21:12,595 | INFO | train_grpo_train | metrics_logged mode=train step=2052
2026-04-12 01:21:17,059 | INFO | train_grpo_train | metrics_logged mode=train step=2053
2026-04-12 01:21:21,871 | INFO | train_grpo_train | metrics_logged mode=train step=2054
2026-04-12 01:21:29,952 | INFO | train_grpo_train | metrics_logged mode=train step=2055
2026-04-12 01:21:34,603 | INFO | train_grpo_train | metrics_logged mode=train step=2056
2026-04-12 01:21:39,255 | INFO | train_grpo_train | metrics_logged mode=train step=2057
2026-04-12 01:21:43,894 | INFO | train_grpo_train | metrics_logged mode=train step=2058
2026-04-12 01:21:48,561 | INFO | train_grpo_train | metrics_logged mode=train step=2059
2026-04-12 01:21:53,661 | INFO | train_grpo_train | metrics_logged mode=train step=2060
2026-04-12 01:21:59,046 | INFO | train_grpo_train | metrics_logged mode=train step=2061
2026-04-12 01:22:04,374 | INFO | train_grpo_train | metrics_logged mode=train step=2062
2026-04-12 01:22:09,355 | INFO | train_grpo_train | metrics_logged mode=train step=2063
2026-04-12 01:22:14,549 | INFO | train_grpo_train | metrics_logged mode=train step=2064
2026-04-12 01:22:19,323 | INFO | train_grpo_train | metrics_logged mode=train step=2065
2026-04-12 01:22:23,870 | INFO | train_grpo_train | metrics_logged mode=train step=2066
2026-04-12 01:22:32,437 | INFO | train_grpo_train | metrics_logged mode=train step=2067
2026-04-12 01:22:37,160 | INFO | train_grpo_train | metrics_logged mode=train step=2068
2026-04-12 01:22:41,343 | INFO | train_grpo_train | metrics_logged mode=train step=2069
2026-04-12 01:22:45,831 | INFO | train_grpo_train | metrics_logged mode=train step=2070
2026-04-12 01:22:50,726 | INFO | train_grpo_train | metrics_logged mode=train step=2071
2026-04-12 01:22:56,471 | INFO | train_grpo_train | metrics_logged mode=train step=2072
2026-04-12 01:23:01,660 | INFO | train_grpo_train | metrics_logged mode=train step=2073
2026-04-12 01:23:06,108 | INFO | train_grpo_train | metrics_logged mode=train step=2074
2026-04-12 01:23:10,625 | INFO | train_grpo_train | metrics_logged mode=train step=2075
2026-04-12 01:23:15,880 | INFO | train_grpo_train | metrics_logged mode=train step=2076
2026-04-12 01:23:20,534 | INFO | train_grpo_train | metrics_logged mode=train step=2077
2026-04-12 01:23:26,188 | INFO | train_grpo_train | metrics_logged mode=train step=2078
2026-04-12 01:23:30,830 | INFO | train_grpo_train | metrics_logged mode=train step=2079
2026-04-12 01:23:35,103 | INFO | train_grpo_train | metrics_logged mode=train step=2080
2026-04-12 01:23:39,812 | INFO | train_grpo_train | metrics_logged mode=train step=2081
2026-04-12 01:23:44,331 | INFO | train_grpo_train | metrics_logged mode=train step=2082
2026-04-12 01:23:49,930 | INFO | train_grpo_train | metrics_logged mode=train step=2083
2026-04-12 01:23:55,625 | INFO | train_grpo_train | metrics_logged mode=train step=2084
2026-04-12 01:24:03,159 | INFO | train_grpo_train | metrics_logged mode=train step=2085
2026-04-12 01:24:10,614 | INFO | train_grpo_train | metrics_logged mode=train step=2086
2026-04-12 01:24:15,047 | INFO | train_grpo_train | metrics_logged mode=train step=2087
2026-04-12 01:24:20,188 | INFO | train_grpo_train | metrics_logged mode=train step=2088
2026-04-12 01:24:24,663 | INFO | train_grpo_train | metrics_logged mode=train step=2089
2026-04-12 01:24:29,418 | INFO | train_grpo_train | metrics_logged mode=train step=2090
2026-04-12 01:24:34,916 | INFO | train_grpo_train | metrics_logged mode=train step=2091
2026-04-12 01:24:39,163 | INFO | train_grpo_train | metrics_logged mode=train step=2092
2026-04-12 01:24:43,398 | INFO | train_grpo_train | metrics_logged mode=train step=2093
2026-04-12 01:24:47,882 | INFO | train_grpo_train | metrics_logged mode=train step=2094
2026-04-12 01:24:52,411 | INFO | train_grpo_train | metrics_logged mode=train step=2095
2026-04-12 01:24:57,011 | INFO | train_grpo_train | metrics_logged mode=train step=2096
2026-04-12 01:25:01,048 | INFO | train_grpo_train | metrics_logged mode=train step=2097
2026-04-12 01:25:05,784 | INFO | train_grpo_train | metrics_logged mode=train step=2098
2026-04-12 01:25:10,803 | INFO | train_grpo_train | metrics_logged mode=train step=2099
2026-04-12 01:25:15,571 | INFO | train_grpo_train | metrics_logged mode=train step=2100
2026-04-12 01:26:24,192 | INFO | train_grpo_train | metrics_logged mode=eval step=2100
2026-04-12 01:26:33,771 | INFO | train_grpo_train | metrics_logged mode=train step=2101
2026-04-12 01:26:38,054 | INFO | train_grpo_train | metrics_logged mode=train step=2102
2026-04-12 01:26:45,411 | INFO | train_grpo_train | metrics_logged mode=train step=2103
2026-04-12 01:26:53,168 | INFO | train_grpo_train | metrics_logged mode=train step=2104
2026-04-12 01:26:58,863 | INFO | train_grpo_train | metrics_logged mode=train step=2105
2026-04-12 01:27:07,041 | INFO | train_grpo_train | metrics_logged mode=train step=2106
2026-04-12 01:27:12,447 | INFO | train_grpo_train | metrics_logged mode=train step=2107
2026-04-12 01:27:17,764 | INFO | train_grpo_train | metrics_logged mode=train step=2108
2026-04-12 01:27:22,351 | INFO | train_grpo_train | metrics_logged mode=train step=2109
2026-04-12 01:27:26,872 | INFO | train_grpo_train | metrics_logged mode=train step=2110
2026-04-12 01:27:31,642 | INFO | train_grpo_train | metrics_logged mode=train step=2111
2026-04-12 01:27:36,478 | INFO | train_grpo_train | metrics_logged mode=train step=2112
2026-04-12 01:27:45,156 | INFO | train_grpo_train | metrics_logged mode=train step=2113
2026-04-12 01:27:51,911 | INFO | train_grpo_train | metrics_logged mode=train step=2114
2026-04-12 01:28:01,311 | INFO | train_grpo_train | metrics_logged mode=train step=2115
2026-04-12 01:28:07,749 | INFO | train_grpo_train | metrics_logged mode=train step=2116
2026-04-12 01:28:14,712 | INFO | train_grpo_train | metrics_logged mode=train step=2117
2026-04-12 01:28:22,899 | INFO | train_grpo_train | metrics_logged mode=train step=2118
2026-04-12 01:28:27,386 | INFO | train_grpo_train | metrics_logged mode=train step=2119
2026-04-12 01:28:32,085 | INFO | train_grpo_train | metrics_logged mode=train step=2120
2026-04-12 01:28:36,493 | INFO | train_grpo_train | metrics_logged mode=train step=2121
2026-04-12 01:28:45,678 | INFO | train_grpo_train | metrics_logged mode=train step=2122
2026-04-12 01:28:50,187 | INFO | train_grpo_train | metrics_logged mode=train step=2123
2026-04-12 01:28:55,180 | INFO | train_grpo_train | metrics_logged mode=train step=2124
2026-04-12 01:29:00,979 | INFO | train_grpo_train | metrics_logged mode=train step=2125
2026-04-12 01:29:05,272 | INFO | train_grpo_train | metrics_logged mode=train step=2126
2026-04-12 01:29:09,808 | INFO | train_grpo_train | metrics_logged mode=train step=2127
2026-04-12 01:29:16,872 | INFO | train_grpo_train | metrics_logged mode=train step=2128
2026-04-12 01:29:24,053 | INFO | train_grpo_train | metrics_logged mode=train step=2129
2026-04-12 01:29:28,778 | INFO | train_grpo_train | metrics_logged mode=train step=2130
2026-04-12 01:29:34,305 | INFO | train_grpo_train | metrics_logged mode=train step=2131
2026-04-12 01:29:39,496 | INFO | train_grpo_train | metrics_logged mode=train step=2132
2026-04-12 01:29:45,246 | INFO | train_grpo_train | metrics_logged mode=train step=2133
2026-04-12 01:29:49,637 | INFO | train_grpo_train | metrics_logged mode=train step=2134
2026-04-12 01:29:56,555 | INFO | train_grpo_train | metrics_logged mode=train step=2135
2026-04-12 01:30:02,737 | INFO | train_grpo_train | metrics_logged mode=train step=2136
2026-04-12 01:30:08,514 | INFO | train_grpo_train | metrics_logged mode=train step=2137
2026-04-12 01:30:15,695 | INFO | train_grpo_train | metrics_logged mode=train step=2138
2026-04-12 01:30:20,306 | INFO | train_grpo_train | metrics_logged mode=train step=2139
2026-04-12 01:30:25,403 | INFO | train_grpo_train | metrics_logged mode=train step=2140
2026-04-12 01:30:29,879 | INFO | train_grpo_train | metrics_logged mode=train step=2141
2026-04-12 01:30:39,091 | INFO | train_grpo_train | metrics_logged mode=train step=2142
2026-04-12 01:30:43,788 | INFO | train_grpo_train | metrics_logged mode=train step=2143
2026-04-12 01:30:48,468 | INFO | train_grpo_train | metrics_logged mode=train step=2144
2026-04-12 01:30:52,654 | INFO | train_grpo_train | metrics_logged mode=train step=2145
2026-04-12 01:31:01,959 | INFO | train_grpo_train | metrics_logged mode=train step=2146
2026-04-12 01:31:06,686 | INFO | train_grpo_train | metrics_logged mode=train step=2147
2026-04-12 01:31:10,732 | INFO | train_grpo_train | metrics_logged mode=train step=2148
2026-04-12 01:31:16,826 | INFO | train_grpo_train | metrics_logged mode=train step=2149
2026-04-12 01:31:22,731 | INFO | train_grpo_train | metrics_logged mode=train step=2150
2026-04-12 01:32:33,849 | INFO | train_grpo_train | metrics_logged mode=eval step=2150
2026-04-12 01:32:46,143 | INFO | train_grpo_train | metrics_logged mode=train step=2151
2026-04-12 01:32:53,304 | INFO | train_grpo_train | metrics_logged mode=train step=2152
2026-04-12 01:32:57,880 | INFO | train_grpo_train | metrics_logged mode=train step=2153
2026-04-12 01:33:02,556 | INFO | train_grpo_train | metrics_logged mode=train step=2154
2026-04-12 01:33:07,054 | INFO | train_grpo_train | metrics_logged mode=train step=2155
2026-04-12 01:33:12,120 | INFO | train_grpo_train | metrics_logged mode=train step=2156
2026-04-12 01:33:16,381 | INFO | train_grpo_train | metrics_logged mode=train step=2157
2026-04-12 01:33:20,812 | INFO | train_grpo_train | metrics_logged mode=train step=2158
2026-04-12 01:33:25,318 | INFO | train_grpo_train | metrics_logged mode=train step=2159
2026-04-12 01:33:29,999 | INFO | train_grpo_train | metrics_logged mode=train step=2160
2026-04-12 01:33:34,380 | INFO | train_grpo_train | metrics_logged mode=train step=2161
2026-04-12 01:33:39,106 | INFO | train_grpo_train | metrics_logged mode=train step=2162
2026-04-12 01:33:46,062 | INFO | train_grpo_train | metrics_logged mode=train step=2163
2026-04-12 01:33:50,564 | INFO | train_grpo_train | metrics_logged mode=train step=2164
2026-04-12 01:33:55,158 | INFO | train_grpo_train | metrics_logged mode=train step=2165
2026-04-12 01:34:00,328 | INFO | train_grpo_train | metrics_logged mode=train step=2166
2026-04-12 01:34:04,918 | INFO | train_grpo_train | metrics_logged mode=train step=2167
2026-04-12 01:34:08,922 | INFO | train_grpo_train | metrics_logged mode=train step=2168
2026-04-12 01:34:17,019 | INFO | train_grpo_train | metrics_logged mode=train step=2169
2026-04-12 01:34:21,643 | INFO | train_grpo_train | metrics_logged mode=train step=2170
2026-04-12 01:34:26,383 | INFO | train_grpo_train | metrics_logged mode=train step=2171
2026-04-12 01:34:32,790 | INFO | train_grpo_train | metrics_logged mode=train step=2172
2026-04-12 01:34:37,330 | INFO | train_grpo_train | metrics_logged mode=train step=2173
2026-04-12 01:34:42,180 | INFO | train_grpo_train | metrics_logged mode=train step=2174
2026-04-12 01:34:46,919 | INFO | train_grpo_train | metrics_logged mode=train step=2175
2026-04-12 01:34:51,594 | INFO | train_grpo_train | metrics_logged mode=train step=2176
2026-04-12 01:34:55,896 | INFO | train_grpo_train | metrics_logged mode=train step=2177
2026-04-12 01:35:01,842 | INFO | train_grpo_train | metrics_logged mode=train step=2178
2026-04-12 01:35:06,769 | INFO | train_grpo_train | metrics_logged mode=train step=2179
2026-04-12 01:35:13,743 | INFO | train_grpo_train | metrics_logged mode=train step=2180
2026-04-12 01:35:19,020 | INFO | train_grpo_train | metrics_logged mode=train step=2181
2026-04-12 01:35:24,661 | INFO | train_grpo_train | metrics_logged mode=train step=2182
2026-04-12 01:35:29,910 | INFO | train_grpo_train | metrics_logged mode=train step=2183
2026-04-12 01:35:35,454 | INFO | train_grpo_train | metrics_logged mode=train step=2184
2026-04-12 01:35:40,563 | INFO | train_grpo_train | metrics_logged mode=train step=2185
2026-04-12 01:35:45,476 | INFO | train_grpo_train | metrics_logged mode=train step=2186
2026-04-12 01:35:53,798 | INFO | train_grpo_train | metrics_logged mode=train step=2187
2026-04-12 01:35:58,939 | INFO | train_grpo_train | metrics_logged mode=train step=2188
2026-04-12 01:36:03,506 | INFO | train_grpo_train | metrics_logged mode=train step=2189
2026-04-12 01:36:07,790 | INFO | train_grpo_train | metrics_logged mode=train step=2190
2026-04-12 01:36:13,138 | INFO | train_grpo_train | metrics_logged mode=train step=2191
2026-04-12 01:36:18,436 | INFO | train_grpo_train | metrics_logged mode=train step=2192
2026-04-12 01:36:23,358 | INFO | train_grpo_train | metrics_logged mode=train step=2193
2026-04-12 01:36:28,140 | INFO | train_grpo_train | metrics_logged mode=train step=2194
2026-04-12 01:36:33,106 | INFO | train_grpo_train | metrics_logged mode=train step=2195
2026-04-12 01:36:37,846 | INFO | train_grpo_train | metrics_logged mode=train step=2196
2026-04-12 01:36:42,872 | INFO | train_grpo_train | metrics_logged mode=train step=2197
2026-04-12 01:36:47,581 | INFO | train_grpo_train | metrics_logged mode=train step=2198
2026-04-12 01:36:52,193 | INFO | train_grpo_train | metrics_logged mode=train step=2199
2026-04-12 01:36:57,048 | INFO | train_grpo_train | metrics_logged mode=train step=2200
2026-04-12 01:38:02,281 | INFO | train_grpo_train | metrics_logged mode=eval step=2200
2026-04-12 01:38:09,817 | INFO | train_grpo_train | metrics_logged mode=train step=2201
2026-04-12 01:38:17,419 | INFO | train_grpo_train | metrics_logged mode=train step=2202
2026-04-12 01:38:22,322 | INFO | train_grpo_train | metrics_logged mode=train step=2203
2026-04-12 01:38:31,816 | INFO | train_grpo_train | metrics_logged mode=train step=2204
2026-04-12 01:38:39,048 | INFO | train_grpo_train | metrics_logged mode=train step=2205
2026-04-12 01:38:43,601 | INFO | train_grpo_train | metrics_logged mode=train step=2206
2026-04-12 01:38:52,372 | INFO | train_grpo_train | metrics_logged mode=train step=2207
2026-04-12 01:38:56,921 | INFO | train_grpo_train | metrics_logged mode=train step=2208
2026-04-12 01:39:01,562 | INFO | train_grpo_train | metrics_logged mode=train step=2209
2026-04-12 01:39:06,496 | INFO | train_grpo_train | metrics_logged mode=train step=2210
2026-04-12 01:39:11,615 | INFO | train_grpo_train | metrics_logged mode=train step=2211
2026-04-12 01:39:18,955 | INFO | train_grpo_train | metrics_logged mode=train step=2212
2026-04-12 01:39:23,189 | INFO | train_grpo_train | metrics_logged mode=train step=2213
2026-04-12 01:39:30,931 | INFO | train_grpo_train | metrics_logged mode=train step=2214
2026-04-12 01:39:36,238 | INFO | train_grpo_train | metrics_logged mode=train step=2215
2026-04-12 01:39:40,731 | INFO | train_grpo_train | metrics_logged mode=train step=2216
2026-04-12 01:39:45,948 | INFO | train_grpo_train | metrics_logged mode=train step=2217
2026-04-12 01:39:55,654 | INFO | train_grpo_train | metrics_logged mode=train step=2218
2026-04-12 01:40:00,238 | INFO | train_grpo_train | metrics_logged mode=train step=2219
2026-04-12 01:40:05,612 | INFO | train_grpo_train | metrics_logged mode=train step=2220
2026-04-12 01:40:10,348 | INFO | train_grpo_train | metrics_logged mode=train step=2221
2026-04-12 01:40:17,704 | INFO | train_grpo_train | metrics_logged mode=train step=2222
2026-04-12 01:40:23,696 | INFO | train_grpo_train | metrics_logged mode=train step=2223
2026-04-12 01:40:28,161 | INFO | train_grpo_train | metrics_logged mode=train step=2224
2026-04-12 01:40:32,906 | INFO | train_grpo_train | metrics_logged mode=train step=2225
2026-04-12 01:40:37,206 | INFO | train_grpo_train | metrics_logged mode=train step=2226
2026-04-12 01:40:47,321 | INFO | train_grpo_train | metrics_logged mode=train step=2227
2026-04-12 01:40:51,769 | INFO | train_grpo_train | metrics_logged mode=train step=2228
2026-04-12 01:40:57,593 | INFO | train_grpo_train | metrics_logged mode=train step=2229
2026-04-12 01:41:01,932 | INFO | train_grpo_train | metrics_logged mode=train step=2230
2026-04-12 01:41:06,344 | INFO | train_grpo_train | metrics_logged mode=train step=2231
2026-04-12 01:41:10,975 | INFO | train_grpo_train | metrics_logged mode=train step=2232
2026-04-12 01:41:16,589 | INFO | train_grpo_train | metrics_logged mode=train step=2233
2026-04-12 01:41:21,334 | INFO | train_grpo_train | metrics_logged mode=train step=2234
2026-04-12 01:41:26,118 | INFO | train_grpo_train | metrics_logged mode=train step=2235
2026-04-12 01:41:31,231 | INFO | train_grpo_train | metrics_logged mode=train step=2236
2026-04-12 01:41:37,024 | INFO | train_grpo_train | metrics_logged mode=train step=2237
2026-04-12 01:41:41,731 | INFO | train_grpo_train | metrics_logged mode=train step=2238
2026-04-12 01:41:47,075 | INFO | train_grpo_train | metrics_logged mode=train step=2239
2026-04-12 01:41:52,377 | INFO | train_grpo_train | metrics_logged mode=train step=2240
2026-04-12 01:41:57,131 | INFO | train_grpo_train | metrics_logged mode=train step=2241
2026-04-12 01:42:01,996 | INFO | train_grpo_train | metrics_logged mode=train step=2242
2026-04-12 01:42:06,705 | INFO | train_grpo_train | metrics_logged mode=train step=2243
2026-04-12 01:42:11,731 | INFO | train_grpo_train | metrics_logged mode=train step=2244
2026-04-12 01:42:17,663 | INFO | train_grpo_train | metrics_logged mode=train step=2245
2026-04-12 01:42:23,607 | INFO | train_grpo_train | metrics_logged mode=train step=2246
2026-04-12 01:42:29,356 | INFO | train_grpo_train | metrics_logged mode=train step=2247
2026-04-12 01:42:34,381 | INFO | train_grpo_train | metrics_logged mode=train step=2248
2026-04-12 01:42:38,914 | INFO | train_grpo_train | metrics_logged mode=train step=2249
2026-04-12 01:42:43,442 | INFO | train_grpo_train | metrics_logged mode=train step=2250
2026-04-12 01:43:47,813 | INFO | train_grpo_train | metrics_logged mode=eval step=2250
2026-04-12 01:43:55,401 | INFO | train_grpo_train | metrics_logged mode=train step=2251
2026-04-12 01:44:00,351 | INFO | train_grpo_train | metrics_logged mode=train step=2252
2026-04-12 01:44:04,829 | INFO | train_grpo_train | metrics_logged mode=train step=2253
2026-04-12 01:44:11,196 | INFO | train_grpo_train | metrics_logged mode=train step=2254
2026-04-12 01:44:15,575 | INFO | train_grpo_train | metrics_logged mode=train step=2255
2026-04-12 01:44:21,785 | INFO | train_grpo_train | metrics_logged mode=train step=2256
2026-04-12 01:44:28,639 | INFO | train_grpo_train | metrics_logged mode=train step=2257
2026-04-12 01:44:34,544 | INFO | train_grpo_train | metrics_logged mode=train step=2258
2026-04-12 01:44:39,815 | INFO | train_grpo_train | metrics_logged mode=train step=2259
2026-04-12 01:44:48,042 | INFO | train_grpo_train | metrics_logged mode=train step=2260
2026-04-12 01:44:53,150 | INFO | train_grpo_train | metrics_logged mode=train step=2261
2026-04-12 01:44:57,768 | INFO | train_grpo_train | metrics_logged mode=train step=2262
2026-04-12 01:45:02,016 | INFO | train_grpo_train | metrics_logged mode=train step=2263
2026-04-12 01:45:06,465 | INFO | train_grpo_train | metrics_logged mode=train step=2264
2026-04-12 01:45:11,410 | INFO | train_grpo_train | metrics_logged mode=train step=2265
2026-04-12 01:45:16,939 | INFO | train_grpo_train | metrics_logged mode=train step=2266
2026-04-12 01:45:22,341 | INFO | train_grpo_train | metrics_logged mode=train step=2267
2026-04-12 01:45:27,797 | INFO | train_grpo_train | metrics_logged mode=train step=2268
2026-04-12 01:45:33,798 | INFO | train_grpo_train | metrics_logged mode=train step=2269
2026-04-12 01:45:39,854 | INFO | train_grpo_train | metrics_logged mode=train step=2270
2026-04-12 01:45:44,437 | INFO | train_grpo_train | metrics_logged mode=train step=2271
2026-04-12 01:45:49,021 | INFO | train_grpo_train | metrics_logged mode=train step=2272
2026-04-12 01:45:56,629 | INFO | train_grpo_train | metrics_logged mode=train step=2273
2026-04-12 01:46:02,287 | INFO | train_grpo_train | metrics_logged mode=train step=2274
2026-04-12 01:46:06,646 | INFO | train_grpo_train | metrics_logged mode=train step=2275
2026-04-12 01:46:12,260 | INFO | train_grpo_train | metrics_logged mode=train step=2276
2026-04-12 01:46:18,521 | INFO | train_grpo_train | metrics_logged mode=train step=2277
2026-04-12 01:46:23,237 | INFO | train_grpo_train | metrics_logged mode=train step=2278
2026-04-12 01:46:27,684 | INFO | train_grpo_train | metrics_logged mode=train step=2279
2026-04-12 01:46:33,697 | INFO | train_grpo_train | metrics_logged mode=train step=2280
2026-04-12 01:46:38,256 | INFO | train_grpo_train | metrics_logged mode=train step=2281
2026-04-12 01:46:43,710 | INFO | train_grpo_train | metrics_logged mode=train step=2282
2026-04-12 01:46:49,691 | INFO | train_grpo_train | metrics_logged mode=train step=2283
2026-04-12 01:46:53,770 | INFO | train_grpo_train | metrics_logged mode=train step=2284
2026-04-12 01:46:59,711 | INFO | train_grpo_train | metrics_logged mode=train step=2285
2026-04-12 01:47:04,653 | INFO | train_grpo_train | metrics_logged mode=train step=2286
2026-04-12 01:47:09,404 | INFO | train_grpo_train | metrics_logged mode=train step=2287
2026-04-12 01:47:15,166 | INFO | train_grpo_train | metrics_logged mode=train step=2288
2026-04-12 01:47:19,658 | INFO | train_grpo_train | metrics_logged mode=train step=2289
2026-04-12 01:47:24,156 | INFO | train_grpo_train | metrics_logged mode=train step=2290
2026-04-12 01:47:28,573 | INFO | train_grpo_train | metrics_logged mode=train step=2291
2026-04-12 01:47:34,539 | INFO | train_grpo_train | metrics_logged mode=train step=2292
2026-04-12 01:47:43,075 | INFO | train_grpo_train | metrics_logged mode=train step=2293
2026-04-12 01:47:51,080 | INFO | train_grpo_train | metrics_logged mode=train step=2294
2026-04-12 01:47:55,989 | INFO | train_grpo_train | metrics_logged mode=train step=2295
2026-04-12 01:48:00,411 | INFO | train_grpo_train | metrics_logged mode=train step=2296
2026-04-12 01:48:04,576 | INFO | train_grpo_train | metrics_logged mode=train step=2297
2026-04-12 01:48:09,047 | INFO | train_grpo_train | metrics_logged mode=train step=2298
2026-04-12 01:48:14,320 | INFO | train_grpo_train | metrics_logged mode=train step=2299
2026-04-12 01:48:18,765 | INFO | train_grpo_train | metrics_logged mode=train step=2300
2026-04-12 01:49:20,733 | INFO | train_grpo_train | metrics_logged mode=eval step=2300
2026-04-12 01:49:27,932 | INFO | train_grpo_train | metrics_logged mode=train step=2301
2026-04-12 01:49:32,653 | INFO | train_grpo_train | metrics_logged mode=train step=2302
2026-04-12 01:49:41,481 | INFO | train_grpo_train | metrics_logged mode=train step=2303
2026-04-12 01:49:45,805 | INFO | train_grpo_train | metrics_logged mode=train step=2304
2026-04-12 01:49:51,930 | INFO | train_grpo_train | metrics_logged mode=train step=2305
2026-04-12 01:49:55,911 | INFO | train_grpo_train | metrics_logged mode=train step=2306
2026-04-12 01:50:00,175 | INFO | train_grpo_train | metrics_logged mode=train step=2307
2026-04-12 01:50:04,215 | INFO | train_grpo_train | metrics_logged mode=train step=2308
2026-04-12 01:50:08,709 | INFO | train_grpo_train | metrics_logged mode=train step=2309
2026-04-12 01:50:12,880 | INFO | train_grpo_train | metrics_logged mode=train step=2310
2026-04-12 01:50:17,072 | INFO | train_grpo_train | metrics_logged mode=train step=2311
2026-04-12 01:50:21,867 | INFO | train_grpo_train | metrics_logged mode=train step=2312
2026-04-12 01:50:26,094 | INFO | train_grpo_train | metrics_logged mode=train step=2313
2026-04-12 01:50:31,552 | INFO | train_grpo_train | metrics_logged mode=train step=2314
2026-04-12 01:50:36,095 | INFO | train_grpo_train | metrics_logged mode=train step=2315
2026-04-12 01:50:41,249 | INFO | train_grpo_train | metrics_logged mode=train step=2316
2026-04-12 01:50:50,466 | INFO | train_grpo_train | metrics_logged mode=train step=2317
2026-04-12 01:50:55,149 | INFO | train_grpo_train | metrics_logged mode=train step=2318
2026-04-12 01:50:59,593 | INFO | train_grpo_train | metrics_logged mode=train step=2319
2026-04-12 01:51:05,968 | INFO | train_grpo_train | metrics_logged mode=train step=2320
2026-04-12 01:51:10,402 | INFO | train_grpo_train | metrics_logged mode=train step=2321
2026-04-12 01:51:15,053 | INFO | train_grpo_train | metrics_logged mode=train step=2322
2026-04-12 01:51:19,724 | INFO | train_grpo_train | metrics_logged mode=train step=2323
2026-04-12 01:51:25,066 | INFO | train_grpo_train | metrics_logged mode=train step=2324
2026-04-12 01:51:29,876 | INFO | train_grpo_train | metrics_logged mode=train step=2325
2026-04-12 01:51:34,721 | INFO | train_grpo_train | metrics_logged mode=train step=2326
2026-04-12 01:51:39,092 | INFO | train_grpo_train | metrics_logged mode=train step=2327
2026-04-12 01:51:44,641 | INFO | train_grpo_train | metrics_logged mode=train step=2328
2026-04-12 01:51:49,221 | INFO | train_grpo_train | metrics_logged mode=train step=2329
2026-04-12 01:51:53,718 | INFO | train_grpo_train | metrics_logged mode=train step=2330
2026-04-12 01:51:58,289 | INFO | train_grpo_train | metrics_logged mode=train step=2331
2026-04-12 01:52:02,739 | INFO | train_grpo_train | metrics_logged mode=train step=2332
2026-04-12 01:52:07,416 | INFO | train_grpo_train | metrics_logged mode=train step=2333
2026-04-12 01:52:13,805 | INFO | train_grpo_train | metrics_logged mode=train step=2334
2026-04-12 01:52:18,153 | INFO | train_grpo_train | metrics_logged mode=train step=2335
2026-04-12 01:52:22,744 | INFO | train_grpo_train | metrics_logged mode=train step=2336
2026-04-12 01:52:29,077 | INFO | train_grpo_train | metrics_logged mode=train step=2337
2026-04-12 01:52:33,663 | INFO | train_grpo_train | metrics_logged mode=train step=2338
2026-04-12 01:52:39,022 | INFO | train_grpo_train | metrics_logged mode=train step=2339
2026-04-12 01:52:46,295 | INFO | train_grpo_train | metrics_logged mode=train step=2340
2026-04-12 01:52:53,609 | INFO | train_grpo_train | metrics_logged mode=train step=2341
2026-04-12 01:52:58,022 | INFO | train_grpo_train | metrics_logged mode=train step=2342
2026-04-12 01:53:02,574 | INFO | train_grpo_train | metrics_logged mode=train step=2343
2026-04-12 01:53:07,199 | INFO | train_grpo_train | metrics_logged mode=train step=2344
2026-04-12 01:53:11,920 | INFO | train_grpo_train | metrics_logged mode=train step=2345
2026-04-12 01:53:18,868 | INFO | train_grpo_train | metrics_logged mode=train step=2346
2026-04-12 01:53:24,060 | INFO | train_grpo_train | metrics_logged mode=train step=2347
2026-04-12 01:53:30,021 | INFO | train_grpo_train | metrics_logged mode=train step=2348
2026-04-12 01:53:34,953 | INFO | train_grpo_train | metrics_logged mode=train step=2349
2026-04-12 01:53:41,434 | INFO | train_grpo_train | metrics_logged mode=train step=2350
2026-04-12 01:54:49,201 | INFO | train_grpo_train | metrics_logged mode=eval step=2350
2026-04-12 01:54:56,287 | INFO | train_grpo_train | metrics_logged mode=train step=2351
2026-04-12 01:55:00,982 | INFO | train_grpo_train | metrics_logged mode=train step=2352
2026-04-12 01:55:10,789 | INFO | train_grpo_train | metrics_logged mode=train step=2353
2026-04-12 01:55:15,477 | INFO | train_grpo_train | metrics_logged mode=train step=2354
2026-04-12 01:55:23,150 | INFO | train_grpo_train | metrics_logged mode=train step=2355
2026-04-12 01:55:28,125 | INFO | train_grpo_train | metrics_logged mode=train step=2356
2026-04-12 01:55:33,314 | INFO | train_grpo_train | metrics_logged mode=train step=2357
2026-04-12 01:55:40,957 | INFO | train_grpo_train | metrics_logged mode=train step=2358
2026-04-12 01:55:46,028 | INFO | train_grpo_train | metrics_logged mode=train step=2359
2026-04-12 01:55:50,916 | INFO | train_grpo_train | metrics_logged mode=train step=2360
2026-04-12 01:55:57,680 | INFO | train_grpo_train | metrics_logged mode=train step=2361
2026-04-12 01:56:02,181 | INFO | train_grpo_train | metrics_logged mode=train step=2362
2026-04-12 01:56:07,800 | INFO | train_grpo_train | metrics_logged mode=train step=2363
2026-04-12 01:56:14,065 | INFO | train_grpo_train | metrics_logged mode=train step=2364
2026-04-12 01:56:18,907 | INFO | train_grpo_train | metrics_logged mode=train step=2365
2026-04-12 01:56:25,406 | INFO | train_grpo_train | metrics_logged mode=train step=2366
2026-04-12 01:56:31,598 | INFO | train_grpo_train | metrics_logged mode=train step=2367
2026-04-12 01:56:37,335 | INFO | train_grpo_train | metrics_logged mode=train step=2368
2026-04-12 01:56:42,131 | INFO | train_grpo_train | metrics_logged mode=train step=2369
2026-04-12 01:56:46,390 | INFO | train_grpo_train | metrics_logged mode=train step=2370
2026-04-12 01:56:51,096 | INFO | train_grpo_train | metrics_logged mode=train step=2371
2026-04-12 01:56:56,548 | INFO | train_grpo_train | metrics_logged mode=train step=2372
2026-04-12 01:57:02,040 | INFO | train_grpo_train | metrics_logged mode=train step=2373
2026-04-12 01:57:06,744 | INFO | train_grpo_train | metrics_logged mode=train step=2374
2026-04-12 01:57:14,911 | INFO | train_grpo_train | metrics_logged mode=train step=2375
2026-04-12 01:57:19,632 | INFO | train_grpo_train | metrics_logged mode=train step=2376
2026-04-12 01:57:24,257 | INFO | train_grpo_train | metrics_logged mode=train step=2377
2026-04-12 01:57:30,330 | INFO | train_grpo_train | metrics_logged mode=train step=2378
2026-04-12 01:57:35,693 | INFO | train_grpo_train | metrics_logged mode=train step=2379
2026-04-12 01:57:40,472 | INFO | train_grpo_train | metrics_logged mode=train step=2380
2026-04-12 01:57:46,071 | INFO | train_grpo_train | metrics_logged mode=train step=2381
2026-04-12 01:57:50,930 | INFO | train_grpo_train | metrics_logged mode=train step=2382
2026-04-12 01:57:56,338 | INFO | train_grpo_train | metrics_logged mode=train step=2383
2026-04-12 01:58:01,347 | INFO | train_grpo_train | metrics_logged mode=train step=2384
2026-04-12 01:58:05,510 | INFO | train_grpo_train | metrics_logged mode=train step=2385
2026-04-12 01:58:09,899 | INFO | train_grpo_train | metrics_logged mode=train step=2386
2026-04-12 01:58:14,746 | INFO | train_grpo_train | metrics_logged mode=train step=2387
2026-04-12 01:58:18,983 | INFO | train_grpo_train | metrics_logged mode=train step=2388
2026-04-12 01:58:23,787 | INFO | train_grpo_train | metrics_logged mode=train step=2389
2026-04-12 01:58:28,737 | INFO | train_grpo_train | metrics_logged mode=train step=2390
2026-04-12 01:58:34,028 | INFO | train_grpo_train | metrics_logged mode=train step=2391
2026-04-12 01:58:39,687 | INFO | train_grpo_train | metrics_logged mode=train step=2392
2026-04-12 01:58:44,422 | INFO | train_grpo_train | metrics_logged mode=train step=2393
2026-04-12 01:58:48,931 | INFO | train_grpo_train | metrics_logged mode=train step=2394
2026-04-12 01:58:53,439 | INFO | train_grpo_train | metrics_logged mode=train step=2395
2026-04-12 01:58:58,930 | INFO | train_grpo_train | metrics_logged mode=train step=2396
2026-04-12 01:59:04,315 | INFO | train_grpo_train | metrics_logged mode=train step=2397
2026-04-12 01:59:10,734 | INFO | train_grpo_train | metrics_logged mode=train step=2398
2026-04-12 01:59:15,753 | INFO | train_grpo_train | metrics_logged mode=train step=2399
2026-04-12 01:59:20,788 | INFO | train_grpo_train | metrics_logged mode=train step=2400
2026-04-12 02:00:31,987 | INFO | train_grpo_train | metrics_logged mode=eval step=2400
2026-04-12 02:00:39,299 | INFO | train_grpo_train | metrics_logged mode=train step=2401
2026-04-12 02:00:44,409 | INFO | train_grpo_train | metrics_logged mode=train step=2402
2026-04-12 02:00:49,313 | INFO | train_grpo_train | metrics_logged mode=train step=2403
2026-04-12 02:00:59,665 | INFO | train_grpo_train | metrics_logged mode=train step=2404
2026-04-12 02:01:04,204 | INFO | train_grpo_train | metrics_logged mode=train step=2405
2026-04-12 02:01:08,923 | INFO | train_grpo_train | metrics_logged mode=train step=2406
2026-04-12 02:01:13,672 | INFO | train_grpo_train | metrics_logged mode=train step=2407
2026-04-12 02:01:18,678 | INFO | train_grpo_train | metrics_logged mode=train step=2408
2026-04-12 02:01:24,506 | INFO | train_grpo_train | metrics_logged mode=train step=2409
2026-04-12 02:01:29,237 | INFO | train_grpo_train | metrics_logged mode=train step=2410
2026-04-12 02:01:35,067 | INFO | train_grpo_train | metrics_logged mode=train step=2411
2026-04-12 02:01:40,214 | INFO | train_grpo_train | metrics_logged mode=train step=2412
2026-04-12 02:01:48,873 | INFO | train_grpo_train | metrics_logged mode=train step=2413
2026-04-12 02:01:53,649 | INFO | train_grpo_train | metrics_logged mode=train step=2414
2026-04-12 02:01:58,106 | INFO | train_grpo_train | metrics_logged mode=train step=2415
2026-04-12 02:02:03,260 | INFO | train_grpo_train | metrics_logged mode=train step=2416
2026-04-12 02:02:07,544 | INFO | train_grpo_train | metrics_logged mode=train step=2417
2026-04-12 02:02:12,353 | INFO | train_grpo_train | metrics_logged mode=train step=2418
2026-04-12 02:02:17,563 | INFO | train_grpo_train | metrics_logged mode=train step=2419
2026-04-12 02:02:23,606 | INFO | train_grpo_train | metrics_logged mode=train step=2420
2026-04-12 02:02:28,805 | INFO | train_grpo_train | metrics_logged mode=train step=2421
2026-04-12 02:02:34,269 | INFO | train_grpo_train | metrics_logged mode=train step=2422
2026-04-12 02:02:38,938 | INFO | train_grpo_train | metrics_logged mode=train step=2423
2026-04-12 02:02:48,529 | INFO | train_grpo_train | metrics_logged mode=train step=2424
2026-04-12 02:02:53,600 | INFO | train_grpo_train | metrics_logged mode=train step=2425
2026-04-12 02:02:58,232 | INFO | train_grpo_train | metrics_logged mode=train step=2426
2026-04-12 02:03:02,881 | INFO | train_grpo_train | metrics_logged mode=train step=2427
2026-04-12 02:03:07,032 | INFO | train_grpo_train | metrics_logged mode=train step=2428
2026-04-12 02:03:11,592 | INFO | train_grpo_train | metrics_logged mode=train step=2429
2026-04-12 02:03:16,255 | INFO | train_grpo_train | metrics_logged mode=train step=2430
2026-04-12 02:03:21,567 | INFO | train_grpo_train | metrics_logged mode=train step=2431
2026-04-12 02:03:28,590 | INFO | train_grpo_train | metrics_logged mode=train step=2432
2026-04-12 02:03:34,744 | INFO | train_grpo_train | metrics_logged mode=train step=2433
2026-04-12 02:03:39,422 | INFO | train_grpo_train | metrics_logged mode=train step=2434
2026-04-12 02:03:44,518 | INFO | train_grpo_train | metrics_logged mode=train step=2435
2026-04-12 02:03:49,243 | INFO | train_grpo_train | metrics_logged mode=train step=2436
2026-04-12 02:03:54,361 | INFO | train_grpo_train | metrics_logged mode=train step=2437
2026-04-12 02:03:58,902 | INFO | train_grpo_train | metrics_logged mode=train step=2438
2026-04-12 02:04:04,429 | INFO | train_grpo_train | metrics_logged mode=train step=2439
2026-04-12 02:04:12,542 | INFO | train_grpo_train | metrics_logged mode=train step=2440
2026-04-12 02:04:17,274 | INFO | train_grpo_train | metrics_logged mode=train step=2441
2026-04-12 02:04:21,985 | INFO | train_grpo_train | metrics_logged mode=train step=2442
2026-04-12 02:04:26,972 | INFO | train_grpo_train | metrics_logged mode=train step=2443
2026-04-12 02:04:34,392 | INFO | train_grpo_train | metrics_logged mode=train step=2444
2026-04-12 02:04:38,950 | INFO | train_grpo_train | metrics_logged mode=train step=2445
2026-04-12 02:04:43,974 | INFO | train_grpo_train | metrics_logged mode=train step=2446
2026-04-12 02:04:54,187 | INFO | train_grpo_train | metrics_logged mode=train step=2447
2026-04-12 02:05:02,187 | INFO | train_grpo_train | metrics_logged mode=train step=2448
2026-04-12 02:05:09,860 | INFO | train_grpo_train | metrics_logged mode=train step=2449
2026-04-12 02:05:14,331 | INFO | train_grpo_train | metrics_logged mode=train step=2450
2026-04-12 02:06:29,098 | INFO | train_grpo_train | metrics_logged mode=eval step=2450
2026-04-12 02:06:35,703 | INFO | train_grpo_train | metrics_logged mode=train step=2451
2026-04-12 02:06:40,961 | INFO | train_grpo_train | metrics_logged mode=train step=2452
2026-04-12 02:06:45,828 | INFO | train_grpo_train | metrics_logged mode=train step=2453
2026-04-12 02:06:50,093 | INFO | train_grpo_train | metrics_logged mode=train step=2454
2026-04-12 02:06:54,705 | INFO | train_grpo_train | metrics_logged mode=train step=2455
2026-04-12 02:06:59,395 | INFO | train_grpo_train | metrics_logged mode=train step=2456
2026-04-12 02:07:05,398 | INFO | train_grpo_train | metrics_logged mode=train step=2457
2026-04-12 02:07:09,887 | INFO | train_grpo_train | metrics_logged mode=train step=2458
2026-04-12 02:07:15,692 | INFO | train_grpo_train | metrics_logged mode=train step=2459
2026-04-12 02:07:20,226 | INFO | train_grpo_train | metrics_logged mode=train step=2460
2026-04-12 02:07:29,452 | INFO | train_grpo_train | metrics_logged mode=train step=2461
2026-04-12 02:07:34,201 | INFO | train_grpo_train | metrics_logged mode=train step=2462
2026-04-12 02:07:39,132 | INFO | train_grpo_train | metrics_logged mode=train step=2463
2026-04-12 02:07:44,049 | INFO | train_grpo_train | metrics_logged mode=train step=2464
2026-04-12 02:07:51,105 | INFO | train_grpo_train | metrics_logged mode=train step=2465
2026-04-12 02:07:56,560 | INFO | train_grpo_train | metrics_logged mode=train step=2466
2026-04-12 02:08:01,045 | INFO | train_grpo_train | metrics_logged mode=train step=2467
2026-04-12 02:08:05,084 | INFO | train_grpo_train | metrics_logged mode=train step=2468
2026-04-12 02:08:09,864 | INFO | train_grpo_train | metrics_logged mode=train step=2469
2026-04-12 02:08:15,510 | INFO | train_grpo_train | metrics_logged mode=train step=2470
2026-04-12 02:08:19,589 | INFO | train_grpo_train | metrics_logged mode=train step=2471
2026-04-12 02:08:24,567 | INFO | train_grpo_train | metrics_logged mode=train step=2472
2026-04-12 02:08:28,918 | INFO | train_grpo_train | metrics_logged mode=train step=2473
2026-04-12 02:08:35,322 | INFO | train_grpo_train | metrics_logged mode=train step=2474
2026-04-12 02:08:41,981 | INFO | train_grpo_train | metrics_logged mode=train step=2475
2026-04-12 02:08:46,523 | INFO | train_grpo_train | metrics_logged mode=train step=2476
2026-04-12 02:08:54,861 | INFO | train_grpo_train | metrics_logged mode=train step=2477
2026-04-12 02:08:59,877 | INFO | train_grpo_train | metrics_logged mode=train step=2478
2026-04-12 02:09:04,442 | INFO | train_grpo_train | metrics_logged mode=train step=2479
2026-04-12 02:09:09,578 | INFO | train_grpo_train | metrics_logged mode=train step=2480
2026-04-12 02:09:13,963 | INFO | train_grpo_train | metrics_logged mode=train step=2481
2026-04-12 02:09:18,996 | INFO | train_grpo_train | metrics_logged mode=train step=2482
2026-04-12 02:09:23,397 | INFO | train_grpo_train | metrics_logged mode=train step=2483
2026-04-12 02:09:27,839 | INFO | train_grpo_train | metrics_logged mode=train step=2484
2026-04-12 02:09:36,337 | INFO | train_grpo_train | metrics_logged mode=train step=2485
2026-04-12 02:09:42,075 | INFO | train_grpo_train | metrics_logged mode=train step=2486
2026-04-12 02:09:46,577 | INFO | train_grpo_train | metrics_logged mode=train step=2487
2026-04-12 02:09:51,459 | INFO | train_grpo_train | metrics_logged mode=train step=2488
2026-04-12 02:09:55,629 | INFO | train_grpo_train | metrics_logged mode=train step=2489
2026-04-12 02:10:00,684 | INFO | train_grpo_train | metrics_logged mode=train step=2490
2026-04-12 02:10:05,103 | INFO | train_grpo_train | metrics_logged mode=train step=2491
2026-04-12 02:10:10,322 | INFO | train_grpo_train | metrics_logged mode=train step=2492
2026-04-12 02:10:16,207 | INFO | train_grpo_train | metrics_logged mode=train step=2493
2026-04-12 02:10:20,653 | INFO | train_grpo_train | metrics_logged mode=train step=2494
2026-04-12 02:10:25,530 | INFO | train_grpo_train | metrics_logged mode=train step=2495
2026-04-12 02:10:30,503 | INFO | train_grpo_train | metrics_logged mode=train step=2496
2026-04-12 02:10:36,778 | INFO | train_grpo_train | metrics_logged mode=train step=2497
2026-04-12 02:10:41,801 | INFO | train_grpo_train | metrics_logged mode=train step=2498
2026-04-12 02:10:46,406 | INFO | train_grpo_train | metrics_logged mode=train step=2499
2026-04-12 02:10:51,702 | INFO | train_grpo_train | metrics_logged mode=train step=2500
2026-04-12 02:12:07,245 | INFO | train_grpo_train | metrics_logged mode=eval step=2500
2026-04-12 02:12:14,014 | INFO | train_grpo_train | metrics_logged mode=train step=2501
2026-04-12 02:12:18,820 | INFO | train_grpo_train | metrics_logged mode=train step=2502
2026-04-12 02:12:23,575 | INFO | train_grpo_train | metrics_logged mode=train step=2503
2026-04-12 02:12:28,026 | INFO | train_grpo_train | metrics_logged mode=train step=2504
2026-04-12 02:12:32,739 | INFO | train_grpo_train | metrics_logged mode=train step=2505
2026-04-12 02:12:37,291 | INFO | train_grpo_train | metrics_logged mode=train step=2506
2026-04-12 02:12:41,841 | INFO | train_grpo_train | metrics_logged mode=train step=2507
2026-04-12 02:12:46,386 | INFO | train_grpo_train | metrics_logged mode=train step=2508
2026-04-12 02:12:50,931 | INFO | train_grpo_train | metrics_logged mode=train step=2509
2026-04-12 02:12:55,436 | INFO | train_grpo_train | metrics_logged mode=train step=2510
2026-04-12 02:13:00,401 | INFO | train_grpo_train | metrics_logged mode=train step=2511
2026-04-12 02:13:04,906 | INFO | train_grpo_train | metrics_logged mode=train step=2512
2026-04-12 02:13:10,752 | INFO | train_grpo_train | metrics_logged mode=train step=2513
2026-04-12 02:13:15,247 | INFO | train_grpo_train | metrics_logged mode=train step=2514
2026-04-12 02:13:20,545 | INFO | train_grpo_train | metrics_logged mode=train step=2515
2026-04-12 02:13:25,548 | INFO | train_grpo_train | metrics_logged mode=train step=2516
2026-04-12 02:13:30,298 | INFO | train_grpo_train | metrics_logged mode=train step=2517
2026-04-12 02:13:34,461 | INFO | train_grpo_train | metrics_logged mode=train step=2518
2026-04-12 02:13:39,820 | INFO | train_grpo_train | metrics_logged mode=train step=2519
2026-04-12 02:13:44,110 | INFO | train_grpo_train | metrics_logged mode=train step=2520
2026-04-12 02:13:48,675 | INFO | train_grpo_train | metrics_logged mode=train step=2521
2026-04-12 02:13:53,129 | INFO | train_grpo_train | metrics_logged mode=train step=2522
2026-04-12 02:14:03,220 | INFO | train_grpo_train | metrics_logged mode=train step=2523
2026-04-12 02:14:08,290 | INFO | train_grpo_train | metrics_logged mode=train step=2524
2026-04-12 02:14:14,925 | INFO | train_grpo_train | metrics_logged mode=train step=2525
2026-04-12 02:14:19,335 | INFO | train_grpo_train | metrics_logged mode=train step=2526
2026-04-12 02:14:23,820 | INFO | train_grpo_train | metrics_logged mode=train step=2527
2026-04-12 02:14:33,813 | INFO | train_grpo_train | metrics_logged mode=train step=2528
2026-04-12 02:14:38,949 | INFO | train_grpo_train | metrics_logged mode=train step=2529
2026-04-12 02:14:43,284 | INFO | train_grpo_train | metrics_logged mode=train step=2530
2026-04-12 02:14:48,077 | INFO | train_grpo_train | metrics_logged mode=train step=2531
2026-04-12 02:14:52,790 | INFO | train_grpo_train | metrics_logged mode=train step=2532
2026-04-12 02:14:57,134 | INFO | train_grpo_train | metrics_logged mode=train step=2533
2026-04-12 02:15:02,064 | INFO | train_grpo_train | metrics_logged mode=train step=2534
2026-04-12 02:15:12,891 | INFO | train_grpo_train | metrics_logged mode=train step=2535
2026-04-12 02:15:20,924 | INFO | train_grpo_train | metrics_logged mode=train step=2536
2026-04-12 02:15:25,284 | INFO | train_grpo_train | metrics_logged mode=train step=2537
2026-04-12 02:15:30,026 | INFO | train_grpo_train | metrics_logged mode=train step=2538
2026-04-12 02:15:34,799 | INFO | train_grpo_train | metrics_logged mode=train step=2539
2026-04-12 02:15:41,106 | INFO | train_grpo_train | metrics_logged mode=train step=2540
2026-04-12 02:15:46,175 | INFO | train_grpo_train | metrics_logged mode=train step=2541
2026-04-12 02:15:50,649 | INFO | train_grpo_train | metrics_logged mode=train step=2542
2026-04-12 02:15:59,029 | INFO | train_grpo_train | metrics_logged mode=train step=2543
2026-04-12 02:16:03,331 | INFO | train_grpo_train | metrics_logged mode=train step=2544
2026-04-12 02:16:07,739 | INFO | train_grpo_train | metrics_logged mode=train step=2545
2026-04-12 02:16:12,228 | INFO | train_grpo_train | metrics_logged mode=train step=2546
2026-04-12 02:16:20,075 | INFO | train_grpo_train | metrics_logged mode=train step=2547
2026-04-12 02:16:24,394 | INFO | train_grpo_train | metrics_logged mode=train step=2548
2026-04-12 02:16:30,418 | INFO | train_grpo_train | metrics_logged mode=train step=2549
2026-04-12 02:16:35,053 | INFO | train_grpo_train | metrics_logged mode=train step=2550
2026-04-12 02:17:51,356 | INFO | train_grpo_train | metrics_logged mode=eval step=2550
2026-04-12 02:17:59,907 | INFO | train_grpo_train | metrics_logged mode=train step=2551
2026-04-12 02:18:04,984 | INFO | train_grpo_train | metrics_logged mode=train step=2552
2026-04-12 02:18:09,456 | INFO | train_grpo_train | metrics_logged mode=train step=2553
2026-04-12 02:18:14,618 | INFO | train_grpo_train | metrics_logged mode=train step=2554
2026-04-12 02:18:19,694 | INFO | train_grpo_train | metrics_logged mode=train step=2555
2026-04-12 02:18:25,974 | INFO | train_grpo_train | metrics_logged mode=train step=2556
2026-04-12 02:18:30,774 | INFO | train_grpo_train | metrics_logged mode=train step=2557
2026-04-12 02:18:36,180 | INFO | train_grpo_train | metrics_logged mode=train step=2558
2026-04-12 02:18:40,624 | INFO | train_grpo_train | metrics_logged mode=train step=2559
2026-04-12 02:18:48,782 | INFO | train_grpo_train | metrics_logged mode=train step=2560
2026-04-12 02:18:53,526 | INFO | train_grpo_train | metrics_logged mode=train step=2561
2026-04-12 02:18:57,620 | INFO | train_grpo_train | metrics_logged mode=train step=2562
2026-04-12 02:19:02,375 | INFO | train_grpo_train | metrics_logged mode=train step=2563
2026-04-12 02:19:06,674 | INFO | train_grpo_train | metrics_logged mode=train step=2564
2026-04-12 02:19:10,637 | INFO | train_grpo_train | metrics_logged mode=train step=2565
2026-04-12 02:19:15,433 | INFO | train_grpo_train | metrics_logged mode=train step=2566
2026-04-12 02:19:20,234 | INFO | train_grpo_train | metrics_logged mode=train step=2567
2026-04-12 02:19:25,087 | INFO | train_grpo_train | metrics_logged mode=train step=2568
2026-04-12 02:19:29,332 | INFO | train_grpo_train | metrics_logged mode=train step=2569
2026-04-12 02:19:33,885 | INFO | train_grpo_train | metrics_logged mode=train step=2570
2026-04-12 02:19:38,498 | INFO | train_grpo_train | metrics_logged mode=train step=2571
2026-04-12 02:19:42,746 | INFO | train_grpo_train | metrics_logged mode=train step=2572
2026-04-12 02:19:47,424 | INFO | train_grpo_train | metrics_logged mode=train step=2573
2026-04-12 02:19:52,171 | INFO | train_grpo_train | metrics_logged mode=train step=2574
2026-04-12 02:19:57,561 | INFO | train_grpo_train | metrics_logged mode=train step=2575
2026-04-12 02:20:02,300 | INFO | train_grpo_train | metrics_logged mode=train step=2576
2026-04-12 02:20:06,858 | INFO | train_grpo_train | metrics_logged mode=train step=2577
2026-04-12 02:20:11,777 | INFO | train_grpo_train | metrics_logged mode=train step=2578
2026-04-12 02:20:16,857 | INFO | train_grpo_train | metrics_logged mode=train step=2579
2026-04-12 02:20:21,409 | INFO | train_grpo_train | metrics_logged mode=train step=2580
2026-04-12 02:20:26,044 | INFO | train_grpo_train | metrics_logged mode=train step=2581
2026-04-12 02:20:30,733 | INFO | train_grpo_train | metrics_logged mode=train step=2582
2026-04-12 02:20:36,090 | INFO | train_grpo_train | metrics_logged mode=train step=2583
2026-04-12 02:20:40,552 | INFO | train_grpo_train | metrics_logged mode=train step=2584
2026-04-12 02:20:45,269 | INFO | train_grpo_train | metrics_logged mode=train step=2585
2026-04-12 02:20:53,807 | INFO | train_grpo_train | metrics_logged mode=train step=2586
2026-04-12 02:20:58,926 | INFO | train_grpo_train | metrics_logged mode=train step=2587
2026-04-12 02:21:05,168 | INFO | train_grpo_train | metrics_logged mode=train step=2588
2026-04-12 02:21:09,552 | INFO | train_grpo_train | metrics_logged mode=train step=2589
2026-04-12 02:21:14,295 | INFO | train_grpo_train | metrics_logged mode=train step=2590
2026-04-12 02:21:18,403 | INFO | train_grpo_train | metrics_logged mode=train step=2591
2026-04-12 02:21:23,017 | INFO | train_grpo_train | metrics_logged mode=train step=2592
2026-04-12 02:21:29,735 | INFO | train_grpo_train | metrics_logged mode=train step=2593
2026-04-12 02:21:34,343 | INFO | train_grpo_train | metrics_logged mode=train step=2594
2026-04-12 02:21:41,909 | INFO | train_grpo_train | metrics_logged mode=train step=2595
2026-04-12 02:21:52,099 | INFO | train_grpo_train | metrics_logged mode=train step=2596
2026-04-12 02:21:57,496 | INFO | train_grpo_train | metrics_logged mode=train step=2597
2026-04-12 02:22:01,661 | INFO | train_grpo_train | metrics_logged mode=train step=2598
2026-04-12 02:22:06,709 | INFO | train_grpo_train | metrics_logged mode=train step=2599
2026-04-12 02:22:10,941 | INFO | train_grpo_train | metrics_logged mode=train step=2600
2026-04-12 02:23:28,407 | INFO | train_grpo_train | metrics_logged mode=eval step=2600
2026-04-12 02:23:35,405 | INFO | train_grpo_train | metrics_logged mode=train step=2601
2026-04-12 02:23:40,301 | INFO | train_grpo_train | metrics_logged mode=train step=2602
2026-04-12 02:23:45,112 | INFO | train_grpo_train | metrics_logged mode=train step=2603
2026-04-12 02:23:49,831 | INFO | train_grpo_train | metrics_logged mode=train step=2604
2026-04-12 02:23:54,454 | INFO | train_grpo_train | metrics_logged mode=train step=2605
2026-04-12 02:23:59,854 | INFO | train_grpo_train | metrics_logged mode=train step=2606
2026-04-12 02:24:05,994 | INFO | train_grpo_train | metrics_logged mode=train step=2607
2026-04-12 02:24:11,128 | INFO | train_grpo_train | metrics_logged mode=train step=2608
2026-04-12 02:24:15,654 | INFO | train_grpo_train | metrics_logged mode=train step=2609
2026-04-12 02:24:21,797 | INFO | train_grpo_train | metrics_logged mode=train step=2610
2026-04-12 02:24:28,522 | INFO | train_grpo_train | metrics_logged mode=train step=2611
2026-04-12 02:24:33,044 | INFO | train_grpo_train | metrics_logged mode=train step=2612
2026-04-12 02:24:41,089 | INFO | train_grpo_train | metrics_logged mode=train step=2613
2026-04-12 02:24:46,227 | INFO | train_grpo_train | metrics_logged mode=train step=2614
2026-04-12 02:24:50,876 | INFO | train_grpo_train | metrics_logged mode=train step=2615
2026-04-12 02:24:56,425 | INFO | train_grpo_train | metrics_logged mode=train step=2616
2026-04-12 02:25:01,705 | INFO | train_grpo_train | metrics_logged mode=train step=2617
2026-04-12 02:25:06,093 | INFO | train_grpo_train | metrics_logged mode=train step=2618
2026-04-12 02:25:11,072 | INFO | train_grpo_train | metrics_logged mode=train step=2619
2026-04-12 02:25:18,482 | INFO | train_grpo_train | metrics_logged mode=train step=2620
2026-04-12 02:25:26,677 | INFO | train_grpo_train | metrics_logged mode=train step=2621
2026-04-12 02:25:31,330 | INFO | train_grpo_train | metrics_logged mode=train step=2622
2026-04-12 02:25:36,273 | INFO | train_grpo_train | metrics_logged mode=train step=2623
2026-04-12 02:25:41,005 | INFO | train_grpo_train | metrics_logged mode=train step=2624
2026-04-12 02:25:45,284 | INFO | train_grpo_train | metrics_logged mode=train step=2625
2026-04-12 02:25:50,510 | INFO | train_grpo_train | metrics_logged mode=train step=2626
2026-04-12 02:25:55,132 | INFO | train_grpo_train | metrics_logged mode=train step=2627
2026-04-12 02:26:01,666 | INFO | train_grpo_train | metrics_logged mode=train step=2628
2026-04-12 02:26:09,446 | INFO | train_grpo_train | metrics_logged mode=train step=2629
2026-04-12 02:26:13,830 | INFO | train_grpo_train | metrics_logged mode=train step=2630
2026-04-12 02:26:19,247 | INFO | train_grpo_train | metrics_logged mode=train step=2631
2026-04-12 02:26:23,765 | INFO | train_grpo_train | metrics_logged mode=train step=2632
2026-04-12 02:26:29,024 | INFO | train_grpo_train | metrics_logged mode=train step=2633
2026-04-12 02:26:33,591 | INFO | train_grpo_train | metrics_logged mode=train step=2634
2026-04-12 02:26:38,107 | INFO | train_grpo_train | metrics_logged mode=train step=2635
2026-04-12 02:26:43,055 | INFO | train_grpo_train | metrics_logged mode=train step=2636
2026-04-12 02:26:48,212 | INFO | train_grpo_train | metrics_logged mode=train step=2637
2026-04-12 02:26:52,460 | INFO | train_grpo_train | metrics_logged mode=train step=2638
2026-04-12 02:26:57,522 | INFO | train_grpo_train | metrics_logged mode=train step=2639
2026-04-12 02:27:02,016 | INFO | train_grpo_train | metrics_logged mode=train step=2640
2026-04-12 02:27:06,390 | INFO | train_grpo_train | metrics_logged mode=train step=2641
2026-04-12 02:27:10,755 | INFO | train_grpo_train | metrics_logged mode=train step=2642
2026-04-12 02:27:14,995 | INFO | train_grpo_train | metrics_logged mode=train step=2643
2026-04-12 02:27:19,801 | INFO | train_grpo_train | metrics_logged mode=train step=2644
2026-04-12 02:27:24,174 | INFO | train_grpo_train | metrics_logged mode=train step=2645
2026-04-12 02:27:28,133 | INFO | train_grpo_train | metrics_logged mode=train step=2646
2026-04-12 02:27:34,209 | INFO | train_grpo_train | metrics_logged mode=train step=2647
2026-04-12 02:27:39,553 | INFO | train_grpo_train | metrics_logged mode=train step=2648
2026-04-12 02:27:44,086 | INFO | train_grpo_train | metrics_logged mode=train step=2649
2026-04-12 02:27:48,754 | INFO | train_grpo_train | metrics_logged mode=train step=2650
2026-04-12 02:29:02,253 | INFO | train_grpo_train | metrics_logged mode=eval step=2650
2026-04-12 02:29:12,331 | INFO | train_grpo_train | metrics_logged mode=train step=2651
2026-04-12 02:29:17,948 | INFO | train_grpo_train | metrics_logged mode=train step=2652
2026-04-12 02:29:26,900 | INFO | train_grpo_train | metrics_logged mode=train step=2653
2026-04-12 02:29:31,628 | INFO | train_grpo_train | metrics_logged mode=train step=2654
2026-04-12 02:29:36,257 | INFO | train_grpo_train | metrics_logged mode=train step=2655
2026-04-12 02:29:40,753 | INFO | train_grpo_train | metrics_logged mode=train step=2656
2026-04-12 02:29:45,393 | INFO | train_grpo_train | metrics_logged mode=train step=2657
2026-04-12 02:29:49,857 | INFO | train_grpo_train | metrics_logged mode=train step=2658
2026-04-12 02:29:53,938 | INFO | train_grpo_train | metrics_logged mode=train step=2659
2026-04-12 02:29:58,661 | INFO | train_grpo_train | metrics_logged mode=train step=2660
2026-04-12 02:30:03,138 | INFO | train_grpo_train | metrics_logged mode=train step=2661
2026-04-12 02:30:07,485 | INFO | train_grpo_train | metrics_logged mode=train step=2662
2026-04-12 02:30:12,464 | INFO | train_grpo_train | metrics_logged mode=train step=2663
2026-04-12 02:30:17,128 | INFO | train_grpo_train | metrics_logged mode=train step=2664
2026-04-12 02:30:21,766 | INFO | train_grpo_train | metrics_logged mode=train step=2665
2026-04-12 02:30:26,241 | INFO | train_grpo_train | metrics_logged mode=train step=2666
2026-04-12 02:30:31,186 | INFO | train_grpo_train | metrics_logged mode=train step=2667
2026-04-12 02:30:35,417 | INFO | train_grpo_train | metrics_logged mode=train step=2668
2026-04-12 02:30:40,951 | INFO | train_grpo_train | metrics_logged mode=train step=2669
2026-04-12 02:30:45,533 | INFO | train_grpo_train | metrics_logged mode=train step=2670
2026-04-12 02:30:50,034 | INFO | train_grpo_train | metrics_logged mode=train step=2671
2026-04-12 02:30:58,127 | INFO | train_grpo_train | metrics_logged mode=train step=2672
2026-04-12 02:31:02,893 | INFO | train_grpo_train | metrics_logged mode=train step=2673
2026-04-12 02:31:09,995 | INFO | train_grpo_train | metrics_logged mode=train step=2674
2026-04-12 02:31:18,132 | INFO | train_grpo_train | metrics_logged mode=train step=2675
2026-04-12 02:31:22,540 | INFO | train_grpo_train | metrics_logged mode=train step=2676
2026-04-12 02:31:28,713 | INFO | train_grpo_train | metrics_logged mode=train step=2677
2026-04-12 02:31:33,775 | INFO | train_grpo_train | metrics_logged mode=train step=2678
2026-04-12 02:31:38,467 | INFO | train_grpo_train | metrics_logged mode=train step=2679
2026-04-12 02:31:43,375 | INFO | train_grpo_train | metrics_logged mode=train step=2680
2026-04-12 02:31:48,752 | INFO | train_grpo_train | metrics_logged mode=train step=2681
2026-04-12 02:31:53,634 | INFO | train_grpo_train | metrics_logged mode=train step=2682
2026-04-12 02:31:57,961 | INFO | train_grpo_train | metrics_logged mode=train step=2683
2026-04-12 02:32:02,174 | INFO | train_grpo_train | metrics_logged mode=train step=2684
2026-04-12 02:32:06,620 | INFO | train_grpo_train | metrics_logged mode=train step=2685
2026-04-12 02:32:10,774 | INFO | train_grpo_train | metrics_logged mode=train step=2686
2026-04-12 02:32:20,748 | INFO | train_grpo_train | metrics_logged mode=train step=2687
2026-04-12 02:32:26,174 | INFO | train_grpo_train | metrics_logged mode=train step=2688
2026-04-12 02:32:31,440 | INFO | train_grpo_train | metrics_logged mode=train step=2689
2026-04-12 02:32:35,867 | INFO | train_grpo_train | metrics_logged mode=train step=2690
2026-04-12 02:32:41,593 | INFO | train_grpo_train | metrics_logged mode=train step=2691
2026-04-12 02:32:46,098 | INFO | train_grpo_train | metrics_logged mode=train step=2692
2026-04-12 02:32:50,831 | INFO | train_grpo_train | metrics_logged mode=train step=2693
2026-04-12 02:32:55,338 | INFO | train_grpo_train | metrics_logged mode=train step=2694
2026-04-12 02:32:59,861 | INFO | train_grpo_train | metrics_logged mode=train step=2695
2026-04-12 02:33:04,526 | INFO | train_grpo_train | metrics_logged mode=train step=2696
2026-04-12 02:33:10,273 | INFO | train_grpo_train | metrics_logged mode=train step=2697
2026-04-12 02:33:14,963 | INFO | train_grpo_train | metrics_logged mode=train step=2698
2026-04-12 02:33:19,154 | INFO | train_grpo_train | metrics_logged mode=train step=2699
2026-04-12 02:33:23,802 | INFO | train_grpo_train | metrics_logged mode=train step=2700
2026-04-12 02:34:38,749 | INFO | train_grpo_train | metrics_logged mode=eval step=2700
2026-04-12 02:34:45,680 | INFO | train_grpo_train | metrics_logged mode=train step=2701
2026-04-12 02:34:50,424 | INFO | train_grpo_train | metrics_logged mode=train step=2702
2026-04-12 02:34:56,901 | INFO | train_grpo_train | metrics_logged mode=train step=2703
2026-04-12 02:35:01,506 | INFO | train_grpo_train | metrics_logged mode=train step=2704
2026-04-12 02:35:05,965 | INFO | train_grpo_train | metrics_logged mode=train step=2705
2026-04-12 02:35:10,063 | INFO | train_grpo_train | metrics_logged mode=train step=2706
2026-04-12 02:35:14,369 | INFO | train_grpo_train | metrics_logged mode=train step=2707
2026-04-12 02:35:19,444 | INFO | train_grpo_train | metrics_logged mode=train step=2708
2026-04-12 02:35:24,551 | INFO | train_grpo_train | metrics_logged mode=train step=2709
2026-04-12 02:35:29,967 | INFO | train_grpo_train | metrics_logged mode=train step=2710
2026-04-12 02:35:34,455 | INFO | train_grpo_train | metrics_logged mode=train step=2711
2026-04-12 02:35:38,818 | INFO | train_grpo_train | metrics_logged mode=train step=2712
2026-04-12 02:35:43,197 | INFO | train_grpo_train | metrics_logged mode=train step=2713
2026-04-12 02:35:47,898 | INFO | train_grpo_train | metrics_logged mode=train step=2714
2026-04-12 02:35:53,521 | INFO | train_grpo_train | metrics_logged mode=train step=2715
2026-04-12 02:36:02,824 | INFO | train_grpo_train | metrics_logged mode=train step=2716
2026-04-12 02:36:08,102 | INFO | train_grpo_train | metrics_logged mode=train step=2717
2026-04-12 02:36:15,603 | INFO | train_grpo_train | metrics_logged mode=train step=2718
2026-04-12 02:36:19,719 | INFO | train_grpo_train | metrics_logged mode=train step=2719
2026-04-12 02:36:24,715 | INFO | train_grpo_train | metrics_logged mode=train step=2720
2026-04-12 02:36:29,378 | INFO | train_grpo_train | metrics_logged mode=train step=2721
2026-04-12 02:36:34,000 | INFO | train_grpo_train | metrics_logged mode=train step=2722
2026-04-12 02:36:40,656 | INFO | train_grpo_train | metrics_logged mode=train step=2723
2026-04-12 02:36:45,202 | INFO | train_grpo_train | metrics_logged mode=train step=2724
2026-04-12 02:36:49,854 | INFO | train_grpo_train | metrics_logged mode=train step=2725
2026-04-12 02:36:54,905 | INFO | train_grpo_train | metrics_logged mode=train step=2726
2026-04-12 02:36:59,508 | INFO | train_grpo_train | metrics_logged mode=train step=2727
2026-04-12 02:37:03,594 | INFO | train_grpo_train | metrics_logged mode=train step=2728
2026-04-12 02:37:11,638 | INFO | train_grpo_train | metrics_logged mode=train step=2729
2026-04-12 02:37:15,993 | INFO | train_grpo_train | metrics_logged mode=train step=2730
2026-04-12 02:37:20,458 | INFO | train_grpo_train | metrics_logged mode=train step=2731
2026-04-12 02:37:24,578 | INFO | train_grpo_train | metrics_logged mode=train step=2732
2026-04-12 02:37:28,858 | INFO | train_grpo_train | metrics_logged mode=train step=2733
2026-04-12 02:37:35,923 | INFO | train_grpo_train | metrics_logged mode=train step=2734
2026-04-12 02:37:40,524 | INFO | train_grpo_train | metrics_logged mode=train step=2735
2026-04-12 02:37:45,629 | INFO | train_grpo_train | metrics_logged mode=train step=2736
2026-04-12 02:37:50,388 | INFO | train_grpo_train | metrics_logged mode=train step=2737
2026-04-12 02:37:55,163 | INFO | train_grpo_train | metrics_logged mode=train step=2738
2026-04-12 02:37:59,447 | INFO | train_grpo_train | metrics_logged mode=train step=2739
2026-04-12 02:38:03,919 | INFO | train_grpo_train | metrics_logged mode=train step=2740
2026-04-12 02:38:08,840 | INFO | train_grpo_train | metrics_logged mode=train step=2741
2026-04-12 02:38:13,846 | INFO | train_grpo_train | metrics_logged mode=train step=2742
2026-04-12 02:38:18,535 | INFO | train_grpo_train | metrics_logged mode=train step=2743
2026-04-12 02:38:26,129 | INFO | train_grpo_train | metrics_logged mode=train step=2744
2026-04-12 02:38:36,304 | INFO | train_grpo_train | metrics_logged mode=train step=2745
2026-04-12 02:38:40,725 | INFO | train_grpo_train | metrics_logged mode=train step=2746
2026-04-12 02:38:45,326 | INFO | train_grpo_train | metrics_logged mode=train step=2747
2026-04-12 02:38:52,900 | INFO | train_grpo_train | metrics_logged mode=train step=2748
2026-04-12 02:38:57,975 | INFO | train_grpo_train | metrics_logged mode=train step=2749
2026-04-12 02:39:02,961 | INFO | train_grpo_train | metrics_logged mode=train step=2750
2026-04-12 02:40:19,435 | INFO | train_grpo_train | metrics_logged mode=eval step=2750
2026-04-12 02:40:29,786 | INFO | train_grpo_train | metrics_logged mode=train step=2751
2026-04-12 02:40:38,301 | INFO | train_grpo_train | metrics_logged mode=train step=2752
2026-04-12 02:40:43,875 | INFO | train_grpo_train | metrics_logged mode=train step=2753
2026-04-12 02:40:54,921 | INFO | train_grpo_train | metrics_logged mode=train step=2754
2026-04-12 02:41:00,857 | INFO | train_grpo_train | metrics_logged mode=train step=2755
2026-04-12 02:41:07,795 | INFO | train_grpo_train | metrics_logged mode=train step=2756
2026-04-12 02:41:16,030 | INFO | train_grpo_train | metrics_logged mode=train step=2757
2026-04-12 02:41:21,101 | INFO | train_grpo_train | metrics_logged mode=train step=2758
2026-04-12 02:41:29,711 | INFO | train_grpo_train | metrics_logged mode=train step=2759
2026-04-12 02:41:34,190 | INFO | train_grpo_train | metrics_logged mode=train step=2760
2026-04-12 02:41:42,480 | INFO | train_grpo_train | metrics_logged mode=train step=2761
2026-04-12 02:41:47,345 | INFO | train_grpo_train | metrics_logged mode=train step=2762
2026-04-12 02:41:52,507 | INFO | train_grpo_train | metrics_logged mode=train step=2763
2026-04-12 02:41:57,481 | INFO | train_grpo_train | metrics_logged mode=train step=2764
2026-04-12 02:42:03,065 | INFO | train_grpo_train | metrics_logged mode=train step=2765
2026-04-12 02:42:08,455 | INFO | train_grpo_train | metrics_logged mode=train step=2766
2026-04-12 02:42:15,249 | INFO | train_grpo_train | metrics_logged mode=train step=2767
2026-04-12 02:42:20,699 | INFO | train_grpo_train | metrics_logged mode=train step=2768
2026-04-12 02:42:30,943 | INFO | train_grpo_train | metrics_logged mode=train step=2769
2026-04-12 02:42:35,628 | INFO | train_grpo_train | metrics_logged mode=train step=2770
2026-04-12 02:42:41,047 | INFO | train_grpo_train | metrics_logged mode=train step=2771
2026-04-12 02:42:45,737 | INFO | train_grpo_train | metrics_logged mode=train step=2772
2026-04-12 02:42:50,223 | INFO | train_grpo_train | metrics_logged mode=train step=2773
2026-04-12 02:42:56,160 | INFO | train_grpo_train | metrics_logged mode=train step=2774
2026-04-12 02:43:00,993 | INFO | train_grpo_train | metrics_logged mode=train step=2775
2026-04-12 02:43:05,597 | INFO | train_grpo_train | metrics_logged mode=train step=2776
2026-04-12 02:43:10,413 | INFO | train_grpo_train | metrics_logged mode=train step=2777
2026-04-12 02:43:15,747 | INFO | train_grpo_train | metrics_logged mode=train step=2778
2026-04-12 02:43:20,964 | INFO | train_grpo_train | metrics_logged mode=train step=2779
2026-04-12 02:43:28,925 | INFO | train_grpo_train | metrics_logged mode=train step=2780
2026-04-12 02:43:33,307 | INFO | train_grpo_train | metrics_logged mode=train step=2781
2026-04-12 02:43:38,363 | INFO | train_grpo_train | metrics_logged mode=train step=2782
2026-04-12 02:43:42,770 | INFO | train_grpo_train | metrics_logged mode=train step=2783
2026-04-12 02:43:47,212 | INFO | train_grpo_train | metrics_logged mode=train step=2784
2026-04-12 02:43:52,101 | INFO | train_grpo_train | metrics_logged mode=train step=2785
2026-04-12 02:43:56,252 | INFO | train_grpo_train | metrics_logged mode=train step=2786
2026-04-12 02:44:00,359 | INFO | train_grpo_train | metrics_logged mode=train step=2787
2026-04-12 02:44:05,406 | INFO | train_grpo_train | metrics_logged mode=train step=2788
2026-04-12 02:44:09,756 | INFO | train_grpo_train | metrics_logged mode=train step=2789
2026-04-12 02:44:13,918 | INFO | train_grpo_train | metrics_logged mode=train step=2790
2026-04-12 02:44:18,733 | INFO | train_grpo_train | metrics_logged mode=train step=2791
2026-04-12 02:44:25,337 | INFO | train_grpo_train | metrics_logged mode=train step=2792
2026-04-12 02:44:30,195 | INFO | train_grpo_train | metrics_logged mode=train step=2793
2026-04-12 02:44:34,909 | INFO | train_grpo_train | metrics_logged mode=train step=2794
2026-04-12 02:44:40,197 | INFO | train_grpo_train | metrics_logged mode=train step=2795
2026-04-12 02:44:50,020 | INFO | train_grpo_train | metrics_logged mode=train step=2796
2026-04-12 02:44:54,622 | INFO | train_grpo_train | metrics_logged mode=train step=2797
2026-04-12 02:44:59,940 | INFO | train_grpo_train | metrics_logged mode=train step=2798
2026-04-12 02:45:10,197 | INFO | train_grpo_train | metrics_logged mode=train step=2799
2026-04-12 02:45:17,458 | INFO | train_grpo_train | metrics_logged mode=train step=2800
2026-04-12 02:46:35,700 | INFO | train_grpo_train | metrics_logged mode=eval step=2800
2026-04-12 02:46:43,625 | INFO | train_grpo_train | metrics_logged mode=train step=2801
2026-04-12 02:46:49,160 | INFO | train_grpo_train | metrics_logged mode=train step=2802
2026-04-12 02:46:53,763 | INFO | train_grpo_train | metrics_logged mode=train step=2803
2026-04-12 02:47:00,389 | INFO | train_grpo_train | metrics_logged mode=train step=2804
2026-04-12 02:47:05,522 | INFO | train_grpo_train | metrics_logged mode=train step=2805
2026-04-12 02:47:09,845 | INFO | train_grpo_train | metrics_logged mode=train step=2806
2026-04-12 02:47:15,057 | INFO | train_grpo_train | metrics_logged mode=train step=2807
2026-04-12 02:47:19,980 | INFO | train_grpo_train | metrics_logged mode=train step=2808
2026-04-12 02:47:24,559 | INFO | train_grpo_train | metrics_logged mode=train step=2809
2026-04-12 02:47:28,879 | INFO | train_grpo_train | metrics_logged mode=train step=2810
2026-04-12 02:47:33,613 | INFO | train_grpo_train | metrics_logged mode=train step=2811
2026-04-12 02:47:37,877 | INFO | train_grpo_train | metrics_logged mode=train step=2812
2026-04-12 02:47:47,082 | INFO | train_grpo_train | metrics_logged mode=train step=2813
2026-04-12 02:47:52,425 | INFO | train_grpo_train | metrics_logged mode=train step=2814
2026-04-12 02:47:56,686 | INFO | train_grpo_train | metrics_logged mode=train step=2815
2026-04-12 02:48:01,597 | INFO | train_grpo_train | metrics_logged mode=train step=2816
2026-04-12 02:48:06,098 | INFO | train_grpo_train | metrics_logged mode=train step=2817
2026-04-12 02:48:12,224 | INFO | train_grpo_train | metrics_logged mode=train step=2818
2026-04-12 02:48:17,147 | INFO | train_grpo_train | metrics_logged mode=train step=2819
2026-04-12 02:48:21,565 | INFO | train_grpo_train | metrics_logged mode=train step=2820
2026-04-12 02:48:26,085 | INFO | train_grpo_train | metrics_logged mode=train step=2821
2026-04-12 02:48:31,654 | INFO | train_grpo_train | metrics_logged mode=train step=2822
2026-04-12 02:48:35,969 | INFO | train_grpo_train | metrics_logged mode=train step=2823
2026-04-12 02:48:40,574 | INFO | train_grpo_train | metrics_logged mode=train step=2824
2026-04-12 02:48:45,703 | INFO | train_grpo_train | metrics_logged mode=train step=2825
2026-04-12 02:48:50,262 | INFO | train_grpo_train | metrics_logged mode=train step=2826
2026-04-12 02:48:56,542 | INFO | train_grpo_train | metrics_logged mode=train step=2827
2026-04-12 02:49:01,041 | INFO | train_grpo_train | metrics_logged mode=train step=2828
2026-04-12 02:49:06,021 | INFO | train_grpo_train | metrics_logged mode=train step=2829
2026-04-12 02:49:11,769 | INFO | train_grpo_train | metrics_logged mode=train step=2830
2026-04-12 02:49:16,932 | INFO | train_grpo_train | metrics_logged mode=train step=2831
2026-04-12 02:49:21,534 | INFO | train_grpo_train | metrics_logged mode=train step=2832
2026-04-12 02:49:25,740 | INFO | train_grpo_train | metrics_logged mode=train step=2833
2026-04-12 02:49:31,338 | INFO | train_grpo_train | metrics_logged mode=train step=2834
2026-04-12 02:49:35,774 | INFO | train_grpo_train | metrics_logged mode=train step=2835
2026-04-12 02:49:40,631 | INFO | train_grpo_train | metrics_logged mode=train step=2836
2026-04-12 02:49:46,193 | INFO | train_grpo_train | metrics_logged mode=train step=2837
2026-04-12 02:49:51,610 | INFO | train_grpo_train | metrics_logged mode=train step=2838
2026-04-12 02:49:56,101 | INFO | train_grpo_train | metrics_logged mode=train step=2839
2026-04-12 02:50:01,019 | INFO | train_grpo_train | metrics_logged mode=train step=2840
2026-04-12 02:50:05,354 | INFO | train_grpo_train | metrics_logged mode=train step=2841
2026-04-12 02:50:09,713 | INFO | train_grpo_train | metrics_logged mode=train step=2842
2026-04-12 02:50:14,118 | INFO | train_grpo_train | metrics_logged mode=train step=2843
2026-04-12 02:50:18,429 | INFO | train_grpo_train | metrics_logged mode=train step=2844
2026-04-12 02:50:22,697 | INFO | train_grpo_train | metrics_logged mode=train step=2845
2026-04-12 02:50:28,522 | INFO | train_grpo_train | metrics_logged mode=train step=2846
2026-04-12 02:50:33,154 | INFO | train_grpo_train | metrics_logged mode=train step=2847
2026-04-12 02:50:37,200 | INFO | train_grpo_train | metrics_logged mode=train step=2848
2026-04-12 02:50:42,635 | INFO | train_grpo_train | metrics_logged mode=train step=2849
2026-04-12 02:50:46,855 | INFO | train_grpo_train | metrics_logged mode=train step=2850
2026-04-12 02:52:04,188 | INFO | train_grpo_train | metrics_logged mode=eval step=2850
2026-04-12 02:52:14,502 | INFO | train_grpo_train | metrics_logged mode=train step=2851
2026-04-12 02:52:19,238 | INFO | train_grpo_train | metrics_logged mode=train step=2852
2026-04-12 02:52:24,006 | INFO | train_grpo_train | metrics_logged mode=train step=2853
2026-04-12 02:52:29,265 | INFO | train_grpo_train | metrics_logged mode=train step=2854
2026-04-12 02:52:33,706 | INFO | train_grpo_train | metrics_logged mode=train step=2855
2026-04-12 02:52:38,569 | INFO | train_grpo_train | metrics_logged mode=train step=2856
2026-04-12 02:52:42,974 | INFO | train_grpo_train | metrics_logged mode=train step=2857
2026-04-12 02:52:50,251 | INFO | train_grpo_train | metrics_logged mode=train step=2858
2026-04-12 02:52:54,715 | INFO | train_grpo_train | metrics_logged mode=train step=2859
2026-04-12 02:52:59,138 | INFO | train_grpo_train | metrics_logged mode=train step=2860
2026-04-12 02:53:03,097 | INFO | train_grpo_train | metrics_logged mode=train step=2861
2026-04-12 02:53:09,263 | INFO | train_grpo_train | metrics_logged mode=train step=2862
2026-04-12 02:53:13,702 | INFO | train_grpo_train | metrics_logged mode=train step=2863
2026-04-12 02:53:19,304 | INFO | train_grpo_train | metrics_logged mode=train step=2864
2026-04-12 02:53:28,700 | INFO | train_grpo_train | metrics_logged mode=train step=2865
2026-04-12 02:53:32,679 | INFO | train_grpo_train | metrics_logged mode=train step=2866
2026-04-12 02:53:37,106 | INFO | train_grpo_train | metrics_logged mode=train step=2867
2026-04-12 02:53:41,726 | INFO | train_grpo_train | metrics_logged mode=train step=2868
2026-04-12 02:53:46,574 | INFO | train_grpo_train | metrics_logged mode=train step=2869
2026-04-12 02:53:50,902 | INFO | train_grpo_train | metrics_logged mode=train step=2870
2026-04-12 02:53:55,551 | INFO | train_grpo_train | metrics_logged mode=train step=2871
2026-04-12 02:54:02,185 | INFO | train_grpo_train | metrics_logged mode=train step=2872
2026-04-12 02:54:06,596 | INFO | train_grpo_train | metrics_logged mode=train step=2873
2026-04-12 02:54:10,712 | INFO | train_grpo_train | metrics_logged mode=train step=2874
2026-04-12 02:54:15,180 | INFO | train_grpo_train | metrics_logged mode=train step=2875
2026-04-12 02:54:19,491 | INFO | train_grpo_train | metrics_logged mode=train step=2876
2026-04-12 02:54:24,679 | INFO | train_grpo_train | metrics_logged mode=train step=2877
2026-04-12 02:54:32,157 | INFO | train_grpo_train | metrics_logged mode=train step=2878
2026-04-12 02:54:37,052 | INFO | train_grpo_train | metrics_logged mode=train step=2879
2026-04-12 02:54:42,463 | INFO | train_grpo_train | metrics_logged mode=train step=2880
2026-04-12 02:54:47,451 | INFO | train_grpo_train | metrics_logged mode=train step=2881
2026-04-12 02:54:51,908 | INFO | train_grpo_train | metrics_logged mode=train step=2882
2026-04-12 02:54:57,384 | INFO | train_grpo_train | metrics_logged mode=train step=2883
2026-04-12 02:55:01,898 | INFO | train_grpo_train | metrics_logged mode=train step=2884
2026-04-12 02:55:06,492 | INFO | train_grpo_train | metrics_logged mode=train step=2885
2026-04-12 02:55:11,098 | INFO | train_grpo_train | metrics_logged mode=train step=2886
2026-04-12 02:55:15,669 | INFO | train_grpo_train | metrics_logged mode=train step=2887
2026-04-12 02:55:20,683 | INFO | train_grpo_train | metrics_logged mode=train step=2888
2026-04-12 02:55:25,448 | INFO | train_grpo_train | metrics_logged mode=train step=2889
2026-04-12 02:55:30,256 | INFO | train_grpo_train | metrics_logged mode=train step=2890
2026-04-12 02:55:35,206 | INFO | train_grpo_train | metrics_logged mode=train step=2891
2026-04-12 02:55:39,252 | INFO | train_grpo_train | metrics_logged mode=train step=2892
2026-04-12 02:55:43,586 | INFO | train_grpo_train | metrics_logged mode=train step=2893
2026-04-12 02:55:49,181 | INFO | train_grpo_train | metrics_logged mode=train step=2894
2026-04-12 02:55:54,290 | INFO | train_grpo_train | metrics_logged mode=train step=2895
2026-04-12 02:55:58,539 | INFO | train_grpo_train | metrics_logged mode=train step=2896
2026-04-12 02:56:03,595 | INFO | train_grpo_train | metrics_logged mode=train step=2897
2026-04-12 02:56:07,990 | INFO | train_grpo_train | metrics_logged mode=train step=2898
2026-04-12 02:56:12,410 | INFO | train_grpo_train | metrics_logged mode=train step=2899
2026-04-12 02:56:16,806 | INFO | train_grpo_train | metrics_logged mode=train step=2900
2026-04-12 02:57:35,316 | INFO | train_grpo_train | metrics_logged mode=eval step=2900
2026-04-12 02:57:42,905 | INFO | train_grpo_train | metrics_logged mode=train step=2901
2026-04-12 02:57:53,192 | INFO | train_grpo_train | metrics_logged mode=train step=2902
2026-04-12 02:58:01,499 | INFO | train_grpo_train | metrics_logged mode=train step=2903
2026-04-12 02:58:06,042 | INFO | train_grpo_train | metrics_logged mode=train step=2904
2026-04-12 02:58:10,877 | INFO | train_grpo_train | metrics_logged mode=train step=2905
2026-04-12 02:58:15,217 | INFO | train_grpo_train | metrics_logged mode=train step=2906
2026-04-12 02:58:19,506 | INFO | train_grpo_train | metrics_logged mode=train step=2907
2026-04-12 02:58:23,618 | INFO | train_grpo_train | metrics_logged mode=train step=2908
2026-04-12 02:58:31,258 | INFO | train_grpo_train | metrics_logged mode=train step=2909
2026-04-12 02:58:35,304 | INFO | train_grpo_train | metrics_logged mode=train step=2910
2026-04-12 02:58:39,626 | INFO | train_grpo_train | metrics_logged mode=train step=2911
2026-04-12 02:58:43,990 | INFO | train_grpo_train | metrics_logged mode=train step=2912
2026-04-12 02:58:48,475 | INFO | train_grpo_train | metrics_logged mode=train step=2913
2026-04-12 02:58:55,853 | INFO | train_grpo_train | metrics_logged mode=train step=2914
2026-04-12 02:59:02,931 | INFO | train_grpo_train | metrics_logged mode=train step=2915
2026-04-12 02:59:09,063 | INFO | train_grpo_train | metrics_logged mode=train step=2916
2026-04-12 02:59:13,857 | INFO | train_grpo_train | metrics_logged mode=train step=2917
2026-04-12 02:59:18,912 | INFO | train_grpo_train | metrics_logged mode=train step=2918
2026-04-12 02:59:23,953 | INFO | train_grpo_train | metrics_logged mode=train step=2919
2026-04-12 02:59:29,010 | INFO | train_grpo_train | metrics_logged mode=train step=2920
2026-04-12 02:59:33,396 | INFO | train_grpo_train | metrics_logged mode=train step=2921
2026-04-12 02:59:37,714 | INFO | train_grpo_train | metrics_logged mode=train step=2922
2026-04-12 02:59:43,570 | INFO | train_grpo_train | metrics_logged mode=train step=2923
2026-04-12 02:59:48,092 | INFO | train_grpo_train | metrics_logged mode=train step=2924
2026-04-12 02:59:53,590 | INFO | train_grpo_train | metrics_logged mode=train step=2925
2026-04-12 02:59:59,904 | INFO | train_grpo_train | metrics_logged mode=train step=2926
2026-04-12 03:00:04,007 | INFO | train_grpo_train | metrics_logged mode=train step=2927
2026-04-12 03:00:10,488 | INFO | train_grpo_train | metrics_logged mode=train step=2928
2026-04-12 03:00:14,926 | INFO | train_grpo_train | metrics_logged mode=train step=2929
2026-04-12 03:00:19,373 | INFO | train_grpo_train | metrics_logged mode=train step=2930
2026-04-12 03:00:23,947 | INFO | train_grpo_train | metrics_logged mode=train step=2931
2026-04-12 03:00:27,968 | INFO | train_grpo_train | metrics_logged mode=train step=2932
2026-04-12 03:00:32,358 | INFO | train_grpo_train | metrics_logged mode=train step=2933
2026-04-12 03:00:37,029 | INFO | train_grpo_train | metrics_logged mode=train step=2934
2026-04-12 03:00:41,885 | INFO | train_grpo_train | metrics_logged mode=train step=2935
2026-04-12 03:00:52,012 | INFO | train_grpo_train | metrics_logged mode=train step=2936
2026-04-12 03:00:56,631 | INFO | train_grpo_train | metrics_logged mode=train step=2937
2026-04-12 03:01:00,664 | INFO | train_grpo_train | metrics_logged mode=train step=2938
2026-04-12 03:01:04,743 | INFO | train_grpo_train | metrics_logged mode=train step=2939
2026-04-12 03:01:12,497 | INFO | train_grpo_train | metrics_logged mode=train step=2940
2026-04-12 03:01:18,260 | INFO | train_grpo_train | metrics_logged mode=train step=2941
2026-04-12 03:01:25,424 | INFO | train_grpo_train | metrics_logged mode=train step=2942
2026-04-12 03:01:32,695 | INFO | train_grpo_train | metrics_logged mode=train step=2943
2026-04-12 03:01:37,215 | INFO | train_grpo_train | metrics_logged mode=train step=2944
2026-04-12 03:01:42,044 | INFO | train_grpo_train | metrics_logged mode=train step=2945
2026-04-12 03:01:46,528 | INFO | train_grpo_train | metrics_logged mode=train step=2946
2026-04-12 03:01:51,860 | INFO | train_grpo_train | metrics_logged mode=train step=2947
2026-04-12 03:01:56,728 | INFO | train_grpo_train | metrics_logged mode=train step=2948
2026-04-12 03:02:02,193 | INFO | train_grpo_train | metrics_logged mode=train step=2949
2026-04-12 03:02:07,356 | INFO | train_grpo_train | metrics_logged mode=train step=2950
2026-04-12 03:03:22,934 | INFO | train_grpo_train | metrics_logged mode=eval step=2950
2026-04-12 03:03:29,949 | INFO | train_grpo_train | metrics_logged mode=train step=2951
2026-04-12 03:03:34,591 | INFO | train_grpo_train | metrics_logged mode=train step=2952
2026-04-12 03:03:39,871 | INFO | train_grpo_train | metrics_logged mode=train step=2953
2026-04-12 03:03:44,504 | INFO | train_grpo_train | metrics_logged mode=train step=2954
2026-04-12 03:03:50,750 | INFO | train_grpo_train | metrics_logged mode=train step=2955
2026-04-12 03:03:55,568 | INFO | train_grpo_train | metrics_logged mode=train step=2956
2026-04-12 03:04:00,303 | INFO | train_grpo_train | metrics_logged mode=train step=2957
2026-04-12 03:04:08,509 | INFO | train_grpo_train | metrics_logged mode=train step=2958
2026-04-12 03:04:16,907 | INFO | train_grpo_train | metrics_logged mode=train step=2959
2026-04-12 03:04:25,063 | INFO | train_grpo_train | metrics_logged mode=train step=2960
2026-04-12 03:04:29,975 | INFO | train_grpo_train | metrics_logged mode=train step=2961
2026-04-12 03:04:34,492 | INFO | train_grpo_train | metrics_logged mode=train step=2962
2026-04-12 03:04:40,248 | INFO | train_grpo_train | metrics_logged mode=train step=2963
2026-04-12 03:04:44,863 | INFO | train_grpo_train | metrics_logged mode=train step=2964
2026-04-12 03:04:49,459 | INFO | train_grpo_train | metrics_logged mode=train step=2965
2026-04-12 03:04:57,004 | INFO | train_grpo_train | metrics_logged mode=train step=2966
2026-04-12 03:05:02,049 | INFO | train_grpo_train | metrics_logged mode=train step=2967
2026-04-12 03:05:10,129 | INFO | train_grpo_train | metrics_logged mode=train step=2968
2026-04-12 03:05:14,289 | INFO | train_grpo_train | metrics_logged mode=train step=2969
2026-04-12 03:05:19,786 | INFO | train_grpo_train | metrics_logged mode=train step=2970
2026-04-12 03:05:24,856 | INFO | train_grpo_train | metrics_logged mode=train step=2971
2026-04-12 03:05:29,044 | INFO | train_grpo_train | metrics_logged mode=train step=2972
2026-04-12 03:05:36,126 | INFO | train_grpo_train | metrics_logged mode=train step=2973
2026-04-12 03:05:43,899 | INFO | train_grpo_train | metrics_logged mode=train step=2974
2026-04-12 03:05:48,926 | INFO | train_grpo_train | metrics_logged mode=train step=2975
2026-04-12 03:05:54,322 | INFO | train_grpo_train | metrics_logged mode=train step=2976
2026-04-12 03:05:59,418 | INFO | train_grpo_train | metrics_logged mode=train step=2977
2026-04-12 03:06:05,213 | INFO | train_grpo_train | metrics_logged mode=train step=2978
2026-04-12 03:06:09,941 | INFO | train_grpo_train | metrics_logged mode=train step=2979
2026-04-12 03:06:14,686 | INFO | train_grpo_train | metrics_logged mode=train step=2980
2026-04-12 03:06:18,987 | INFO | train_grpo_train | metrics_logged mode=train step=2981
2026-04-12 03:06:24,257 | INFO | train_grpo_train | metrics_logged mode=train step=2982
2026-04-12 03:06:29,367 | INFO | train_grpo_train | metrics_logged mode=train step=2983
2026-04-12 03:06:33,722 | INFO | train_grpo_train | metrics_logged mode=train step=2984
2026-04-12 03:06:39,795 | INFO | train_grpo_train | metrics_logged mode=train step=2985
2026-04-12 03:06:45,176 | INFO | train_grpo_train | metrics_logged mode=train step=2986
2026-04-12 03:06:50,322 | INFO | train_grpo_train | metrics_logged mode=train step=2987
2026-04-12 03:06:55,255 | INFO | train_grpo_train | metrics_logged mode=train step=2988
2026-04-12 03:07:01,412 | INFO | train_grpo_train | metrics_logged mode=train step=2989
2026-04-12 03:07:06,755 | INFO | train_grpo_train | metrics_logged mode=train step=2990
2026-04-12 03:07:11,572 | INFO | train_grpo_train | metrics_logged mode=train step=2991
2026-04-12 03:07:16,447 | INFO | train_grpo_train | metrics_logged mode=train step=2992
2026-04-12 03:07:24,856 | INFO | train_grpo_train | metrics_logged mode=train step=2993
2026-04-12 03:07:29,814 | INFO | train_grpo_train | metrics_logged mode=train step=2994
2026-04-12 03:07:34,435 | INFO | train_grpo_train | metrics_logged mode=train step=2995
2026-04-12 03:07:40,251 | INFO | train_grpo_train | metrics_logged mode=train step=2996
2026-04-12 03:07:50,670 | INFO | train_grpo_train | metrics_logged mode=train step=2997
2026-04-12 03:07:55,796 | INFO | train_grpo_train | metrics_logged mode=train step=2998
2026-04-12 03:08:00,676 | INFO | train_grpo_train | metrics_logged mode=train step=2999
2026-04-12 03:08:05,313 | INFO | train_grpo_train | metrics_logged mode=train step=3000
2026-04-12 03:09:24,857 | INFO | train_grpo_train | metrics_logged mode=eval step=3000
2026-04-12 03:09:32,527 | INFO | train_grpo_train | metrics_logged mode=train step=3001
2026-04-12 03:09:37,660 | INFO | train_grpo_train | metrics_logged mode=train step=3002
2026-04-12 03:09:43,264 | INFO | train_grpo_train | metrics_logged mode=train step=3003
2026-04-12 03:09:48,930 | INFO | train_grpo_train | metrics_logged mode=train step=3004
2026-04-12 03:09:55,415 | INFO | train_grpo_train | metrics_logged mode=train step=3005
2026-04-12 03:09:59,631 | INFO | train_grpo_train | metrics_logged mode=train step=3006
2026-04-12 03:10:05,709 | INFO | train_grpo_train | metrics_logged mode=train step=3007
2026-04-12 03:10:14,651 | INFO | train_grpo_train | metrics_logged mode=train step=3008
2026-04-12 03:10:19,165 | INFO | train_grpo_train | metrics_logged mode=train step=3009
2026-04-12 03:10:24,068 | INFO | train_grpo_train | metrics_logged mode=train step=3010
2026-04-12 03:10:29,299 | INFO | train_grpo_train | metrics_logged mode=train step=3011
2026-04-12 03:10:34,412 | INFO | train_grpo_train | metrics_logged mode=train step=3012
2026-04-12 03:10:39,379 | INFO | train_grpo_train | metrics_logged mode=train step=3013
2026-04-12 03:10:44,940 | INFO | train_grpo_train | metrics_logged mode=train step=3014
2026-04-12 03:10:49,569 | INFO | train_grpo_train | metrics_logged mode=train step=3015
2026-04-12 03:10:55,715 | INFO | train_grpo_train | metrics_logged mode=train step=3016
2026-04-12 03:11:00,849 | INFO | train_grpo_train | metrics_logged mode=train step=3017
2026-04-12 03:11:10,518 | INFO | train_grpo_train | metrics_logged mode=train step=3018
2026-04-12 03:11:15,410 | INFO | train_grpo_train | metrics_logged mode=train step=3019
2026-04-12 03:11:20,635 | INFO | train_grpo_train | metrics_logged mode=train step=3020
2026-04-12 03:11:27,036 | INFO | train_grpo_train | metrics_logged mode=train step=3021
2026-04-12 03:11:31,300 | INFO | train_grpo_train | metrics_logged mode=train step=3022
2026-04-12 03:11:36,290 | INFO | train_grpo_train | metrics_logged mode=train step=3023
2026-04-12 03:11:41,089 | INFO | train_grpo_train | metrics_logged mode=train step=3024
2026-04-12 03:11:46,275 | INFO | train_grpo_train | metrics_logged mode=train step=3025
2026-04-12 03:11:51,530 | INFO | train_grpo_train | metrics_logged mode=train step=3026
2026-04-12 03:11:56,324 | INFO | train_grpo_train | metrics_logged mode=train step=3027
2026-04-12 03:12:00,733 | INFO | train_grpo_train | metrics_logged mode=train step=3028
2026-04-12 03:12:05,800 | INFO | train_grpo_train | metrics_logged mode=train step=3029
2026-04-12 03:12:13,782 | INFO | train_grpo_train | metrics_logged mode=train step=3030
2026-04-12 03:12:19,626 | INFO | train_grpo_train | metrics_logged mode=train step=3031
2026-04-12 03:12:24,387 | INFO | train_grpo_train | metrics_logged mode=train step=3032
2026-04-12 03:12:30,549 | INFO | train_grpo_train | metrics_logged mode=train step=3033
2026-04-12 03:12:34,640 | INFO | train_grpo_train | metrics_logged mode=train step=3034
2026-04-12 03:12:38,943 | INFO | train_grpo_train | metrics_logged mode=train step=3035
2026-04-12 03:12:42,938 | INFO | train_grpo_train | metrics_logged mode=train step=3036
2026-04-12 03:12:47,974 | INFO | train_grpo_train | metrics_logged mode=train step=3037
2026-04-12 03:12:58,052 | INFO | train_grpo_train | metrics_logged mode=train step=3038
2026-04-12 03:13:04,626 | INFO | train_grpo_train | metrics_logged mode=train step=3039
2026-04-12 03:13:09,225 | INFO | train_grpo_train | metrics_logged mode=train step=3040
2026-04-12 03:13:13,204 | INFO | train_grpo_train | metrics_logged mode=train step=3041
2026-04-12 03:13:17,914 | INFO | train_grpo_train | metrics_logged mode=train step=3042
2026-04-12 03:13:22,215 | INFO | train_grpo_train | metrics_logged mode=train step=3043
2026-04-12 03:13:26,703 | INFO | train_grpo_train | metrics_logged mode=train step=3044
2026-04-12 03:13:31,679 | INFO | train_grpo_train | metrics_logged mode=train step=3045
2026-04-12 03:13:36,187 | INFO | train_grpo_train | metrics_logged mode=train step=3046
2026-04-12 03:13:42,295 | INFO | train_grpo_train | metrics_logged mode=train step=3047
2026-04-12 03:13:46,470 | INFO | train_grpo_train | metrics_logged mode=train step=3048
2026-04-12 03:13:51,841 | INFO | train_grpo_train | metrics_logged mode=train step=3049
2026-04-12 03:13:58,488 | INFO | train_grpo_train | metrics_logged mode=train step=3050
2026-04-12 03:15:16,123 | INFO | train_grpo_train | metrics_logged mode=eval step=3050
2026-04-12 03:15:25,738 | INFO | train_grpo_train | metrics_logged mode=train step=3051
2026-04-12 03:15:33,935 | INFO | train_grpo_train | metrics_logged mode=train step=3052
2026-04-12 03:15:38,663 | INFO | train_grpo_train | metrics_logged mode=train step=3053
2026-04-12 03:15:44,242 | INFO | train_grpo_train | metrics_logged mode=train step=3054
2026-04-12 03:15:50,716 | INFO | train_grpo_train | metrics_logged mode=train step=3055
2026-04-12 03:15:56,105 | INFO | train_grpo_train | metrics_logged mode=train step=3056
2026-04-12 03:16:00,577 | INFO | train_grpo_train | metrics_logged mode=train step=3057
2026-04-12 03:16:05,017 | INFO | train_grpo_train | metrics_logged mode=train step=3058
2026-04-12 03:16:10,160 | INFO | train_grpo_train | metrics_logged mode=train step=3059
2026-04-12 03:16:15,622 | INFO | train_grpo_train | metrics_logged mode=train step=3060
2026-04-12 03:16:19,701 | INFO | train_grpo_train | metrics_logged mode=train step=3061
2026-04-12 03:16:24,892 | INFO | train_grpo_train | metrics_logged mode=train step=3062
2026-04-12 03:16:30,203 | INFO | train_grpo_train | metrics_logged mode=train step=3063
2026-04-12 03:16:34,778 | INFO | train_grpo_train | metrics_logged mode=train step=3064
2026-04-12 03:16:42,782 | INFO | train_grpo_train | metrics_logged mode=train step=3065
2026-04-12 03:16:46,846 | INFO | train_grpo_train | metrics_logged mode=train step=3066
2026-04-12 03:16:51,396 | INFO | train_grpo_train | metrics_logged mode=train step=3067
2026-04-12 03:16:57,217 | INFO | train_grpo_train | metrics_logged mode=train step=3068
2026-04-12 03:17:04,347 | INFO | train_grpo_train | metrics_logged mode=train step=3069
2026-04-12 03:17:11,012 | INFO | train_grpo_train | metrics_logged mode=train step=3070
2026-04-12 03:17:15,757 | INFO | train_grpo_train | metrics_logged mode=train step=3071
2026-04-12 03:17:20,110 | INFO | train_grpo_train | metrics_logged mode=train step=3072
2026-04-12 03:17:24,715 | INFO | train_grpo_train | metrics_logged mode=train step=3073
2026-04-12 03:17:30,024 | INFO | train_grpo_train | metrics_logged mode=train step=3074
2026-04-12 03:17:34,617 | INFO | train_grpo_train | metrics_logged mode=train step=3075
2026-04-12 03:17:38,999 | INFO | train_grpo_train | metrics_logged mode=train step=3076
2026-04-12 03:17:43,587 | INFO | train_grpo_train | metrics_logged mode=train step=3077
2026-04-12 03:17:48,356 | INFO | train_grpo_train | metrics_logged mode=train step=3078
2026-04-12 03:17:54,173 | INFO | train_grpo_train | metrics_logged mode=train step=3079
2026-04-12 03:17:58,744 | INFO | train_grpo_train | metrics_logged mode=train step=3080
2026-04-12 03:18:03,991 | INFO | train_grpo_train | metrics_logged mode=train step=3081
2026-04-12 03:18:11,754 | INFO | train_grpo_train | metrics_logged mode=train step=3082
2026-04-12 03:18:16,519 | INFO | train_grpo_train | metrics_logged mode=train step=3083
2026-04-12 03:18:21,274 | INFO | train_grpo_train | metrics_logged mode=train step=3084
2026-04-12 03:18:27,304 | INFO | train_grpo_train | metrics_logged mode=train step=3085
2026-04-12 03:18:32,829 | INFO | train_grpo_train | metrics_logged mode=train step=3086
2026-04-12 03:18:37,451 | INFO | train_grpo_train | metrics_logged mode=train step=3087
2026-04-12 03:18:42,590 | INFO | train_grpo_train | metrics_logged mode=train step=3088
2026-04-12 03:18:50,962 | INFO | train_grpo_train | metrics_logged mode=train step=3089
2026-04-12 03:18:55,566 | INFO | train_grpo_train | metrics_logged mode=train step=3090
2026-04-12 03:19:00,137 | INFO | train_grpo_train | metrics_logged mode=train step=3091
2026-04-12 03:19:05,357 | INFO | train_grpo_train | metrics_logged mode=train step=3092
2026-04-12 03:19:09,860 | INFO | train_grpo_train | metrics_logged mode=train step=3093
2026-04-12 03:19:14,341 | INFO | train_grpo_train | metrics_logged mode=train step=3094
2026-04-12 03:19:19,683 | INFO | train_grpo_train | metrics_logged mode=train step=3095
2026-04-12 03:19:24,623 | INFO | train_grpo_train | metrics_logged mode=train step=3096
2026-04-12 03:19:29,237 | INFO | train_grpo_train | metrics_logged mode=train step=3097
2026-04-12 03:19:37,538 | INFO | train_grpo_train | metrics_logged mode=train step=3098
2026-04-12 03:19:43,127 | INFO | train_grpo_train | metrics_logged mode=train step=3099
2026-04-12 03:19:48,567 | INFO | train_grpo_train | metrics_logged mode=train step=3100
2026-04-12 03:21:06,357 | INFO | train_grpo_train | metrics_logged mode=eval step=3100
2026-04-12 03:21:16,534 | INFO | train_grpo_train | metrics_logged mode=train step=3101
2026-04-12 03:21:22,556 | INFO | train_grpo_train | metrics_logged mode=train step=3102
2026-04-12 03:21:28,585 | INFO | train_grpo_train | metrics_logged mode=train step=3103
2026-04-12 03:21:34,867 | INFO | train_grpo_train | metrics_logged mode=train step=3104
2026-04-12 03:21:41,086 | INFO | train_grpo_train | metrics_logged mode=train step=3105
2026-04-12 03:21:47,086 | INFO | train_grpo_train | metrics_logged mode=train step=3106
2026-04-12 03:21:56,486 | INFO | train_grpo_train | metrics_logged mode=train step=3107
2026-04-12 03:22:01,832 | INFO | train_grpo_train | metrics_logged mode=train step=3108
2026-04-12 03:22:08,295 | INFO | train_grpo_train | metrics_logged mode=train step=3109
2026-04-12 03:22:14,163 | INFO | train_grpo_train | metrics_logged mode=train step=3110
2026-04-12 03:22:18,627 | INFO | train_grpo_train | metrics_logged mode=train step=3111
2026-04-12 03:22:26,275 | INFO | train_grpo_train | metrics_logged mode=train step=3112
2026-04-12 03:22:30,484 | INFO | train_grpo_train | metrics_logged mode=train step=3113
2026-04-12 03:22:35,492 | INFO | train_grpo_train | metrics_logged mode=train step=3114
2026-04-12 03:22:40,080 | INFO | train_grpo_train | metrics_logged mode=train step=3115
2026-04-12 03:22:50,387 | INFO | train_grpo_train | metrics_logged mode=train step=3116
2026-04-12 03:22:54,727 | INFO | train_grpo_train | metrics_logged mode=train step=3117
2026-04-12 03:23:02,984 | INFO | train_grpo_train | metrics_logged mode=train step=3118
2026-04-12 03:23:07,718 | INFO | train_grpo_train | metrics_logged mode=train step=3119
2026-04-12 03:23:12,338 | INFO | train_grpo_train | metrics_logged mode=train step=3120
2026-04-12 03:23:21,514 | INFO | train_grpo_train | metrics_logged mode=train step=3121
2026-04-12 03:23:26,950 | INFO | train_grpo_train | metrics_logged mode=train step=3122
2026-04-12 03:23:32,251 | INFO | train_grpo_train | metrics_logged mode=train step=3123
2026-04-12 03:23:42,525 | INFO | train_grpo_train | metrics_logged mode=train step=3124
2026-04-12 03:23:47,170 | INFO | train_grpo_train | metrics_logged mode=train step=3125
2026-04-12 03:23:56,223 | INFO | train_grpo_train | metrics_logged mode=train step=3126
2026-04-12 03:24:06,293 | INFO | train_grpo_train | metrics_logged mode=train step=3127
2026-04-12 03:24:12,668 | INFO | train_grpo_train | metrics_logged mode=train step=3128
2026-04-12 03:24:18,217 | INFO | train_grpo_train | metrics_logged mode=train step=3129
2026-04-12 03:24:23,067 | INFO | train_grpo_train | metrics_logged mode=train step=3130
2026-04-12 03:24:27,805 | INFO | train_grpo_train | metrics_logged mode=train step=3131
2026-04-12 03:24:32,669 | INFO | train_grpo_train | metrics_logged mode=train step=3132
2026-04-12 03:24:37,877 | INFO | train_grpo_train | metrics_logged mode=train step=3133
2026-04-12 03:24:43,019 | INFO | train_grpo_train | metrics_logged mode=train step=3134
2026-04-12 03:24:48,093 | INFO | train_grpo_train | metrics_logged mode=train step=3135
2026-04-12 03:24:52,756 | INFO | train_grpo_train | metrics_logged mode=train step=3136
2026-04-12 03:24:57,681 | INFO | train_grpo_train | metrics_logged mode=train step=3137
2026-04-12 03:25:01,999 | INFO | train_grpo_train | metrics_logged mode=train step=3138
2026-04-12 03:25:06,447 | INFO | train_grpo_train | metrics_logged mode=train step=3139
2026-04-12 03:25:14,182 | INFO | train_grpo_train | metrics_logged mode=train step=3140
2026-04-12 03:25:18,329 | INFO | train_grpo_train | metrics_logged mode=train step=3141
2026-04-12 03:25:22,959 | INFO | train_grpo_train | metrics_logged mode=train step=3142
2026-04-12 03:25:28,302 | INFO | train_grpo_train | metrics_logged mode=train step=3143
2026-04-12 03:25:32,878 | INFO | train_grpo_train | metrics_logged mode=train step=3144
2026-04-12 03:25:37,738 | INFO | train_grpo_train | metrics_logged mode=train step=3145
2026-04-12 03:25:41,760 | INFO | train_grpo_train | metrics_logged mode=train step=3146
2026-04-12 03:25:49,542 | INFO | train_grpo_train | metrics_logged mode=train step=3147
2026-04-12 03:25:54,491 | INFO | train_grpo_train | metrics_logged mode=train step=3148
2026-04-12 03:26:04,658 | INFO | train_grpo_train | metrics_logged mode=train step=3149
2026-04-12 03:26:09,022 | INFO | train_grpo_train | metrics_logged mode=train step=3150
2026-04-12 03:27:29,553 | INFO | train_grpo_train | metrics_logged mode=eval step=3150
2026-04-12 03:27:37,178 | INFO | train_grpo_train | metrics_logged mode=train step=3151
2026-04-12 03:27:42,019 | INFO | train_grpo_train | metrics_logged mode=train step=3152
2026-04-12 03:27:48,298 | INFO | train_grpo_train | metrics_logged mode=train step=3153
2026-04-12 03:27:53,571 | INFO | train_grpo_train | metrics_logged mode=train step=3154
2026-04-12 03:27:58,078 | INFO | train_grpo_train | metrics_logged mode=train step=3155
2026-04-12 03:28:02,401 | INFO | train_grpo_train | metrics_logged mode=train step=3156
2026-04-12 03:28:06,665 | INFO | train_grpo_train | metrics_logged mode=train step=3157
2026-04-12 03:28:11,203 | INFO | train_grpo_train | metrics_logged mode=train step=3158
2026-04-12 03:28:15,983 | INFO | train_grpo_train | metrics_logged mode=train step=3159
2026-04-12 03:28:26,108 | INFO | train_grpo_train | metrics_logged mode=train step=3160
2026-04-12 03:28:34,194 | INFO | train_grpo_train | metrics_logged mode=train step=3161
2026-04-12 03:28:38,825 | INFO | train_grpo_train | metrics_logged mode=train step=3162
2026-04-12 03:28:43,424 | INFO | train_grpo_train | metrics_logged mode=train step=3163
2026-04-12 03:28:47,771 | INFO | train_grpo_train | metrics_logged mode=train step=3164
2026-04-12 03:28:52,279 | INFO | train_grpo_train | metrics_logged mode=train step=3165
2026-04-12 03:28:56,800 | INFO | train_grpo_train | metrics_logged mode=train step=3166
2026-04-12 03:29:01,966 | INFO | train_grpo_train | metrics_logged mode=train step=3167
2026-04-12 03:29:06,438 | INFO | train_grpo_train | metrics_logged mode=train step=3168
2026-04-12 03:29:11,798 | INFO | train_grpo_train | metrics_logged mode=train step=3169
2026-04-12 03:29:18,580 | INFO | train_grpo_train | metrics_logged mode=train step=3170
2026-04-12 03:29:23,166 | INFO | train_grpo_train | metrics_logged mode=train step=3171
2026-04-12 03:29:27,549 | INFO | train_grpo_train | metrics_logged mode=train step=3172
2026-04-12 03:29:34,152 | INFO | train_grpo_train | metrics_logged mode=train step=3173
2026-04-12 03:29:38,352 | INFO | train_grpo_train | metrics_logged mode=train step=3174
2026-04-12 03:29:43,661 | INFO | train_grpo_train | metrics_logged mode=train step=3175
2026-04-12 03:29:51,838 | INFO | train_grpo_train | metrics_logged mode=train step=3176
2026-04-12 03:29:56,181 | INFO | train_grpo_train | metrics_logged mode=train step=3177
2026-04-12 03:30:00,793 | INFO | train_grpo_train | metrics_logged mode=train step=3178
2026-04-12 03:30:08,188 | INFO | train_grpo_train | metrics_logged mode=train step=3179
2026-04-12 03:30:13,574 | INFO | train_grpo_train | metrics_logged mode=train step=3180
2026-04-12 03:30:19,400 | INFO | train_grpo_train | metrics_logged mode=train step=3181
2026-04-12 03:30:24,043 | INFO | train_grpo_train | metrics_logged mode=train step=3182
2026-04-12 03:30:28,090 | INFO | train_grpo_train | metrics_logged mode=train step=3183
2026-04-12 03:30:32,493 | INFO | train_grpo_train | metrics_logged mode=train step=3184
2026-04-12 03:30:37,108 | INFO | train_grpo_train | metrics_logged mode=train step=3185
2026-04-12 03:30:41,449 | INFO | train_grpo_train | metrics_logged mode=train step=3186
2026-04-12 03:30:46,133 | INFO | train_grpo_train | metrics_logged mode=train step=3187
2026-04-12 03:30:51,148 | INFO | train_grpo_train | metrics_logged mode=train step=3188
2026-04-12 03:30:55,267 | INFO | train_grpo_train | metrics_logged mode=train step=3189
2026-04-12 03:30:59,819 | INFO | train_grpo_train | metrics_logged mode=train step=3190
2026-04-12 03:31:04,290 | INFO | train_grpo_train | metrics_logged mode=train step=3191
2026-04-12 03:31:08,560 | INFO | train_grpo_train | metrics_logged mode=train step=3192
2026-04-12 03:31:12,967 | INFO | train_grpo_train | metrics_logged mode=train step=3193
2026-04-12 03:31:18,253 | INFO | train_grpo_train | metrics_logged mode=train step=3194
2026-04-12 03:31:22,414 | INFO | train_grpo_train | metrics_logged mode=train step=3195
2026-04-12 03:31:31,302 | INFO | train_grpo_train | metrics_logged mode=train step=3196
2026-04-12 03:31:38,772 | INFO | train_grpo_train | metrics_logged mode=train step=3197
2026-04-12 03:31:43,120 | INFO | train_grpo_train | metrics_logged mode=train step=3198
2026-04-12 03:31:49,442 | INFO | train_grpo_train | metrics_logged mode=train step=3199
2026-04-12 03:31:54,214 | INFO | train_grpo_train | metrics_logged mode=train step=3200
2026-04-12 03:33:12,688 | INFO | train_grpo_train | metrics_logged mode=eval step=3200
2026-04-12 03:33:20,802 | INFO | train_grpo_train | metrics_logged mode=train step=3201
2026-04-12 03:33:26,158 | INFO | train_grpo_train | metrics_logged mode=train step=3202
2026-04-12 03:33:33,516 | INFO | train_grpo_train | metrics_logged mode=train step=3203
2026-04-12 03:33:38,133 | INFO | train_grpo_train | metrics_logged mode=train step=3204
2026-04-12 03:33:42,207 | INFO | train_grpo_train | metrics_logged mode=train step=3205
2026-04-12 03:33:47,442 | INFO | train_grpo_train | metrics_logged mode=train step=3206
2026-04-12 03:33:52,230 | INFO | train_grpo_train | metrics_logged mode=train step=3207
2026-04-12 03:33:57,016 | INFO | train_grpo_train | metrics_logged mode=train step=3208
2026-04-12 03:34:02,646 | INFO | train_grpo_train | metrics_logged mode=train step=3209
2026-04-12 03:34:07,176 | INFO | train_grpo_train | metrics_logged mode=train step=3210
2026-04-12 03:34:11,751 | INFO | train_grpo_train | metrics_logged mode=train step=3211
2026-04-12 03:34:16,200 | INFO | train_grpo_train | metrics_logged mode=train step=3212
2026-04-12 03:34:23,953 | INFO | train_grpo_train | metrics_logged mode=train step=3213
2026-04-12 03:34:29,820 | INFO | train_grpo_train | metrics_logged mode=train step=3214
2026-04-12 03:34:34,394 | INFO | train_grpo_train | metrics_logged mode=train step=3215
2026-04-12 03:34:38,445 | INFO | train_grpo_train | metrics_logged mode=train step=3216
2026-04-12 03:34:43,226 | INFO | train_grpo_train | metrics_logged mode=train step=3217
2026-04-12 03:34:48,590 | INFO | train_grpo_train | metrics_logged mode=train step=3218
2026-04-12 03:34:53,682 | INFO | train_grpo_train | metrics_logged mode=train step=3219
2026-04-12 03:34:58,252 | INFO | train_grpo_train | metrics_logged mode=train step=3220
2026-04-12 03:35:02,871 | INFO | train_grpo_train | metrics_logged mode=train step=3221
2026-04-12 03:35:09,039 | INFO | train_grpo_train | metrics_logged mode=train step=3222
2026-04-12 03:35:13,312 | INFO | train_grpo_train | metrics_logged mode=train step=3223
2026-04-12 03:35:17,971 | INFO | train_grpo_train | metrics_logged mode=train step=3224
2026-04-12 03:35:22,417 | INFO | train_grpo_train | metrics_logged mode=train step=3225
2026-04-12 03:35:26,738 | INFO | train_grpo_train | metrics_logged mode=train step=3226
2026-04-12 03:35:31,137 | INFO | train_grpo_train | metrics_logged mode=train step=3227
2026-04-12 03:35:35,414 | INFO | train_grpo_train | metrics_logged mode=train step=3228
2026-04-12 03:35:40,228 | INFO | train_grpo_train | metrics_logged mode=train step=3229
2026-04-12 03:35:44,663 | INFO | train_grpo_train | metrics_logged mode=train step=3230
2026-04-12 03:35:49,679 | INFO | train_grpo_train | metrics_logged mode=train step=3231
2026-04-12 03:35:54,388 | INFO | train_grpo_train | metrics_logged mode=train step=3232
2026-04-12 03:35:59,576 | INFO | train_grpo_train | metrics_logged mode=train step=3233
2026-04-12 03:36:03,854 | INFO | train_grpo_train | metrics_logged mode=train step=3234
2026-04-12 03:36:09,210 | INFO | train_grpo_train | metrics_logged mode=train step=3235
2026-04-12 03:36:16,489 | INFO | train_grpo_train | metrics_logged mode=train step=3236
2026-04-12 03:36:20,919 | INFO | train_grpo_train | metrics_logged mode=train step=3237
2026-04-12 03:36:26,233 | INFO | train_grpo_train | metrics_logged mode=train step=3238
2026-04-12 03:36:30,812 | INFO | train_grpo_train | metrics_logged mode=train step=3239
2026-04-12 03:36:39,055 | INFO | train_grpo_train | metrics_logged mode=train step=3240
2026-04-12 03:36:47,429 | INFO | train_grpo_train | metrics_logged mode=train step=3241
2026-04-12 03:36:54,565 | INFO | train_grpo_train | metrics_logged mode=train step=3242
2026-04-12 03:37:00,175 | INFO | train_grpo_train | metrics_logged mode=train step=3243
2026-04-12 03:37:05,903 | INFO | train_grpo_train | metrics_logged mode=train step=3244
2026-04-12 03:37:11,390 | INFO | train_grpo_train | metrics_logged mode=train step=3245
2026-04-12 03:37:18,742 | INFO | train_grpo_train | metrics_logged mode=train step=3246
2026-04-12 03:37:23,260 | INFO | train_grpo_train | metrics_logged mode=train step=3247
2026-04-12 03:37:29,114 | INFO | train_grpo_train | metrics_logged mode=train step=3248
2026-04-12 03:37:39,335 | INFO | train_grpo_train | metrics_logged mode=train step=3249
2026-04-12 03:37:44,780 | INFO | train_grpo_train | metrics_logged mode=train step=3250
2026-04-12 03:39:02,963 | INFO | train_grpo_train | metrics_logged mode=eval step=3250
2026-04-12 03:39:09,685 | INFO | train_grpo_train | metrics_logged mode=train step=3251
2026-04-12 03:39:16,012 | INFO | train_grpo_train | metrics_logged mode=train step=3252
2026-04-12 03:39:21,829 | INFO | train_grpo_train | metrics_logged mode=train step=3253
2026-04-12 03:39:28,647 | INFO | train_grpo_train | metrics_logged mode=train step=3254
2026-04-12 03:39:33,210 | INFO | train_grpo_train | metrics_logged mode=train step=3255
2026-04-12 03:39:38,220 | INFO | train_grpo_train | metrics_logged mode=train step=3256
2026-04-12 03:39:42,838 | INFO | train_grpo_train | metrics_logged mode=train step=3257
2026-04-12 03:39:47,459 | INFO | train_grpo_train | metrics_logged mode=train step=3258
2026-04-12 03:39:53,186 | INFO | train_grpo_train | metrics_logged mode=train step=3259
2026-04-12 03:39:57,379 | INFO | train_grpo_train | metrics_logged mode=train step=3260
2026-04-12 03:40:02,120 | INFO | train_grpo_train | metrics_logged mode=train step=3261
2026-04-12 03:40:06,788 | INFO | train_grpo_train | metrics_logged mode=train step=3262
2026-04-12 03:40:11,819 | INFO | train_grpo_train | metrics_logged mode=train step=3263
2026-04-12 03:40:16,667 | INFO | train_grpo_train | metrics_logged mode=train step=3264
2026-04-12 03:40:22,530 | INFO | train_grpo_train | metrics_logged mode=train step=3265
2026-04-12 03:40:28,419 | INFO | train_grpo_train | metrics_logged mode=train step=3266
2026-04-12 03:40:34,116 | INFO | train_grpo_train | metrics_logged mode=train step=3267
2026-04-12 03:40:39,416 | INFO | train_grpo_train | metrics_logged mode=train step=3268
2026-04-12 03:40:43,691 | INFO | train_grpo_train | metrics_logged mode=train step=3269
2026-04-12 03:40:50,402 | INFO | train_grpo_train | metrics_logged mode=train step=3270
2026-04-12 03:40:55,595 | INFO | train_grpo_train | metrics_logged mode=train step=3271
2026-04-12 03:41:01,240 | INFO | train_grpo_train | metrics_logged mode=train step=3272
2026-04-12 03:41:05,871 | INFO | train_grpo_train | metrics_logged mode=train step=3273
2026-04-12 03:41:10,520 | INFO | train_grpo_train | metrics_logged mode=train step=3274
2026-04-12 03:41:14,957 | INFO | train_grpo_train | metrics_logged mode=train step=3275
2026-04-12 03:41:19,623 | INFO | train_grpo_train | metrics_logged mode=train step=3276
2026-04-12 03:41:27,164 | INFO | train_grpo_train | metrics_logged mode=train step=3277
2026-04-12 03:41:34,989 | INFO | train_grpo_train | metrics_logged mode=train step=3278
2026-04-12 03:41:39,452 | INFO | train_grpo_train | metrics_logged mode=train step=3279
2026-04-12 03:41:44,323 | INFO | train_grpo_train | metrics_logged mode=train step=3280
2026-04-12 03:41:48,498 | INFO | train_grpo_train | metrics_logged mode=train step=3281
2026-04-12 03:41:53,392 | INFO | train_grpo_train | metrics_logged mode=train step=3282
2026-04-12 03:41:58,113 | INFO | train_grpo_train | metrics_logged mode=train step=3283
2026-04-12 03:42:03,452 | INFO | train_grpo_train | metrics_logged mode=train step=3284
2026-04-12 03:42:11,948 | INFO | train_grpo_train | metrics_logged mode=train step=3285
2026-04-12 03:42:18,876 | INFO | train_grpo_train | metrics_logged mode=train step=3286
2026-04-12 03:42:24,121 | INFO | train_grpo_train | metrics_logged mode=train step=3287
2026-04-12 03:42:29,158 | INFO | train_grpo_train | metrics_logged mode=train step=3288
2026-04-12 03:42:34,240 | INFO | train_grpo_train | metrics_logged mode=train step=3289
2026-04-12 03:42:40,514 | INFO | train_grpo_train | metrics_logged mode=train step=3290
2026-04-12 03:42:45,304 | INFO | train_grpo_train | metrics_logged mode=train step=3291
2026-04-12 03:42:49,749 | INFO | train_grpo_train | metrics_logged mode=train step=3292
2026-04-12 03:42:59,245 | INFO | train_grpo_train | metrics_logged mode=train step=3293
2026-04-12 03:43:03,854 | INFO | train_grpo_train | metrics_logged mode=train step=3294
2026-04-12 03:43:08,258 | INFO | train_grpo_train | metrics_logged mode=train step=3295
2026-04-12 03:43:14,629 | INFO | train_grpo_train | metrics_logged mode=train step=3296
2026-04-12 03:43:22,327 | INFO | train_grpo_train | metrics_logged mode=train step=3297
2026-04-12 03:43:26,891 | INFO | train_grpo_train | metrics_logged mode=train step=3298
2026-04-12 03:43:32,611 | INFO | train_grpo_train | metrics_logged mode=train step=3299
2026-04-12 03:43:36,813 | INFO | train_grpo_train | metrics_logged mode=train step=3300
2026-04-12 03:44:57,274 | INFO | train_grpo_train | metrics_logged mode=eval step=3300
2026-04-12 03:45:00,970 | INFO | train_grpo_train | metrics_logged mode=train step=3300
2026-04-12 03:46:19,803 | INFO | train_grpo_train | pushing final adapter to hub repo=Shaer-AI/Shaer-adapters-grpo