2026-04-12 15:56:00,391 | INFO | train_grpo_train | mode=train 2026-04-12 15:58:25,741 | INFO | train_grpo_train | dataset_id=Shaer-AI/ashaar-enhanced-desc-baseform-final-sft-lte20-min500-splits-grpo-meter-count-v1 train_size=19001 eval_size=104 2026-04-12 15:58:25,741 | 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 2026-04-12 15:58:25,742 | INFO | train_grpo_train | active_rewards=['meter', 'count_adherence', 'arabic_clean', 'hard_gate', 'arabic_floor', 'count_floor', 'lexical_plausibility', 'judge_quality', 'repeat_penalty', 'repeat_floor', 'near_duplicate_penalty', 'opening_diversity', 'distinct_2', 'total_composite'] 2026-04-12 15:58:25,742 | INFO | train_grpo_train | reward_weights={'meter': 0.0, 'count_adherence': 0.0, 'arabic_clean': 0.0, 'hard_gate': 0.0, 'arabic_floor': 0.0, 'count_floor': 0.0, 'lexical_plausibility': 0.0, 'judge_quality': 0.0, 'repeat_penalty': 0.0, 'repeat_floor': 0.0, 'near_duplicate_penalty': 0.0, 'opening_diversity': 0.0, 'distinct_2': 0.0, 'total_composite': 1.0} 2026-04-12 15:58:25,742 | INFO | train_grpo_train | output_repo=Shaer-AI/Shaer-adapters-grpo-friend-v1-easyfirst 2026-04-12 15:58:25,742 | INFO | train_grpo_train | train_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_easyfirst_drop_trio/cap_3000/selected_manifest.csv 2026-04-12 15:58:25,742 | INFO | train_grpo_train | hard_diagnostic_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_easyfirst_drop_trio/hard_diagnostic_cap_256/selected_manifest.csv 2026-04-12 15:58:25,742 | INFO | train_grpo_train | trainable_params=159907840 total_params=7160467456 trainable_ratio=0.022332 2026-04-12 15:58:25,742 | INFO | train_grpo_train | resume_decision={"timestamp_utc": "2026-04-12T15:58:06Z", "resume_mode": "fresh", "requested_spec": "", "result": "fresh", "reason": "explicit_fresh", "local_resume_path": null, "remote_repo": null, "remote_prefix": null, "compatibility": "unchecked", "config_fingerprint": "429b334e6c80dfa9b81f2594e6165bdb27e9289404e07f5b1493fe2fe6227203"} 2026-04-12 15:58:25,742 | INFO | train_grpo_train | starting trainer.train() 2026-04-12 15:58:35,463 | INFO | train_grpo_train | metrics_logged mode=train step=1 2026-04-12 15:58:46,910 | INFO | train_grpo_train | metrics_logged mode=train step=2 2026-04-12 15:58:57,241 | INFO | train_grpo_train | metrics_logged mode=train step=3 2026-04-12 15:59:07,085 | INFO | train_grpo_train | metrics_logged mode=train step=4 2026-04-12 15:59:16,150 | INFO | train_grpo_train | metrics_logged mode=train step=5 2026-04-12 15:59:25,788 | INFO | train_grpo_train | metrics_logged mode=train step=6 2026-04-12 15:59:34,715 | INFO | train_grpo_train | metrics_logged mode=train step=7 2026-04-12 15:59:43,794 | INFO | train_grpo_train | metrics_logged mode=train step=8 2026-04-12 15:59:53,490 | INFO | train_grpo_train | metrics_logged mode=train step=9 2026-04-12 16:00:03,916 | INFO | train_grpo_train | metrics_logged mode=train step=10 2026-04-12 16:00:13,554 | INFO | train_grpo_train | metrics_logged mode=train step=11 2026-04-12 16:00:21,102 | INFO | train_grpo_train | metrics_logged mode=train step=12 2026-04-12 16:00:30,280 | INFO | train_grpo_train | metrics_logged mode=train step=13 2026-04-12 16:00:39,281 | INFO | train_grpo_train | metrics_logged mode=train step=14 2026-04-12 16:00:47,835 | INFO | train_grpo_train | metrics_logged mode=train step=15 2026-04-12 16:00:56,166 | INFO | train_grpo_train | metrics_logged mode=train step=16 2026-04-12 16:01:04,525 | INFO | train_grpo_train | metrics_logged mode=train step=17 2026-04-12 16:01:15,493 | INFO | train_grpo_train | metrics_logged mode=train step=18 2026-04-12 16:01:25,431 | INFO | train_grpo_train | metrics_logged mode=train step=19 2026-04-12 16:01:34,560 | INFO | train_grpo_train | metrics_logged mode=train step=20 2026-04-12 16:01:45,647 | INFO | train_grpo_train | metrics_logged mode=train step=21 2026-04-12 16:01:53,633 | INFO | train_grpo_train | metrics_logged mode=train step=22 2026-04-12 16:02:03,511 | INFO | train_grpo_train | metrics_logged mode=train step=23 2026-04-12 16:02:11,433 | INFO | train_grpo_train | metrics_logged mode=train step=24 2026-04-12 16:02:20,846 | INFO | train_grpo_train | metrics_logged mode=train step=25 2026-04-12 16:02:30,805 | INFO | train_grpo_train | metrics_logged mode=train step=26 2026-04-12 16:02:42,890 | INFO | train_grpo_train | metrics_logged mode=train step=27 2026-04-12 16:02:52,988 | INFO | train_grpo_train | metrics_logged mode=train step=28 2026-04-12 16:03:01,728 | INFO | train_grpo_train | metrics_logged mode=train step=29 2026-04-12 16:03:10,694 | INFO | train_grpo_train | metrics_logged mode=train step=30 2026-04-12 16:03:20,441 | INFO | train_grpo_train | metrics_logged mode=train step=31 2026-04-12 16:03:30,214 | INFO | train_grpo_train | metrics_logged mode=train step=32 2026-04-12 16:03:43,922 | INFO | train_grpo_train | metrics_logged mode=train step=33 2026-04-12 16:03:53,024 | INFO | train_grpo_train | metrics_logged mode=train step=34 2026-04-12 16:04:12,397 | INFO | train_grpo_train | metrics_logged mode=train step=35 2026-04-12 16:04:22,116 | INFO | train_grpo_train | metrics_logged mode=train step=36 2026-04-12 16:04:31,040 | INFO | train_grpo_train | metrics_logged mode=train step=37 2026-04-12 16:04:40,285 | INFO | train_grpo_train | metrics_logged mode=train step=38 2026-04-12 16:04:51,324 | INFO | train_grpo_train | metrics_logged mode=train step=39 2026-04-12 16:05:00,957 | INFO | train_grpo_train | metrics_logged mode=train step=40 2026-04-12 16:05:09,387 | INFO | train_grpo_train | metrics_logged mode=train step=41 2026-04-12 16:05:18,423 | INFO | train_grpo_train | metrics_logged mode=train step=42 2026-04-12 16:05:28,009 | INFO | train_grpo_train | metrics_logged mode=train step=43 2026-04-12 16:05:38,658 | INFO | train_grpo_train | metrics_logged mode=train step=44 2026-04-12 16:05:48,751 | INFO | train_grpo_train | metrics_logged mode=train step=45 2026-04-12 16:05:58,779 | INFO | train_grpo_train | metrics_logged mode=train step=46 2026-04-12 16:06:06,893 | INFO | train_grpo_train | metrics_logged mode=train step=47 2026-04-12 16:06:18,504 | INFO | train_grpo_train | metrics_logged mode=train step=48 2026-04-12 16:06:27,763 | INFO | train_grpo_train | metrics_logged mode=train step=49 2026-04-12 16:06:36,886 | INFO | train_grpo_train | metrics_logged mode=train step=50 2026-04-12 16:08:51,138 | INFO | train_grpo_train | metrics_logged mode=eval step=50 2026-04-12 16:09:03,313 | INFO | train_grpo_train | metrics_logged mode=train step=51 2026-04-12 16:09:12,961 | INFO | train_grpo_train | metrics_logged mode=train step=52 2026-04-12 16:09:22,504 | INFO | train_grpo_train | metrics_logged mode=train step=53 2026-04-12 16:09:30,570 | INFO | train_grpo_train | metrics_logged mode=train step=54 2026-04-12 16:09:38,628 | INFO | train_grpo_train | metrics_logged mode=train step=55 2026-04-12 16:09:47,788 | INFO | train_grpo_train | metrics_logged mode=train step=56 2026-04-12 16:10:00,649 | INFO | train_grpo_train | metrics_logged mode=train step=57 2026-04-12 16:10:09,834 | INFO | train_grpo_train | metrics_logged mode=train step=58 2026-04-12 16:10:18,876 | INFO | train_grpo_train | metrics_logged mode=train step=59 2026-04-12 16:10:29,601 | INFO | train_grpo_train | metrics_logged mode=train step=60 2026-04-12 16:10:38,544 | INFO | train_grpo_train | metrics_logged mode=train step=61 2026-04-12 16:10:46,472 | INFO | train_grpo_train | metrics_logged mode=train step=62 2026-04-12 16:10:54,808 | INFO | train_grpo_train | metrics_logged mode=train step=63 2026-04-12 16:11:04,280 | INFO | train_grpo_train | metrics_logged mode=train step=64 2026-04-12 16:11:13,348 | INFO | train_grpo_train | metrics_logged mode=train step=65 2026-04-12 16:11:21,387 | INFO | train_grpo_train | metrics_logged mode=train step=66 2026-04-12 16:11:32,451 | INFO | train_grpo_train | metrics_logged mode=train step=67 2026-04-12 16:11:43,691 | INFO | train_grpo_train | metrics_logged mode=train step=68 2026-04-12 16:11:52,200 | INFO | train_grpo_train | metrics_logged mode=train step=69 2026-04-12 16:12:00,825 | INFO | train_grpo_train | metrics_logged mode=train step=70 2026-04-12 16:12:09,287 | INFO | train_grpo_train | metrics_logged mode=train step=71 2026-04-12 16:12:25,266 | INFO | train_grpo_train | metrics_logged mode=train step=72 2026-04-12 16:12:33,953 | INFO | train_grpo_train | metrics_logged mode=train step=73 2026-04-12 16:12:43,374 | INFO | train_grpo_train | metrics_logged mode=train step=74 2026-04-12 16:12:52,193 | INFO | train_grpo_train | metrics_logged mode=train step=75 2026-04-12 16:13:03,247 | INFO | train_grpo_train | metrics_logged mode=train step=76 2026-04-12 16:13:12,191 | INFO | train_grpo_train | metrics_logged mode=train step=77 2026-04-12 16:13:20,650 | INFO | train_grpo_train | metrics_logged mode=train step=78 2026-04-12 16:13:29,556 | INFO | train_grpo_train | metrics_logged mode=train step=79 2026-04-12 16:13:38,506 | INFO | train_grpo_train | metrics_logged mode=train step=80 2026-04-12 16:13:47,705 | INFO | train_grpo_train | metrics_logged mode=train step=81 2026-04-12 16:14:01,861 | INFO | train_grpo_train | metrics_logged mode=train step=82 2026-04-12 16:14:09,962 | INFO | train_grpo_train | metrics_logged mode=train step=83 2026-04-12 16:14:18,582 | INFO | train_grpo_train | metrics_logged mode=train step=84 2026-04-12 16:14:29,108 | INFO | train_grpo_train | metrics_logged mode=train step=85 2026-04-12 16:14:36,893 | INFO | train_grpo_train | metrics_logged mode=train step=86 2026-04-12 16:14:45,928 | INFO | train_grpo_train | metrics_logged mode=train step=87 2026-04-12 16:14:58,462 | INFO | train_grpo_train | metrics_logged mode=train step=88 2026-04-12 16:15:06,781 | INFO | train_grpo_train | metrics_logged mode=train step=89 2026-04-12 16:15:15,010 | INFO | train_grpo_train | metrics_logged mode=train step=90 2026-04-12 16:15:26,018 | INFO | train_grpo_train | metrics_logged mode=train step=91 2026-04-12 16:15:39,925 | INFO | train_grpo_train | metrics_logged mode=train step=92 2026-04-12 16:15:48,245 | INFO | train_grpo_train | metrics_logged mode=train step=93 2026-04-12 16:15:57,552 | INFO | train_grpo_train | metrics_logged mode=train step=94 2026-04-12 16:16:06,000 | INFO | train_grpo_train | metrics_logged mode=train step=95 2026-04-12 16:16:15,182 | INFO | train_grpo_train | metrics_logged mode=train step=96 2026-04-12 16:16:25,902 | INFO | train_grpo_train | metrics_logged mode=train step=97 2026-04-12 16:16:35,761 | INFO | train_grpo_train | metrics_logged mode=train step=98 2026-04-12 16:16:45,601 | INFO | train_grpo_train | metrics_logged mode=train step=99 2026-04-12 16:16:56,652 | INFO | train_grpo_train | metrics_logged mode=train step=100 2026-04-12 16:19:30,443 | INFO | train_grpo_train | metrics_logged mode=eval step=100 2026-04-12 16:19:41,653 | INFO | train_grpo_train | metrics_logged mode=train step=101 2026-04-12 16:19:51,397 | INFO | train_grpo_train | metrics_logged mode=train step=102 2026-04-12 16:20:00,004 | INFO | train_grpo_train | metrics_logged mode=train step=103 2026-04-12 16:20:07,984 | INFO | train_grpo_train | metrics_logged mode=train step=104 2026-04-12 16:20:16,601 | INFO | train_grpo_train | metrics_logged mode=train step=105 2026-04-12 16:20:24,456 | INFO | train_grpo_train | metrics_logged mode=train step=106 2026-04-12 16:20:36,711 | INFO | train_grpo_train | metrics_logged mode=train step=107 2026-04-12 16:20:45,809 | INFO | train_grpo_train | metrics_logged mode=train step=108 2026-04-12 16:20:55,154 | INFO | train_grpo_train | metrics_logged mode=train step=109 2026-04-12 16:21:03,253 | INFO | train_grpo_train | metrics_logged mode=train step=110 2026-04-12 16:21:11,741 | INFO | train_grpo_train | metrics_logged mode=train step=111 2026-04-12 16:21:20,926 | INFO | train_grpo_train | metrics_logged mode=train step=112 2026-04-12 16:21:29,796 | INFO | train_grpo_train | metrics_logged mode=train step=113 2026-04-12 16:21:39,438 | INFO | train_grpo_train | metrics_logged mode=train step=114 2026-04-12 16:21:48,982 | INFO | train_grpo_train | metrics_logged mode=train step=115 2026-04-12 16:21:59,765 | INFO | train_grpo_train | metrics_logged mode=train step=116 2026-04-12 16:22:09,885 | INFO | train_grpo_train | metrics_logged mode=train step=117 2026-04-12 16:22:18,300 | INFO | train_grpo_train | metrics_logged mode=train step=118 2026-04-12 16:22:26,160 | INFO | train_grpo_train | metrics_logged mode=train step=119 2026-04-12 16:22:35,945 | INFO | train_grpo_train | metrics_logged mode=train step=120 2026-04-12 16:22:48,975 | INFO | train_grpo_train | metrics_logged mode=train step=121 2026-04-12 16:23:01,030 | INFO | train_grpo_train | metrics_logged mode=train step=122 2026-04-12 16:23:11,917 | INFO | train_grpo_train | metrics_logged mode=train step=123 2026-04-12 16:23:20,924 | INFO | train_grpo_train | metrics_logged mode=train step=124 2026-04-12 16:23:29,322 | INFO | train_grpo_train | metrics_logged mode=train step=125 2026-04-12 16:23:42,052 | INFO | train_grpo_train | metrics_logged mode=train step=126 2026-04-12 16:23:50,305 | INFO | train_grpo_train | metrics_logged mode=train step=127 2026-04-12 16:23:59,185 | INFO | train_grpo_train | metrics_logged mode=train step=128 2026-04-12 16:24:08,446 | INFO | train_grpo_train | metrics_logged mode=train step=129 2026-04-12 16:24:18,388 | INFO | train_grpo_train | metrics_logged mode=train step=130 2026-04-12 16:24:29,020 | INFO | train_grpo_train | metrics_logged mode=train step=131 2026-04-12 16:24:37,631 | INFO | train_grpo_train | metrics_logged mode=train step=132 2026-04-12 16:24:46,148 | INFO | train_grpo_train | metrics_logged mode=train step=133 2026-04-12 16:24:55,379 | INFO | train_grpo_train | metrics_logged mode=train step=134 2026-04-12 16:25:04,693 | INFO | train_grpo_train | metrics_logged mode=train step=135 2026-04-12 16:25:18,651 | INFO | train_grpo_train | metrics_logged mode=train step=136 2026-04-12 16:25:32,753 | INFO | train_grpo_train | metrics_logged mode=train step=137 2026-04-12 16:25:41,710 | INFO | train_grpo_train | metrics_logged mode=train step=138 2026-04-12 16:25:50,090 | INFO | train_grpo_train | metrics_logged mode=train step=139 2026-04-12 16:25:58,455 | INFO | train_grpo_train | metrics_logged mode=train step=140 2026-04-12 16:26:06,535 | INFO | train_grpo_train | metrics_logged mode=train step=141 2026-04-12 16:26:15,475 | INFO | train_grpo_train | metrics_logged mode=train step=142 2026-04-12 16:26:29,552 | INFO | train_grpo_train | metrics_logged mode=train step=143 2026-04-12 16:26:38,904 | INFO | train_grpo_train | metrics_logged mode=train step=144 2026-04-12 16:26:48,841 | INFO | train_grpo_train | metrics_logged mode=train step=145 2026-04-12 16:27:06,770 | INFO | train_grpo_train | metrics_logged mode=train step=146 2026-04-12 16:27:21,314 | INFO | train_grpo_train | metrics_logged mode=train step=147 2026-04-12 16:27:35,080 | INFO | train_grpo_train | metrics_logged mode=train step=148 2026-04-12 16:27:50,334 | INFO | train_grpo_train | metrics_logged mode=train step=149 2026-04-12 16:27:58,445 | INFO | train_grpo_train | metrics_logged mode=train step=150 2026-04-12 16:30:27,318 | INFO | train_grpo_train | metrics_logged mode=eval step=150 2026-04-12 16:30:37,425 | INFO | train_grpo_train | metrics_logged mode=train step=151 2026-04-12 16:30:46,684 | INFO | train_grpo_train | metrics_logged mode=train step=152 2026-04-12 16:30:55,806 | INFO | train_grpo_train | metrics_logged mode=train step=153 2026-04-12 16:31:05,060 | INFO | train_grpo_train | metrics_logged mode=train step=154 2026-04-12 16:31:13,054 | INFO | train_grpo_train | metrics_logged mode=train step=155 2026-04-12 16:31:26,975 | INFO | train_grpo_train | metrics_logged mode=train step=156 2026-04-12 16:31:34,530 | INFO | train_grpo_train | metrics_logged mode=train step=157 2026-04-12 16:31:48,122 | INFO | train_grpo_train | metrics_logged mode=train step=158 2026-04-12 16:32:01,943 | INFO | train_grpo_train | metrics_logged mode=train step=159 2026-04-12 16:32:16,892 | INFO | train_grpo_train | metrics_logged mode=train step=160 2026-04-12 16:32:32,078 | INFO | train_grpo_train | metrics_logged mode=train step=161 2026-04-12 16:32:41,567 | INFO | train_grpo_train | metrics_logged mode=train step=162 2026-04-12 16:32:50,006 | INFO | train_grpo_train | metrics_logged mode=train step=163 2026-04-12 16:32:59,922 | INFO | train_grpo_train | metrics_logged mode=train step=164 2026-04-12 16:33:08,995 | INFO | train_grpo_train | metrics_logged mode=train step=165 2026-04-12 16:33:22,863 | INFO | train_grpo_train | metrics_logged mode=train step=166 2026-04-12 16:33:32,028 | INFO | train_grpo_train | metrics_logged mode=train step=167 2026-04-12 16:33:45,648 | INFO | train_grpo_train | metrics_logged mode=train step=168 2026-04-12 16:33:56,869 | INFO | train_grpo_train | metrics_logged mode=train step=169 2026-04-12 16:34:04,890 | INFO | train_grpo_train | metrics_logged mode=train step=170 2026-04-12 16:34:14,687 | INFO | train_grpo_train | metrics_logged mode=train step=171 2026-04-12 16:34:28,130 | INFO | train_grpo_train | metrics_logged mode=train step=172 2026-04-12 16:34:36,800 | INFO | train_grpo_train | metrics_logged mode=train step=173 2026-04-12 16:34:45,072 | INFO | train_grpo_train | metrics_logged mode=train step=174 2026-04-12 16:34:53,163 | INFO | train_grpo_train | metrics_logged mode=train step=175 2026-04-12 16:35:06,666 | INFO | train_grpo_train | metrics_logged mode=train step=176 2026-04-12 16:35:19,569 | INFO | train_grpo_train | metrics_logged mode=train step=177 2026-04-12 16:35:33,294 | INFO | train_grpo_train | metrics_logged mode=train step=178 2026-04-12 16:35:47,075 | INFO | train_grpo_train | metrics_logged mode=train step=179 2026-04-12 16:36:00,944 | INFO | train_grpo_train | metrics_logged mode=train step=180 2026-04-12 16:36:11,838 | INFO | train_grpo_train | metrics_logged mode=train step=181 2026-04-12 16:36:20,580 | INFO | train_grpo_train | metrics_logged mode=train step=182 2026-04-12 16:36:27,858 | INFO | train_grpo_train | metrics_logged mode=train step=183 2026-04-12 16:36:41,094 | INFO | train_grpo_train | metrics_logged mode=train step=184 2026-04-12 16:36:51,728 | INFO | train_grpo_train | metrics_logged mode=train step=185 2026-04-12 16:37:05,531 | INFO | train_grpo_train | metrics_logged mode=train step=186 2026-04-12 16:37:19,403 | INFO | train_grpo_train | metrics_logged mode=train step=187 2026-04-12 16:37:27,546 | INFO | train_grpo_train | metrics_logged mode=train step=188 2026-04-12 16:37:40,930 | INFO | train_grpo_train | metrics_logged mode=train step=189 2026-04-12 16:37:51,703 | INFO | train_grpo_train | metrics_logged mode=train step=190 2026-04-12 16:37:59,943 | INFO | train_grpo_train | metrics_logged mode=train step=191 2026-04-12 16:38:13,495 | INFO | train_grpo_train | metrics_logged mode=train step=192 2026-04-12 16:38:26,913 | INFO | train_grpo_train | metrics_logged mode=train step=193 2026-04-12 16:38:39,833 | INFO | train_grpo_train | metrics_logged mode=train step=194 2026-04-12 16:38:49,421 | INFO | train_grpo_train | metrics_logged mode=train step=195 2026-04-12 16:39:03,225 | INFO | train_grpo_train | metrics_logged mode=train step=196 2026-04-12 16:39:17,394 | INFO | train_grpo_train | metrics_logged mode=train step=197 2026-04-12 16:39:31,535 | INFO | train_grpo_train | metrics_logged mode=train step=198 2026-04-12 16:39:39,687 | INFO | train_grpo_train | metrics_logged mode=train step=199 2026-04-12 16:39:47,669 | INFO | train_grpo_train | metrics_logged mode=train step=200 2026-04-12 16:42:18,733 | INFO | train_grpo_train | metrics_logged mode=eval step=200 2026-04-12 16:42:29,762 | INFO | train_grpo_train | metrics_logged mode=train step=201 2026-04-12 16:42:43,702 | INFO | train_grpo_train | metrics_logged mode=train step=202 2026-04-12 16:42:52,052 | INFO | train_grpo_train | metrics_logged mode=train step=203 2026-04-12 16:43:06,228 | INFO | train_grpo_train | metrics_logged mode=train step=204 2026-04-12 16:43:20,620 | INFO | train_grpo_train | metrics_logged mode=train step=205 2026-04-12 16:43:34,635 | INFO | train_grpo_train | metrics_logged mode=train step=206 2026-04-12 16:43:48,830 | INFO | train_grpo_train | metrics_logged mode=train step=207 2026-04-12 16:43:57,663 | INFO | train_grpo_train | metrics_logged mode=train step=208 2026-04-12 16:44:11,996 | INFO | train_grpo_train | metrics_logged mode=train step=209 2026-04-12 16:44:26,206 | INFO | train_grpo_train | metrics_logged mode=train step=210 2026-04-12 16:44:35,151 | INFO | train_grpo_train | metrics_logged mode=train step=211 2026-04-12 16:44:49,771 | INFO | train_grpo_train | metrics_logged mode=train step=212 2026-04-12 16:44:57,129 | INFO | train_grpo_train | metrics_logged mode=train step=213 2026-04-12 16:45:11,224 | INFO | train_grpo_train | metrics_logged mode=train step=214 2026-04-12 16:45:20,277 | INFO | train_grpo_train | metrics_logged mode=train step=215 2026-04-12 16:45:33,499 | INFO | train_grpo_train | metrics_logged mode=train step=216 2026-04-12 16:45:41,967 | INFO | train_grpo_train | metrics_logged mode=train step=217 2026-04-12 16:45:50,827 | INFO | train_grpo_train | metrics_logged mode=train step=218 2026-04-12 16:45:59,167 | INFO | train_grpo_train | metrics_logged mode=train step=219 2026-04-12 16:46:13,040 | INFO | train_grpo_train | metrics_logged mode=train step=220 2026-04-12 16:46:26,816 | INFO | train_grpo_train | metrics_logged mode=train step=221 2026-04-12 16:46:41,246 | INFO | train_grpo_train | metrics_logged mode=train step=222 2026-04-12 16:46:50,234 | INFO | train_grpo_train | metrics_logged mode=train step=223 2026-04-12 16:47:04,141 | INFO | train_grpo_train | metrics_logged mode=train step=224 2026-04-12 16:47:12,721 | INFO | train_grpo_train | metrics_logged mode=train step=225 2026-04-12 16:47:26,341 | INFO | train_grpo_train | metrics_logged mode=train step=226 2026-04-12 16:47:35,584 | INFO | train_grpo_train | metrics_logged mode=train step=227 2026-04-12 16:47:44,664 | INFO | train_grpo_train | metrics_logged mode=train step=228 2026-04-12 16:47:58,663 | INFO | train_grpo_train | metrics_logged mode=train step=229 2026-04-12 16:48:06,087 | INFO | train_grpo_train | metrics_logged mode=train step=230 2026-04-12 16:48:14,257 | INFO | train_grpo_train | metrics_logged mode=train step=231 2026-04-12 16:48:27,232 | INFO | train_grpo_train | metrics_logged mode=train step=232 2026-04-12 16:48:35,389 | INFO | train_grpo_train | metrics_logged mode=train step=233 2026-04-12 16:48:44,331 | INFO | train_grpo_train | metrics_logged mode=train step=234 2026-04-12 16:48:52,974 | INFO | train_grpo_train | metrics_logged mode=train step=235 2026-04-12 16:49:01,635 | INFO | train_grpo_train | metrics_logged mode=train step=236 2026-04-12 16:49:10,619 | INFO | train_grpo_train | metrics_logged mode=train step=237 2026-04-12 16:49:25,225 | INFO | train_grpo_train | metrics_logged mode=train step=238 2026-04-12 16:49:34,285 | INFO | train_grpo_train | metrics_logged mode=train step=239 2026-04-12 16:49:48,157 | INFO | train_grpo_train | metrics_logged mode=train step=240 2026-04-12 16:50:01,789 | INFO | train_grpo_train | metrics_logged mode=train step=241 2026-04-12 16:50:09,431 | INFO | train_grpo_train | metrics_logged mode=train step=242 2026-04-12 16:50:23,535 | INFO | train_grpo_train | metrics_logged mode=train step=243 2026-04-12 16:50:31,778 | INFO | train_grpo_train | metrics_logged mode=train step=244 2026-04-12 16:50:40,437 | INFO | train_grpo_train | metrics_logged mode=train step=245 2026-04-12 16:50:55,386 | INFO | train_grpo_train | metrics_logged mode=train step=246 2026-04-12 16:51:03,583 | INFO | train_grpo_train | metrics_logged mode=train step=247 2026-04-12 16:51:17,396 | INFO | train_grpo_train | metrics_logged mode=train step=248 2026-04-12 16:51:27,547 | INFO | train_grpo_train | metrics_logged mode=train step=249 2026-04-12 16:51:36,126 | INFO | train_grpo_train | metrics_logged mode=train step=250 2026-04-12 16:53:49,597 | INFO | train_grpo_train | metrics_logged mode=eval step=250 2026-04-12 16:54:02,603 | INFO | train_grpo_train | metrics_logged mode=train step=251 2026-04-12 16:54:12,641 | INFO | train_grpo_train | metrics_logged mode=train step=252 2026-04-12 16:54:25,808 | INFO | train_grpo_train | metrics_logged mode=train step=253 2026-04-12 16:54:33,618 | INFO | train_grpo_train | metrics_logged mode=train step=254 2026-04-12 16:54:41,071 | INFO | train_grpo_train | metrics_logged mode=train step=255 2026-04-12 16:54:54,743 | INFO | train_grpo_train | metrics_logged mode=train step=256 2026-04-12 16:55:02,663 | INFO | train_grpo_train | metrics_logged mode=train step=257 2026-04-12 16:55:11,965 | INFO | train_grpo_train | metrics_logged mode=train step=258 2026-04-12 16:55:20,662 | INFO | train_grpo_train | metrics_logged mode=train step=259 2026-04-12 16:55:29,004 | INFO | train_grpo_train | metrics_logged mode=train step=260 2026-04-12 16:55:36,266 | INFO | train_grpo_train | metrics_logged mode=train step=261 2026-04-12 16:55:46,838 | INFO | train_grpo_train | metrics_logged mode=train step=262 2026-04-12 16:55:54,733 | INFO | train_grpo_train | metrics_logged mode=train step=263 2026-04-12 16:56:04,028 | INFO | train_grpo_train | metrics_logged mode=train step=264 2026-04-12 16:56:17,394 | INFO | train_grpo_train | metrics_logged mode=train step=265 2026-04-12 16:56:31,008 | INFO | train_grpo_train | metrics_logged mode=train step=266 2026-04-12 16:56:38,816 | INFO | train_grpo_train | metrics_logged mode=train step=267 2026-04-12 16:56:48,095 | INFO | train_grpo_train | metrics_logged mode=train step=268 2026-04-12 16:57:02,364 | INFO | train_grpo_train | metrics_logged mode=train step=269 2026-04-12 16:57:16,004 | INFO | train_grpo_train | metrics_logged mode=train step=270 2026-04-12 16:57:24,909 | INFO | train_grpo_train | metrics_logged mode=train step=271 2026-04-12 16:57:32,989 | INFO | train_grpo_train | metrics_logged mode=train step=272 2026-04-12 16:57:41,514 | INFO | train_grpo_train | metrics_logged mode=train step=273 2026-04-12 16:57:49,722 | INFO | train_grpo_train | metrics_logged mode=train step=274 2026-04-12 16:57:58,238 | INFO | train_grpo_train | metrics_logged mode=train step=275 2026-04-12 16:58:07,099 | INFO | train_grpo_train | metrics_logged mode=train step=276 2026-04-12 16:58:17,933 | INFO | train_grpo_train | metrics_logged mode=train step=277 2026-04-12 16:58:26,348 | INFO | train_grpo_train | metrics_logged mode=train step=278 2026-04-12 16:58:40,372 | INFO | train_grpo_train | metrics_logged mode=train step=279 2026-04-12 16:58:49,621 | INFO | train_grpo_train | metrics_logged mode=train step=280 2026-04-12 16:58:58,420 | INFO | train_grpo_train | metrics_logged mode=train step=281 2026-04-12 16:59:07,335 | INFO | train_grpo_train | metrics_logged mode=train step=282 2026-04-12 16:59:14,981 | INFO | train_grpo_train | metrics_logged mode=train step=283 2026-04-12 16:59:25,169 | INFO | train_grpo_train | metrics_logged mode=train step=284 2026-04-12 16:59:38,583 | INFO | train_grpo_train | metrics_logged mode=train step=285 2026-04-12 16:59:53,102 | INFO | train_grpo_train | metrics_logged mode=train step=286 2026-04-12 17:00:02,067 | INFO | train_grpo_train | metrics_logged mode=train step=287 2026-04-12 17:00:09,978 | INFO | train_grpo_train | metrics_logged mode=train step=288 2026-04-12 17:00:18,243 | INFO | train_grpo_train | metrics_logged mode=train step=289 2026-04-12 17:00:25,403 | INFO | train_grpo_train | metrics_logged mode=train step=290 2026-04-12 17:00:36,545 | INFO | train_grpo_train | metrics_logged mode=train step=291 2026-04-12 17:00:48,690 | INFO | train_grpo_train | metrics_logged mode=train step=292 2026-04-12 17:00:58,219 | INFO | train_grpo_train | metrics_logged mode=train step=293 2026-04-12 17:01:07,429 | INFO | train_grpo_train | metrics_logged mode=train step=294 2026-04-12 17:01:18,927 | INFO | train_grpo_train | metrics_logged mode=train step=295 2026-04-12 17:01:27,932 | INFO | train_grpo_train | metrics_logged mode=train step=296 2026-04-12 17:01:36,642 | INFO | train_grpo_train | metrics_logged mode=train step=297 2026-04-12 17:01:44,851 | INFO | train_grpo_train | metrics_logged mode=train step=298 2026-04-12 17:01:53,684 | INFO | train_grpo_train | metrics_logged mode=train step=299 2026-04-12 17:02:03,373 | INFO | train_grpo_train | metrics_logged mode=train step=300 2026-04-12 17:04:15,258 | INFO | train_grpo_train | metrics_logged mode=eval step=300 2026-04-12 17:04:26,090 | INFO | train_grpo_train | metrics_logged mode=train step=301 2026-04-12 17:04:33,412 | INFO | train_grpo_train | metrics_logged mode=train step=302 2026-04-12 17:04:40,946 | INFO | train_grpo_train | metrics_logged mode=train step=303 2026-04-12 17:04:52,838 | INFO | train_grpo_train | metrics_logged mode=train step=304 2026-04-12 17:04:59,862 | INFO | train_grpo_train | metrics_logged mode=train step=305 2026-04-12 17:05:07,936 | INFO | train_grpo_train | metrics_logged mode=train step=306 2026-04-12 17:05:16,654 | INFO | train_grpo_train | metrics_logged mode=train step=307 2026-04-12 17:05:25,354 | INFO | train_grpo_train | metrics_logged mode=train step=308 2026-04-12 17:05:36,011 | INFO | train_grpo_train | metrics_logged mode=train step=309 2026-04-12 17:05:43,739 | INFO | train_grpo_train | metrics_logged mode=train step=310 2026-04-12 17:05:54,306 | INFO | train_grpo_train | metrics_logged mode=train step=311 2026-04-12 17:06:03,628 | INFO | train_grpo_train | metrics_logged mode=train step=312 2026-04-12 17:06:11,543 | INFO | train_grpo_train | metrics_logged mode=train step=313 2026-04-12 17:06:19,412 | INFO | train_grpo_train | metrics_logged mode=train step=314 2026-04-12 17:06:29,122 | INFO | train_grpo_train | metrics_logged mode=train step=315 2026-04-12 17:06:38,944 | INFO | train_grpo_train | metrics_logged mode=train step=316 2026-04-12 17:06:52,017 | INFO | train_grpo_train | metrics_logged mode=train step=317 2026-04-12 17:07:01,186 | INFO | train_grpo_train | metrics_logged mode=train step=318 2026-04-12 17:07:09,423 | INFO | train_grpo_train | metrics_logged mode=train step=319 2026-04-12 17:07:18,145 | INFO | train_grpo_train | metrics_logged mode=train step=320 2026-04-12 17:07:33,404 | INFO | train_grpo_train | metrics_logged mode=train step=321 2026-04-12 17:07:47,207 | INFO | train_grpo_train | metrics_logged mode=train step=322 2026-04-12 17:07:55,953 | INFO | train_grpo_train | metrics_logged mode=train step=323 2026-04-12 17:08:03,594 | INFO | train_grpo_train | metrics_logged mode=train step=324 2026-04-12 17:08:16,900 | INFO | train_grpo_train | metrics_logged mode=train step=325 2026-04-12 17:08:27,656 | INFO | train_grpo_train | metrics_logged mode=train step=326 2026-04-12 17:08:41,647 | INFO | train_grpo_train | metrics_logged mode=train step=327 2026-04-12 17:08:55,532 | INFO | train_grpo_train | metrics_logged mode=train step=328 2026-04-12 17:09:03,952 | INFO | train_grpo_train | metrics_logged mode=train step=329 2026-04-12 17:09:14,512 | INFO | train_grpo_train | metrics_logged mode=train step=330 2026-04-12 17:09:24,775 | INFO | train_grpo_train | metrics_logged mode=train step=331 2026-04-12 17:09:32,645 | INFO | train_grpo_train | metrics_logged mode=train step=332 2026-04-12 17:09:45,757 | INFO | train_grpo_train | metrics_logged mode=train step=333 2026-04-12 17:09:53,582 | INFO | train_grpo_train | metrics_logged mode=train step=334 2026-04-12 17:10:07,507 | INFO | train_grpo_train | metrics_logged mode=train step=335 2026-04-12 17:10:16,595 | INFO | train_grpo_train | metrics_logged mode=train step=336 2026-04-12 17:10:23,943 | INFO | train_grpo_train | metrics_logged mode=train step=337 2026-04-12 17:10:32,387 | INFO | train_grpo_train | metrics_logged mode=train step=338 2026-04-12 17:10:43,827 | INFO | train_grpo_train | metrics_logged mode=train step=339 2026-04-12 17:10:57,485 | INFO | train_grpo_train | metrics_logged mode=train step=340 2026-04-12 17:11:05,799 | INFO | train_grpo_train | metrics_logged mode=train step=341 2026-04-12 17:11:19,299 | INFO | train_grpo_train | metrics_logged mode=train step=342 2026-04-12 17:11:27,017 | INFO | train_grpo_train | metrics_logged mode=train step=343 2026-04-12 17:11:35,270 | INFO | train_grpo_train | metrics_logged mode=train step=344 2026-04-12 17:11:43,374 | INFO | train_grpo_train | metrics_logged mode=train step=345 2026-04-12 17:11:57,056 | INFO | train_grpo_train | metrics_logged mode=train step=346 2026-04-12 17:12:04,245 | INFO | train_grpo_train | metrics_logged mode=train step=347 2026-04-12 17:12:12,288 | INFO | train_grpo_train | metrics_logged mode=train step=348 2026-04-12 17:12:20,649 | INFO | train_grpo_train | metrics_logged mode=train step=349 2026-04-12 17:12:30,711 | INFO | train_grpo_train | metrics_logged mode=train step=350 2026-04-12 17:14:55,503 | INFO | train_grpo_train | metrics_logged mode=eval step=350 2026-04-12 17:15:08,810 | INFO | train_grpo_train | metrics_logged mode=train step=351 2026-04-12 17:15:17,111 | INFO | train_grpo_train | metrics_logged mode=train step=352 2026-04-12 17:15:26,031 | INFO | train_grpo_train | metrics_logged mode=train step=353 2026-04-12 17:15:35,417 | INFO | train_grpo_train | metrics_logged mode=train step=354 2026-04-12 17:15:45,487 | INFO | train_grpo_train | metrics_logged mode=train step=355 2026-04-12 17:15:59,887 | INFO | train_grpo_train | metrics_logged mode=train step=356 2026-04-12 17:16:07,499 | INFO | train_grpo_train | metrics_logged mode=train step=357 2026-04-12 17:16:16,312 | INFO | train_grpo_train | metrics_logged mode=train step=358 2026-04-12 17:16:26,620 | INFO | train_grpo_train | metrics_logged mode=train step=359 2026-04-12 17:16:36,510 | INFO | train_grpo_train | metrics_logged mode=train step=360 2026-04-12 17:16:44,616 | INFO | train_grpo_train | metrics_logged mode=train step=361 2026-04-12 17:16:54,834 | INFO | train_grpo_train | metrics_logged mode=train step=362 2026-04-12 17:17:09,669 | INFO | train_grpo_train | metrics_logged mode=train step=363 2026-04-12 17:17:19,761 | INFO | train_grpo_train | metrics_logged mode=train step=364 2026-04-12 17:17:29,194 | INFO | train_grpo_train | metrics_logged mode=train step=365 2026-04-12 17:17:38,374 | INFO | train_grpo_train | metrics_logged mode=train step=366 2026-04-12 17:17:47,709 | INFO | train_grpo_train | metrics_logged mode=train step=367 2026-04-12 17:17:55,919 | INFO | train_grpo_train | metrics_logged mode=train step=368 2026-04-12 17:18:07,104 | INFO | train_grpo_train | metrics_logged mode=train step=369 2026-04-12 17:18:17,180 | INFO | train_grpo_train | metrics_logged mode=train step=370 2026-04-12 17:18:29,723 | INFO | train_grpo_train | metrics_logged mode=train step=371 2026-04-12 17:18:40,127 | INFO | train_grpo_train | metrics_logged mode=train step=372 2026-04-12 17:18:49,218 | INFO | train_grpo_train | metrics_logged mode=train step=373 2026-04-12 17:18:57,593 | INFO | train_grpo_train | metrics_logged mode=train step=374 2026-04-12 17:19:08,946 | INFO | train_grpo_train | metrics_logged mode=train step=375 2026-04-12 17:19:17,784 | INFO | train_grpo_train | metrics_logged mode=train step=376 2026-04-12 17:19:26,685 | INFO | train_grpo_train | metrics_logged mode=train step=377 2026-04-12 17:19:35,001 | INFO | train_grpo_train | metrics_logged mode=train step=378 2026-04-12 17:19:44,253 | INFO | train_grpo_train | metrics_logged mode=train step=379 2026-04-12 17:19:53,296 | INFO | train_grpo_train | metrics_logged mode=train step=380 2026-04-12 17:20:01,923 | INFO | train_grpo_train | metrics_logged mode=train step=381 2026-04-12 17:20:09,950 | INFO | train_grpo_train | metrics_logged mode=train step=382 2026-04-12 17:20:18,175 | INFO | train_grpo_train | metrics_logged mode=train step=383 2026-04-12 17:20:31,938 | INFO | train_grpo_train | metrics_logged mode=train step=384 2026-04-12 17:20:41,260 | INFO | train_grpo_train | metrics_logged mode=train step=385 2026-04-12 17:20:55,060 | INFO | train_grpo_train | metrics_logged mode=train step=386 2026-04-12 17:21:10,412 | INFO | train_grpo_train | metrics_logged mode=train step=387 2026-04-12 17:21:25,943 | INFO | train_grpo_train | metrics_logged mode=train step=388 2026-04-12 17:21:39,924 | INFO | train_grpo_train | metrics_logged mode=train step=389 2026-04-12 17:21:54,244 | INFO | train_grpo_train | metrics_logged mode=train step=390 2026-04-12 17:22:03,789 | INFO | train_grpo_train | metrics_logged mode=train step=391 2026-04-12 17:22:12,984 | INFO | train_grpo_train | metrics_logged mode=train step=392 2026-04-12 17:22:27,354 | INFO | train_grpo_train | metrics_logged mode=train step=393 2026-04-12 17:22:36,949 | INFO | train_grpo_train | metrics_logged mode=train step=394 2026-04-12 17:22:45,217 | INFO | train_grpo_train | metrics_logged mode=train step=395 2026-04-12 17:22:59,875 | INFO | train_grpo_train | metrics_logged mode=train step=396 2026-04-12 17:23:14,807 | INFO | train_grpo_train | metrics_logged mode=train step=397 2026-04-12 17:23:28,279 | INFO | train_grpo_train | metrics_logged mode=train step=398 2026-04-12 17:23:41,586 | INFO | train_grpo_train | metrics_logged mode=train step=399 2026-04-12 17:23:49,918 | INFO | train_grpo_train | metrics_logged mode=train step=400 2026-04-12 17:26:18,486 | INFO | train_grpo_train | metrics_logged mode=eval step=400 2026-04-12 17:26:31,547 | INFO | train_grpo_train | metrics_logged mode=train step=401 2026-04-12 17:26:40,407 | INFO | train_grpo_train | metrics_logged mode=train step=402 2026-04-12 17:26:48,673 | INFO | train_grpo_train | metrics_logged mode=train step=403 2026-04-12 17:26:56,796 | INFO | train_grpo_train | metrics_logged mode=train step=404 2026-04-12 17:27:05,499 | INFO | train_grpo_train | metrics_logged mode=train step=405 2026-04-12 17:27:14,116 | INFO | train_grpo_train | metrics_logged mode=train step=406 2026-04-12 17:27:28,819 | INFO | train_grpo_train | metrics_logged mode=train step=407 2026-04-12 17:27:39,741 | INFO | train_grpo_train | metrics_logged mode=train step=408 2026-04-12 17:27:53,543 | INFO | train_grpo_train | metrics_logged mode=train step=409 2026-04-12 17:28:02,998 | INFO | train_grpo_train | metrics_logged mode=train step=410 2026-04-12 17:28:11,737 | INFO | train_grpo_train | metrics_logged mode=train step=411 2026-04-12 17:28:21,868 | INFO | train_grpo_train | metrics_logged mode=train step=412 2026-04-12 17:28:30,690 | INFO | train_grpo_train | metrics_logged mode=train step=413 2026-04-12 17:28:44,011 | INFO | train_grpo_train | metrics_logged mode=train step=414 2026-04-12 17:28:53,779 | INFO | train_grpo_train | metrics_logged mode=train step=415 2026-04-12 17:29:03,303 | INFO | train_grpo_train | metrics_logged mode=train step=416 2026-04-12 17:29:11,237 | INFO | train_grpo_train | metrics_logged mode=train step=417 2026-04-12 17:29:25,758 | INFO | train_grpo_train | metrics_logged mode=train step=418 2026-04-12 17:29:39,410 | INFO | train_grpo_train | metrics_logged mode=train step=419 2026-04-12 17:29:52,857 | INFO | train_grpo_train | metrics_logged mode=train step=420 2026-04-12 17:30:01,673 | INFO | train_grpo_train | metrics_logged mode=train step=421 2026-04-12 17:30:11,360 | INFO | train_grpo_train | metrics_logged mode=train step=422 2026-04-12 17:30:19,999 | INFO | train_grpo_train | metrics_logged mode=train step=423 2026-04-12 17:30:30,058 | INFO | train_grpo_train | metrics_logged mode=train step=424 2026-04-12 17:30:37,481 | INFO | train_grpo_train | metrics_logged mode=train step=425 2026-04-12 17:30:47,907 | INFO | train_grpo_train | metrics_logged mode=train step=426 2026-04-12 17:30:56,731 | INFO | train_grpo_train | metrics_logged mode=train step=427 2026-04-12 17:31:04,528 | INFO | train_grpo_train | metrics_logged mode=train step=428 2026-04-12 17:31:19,148 | INFO | train_grpo_train | metrics_logged mode=train step=429 2026-04-12 17:31:28,317 | INFO | train_grpo_train | metrics_logged mode=train step=430 2026-04-12 17:31:36,386 | INFO | train_grpo_train | metrics_logged mode=train step=431 2026-04-12 17:31:44,855 | INFO | train_grpo_train | metrics_logged mode=train step=432 2026-04-12 17:31:55,347 | INFO | train_grpo_train | metrics_logged mode=train step=433 2026-04-12 17:32:09,743 | INFO | train_grpo_train | metrics_logged mode=train step=434 2026-04-12 17:32:19,670 | INFO | train_grpo_train | metrics_logged mode=train step=435 2026-04-12 17:32:28,370 | INFO | train_grpo_train | metrics_logged mode=train step=436 2026-04-12 17:32:37,132 | INFO | train_grpo_train | metrics_logged mode=train step=437 2026-04-12 17:32:50,377 | INFO | train_grpo_train | metrics_logged mode=train step=438 2026-04-12 17:32:58,709 | INFO | train_grpo_train | metrics_logged mode=train step=439 2026-04-12 17:33:07,030 | INFO | train_grpo_train | metrics_logged mode=train step=440 2026-04-12 17:33:15,416 | INFO | train_grpo_train | metrics_logged mode=train step=441 2026-04-12 17:33:24,085 | INFO | train_grpo_train | metrics_logged mode=train step=442 2026-04-12 17:33:33,622 | INFO | train_grpo_train | metrics_logged mode=train step=443 2026-04-12 17:33:47,775 | INFO | train_grpo_train | metrics_logged mode=train step=444 2026-04-12 17:33:56,350 | INFO | train_grpo_train | metrics_logged mode=train step=445 2026-04-12 17:34:09,953 | INFO | train_grpo_train | metrics_logged mode=train step=446 2026-04-12 17:34:19,482 | INFO | train_grpo_train | metrics_logged mode=train step=447 2026-04-12 17:34:27,660 | INFO | train_grpo_train | metrics_logged mode=train step=448 2026-04-12 17:34:41,804 | INFO | train_grpo_train | metrics_logged mode=train step=449 2026-04-12 17:34:55,845 | INFO | train_grpo_train | metrics_logged mode=train step=450 2026-04-12 17:37:20,096 | INFO | train_grpo_train | metrics_logged mode=eval step=450 2026-04-12 17:37:36,247 | INFO | train_grpo_train | metrics_logged mode=train step=451 2026-04-12 17:37:45,853 | INFO | train_grpo_train | metrics_logged mode=train step=452 2026-04-12 17:37:54,216 | INFO | train_grpo_train | metrics_logged mode=train step=453 2026-04-12 17:38:08,356 | INFO | train_grpo_train | metrics_logged mode=train step=454 2026-04-12 17:38:17,512 | INFO | train_grpo_train | metrics_logged mode=train step=455 2026-04-12 17:38:30,975 | INFO | train_grpo_train | metrics_logged mode=train step=456 2026-04-12 17:38:40,022 | INFO | train_grpo_train | metrics_logged mode=train step=457 2026-04-12 17:38:48,508 | INFO | train_grpo_train | metrics_logged mode=train step=458 2026-04-12 17:38:59,537 | INFO | train_grpo_train | metrics_logged mode=train step=459 2026-04-12 17:39:08,830 | INFO | train_grpo_train | metrics_logged mode=train step=460 2026-04-12 17:39:17,948 | INFO | train_grpo_train | metrics_logged mode=train step=461 2026-04-12 17:39:27,356 | INFO | train_grpo_train | metrics_logged mode=train step=462 2026-04-12 17:39:37,522 | INFO | train_grpo_train | metrics_logged mode=train step=463 2026-04-12 17:39:45,788 | INFO | train_grpo_train | metrics_logged mode=train step=464 2026-04-12 17:39:54,658 | INFO | train_grpo_train | metrics_logged mode=train step=465 2026-04-12 17:40:03,408 | INFO | train_grpo_train | metrics_logged mode=train step=466 2026-04-12 17:40:17,440 | INFO | train_grpo_train | metrics_logged mode=train step=467 2026-04-12 17:40:26,375 | INFO | train_grpo_train | metrics_logged mode=train step=468 2026-04-12 17:40:34,141 | INFO | train_grpo_train | metrics_logged mode=train step=469 2026-04-12 17:40:42,627 | INFO | train_grpo_train | metrics_logged mode=train step=470 2026-04-12 17:40:51,816 | INFO | train_grpo_train | metrics_logged mode=train step=471 2026-04-12 17:41:05,576 | INFO | train_grpo_train | metrics_logged mode=train step=472 2026-04-12 17:41:14,173 | INFO | train_grpo_train | metrics_logged mode=train step=473 2026-04-12 17:41:28,354 | INFO | train_grpo_train | metrics_logged mode=train step=474 2026-04-12 17:41:37,110 | INFO | train_grpo_train | metrics_logged mode=train step=475 2026-04-12 17:41:50,774 | INFO | train_grpo_train | metrics_logged mode=train step=476 2026-04-12 17:41:59,891 | INFO | train_grpo_train | metrics_logged mode=train step=477 2026-04-12 17:42:09,889 | INFO | train_grpo_train | metrics_logged mode=train step=478 2026-04-12 17:42:17,672 | INFO | train_grpo_train | metrics_logged mode=train step=479 2026-04-12 17:42:25,663 | INFO | train_grpo_train | metrics_logged mode=train step=480 2026-04-12 17:42:33,610 | INFO | train_grpo_train | metrics_logged mode=train step=481 2026-04-12 17:42:47,895 | INFO | train_grpo_train | metrics_logged mode=train step=482 2026-04-12 17:42:55,695 | INFO | train_grpo_train | metrics_logged mode=train step=483 2026-04-12 17:43:03,452 | INFO | train_grpo_train | metrics_logged mode=train step=484 2026-04-12 17:43:11,700 | INFO | train_grpo_train | metrics_logged mode=train step=485 2026-04-12 17:43:21,745 | INFO | train_grpo_train | metrics_logged mode=train step=486 2026-04-12 17:43:35,702 | INFO | train_grpo_train | metrics_logged mode=train step=487 2026-04-12 17:43:44,560 | INFO | train_grpo_train | metrics_logged mode=train step=488 2026-04-12 17:43:53,577 | INFO | train_grpo_train | metrics_logged mode=train step=489 2026-04-12 17:44:02,740 | INFO | train_grpo_train | metrics_logged mode=train step=490 2026-04-12 17:44:10,627 | INFO | train_grpo_train | metrics_logged mode=train step=491 2026-04-12 17:44:19,475 | INFO | train_grpo_train | metrics_logged mode=train step=492 2026-04-12 17:44:29,013 | INFO | train_grpo_train | metrics_logged mode=train step=493 2026-04-12 17:44:37,117 | INFO | train_grpo_train | metrics_logged mode=train step=494 2026-04-12 17:44:51,289 | INFO | train_grpo_train | metrics_logged mode=train step=495 2026-04-12 17:45:05,490 | INFO | train_grpo_train | metrics_logged mode=train step=496 2026-04-12 17:45:19,207 | INFO | train_grpo_train | metrics_logged mode=train step=497 2026-04-12 17:45:28,612 | INFO | train_grpo_train | metrics_logged mode=train step=498 2026-04-12 17:45:38,200 | INFO | train_grpo_train | metrics_logged mode=train step=499 2026-04-12 17:45:46,859 | INFO | train_grpo_train | metrics_logged mode=train step=500 2026-04-12 17:48:06,937 | INFO | train_grpo_train | metrics_logged mode=eval step=500 2026-04-12 17:48:24,342 | INFO | train_grpo_train | metrics_logged mode=train step=501 2026-04-12 17:48:33,618 | INFO | train_grpo_train | metrics_logged mode=train step=502 2026-04-12 17:48:42,727 | INFO | train_grpo_train | metrics_logged mode=train step=503 2026-04-12 17:48:50,735 | INFO | train_grpo_train | metrics_logged mode=train step=504 2026-04-12 17:49:04,529 | INFO | train_grpo_train | metrics_logged mode=train step=505 2026-04-12 17:49:18,242 | INFO | train_grpo_train | metrics_logged mode=train step=506 2026-04-12 17:49:32,545 | INFO | train_grpo_train | metrics_logged mode=train step=507 2026-04-12 17:49:40,200 | INFO | train_grpo_train | metrics_logged mode=train step=508 2026-04-12 17:49:48,377 | INFO | train_grpo_train | metrics_logged mode=train step=509 2026-04-12 17:49:56,573 | INFO | train_grpo_train | metrics_logged mode=train step=510 2026-04-12 17:50:11,725 | INFO | train_grpo_train | metrics_logged mode=train step=511 2026-04-12 17:50:27,582 | INFO | train_grpo_train | metrics_logged mode=train step=512 2026-04-12 17:50:37,581 | INFO | train_grpo_train | metrics_logged mode=train step=513 2026-04-12 17:50:51,858 | INFO | train_grpo_train | metrics_logged mode=train step=514 2026-04-12 17:51:01,442 | INFO | train_grpo_train | metrics_logged mode=train step=515 2026-04-12 17:51:11,579 | INFO | train_grpo_train | metrics_logged mode=train step=516 2026-04-12 17:51:19,509 | INFO | train_grpo_train | metrics_logged mode=train step=517 2026-04-12 17:51:28,904 | INFO | train_grpo_train | metrics_logged mode=train step=518 2026-04-12 17:51:39,430 | INFO | train_grpo_train | metrics_logged mode=train step=519 2026-04-12 17:51:47,993 | INFO | train_grpo_train | metrics_logged mode=train step=520 2026-04-12 17:51:56,525 | INFO | train_grpo_train | metrics_logged mode=train step=521 2026-04-12 17:52:06,375 | INFO | train_grpo_train | metrics_logged mode=train step=522 2026-04-12 17:52:15,258 | INFO | train_grpo_train | metrics_logged mode=train step=523 2026-04-12 17:52:23,421 | INFO | train_grpo_train | metrics_logged mode=train step=524 2026-04-12 17:52:31,850 | INFO | train_grpo_train | metrics_logged mode=train step=525 2026-04-12 17:52:41,766 | INFO | train_grpo_train | metrics_logged mode=train step=526 2026-04-12 17:52:50,793 | INFO | train_grpo_train | metrics_logged mode=train step=527 2026-04-12 17:53:04,540 | INFO | train_grpo_train | metrics_logged mode=train step=528 2026-04-12 17:53:13,015 | INFO | train_grpo_train | metrics_logged mode=train step=529 2026-04-12 17:53:22,233 | INFO | train_grpo_train | metrics_logged mode=train step=530 2026-04-12 17:53:36,446 | INFO | train_grpo_train | metrics_logged mode=train step=531 2026-04-12 17:53:43,999 | INFO | train_grpo_train | metrics_logged mode=train step=532 2026-04-12 17:53:53,542 | INFO | train_grpo_train | metrics_logged mode=train step=533 2026-04-12 17:54:01,988 | INFO | train_grpo_train | metrics_logged mode=train step=534 2026-04-12 17:54:10,499 | INFO | train_grpo_train | metrics_logged mode=train step=535 2026-04-12 17:54:19,149 | INFO | train_grpo_train | metrics_logged mode=train step=536 2026-04-12 17:54:26,576 | INFO | train_grpo_train | metrics_logged mode=train step=537 2026-04-12 17:54:34,915 | INFO | train_grpo_train | metrics_logged mode=train step=538 2026-04-12 17:54:42,367 | INFO | train_grpo_train | metrics_logged mode=train step=539 2026-04-12 17:54:53,989 | INFO | train_grpo_train | metrics_logged mode=train step=540 2026-04-12 17:55:02,987 | INFO | train_grpo_train | metrics_logged mode=train step=541 2026-04-12 17:55:12,686 | INFO | train_grpo_train | metrics_logged mode=train step=542 2026-04-12 17:55:26,487 | INFO | train_grpo_train | metrics_logged mode=train step=543 2026-04-12 17:55:35,140 | INFO | train_grpo_train | metrics_logged mode=train step=544 2026-04-12 17:55:43,549 | INFO | train_grpo_train | metrics_logged mode=train step=545 2026-04-12 17:55:51,027 | INFO | train_grpo_train | metrics_logged mode=train step=546 2026-04-12 17:56:00,177 | INFO | train_grpo_train | metrics_logged mode=train step=547 2026-04-12 17:56:09,007 | INFO | train_grpo_train | metrics_logged mode=train step=548 2026-04-12 17:56:19,183 | INFO | train_grpo_train | metrics_logged mode=train step=549 2026-04-12 17:56:32,346 | INFO | train_grpo_train | metrics_logged mode=train step=550 2026-04-12 17:59:00,752 | INFO | train_grpo_train | metrics_logged mode=eval step=550 2026-04-12 17:59:18,406 | INFO | train_grpo_train | metrics_logged mode=train step=551 2026-04-12 17:59:33,705 | INFO | train_grpo_train | metrics_logged mode=train step=552 2026-04-12 17:59:42,522 | INFO | train_grpo_train | metrics_logged mode=train step=553 2026-04-12 17:59:51,521 | INFO | train_grpo_train | metrics_logged mode=train step=554 2026-04-12 18:00:00,698 | INFO | train_grpo_train | metrics_logged mode=train step=555 2026-04-12 18:00:09,920 | INFO | train_grpo_train | metrics_logged mode=train step=556 2026-04-12 18:00:17,842 | INFO | train_grpo_train | metrics_logged mode=train step=557 2026-04-12 18:00:33,607 | INFO | train_grpo_train | metrics_logged mode=train step=558 2026-04-12 18:00:48,395 | INFO | train_grpo_train | metrics_logged mode=train step=559 2026-04-12 18:01:03,299 | INFO | train_grpo_train | metrics_logged mode=train step=560 2026-04-12 18:01:18,001 | INFO | train_grpo_train | metrics_logged mode=train step=561 2026-04-12 18:01:32,035 | INFO | train_grpo_train | metrics_logged mode=train step=562 2026-04-12 18:01:45,524 | INFO | train_grpo_train | metrics_logged mode=train step=563 2026-04-12 18:01:59,469 | INFO | train_grpo_train | metrics_logged mode=train step=564 2026-04-12 18:02:13,350 | INFO | train_grpo_train | metrics_logged mode=train step=565 2026-04-12 18:02:27,877 | INFO | train_grpo_train | metrics_logged mode=train step=566 2026-04-12 18:02:42,586 | INFO | train_grpo_train | metrics_logged mode=train step=567 2026-04-12 18:02:56,579 | INFO | train_grpo_train | metrics_logged mode=train step=568 2026-04-12 18:03:09,386 | INFO | train_grpo_train | metrics_logged mode=train step=569 2026-04-12 18:03:17,714 | INFO | train_grpo_train | metrics_logged mode=train step=570 2026-04-12 18:03:29,251 | INFO | train_grpo_train | metrics_logged mode=train step=571 2026-04-12 18:03:42,923 | INFO | train_grpo_train | metrics_logged mode=train step=572 2026-04-12 18:03:52,741 | INFO | train_grpo_train | metrics_logged mode=train step=573 2026-04-12 18:04:06,263 | INFO | train_grpo_train | metrics_logged mode=train step=574 2026-04-12 18:04:14,626 | INFO | train_grpo_train | metrics_logged mode=train step=575 2026-04-12 18:04:23,436 | INFO | train_grpo_train | metrics_logged mode=train step=576 2026-04-12 18:04:30,814 | INFO | train_grpo_train | metrics_logged mode=train step=577 2026-04-12 18:04:41,061 | INFO | train_grpo_train | metrics_logged mode=train step=578 2026-04-12 18:04:54,141 | INFO | train_grpo_train | metrics_logged mode=train step=579 2026-04-12 18:05:09,049 | INFO | train_grpo_train | metrics_logged mode=train step=580 2026-04-12 18:05:20,113 | INFO | train_grpo_train | metrics_logged mode=train step=581 2026-04-12 18:05:33,234 | INFO | train_grpo_train | metrics_logged mode=train step=582 2026-04-12 18:05:41,549 | INFO | train_grpo_train | metrics_logged mode=train step=583 2026-04-12 18:05:55,704 | INFO | train_grpo_train | metrics_logged mode=train step=584 2026-04-12 18:06:04,721 | INFO | train_grpo_train | metrics_logged mode=train step=585 2026-04-12 18:06:18,272 | INFO | train_grpo_train | metrics_logged mode=train step=586 2026-04-12 18:06:31,614 | INFO | train_grpo_train | metrics_logged mode=train step=587 2026-04-12 18:06:42,727 | INFO | train_grpo_train | metrics_logged mode=train step=588 2026-04-12 18:06:51,169 | INFO | train_grpo_train | metrics_logged mode=train step=589 2026-04-12 18:07:04,614 | INFO | train_grpo_train | metrics_logged mode=train step=590 2026-04-12 18:07:13,397 | INFO | train_grpo_train | metrics_logged mode=train step=591 2026-04-12 18:07:21,399 | INFO | train_grpo_train | metrics_logged mode=train step=592 2026-04-12 18:07:29,303 | INFO | train_grpo_train | metrics_logged mode=train step=593 2026-04-12 18:07:40,338 | INFO | train_grpo_train | metrics_logged mode=train step=594 2026-04-12 18:07:48,032 | INFO | train_grpo_train | metrics_logged mode=train step=595 2026-04-12 18:07:56,142 | INFO | train_grpo_train | metrics_logged mode=train step=596 2026-04-12 18:08:10,489 | INFO | train_grpo_train | metrics_logged mode=train step=597 2026-04-12 18:08:25,353 | INFO | train_grpo_train | metrics_logged mode=train step=598 2026-04-12 18:08:33,889 | INFO | train_grpo_train | metrics_logged mode=train step=599 2026-04-12 18:08:48,057 | INFO | train_grpo_train | metrics_logged mode=train step=600 2026-04-12 18:11:21,902 | INFO | train_grpo_train | metrics_logged mode=eval step=600 2026-04-12 18:11:38,417 | INFO | train_grpo_train | metrics_logged mode=train step=601 2026-04-12 18:11:53,056 | INFO | train_grpo_train | metrics_logged mode=train step=602 2026-04-12 18:12:07,009 | INFO | train_grpo_train | metrics_logged mode=train step=603 2026-04-12 18:12:20,676 | INFO | train_grpo_train | metrics_logged mode=train step=604 2026-04-12 18:12:29,018 | INFO | train_grpo_train | metrics_logged mode=train step=605 2026-04-12 18:12:38,346 | INFO | train_grpo_train | metrics_logged mode=train step=606 2026-04-12 18:12:51,689 | INFO | train_grpo_train | metrics_logged mode=train step=607 2026-04-12 18:12:59,762 | INFO | train_grpo_train | metrics_logged mode=train step=608 2026-04-12 18:13:13,793 | INFO | train_grpo_train | metrics_logged mode=train step=609 2026-04-12 18:13:22,990 | INFO | train_grpo_train | metrics_logged mode=train step=610 2026-04-12 18:13:36,472 | INFO | train_grpo_train | metrics_logged mode=train step=611 2026-04-12 18:13:50,513 | INFO | train_grpo_train | metrics_logged mode=train step=612 2026-04-12 18:13:58,377 | INFO | train_grpo_train | metrics_logged mode=train step=613 2026-04-12 18:14:11,921 | INFO | train_grpo_train | metrics_logged mode=train step=614 2026-04-12 18:14:26,140 | INFO | train_grpo_train | metrics_logged mode=train step=615 2026-04-12 18:14:34,601 | INFO | train_grpo_train | metrics_logged mode=train step=616 2026-04-12 18:14:48,238 | INFO | train_grpo_train | metrics_logged mode=train step=617 2026-04-12 18:15:01,606 | INFO | train_grpo_train | metrics_logged mode=train step=618 2026-04-12 18:15:10,942 | INFO | train_grpo_train | metrics_logged mode=train step=619 2026-04-12 18:15:24,488 | INFO | train_grpo_train | metrics_logged mode=train step=620 2026-04-12 18:15:39,282 | INFO | train_grpo_train | metrics_logged mode=train step=621 2026-04-12 18:15:47,479 | INFO | train_grpo_train | metrics_logged mode=train step=622 2026-04-12 18:16:00,831 | INFO | train_grpo_train | metrics_logged mode=train step=623 2026-04-12 18:16:15,018 | INFO | train_grpo_train | metrics_logged mode=train step=624 2026-04-12 18:16:23,266 | INFO | train_grpo_train | metrics_logged mode=train step=625 2026-04-12 18:16:37,098 | INFO | train_grpo_train | metrics_logged mode=train step=626 2026-04-12 18:16:50,671 | INFO | train_grpo_train | metrics_logged mode=train step=627 2026-04-12 18:17:00,217 | INFO | train_grpo_train | metrics_logged mode=train step=628 2026-04-12 18:17:09,352 | INFO | train_grpo_train | metrics_logged mode=train step=629 2026-04-12 18:17:18,795 | INFO | train_grpo_train | metrics_logged mode=train step=630 2026-04-12 18:17:33,066 | INFO | train_grpo_train | metrics_logged mode=train step=631 2026-04-12 18:17:43,587 | INFO | train_grpo_train | metrics_logged mode=train step=632 2026-04-12 18:17:57,209 | INFO | train_grpo_train | metrics_logged mode=train step=633 2026-04-12 18:18:06,003 | INFO | train_grpo_train | metrics_logged mode=train step=634 2026-04-12 18:18:14,544 | INFO | train_grpo_train | metrics_logged mode=train step=635 2026-04-12 18:18:28,280 | INFO | train_grpo_train | metrics_logged mode=train step=636 2026-04-12 18:18:37,812 | INFO | train_grpo_train | metrics_logged mode=train step=637 2026-04-12 18:18:51,936 | INFO | train_grpo_train | metrics_logged mode=train step=638 2026-04-12 18:18:59,488 | INFO | train_grpo_train | metrics_logged mode=train step=639 2026-04-12 18:19:08,483 | INFO | train_grpo_train | metrics_logged mode=train step=640 2026-04-12 18:19:16,927 | INFO | train_grpo_train | metrics_logged mode=train step=641 2026-04-12 18:19:30,870 | INFO | train_grpo_train | metrics_logged mode=train step=642 2026-04-12 18:19:44,999 | INFO | train_grpo_train | metrics_logged mode=train step=643 2026-04-12 18:19:58,309 | INFO | train_grpo_train | metrics_logged mode=train step=644 2026-04-12 18:20:06,166 | INFO | train_grpo_train | metrics_logged mode=train step=645 2026-04-12 18:20:14,427 | INFO | train_grpo_train | metrics_logged mode=train step=646 2026-04-12 18:20:24,898 | INFO | train_grpo_train | metrics_logged mode=train step=647 2026-04-12 18:20:33,002 | INFO | train_grpo_train | metrics_logged mode=train step=648 2026-04-12 18:20:43,065 | INFO | train_grpo_train | metrics_logged mode=train step=649 2026-04-12 18:20:51,973 | INFO | train_grpo_train | metrics_logged mode=train step=650 2026-04-12 18:23:15,462 | INFO | train_grpo_train | metrics_logged mode=eval step=650 2026-04-12 18:23:31,183 | INFO | train_grpo_train | metrics_logged mode=train step=651 2026-04-12 18:23:39,195 | INFO | train_grpo_train | metrics_logged mode=train step=652 2026-04-12 18:23:47,479 | INFO | train_grpo_train | metrics_logged mode=train step=653 2026-04-12 18:23:56,729 | INFO | train_grpo_train | metrics_logged mode=train step=654 2026-04-12 18:24:06,132 | INFO | train_grpo_train | metrics_logged mode=train step=655 2026-04-12 18:24:16,669 | INFO | train_grpo_train | metrics_logged mode=train step=656 2026-04-12 18:24:28,836 | INFO | train_grpo_train | metrics_logged mode=train step=657 2026-04-12 18:24:37,644 | INFO | train_grpo_train | metrics_logged mode=train step=658 2026-04-12 18:24:46,500 | INFO | train_grpo_train | metrics_logged mode=train step=659 2026-04-12 18:24:59,914 | INFO | train_grpo_train | metrics_logged mode=train step=660 2026-04-12 18:25:09,360 | INFO | train_grpo_train | metrics_logged mode=train step=661 2026-04-12 18:25:17,772 | INFO | train_grpo_train | metrics_logged mode=train step=662 2026-04-12 18:25:26,456 | INFO | train_grpo_train | metrics_logged mode=train step=663 2026-04-12 18:25:40,825 | INFO | train_grpo_train | metrics_logged mode=train step=664 2026-04-12 18:25:55,382 | INFO | train_grpo_train | metrics_logged mode=train step=665 2026-04-12 18:26:09,363 | INFO | train_grpo_train | metrics_logged mode=train step=666 2026-04-12 18:26:17,823 | INFO | train_grpo_train | metrics_logged mode=train step=667 2026-04-12 18:26:31,310 | INFO | train_grpo_train | metrics_logged mode=train step=668 2026-04-12 18:26:40,529 | INFO | train_grpo_train | metrics_logged mode=train step=669 2026-04-12 18:26:49,073 | INFO | train_grpo_train | metrics_logged mode=train step=670 2026-04-12 18:27:02,699 | INFO | train_grpo_train | metrics_logged mode=train step=671 2026-04-12 18:27:11,264 | INFO | train_grpo_train | metrics_logged mode=train step=672 2026-04-12 18:27:19,033 | INFO | train_grpo_train | metrics_logged mode=train step=673 2026-04-12 18:27:33,342 | INFO | train_grpo_train | metrics_logged mode=train step=674 2026-04-12 18:27:47,944 | INFO | train_grpo_train | metrics_logged mode=train step=675 2026-04-12 18:27:58,748 | INFO | train_grpo_train | metrics_logged mode=train step=676 2026-04-12 18:28:07,132 | INFO | train_grpo_train | metrics_logged mode=train step=677 2026-04-12 18:28:17,212 | INFO | train_grpo_train | metrics_logged mode=train step=678 2026-04-12 18:28:26,684 | INFO | train_grpo_train | metrics_logged mode=train step=679 2026-04-12 18:28:35,857 | INFO | train_grpo_train | metrics_logged mode=train step=680 2026-04-12 18:28:44,246 | INFO | train_grpo_train | metrics_logged mode=train step=681 2026-04-12 18:28:53,478 | INFO | train_grpo_train | metrics_logged mode=train step=682 2026-04-12 18:29:02,206 | INFO | train_grpo_train | metrics_logged mode=train step=683 2026-04-12 18:29:16,118 | INFO | train_grpo_train | metrics_logged mode=train step=684 2026-04-12 18:29:25,327 | INFO | train_grpo_train | metrics_logged mode=train step=685 2026-04-12 18:29:35,745 | INFO | train_grpo_train | metrics_logged mode=train step=686 2026-04-12 18:29:45,357 | INFO | train_grpo_train | metrics_logged mode=train step=687 2026-04-12 18:29:54,770 | INFO | train_grpo_train | metrics_logged mode=train step=688 2026-04-12 18:30:07,902 | INFO | train_grpo_train | metrics_logged mode=train step=689 2026-04-12 18:30:16,074 | INFO | train_grpo_train | metrics_logged mode=train step=690 2026-04-12 18:30:24,632 | INFO | train_grpo_train | metrics_logged mode=train step=691 2026-04-12 18:30:41,038 | INFO | train_grpo_train | metrics_logged mode=train step=692 2026-04-12 18:30:54,448 | INFO | train_grpo_train | metrics_logged mode=train step=693 2026-04-12 18:31:02,991 | INFO | train_grpo_train | metrics_logged mode=train step=694 2026-04-12 18:31:13,846 | INFO | train_grpo_train | metrics_logged mode=train step=695 2026-04-12 18:31:23,916 | INFO | train_grpo_train | metrics_logged mode=train step=696 2026-04-12 18:31:37,387 | INFO | train_grpo_train | metrics_logged mode=train step=697 2026-04-12 18:31:51,231 | INFO | train_grpo_train | metrics_logged mode=train step=698 2026-04-12 18:32:04,917 | INFO | train_grpo_train | metrics_logged mode=train step=699 2026-04-12 18:32:19,162 | INFO | train_grpo_train | metrics_logged mode=train step=700 2026-04-12 18:34:50,220 | INFO | train_grpo_train | metrics_logged mode=eval step=700 2026-04-12 18:35:03,069 | INFO | train_grpo_train | metrics_logged mode=train step=701 2026-04-12 18:35:12,107 | INFO | train_grpo_train | metrics_logged mode=train step=702 2026-04-12 18:35:21,206 | INFO | train_grpo_train | metrics_logged mode=train step=703 2026-04-12 18:35:31,631 | INFO | train_grpo_train | metrics_logged mode=train step=704 2026-04-12 18:35:39,521 | INFO | train_grpo_train | metrics_logged mode=train step=705 2026-04-12 18:35:54,888 | INFO | train_grpo_train | metrics_logged mode=train step=706 2026-04-12 18:36:08,339 | INFO | train_grpo_train | metrics_logged mode=train step=707 2026-04-12 18:36:22,659 | INFO | train_grpo_train | metrics_logged mode=train step=708 2026-04-12 18:36:36,243 | INFO | train_grpo_train | metrics_logged mode=train step=709 2026-04-12 18:36:44,821 | INFO | train_grpo_train | metrics_logged mode=train step=710 2026-04-12 18:36:52,647 | INFO | train_grpo_train | metrics_logged mode=train step=711 2026-04-12 18:37:06,316 | INFO | train_grpo_train | metrics_logged mode=train step=712 2026-04-12 18:37:13,839 | INFO | train_grpo_train | metrics_logged mode=train step=713 2026-04-12 18:37:27,572 | INFO | train_grpo_train | metrics_logged mode=train step=714 2026-04-12 18:37:35,829 | INFO | train_grpo_train | metrics_logged mode=train step=715 2026-04-12 18:37:44,701 | INFO | train_grpo_train | metrics_logged mode=train step=716 2026-04-12 18:37:59,504 | INFO | train_grpo_train | metrics_logged mode=train step=717 2026-04-12 18:38:13,847 | INFO | train_grpo_train | metrics_logged mode=train step=718 2026-04-12 18:38:27,595 | INFO | train_grpo_train | metrics_logged mode=train step=719 2026-04-12 18:38:40,524 | INFO | train_grpo_train | metrics_logged mode=train step=720 2026-04-12 18:38:48,463 | INFO | train_grpo_train | metrics_logged mode=train step=721 2026-04-12 18:39:02,536 | INFO | train_grpo_train | metrics_logged mode=train step=722 2026-04-12 18:39:18,439 | INFO | train_grpo_train | metrics_logged mode=train step=723 2026-04-12 18:39:35,597 | INFO | train_grpo_train | metrics_logged mode=train step=724 2026-04-12 18:39:48,606 | INFO | train_grpo_train | metrics_logged mode=train step=725 2026-04-12 18:40:02,752 | INFO | train_grpo_train | metrics_logged mode=train step=726 2026-04-12 18:40:18,285 | INFO | train_grpo_train | metrics_logged mode=train step=727 2026-04-12 18:40:31,556 | INFO | train_grpo_train | metrics_logged mode=train step=728 2026-04-12 18:40:48,061 | INFO | train_grpo_train | metrics_logged mode=train step=729 2026-04-12 18:40:56,119 | INFO | train_grpo_train | metrics_logged mode=train step=730 2026-04-12 18:41:10,081 | INFO | train_grpo_train | metrics_logged mode=train step=731 2026-04-12 18:41:25,882 | INFO | train_grpo_train | metrics_logged mode=train step=732 2026-04-12 18:41:39,806 | INFO | train_grpo_train | metrics_logged mode=train step=733 2026-04-12 18:41:55,329 | INFO | train_grpo_train | metrics_logged mode=train step=734 2026-04-12 18:42:09,883 | INFO | train_grpo_train | metrics_logged mode=train step=735 2026-04-12 18:42:23,317 | INFO | train_grpo_train | metrics_logged mode=train step=736 2026-04-12 18:42:37,021 | INFO | train_grpo_train | metrics_logged mode=train step=737 2026-04-12 18:42:50,486 | INFO | train_grpo_train | metrics_logged mode=train step=738 2026-04-12 18:43:04,501 | INFO | train_grpo_train | metrics_logged mode=train step=739 2026-04-12 18:43:12,938 | INFO | train_grpo_train | metrics_logged mode=train step=740 2026-04-12 18:43:23,294 | INFO | train_grpo_train | metrics_logged mode=train step=741 2026-04-12 18:43:36,675 | INFO | train_grpo_train | metrics_logged mode=train step=742 2026-04-12 18:43:52,876 | INFO | train_grpo_train | metrics_logged mode=train step=743 2026-04-12 18:44:09,652 | INFO | train_grpo_train | metrics_logged mode=train step=744 2026-04-12 18:44:17,043 | INFO | train_grpo_train | metrics_logged mode=train step=745 2026-04-12 18:44:30,020 | INFO | train_grpo_train | metrics_logged mode=train step=746 2026-04-12 18:44:44,074 | INFO | train_grpo_train | metrics_logged mode=train step=747 2026-04-12 18:44:56,806 | INFO | train_grpo_train | metrics_logged mode=train step=748 2026-04-12 18:45:10,469 | INFO | train_grpo_train | metrics_logged mode=train step=749 2026-04-12 18:45:24,513 | INFO | train_grpo_train | metrics_logged mode=train step=750 2026-04-12 18:47:45,358 | INFO | train_grpo_train | metrics_logged mode=eval step=750 2026-04-12 18:48:01,638 | INFO | train_grpo_train | metrics_logged mode=train step=751 2026-04-12 18:48:15,132 | INFO | train_grpo_train | metrics_logged mode=train step=752 2026-04-12 18:48:22,900 | INFO | train_grpo_train | metrics_logged mode=train step=753 2026-04-12 18:48:36,424 | INFO | train_grpo_train | metrics_logged mode=train step=754 2026-04-12 18:48:49,457 | INFO | train_grpo_train | metrics_logged mode=train step=755 2026-04-12 18:49:02,527 | INFO | train_grpo_train | metrics_logged mode=train step=756 2026-04-12 18:49:11,383 | INFO | train_grpo_train | metrics_logged mode=train step=757 2026-04-12 18:49:19,263 | INFO | train_grpo_train | metrics_logged mode=train step=758 2026-04-12 18:49:34,946 | INFO | train_grpo_train | metrics_logged mode=train step=759 2026-04-12 18:49:43,806 | INFO | train_grpo_train | metrics_logged mode=train step=760 2026-04-12 18:49:57,461 | INFO | train_grpo_train | metrics_logged mode=train step=761 2026-04-12 18:50:11,312 | INFO | train_grpo_train | metrics_logged mode=train step=762 2026-04-12 18:50:20,312 | INFO | train_grpo_train | metrics_logged mode=train step=763 2026-04-12 18:50:29,372 | INFO | train_grpo_train | metrics_logged mode=train step=764 2026-04-12 18:50:37,924 | INFO | train_grpo_train | metrics_logged mode=train step=765 2026-04-12 18:50:46,483 | INFO | train_grpo_train | metrics_logged mode=train step=766 2026-04-12 18:50:54,450 | INFO | train_grpo_train | metrics_logged mode=train step=767 2026-04-12 18:51:02,742 | INFO | train_grpo_train | metrics_logged mode=train step=768 2026-04-12 18:51:10,611 | INFO | train_grpo_train | metrics_logged mode=train step=769 2026-04-12 18:51:19,931 | INFO | train_grpo_train | metrics_logged mode=train step=770 2026-04-12 18:51:33,012 | INFO | train_grpo_train | metrics_logged mode=train step=771 2026-04-12 18:51:46,591 | INFO | train_grpo_train | metrics_logged mode=train step=772 2026-04-12 18:51:55,103 | INFO | train_grpo_train | metrics_logged mode=train step=773 2026-04-12 18:52:03,589 | INFO | train_grpo_train | metrics_logged mode=train step=774 2026-04-12 18:52:12,274 | INFO | train_grpo_train | metrics_logged mode=train step=775 2026-04-12 18:52:20,759 | INFO | train_grpo_train | metrics_logged mode=train step=776 2026-04-12 18:52:29,702 | INFO | train_grpo_train | metrics_logged mode=train step=777 2026-04-12 18:52:36,981 | INFO | train_grpo_train | metrics_logged mode=train step=778 2026-04-12 18:52:44,850 | INFO | train_grpo_train | metrics_logged mode=train step=779 2026-04-12 18:52:52,918 | INFO | train_grpo_train | metrics_logged mode=train step=780 2026-04-12 18:53:06,174 | INFO | train_grpo_train | metrics_logged mode=train step=781 2026-04-12 18:53:14,109 | INFO | train_grpo_train | metrics_logged mode=train step=782 2026-04-12 18:53:22,221 | INFO | train_grpo_train | metrics_logged mode=train step=783 2026-04-12 18:53:30,285 | INFO | train_grpo_train | metrics_logged mode=train step=784 2026-04-12 18:53:38,714 | INFO | train_grpo_train | metrics_logged mode=train step=785 2026-04-12 18:53:48,147 | INFO | train_grpo_train | metrics_logged mode=train step=786 2026-04-12 18:53:56,587 | INFO | train_grpo_train | metrics_logged mode=train step=787 2026-04-12 18:54:04,760 | INFO | train_grpo_train | metrics_logged mode=train step=788 2026-04-12 18:54:13,647 | INFO | train_grpo_train | metrics_logged mode=train step=789 2026-04-12 18:54:24,410 | INFO | train_grpo_train | metrics_logged mode=train step=790 2026-04-12 18:54:33,025 | INFO | train_grpo_train | metrics_logged mode=train step=791 2026-04-12 18:54:42,057 | INFO | train_grpo_train | metrics_logged mode=train step=792 2026-04-12 18:54:49,823 | INFO | train_grpo_train | metrics_logged mode=train step=793 2026-04-12 18:54:58,229 | INFO | train_grpo_train | metrics_logged mode=train step=794 2026-04-12 18:55:05,613 | INFO | train_grpo_train | metrics_logged mode=train step=795 2026-04-12 18:55:14,625 | INFO | train_grpo_train | metrics_logged mode=train step=796 2026-04-12 18:55:23,239 | INFO | train_grpo_train | metrics_logged mode=train step=797 2026-04-12 18:55:31,223 | INFO | train_grpo_train | metrics_logged mode=train step=798 2026-04-12 18:55:38,792 | INFO | train_grpo_train | metrics_logged mode=train step=799 2026-04-12 18:55:47,170 | INFO | train_grpo_train | metrics_logged mode=train step=800 2026-04-12 18:57:37,936 | INFO | train_grpo_train | metrics_logged mode=eval step=800 2026-04-12 18:57:50,544 | INFO | train_grpo_train | metrics_logged mode=train step=801 2026-04-12 18:57:58,151 | INFO | train_grpo_train | metrics_logged mode=train step=802 2026-04-12 18:58:05,600 | INFO | train_grpo_train | metrics_logged mode=train step=803 2026-04-12 18:58:18,775 | INFO | train_grpo_train | metrics_logged mode=train step=804 2026-04-12 18:58:26,554 | INFO | train_grpo_train | metrics_logged mode=train step=805 2026-04-12 18:58:34,699 | INFO | train_grpo_train | metrics_logged mode=train step=806 2026-04-12 18:58:43,951 | INFO | train_grpo_train | metrics_logged mode=train step=807 2026-04-12 18:58:51,472 | INFO | train_grpo_train | metrics_logged mode=train step=808 2026-04-12 18:58:59,414 | INFO | train_grpo_train | metrics_logged mode=train step=809 2026-04-12 18:59:08,017 | INFO | train_grpo_train | metrics_logged mode=train step=810 2026-04-12 18:59:17,279 | INFO | train_grpo_train | metrics_logged mode=train step=811 2026-04-12 18:59:25,942 | INFO | train_grpo_train | metrics_logged mode=train step=812 2026-04-12 18:59:39,618 | INFO | train_grpo_train | metrics_logged mode=train step=813 2026-04-12 18:59:53,665 | INFO | train_grpo_train | metrics_logged mode=train step=814 2026-04-12 19:00:03,294 | INFO | train_grpo_train | metrics_logged mode=train step=815 2026-04-12 19:00:11,647 | INFO | train_grpo_train | metrics_logged mode=train step=816 2026-04-12 19:00:19,896 | INFO | train_grpo_train | metrics_logged mode=train step=817 2026-04-12 19:00:28,412 | INFO | train_grpo_train | metrics_logged mode=train step=818 2026-04-12 19:00:36,681 | INFO | train_grpo_train | metrics_logged mode=train step=819 2026-04-12 19:00:49,618 | INFO | train_grpo_train | metrics_logged mode=train step=820 2026-04-12 19:01:02,644 | INFO | train_grpo_train | metrics_logged mode=train step=821 2026-04-12 19:01:16,739 | INFO | train_grpo_train | metrics_logged mode=train step=822 2026-04-12 19:01:30,680 | INFO | train_grpo_train | metrics_logged mode=train step=823 2026-04-12 19:01:45,078 | INFO | train_grpo_train | metrics_logged mode=train step=824 2026-04-12 19:01:58,568 | INFO | train_grpo_train | metrics_logged mode=train step=825 2026-04-12 19:02:12,514 | INFO | train_grpo_train | metrics_logged mode=train step=826 2026-04-12 19:02:25,783 | INFO | train_grpo_train | metrics_logged mode=train step=827 2026-04-12 19:02:39,148 | INFO | train_grpo_train | metrics_logged mode=train step=828 2026-04-12 19:02:52,498 | INFO | train_grpo_train | metrics_logged mode=train step=829 2026-04-12 19:03:00,160 | INFO | train_grpo_train | metrics_logged mode=train step=830 2026-04-12 19:03:12,901 | INFO | train_grpo_train | metrics_logged mode=train step=831 2026-04-12 19:03:21,040 | INFO | train_grpo_train | metrics_logged mode=train step=832 2026-04-12 19:03:34,505 | INFO | train_grpo_train | metrics_logged mode=train step=833 2026-04-12 19:03:49,471 | INFO | train_grpo_train | metrics_logged mode=train step=834 2026-04-12 19:04:03,520 | INFO | train_grpo_train | metrics_logged mode=train step=835 2026-04-12 19:04:11,797 | INFO | train_grpo_train | metrics_logged mode=train step=836 2026-04-12 19:04:25,124 | INFO | train_grpo_train | metrics_logged mode=train step=837 2026-04-12 19:04:38,565 | INFO | train_grpo_train | metrics_logged mode=train step=838 2026-04-12 19:04:52,345 | INFO | train_grpo_train | metrics_logged mode=train step=839 2026-04-12 19:05:05,811 | INFO | train_grpo_train | metrics_logged mode=train step=840 2026-04-12 19:05:14,127 | INFO | train_grpo_train | metrics_logged mode=train step=841 2026-04-12 19:05:28,070 | INFO | train_grpo_train | metrics_logged mode=train step=842 2026-04-12 19:05:42,119 | INFO | train_grpo_train | metrics_logged mode=train step=843 2026-04-12 19:05:55,718 | INFO | train_grpo_train | metrics_logged mode=train step=844 2026-04-12 19:06:09,272 | INFO | train_grpo_train | metrics_logged mode=train step=845 2026-04-12 19:06:17,317 | INFO | train_grpo_train | metrics_logged mode=train step=846 2026-04-12 19:06:25,473 | INFO | train_grpo_train | metrics_logged mode=train step=847 2026-04-12 19:06:34,966 | INFO | train_grpo_train | metrics_logged mode=train step=848 2026-04-12 19:06:48,478 | INFO | train_grpo_train | metrics_logged mode=train step=849 2026-04-12 19:06:56,664 | INFO | train_grpo_train | metrics_logged mode=train step=850 2026-04-12 19:08:59,066 | INFO | train_grpo_train | metrics_logged mode=eval step=850 2026-04-12 19:09:10,830 | INFO | train_grpo_train | metrics_logged mode=train step=851 2026-04-12 19:09:18,839 | INFO | train_grpo_train | metrics_logged mode=train step=852 2026-04-12 19:09:38,216 | INFO | train_grpo_train | metrics_logged mode=train step=853 2026-04-12 19:09:52,335 | INFO | train_grpo_train | metrics_logged mode=train step=854 2026-04-12 19:10:05,906 | INFO | train_grpo_train | metrics_logged mode=train step=855 2026-04-12 19:10:14,774 | INFO | train_grpo_train | metrics_logged mode=train step=856 2026-04-12 19:10:28,644 | INFO | train_grpo_train | metrics_logged mode=train step=857 2026-04-12 19:10:41,553 | INFO | train_grpo_train | metrics_logged mode=train step=858 2026-04-12 19:10:50,506 | INFO | train_grpo_train | metrics_logged mode=train step=859 2026-04-12 19:10:59,502 | INFO | train_grpo_train | metrics_logged mode=train step=860 2026-04-12 19:11:09,003 | INFO | train_grpo_train | metrics_logged mode=train step=861 2026-04-12 19:11:22,381 | INFO | train_grpo_train | metrics_logged mode=train step=862 2026-04-12 19:11:31,100 | INFO | train_grpo_train | metrics_logged mode=train step=863 2026-04-12 19:11:38,855 | INFO | train_grpo_train | metrics_logged mode=train step=864 2026-04-12 19:11:52,688 | INFO | train_grpo_train | metrics_logged mode=train step=865 2026-04-12 19:12:00,773 | INFO | train_grpo_train | metrics_logged mode=train step=866 2026-04-12 19:12:08,226 | INFO | train_grpo_train | metrics_logged mode=train step=867 2026-04-12 19:12:21,275 | INFO | train_grpo_train | metrics_logged mode=train step=868 2026-04-12 19:12:34,990 | INFO | train_grpo_train | metrics_logged mode=train step=869 2026-04-12 19:12:48,445 | INFO | train_grpo_train | metrics_logged mode=train step=870 2026-04-12 19:12:57,371 | INFO | train_grpo_train | metrics_logged mode=train step=871 2026-04-12 19:13:06,877 | INFO | train_grpo_train | metrics_logged mode=train step=872 2026-04-12 19:13:21,606 | INFO | train_grpo_train | metrics_logged mode=train step=873 2026-04-12 19:13:32,402 | INFO | train_grpo_train | metrics_logged mode=train step=874 2026-04-12 19:13:41,588 | INFO | train_grpo_train | metrics_logged mode=train step=875 2026-04-12 19:13:52,981 | INFO | train_grpo_train | metrics_logged mode=train step=876 2026-04-12 19:14:00,746 | INFO | train_grpo_train | metrics_logged mode=train step=877 2026-04-12 19:14:10,995 | INFO | train_grpo_train | metrics_logged mode=train step=878 2026-04-12 19:14:18,969 | INFO | train_grpo_train | metrics_logged mode=train step=879 2026-04-12 19:14:29,262 | INFO | train_grpo_train | metrics_logged mode=train step=880 2026-04-12 19:14:37,299 | INFO | train_grpo_train | metrics_logged mode=train step=881 2026-04-12 19:14:50,881 | INFO | train_grpo_train | metrics_logged mode=train step=882 2026-04-12 19:15:04,461 | INFO | train_grpo_train | metrics_logged mode=train step=883 2026-04-12 19:15:19,007 | INFO | train_grpo_train | metrics_logged mode=train step=884 2026-04-12 19:15:33,692 | INFO | train_grpo_train | metrics_logged mode=train step=885 2026-04-12 19:15:48,391 | INFO | train_grpo_train | metrics_logged mode=train step=886 2026-04-12 19:15:57,152 | INFO | train_grpo_train | metrics_logged mode=train step=887 2026-04-12 19:16:11,695 | INFO | train_grpo_train | metrics_logged mode=train step=888 2026-04-12 19:16:25,415 | INFO | train_grpo_train | metrics_logged mode=train step=889 2026-04-12 19:16:39,428 | INFO | train_grpo_train | metrics_logged mode=train step=890 2026-04-12 19:16:53,804 | INFO | train_grpo_train | metrics_logged mode=train step=891 2026-04-12 19:17:12,713 | INFO | train_grpo_train | metrics_logged mode=train step=892 2026-04-12 19:17:22,070 | INFO | train_grpo_train | metrics_logged mode=train step=893 2026-04-12 19:17:31,907 | INFO | train_grpo_train | metrics_logged mode=train step=894 2026-04-12 19:17:44,971 | INFO | train_grpo_train | metrics_logged mode=train step=895 2026-04-12 19:17:58,993 | INFO | train_grpo_train | metrics_logged mode=train step=896 2026-04-12 19:18:07,622 | INFO | train_grpo_train | metrics_logged mode=train step=897 2026-04-12 19:18:16,135 | INFO | train_grpo_train | metrics_logged mode=train step=898 2026-04-12 19:18:29,827 | INFO | train_grpo_train | metrics_logged mode=train step=899 2026-04-12 19:18:39,007 | INFO | train_grpo_train | metrics_logged mode=train step=900 2026-04-12 19:21:15,970 | INFO | train_grpo_train | metrics_logged mode=eval step=900 2026-04-12 19:21:28,303 | INFO | train_grpo_train | metrics_logged mode=train step=901 2026-04-12 19:21:40,700 | INFO | train_grpo_train | metrics_logged mode=train step=902 2026-04-12 19:21:58,146 | INFO | train_grpo_train | metrics_logged mode=train step=903 2026-04-12 19:22:11,989 | INFO | train_grpo_train | metrics_logged mode=train step=904 2026-04-12 19:22:20,373 | INFO | train_grpo_train | metrics_logged mode=train step=905 2026-04-12 19:22:34,929 | INFO | train_grpo_train | metrics_logged mode=train step=906 2026-04-12 19:22:43,426 | INFO | train_grpo_train | metrics_logged mode=train step=907 2026-04-12 19:22:57,231 | INFO | train_grpo_train | metrics_logged mode=train step=908 2026-04-12 19:23:12,302 | INFO | train_grpo_train | metrics_logged mode=train step=909 2026-04-12 19:23:28,778 | INFO | train_grpo_train | metrics_logged mode=train step=910 2026-04-12 19:23:39,061 | INFO | train_grpo_train | metrics_logged mode=train step=911 2026-04-12 19:23:48,649 | INFO | train_grpo_train | metrics_logged mode=train step=912 2026-04-12 19:24:02,412 | INFO | train_grpo_train | metrics_logged mode=train step=913 2026-04-12 19:24:14,638 | INFO | train_grpo_train | metrics_logged mode=train step=914 2026-04-12 19:24:23,181 | INFO | train_grpo_train | metrics_logged mode=train step=915 2026-04-12 19:24:37,356 | INFO | train_grpo_train | metrics_logged mode=train step=916 2026-04-12 19:24:54,235 | INFO | train_grpo_train | metrics_logged mode=train step=917 2026-04-12 19:25:08,954 | INFO | train_grpo_train | metrics_logged mode=train step=918 2026-04-12 19:25:19,803 | INFO | train_grpo_train | metrics_logged mode=train step=919 2026-04-12 19:25:28,138 | INFO | train_grpo_train | metrics_logged mode=train step=920 2026-04-12 19:25:38,032 | INFO | train_grpo_train | metrics_logged mode=train step=921 2026-04-12 19:25:46,362 | INFO | train_grpo_train | metrics_logged mode=train step=922 2026-04-12 19:25:55,463 | INFO | train_grpo_train | metrics_logged mode=train step=923 2026-04-12 19:26:09,889 | INFO | train_grpo_train | metrics_logged mode=train step=924 2026-04-12 19:26:23,541 | INFO | train_grpo_train | metrics_logged mode=train step=925 2026-04-12 19:26:37,819 | INFO | train_grpo_train | metrics_logged mode=train step=926 2026-04-12 19:26:51,071 | INFO | train_grpo_train | metrics_logged mode=train step=927 2026-04-12 19:26:59,595 | INFO | train_grpo_train | metrics_logged mode=train step=928 2026-04-12 19:27:08,179 | INFO | train_grpo_train | metrics_logged mode=train step=929 2026-04-12 19:27:22,464 | INFO | train_grpo_train | metrics_logged mode=train step=930 2026-04-12 19:27:31,580 | INFO | train_grpo_train | metrics_logged mode=train step=931 2026-04-12 19:27:47,064 | INFO | train_grpo_train | metrics_logged mode=train step=932 2026-04-12 19:28:01,080 | INFO | train_grpo_train | metrics_logged mode=train step=933 2026-04-12 19:28:09,657 | INFO | train_grpo_train | metrics_logged mode=train step=934 2026-04-12 19:28:20,680 | INFO | train_grpo_train | metrics_logged mode=train step=935 2026-04-12 19:28:34,183 | INFO | train_grpo_train | metrics_logged mode=train step=936 2026-04-12 19:28:47,887 | INFO | train_grpo_train | metrics_logged mode=train step=937 2026-04-12 19:29:01,656 | INFO | train_grpo_train | metrics_logged mode=train step=938 2026-04-12 19:29:15,099 | INFO | train_grpo_train | metrics_logged mode=train step=939 2026-04-12 19:29:29,084 | INFO | train_grpo_train | metrics_logged mode=train step=940 2026-04-12 19:29:44,724 | INFO | train_grpo_train | metrics_logged mode=train step=941 2026-04-12 19:29:59,681 | INFO | train_grpo_train | metrics_logged mode=train step=942 2026-04-12 19:30:14,588 | INFO | train_grpo_train | metrics_logged mode=train step=943 2026-04-12 19:30:23,951 | INFO | train_grpo_train | metrics_logged mode=train step=944 2026-04-12 19:30:33,669 | INFO | train_grpo_train | metrics_logged mode=train step=945 2026-04-12 19:30:42,508 | INFO | train_grpo_train | metrics_logged mode=train step=946 2026-04-12 19:30:52,142 | INFO | train_grpo_train | metrics_logged mode=train step=947 2026-04-12 19:31:03,138 | INFO | train_grpo_train | metrics_logged mode=train step=948 2026-04-12 19:31:17,138 | INFO | train_grpo_train | metrics_logged mode=train step=949 2026-04-12 19:31:25,658 | INFO | train_grpo_train | metrics_logged mode=train step=950 2026-04-12 19:33:46,037 | INFO | train_grpo_train | metrics_logged mode=eval step=950 2026-04-12 19:34:01,153 | INFO | train_grpo_train | metrics_logged mode=train step=951 2026-04-12 19:34:11,231 | INFO | train_grpo_train | metrics_logged mode=train step=952 2026-04-12 19:34:19,134 | INFO | train_grpo_train | metrics_logged mode=train step=953 2026-04-12 19:34:28,218 | INFO | train_grpo_train | metrics_logged mode=train step=954 2026-04-12 19:34:39,345 | INFO | train_grpo_train | metrics_logged mode=train step=955 2026-04-12 19:34:53,785 | INFO | train_grpo_train | metrics_logged mode=train step=956 2026-04-12 19:35:03,302 | INFO | train_grpo_train | metrics_logged mode=train step=957 2026-04-12 19:35:17,467 | INFO | train_grpo_train | metrics_logged mode=train step=958 2026-04-12 19:35:30,453 | INFO | train_grpo_train | metrics_logged mode=train step=959 2026-04-12 19:35:44,172 | INFO | train_grpo_train | metrics_logged mode=train step=960 2026-04-12 19:35:53,248 | INFO | train_grpo_train | metrics_logged mode=train step=961 2026-04-12 19:36:01,954 | INFO | train_grpo_train | metrics_logged mode=train step=962 2026-04-12 19:36:13,520 | INFO | train_grpo_train | metrics_logged mode=train step=963 2026-04-12 19:36:21,782 | INFO | train_grpo_train | metrics_logged mode=train step=964 2026-04-12 19:36:36,176 | INFO | train_grpo_train | metrics_logged mode=train step=965 2026-04-12 19:36:50,444 | INFO | train_grpo_train | metrics_logged mode=train step=966 2026-04-12 19:37:05,040 | INFO | train_grpo_train | metrics_logged mode=train step=967 2026-04-12 19:37:18,740 | INFO | train_grpo_train | metrics_logged mode=train step=968 2026-04-12 19:37:27,504 | INFO | train_grpo_train | metrics_logged mode=train step=969 2026-04-12 19:37:40,719 | INFO | train_grpo_train | metrics_logged mode=train step=970 2026-04-12 19:37:50,565 | INFO | train_grpo_train | metrics_logged mode=train step=971 2026-04-12 19:38:04,725 | INFO | train_grpo_train | metrics_logged mode=train step=972 2026-04-12 19:38:18,441 | INFO | train_grpo_train | metrics_logged mode=train step=973 2026-04-12 19:38:28,621 | INFO | train_grpo_train | metrics_logged mode=train step=974 2026-04-12 19:38:43,809 | INFO | train_grpo_train | metrics_logged mode=train step=975 2026-04-12 19:38:57,927 | INFO | train_grpo_train | metrics_logged mode=train step=976 2026-04-12 19:39:07,675 | INFO | train_grpo_train | metrics_logged mode=train step=977 2026-04-12 19:39:22,249 | INFO | train_grpo_train | metrics_logged mode=train step=978 2026-04-12 19:39:36,776 | INFO | train_grpo_train | metrics_logged mode=train step=979 2026-04-12 19:39:52,089 | INFO | train_grpo_train | metrics_logged mode=train step=980 2026-04-12 19:40:08,024 | INFO | train_grpo_train | metrics_logged mode=train step=981 2026-04-12 19:40:21,640 | INFO | train_grpo_train | metrics_logged mode=train step=982 2026-04-12 19:40:36,717 | INFO | train_grpo_train | metrics_logged mode=train step=983 2026-04-12 19:40:46,162 | INFO | train_grpo_train | metrics_logged mode=train step=984 2026-04-12 19:41:00,360 | INFO | train_grpo_train | metrics_logged mode=train step=985 2026-04-12 19:41:14,891 | INFO | train_grpo_train | metrics_logged mode=train step=986 2026-04-12 19:41:23,135 | INFO | train_grpo_train | metrics_logged mode=train step=987 2026-04-12 19:41:37,397 | INFO | train_grpo_train | metrics_logged mode=train step=988 2026-04-12 19:41:46,154 | INFO | train_grpo_train | metrics_logged mode=train step=989 2026-04-12 19:41:55,664 | INFO | train_grpo_train | metrics_logged mode=train step=990 2026-04-12 19:42:10,041 | INFO | train_grpo_train | metrics_logged mode=train step=991 2026-04-12 19:42:17,559 | INFO | train_grpo_train | metrics_logged mode=train step=992 2026-04-12 19:42:25,620 | INFO | train_grpo_train | metrics_logged mode=train step=993 2026-04-12 19:42:39,423 | INFO | train_grpo_train | metrics_logged mode=train step=994 2026-04-12 19:42:54,100 | INFO | train_grpo_train | metrics_logged mode=train step=995 2026-04-12 19:43:08,725 | INFO | train_grpo_train | metrics_logged mode=train step=996 2026-04-12 19:43:18,864 | INFO | train_grpo_train | metrics_logged mode=train step=997 2026-04-12 19:43:32,477 | INFO | train_grpo_train | metrics_logged mode=train step=998 2026-04-12 19:43:41,059 | INFO | train_grpo_train | metrics_logged mode=train step=999 2026-04-12 19:43:50,322 | INFO | train_grpo_train | metrics_logged mode=train step=1000 2026-04-12 19:45:47,624 | INFO | train_grpo_train | metrics_logged mode=eval step=1000 2026-04-12 19:45:59,153 | INFO | train_grpo_train | metrics_logged mode=train step=1001 2026-04-12 19:46:08,553 | INFO | train_grpo_train | metrics_logged mode=train step=1002 2026-04-12 19:46:21,741 | INFO | train_grpo_train | metrics_logged mode=train step=1003 2026-04-12 19:46:32,855 | INFO | train_grpo_train | metrics_logged mode=train step=1004 2026-04-12 19:46:41,925 | INFO | train_grpo_train | metrics_logged mode=train step=1005 2026-04-12 19:46:52,502 | INFO | train_grpo_train | metrics_logged mode=train step=1006 2026-04-12 19:47:05,598 | INFO | train_grpo_train | metrics_logged mode=train step=1007 2026-04-12 19:47:14,108 | INFO | train_grpo_train | metrics_logged mode=train step=1008 2026-04-12 19:47:21,700 | INFO | train_grpo_train | metrics_logged mode=train step=1009 2026-04-12 19:47:34,988 | INFO | train_grpo_train | metrics_logged mode=train step=1010 2026-04-12 19:47:49,377 | INFO | train_grpo_train | metrics_logged mode=train step=1011 2026-04-12 19:47:58,724 | INFO | train_grpo_train | metrics_logged mode=train step=1012 2026-04-12 19:48:12,346 | INFO | train_grpo_train | metrics_logged mode=train step=1013 2026-04-12 19:48:21,242 | INFO | train_grpo_train | metrics_logged mode=train step=1014 2026-04-12 19:48:30,300 | INFO | train_grpo_train | metrics_logged mode=train step=1015 2026-04-12 19:48:44,737 | INFO | train_grpo_train | metrics_logged mode=train step=1016 2026-04-12 19:48:53,906 | INFO | train_grpo_train | metrics_logged mode=train step=1017 2026-04-12 19:49:02,756 | INFO | train_grpo_train | metrics_logged mode=train step=1018 2026-04-12 19:49:10,979 | INFO | train_grpo_train | metrics_logged mode=train step=1019 2026-04-12 19:49:24,271 | INFO | train_grpo_train | metrics_logged mode=train step=1020 2026-04-12 19:49:33,705 | INFO | train_grpo_train | metrics_logged mode=train step=1021 2026-04-12 19:49:48,235 | INFO | train_grpo_train | metrics_logged mode=train step=1022 2026-04-12 19:49:57,819 | INFO | train_grpo_train | metrics_logged mode=train step=1023 2026-04-12 19:50:11,441 | INFO | train_grpo_train | metrics_logged mode=train step=1024 2026-04-12 19:50:20,424 | INFO | train_grpo_train | metrics_logged mode=train step=1025 2026-04-12 19:50:30,877 | INFO | train_grpo_train | metrics_logged mode=train step=1026 2026-04-12 19:50:44,943 | INFO | train_grpo_train | metrics_logged mode=train step=1027 2026-04-12 19:50:58,361 | INFO | train_grpo_train | metrics_logged mode=train step=1028 2026-04-12 19:51:11,677 | INFO | train_grpo_train | metrics_logged mode=train step=1029 2026-04-12 19:51:21,923 | INFO | train_grpo_train | metrics_logged mode=train step=1030 2026-04-12 19:51:30,593 | INFO | train_grpo_train | metrics_logged mode=train step=1031 2026-04-12 19:51:44,155 | INFO | train_grpo_train | metrics_logged mode=train step=1032 2026-04-12 19:51:58,238 | INFO | train_grpo_train | metrics_logged mode=train step=1033 2026-04-12 19:52:11,955 | INFO | train_grpo_train | metrics_logged mode=train step=1034 2026-04-12 19:52:26,437 | INFO | train_grpo_train | metrics_logged mode=train step=1035 2026-04-12 19:52:40,540 | INFO | train_grpo_train | metrics_logged mode=train step=1036 2026-04-12 19:52:54,361 | INFO | train_grpo_train | metrics_logged mode=train step=1037 2026-04-12 19:53:03,978 | INFO | train_grpo_train | metrics_logged mode=train step=1038 2026-04-12 19:53:14,052 | INFO | train_grpo_train | metrics_logged mode=train step=1039 2026-04-12 19:53:24,130 | INFO | train_grpo_train | metrics_logged mode=train step=1040 2026-04-12 19:53:37,826 | INFO | train_grpo_train | metrics_logged mode=train step=1041 2026-04-12 19:53:53,978 | INFO | train_grpo_train | metrics_logged mode=train step=1042 2026-04-12 19:54:08,035 | INFO | train_grpo_train | metrics_logged mode=train step=1043 2026-04-12 19:54:24,642 | INFO | train_grpo_train | metrics_logged mode=train step=1044 2026-04-12 19:54:38,652 | INFO | train_grpo_train | metrics_logged mode=train step=1045 2026-04-12 19:54:53,393 | INFO | train_grpo_train | metrics_logged mode=train step=1046 2026-04-12 19:55:07,031 | INFO | train_grpo_train | metrics_logged mode=train step=1047 2026-04-12 19:55:23,009 | INFO | train_grpo_train | metrics_logged mode=train step=1048 2026-04-12 19:55:37,950 | INFO | train_grpo_train | metrics_logged mode=train step=1049 2026-04-12 19:55:48,788 | INFO | train_grpo_train | metrics_logged mode=train step=1050 2026-04-12 19:58:34,754 | INFO | train_grpo_train | metrics_logged mode=eval step=1050 2026-04-12 19:58:56,920 | INFO | train_grpo_train | metrics_logged mode=train step=1051 2026-04-12 19:59:15,688 | INFO | train_grpo_train | metrics_logged mode=train step=1052 2026-04-12 19:59:34,032 | INFO | train_grpo_train | metrics_logged mode=train step=1053 2026-04-12 19:59:44,906 | INFO | train_grpo_train | metrics_logged mode=train step=1054 2026-04-12 20:00:02,548 | INFO | train_grpo_train | metrics_logged mode=train step=1055 2026-04-12 20:00:13,191 | INFO | train_grpo_train | metrics_logged mode=train step=1056 2026-04-12 20:00:30,909 | INFO | train_grpo_train | metrics_logged mode=train step=1057 2026-04-12 20:00:45,043 | INFO | train_grpo_train | metrics_logged mode=train step=1058 2026-04-12 20:00:59,060 | INFO | train_grpo_train | metrics_logged mode=train step=1059 2026-04-12 20:01:17,628 | INFO | train_grpo_train | metrics_logged mode=train step=1060 2026-04-12 20:01:32,425 | INFO | train_grpo_train | metrics_logged mode=train step=1061 2026-04-12 20:01:41,245 | INFO | train_grpo_train | metrics_logged mode=train step=1062 2026-04-12 20:01:56,590 | INFO | train_grpo_train | metrics_logged mode=train step=1063 2026-04-12 20:02:12,821 | INFO | train_grpo_train | metrics_logged mode=train step=1064 2026-04-12 20:02:27,635 | INFO | train_grpo_train | metrics_logged mode=train step=1065 2026-04-12 20:02:42,697 | INFO | train_grpo_train | metrics_logged mode=train step=1066 2026-04-12 20:02:58,595 | INFO | train_grpo_train | metrics_logged mode=train step=1067 2026-04-12 20:03:07,738 | INFO | train_grpo_train | metrics_logged mode=train step=1068 2026-04-12 20:03:23,918 | INFO | train_grpo_train | metrics_logged mode=train step=1069 2026-04-12 20:03:42,573 | INFO | train_grpo_train | metrics_logged mode=train step=1070 2026-04-12 20:03:52,482 | INFO | train_grpo_train | metrics_logged mode=train step=1071 2026-04-12 20:04:01,636 | INFO | train_grpo_train | metrics_logged mode=train step=1072 2026-04-12 20:04:18,268 | INFO | train_grpo_train | metrics_logged mode=train step=1073 2026-04-12 20:04:25,891 | INFO | train_grpo_train | metrics_logged mode=train step=1074 2026-04-12 20:04:38,919 | INFO | train_grpo_train | metrics_logged mode=train step=1075 2026-04-12 20:04:52,503 | INFO | train_grpo_train | metrics_logged mode=train step=1076 2026-04-12 20:05:03,150 | INFO | train_grpo_train | metrics_logged mode=train step=1077 2026-04-12 20:05:17,025 | INFO | train_grpo_train | metrics_logged mode=train step=1078 2026-04-12 20:05:32,434 | INFO | train_grpo_train | metrics_logged mode=train step=1079 2026-04-12 20:05:40,268 | INFO | train_grpo_train | metrics_logged mode=train step=1080 2026-04-12 20:05:54,697 | INFO | train_grpo_train | metrics_logged mode=train step=1081 2026-04-12 20:06:06,776 | INFO | train_grpo_train | metrics_logged mode=train step=1082 2026-04-12 20:06:20,402 | INFO | train_grpo_train | metrics_logged mode=train step=1083 2026-04-12 20:06:36,930 | INFO | train_grpo_train | metrics_logged mode=train step=1084 2026-04-12 20:06:51,379 | INFO | train_grpo_train | metrics_logged mode=train step=1085 2026-04-12 20:07:00,748 | INFO | train_grpo_train | metrics_logged mode=train step=1086 2026-04-12 20:07:15,251 | INFO | train_grpo_train | metrics_logged mode=train step=1087 2026-04-12 20:07:23,879 | INFO | train_grpo_train | metrics_logged mode=train step=1088 2026-04-12 20:07:37,476 | INFO | train_grpo_train | metrics_logged mode=train step=1089 2026-04-12 20:07:45,896 | INFO | train_grpo_train | metrics_logged mode=train step=1090 2026-04-12 20:07:59,437 | INFO | train_grpo_train | metrics_logged mode=train step=1091 2026-04-12 20:08:13,160 | INFO | train_grpo_train | metrics_logged mode=train step=1092 2026-04-12 20:08:22,807 | INFO | train_grpo_train | metrics_logged mode=train step=1093 2026-04-12 20:08:31,477 | INFO | train_grpo_train | metrics_logged mode=train step=1094 2026-04-12 20:08:46,122 | INFO | train_grpo_train | metrics_logged mode=train step=1095 2026-04-12 20:08:59,645 | INFO | train_grpo_train | metrics_logged mode=train step=1096 2026-04-12 20:09:07,748 | INFO | train_grpo_train | metrics_logged mode=train step=1097 2026-04-12 20:09:22,996 | INFO | train_grpo_train | metrics_logged mode=train step=1098 2026-04-12 20:09:31,803 | INFO | train_grpo_train | metrics_logged mode=train step=1099 2026-04-12 20:09:41,966 | INFO | train_grpo_train | metrics_logged mode=train step=1100 2026-04-12 20:12:05,336 | INFO | train_grpo_train | metrics_logged mode=eval step=1100 2026-04-12 20:12:21,413 | INFO | train_grpo_train | metrics_logged mode=train step=1101 2026-04-12 20:12:30,624 | INFO | train_grpo_train | metrics_logged mode=train step=1102 2026-04-12 20:12:43,447 | INFO | train_grpo_train | metrics_logged mode=train step=1103 2026-04-12 20:12:57,591 | INFO | train_grpo_train | metrics_logged mode=train step=1104 2026-04-12 20:13:06,566 | INFO | train_grpo_train | metrics_logged mode=train step=1105 2026-04-12 20:13:20,849 | INFO | train_grpo_train | metrics_logged mode=train step=1106 2026-04-12 20:13:34,722 | INFO | train_grpo_train | metrics_logged mode=train step=1107 2026-04-12 20:13:45,720 | INFO | train_grpo_train | metrics_logged mode=train step=1108 2026-04-12 20:13:59,021 | INFO | train_grpo_train | metrics_logged mode=train step=1109 2026-04-12 20:14:13,444 | INFO | train_grpo_train | metrics_logged mode=train step=1110 2026-04-12 20:14:27,376 | INFO | train_grpo_train | metrics_logged mode=train step=1111 2026-04-12 20:14:41,687 | INFO | train_grpo_train | metrics_logged mode=train step=1112 2026-04-12 20:14:55,608 | INFO | train_grpo_train | metrics_logged mode=train step=1113 2026-04-12 20:15:05,764 | INFO | train_grpo_train | metrics_logged mode=train step=1114 2026-04-12 20:15:13,520 | INFO | train_grpo_train | metrics_logged mode=train step=1115 2026-04-12 20:15:22,672 | INFO | train_grpo_train | metrics_logged mode=train step=1116 2026-04-12 20:15:31,577 | INFO | train_grpo_train | metrics_logged mode=train step=1117 2026-04-12 20:15:45,835 | INFO | train_grpo_train | metrics_logged mode=train step=1118 2026-04-12 20:15:54,898 | INFO | train_grpo_train | metrics_logged mode=train step=1119 2026-04-12 20:16:08,947 | INFO | train_grpo_train | metrics_logged mode=train step=1120 2026-04-12 20:16:24,103 | INFO | train_grpo_train | metrics_logged mode=train step=1121 2026-04-12 20:16:37,997 | INFO | train_grpo_train | metrics_logged mode=train step=1122 2026-04-12 20:16:46,738 | INFO | train_grpo_train | metrics_logged mode=train step=1123 2026-04-12 20:16:56,412 | INFO | train_grpo_train | metrics_logged mode=train step=1124 2026-04-12 20:17:05,244 | INFO | train_grpo_train | metrics_logged mode=train step=1125 2026-04-12 20:17:18,562 | INFO | train_grpo_train | metrics_logged mode=train step=1126 2026-04-12 20:17:27,962 | INFO | train_grpo_train | metrics_logged mode=train step=1127 2026-04-12 20:17:36,308 | INFO | train_grpo_train | metrics_logged mode=train step=1128 2026-04-12 20:17:45,151 | INFO | train_grpo_train | metrics_logged mode=train step=1129 2026-04-12 20:17:57,076 | INFO | train_grpo_train | metrics_logged mode=train step=1130 2026-04-12 20:18:06,875 | INFO | train_grpo_train | metrics_logged mode=train step=1131 2026-04-12 20:18:21,307 | INFO | train_grpo_train | metrics_logged mode=train step=1132 2026-04-12 20:18:35,172 | INFO | train_grpo_train | metrics_logged mode=train step=1133 2026-04-12 20:18:50,650 | INFO | train_grpo_train | metrics_logged mode=train step=1134 2026-04-12 20:19:04,194 | INFO | train_grpo_train | metrics_logged mode=train step=1135 2026-04-12 20:19:12,923 | INFO | train_grpo_train | metrics_logged mode=train step=1136 2026-04-12 20:19:27,216 | INFO | train_grpo_train | metrics_logged mode=train step=1137 2026-04-12 20:19:36,707 | INFO | train_grpo_train | metrics_logged mode=train step=1138 2026-04-12 20:19:51,141 | INFO | train_grpo_train | metrics_logged mode=train step=1139 2026-04-12 20:20:04,538 | INFO | train_grpo_train | metrics_logged mode=train step=1140 2026-04-12 20:20:12,504 | INFO | train_grpo_train | metrics_logged mode=train step=1141 2026-04-12 20:20:27,504 | INFO | train_grpo_train | metrics_logged mode=train step=1142 2026-04-12 20:20:41,738 | INFO | train_grpo_train | metrics_logged mode=train step=1143 2026-04-12 20:20:57,402 | INFO | train_grpo_train | metrics_logged mode=train step=1144 2026-04-12 20:21:05,629 | INFO | train_grpo_train | metrics_logged mode=train step=1145 2026-04-12 20:21:19,860 | INFO | train_grpo_train | metrics_logged mode=train step=1146 2026-04-12 20:21:34,141 | INFO | train_grpo_train | metrics_logged mode=train step=1147 2026-04-12 20:21:48,310 | INFO | train_grpo_train | metrics_logged mode=train step=1148 2026-04-12 20:21:57,318 | INFO | train_grpo_train | metrics_logged mode=train step=1149 2026-04-12 20:22:05,603 | INFO | train_grpo_train | metrics_logged mode=train step=1150 2026-04-12 20:24:18,678 | INFO | train_grpo_train | metrics_logged mode=eval step=1150 2026-04-12 20:24:35,622 | INFO | train_grpo_train | metrics_logged mode=train step=1151 2026-04-12 20:24:50,414 | INFO | train_grpo_train | metrics_logged mode=train step=1152 2026-04-12 20:24:59,237 | INFO | train_grpo_train | metrics_logged mode=train step=1153 2026-04-12 20:25:08,524 | INFO | train_grpo_train | metrics_logged mode=train step=1154 2026-04-12 20:25:18,907 | INFO | train_grpo_train | metrics_logged mode=train step=1155 2026-04-12 20:25:27,738 | INFO | train_grpo_train | metrics_logged mode=train step=1156 2026-04-12 20:25:42,376 | INFO | train_grpo_train | metrics_logged mode=train step=1157 2026-04-12 20:25:51,453 | INFO | train_grpo_train | metrics_logged mode=train step=1158 2026-04-12 20:26:05,696 | INFO | train_grpo_train | metrics_logged mode=train step=1159 2026-04-12 20:26:14,672 | INFO | train_grpo_train | metrics_logged mode=train step=1160 2026-04-12 20:26:30,250 | INFO | train_grpo_train | metrics_logged mode=train step=1161 2026-04-12 20:26:45,334 | INFO | train_grpo_train | metrics_logged mode=train step=1162 2026-04-12 20:26:54,464 | INFO | train_grpo_train | metrics_logged mode=train step=1163 2026-04-12 20:27:03,695 | INFO | train_grpo_train | metrics_logged mode=train step=1164 2026-04-12 20:27:12,115 | INFO | train_grpo_train | metrics_logged mode=train step=1165 2026-04-12 20:27:21,348 | INFO | train_grpo_train | metrics_logged mode=train step=1166 2026-04-12 20:27:31,693 | INFO | train_grpo_train | metrics_logged mode=train step=1167 2026-04-12 20:27:45,844 | INFO | train_grpo_train | metrics_logged mode=train step=1168 2026-04-12 20:28:00,904 | INFO | train_grpo_train | metrics_logged mode=train step=1169 2026-04-12 20:28:10,464 | INFO | train_grpo_train | metrics_logged mode=train step=1170 2026-04-12 20:28:25,971 | INFO | train_grpo_train | metrics_logged mode=train step=1171 2026-04-12 20:28:40,466 | INFO | train_grpo_train | metrics_logged mode=train step=1172 2026-04-12 20:28:54,306 | INFO | train_grpo_train | metrics_logged mode=train step=1173 2026-04-12 20:29:03,070 | INFO | train_grpo_train | metrics_logged mode=train step=1174 2026-04-12 20:29:17,149 | INFO | train_grpo_train | metrics_logged mode=train step=1175 2026-04-12 20:29:27,153 | INFO | train_grpo_train | metrics_logged mode=train step=1176 2026-04-12 20:29:36,456 | INFO | train_grpo_train | metrics_logged mode=train step=1177 2026-04-12 20:29:46,302 | INFO | train_grpo_train | metrics_logged mode=train step=1178 2026-04-12 20:30:01,549 | INFO | train_grpo_train | metrics_logged mode=train step=1179 2026-04-12 20:30:09,975 | INFO | train_grpo_train | metrics_logged mode=train step=1180 2026-04-12 20:30:17,830 | INFO | train_grpo_train | metrics_logged mode=train step=1181 2026-04-12 20:30:27,549 | INFO | train_grpo_train | metrics_logged mode=train step=1182 2026-04-12 20:30:35,995 | INFO | train_grpo_train | metrics_logged mode=train step=1183 2026-04-12 20:30:45,275 | INFO | train_grpo_train | metrics_logged mode=train step=1184 2026-04-12 20:30:55,037 | INFO | train_grpo_train | metrics_logged mode=train step=1185 2026-04-12 20:31:04,387 | INFO | train_grpo_train | metrics_logged mode=train step=1186 2026-04-12 20:31:12,187 | INFO | train_grpo_train | metrics_logged mode=train step=1187 2026-04-12 20:31:19,768 | INFO | train_grpo_train | metrics_logged mode=train step=1188 2026-04-12 20:31:28,899 | INFO | train_grpo_train | metrics_logged mode=train step=1189 2026-04-12 20:31:43,053 | INFO | train_grpo_train | metrics_logged mode=train step=1190 2026-04-12 20:31:51,592 | INFO | train_grpo_train | metrics_logged mode=train step=1191 2026-04-12 20:31:59,932 | INFO | train_grpo_train | metrics_logged mode=train step=1192 2026-04-12 20:32:09,353 | INFO | train_grpo_train | metrics_logged mode=train step=1193 2026-04-12 20:32:19,402 | INFO | train_grpo_train | metrics_logged mode=train step=1194 2026-04-12 20:32:28,830 | INFO | train_grpo_train | metrics_logged mode=train step=1195 2026-04-12 20:32:37,507 | INFO | train_grpo_train | metrics_logged mode=train step=1196 2026-04-12 20:32:51,399 | INFO | train_grpo_train | metrics_logged mode=train step=1197 2026-04-12 20:33:00,755 | INFO | train_grpo_train | metrics_logged mode=train step=1198 2026-04-12 20:33:15,450 | INFO | train_grpo_train | metrics_logged mode=train step=1199 2026-04-12 20:33:27,035 | INFO | train_grpo_train | metrics_logged mode=train step=1200 2026-04-12 20:35:18,831 | INFO | train_grpo_train | metrics_logged mode=eval step=1200 2026-04-12 20:35:36,441 | INFO | train_grpo_train | metrics_logged mode=train step=1201 2026-04-12 20:35:45,229 | INFO | train_grpo_train | metrics_logged mode=train step=1202 2026-04-12 20:35:53,395 | INFO | train_grpo_train | metrics_logged mode=train step=1203 2026-04-12 20:36:03,205 | INFO | train_grpo_train | metrics_logged mode=train step=1204 2026-04-12 20:36:12,049 | INFO | train_grpo_train | metrics_logged mode=train step=1205 2026-04-12 20:36:20,673 | INFO | train_grpo_train | metrics_logged mode=train step=1206 2026-04-12 20:36:34,366 | INFO | train_grpo_train | metrics_logged mode=train step=1207 2026-04-12 20:36:42,890 | INFO | train_grpo_train | metrics_logged mode=train step=1208 2026-04-12 20:36:56,803 | INFO | train_grpo_train | metrics_logged mode=train step=1209 2026-04-12 20:37:04,937 | INFO | train_grpo_train | metrics_logged mode=train step=1210 2026-04-12 20:37:18,802 | INFO | train_grpo_train | metrics_logged mode=train step=1211 2026-04-12 20:37:32,435 | INFO | train_grpo_train | metrics_logged mode=train step=1212 2026-04-12 20:37:41,359 | INFO | train_grpo_train | metrics_logged mode=train step=1213 2026-04-12 20:37:49,781 | INFO | train_grpo_train | metrics_logged mode=train step=1214 2026-04-12 20:38:03,600 | INFO | train_grpo_train | metrics_logged mode=train step=1215 2026-04-12 20:38:11,680 | INFO | train_grpo_train | metrics_logged mode=train step=1216 2026-04-12 20:38:26,558 | INFO | train_grpo_train | metrics_logged mode=train step=1217 2026-04-12 20:38:40,450 | INFO | train_grpo_train | metrics_logged mode=train step=1218 2026-04-12 20:38:50,472 | INFO | train_grpo_train | metrics_logged mode=train step=1219 2026-04-12 20:38:59,684 | INFO | train_grpo_train | metrics_logged mode=train step=1220 2026-04-12 20:39:08,231 | INFO | train_grpo_train | metrics_logged mode=train step=1221 2026-04-12 20:39:22,954 | INFO | train_grpo_train | metrics_logged mode=train step=1222 2026-04-12 20:39:37,428 | INFO | train_grpo_train | metrics_logged mode=train step=1223 2026-04-12 20:39:51,342 | INFO | train_grpo_train | metrics_logged mode=train step=1224 2026-04-12 20:40:00,182 | INFO | train_grpo_train | metrics_logged mode=train step=1225 2026-04-12 20:40:08,378 | INFO | train_grpo_train | metrics_logged mode=train step=1226 2026-04-12 20:40:16,734 | INFO | train_grpo_train | metrics_logged mode=train step=1227 2026-04-12 20:40:25,684 | INFO | train_grpo_train | metrics_logged mode=train step=1228 2026-04-12 20:40:40,095 | INFO | train_grpo_train | metrics_logged mode=train step=1229 2026-04-12 20:40:49,193 | INFO | train_grpo_train | metrics_logged mode=train step=1230 2026-04-12 20:40:58,224 | INFO | train_grpo_train | metrics_logged mode=train step=1231 2026-04-12 20:41:12,901 | INFO | train_grpo_train | metrics_logged mode=train step=1232 2026-04-12 20:41:27,483 | INFO | train_grpo_train | metrics_logged mode=train step=1233 2026-04-12 20:41:41,583 | INFO | train_grpo_train | metrics_logged mode=train step=1234 2026-04-12 20:41:55,739 | INFO | train_grpo_train | metrics_logged mode=train step=1235 2026-04-12 20:42:09,988 | INFO | train_grpo_train | metrics_logged mode=train step=1236 2026-04-12 20:42:24,228 | INFO | train_grpo_train | metrics_logged mode=train step=1237 2026-04-12 20:42:32,394 | INFO | train_grpo_train | metrics_logged mode=train step=1238 2026-04-12 20:42:40,455 | INFO | train_grpo_train | metrics_logged mode=train step=1239 2026-04-12 20:42:47,963 | INFO | train_grpo_train | metrics_logged mode=train step=1240 2026-04-12 20:42:55,389 | INFO | train_grpo_train | metrics_logged mode=train step=1241 2026-04-12 20:43:09,496 | INFO | train_grpo_train | metrics_logged mode=train step=1242 2026-04-12 20:43:23,550 | INFO | train_grpo_train | metrics_logged mode=train step=1243 2026-04-12 20:43:37,137 | INFO | train_grpo_train | metrics_logged mode=train step=1244 2026-04-12 20:43:46,377 | INFO | train_grpo_train | metrics_logged mode=train step=1245 2026-04-12 20:44:00,767 | INFO | train_grpo_train | metrics_logged mode=train step=1246 2026-04-12 20:44:09,232 | INFO | train_grpo_train | metrics_logged mode=train step=1247 2026-04-12 20:44:18,331 | INFO | train_grpo_train | metrics_logged mode=train step=1248 2026-04-12 20:44:27,603 | INFO | train_grpo_train | metrics_logged mode=train step=1249 2026-04-12 20:44:36,749 | INFO | train_grpo_train | metrics_logged mode=train step=1250 2026-04-12 20:46:30,724 | INFO | train_grpo_train | metrics_logged mode=eval step=1250 2026-04-12 20:46:44,835 | INFO | train_grpo_train | metrics_logged mode=train step=1251 2026-04-12 20:47:02,538 | INFO | train_grpo_train | metrics_logged mode=train step=1252 2026-04-12 20:47:17,574 | INFO | train_grpo_train | metrics_logged mode=train step=1253 2026-04-12 20:47:26,287 | INFO | train_grpo_train | metrics_logged mode=train step=1254 2026-04-12 20:47:39,629 | INFO | train_grpo_train | metrics_logged mode=train step=1255 2026-04-12 20:47:49,359 | INFO | train_grpo_train | metrics_logged mode=train step=1256 2026-04-12 20:48:03,622 | INFO | train_grpo_train | metrics_logged mode=train step=1257 2026-04-12 20:48:13,709 | INFO | train_grpo_train | metrics_logged mode=train step=1258 2026-04-12 20:48:24,713 | INFO | train_grpo_train | metrics_logged mode=train step=1259 2026-04-12 20:48:36,315 | INFO | train_grpo_train | metrics_logged mode=train step=1260 2026-04-12 20:48:46,378 | INFO | train_grpo_train | metrics_logged mode=train step=1261 2026-04-12 20:48:58,882 | INFO | train_grpo_train | metrics_logged mode=train step=1262 2026-04-12 20:49:08,314 | INFO | train_grpo_train | metrics_logged mode=train step=1263 2026-04-12 20:49:19,163 | INFO | train_grpo_train | metrics_logged mode=train step=1264 2026-04-12 20:49:31,784 | INFO | train_grpo_train | metrics_logged mode=train step=1265 2026-04-12 20:49:47,044 | INFO | train_grpo_train | metrics_logged mode=train step=1266 2026-04-12 20:49:58,585 | INFO | train_grpo_train | metrics_logged mode=train step=1267 2026-04-12 20:50:07,409 | INFO | train_grpo_train | metrics_logged mode=train step=1268 2026-04-12 20:50:16,191 | INFO | train_grpo_train | metrics_logged mode=train step=1269 2026-04-12 20:50:27,194 | INFO | train_grpo_train | metrics_logged mode=train step=1270 2026-04-12 20:50:42,139 | INFO | train_grpo_train | metrics_logged mode=train step=1271 2026-04-12 20:50:58,269 | INFO | train_grpo_train | metrics_logged mode=train step=1272 2026-04-12 20:51:09,385 | INFO | train_grpo_train | metrics_logged mode=train step=1273 2026-04-12 20:51:17,934 | INFO | train_grpo_train | metrics_logged mode=train step=1274 2026-04-12 20:51:26,159 | INFO | train_grpo_train | metrics_logged mode=train step=1275 2026-04-12 20:51:36,258 | INFO | train_grpo_train | metrics_logged mode=train step=1276 2026-04-12 20:51:45,584 | INFO | train_grpo_train | metrics_logged mode=train step=1277 2026-04-12 20:51:57,376 | INFO | train_grpo_train | metrics_logged mode=train step=1278 2026-04-12 20:52:10,830 | INFO | train_grpo_train | metrics_logged mode=train step=1279 2026-04-12 20:52:19,139 | INFO | train_grpo_train | metrics_logged mode=train step=1280 2026-04-12 20:52:34,461 | INFO | train_grpo_train | metrics_logged mode=train step=1281 2026-04-12 20:52:49,094 | INFO | train_grpo_train | metrics_logged mode=train step=1282 2026-04-12 20:52:57,963 | INFO | train_grpo_train | metrics_logged mode=train step=1283 2026-04-12 20:53:07,654 | INFO | train_grpo_train | metrics_logged mode=train step=1284 2026-04-12 20:53:22,244 | INFO | train_grpo_train | metrics_logged mode=train step=1285 2026-04-12 20:53:32,522 | INFO | train_grpo_train | metrics_logged mode=train step=1286 2026-04-12 20:53:42,128 | INFO | train_grpo_train | metrics_logged mode=train step=1287 2026-04-12 20:53:51,466 | INFO | train_grpo_train | metrics_logged mode=train step=1288 2026-04-12 20:54:05,536 | INFO | train_grpo_train | metrics_logged mode=train step=1289 2026-04-12 20:54:16,047 | INFO | train_grpo_train | metrics_logged mode=train step=1290 2026-04-12 20:54:30,021 | INFO | train_grpo_train | metrics_logged mode=train step=1291 2026-04-12 20:54:44,232 | INFO | train_grpo_train | metrics_logged mode=train step=1292 2026-04-12 20:54:58,390 | INFO | train_grpo_train | metrics_logged mode=train step=1293 2026-04-12 20:55:12,320 | INFO | train_grpo_train | metrics_logged mode=train step=1294 2026-04-12 20:55:26,517 | INFO | train_grpo_train | metrics_logged mode=train step=1295 2026-04-12 20:55:44,640 | INFO | train_grpo_train | metrics_logged mode=train step=1296 2026-04-12 20:55:53,392 | INFO | train_grpo_train | metrics_logged mode=train step=1297 2026-04-12 20:56:02,948 | INFO | train_grpo_train | metrics_logged mode=train step=1298 2026-04-12 20:56:13,212 | INFO | train_grpo_train | metrics_logged mode=train step=1299 2026-04-12 20:56:28,078 | INFO | train_grpo_train | metrics_logged mode=train step=1300 2026-04-12 20:58:29,179 | INFO | train_grpo_train | metrics_logged mode=eval step=1300 2026-04-12 20:58:46,680 | INFO | train_grpo_train | metrics_logged mode=train step=1301 2026-04-12 20:58:56,486 | INFO | train_grpo_train | metrics_logged mode=train step=1302 2026-04-12 20:59:06,366 | INFO | train_grpo_train | metrics_logged mode=train step=1303 2026-04-12 20:59:14,310 | INFO | train_grpo_train | metrics_logged mode=train step=1304 2026-04-12 20:59:21,978 | INFO | train_grpo_train | metrics_logged mode=train step=1305 2026-04-12 20:59:36,082 | INFO | train_grpo_train | metrics_logged mode=train step=1306 2026-04-12 20:59:43,717 | INFO | train_grpo_train | metrics_logged mode=train step=1307 2026-04-12 20:59:57,601 | INFO | train_grpo_train | metrics_logged mode=train step=1308 2026-04-12 21:00:07,212 | INFO | train_grpo_train | metrics_logged mode=train step=1309 2026-04-12 21:00:16,439 | INFO | train_grpo_train | metrics_logged mode=train step=1310 2026-04-12 21:00:26,093 | INFO | train_grpo_train | metrics_logged mode=train step=1311 2026-04-12 21:00:35,915 | INFO | train_grpo_train | metrics_logged mode=train step=1312 2026-04-12 21:00:44,331 | INFO | train_grpo_train | metrics_logged mode=train step=1313 2026-04-12 21:00:54,893 | INFO | train_grpo_train | metrics_logged mode=train step=1314 2026-04-12 21:01:08,687 | INFO | train_grpo_train | metrics_logged mode=train step=1315 2026-04-12 21:01:16,775 | INFO | train_grpo_train | metrics_logged mode=train step=1316 2026-04-12 21:01:30,595 | INFO | train_grpo_train | metrics_logged mode=train step=1317 2026-04-12 21:01:44,606 | INFO | train_grpo_train | metrics_logged mode=train step=1318 2026-04-12 21:01:53,079 | INFO | train_grpo_train | metrics_logged mode=train step=1319 2026-04-12 21:02:01,532 | INFO | train_grpo_train | metrics_logged mode=train step=1320 2026-04-12 21:02:09,980 | INFO | train_grpo_train | metrics_logged mode=train step=1321 2026-04-12 21:02:23,522 | INFO | train_grpo_train | metrics_logged mode=train step=1322 2026-04-12 21:02:31,977 | INFO | train_grpo_train | metrics_logged mode=train step=1323 2026-04-12 21:02:41,150 | INFO | train_grpo_train | metrics_logged mode=train step=1324 2026-04-12 21:02:49,215 | INFO | train_grpo_train | metrics_logged mode=train step=1325 2026-04-12 21:03:02,566 | INFO | train_grpo_train | metrics_logged mode=train step=1326 2026-04-12 21:03:12,007 | INFO | train_grpo_train | metrics_logged mode=train step=1327 2026-04-12 21:03:19,603 | INFO | train_grpo_train | metrics_logged mode=train step=1328 2026-04-12 21:03:28,731 | INFO | train_grpo_train | metrics_logged mode=train step=1329 2026-04-12 21:03:37,728 | INFO | train_grpo_train | metrics_logged mode=train step=1330 2026-04-12 21:03:51,267 | INFO | train_grpo_train | metrics_logged mode=train step=1331 2026-04-12 21:04:00,205 | INFO | train_grpo_train | metrics_logged mode=train step=1332 2026-04-12 21:04:07,921 | INFO | train_grpo_train | metrics_logged mode=train step=1333 2026-04-12 21:04:21,907 | INFO | train_grpo_train | metrics_logged mode=train step=1334 2026-04-12 21:04:30,400 | INFO | train_grpo_train | metrics_logged mode=train step=1335 2026-04-12 21:04:38,412 | INFO | train_grpo_train | metrics_logged mode=train step=1336 2026-04-12 21:04:46,536 | INFO | train_grpo_train | metrics_logged mode=train step=1337 2026-04-12 21:04:55,337 | INFO | train_grpo_train | metrics_logged mode=train step=1338 2026-04-12 21:05:04,187 | INFO | train_grpo_train | metrics_logged mode=train step=1339 2026-04-12 21:05:13,742 | INFO | train_grpo_train | metrics_logged mode=train step=1340 2026-04-12 21:05:22,511 | INFO | train_grpo_train | metrics_logged mode=train step=1341 2026-04-12 21:05:30,784 | INFO | train_grpo_train | metrics_logged mode=train step=1342 2026-04-12 21:05:40,091 | INFO | train_grpo_train | metrics_logged mode=train step=1343 2026-04-12 21:05:53,556 | INFO | train_grpo_train | metrics_logged mode=train step=1344 2026-04-12 21:06:03,350 | INFO | train_grpo_train | metrics_logged mode=train step=1345 2026-04-12 21:06:12,747 | INFO | train_grpo_train | metrics_logged mode=train step=1346 2026-04-12 21:06:22,718 | INFO | train_grpo_train | metrics_logged mode=train step=1347 2026-04-12 21:06:32,328 | INFO | train_grpo_train | metrics_logged mode=train step=1348 2026-04-12 21:06:42,207 | INFO | train_grpo_train | metrics_logged mode=train step=1349 2026-04-12 21:06:55,731 | INFO | train_grpo_train | metrics_logged mode=train step=1350 2026-04-12 21:08:49,745 | INFO | train_grpo_train | metrics_logged mode=eval step=1350 2026-04-12 21:09:04,424 | INFO | train_grpo_train | metrics_logged mode=train step=1351 2026-04-12 21:09:13,452 | INFO | train_grpo_train | metrics_logged mode=train step=1352 2026-04-12 21:09:21,863 | INFO | train_grpo_train | metrics_logged mode=train step=1353 2026-04-12 21:09:35,924 | INFO | train_grpo_train | metrics_logged mode=train step=1354 2026-04-12 21:09:44,616 | INFO | train_grpo_train | metrics_logged mode=train step=1355 2026-04-12 21:09:58,620 | INFO | train_grpo_train | metrics_logged mode=train step=1356 2026-04-12 21:10:07,312 | INFO | train_grpo_train | metrics_logged mode=train step=1357 2026-04-12 21:10:21,065 | INFO | train_grpo_train | metrics_logged mode=train step=1358 2026-04-12 21:10:29,218 | INFO | train_grpo_train | metrics_logged mode=train step=1359 2026-04-12 21:10:43,072 | INFO | train_grpo_train | metrics_logged mode=train step=1360 2026-04-12 21:10:56,529 | INFO | train_grpo_train | metrics_logged mode=train step=1361 2026-04-12 21:11:11,601 | INFO | train_grpo_train | metrics_logged mode=train step=1362 2026-04-12 21:11:25,020 | INFO | train_grpo_train | metrics_logged mode=train step=1363 2026-04-12 21:11:34,106 | INFO | train_grpo_train | metrics_logged mode=train step=1364 2026-04-12 21:11:44,427 | INFO | train_grpo_train | metrics_logged mode=train step=1365 2026-04-12 21:11:58,120 | INFO | train_grpo_train | metrics_logged mode=train step=1366 2026-04-12 21:12:11,468 | INFO | train_grpo_train | metrics_logged mode=train step=1367 2026-04-12 21:12:20,694 | INFO | train_grpo_train | metrics_logged mode=train step=1368 2026-04-12 21:12:30,050 | INFO | train_grpo_train | metrics_logged mode=train step=1369 2026-04-12 21:12:39,296 | INFO | train_grpo_train | metrics_logged mode=train step=1370 2026-04-12 21:12:48,607 | INFO | train_grpo_train | metrics_logged mode=train step=1371 2026-04-12 21:12:58,043 | INFO | train_grpo_train | metrics_logged mode=train step=1372 2026-04-12 21:13:06,934 | INFO | train_grpo_train | metrics_logged mode=train step=1373 2026-04-12 21:13:15,385 | INFO | train_grpo_train | metrics_logged mode=train step=1374 2026-04-12 21:13:29,475 | INFO | train_grpo_train | metrics_logged mode=train step=1375 2026-04-12 21:13:43,613 | INFO | train_grpo_train | metrics_logged mode=train step=1376 2026-04-12 21:13:58,031 | INFO | train_grpo_train | metrics_logged mode=train step=1377 2026-04-12 21:14:06,392 | INFO | train_grpo_train | metrics_logged mode=train step=1378 2026-04-12 21:14:20,715 | INFO | train_grpo_train | metrics_logged mode=train step=1379 2026-04-12 21:14:28,981 | INFO | train_grpo_train | metrics_logged mode=train step=1380 2026-04-12 21:14:43,453 | INFO | train_grpo_train | metrics_logged mode=train step=1381 2026-04-12 21:14:53,466 | INFO | train_grpo_train | metrics_logged mode=train step=1382 2026-04-12 21:15:02,853 | INFO | train_grpo_train | metrics_logged mode=train step=1383 2026-04-12 21:15:11,770 | INFO | train_grpo_train | metrics_logged mode=train step=1384 2026-04-12 21:15:21,424 | INFO | train_grpo_train | metrics_logged mode=train step=1385 2026-04-12 21:15:30,980 | INFO | train_grpo_train | metrics_logged mode=train step=1386 2026-04-12 21:15:40,207 | INFO | train_grpo_train | metrics_logged mode=train step=1387 2026-04-12 21:15:48,915 | INFO | train_grpo_train | metrics_logged mode=train step=1388 2026-04-12 21:15:56,837 | INFO | train_grpo_train | metrics_logged mode=train step=1389 2026-04-12 21:16:12,013 | INFO | train_grpo_train | metrics_logged mode=train step=1390 2026-04-12 21:16:21,102 | INFO | train_grpo_train | metrics_logged mode=train step=1391 2026-04-12 21:16:35,152 | INFO | train_grpo_train | metrics_logged mode=train step=1392 2026-04-12 21:16:49,554 | INFO | train_grpo_train | metrics_logged mode=train step=1393 2026-04-12 21:16:58,245 | INFO | train_grpo_train | metrics_logged mode=train step=1394 2026-04-12 21:17:07,530 | INFO | train_grpo_train | metrics_logged mode=train step=1395 2026-04-12 21:17:17,007 | INFO | train_grpo_train | metrics_logged mode=train step=1396 2026-04-12 21:17:32,140 | INFO | train_grpo_train | metrics_logged mode=train step=1397 2026-04-12 21:17:40,993 | INFO | train_grpo_train | metrics_logged mode=train step=1398 2026-04-12 21:17:50,986 | INFO | train_grpo_train | metrics_logged mode=train step=1399 2026-04-12 21:18:05,178 | INFO | train_grpo_train | metrics_logged mode=train step=1400 2026-04-12 21:20:35,237 | INFO | train_grpo_train | metrics_logged mode=eval step=1400 2026-04-12 21:20:55,049 | INFO | train_grpo_train | metrics_logged mode=train step=1401 2026-04-12 21:21:08,734 | INFO | train_grpo_train | metrics_logged mode=train step=1402 2026-04-12 21:21:22,674 | INFO | train_grpo_train | metrics_logged mode=train step=1403 2026-04-12 21:21:36,660 | INFO | train_grpo_train | metrics_logged mode=train step=1404 2026-04-12 21:21:51,215 | INFO | train_grpo_train | metrics_logged mode=train step=1405 2026-04-12 21:22:01,173 | INFO | train_grpo_train | metrics_logged mode=train step=1406 2026-04-12 21:22:15,783 | INFO | train_grpo_train | metrics_logged mode=train step=1407 2026-04-12 21:22:26,775 | INFO | train_grpo_train | metrics_logged mode=train step=1408 2026-04-12 21:22:40,781 | INFO | train_grpo_train | metrics_logged mode=train step=1409 2026-04-12 21:22:55,782 | INFO | train_grpo_train | metrics_logged mode=train step=1410 2026-04-12 21:23:12,580 | INFO | train_grpo_train | metrics_logged mode=train step=1411 2026-04-12 21:23:21,931 | INFO | train_grpo_train | metrics_logged mode=train step=1412 2026-04-12 21:23:30,985 | INFO | train_grpo_train | metrics_logged mode=train step=1413 2026-04-12 21:23:39,896 | INFO | train_grpo_train | metrics_logged mode=train step=1414 2026-04-12 21:23:49,883 | INFO | train_grpo_train | metrics_logged mode=train step=1415 2026-04-12 21:24:11,266 | INFO | train_grpo_train | metrics_logged mode=train step=1416 2026-04-12 21:24:25,206 | INFO | train_grpo_train | metrics_logged mode=train step=1417 2026-04-12 21:24:39,108 | INFO | train_grpo_train | metrics_logged mode=train step=1418 2026-04-12 21:24:53,528 | INFO | train_grpo_train | metrics_logged mode=train step=1419 2026-04-12 21:25:08,813 | INFO | train_grpo_train | metrics_logged mode=train step=1420 2026-04-12 21:25:22,816 | INFO | train_grpo_train | metrics_logged mode=train step=1421 2026-04-12 21:25:37,026 | INFO | train_grpo_train | metrics_logged mode=train step=1422 2026-04-12 21:25:50,712 | INFO | train_grpo_train | metrics_logged mode=train step=1423 2026-04-12 21:26:00,566 | INFO | train_grpo_train | metrics_logged mode=train step=1424 2026-04-12 21:26:10,380 | INFO | train_grpo_train | metrics_logged mode=train step=1425 2026-04-12 21:26:23,879 | INFO | train_grpo_train | metrics_logged mode=train step=1426 2026-04-12 21:26:38,291 | INFO | train_grpo_train | metrics_logged mode=train step=1427 2026-04-12 21:26:47,735 | INFO | train_grpo_train | metrics_logged mode=train step=1428 2026-04-12 21:27:01,473 | INFO | train_grpo_train | metrics_logged mode=train step=1429 2026-04-12 21:27:16,008 | INFO | train_grpo_train | metrics_logged mode=train step=1430 2026-04-12 21:27:26,849 | INFO | train_grpo_train | metrics_logged mode=train step=1431 2026-04-12 21:27:40,821 | INFO | train_grpo_train | metrics_logged mode=train step=1432 2026-04-12 21:27:53,211 | INFO | train_grpo_train | metrics_logged mode=train step=1433 2026-04-12 21:28:02,011 | INFO | train_grpo_train | metrics_logged mode=train step=1434 2026-04-12 21:28:11,684 | INFO | train_grpo_train | metrics_logged mode=train step=1435 2026-04-12 21:28:26,414 | INFO | train_grpo_train | metrics_logged mode=train step=1436 2026-04-12 21:28:35,554 | INFO | train_grpo_train | metrics_logged mode=train step=1437 2026-04-12 21:28:50,179 | INFO | train_grpo_train | metrics_logged mode=train step=1438 2026-04-12 21:28:58,653 | INFO | train_grpo_train | metrics_logged mode=train step=1439 2026-04-12 21:29:08,611 | INFO | train_grpo_train | metrics_logged mode=train step=1440 2026-04-12 21:29:22,215 | INFO | train_grpo_train | metrics_logged mode=train step=1441 2026-04-12 21:29:37,549 | INFO | train_grpo_train | metrics_logged mode=train step=1442 2026-04-12 21:29:47,050 | INFO | train_grpo_train | metrics_logged mode=train step=1443 2026-04-12 21:30:00,914 | INFO | train_grpo_train | metrics_logged mode=train step=1444 2026-04-12 21:30:14,955 | INFO | train_grpo_train | metrics_logged mode=train step=1445 2026-04-12 21:30:24,254 | INFO | train_grpo_train | metrics_logged mode=train step=1446 2026-04-12 21:30:33,860 | INFO | train_grpo_train | metrics_logged mode=train step=1447 2026-04-12 21:30:47,828 | INFO | train_grpo_train | metrics_logged mode=train step=1448 2026-04-12 21:31:01,755 | INFO | train_grpo_train | metrics_logged mode=train step=1449 2026-04-12 21:31:11,239 | INFO | train_grpo_train | metrics_logged mode=train step=1450 2026-04-12 21:33:08,248 | INFO | train_grpo_train | metrics_logged mode=eval step=1450 2026-04-12 21:33:20,010 | INFO | train_grpo_train | metrics_logged mode=train step=1451 2026-04-12 21:33:29,496 | INFO | train_grpo_train | metrics_logged mode=train step=1452 2026-04-12 21:33:39,130 | INFO | train_grpo_train | metrics_logged mode=train step=1453 2026-04-12 21:33:49,079 | INFO | train_grpo_train | metrics_logged mode=train step=1454 2026-04-12 21:34:02,886 | INFO | train_grpo_train | metrics_logged mode=train step=1455 2026-04-12 21:34:12,356 | INFO | train_grpo_train | metrics_logged mode=train step=1456 2026-04-12 21:34:22,538 | INFO | train_grpo_train | metrics_logged mode=train step=1457 2026-04-12 21:34:36,944 | INFO | train_grpo_train | metrics_logged mode=train step=1458 2026-04-12 21:34:47,392 | INFO | train_grpo_train | metrics_logged mode=train step=1459 2026-04-12 21:34:55,251 | INFO | train_grpo_train | metrics_logged mode=train step=1460 2026-04-12 21:35:03,975 | INFO | train_grpo_train | metrics_logged mode=train step=1461 2026-04-12 21:35:13,043 | INFO | train_grpo_train | metrics_logged mode=train step=1462 2026-04-12 21:35:21,870 | INFO | train_grpo_train | metrics_logged mode=train step=1463 2026-04-12 21:35:36,463 | INFO | train_grpo_train | metrics_logged mode=train step=1464 2026-04-12 21:35:45,563 | INFO | train_grpo_train | metrics_logged mode=train step=1465 2026-04-12 21:36:00,191 | INFO | train_grpo_train | metrics_logged mode=train step=1466 2026-04-12 21:36:09,156 | INFO | train_grpo_train | metrics_logged mode=train step=1467 2026-04-12 21:36:18,865 | INFO | train_grpo_train | metrics_logged mode=train step=1468 2026-04-12 21:36:28,424 | INFO | train_grpo_train | metrics_logged mode=train step=1469 2026-04-12 21:36:37,353 | INFO | train_grpo_train | metrics_logged mode=train step=1470 2026-04-12 21:36:46,436 | INFO | train_grpo_train | metrics_logged mode=train step=1471 2026-04-12 21:37:00,605 | INFO | train_grpo_train | metrics_logged mode=train step=1472 2026-04-12 21:37:13,926 | INFO | train_grpo_train | metrics_logged mode=train step=1473 2026-04-12 21:37:22,336 | INFO | train_grpo_train | metrics_logged mode=train step=1474 2026-04-12 21:37:33,097 | INFO | train_grpo_train | metrics_logged mode=train step=1475 2026-04-12 21:37:47,024 | INFO | train_grpo_train | metrics_logged mode=train step=1476 2026-04-12 21:37:55,377 | INFO | train_grpo_train | metrics_logged mode=train step=1477 2026-04-12 21:38:09,926 | INFO | train_grpo_train | metrics_logged mode=train step=1478 2026-04-12 21:38:19,465 | INFO | train_grpo_train | metrics_logged mode=train step=1479 2026-04-12 21:38:28,369 | INFO | train_grpo_train | metrics_logged mode=train step=1480 2026-04-12 21:38:36,446 | INFO | train_grpo_train | metrics_logged mode=train step=1481 2026-04-12 21:38:49,771 | INFO | train_grpo_train | metrics_logged mode=train step=1482 2026-04-12 21:38:58,012 | INFO | train_grpo_train | metrics_logged mode=train step=1483 2026-04-12 21:39:08,442 | INFO | train_grpo_train | metrics_logged mode=train step=1484 2026-04-12 21:39:21,899 | INFO | train_grpo_train | metrics_logged mode=train step=1485 2026-04-12 21:39:35,166 | INFO | train_grpo_train | metrics_logged mode=train step=1486 2026-04-12 21:39:49,126 | INFO | train_grpo_train | metrics_logged mode=train step=1487 2026-04-12 21:39:58,256 | INFO | train_grpo_train | metrics_logged mode=train step=1488 2026-04-12 21:40:13,905 | INFO | train_grpo_train | metrics_logged mode=train step=1489 2026-04-12 21:40:28,046 | INFO | train_grpo_train | metrics_logged mode=train step=1490 2026-04-12 21:40:37,904 | INFO | train_grpo_train | metrics_logged mode=train step=1491 2026-04-12 21:40:47,518 | INFO | train_grpo_train | metrics_logged mode=train step=1492 2026-04-12 21:41:01,204 | INFO | train_grpo_train | metrics_logged mode=train step=1493 2026-04-12 21:41:14,726 | INFO | train_grpo_train | metrics_logged mode=train step=1494 2026-04-12 21:41:24,699 | INFO | train_grpo_train | metrics_logged mode=train step=1495 2026-04-12 21:41:34,197 | INFO | train_grpo_train | metrics_logged mode=train step=1496 2026-04-12 21:41:47,614 | INFO | train_grpo_train | metrics_logged mode=train step=1497 2026-04-12 21:41:56,597 | INFO | train_grpo_train | metrics_logged mode=train step=1498 2026-04-12 21:42:10,127 | INFO | train_grpo_train | metrics_logged mode=train step=1499 2026-04-12 21:42:19,327 | INFO | train_grpo_train | metrics_logged mode=train step=1500 2026-04-12 21:44:28,341 | INFO | train_grpo_train | metrics_logged mode=eval step=1500 2026-04-12 21:44:46,232 | INFO | train_grpo_train | metrics_logged mode=train step=1501 2026-04-12 21:44:54,503 | INFO | train_grpo_train | metrics_logged mode=train step=1502 2026-04-12 21:45:11,172 | INFO | train_grpo_train | metrics_logged mode=train step=1503 2026-04-12 21:45:20,268 | INFO | train_grpo_train | metrics_logged mode=train step=1504 2026-04-12 21:45:29,449 | INFO | train_grpo_train | metrics_logged mode=train step=1505 2026-04-12 21:45:38,553 | INFO | train_grpo_train | metrics_logged mode=train step=1506 2026-04-12 21:45:46,993 | INFO | train_grpo_train | metrics_logged mode=train step=1507 2026-04-12 21:46:01,879 | INFO | train_grpo_train | metrics_logged mode=train step=1508 2026-04-12 21:46:10,707 | INFO | train_grpo_train | metrics_logged mode=train step=1509 2026-04-12 21:46:23,237 | INFO | train_grpo_train | metrics_logged mode=train step=1510 2026-04-12 21:46:35,254 | INFO | train_grpo_train | metrics_logged mode=train step=1511 2026-04-12 21:46:47,030 | INFO | train_grpo_train | metrics_logged mode=train step=1512 2026-04-12 21:46:54,930 | INFO | train_grpo_train | metrics_logged mode=train step=1513 2026-04-12 21:47:06,584 | INFO | train_grpo_train | metrics_logged mode=train step=1514 2026-04-12 21:47:12,924 | INFO | train_grpo_train | metrics_logged mode=train step=1515 2026-04-12 21:47:21,136 | INFO | train_grpo_train | metrics_logged mode=train step=1516 2026-04-12 21:47:33,525 | INFO | train_grpo_train | metrics_logged mode=train step=1517 2026-04-12 21:47:45,357 | INFO | train_grpo_train | metrics_logged mode=train step=1518 2026-04-12 21:47:56,754 | INFO | train_grpo_train | metrics_logged mode=train step=1519 2026-04-12 21:48:03,145 | INFO | train_grpo_train | metrics_logged mode=train step=1520 2026-04-12 21:48:09,713 | INFO | train_grpo_train | metrics_logged mode=train step=1521 2026-04-12 21:48:16,645 | INFO | train_grpo_train | metrics_logged mode=train step=1522 2026-04-12 21:48:28,298 | INFO | train_grpo_train | metrics_logged mode=train step=1523 2026-04-12 21:48:35,014 | INFO | train_grpo_train | metrics_logged mode=train step=1524 2026-04-12 21:48:41,235 | INFO | train_grpo_train | metrics_logged mode=train step=1525 2026-04-12 21:48:52,959 | INFO | train_grpo_train | metrics_logged mode=train step=1526 2026-04-12 21:49:04,428 | INFO | train_grpo_train | metrics_logged mode=train step=1527 2026-04-12 21:49:15,811 | INFO | train_grpo_train | metrics_logged mode=train step=1528 2026-04-12 21:49:21,993 | INFO | train_grpo_train | metrics_logged mode=train step=1529 2026-04-12 21:49:27,867 | INFO | train_grpo_train | metrics_logged mode=train step=1530 2026-04-12 21:49:34,094 | INFO | train_grpo_train | metrics_logged mode=train step=1531 2026-04-12 21:49:46,010 | INFO | train_grpo_train | metrics_logged mode=train step=1532 2026-04-12 21:49:57,450 | INFO | train_grpo_train | metrics_logged mode=train step=1533 2026-04-12 21:50:08,872 | INFO | train_grpo_train | metrics_logged mode=train step=1534 2026-04-12 21:50:21,024 | INFO | train_grpo_train | metrics_logged mode=train step=1535 2026-04-12 21:50:27,980 | INFO | train_grpo_train | metrics_logged mode=train step=1536 2026-04-12 21:50:40,319 | INFO | train_grpo_train | metrics_logged mode=train step=1537 2026-04-12 21:50:52,507 | INFO | train_grpo_train | metrics_logged mode=train step=1538 2026-04-12 21:50:59,634 | INFO | train_grpo_train | metrics_logged mode=train step=1539 2026-04-12 21:51:12,017 | INFO | train_grpo_train | metrics_logged mode=train step=1540 2026-04-12 21:51:22,392 | INFO | train_grpo_train | metrics_logged mode=train step=1541 2026-04-12 21:51:34,169 | INFO | train_grpo_train | metrics_logged mode=train step=1542 2026-04-12 21:51:40,507 | INFO | train_grpo_train | metrics_logged mode=train step=1543 2026-04-12 21:51:53,381 | INFO | train_grpo_train | metrics_logged mode=train step=1544 2026-04-12 21:52:04,437 | INFO | train_grpo_train | metrics_logged mode=train step=1545 2026-04-12 21:52:16,251 | INFO | train_grpo_train | metrics_logged mode=train step=1546 2026-04-12 21:52:22,622 | INFO | train_grpo_train | metrics_logged mode=train step=1547 2026-04-12 21:52:28,954 | INFO | train_grpo_train | metrics_logged mode=train step=1548 2026-04-12 21:52:35,178 | INFO | train_grpo_train | metrics_logged mode=train step=1549 2026-04-12 21:52:42,741 | INFO | train_grpo_train | metrics_logged mode=train step=1550 2026-04-12 21:54:29,472 | INFO | train_grpo_train | metrics_logged mode=eval step=1550 2026-04-12 21:54:43,931 | INFO | train_grpo_train | metrics_logged mode=train step=1551