2026-04-13 07:18:50,586 | INFO | train_grpo_train | mode=train 2026-04-13 07:20:57,395 | INFO | train_grpo_train | dataset_id=Shaer-AI/ashaar-enhanced-desc-baseform-final-sft-lte20-min500-splits-grpo-meter-count-v1 train_size=9955 eval_size=80 2026-04-13 07:20:57,395 | INFO | train_grpo_train | source_dataset_id=Shaer-AI/ashaar-with-enhanced-descriptions-baseform-final-sft-lte20-min500-splits test_size=80 hard_diagnostic_size=3126 2026-04-13 07:20:57,395 | INFO | train_grpo_train | active_rewards=['meter', 'count_adherence', 'hard_gate', 'judge_quality', 'repeat_soft', 'total_composite'] 2026-04-13 07:20:57,395 | INFO | train_grpo_train | reward_weights={'meter': 0.0, 'count_adherence': 0.0, 'hard_gate': 0.0, 'judge_quality': 0.0, 'repeat_soft': 0.0, 'total_composite': 1.0} 2026-04-13 07:20:57,395 | INFO | train_grpo_train | output_repo=Shaer-AI/Shaer-adapters-grpo-short1k-no-trio-v3 2026-04-13 07:20:57,396 | INFO | train_grpo_train | train_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_easyfirst_short_drop_trio/cap_1000/selected_manifest.csv 2026-04-13 07:20:57,396 | INFO | train_grpo_train | hard_diagnostic_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_easyfirst_short_drop_trio/hard_diagnostic_cap_256/selected_manifest.csv 2026-04-13 07:20:57,396 | INFO | train_grpo_train | trainable_params=159907840 total_params=7160467456 trainable_ratio=0.022332 2026-04-13 07:20:57,396 | INFO | train_grpo_train | resume_decision={"timestamp_utc": "2026-04-13T07:20:37Z", "resume_mode": "fresh", "requested_spec": "", "result": "fresh", "reason": "explicit_fresh", "local_resume_path": null, "remote_repo": null, "remote_prefix": null, "compatibility": "unchecked", "config_fingerprint": "002103f46be89ed6311e30cbbf1952cf127698400c47c48f018bf0a5f0eb1c65"} 2026-04-13 07:20:57,396 | INFO | train_grpo_train | starting trainer.train() 2026-04-13 07:21:02,713 | INFO | train_grpo_train | metrics_logged mode=train step=1 2026-04-13 07:21:10,827 | INFO | train_grpo_train | metrics_logged mode=train step=2 2026-04-13 07:21:18,146 | INFO | train_grpo_train | metrics_logged mode=train step=3 2026-04-13 07:21:25,975 | INFO | train_grpo_train | metrics_logged mode=train step=4 2026-04-13 07:21:33,716 | INFO | train_grpo_train | metrics_logged mode=train step=5 2026-04-13 07:21:41,483 | INFO | train_grpo_train | metrics_logged mode=train step=6 2026-04-13 07:21:48,954 | INFO | train_grpo_train | metrics_logged mode=train step=7 2026-04-13 07:21:55,540 | INFO | train_grpo_train | metrics_logged mode=train step=8 2026-04-13 07:22:03,772 | INFO | train_grpo_train | metrics_logged mode=train step=9 2026-04-13 07:22:10,367 | INFO | train_grpo_train | metrics_logged mode=train step=10 2026-04-13 07:22:16,876 | INFO | train_grpo_train | metrics_logged mode=train step=11 2026-04-13 07:22:23,318 | INFO | train_grpo_train | metrics_logged mode=train step=12 2026-04-13 07:22:29,654 | INFO | train_grpo_train | metrics_logged mode=train step=13 2026-04-13 07:22:38,259 | INFO | train_grpo_train | metrics_logged mode=train step=14 2026-04-13 07:22:45,540 | INFO | train_grpo_train | metrics_logged mode=train step=15 2026-04-13 07:22:52,386 | INFO | train_grpo_train | metrics_logged mode=train step=16 2026-04-13 07:22:59,755 | INFO | train_grpo_train | metrics_logged mode=train step=17 2026-04-13 07:23:05,954 | INFO | train_grpo_train | metrics_logged mode=train step=18 2026-04-13 07:23:13,047 | INFO | train_grpo_train | metrics_logged mode=train step=19 2026-04-13 07:23:20,309 | INFO | train_grpo_train | metrics_logged mode=train step=20 2026-04-13 07:23:27,032 | INFO | train_grpo_train | metrics_logged mode=train step=21 2026-04-13 07:23:34,121 | INFO | train_grpo_train | metrics_logged mode=train step=22 2026-04-13 07:23:41,963 | INFO | train_grpo_train | metrics_logged mode=train step=23 2026-04-13 07:23:49,952 | INFO | train_grpo_train | metrics_logged mode=train step=24 2026-04-13 07:23:58,346 | INFO | train_grpo_train | metrics_logged mode=train step=25 2026-04-13 07:24:04,393 | INFO | train_grpo_train | metrics_logged mode=train step=26 2026-04-13 07:24:12,766 | INFO | train_grpo_train | metrics_logged mode=train step=27 2026-04-13 07:24:19,830 | INFO | train_grpo_train | metrics_logged mode=train step=28 2026-04-13 07:24:28,815 | INFO | train_grpo_train | metrics_logged mode=train step=29 2026-04-13 07:24:36,131 | INFO | train_grpo_train | metrics_logged mode=train step=30 2026-04-13 07:24:43,527 | INFO | train_grpo_train | metrics_logged mode=train step=31 2026-04-13 07:24:50,677 | INFO | train_grpo_train | metrics_logged mode=train step=32 2026-04-13 07:24:58,214 | INFO | train_grpo_train | metrics_logged mode=train step=33 2026-04-13 07:25:05,247 | INFO | train_grpo_train | metrics_logged mode=train step=34 2026-04-13 07:25:11,604 | INFO | train_grpo_train | metrics_logged mode=train step=35 2026-04-13 07:25:18,110 | INFO | train_grpo_train | metrics_logged mode=train step=36 2026-04-13 07:25:24,676 | INFO | train_grpo_train | metrics_logged mode=train step=37 2026-04-13 07:25:31,864 | INFO | train_grpo_train | metrics_logged mode=train step=38 2026-04-13 07:25:39,218 | INFO | train_grpo_train | metrics_logged mode=train step=39 2026-04-13 07:25:46,335 | INFO | train_grpo_train | metrics_logged mode=train step=40 2026-04-13 07:25:54,335 | INFO | train_grpo_train | metrics_logged mode=train step=41 2026-04-13 07:26:01,850 | INFO | train_grpo_train | metrics_logged mode=train step=42 2026-04-13 07:26:08,904 | INFO | train_grpo_train | metrics_logged mode=train step=43 2026-04-13 07:26:16,206 | INFO | train_grpo_train | metrics_logged mode=train step=44 2026-04-13 07:26:23,313 | INFO | train_grpo_train | metrics_logged mode=train step=45 2026-04-13 07:26:31,050 | INFO | train_grpo_train | metrics_logged mode=train step=46 2026-04-13 07:26:37,775 | INFO | train_grpo_train | metrics_logged mode=train step=47 2026-04-13 07:26:44,594 | INFO | train_grpo_train | metrics_logged mode=train step=48 2026-04-13 07:26:52,860 | INFO | train_grpo_train | metrics_logged mode=train step=49 2026-04-13 07:27:01,138 | INFO | train_grpo_train | metrics_logged mode=train step=50 2026-04-13 07:28:10,359 | INFO | train_grpo_train | metrics_logged mode=eval step=50 2026-04-13 07:28:20,805 | INFO | train_grpo_train | metrics_logged mode=train step=51 2026-04-13 07:28:33,801 | INFO | train_grpo_train | metrics_logged mode=train step=52 2026-04-13 07:28:40,826 | INFO | train_grpo_train | metrics_logged mode=train step=53 2026-04-13 07:28:49,471 | INFO | train_grpo_train | metrics_logged mode=train step=54 2026-04-13 07:28:55,789 | INFO | train_grpo_train | metrics_logged mode=train step=55 2026-04-13 07:29:02,081 | INFO | train_grpo_train | metrics_logged mode=train step=56 2026-04-13 07:29:09,866 | INFO | train_grpo_train | metrics_logged mode=train step=57 2026-04-13 07:29:17,622 | INFO | train_grpo_train | metrics_logged mode=train step=58 2026-04-13 07:29:26,917 | INFO | train_grpo_train | metrics_logged mode=train step=59 2026-04-13 07:29:33,616 | INFO | train_grpo_train | metrics_logged mode=train step=60 2026-04-13 07:29:40,661 | INFO | train_grpo_train | metrics_logged mode=train step=61 2026-04-13 07:29:52,587 | INFO | train_grpo_train | metrics_logged mode=train step=62 2026-04-13 07:30:00,236 | INFO | train_grpo_train | metrics_logged mode=train step=63 2026-04-13 07:30:08,379 | INFO | train_grpo_train | metrics_logged mode=train step=64 2026-04-13 07:30:15,008 | INFO | train_grpo_train | metrics_logged mode=train step=65 2026-04-13 07:30:26,625 | INFO | train_grpo_train | metrics_logged mode=train step=66 2026-04-13 07:30:34,025 | INFO | train_grpo_train | metrics_logged mode=train step=67 2026-04-13 07:30:41,131 | INFO | train_grpo_train | metrics_logged mode=train step=68 2026-04-13 07:30:48,280 | INFO | train_grpo_train | metrics_logged mode=train step=69 2026-04-13 07:30:56,061 | INFO | train_grpo_train | metrics_logged mode=train step=70 2026-04-13 07:31:02,060 | INFO | train_grpo_train | metrics_logged mode=train step=71 2026-04-13 07:31:09,250 | INFO | train_grpo_train | metrics_logged mode=train step=72 2026-04-13 07:31:16,138 | INFO | train_grpo_train | metrics_logged mode=train step=73 2026-04-13 07:31:23,724 | INFO | train_grpo_train | metrics_logged mode=train step=74 2026-04-13 07:31:32,522 | INFO | train_grpo_train | metrics_logged mode=train step=75 2026-04-13 07:31:39,229 | INFO | train_grpo_train | metrics_logged mode=train step=76 2026-04-13 07:31:46,302 | INFO | train_grpo_train | metrics_logged mode=train step=77 2026-04-13 07:31:53,792 | INFO | train_grpo_train | metrics_logged mode=train step=78 2026-04-13 07:32:06,295 | INFO | train_grpo_train | metrics_logged mode=train step=79 2026-04-13 07:32:17,345 | INFO | train_grpo_train | metrics_logged mode=train step=80 2026-04-13 07:32:26,966 | INFO | train_grpo_train | metrics_logged mode=train step=81 2026-04-13 07:32:33,903 | INFO | train_grpo_train | metrics_logged mode=train step=82 2026-04-13 07:32:40,617 | INFO | train_grpo_train | metrics_logged mode=train step=83 2026-04-13 07:32:48,034 | INFO | train_grpo_train | metrics_logged mode=train step=84 2026-04-13 07:32:55,417 | INFO | train_grpo_train | metrics_logged mode=train step=85 2026-04-13 07:33:03,642 | INFO | train_grpo_train | metrics_logged mode=train step=86 2026-04-13 07:33:10,260 | INFO | train_grpo_train | metrics_logged mode=train step=87 2026-04-13 07:33:17,013 | INFO | train_grpo_train | metrics_logged mode=train step=88 2026-04-13 07:33:24,011 | INFO | train_grpo_train | metrics_logged mode=train step=89 2026-04-13 07:33:30,143 | INFO | train_grpo_train | metrics_logged mode=train step=90 2026-04-13 07:33:38,619 | INFO | train_grpo_train | metrics_logged mode=train step=91 2026-04-13 07:33:45,779 | INFO | train_grpo_train | metrics_logged mode=train step=92 2026-04-13 07:33:52,978 | INFO | train_grpo_train | metrics_logged mode=train step=93 2026-04-13 07:33:59,792 | INFO | train_grpo_train | metrics_logged mode=train step=94 2026-04-13 07:34:07,237 | INFO | train_grpo_train | metrics_logged mode=train step=95 2026-04-13 07:34:14,616 | INFO | train_grpo_train | metrics_logged mode=train step=96 2026-04-13 07:34:22,091 | INFO | train_grpo_train | metrics_logged mode=train step=97 2026-04-13 07:34:30,179 | INFO | train_grpo_train | metrics_logged mode=train step=98 2026-04-13 07:34:36,679 | INFO | train_grpo_train | metrics_logged mode=train step=99 2026-04-13 07:34:44,044 | INFO | train_grpo_train | metrics_logged mode=train step=100 2026-04-13 07:35:34,748 | INFO | train_grpo_train | metrics_logged mode=eval step=100 2026-04-13 07:35:45,845 | INFO | train_grpo_train | metrics_logged mode=train step=101 2026-04-13 07:35:53,832 | INFO | train_grpo_train | metrics_logged mode=train step=102 2026-04-13 07:36:01,337 | INFO | train_grpo_train | metrics_logged mode=train step=103 2026-04-13 07:36:08,645 | INFO | train_grpo_train | metrics_logged mode=train step=104 2026-04-13 07:36:15,919 | INFO | train_grpo_train | metrics_logged mode=train step=105 2026-04-13 07:36:23,181 | INFO | train_grpo_train | metrics_logged mode=train step=106 2026-04-13 07:36:30,996 | INFO | train_grpo_train | metrics_logged mode=train step=107 2026-04-13 07:36:38,512 | INFO | train_grpo_train | metrics_logged mode=train step=108 2026-04-13 07:36:45,141 | INFO | train_grpo_train | metrics_logged mode=train step=109 2026-04-13 07:36:51,868 | INFO | train_grpo_train | metrics_logged mode=train step=110 2026-04-13 07:36:59,357 | INFO | train_grpo_train | metrics_logged mode=train step=111 2026-04-13 07:37:06,378 | INFO | train_grpo_train | metrics_logged mode=train step=112 2026-04-13 07:37:13,992 | INFO | train_grpo_train | metrics_logged mode=train step=113 2026-04-13 07:37:20,686 | INFO | train_grpo_train | metrics_logged mode=train step=114 2026-04-13 07:37:28,723 | INFO | train_grpo_train | metrics_logged mode=train step=115 2026-04-13 07:37:35,791 | INFO | train_grpo_train | metrics_logged mode=train step=116 2026-04-13 07:37:42,560 | INFO | train_grpo_train | metrics_logged mode=train step=117 2026-04-13 07:37:50,714 | INFO | train_grpo_train | metrics_logged mode=train step=118 2026-04-13 07:37:58,052 | INFO | train_grpo_train | metrics_logged mode=train step=119 2026-04-13 07:38:05,742 | INFO | train_grpo_train | metrics_logged mode=train step=120 2026-04-13 07:38:13,669 | INFO | train_grpo_train | metrics_logged mode=train step=121 2026-04-13 07:38:21,732 | INFO | train_grpo_train | metrics_logged mode=train step=122 2026-04-13 07:38:28,325 | INFO | train_grpo_train | metrics_logged mode=train step=123 2026-04-13 07:38:34,980 | INFO | train_grpo_train | metrics_logged mode=train step=124 2026-04-13 07:38:42,152 | INFO | train_grpo_train | metrics_logged mode=train step=125 2026-04-13 07:38:51,685 | INFO | train_grpo_train | metrics_logged mode=train step=126 2026-04-13 07:38:58,887 | INFO | train_grpo_train | metrics_logged mode=train step=127 2026-04-13 07:39:06,515 | INFO | train_grpo_train | metrics_logged mode=train step=128 2026-04-13 07:39:14,232 | INFO | train_grpo_train | metrics_logged mode=train step=129 2026-04-13 07:39:23,696 | INFO | train_grpo_train | metrics_logged mode=train step=130 2026-04-13 07:39:33,018 | INFO | train_grpo_train | metrics_logged mode=train step=131 2026-04-13 07:39:41,207 | INFO | train_grpo_train | metrics_logged mode=train step=132 2026-04-13 07:39:49,432 | INFO | train_grpo_train | metrics_logged mode=train step=133 2026-04-13 07:39:57,936 | INFO | train_grpo_train | metrics_logged mode=train step=134 2026-04-13 07:40:06,165 | INFO | train_grpo_train | metrics_logged mode=train step=135 2026-04-13 07:40:13,200 | INFO | train_grpo_train | metrics_logged mode=train step=136 2026-04-13 07:40:19,613 | INFO | train_grpo_train | metrics_logged mode=train step=137 2026-04-13 07:40:26,894 | INFO | train_grpo_train | metrics_logged mode=train step=138 2026-04-13 07:40:33,596 | INFO | train_grpo_train | metrics_logged mode=train step=139 2026-04-13 07:40:41,040 | INFO | train_grpo_train | metrics_logged mode=train step=140 2026-04-13 07:40:49,726 | INFO | train_grpo_train | metrics_logged mode=train step=141 2026-04-13 07:40:56,297 | INFO | train_grpo_train | metrics_logged mode=train step=142 2026-04-13 07:41:04,419 | INFO | train_grpo_train | metrics_logged mode=train step=143 2026-04-13 07:41:11,587 | INFO | train_grpo_train | metrics_logged mode=train step=144 2026-04-13 07:41:18,239 | INFO | train_grpo_train | metrics_logged mode=train step=145 2026-04-13 07:41:25,434 | INFO | train_grpo_train | metrics_logged mode=train step=146 2026-04-13 07:41:31,964 | INFO | train_grpo_train | metrics_logged mode=train step=147 2026-04-13 07:41:40,720 | INFO | train_grpo_train | metrics_logged mode=train step=148 2026-04-13 07:41:49,400 | INFO | train_grpo_train | metrics_logged mode=train step=149 2026-04-13 07:41:57,215 | INFO | train_grpo_train | metrics_logged mode=train step=150 2026-04-13 07:42:46,815 | INFO | train_grpo_train | metrics_logged mode=eval step=150 2026-04-13 07:42:55,587 | INFO | train_grpo_train | metrics_logged mode=train step=151 2026-04-13 07:43:04,124 | INFO | train_grpo_train | metrics_logged mode=train step=152 2026-04-13 07:43:11,225 | INFO | train_grpo_train | metrics_logged mode=train step=153 2026-04-13 07:43:18,153 | INFO | train_grpo_train | metrics_logged mode=train step=154 2026-04-13 07:43:24,803 | INFO | train_grpo_train | metrics_logged mode=train step=155 2026-04-13 07:43:31,947 | INFO | train_grpo_train | metrics_logged mode=train step=156 2026-04-13 07:43:38,618 | INFO | train_grpo_train | metrics_logged mode=train step=157 2026-04-13 07:43:46,383 | INFO | train_grpo_train | metrics_logged mode=train step=158 2026-04-13 07:43:53,303 | INFO | train_grpo_train | metrics_logged mode=train step=159 2026-04-13 07:43:59,777 | INFO | train_grpo_train | metrics_logged mode=train step=160 2026-04-13 07:44:06,901 | INFO | train_grpo_train | metrics_logged mode=train step=161 2026-04-13 07:44:13,472 | INFO | train_grpo_train | metrics_logged mode=train step=162 2026-04-13 07:44:20,322 | INFO | train_grpo_train | metrics_logged mode=train step=163 2026-04-13 07:44:27,701 | INFO | train_grpo_train | metrics_logged mode=train step=164 2026-04-13 07:44:34,913 | INFO | train_grpo_train | metrics_logged mode=train step=165 2026-04-13 07:44:42,251 | INFO | train_grpo_train | metrics_logged mode=train step=166 2026-04-13 07:44:49,271 | INFO | train_grpo_train | metrics_logged mode=train step=167 2026-04-13 07:44:56,499 | INFO | train_grpo_train | metrics_logged mode=train step=168 2026-04-13 07:45:02,916 | INFO | train_grpo_train | metrics_logged mode=train step=169 2026-04-13 07:45:09,725 | INFO | train_grpo_train | metrics_logged mode=train step=170 2026-04-13 07:45:16,814 | INFO | train_grpo_train | metrics_logged mode=train step=171 2026-04-13 07:45:23,301 | INFO | train_grpo_train | metrics_logged mode=train step=172 2026-04-13 07:45:30,206 | INFO | train_grpo_train | metrics_logged mode=train step=173 2026-04-13 07:45:37,165 | INFO | train_grpo_train | metrics_logged mode=train step=174 2026-04-13 07:45:45,005 | INFO | train_grpo_train | metrics_logged mode=train step=175 2026-04-13 07:45:51,568 | INFO | train_grpo_train | metrics_logged mode=train step=176 2026-04-13 07:45:59,489 | INFO | train_grpo_train | metrics_logged mode=train step=177 2026-04-13 07:46:07,802 | INFO | train_grpo_train | metrics_logged mode=train step=178 2026-04-13 07:46:14,914 | INFO | train_grpo_train | metrics_logged mode=train step=179 2026-04-13 07:46:22,641 | INFO | train_grpo_train | metrics_logged mode=train step=180 2026-04-13 07:46:30,242 | INFO | train_grpo_train | metrics_logged mode=train step=181 2026-04-13 07:46:36,705 | INFO | train_grpo_train | metrics_logged mode=train step=182 2026-04-13 07:46:42,972 | INFO | train_grpo_train | metrics_logged mode=train step=183 2026-04-13 07:46:49,616 | INFO | train_grpo_train | metrics_logged mode=train step=184 2026-04-13 07:46:56,116 | INFO | train_grpo_train | metrics_logged mode=train step=185 2026-04-13 07:47:02,976 | INFO | train_grpo_train | metrics_logged mode=train step=186 2026-04-13 07:47:11,091 | INFO | train_grpo_train | metrics_logged mode=train step=187 2026-04-13 07:47:17,835 | INFO | train_grpo_train | metrics_logged mode=train step=188 2026-04-13 07:47:24,937 | INFO | train_grpo_train | metrics_logged mode=train step=189 2026-04-13 07:47:32,541 | INFO | train_grpo_train | metrics_logged mode=train step=190 2026-04-13 07:47:42,078 | INFO | train_grpo_train | metrics_logged mode=train step=191 2026-04-13 07:47:49,555 | INFO | train_grpo_train | metrics_logged mode=train step=192 2026-04-13 07:47:57,080 | INFO | train_grpo_train | metrics_logged mode=train step=193 2026-04-13 07:48:05,006 | INFO | train_grpo_train | metrics_logged mode=train step=194 2026-04-13 07:48:12,397 | INFO | train_grpo_train | metrics_logged mode=train step=195 2026-04-13 07:48:18,703 | INFO | train_grpo_train | metrics_logged mode=train step=196 2026-04-13 07:48:24,841 | INFO | train_grpo_train | metrics_logged mode=train step=197 2026-04-13 07:48:31,934 | INFO | train_grpo_train | metrics_logged mode=train step=198 2026-04-13 07:48:38,586 | INFO | train_grpo_train | metrics_logged mode=train step=199 2026-04-13 07:48:46,671 | INFO | train_grpo_train | metrics_logged mode=train step=200 2026-04-13 07:49:35,968 | INFO | train_grpo_train | metrics_logged mode=eval step=200 2026-04-13 07:49:46,059 | INFO | train_grpo_train | metrics_logged mode=train step=201 2026-04-13 07:49:54,103 | INFO | train_grpo_train | metrics_logged mode=train step=202 2026-04-13 07:50:03,013 | INFO | train_grpo_train | metrics_logged mode=train step=203 2026-04-13 07:50:10,046 | INFO | train_grpo_train | metrics_logged mode=train step=204 2026-04-13 07:50:17,545 | INFO | train_grpo_train | metrics_logged mode=train step=205 2026-04-13 07:50:24,500 | INFO | train_grpo_train | metrics_logged mode=train step=206 2026-04-13 07:50:32,121 | INFO | train_grpo_train | metrics_logged mode=train step=207 2026-04-13 07:50:38,366 | INFO | train_grpo_train | metrics_logged mode=train step=208 2026-04-13 07:50:45,222 | INFO | train_grpo_train | metrics_logged mode=train step=209 2026-04-13 07:50:52,653 | INFO | train_grpo_train | metrics_logged mode=train step=210 2026-04-13 07:50:58,797 | INFO | train_grpo_train | metrics_logged mode=train step=211 2026-04-13 07:51:06,636 | INFO | train_grpo_train | metrics_logged mode=train step=212 2026-04-13 07:51:14,747 | INFO | train_grpo_train | metrics_logged mode=train step=213 2026-04-13 07:51:21,703 | INFO | train_grpo_train | metrics_logged mode=train step=214 2026-04-13 07:51:28,885 | INFO | train_grpo_train | metrics_logged mode=train step=215 2026-04-13 07:51:36,486 | INFO | train_grpo_train | metrics_logged mode=train step=216 2026-04-13 07:51:44,138 | INFO | train_grpo_train | metrics_logged mode=train step=217 2026-04-13 07:51:52,104 | INFO | train_grpo_train | metrics_logged mode=train step=218 2026-04-13 07:51:59,189 | INFO | train_grpo_train | metrics_logged mode=train step=219 2026-04-13 07:52:06,295 | INFO | train_grpo_train | metrics_logged mode=train step=220 2026-04-13 07:52:12,640 | INFO | train_grpo_train | metrics_logged mode=train step=221 2026-04-13 07:52:19,762 | INFO | train_grpo_train | metrics_logged mode=train step=222 2026-04-13 07:52:27,813 | INFO | train_grpo_train | metrics_logged mode=train step=223 2026-04-13 07:52:35,133 | INFO | train_grpo_train | metrics_logged mode=train step=224 2026-04-13 07:52:42,786 | INFO | train_grpo_train | metrics_logged mode=train step=225 2026-04-13 07:52:49,823 | INFO | train_grpo_train | metrics_logged mode=train step=226 2026-04-13 07:52:57,430 | INFO | train_grpo_train | metrics_logged mode=train step=227 2026-04-13 07:53:05,026 | INFO | train_grpo_train | metrics_logged mode=train step=228 2026-04-13 07:53:11,486 | INFO | train_grpo_train | metrics_logged mode=train step=229 2026-04-13 07:53:18,068 | INFO | train_grpo_train | metrics_logged mode=train step=230 2026-04-13 07:53:24,817 | INFO | train_grpo_train | metrics_logged mode=train step=231 2026-04-13 07:53:32,064 | INFO | train_grpo_train | metrics_logged mode=train step=232 2026-04-13 07:53:41,385 | INFO | train_grpo_train | metrics_logged mode=train step=233 2026-04-13 07:53:48,191 | INFO | train_grpo_train | metrics_logged mode=train step=234 2026-04-13 07:53:57,842 | INFO | train_grpo_train | metrics_logged mode=train step=235 2026-04-13 07:54:06,342 | INFO | train_grpo_train | metrics_logged mode=train step=236 2026-04-13 07:54:18,463 | INFO | train_grpo_train | metrics_logged mode=train step=237 2026-04-13 07:54:26,762 | INFO | train_grpo_train | metrics_logged mode=train step=238 2026-04-13 07:54:33,740 | INFO | train_grpo_train | metrics_logged mode=train step=239 2026-04-13 07:54:41,079 | INFO | train_grpo_train | metrics_logged mode=train step=240 2026-04-13 07:54:54,957 | INFO | train_grpo_train | metrics_logged mode=train step=241 2026-04-13 07:55:01,288 | INFO | train_grpo_train | metrics_logged mode=train step=242 2026-04-13 07:55:08,768 | INFO | train_grpo_train | metrics_logged mode=train step=243 2026-04-13 07:55:16,376 | INFO | train_grpo_train | metrics_logged mode=train step=244 2026-04-13 07:55:24,283 | INFO | train_grpo_train | metrics_logged mode=train step=245 2026-04-13 07:55:34,800 | INFO | train_grpo_train | metrics_logged mode=train step=246 2026-04-13 07:55:43,592 | INFO | train_grpo_train | metrics_logged mode=train step=247 2026-04-13 07:55:55,543 | INFO | train_grpo_train | metrics_logged mode=train step=248 2026-04-13 07:56:01,761 | INFO | train_grpo_train | metrics_logged mode=train step=249 2026-04-13 07:56:28,043 | INFO | train_grpo_train | metrics_logged mode=train step=250 2026-04-13 07:57:42,149 | INFO | train_grpo_train | metrics_logged mode=eval step=250 2026-04-13 07:57:52,908 | INFO | train_grpo_train | metrics_logged mode=train step=251 2026-04-13 07:58:01,025 | INFO | train_grpo_train | metrics_logged mode=train step=252 2026-04-13 07:58:08,108 | INFO | train_grpo_train | metrics_logged mode=train step=253 2026-04-13 07:58:28,784 | INFO | train_grpo_train | metrics_logged mode=train step=254 2026-04-13 07:58:36,404 | INFO | train_grpo_train | metrics_logged mode=train step=255 2026-04-13 07:58:43,151 | INFO | train_grpo_train | metrics_logged mode=train step=256 2026-04-13 07:58:53,932 | INFO | train_grpo_train | metrics_logged mode=train step=257 2026-04-13 07:59:01,248 | INFO | train_grpo_train | metrics_logged mode=train step=258 2026-04-13 07:59:13,106 | INFO | train_grpo_train | metrics_logged mode=train step=259 2026-04-13 07:59:20,565 | INFO | train_grpo_train | metrics_logged mode=train step=260 2026-04-13 07:59:28,073 | INFO | train_grpo_train | metrics_logged mode=train step=261 2026-04-13 07:59:34,643 | INFO | train_grpo_train | metrics_logged mode=train step=262 2026-04-13 07:59:41,856 | INFO | train_grpo_train | metrics_logged mode=train step=263 2026-04-13 07:59:48,996 | INFO | train_grpo_train | metrics_logged mode=train step=264 2026-04-13 07:59:56,598 | INFO | train_grpo_train | metrics_logged mode=train step=265 2026-04-13 08:00:03,727 | INFO | train_grpo_train | metrics_logged mode=train step=266 2026-04-13 08:00:11,451 | INFO | train_grpo_train | metrics_logged mode=train step=267 2026-04-13 08:00:19,067 | INFO | train_grpo_train | metrics_logged mode=train step=268 2026-04-13 08:00:25,731 | INFO | train_grpo_train | metrics_logged mode=train step=269 2026-04-13 08:00:32,718 | INFO | train_grpo_train | metrics_logged mode=train step=270 2026-04-13 08:00:39,281 | INFO | train_grpo_train | metrics_logged mode=train step=271 2026-04-13 08:00:46,139 | INFO | train_grpo_train | metrics_logged mode=train step=272 2026-04-13 08:00:53,350 | INFO | train_grpo_train | metrics_logged mode=train step=273 2026-04-13 08:00:59,973 | INFO | train_grpo_train | metrics_logged mode=train step=274 2026-04-13 08:01:08,673 | INFO | train_grpo_train | metrics_logged mode=train step=275 2026-04-13 08:01:15,807 | INFO | train_grpo_train | metrics_logged mode=train step=276 2026-04-13 08:01:22,927 | INFO | train_grpo_train | metrics_logged mode=train step=277 2026-04-13 08:01:29,489 | INFO | train_grpo_train | metrics_logged mode=train step=278 2026-04-13 08:01:37,087 | INFO | train_grpo_train | metrics_logged mode=train step=279 2026-04-13 08:01:45,881 | INFO | train_grpo_train | metrics_logged mode=train step=280 2026-04-13 08:01:52,658 | INFO | train_grpo_train | metrics_logged mode=train step=281 2026-04-13 08:01:59,738 | INFO | train_grpo_train | metrics_logged mode=train step=282 2026-04-13 08:02:07,916 | INFO | train_grpo_train | metrics_logged mode=train step=283 2026-04-13 08:02:15,862 | INFO | train_grpo_train | metrics_logged mode=train step=284 2026-04-13 08:02:22,653 | INFO | train_grpo_train | metrics_logged mode=train step=285 2026-04-13 08:02:34,775 | INFO | train_grpo_train | metrics_logged mode=train step=286 2026-04-13 08:02:46,816 | INFO | train_grpo_train | metrics_logged mode=train step=287 2026-04-13 08:02:53,409 | INFO | train_grpo_train | metrics_logged mode=train step=288 2026-04-13 08:03:01,344 | INFO | train_grpo_train | metrics_logged mode=train step=289 2026-04-13 08:03:08,354 | INFO | train_grpo_train | metrics_logged mode=train step=290 2026-04-13 08:03:15,294 | INFO | train_grpo_train | metrics_logged mode=train step=291 2026-04-13 08:03:23,397 | INFO | train_grpo_train | metrics_logged mode=train step=292 2026-04-13 08:03:30,930 | INFO | train_grpo_train | metrics_logged mode=train step=293 2026-04-13 08:03:40,291 | INFO | train_grpo_train | metrics_logged mode=train step=294 2026-04-13 08:03:46,885 | INFO | train_grpo_train | metrics_logged mode=train step=295 2026-04-13 08:03:54,001 | INFO | train_grpo_train | metrics_logged mode=train step=296 2026-04-13 08:04:01,426 | INFO | train_grpo_train | metrics_logged mode=train step=297 2026-04-13 08:04:09,197 | INFO | train_grpo_train | metrics_logged mode=train step=298 2026-04-13 08:04:16,009 | INFO | train_grpo_train | metrics_logged mode=train step=299 2026-04-13 08:04:22,970 | INFO | train_grpo_train | metrics_logged mode=train step=300 2026-04-13 08:05:13,469 | INFO | train_grpo_train | metrics_logged mode=eval step=300 2026-04-13 08:05:23,219 | INFO | train_grpo_train | metrics_logged mode=train step=301 2026-04-13 08:05:31,282 | INFO | train_grpo_train | metrics_logged mode=train step=302 2026-04-13 08:05:38,631 | INFO | train_grpo_train | metrics_logged mode=train step=303 2026-04-13 08:05:46,469 | INFO | train_grpo_train | metrics_logged mode=train step=304 2026-04-13 08:05:54,216 | INFO | train_grpo_train | metrics_logged mode=train step=305 2026-04-13 08:06:02,218 | INFO | train_grpo_train | metrics_logged mode=train step=306 2026-04-13 08:06:09,262 | INFO | train_grpo_train | metrics_logged mode=train step=307 2026-04-13 08:06:16,858 | INFO | train_grpo_train | metrics_logged mode=train step=308 2026-04-13 08:06:24,460 | INFO | train_grpo_train | metrics_logged mode=train step=309 2026-04-13 08:06:33,240 | INFO | train_grpo_train | metrics_logged mode=train step=310 2026-04-13 08:06:41,238 | INFO | train_grpo_train | metrics_logged mode=train step=311 2026-04-13 08:06:48,571 | INFO | train_grpo_train | metrics_logged mode=train step=312 2026-04-13 08:06:57,158 | INFO | train_grpo_train | metrics_logged mode=train step=313 2026-04-13 08:07:03,863 | INFO | train_grpo_train | metrics_logged mode=train step=314 2026-04-13 08:07:11,572 | INFO | train_grpo_train | metrics_logged mode=train step=315 2026-04-13 08:07:18,448 | INFO | train_grpo_train | metrics_logged mode=train step=316 2026-04-13 08:07:25,581 | INFO | train_grpo_train | metrics_logged mode=train step=317 2026-04-13 08:07:34,083 | INFO | train_grpo_train | metrics_logged mode=train step=318 2026-04-13 08:07:41,100 | INFO | train_grpo_train | metrics_logged mode=train step=319 2026-04-13 08:07:48,604 | INFO | train_grpo_train | metrics_logged mode=train step=320 2026-04-13 08:07:56,603 | INFO | train_grpo_train | metrics_logged mode=train step=321 2026-04-13 08:08:04,351 | INFO | train_grpo_train | metrics_logged mode=train step=322 2026-04-13 08:08:16,980 | INFO | train_grpo_train | metrics_logged mode=train step=323 2026-04-13 08:08:24,674 | INFO | train_grpo_train | metrics_logged mode=train step=324 2026-04-13 08:08:32,499 | INFO | train_grpo_train | metrics_logged mode=train step=325 2026-04-13 08:08:39,866 | INFO | train_grpo_train | metrics_logged mode=train step=326 2026-04-13 08:08:47,208 | INFO | train_grpo_train | metrics_logged mode=train step=327 2026-04-13 08:08:55,079 | INFO | train_grpo_train | metrics_logged mode=train step=328 2026-04-13 08:09:02,426 | INFO | train_grpo_train | metrics_logged mode=train step=329 2026-04-13 08:09:10,136 | INFO | train_grpo_train | metrics_logged mode=train step=330 2026-04-13 08:09:17,472 | INFO | train_grpo_train | metrics_logged mode=train step=331 2026-04-13 08:09:24,382 | INFO | train_grpo_train | metrics_logged mode=train step=332 2026-04-13 08:09:38,081 | INFO | train_grpo_train | metrics_logged mode=train step=333 2026-04-13 08:09:45,618 | INFO | train_grpo_train | metrics_logged mode=train step=334 2026-04-13 08:09:52,665 | INFO | train_grpo_train | metrics_logged mode=train step=335 2026-04-13 08:09:59,950 | INFO | train_grpo_train | metrics_logged mode=train step=336 2026-04-13 08:10:07,757 | INFO | train_grpo_train | metrics_logged mode=train step=337 2026-04-13 08:10:20,444 | INFO | train_grpo_train | metrics_logged mode=train step=338 2026-04-13 08:10:29,683 | INFO | train_grpo_train | metrics_logged mode=train step=339 2026-04-13 08:10:37,251 | INFO | train_grpo_train | metrics_logged mode=train step=340 2026-04-13 08:10:44,895 | INFO | train_grpo_train | metrics_logged mode=train step=341 2026-04-13 08:10:56,747 | INFO | train_grpo_train | metrics_logged mode=train step=342 2026-04-13 08:11:04,926 | INFO | train_grpo_train | metrics_logged mode=train step=343 2026-04-13 08:11:15,981 | INFO | train_grpo_train | metrics_logged mode=train step=344 2026-04-13 08:11:23,428 | INFO | train_grpo_train | metrics_logged mode=train step=345 2026-04-13 08:11:34,361 | INFO | train_grpo_train | metrics_logged mode=train step=346 2026-04-13 08:11:48,907 | INFO | train_grpo_train | metrics_logged mode=train step=347 2026-04-13 08:11:56,378 | INFO | train_grpo_train | metrics_logged mode=train step=348 2026-04-13 08:12:04,232 | INFO | train_grpo_train | metrics_logged mode=train step=349 2026-04-13 08:12:12,030 | INFO | train_grpo_train | metrics_logged mode=train step=350 2026-04-13 08:13:35,414 | INFO | train_grpo_train | metrics_logged mode=eval step=350 2026-04-13 08:13:54,554 | INFO | train_grpo_train | metrics_logged mode=train step=351 2026-04-13 08:14:03,869 | INFO | train_grpo_train | metrics_logged mode=train step=352 2026-04-13 08:14:15,581 | INFO | train_grpo_train | metrics_logged mode=train step=353 2026-04-13 08:14:22,968 | INFO | train_grpo_train | metrics_logged mode=train step=354 2026-04-13 08:14:35,822 | INFO | train_grpo_train | metrics_logged mode=train step=355 2026-04-13 08:14:54,597 | INFO | train_grpo_train | metrics_logged mode=train step=356 2026-04-13 08:15:10,852 | INFO | train_grpo_train | metrics_logged mode=train step=357 2026-04-13 08:15:18,343 | INFO | train_grpo_train | metrics_logged mode=train step=358 2026-04-13 08:15:28,367 | INFO | train_grpo_train | metrics_logged mode=train step=359 2026-04-13 08:15:38,342 | INFO | train_grpo_train | metrics_logged mode=train step=360 2026-04-13 08:15:50,110 | INFO | train_grpo_train | metrics_logged mode=train step=361 2026-04-13 08:15:56,698 | INFO | train_grpo_train | metrics_logged mode=train step=362 2026-04-13 08:16:08,773 | INFO | train_grpo_train | metrics_logged mode=train step=363 2026-04-13 08:16:15,384 | INFO | train_grpo_train | metrics_logged mode=train step=364 2026-04-13 08:16:23,239 | INFO | train_grpo_train | metrics_logged mode=train step=365 2026-04-13 08:16:29,671 | INFO | train_grpo_train | metrics_logged mode=train step=366 2026-04-13 08:16:41,690 | INFO | train_grpo_train | metrics_logged mode=train step=367 2026-04-13 08:16:57,119 | INFO | train_grpo_train | metrics_logged mode=train step=368 2026-04-13 08:17:04,703 | INFO | train_grpo_train | metrics_logged mode=train step=369 2026-04-13 08:17:11,347 | INFO | train_grpo_train | metrics_logged mode=train step=370 2026-04-13 08:17:18,685 | INFO | train_grpo_train | metrics_logged mode=train step=371 2026-04-13 08:17:25,820 | INFO | train_grpo_train | metrics_logged mode=train step=372 2026-04-13 08:17:34,043 | INFO | train_grpo_train | metrics_logged mode=train step=373 2026-04-13 08:17:40,469 | INFO | train_grpo_train | metrics_logged mode=train step=374 2026-04-13 08:17:47,381 | INFO | train_grpo_train | metrics_logged mode=train step=375 2026-04-13 08:17:53,560 | INFO | train_grpo_train | metrics_logged mode=train step=376 2026-04-13 08:18:00,424 | INFO | train_grpo_train | metrics_logged mode=train step=377 2026-04-13 08:18:07,177 | INFO | train_grpo_train | metrics_logged mode=train step=378 2026-04-13 08:18:14,462 | INFO | train_grpo_train | metrics_logged mode=train step=379 2026-04-13 08:18:22,021 | INFO | train_grpo_train | metrics_logged mode=train step=380 2026-04-13 08:18:28,848 | INFO | train_grpo_train | metrics_logged mode=train step=381 2026-04-13 08:18:35,537 | INFO | train_grpo_train | metrics_logged mode=train step=382 2026-04-13 08:18:42,946 | INFO | train_grpo_train | metrics_logged mode=train step=383 2026-04-13 08:18:50,026 | INFO | train_grpo_train | metrics_logged mode=train step=384 2026-04-13 08:18:56,383 | INFO | train_grpo_train | metrics_logged mode=train step=385 2026-04-13 08:19:03,299 | INFO | train_grpo_train | metrics_logged mode=train step=386 2026-04-13 08:19:09,960 | INFO | train_grpo_train | metrics_logged mode=train step=387 2026-04-13 08:19:21,595 | INFO | train_grpo_train | metrics_logged mode=train step=388 2026-04-13 08:19:33,456 | INFO | train_grpo_train | metrics_logged mode=train step=389 2026-04-13 08:19:40,465 | INFO | train_grpo_train | metrics_logged mode=train step=390 2026-04-13 08:19:46,640 | INFO | train_grpo_train | metrics_logged mode=train step=391 2026-04-13 08:19:53,513 | INFO | train_grpo_train | metrics_logged mode=train step=392 2026-04-13 08:20:00,590 | INFO | train_grpo_train | metrics_logged mode=train step=393 2026-04-13 08:20:07,819 | INFO | train_grpo_train | metrics_logged mode=train step=394 2026-04-13 08:20:19,711 | INFO | train_grpo_train | metrics_logged mode=train step=395 2026-04-13 08:20:28,714 | INFO | train_grpo_train | metrics_logged mode=train step=396 2026-04-13 08:20:35,202 | INFO | train_grpo_train | metrics_logged mode=train step=397 2026-04-13 08:20:42,217 | INFO | train_grpo_train | metrics_logged mode=train step=398 2026-04-13 08:20:54,770 | INFO | train_grpo_train | metrics_logged mode=train step=399 2026-04-13 08:21:01,571 | INFO | train_grpo_train | metrics_logged mode=train step=400 2026-04-13 08:21:52,053 | INFO | train_grpo_train | metrics_logged mode=eval step=400 2026-04-13 08:22:03,143 | INFO | train_grpo_train | metrics_logged mode=train step=401 2026-04-13 08:22:10,661 | INFO | train_grpo_train | metrics_logged mode=train step=402 2026-04-13 08:22:18,202 | INFO | train_grpo_train | metrics_logged mode=train step=403 2026-04-13 08:22:26,037 | INFO | train_grpo_train | metrics_logged mode=train step=404 2026-04-13 08:22:33,683 | INFO | train_grpo_train | metrics_logged mode=train step=405 2026-04-13 08:22:40,868 | INFO | train_grpo_train | metrics_logged mode=train step=406 2026-04-13 08:22:50,028 | INFO | train_grpo_train | metrics_logged mode=train step=407 2026-04-13 08:22:57,765 | INFO | train_grpo_train | metrics_logged mode=train step=408 2026-04-13 08:23:05,870 | INFO | train_grpo_train | metrics_logged mode=train step=409 2026-04-13 08:23:12,457 | INFO | train_grpo_train | metrics_logged mode=train step=410 2026-04-13 08:23:20,144 | INFO | train_grpo_train | metrics_logged mode=train step=411 2026-04-13 08:23:29,472 | INFO | train_grpo_train | metrics_logged mode=train step=412 2026-04-13 08:23:39,329 | INFO | train_grpo_train | metrics_logged mode=train step=413 2026-04-13 08:23:46,264 | INFO | train_grpo_train | metrics_logged mode=train step=414 2026-04-13 08:23:52,885 | INFO | train_grpo_train | metrics_logged mode=train step=415 2026-04-13 08:23:59,224 | INFO | train_grpo_train | metrics_logged mode=train step=416 2026-04-13 08:24:06,125 | INFO | train_grpo_train | metrics_logged mode=train step=417 2026-04-13 08:24:13,798 | INFO | train_grpo_train | metrics_logged mode=train step=418 2026-04-13 08:24:21,248 | INFO | train_grpo_train | metrics_logged mode=train step=419 2026-04-13 08:24:27,967 | INFO | train_grpo_train | metrics_logged mode=train step=420 2026-04-13 08:24:35,666 | INFO | train_grpo_train | metrics_logged mode=train step=421 2026-04-13 08:24:42,945 | INFO | train_grpo_train | metrics_logged mode=train step=422 2026-04-13 08:24:51,651 | INFO | train_grpo_train | metrics_logged mode=train step=423 2026-04-13 08:25:00,429 | INFO | train_grpo_train | metrics_logged mode=train step=424 2026-04-13 08:25:07,987 | INFO | train_grpo_train | metrics_logged mode=train step=425 2026-04-13 08:25:15,338 | INFO | train_grpo_train | metrics_logged mode=train step=426 2026-04-13 08:25:24,865 | INFO | train_grpo_train | metrics_logged mode=train step=427 2026-04-13 08:25:32,767 | INFO | train_grpo_train | metrics_logged mode=train step=428 2026-04-13 08:25:41,146 | INFO | train_grpo_train | metrics_logged mode=train step=429 2026-04-13 08:25:47,891 | INFO | train_grpo_train | metrics_logged mode=train step=430 2026-04-13 08:25:55,092 | INFO | train_grpo_train | metrics_logged mode=train step=431 2026-04-13 08:26:03,365 | INFO | train_grpo_train | metrics_logged mode=train step=432 2026-04-13 08:26:09,863 | INFO | train_grpo_train | metrics_logged mode=train step=433 2026-04-13 08:26:16,709 | INFO | train_grpo_train | metrics_logged mode=train step=434 2026-04-13 08:26:22,940 | INFO | train_grpo_train | metrics_logged mode=train step=435 2026-04-13 08:26:30,978 | INFO | train_grpo_train | metrics_logged mode=train step=436 2026-04-13 08:26:38,268 | INFO | train_grpo_train | metrics_logged mode=train step=437 2026-04-13 08:26:45,677 | INFO | train_grpo_train | metrics_logged mode=train step=438 2026-04-13 08:26:52,665 | INFO | train_grpo_train | metrics_logged mode=train step=439 2026-04-13 08:27:00,350 | INFO | train_grpo_train | metrics_logged mode=train step=440 2026-04-13 08:27:07,268 | INFO | train_grpo_train | metrics_logged mode=train step=441 2026-04-13 08:27:13,756 | INFO | train_grpo_train | metrics_logged mode=train step=442 2026-04-13 08:27:22,070 | INFO | train_grpo_train | metrics_logged mode=train step=443 2026-04-13 08:27:34,131 | INFO | train_grpo_train | metrics_logged mode=train step=444 2026-04-13 08:27:42,647 | INFO | train_grpo_train | metrics_logged mode=train step=445 2026-04-13 08:27:54,678 | INFO | train_grpo_train | metrics_logged mode=train step=446 2026-04-13 08:28:01,832 | INFO | train_grpo_train | metrics_logged mode=train step=447 2026-04-13 08:28:08,828 | INFO | train_grpo_train | metrics_logged mode=train step=448 2026-04-13 08:28:16,015 | INFO | train_grpo_train | metrics_logged mode=train step=449 2026-04-13 08:28:23,246 | INFO | train_grpo_train | metrics_logged mode=train step=450 2026-04-13 08:29:42,702 | INFO | train_grpo_train | metrics_logged mode=eval step=450 2026-04-13 08:29:53,250 | INFO | train_grpo_train | metrics_logged mode=train step=451 2026-04-13 08:30:06,001 | INFO | train_grpo_train | metrics_logged mode=train step=452 2026-04-13 08:30:17,991 | INFO | train_grpo_train | metrics_logged mode=train step=453 2026-04-13 08:30:25,788 | INFO | train_grpo_train | metrics_logged mode=train step=454 2026-04-13 08:30:38,445 | INFO | train_grpo_train | metrics_logged mode=train step=455 2026-04-13 08:30:46,244 | INFO | train_grpo_train | metrics_logged mode=train step=456 2026-04-13 08:30:58,332 | INFO | train_grpo_train | metrics_logged mode=train step=457 2026-04-13 08:31:04,989 | INFO | train_grpo_train | metrics_logged mode=train step=458 2026-04-13 08:31:12,981 | INFO | train_grpo_train | metrics_logged mode=train step=459 2026-04-13 08:31:21,108 | INFO | train_grpo_train | metrics_logged mode=train step=460 2026-04-13 08:31:28,599 | INFO | train_grpo_train | metrics_logged mode=train step=461 2026-04-13 08:31:36,329 | INFO | train_grpo_train | metrics_logged mode=train step=462 2026-04-13 08:31:43,394 | INFO | train_grpo_train | metrics_logged mode=train step=463 2026-04-13 08:31:50,681 | INFO | train_grpo_train | metrics_logged mode=train step=464 2026-04-13 08:31:57,566 | INFO | train_grpo_train | metrics_logged mode=train step=465 2026-04-13 08:32:06,009 | INFO | train_grpo_train | metrics_logged mode=train step=466 2026-04-13 08:32:12,755 | INFO | train_grpo_train | metrics_logged mode=train step=467 2026-04-13 08:32:19,906 | INFO | train_grpo_train | metrics_logged mode=train step=468 2026-04-13 08:32:27,178 | INFO | train_grpo_train | metrics_logged mode=train step=469 2026-04-13 08:32:34,237 | INFO | train_grpo_train | metrics_logged mode=train step=470 2026-04-13 08:32:41,154 | INFO | train_grpo_train | metrics_logged mode=train step=471 2026-04-13 08:32:48,326 | INFO | train_grpo_train | metrics_logged mode=train step=472 2026-04-13 08:33:00,702 | INFO | train_grpo_train | metrics_logged mode=train step=473 2026-04-13 08:33:10,187 | INFO | train_grpo_train | metrics_logged mode=train step=474 2026-04-13 08:33:16,703 | INFO | train_grpo_train | metrics_logged mode=train step=475 2026-04-13 08:33:24,020 | INFO | train_grpo_train | metrics_logged mode=train step=476 2026-04-13 08:33:30,993 | INFO | train_grpo_train | metrics_logged mode=train step=477 2026-04-13 08:33:43,220 | INFO | train_grpo_train | metrics_logged mode=train step=478 2026-04-13 08:33:55,679 | INFO | train_grpo_train | metrics_logged mode=train step=479 2026-04-13 08:34:07,270 | INFO | train_grpo_train | metrics_logged mode=train step=480 2026-04-13 08:34:18,460 | INFO | train_grpo_train | metrics_logged mode=train step=481 2026-04-13 08:34:31,879 | INFO | train_grpo_train | metrics_logged mode=train step=482 2026-04-13 08:34:44,076 | INFO | train_grpo_train | metrics_logged mode=train step=483 2026-04-13 08:34:55,983 | INFO | train_grpo_train | metrics_logged mode=train step=484 2026-04-13 08:35:01,842 | INFO | train_grpo_train | metrics_logged mode=train step=485 2026-04-13 08:35:07,400 | INFO | train_grpo_train | metrics_logged mode=train step=486 2026-04-13 08:35:13,437 | INFO | train_grpo_train | metrics_logged mode=train step=487 2026-04-13 08:35:20,506 | INFO | train_grpo_train | metrics_logged mode=train step=488 2026-04-13 08:35:27,483 | INFO | train_grpo_train | metrics_logged mode=train step=489 2026-04-13 08:35:33,323 | INFO | train_grpo_train | metrics_logged mode=train step=490 2026-04-13 08:35:39,432 | INFO | train_grpo_train | metrics_logged mode=train step=491 2026-04-13 08:35:45,842 | INFO | train_grpo_train | metrics_logged mode=train step=492 2026-04-13 08:35:55,144 | INFO | train_grpo_train | metrics_logged mode=train step=493 2026-04-13 08:36:06,230 | INFO | train_grpo_train | metrics_logged mode=train step=494 2026-04-13 08:36:12,818 | INFO | train_grpo_train | metrics_logged mode=train step=495 2026-04-13 08:36:18,721 | INFO | train_grpo_train | metrics_logged mode=train step=496 2026-04-13 08:36:26,968 | INFO | train_grpo_train | metrics_logged mode=train step=497 2026-04-13 08:36:33,154 | INFO | train_grpo_train | metrics_logged mode=train step=498 2026-04-13 08:36:39,395 | INFO | train_grpo_train | metrics_logged mode=train step=499 2026-04-13 08:36:51,181 | INFO | train_grpo_train | metrics_logged mode=train step=500 2026-04-13 08:37:43,626 | INFO | train_grpo_train | metrics_logged mode=eval step=500 2026-04-13 08:37:52,792 | INFO | train_grpo_train | metrics_logged mode=train step=501 2026-04-13 08:37:59,875 | INFO | train_grpo_train | metrics_logged mode=train step=502 2026-04-13 08:38:11,072 | INFO | train_grpo_train | metrics_logged mode=train step=503 2026-04-13 08:38:22,036 | INFO | train_grpo_train | metrics_logged mode=train step=504 2026-04-13 08:38:28,057 | INFO | train_grpo_train | metrics_logged mode=train step=505 2026-04-13 08:38:34,164 | INFO | train_grpo_train | metrics_logged mode=train step=506 2026-04-13 08:38:45,125 | INFO | train_grpo_train | metrics_logged mode=train step=507 2026-04-13 08:38:56,251 | INFO | train_grpo_train | metrics_logged mode=train step=508 2026-04-13 08:39:02,594 | INFO | train_grpo_train | metrics_logged mode=train step=509 2026-04-13 08:39:08,614 | INFO | train_grpo_train | metrics_logged mode=train step=510 2026-04-13 08:39:19,614 | INFO | train_grpo_train | metrics_logged mode=train step=511 2026-04-13 08:39:26,127 | INFO | train_grpo_train | metrics_logged mode=train step=512 2026-04-13 08:39:37,227 | INFO | train_grpo_train | metrics_logged mode=train step=513 2026-04-13 08:39:42,968 | INFO | train_grpo_train | metrics_logged mode=train step=514 2026-04-13 08:39:48,638 | INFO | train_grpo_train | metrics_logged mode=train step=515 2026-04-13 08:39:59,666 | INFO | train_grpo_train | metrics_logged mode=train step=516 2026-04-13 08:40:10,676 | INFO | train_grpo_train | metrics_logged mode=train step=517 2026-04-13 08:40:18,623 | INFO | train_grpo_train | metrics_logged mode=train step=518 2026-04-13 08:40:24,402 | INFO | train_grpo_train | metrics_logged mode=train step=519 2026-04-13 08:40:30,127 | INFO | train_grpo_train | metrics_logged mode=train step=520 2026-04-13 08:40:36,307 | INFO | train_grpo_train | metrics_logged mode=train step=521 2026-04-13 08:40:42,629 | INFO | train_grpo_train | metrics_logged mode=train step=522 2026-04-13 08:40:49,893 | INFO | train_grpo_train | metrics_logged mode=train step=523 2026-04-13 08:40:55,694 | INFO | train_grpo_train | metrics_logged mode=train step=524 2026-04-13 08:41:01,661 | INFO | train_grpo_train | metrics_logged mode=train step=525 2026-04-13 08:41:07,827 | INFO | train_grpo_train | metrics_logged mode=train step=526 2026-04-13 08:41:18,376 | INFO | train_grpo_train | metrics_logged mode=train step=527 2026-04-13 08:41:27,330 | INFO | train_grpo_train | metrics_logged mode=train step=528 2026-04-13 08:41:34,612 | INFO | train_grpo_train | metrics_logged mode=train step=529 2026-04-13 08:41:42,237 | INFO | train_grpo_train | metrics_logged mode=train step=530 2026-04-13 08:41:48,722 | INFO | train_grpo_train | metrics_logged mode=train step=531 2026-04-13 08:41:54,717 | INFO | train_grpo_train | metrics_logged mode=train step=532 2026-04-13 08:42:00,827 | INFO | train_grpo_train | metrics_logged mode=train step=533 2026-04-13 08:42:19,042 | INFO | train_grpo_train | metrics_logged mode=train step=534 2026-04-13 08:42:26,768 | INFO | train_grpo_train | metrics_logged mode=train step=535 2026-04-13 08:42:33,464 | INFO | train_grpo_train | metrics_logged mode=train step=536 2026-04-13 08:42:39,248 | INFO | train_grpo_train | metrics_logged mode=train step=537 2026-04-13 08:42:45,876 | INFO | train_grpo_train | metrics_logged mode=train step=538 2026-04-13 08:42:52,344 | INFO | train_grpo_train | metrics_logged mode=train step=539 2026-04-13 08:43:03,426 | INFO | train_grpo_train | metrics_logged mode=train step=540 2026-04-13 08:43:09,834 | INFO | train_grpo_train | metrics_logged mode=train step=541 2026-04-13 08:43:15,770 | INFO | train_grpo_train | metrics_logged mode=train step=542 2026-04-13 08:43:26,972 | INFO | train_grpo_train | metrics_logged mode=train step=543 2026-04-13 08:43:32,921 | INFO | train_grpo_train | metrics_logged mode=train step=544 2026-04-13 08:43:39,016 | INFO | train_grpo_train | metrics_logged mode=train step=545 2026-04-13 08:43:45,014 | INFO | train_grpo_train | metrics_logged mode=train step=546 2026-04-13 08:43:50,858 | INFO | train_grpo_train | metrics_logged mode=train step=547 2026-04-13 08:43:56,742 | INFO | train_grpo_train | metrics_logged mode=train step=548 2026-04-13 08:44:03,816 | INFO | train_grpo_train | metrics_logged mode=train step=549 2026-04-13 08:44:10,163 | INFO | train_grpo_train | metrics_logged mode=train step=550 2026-04-13 08:44:53,871 | INFO | train_grpo_train | metrics_logged mode=eval step=550 2026-04-13 08:45:04,294 | INFO | train_grpo_train | metrics_logged mode=train step=551 2026-04-13 08:45:10,769 | INFO | train_grpo_train | metrics_logged mode=train step=552 2026-04-13 08:45:17,233 | INFO | train_grpo_train | metrics_logged mode=train step=553 2026-04-13 08:45:28,957 | INFO | train_grpo_train | metrics_logged mode=train step=554 2026-04-13 08:45:35,351 | INFO | train_grpo_train | metrics_logged mode=train step=555 2026-04-13 08:45:41,762 | INFO | train_grpo_train | metrics_logged mode=train step=556 2026-04-13 08:45:47,932 | INFO | train_grpo_train | metrics_logged mode=train step=557 2026-04-13 08:45:54,455 | INFO | train_grpo_train | metrics_logged mode=train step=558 2026-04-13 08:46:01,392 | INFO | train_grpo_train | metrics_logged mode=train step=559 2026-04-13 08:46:07,194 | INFO | train_grpo_train | metrics_logged mode=train step=560 2026-04-13 08:46:18,831 | INFO | train_grpo_train | metrics_logged mode=train step=561 2026-04-13 08:46:26,253 | INFO | train_grpo_train | metrics_logged mode=train step=562 2026-04-13 08:46:33,269 | INFO | train_grpo_train | metrics_logged mode=train step=563 2026-04-13 08:46:39,152 | INFO | train_grpo_train | metrics_logged mode=train step=564 2026-04-13 08:46:45,260 | INFO | train_grpo_train | metrics_logged mode=train step=565 2026-04-13 08:46:51,655 | INFO | train_grpo_train | metrics_logged mode=train step=566 2026-04-13 08:46:57,713 | INFO | train_grpo_train | metrics_logged mode=train step=567 2026-04-13 08:47:04,240 | INFO | train_grpo_train | metrics_logged mode=train step=568 2026-04-13 08:47:10,169 | INFO | train_grpo_train | metrics_logged mode=train step=569 2026-04-13 08:47:16,080 | INFO | train_grpo_train | metrics_logged mode=train step=570 2026-04-13 08:47:27,537 | INFO | train_grpo_train | metrics_logged mode=train step=571 2026-04-13 08:47:34,005 | INFO | train_grpo_train | metrics_logged mode=train step=572 2026-04-13 08:47:45,137 | INFO | train_grpo_train | metrics_logged mode=train step=573 2026-04-13 08:47:51,108 | INFO | train_grpo_train | metrics_logged mode=train step=574 2026-04-13 08:47:57,079 | INFO | train_grpo_train | metrics_logged mode=train step=575 2026-04-13 08:48:03,152 | INFO | train_grpo_train | metrics_logged mode=train step=576 2026-04-13 08:48:14,633 | INFO | train_grpo_train | metrics_logged mode=train step=577 2026-04-13 08:48:20,772 | INFO | train_grpo_train | metrics_logged mode=train step=578 2026-04-13 08:48:27,165 | INFO | train_grpo_train | metrics_logged mode=train step=579 2026-04-13 08:48:34,317 | INFO | train_grpo_train | metrics_logged mode=train step=580 2026-04-13 08:48:40,485 | INFO | train_grpo_train | metrics_logged mode=train step=581 2026-04-13 08:48:46,590 | INFO | train_grpo_train | metrics_logged mode=train step=582 2026-04-13 08:48:52,531 | INFO | train_grpo_train | metrics_logged mode=train step=583 2026-04-13 08:49:04,216 | INFO | train_grpo_train | metrics_logged mode=train step=584 2026-04-13 08:49:10,339 | INFO | train_grpo_train | metrics_logged mode=train step=585 2026-04-13 08:49:22,157 | INFO | train_grpo_train | metrics_logged mode=train step=586 2026-04-13 08:49:28,365 | INFO | train_grpo_train | metrics_logged mode=train step=587 2026-04-13 08:49:35,005 | INFO | train_grpo_train | metrics_logged mode=train step=588 2026-04-13 08:49:41,148 | INFO | train_grpo_train | metrics_logged mode=train step=589 2026-04-13 08:49:47,503 | INFO | train_grpo_train | metrics_logged mode=train step=590 2026-04-13 08:49:54,785 | INFO | train_grpo_train | metrics_logged mode=train step=591 2026-04-13 08:50:06,516 | INFO | train_grpo_train | metrics_logged mode=train step=592 2026-04-13 08:50:13,544 | INFO | train_grpo_train | metrics_logged mode=train step=593 2026-04-13 08:50:20,578 | INFO | train_grpo_train | metrics_logged mode=train step=594 2026-04-13 08:50:26,203 | INFO | train_grpo_train | metrics_logged mode=train step=595 2026-04-13 08:50:32,617 | INFO | train_grpo_train | metrics_logged mode=train step=596 2026-04-13 08:50:43,685 | INFO | train_grpo_train | metrics_logged mode=train step=597 2026-04-13 08:50:49,750 | INFO | train_grpo_train | metrics_logged mode=train step=598 2026-04-13 08:51:01,302 | INFO | train_grpo_train | metrics_logged mode=train step=599 2026-04-13 08:51:07,079 | INFO | train_grpo_train | metrics_logged mode=train step=600 2026-04-13 08:52:03,947 | INFO | train_grpo_train | metrics_logged mode=eval step=600 2026-04-13 08:52:13,244 | INFO | train_grpo_train | metrics_logged mode=train step=601 2026-04-13 08:52:21,030 | INFO | train_grpo_train | metrics_logged mode=train step=602 2026-04-13 08:52:32,569 | INFO | train_grpo_train | metrics_logged mode=train step=603 2026-04-13 08:52:43,566 | INFO | train_grpo_train | metrics_logged mode=train step=604 2026-04-13 08:52:49,449 | INFO | train_grpo_train | metrics_logged mode=train step=605 2026-04-13 08:53:00,592 | INFO | train_grpo_train | metrics_logged mode=train step=606 2026-04-13 08:53:13,213 | INFO | train_grpo_train | metrics_logged mode=train step=607 2026-04-13 08:53:25,077 | INFO | train_grpo_train | metrics_logged mode=train step=608 2026-04-13 08:53:36,905 | INFO | train_grpo_train | metrics_logged mode=train step=609 2026-04-13 08:53:48,350 | INFO | train_grpo_train | metrics_logged mode=train step=610 2026-04-13 08:53:59,581 | INFO | train_grpo_train | metrics_logged mode=train step=611 2026-04-13 08:54:11,359 | INFO | train_grpo_train | metrics_logged mode=train step=612 2026-04-13 08:54:17,282 | INFO | train_grpo_train | metrics_logged mode=train step=613 2026-04-13 08:54:23,635 | INFO | train_grpo_train | metrics_logged mode=train step=614 2026-04-13 08:54:35,859 | INFO | train_grpo_train | metrics_logged mode=train step=615 2026-04-13 08:54:41,789 | INFO | train_grpo_train | metrics_logged mode=train step=616 2026-04-13 08:54:47,565 | INFO | train_grpo_train | metrics_logged mode=train step=617 2026-04-13 08:54:58,972 | INFO | train_grpo_train | metrics_logged mode=train step=618 2026-04-13 08:55:05,110 | INFO | train_grpo_train | metrics_logged mode=train step=619 2026-04-13 08:55:11,365 | INFO | train_grpo_train | metrics_logged mode=train step=620 2026-04-13 08:55:17,398 | INFO | train_grpo_train | metrics_logged mode=train step=621 2026-04-13 08:55:28,593 | INFO | train_grpo_train | metrics_logged mode=train step=622 2026-04-13 08:55:34,366 | INFO | train_grpo_train | metrics_logged mode=train step=623 2026-04-13 08:55:40,546 | INFO | train_grpo_train | metrics_logged mode=train step=624 2026-04-13 08:55:47,051 | INFO | train_grpo_train | metrics_logged mode=train step=625 2026-04-13 08:55:53,142 | INFO | train_grpo_train | metrics_logged mode=train step=626 2026-04-13 08:55:59,800 | INFO | train_grpo_train | metrics_logged mode=train step=627 2026-04-13 08:56:11,111 | INFO | train_grpo_train | metrics_logged mode=train step=628 2026-04-13 08:56:17,255 | INFO | train_grpo_train | metrics_logged mode=train step=629 2026-04-13 08:56:28,659 | INFO | train_grpo_train | metrics_logged mode=train step=630 2026-04-13 08:56:35,278 | INFO | train_grpo_train | metrics_logged mode=train step=631 2026-04-13 08:56:46,617 | INFO | train_grpo_train | metrics_logged mode=train step=632 2026-04-13 08:56:53,946 | INFO | train_grpo_train | metrics_logged mode=train step=633 2026-04-13 08:57:00,222 | INFO | train_grpo_train | metrics_logged mode=train step=634 2026-04-13 08:57:06,550 | INFO | train_grpo_train | metrics_logged mode=train step=635 2026-04-13 08:57:17,961 | INFO | train_grpo_train | metrics_logged mode=train step=636 2026-04-13 08:57:24,336 | INFO | train_grpo_train | metrics_logged mode=train step=637 2026-04-13 08:57:30,593 | INFO | train_grpo_train | metrics_logged mode=train step=638 2026-04-13 08:57:42,006 | INFO | train_grpo_train | metrics_logged mode=train step=639 2026-04-13 08:57:48,842 | INFO | train_grpo_train | metrics_logged mode=train step=640 2026-04-13 08:57:54,825 | INFO | train_grpo_train | metrics_logged mode=train step=641 2026-04-13 08:58:01,517 | INFO | train_grpo_train | metrics_logged mode=train step=642 2026-04-13 08:58:12,653 | INFO | train_grpo_train | metrics_logged mode=train step=643 2026-04-13 08:58:20,273 | INFO | train_grpo_train | metrics_logged mode=train step=644 2026-04-13 08:58:27,066 | INFO | train_grpo_train | metrics_logged mode=train step=645 2026-04-13 08:58:33,266 | INFO | train_grpo_train | metrics_logged mode=train step=646 2026-04-13 08:58:40,132 | INFO | train_grpo_train | metrics_logged mode=train step=647 2026-04-13 08:58:46,044 | INFO | train_grpo_train | metrics_logged mode=train step=648 2026-04-13 08:58:51,920 | INFO | train_grpo_train | metrics_logged mode=train step=649 2026-04-13 08:58:58,669 | INFO | train_grpo_train | metrics_logged mode=train step=650 2026-04-13 08:59:44,348 | INFO | train_grpo_train | metrics_logged mode=eval step=650 2026-04-13 08:59:53,922 | INFO | train_grpo_train | metrics_logged mode=train step=651 2026-04-13 09:00:00,098 | INFO | train_grpo_train | metrics_logged mode=train step=652 2026-04-13 09:00:11,635 | INFO | train_grpo_train | metrics_logged mode=train step=653 2026-04-13 09:00:18,118 | INFO | train_grpo_train | metrics_logged mode=train step=654 2026-04-13 09:00:25,102 | INFO | train_grpo_train | metrics_logged mode=train step=655 2026-04-13 09:00:32,076 | INFO | train_grpo_train | metrics_logged mode=train step=656 2026-04-13 09:00:38,731 | INFO | train_grpo_train | metrics_logged mode=train step=657 2026-04-13 09:00:45,046 | INFO | train_grpo_train | metrics_logged mode=train step=658 2026-04-13 09:00:50,871 | INFO | train_grpo_train | metrics_logged mode=train step=659 2026-04-13 09:00:56,813 | INFO | train_grpo_train | metrics_logged mode=train step=660 2026-04-13 09:01:02,536 | INFO | train_grpo_train | metrics_logged mode=train step=661 2026-04-13 09:01:08,782 | INFO | train_grpo_train | metrics_logged mode=train step=662 2026-04-13 09:01:20,892 | INFO | train_grpo_train | metrics_logged mode=train step=663 2026-04-13 09:01:27,267 | INFO | train_grpo_train | metrics_logged mode=train step=664 2026-04-13 09:01:33,188 | INFO | train_grpo_train | metrics_logged mode=train step=665 2026-04-13 09:01:39,272 | INFO | train_grpo_train | metrics_logged mode=train step=666 2026-04-13 09:01:45,073 | INFO | train_grpo_train | metrics_logged mode=train step=667 2026-04-13 09:01:50,725 | INFO | train_grpo_train | metrics_logged mode=train step=668 2026-04-13 09:01:56,246 | INFO | train_grpo_train | metrics_logged mode=train step=669 2026-04-13 09:02:02,838 | INFO | train_grpo_train | metrics_logged mode=train step=670 2026-04-13 09:02:08,690 | INFO | train_grpo_train | metrics_logged mode=train step=671 2026-04-13 09:02:15,682 | INFO | train_grpo_train | metrics_logged mode=train step=672 2026-04-13 09:02:26,925 | INFO | train_grpo_train | metrics_logged mode=train step=673 2026-04-13 09:02:38,415 | INFO | train_grpo_train | metrics_logged mode=train step=674 2026-04-13 09:02:44,631 | INFO | train_grpo_train | metrics_logged mode=train step=675 2026-04-13 09:02:51,394 | INFO | train_grpo_train | metrics_logged mode=train step=676 2026-04-13 09:02:57,435 | INFO | train_grpo_train | metrics_logged mode=train step=677 2026-04-13 09:03:03,396 | INFO | train_grpo_train | metrics_logged mode=train step=678 2026-04-13 09:03:09,440 | INFO | train_grpo_train | metrics_logged mode=train step=679 2026-04-13 09:03:15,179 | INFO | train_grpo_train | metrics_logged mode=train step=680 2026-04-13 09:03:21,020 | INFO | train_grpo_train | metrics_logged mode=train step=681 2026-04-13 09:03:26,950 | INFO | train_grpo_train | metrics_logged mode=train step=682 2026-04-13 09:03:32,817 | INFO | train_grpo_train | metrics_logged mode=train step=683 2026-04-13 09:03:38,722 | INFO | train_grpo_train | metrics_logged mode=train step=684 2026-04-13 09:03:44,622 | INFO | train_grpo_train | metrics_logged mode=train step=685 2026-04-13 09:03:50,663 | INFO | train_grpo_train | metrics_logged mode=train step=686 2026-04-13 09:03:56,540 | INFO | train_grpo_train | metrics_logged mode=train step=687 2026-04-13 09:04:08,398 | INFO | train_grpo_train | metrics_logged mode=train step=688 2026-04-13 09:04:16,349 | INFO | train_grpo_train | metrics_logged mode=train step=689 2026-04-13 09:04:23,299 | INFO | train_grpo_train | metrics_logged mode=train step=690 2026-04-13 09:04:29,641 | INFO | train_grpo_train | metrics_logged mode=train step=691 2026-04-13 09:04:36,454 | INFO | train_grpo_train | metrics_logged mode=train step=692 2026-04-13 09:04:43,446 | INFO | train_grpo_train | metrics_logged mode=train step=693 2026-04-13 09:04:50,499 | INFO | train_grpo_train | metrics_logged mode=train step=694 2026-04-13 09:04:57,380 | INFO | train_grpo_train | metrics_logged mode=train step=695 2026-04-13 09:05:04,859 | INFO | train_grpo_train | metrics_logged mode=train step=696 2026-04-13 09:05:11,323 | INFO | train_grpo_train | metrics_logged mode=train step=697 2026-04-13 09:05:23,087 | INFO | train_grpo_train | metrics_logged mode=train step=698 2026-04-13 09:05:30,786 | INFO | train_grpo_train | metrics_logged mode=train step=699 2026-04-13 09:05:37,614 | INFO | train_grpo_train | metrics_logged mode=train step=700 2026-04-13 09:06:24,791 | INFO | train_grpo_train | metrics_logged mode=eval step=700 2026-04-13 09:06:33,810 | INFO | train_grpo_train | metrics_logged mode=train step=701 2026-04-13 09:06:40,852 | INFO | train_grpo_train | metrics_logged mode=train step=702 2026-04-13 09:06:52,412 | INFO | train_grpo_train | metrics_logged mode=train step=703 2026-04-13 09:06:59,065 | INFO | train_grpo_train | metrics_logged mode=train step=704 2026-04-13 09:07:06,145 | INFO | train_grpo_train | metrics_logged mode=train step=705 2026-04-13 09:07:17,705 | INFO | train_grpo_train | metrics_logged mode=train step=706 2026-04-13 09:07:25,174 | INFO | train_grpo_train | metrics_logged mode=train step=707 2026-04-13 09:07:37,672 | INFO | train_grpo_train | metrics_logged mode=train step=708 2026-04-13 09:07:44,601 | INFO | train_grpo_train | metrics_logged mode=train step=709 2026-04-13 09:07:51,224 | INFO | train_grpo_train | metrics_logged mode=train step=710 2026-04-13 09:07:57,560 | INFO | train_grpo_train | metrics_logged mode=train step=711 2026-04-13 09:08:04,207 | INFO | train_grpo_train | metrics_logged mode=train step=712 2026-04-13 09:08:11,301 | INFO | train_grpo_train | metrics_logged mode=train step=713 2026-04-13 09:08:18,577 | INFO | train_grpo_train | metrics_logged mode=train step=714 2026-04-13 09:08:25,738 | INFO | train_grpo_train | metrics_logged mode=train step=715 2026-04-13 09:08:32,812 | INFO | train_grpo_train | metrics_logged mode=train step=716 2026-04-13 09:08:44,839 | INFO | train_grpo_train | metrics_logged mode=train step=717 2026-04-13 09:08:51,490 | INFO | train_grpo_train | metrics_logged mode=train step=718 2026-04-13 09:08:57,829 | INFO | train_grpo_train | metrics_logged mode=train step=719 2026-04-13 09:09:03,802 | INFO | train_grpo_train | metrics_logged mode=train step=720 2026-04-13 09:09:10,720 | INFO | train_grpo_train | metrics_logged mode=train step=721 2026-04-13 09:09:16,995 | INFO | train_grpo_train | metrics_logged mode=train step=722 2026-04-13 09:09:28,477 | INFO | train_grpo_train | metrics_logged mode=train step=723 2026-04-13 09:09:34,116 | INFO | train_grpo_train | metrics_logged mode=train step=724 2026-04-13 09:09:40,460 | INFO | train_grpo_train | metrics_logged mode=train step=725 2026-04-13 09:09:48,188 | INFO | train_grpo_train | metrics_logged mode=train step=726 2026-04-13 09:09:54,057 | INFO | train_grpo_train | metrics_logged mode=train step=727 2026-04-13 09:10:00,090 | INFO | train_grpo_train | metrics_logged mode=train step=728 2026-04-13 09:10:06,324 | INFO | train_grpo_train | metrics_logged mode=train step=729 2026-04-13 09:10:13,189 | INFO | train_grpo_train | metrics_logged mode=train step=730 2026-04-13 09:10:19,820 | INFO | train_grpo_train | metrics_logged mode=train step=731 2026-04-13 09:10:26,735 | INFO | train_grpo_train | metrics_logged mode=train step=732 2026-04-13 09:10:37,823 | INFO | train_grpo_train | metrics_logged mode=train step=733 2026-04-13 09:10:43,811 | INFO | train_grpo_train | metrics_logged mode=train step=734 2026-04-13 09:10:49,514 | INFO | train_grpo_train | metrics_logged mode=train step=735 2026-04-13 09:11:00,496 | INFO | train_grpo_train | metrics_logged mode=train step=736 2026-04-13 09:11:06,455 | INFO | train_grpo_train | metrics_logged mode=train step=737 2026-04-13 09:11:12,459 | INFO | train_grpo_train | metrics_logged mode=train step=738 2026-04-13 09:11:19,037 | INFO | train_grpo_train | metrics_logged mode=train step=739 2026-04-13 09:11:30,059 | INFO | train_grpo_train | metrics_logged mode=train step=740 2026-04-13 09:11:41,213 | INFO | train_grpo_train | metrics_logged mode=train step=741 2026-04-13 09:11:52,525 | INFO | train_grpo_train | metrics_logged mode=train step=742 2026-04-13 09:11:58,997 | INFO | train_grpo_train | metrics_logged mode=train step=743 2026-04-13 09:12:05,912 | INFO | train_grpo_train | metrics_logged mode=train step=744 2026-04-13 09:12:11,987 | INFO | train_grpo_train | metrics_logged mode=train step=745 2026-04-13 09:12:18,027 | INFO | train_grpo_train | metrics_logged mode=train step=746 2026-04-13 09:12:23,922 | INFO | train_grpo_train | metrics_logged mode=train step=747 2026-04-13 09:12:29,666 | INFO | train_grpo_train | metrics_logged mode=train step=748 2026-04-13 09:12:41,120 | INFO | train_grpo_train | metrics_logged mode=train step=749 2026-04-13 09:12:52,390 | INFO | train_grpo_train | metrics_logged mode=train step=750 2026-04-13 09:13:52,285 | INFO | train_grpo_train | metrics_logged mode=eval step=750 2026-04-13 09:14:06,568 | INFO | train_grpo_train | metrics_logged mode=train step=751 2026-04-13 09:14:17,816 | INFO | train_grpo_train | metrics_logged mode=train step=752 2026-04-13 09:14:24,235 | INFO | train_grpo_train | metrics_logged mode=train step=753 2026-04-13 09:14:30,336 | INFO | train_grpo_train | metrics_logged mode=train step=754 2026-04-13 09:14:41,406 | INFO | train_grpo_train | metrics_logged mode=train step=755 2026-04-13 09:14:47,463 | INFO | train_grpo_train | metrics_logged mode=train step=756 2026-04-13 09:14:53,555 | INFO | train_grpo_train | metrics_logged mode=train step=757 2026-04-13 09:14:59,590 | INFO | train_grpo_train | metrics_logged mode=train step=758 2026-04-13 09:15:11,124 | INFO | train_grpo_train | metrics_logged mode=train step=759 2026-04-13 09:15:17,465 | INFO | train_grpo_train | metrics_logged mode=train step=760 2026-04-13 09:15:29,346 | INFO | train_grpo_train | metrics_logged mode=train step=761 2026-04-13 09:15:36,850 | INFO | train_grpo_train | metrics_logged mode=train step=762 2026-04-13 09:15:47,887 | INFO | train_grpo_train | metrics_logged mode=train step=763 2026-04-13 09:15:54,202 | INFO | train_grpo_train | metrics_logged mode=train step=764 2026-04-13 09:16:05,689 | INFO | train_grpo_train | metrics_logged mode=train step=765 2026-04-13 09:16:11,964 | INFO | train_grpo_train | metrics_logged mode=train step=766 2026-04-13 09:16:18,490 | INFO | train_grpo_train | metrics_logged mode=train step=767 2026-04-13 09:16:24,489 | INFO | train_grpo_train | metrics_logged mode=train step=768 2026-04-13 09:16:30,275 | INFO | train_grpo_train | metrics_logged mode=train step=769 2026-04-13 09:16:41,705 | INFO | train_grpo_train | metrics_logged mode=train step=770 2026-04-13 09:16:48,038 | INFO | train_grpo_train | metrics_logged mode=train step=771 2026-04-13 09:16:59,166 | INFO | train_grpo_train | metrics_logged mode=train step=772 2026-04-13 09:17:05,097 | INFO | train_grpo_train | metrics_logged mode=train step=773 2026-04-13 09:17:11,942 | INFO | train_grpo_train | metrics_logged mode=train step=774 2026-04-13 09:17:24,112 | INFO | train_grpo_train | metrics_logged mode=train step=775 2026-04-13 09:17:35,911 | INFO | train_grpo_train | metrics_logged mode=train step=776 2026-04-13 09:17:42,503 | INFO | train_grpo_train | metrics_logged mode=train step=777 2026-04-13 09:17:49,087 | INFO | train_grpo_train | metrics_logged mode=train step=778 2026-04-13 09:17:55,096 | INFO | train_grpo_train | metrics_logged mode=train step=779 2026-04-13 09:18:06,490 | INFO | train_grpo_train | metrics_logged mode=train step=780 2026-04-13 09:18:18,205 | INFO | train_grpo_train | metrics_logged mode=train step=781 2026-04-13 09:18:29,277 | INFO | train_grpo_train | metrics_logged mode=train step=782 2026-04-13 09:18:40,484 | INFO | train_grpo_train | metrics_logged mode=train step=783 2026-04-13 09:18:51,856 | INFO | train_grpo_train | metrics_logged mode=train step=784 2026-04-13 09:18:58,843 | INFO | train_grpo_train | metrics_logged mode=train step=785 2026-04-13 09:19:04,572 | INFO | train_grpo_train | metrics_logged mode=train step=786 2026-04-13 09:19:10,856 | INFO | train_grpo_train | metrics_logged mode=train step=787 2026-04-13 09:19:17,519 | INFO | train_grpo_train | metrics_logged mode=train step=788 2026-04-13 09:19:23,598 | INFO | train_grpo_train | metrics_logged mode=train step=789 2026-04-13 09:19:31,248 | INFO | train_grpo_train | metrics_logged mode=train step=790 2026-04-13 09:19:42,858 | INFO | train_grpo_train | metrics_logged mode=train step=791 2026-04-13 09:19:48,805 | INFO | train_grpo_train | metrics_logged mode=train step=792 2026-04-13 09:20:00,232 | INFO | train_grpo_train | metrics_logged mode=train step=793 2026-04-13 09:20:13,336 | INFO | train_grpo_train | metrics_logged mode=train step=794 2026-04-13 09:20:20,505 | INFO | train_grpo_train | metrics_logged mode=train step=795 2026-04-13 09:20:31,586 | INFO | train_grpo_train | metrics_logged mode=train step=796 2026-04-13 09:20:43,172 | INFO | train_grpo_train | metrics_logged mode=train step=797 2026-04-13 09:20:49,837 | INFO | train_grpo_train | metrics_logged mode=train step=798 2026-04-13 09:20:56,430 | INFO | train_grpo_train | metrics_logged mode=train step=799 2026-04-13 09:21:02,618 | INFO | train_grpo_train | metrics_logged mode=train step=800 2026-04-13 09:21:55,610 | INFO | train_grpo_train | metrics_logged mode=eval step=800 2026-04-13 09:22:04,602 | INFO | train_grpo_train | metrics_logged mode=train step=801 2026-04-13 09:22:11,017 | INFO | train_grpo_train | metrics_logged mode=train step=802 2026-04-13 09:22:22,351 | INFO | train_grpo_train | metrics_logged mode=train step=803 2026-04-13 09:22:29,351 | INFO | train_grpo_train | metrics_logged mode=train step=804 2026-04-13 09:22:36,133 | INFO | train_grpo_train | metrics_logged mode=train step=805 2026-04-13 09:22:42,519 | INFO | train_grpo_train | metrics_logged mode=train step=806 2026-04-13 09:22:54,593 | INFO | train_grpo_train | metrics_logged mode=train step=807 2026-04-13 09:23:01,796 | INFO | train_grpo_train | metrics_logged mode=train step=808 2026-04-13 09:23:08,686 | INFO | train_grpo_train | metrics_logged mode=train step=809 2026-04-13 09:23:16,113 | INFO | train_grpo_train | metrics_logged mode=train step=810 2026-04-13 09:23:22,972 | INFO | train_grpo_train | metrics_logged mode=train step=811 2026-04-13 09:23:34,827 | INFO | train_grpo_train | metrics_logged mode=train step=812 2026-04-13 09:23:46,093 | INFO | train_grpo_train | metrics_logged mode=train step=813 2026-04-13 09:23:57,230 | INFO | train_grpo_train | metrics_logged mode=train step=814 2026-04-13 09:24:03,425 | INFO | train_grpo_train | metrics_logged mode=train step=815 2026-04-13 09:24:09,707 | INFO | train_grpo_train | metrics_logged mode=train step=816 2026-04-13 09:24:16,588 | INFO | train_grpo_train | metrics_logged mode=train step=817 2026-04-13 09:24:22,778 | INFO | train_grpo_train | metrics_logged mode=train step=818 2026-04-13 09:24:33,857 | INFO | train_grpo_train | metrics_logged mode=train step=819 2026-04-13 09:24:45,031 | INFO | train_grpo_train | metrics_logged mode=train step=820 2026-04-13 09:24:51,693 | INFO | train_grpo_train | metrics_logged mode=train step=821 2026-04-13 09:24:58,113 | INFO | train_grpo_train | metrics_logged mode=train step=822 2026-04-13 09:25:04,837 | INFO | train_grpo_train | metrics_logged mode=train step=823 2026-04-13 09:25:11,448 | INFO | train_grpo_train | metrics_logged mode=train step=824 2026-04-13 09:25:23,081 | INFO | train_grpo_train | metrics_logged mode=train step=825 2026-04-13 09:25:34,458 | INFO | train_grpo_train | metrics_logged mode=train step=826 2026-04-13 09:25:46,070 | INFO | train_grpo_train | metrics_logged mode=train step=827 2026-04-13 09:25:53,212 | INFO | train_grpo_train | metrics_logged mode=train step=828 2026-04-13 09:26:04,670 | INFO | train_grpo_train | metrics_logged mode=train step=829 2026-04-13 09:26:12,433 | INFO | train_grpo_train | metrics_logged mode=train step=830 2026-04-13 09:26:19,169 | INFO | train_grpo_train | metrics_logged mode=train step=831 2026-04-13 09:26:24,914 | INFO | train_grpo_train | metrics_logged mode=train step=832 2026-04-13 09:26:36,325 | INFO | train_grpo_train | metrics_logged mode=train step=833 2026-04-13 09:26:43,420 | INFO | train_grpo_train | metrics_logged mode=train step=834 2026-04-13 09:26:50,217 | INFO | train_grpo_train | metrics_logged mode=train step=835 2026-04-13 09:26:56,210 | INFO | train_grpo_train | metrics_logged mode=train step=836 2026-04-13 09:27:07,345 | INFO | train_grpo_train | metrics_logged mode=train step=837 2026-04-13 09:27:18,273 | INFO | train_grpo_train | metrics_logged mode=train step=838 2026-04-13 09:27:29,927 | INFO | train_grpo_train | metrics_logged mode=train step=839 2026-04-13 09:27:35,919 | INFO | train_grpo_train | metrics_logged mode=train step=840 2026-04-13 09:27:43,688 | INFO | train_grpo_train | metrics_logged mode=train step=841 2026-04-13 09:27:55,165 | INFO | train_grpo_train | metrics_logged mode=train step=842 2026-04-13 09:28:02,095 | INFO | train_grpo_train | metrics_logged mode=train step=843 2026-04-13 09:28:08,503 | INFO | train_grpo_train | metrics_logged mode=train step=844 2026-04-13 09:28:14,435 | INFO | train_grpo_train | metrics_logged mode=train step=845 2026-04-13 09:28:26,047 | INFO | train_grpo_train | metrics_logged mode=train step=846 2026-04-13 09:28:32,155 | INFO | train_grpo_train | metrics_logged mode=train step=847 2026-04-13 09:28:43,797 | INFO | train_grpo_train | metrics_logged mode=train step=848 2026-04-13 09:28:49,697 | INFO | train_grpo_train | metrics_logged mode=train step=849 2026-04-13 09:28:55,586 | INFO | train_grpo_train | metrics_logged mode=train step=850 2026-04-13 09:30:07,451 | INFO | train_grpo_train | metrics_logged mode=eval step=850 2026-04-13 09:30:17,131 | INFO | train_grpo_train | metrics_logged mode=train step=851 2026-04-13 09:30:29,071 | INFO | train_grpo_train | metrics_logged mode=train step=852 2026-04-13 09:30:40,507 | INFO | train_grpo_train | metrics_logged mode=train step=853 2026-04-13 09:30:46,964 | INFO | train_grpo_train | metrics_logged mode=train step=854 2026-04-13 09:30:58,487 | INFO | train_grpo_train | metrics_logged mode=train step=855 2026-04-13 09:31:09,751 | INFO | train_grpo_train | metrics_logged mode=train step=856 2026-04-13 09:31:21,149 | INFO | train_grpo_train | metrics_logged mode=train step=857 2026-04-13 09:31:27,915 | INFO | train_grpo_train | metrics_logged mode=train step=858 2026-04-13 09:31:39,199 | INFO | train_grpo_train | metrics_logged mode=train step=859 2026-04-13 09:31:46,210 | INFO | train_grpo_train | metrics_logged mode=train step=860 2026-04-13 09:31:57,924 | INFO | train_grpo_train | metrics_logged mode=train step=861 2026-04-13 09:32:03,782 | INFO | train_grpo_train | metrics_logged mode=train step=862 2026-04-13 09:32:15,262 | INFO | train_grpo_train | metrics_logged mode=train step=863 2026-04-13 09:32:26,667 | INFO | train_grpo_train | metrics_logged mode=train step=864 2026-04-13 09:32:37,562 | INFO | train_grpo_train | metrics_logged mode=train step=865 2026-04-13 09:32:43,556 | INFO | train_grpo_train | metrics_logged mode=train step=866 2026-04-13 09:32:49,850 | INFO | train_grpo_train | metrics_logged mode=train step=867 2026-04-13 09:33:00,915 | INFO | train_grpo_train | metrics_logged mode=train step=868 2026-04-13 09:33:06,603 | INFO | train_grpo_train | metrics_logged mode=train step=869 2026-04-13 09:33:18,904 | INFO | train_grpo_train | metrics_logged mode=train step=870 2026-04-13 09:33:25,673 | INFO | train_grpo_train | metrics_logged mode=train step=871 2026-04-13 09:33:31,848 | INFO | train_grpo_train | metrics_logged mode=train step=872 2026-04-13 09:33:43,515 | INFO | train_grpo_train | metrics_logged mode=train step=873 2026-04-13 09:33:49,864 | INFO | train_grpo_train | metrics_logged mode=train step=874 2026-04-13 09:34:04,129 | INFO | train_grpo_train | metrics_logged mode=train step=875 2026-04-13 09:34:15,746 | INFO | train_grpo_train | metrics_logged mode=train step=876 2026-04-13 09:34:26,800 | INFO | train_grpo_train | metrics_logged mode=train step=877 2026-04-13 09:34:35,093 | INFO | train_grpo_train | metrics_logged mode=train step=878 2026-04-13 09:34:41,139 | INFO | train_grpo_train | metrics_logged mode=train step=879 2026-04-13 09:34:47,978 | INFO | train_grpo_train | metrics_logged mode=train step=880 2026-04-13 09:34:55,649 | INFO | train_grpo_train | metrics_logged mode=train step=881 2026-04-13 09:35:02,746 | INFO | train_grpo_train | metrics_logged mode=train step=882 2026-04-13 09:35:09,150 | INFO | train_grpo_train | metrics_logged mode=train step=883 2026-04-13 09:35:20,586 | INFO | train_grpo_train | metrics_logged mode=train step=884 2026-04-13 09:35:32,044 | INFO | train_grpo_train | metrics_logged mode=train step=885 2026-04-13 09:35:38,596 | INFO | train_grpo_train | metrics_logged mode=train step=886 2026-04-13 09:35:44,894 | INFO | train_grpo_train | metrics_logged mode=train step=887 2026-04-13 09:35:51,969 | INFO | train_grpo_train | metrics_logged mode=train step=888 2026-04-13 09:35:58,206 | INFO | train_grpo_train | metrics_logged mode=train step=889 2026-04-13 09:36:04,788 | INFO | train_grpo_train | metrics_logged mode=train step=890 2026-04-13 09:36:10,929 | INFO | train_grpo_train | metrics_logged mode=train step=891 2026-04-13 09:36:17,225 | INFO | train_grpo_train | metrics_logged mode=train step=892 2026-04-13 09:36:23,411 | INFO | train_grpo_train | metrics_logged mode=train step=893 2026-04-13 09:36:29,186 | INFO | train_grpo_train | metrics_logged mode=train step=894 2026-04-13 09:36:35,548 | INFO | train_grpo_train | metrics_logged mode=train step=895 2026-04-13 09:36:41,760 | INFO | train_grpo_train | metrics_logged mode=train step=896 2026-04-13 09:36:48,390 | INFO | train_grpo_train | metrics_logged mode=train step=897 2026-04-13 09:36:59,789 | INFO | train_grpo_train | metrics_logged mode=train step=898 2026-04-13 09:37:06,073 | INFO | train_grpo_train | metrics_logged mode=train step=899 2026-04-13 09:37:13,045 | INFO | train_grpo_train | metrics_logged mode=train step=900 2026-04-13 09:38:06,570 | INFO | train_grpo_train | metrics_logged mode=eval step=900 2026-04-13 09:38:15,778 | INFO | train_grpo_train | metrics_logged mode=train step=901 2026-04-13 09:38:22,332 | INFO | train_grpo_train | metrics_logged mode=train step=902 2026-04-13 09:38:34,263 | INFO | train_grpo_train | metrics_logged mode=train step=903 2026-04-13 09:38:40,771 | INFO | train_grpo_train | metrics_logged mode=train step=904 2026-04-13 09:38:46,549 | INFO | train_grpo_train | metrics_logged mode=train step=905 2026-04-13 09:38:58,019 | INFO | train_grpo_train | metrics_logged mode=train step=906 2026-04-13 09:39:04,975 | INFO | train_grpo_train | metrics_logged mode=train step=907 2026-04-13 09:39:11,799 | INFO | train_grpo_train | metrics_logged mode=train step=908 2026-04-13 09:39:17,833 | INFO | train_grpo_train | metrics_logged mode=train step=909 2026-04-13 09:39:29,036 | INFO | train_grpo_train | metrics_logged mode=train step=910 2026-04-13 09:39:35,024 | INFO | train_grpo_train | metrics_logged mode=train step=911 2026-04-13 09:39:40,827 | INFO | train_grpo_train | metrics_logged mode=train step=912 2026-04-13 09:39:47,070 | INFO | train_grpo_train | metrics_logged mode=train step=913 2026-04-13 09:39:53,918 | INFO | train_grpo_train | metrics_logged mode=train step=914 2026-04-13 09:40:00,694 | INFO | train_grpo_train | metrics_logged mode=train step=915 2026-04-13 09:40:06,537 | INFO | train_grpo_train | metrics_logged mode=train step=916 2026-04-13 09:40:17,513 | INFO | train_grpo_train | metrics_logged mode=train step=917 2026-04-13 09:40:28,811 | INFO | train_grpo_train | metrics_logged mode=train step=918 2026-04-13 09:40:34,822 | INFO | train_grpo_train | metrics_logged mode=train step=919 2026-04-13 09:40:45,985 | INFO | train_grpo_train | metrics_logged mode=train step=920 2026-04-13 09:40:52,133 | INFO | train_grpo_train | metrics_logged mode=train step=921 2026-04-13 09:40:58,827 | INFO | train_grpo_train | metrics_logged mode=train step=922 2026-04-13 09:41:04,990 | INFO | train_grpo_train | metrics_logged mode=train step=923 2026-04-13 09:41:10,909 | INFO | train_grpo_train | metrics_logged mode=train step=924 2026-04-13 09:41:17,098 | INFO | train_grpo_train | metrics_logged mode=train step=925 2026-04-13 09:41:24,176 | INFO | train_grpo_train | metrics_logged mode=train step=926 2026-04-13 09:41:30,694 | INFO | train_grpo_train | metrics_logged mode=train step=927 2026-04-13 09:41:36,734 | INFO | train_grpo_train | metrics_logged mode=train step=928 2026-04-13 09:41:47,867 | INFO | train_grpo_train | metrics_logged mode=train step=929 2026-04-13 09:41:54,056 | INFO | train_grpo_train | metrics_logged mode=train step=930 2026-04-13 09:42:06,090 | INFO | train_grpo_train | metrics_logged mode=train step=931 2026-04-13 09:42:12,916 | INFO | train_grpo_train | metrics_logged mode=train step=932 2026-04-13 09:42:20,741 | INFO | train_grpo_train | metrics_logged mode=train step=933 2026-04-13 09:42:26,731 | INFO | train_grpo_train | metrics_logged mode=train step=934 2026-04-13 09:42:32,613 | INFO | train_grpo_train | metrics_logged mode=train step=935 2026-04-13 09:42:38,839 | INFO | train_grpo_train | metrics_logged mode=train step=936 2026-04-13 09:42:45,420 | INFO | train_grpo_train | metrics_logged mode=train step=937 2026-04-13 09:42:51,998 | INFO | train_grpo_train | metrics_logged mode=train step=938 2026-04-13 09:42:57,935 | INFO | train_grpo_train | metrics_logged mode=train step=939 2026-04-13 09:43:03,836 | INFO | train_grpo_train | metrics_logged mode=train step=940 2026-04-13 09:43:14,714 | INFO | train_grpo_train | metrics_logged mode=train step=941 2026-04-13 09:43:20,426 | INFO | train_grpo_train | metrics_logged mode=train step=942 2026-04-13 09:43:27,397 | INFO | train_grpo_train | metrics_logged mode=train step=943 2026-04-13 09:43:38,317 | INFO | train_grpo_train | metrics_logged mode=train step=944 2026-04-13 09:43:44,412 | INFO | train_grpo_train | metrics_logged mode=train step=945 2026-04-13 09:43:51,589 | INFO | train_grpo_train | metrics_logged mode=train step=946 2026-04-13 09:43:58,319 | INFO | train_grpo_train | metrics_logged mode=train step=947 2026-04-13 09:44:09,116 | INFO | train_grpo_train | metrics_logged mode=train step=948 2026-04-13 09:44:14,653 | INFO | train_grpo_train | metrics_logged mode=train step=949 2026-04-13 09:44:21,142 | INFO | train_grpo_train | metrics_logged mode=train step=950 2026-04-13 09:45:12,003 | INFO | train_grpo_train | metrics_logged mode=eval step=950 2026-04-13 09:45:22,817 | INFO | train_grpo_train | metrics_logged mode=train step=951 2026-04-13 09:45:29,230 | INFO | train_grpo_train | metrics_logged mode=train step=952 2026-04-13 09:45:35,243 | INFO | train_grpo_train | metrics_logged mode=train step=953 2026-04-13 09:45:46,560 | INFO | train_grpo_train | metrics_logged mode=train step=954 2026-04-13 09:45:53,519 | INFO | train_grpo_train | metrics_logged mode=train step=955 2026-04-13 09:46:00,142 | INFO | train_grpo_train | metrics_logged mode=train step=956 2026-04-13 09:46:05,820 | INFO | train_grpo_train | metrics_logged mode=train step=957 2026-04-13 09:46:11,741 | INFO | train_grpo_train | metrics_logged mode=train step=958 2026-04-13 09:46:23,189 | INFO | train_grpo_train | metrics_logged mode=train step=959 2026-04-13 09:46:29,705 | INFO | train_grpo_train | metrics_logged mode=train step=960 2026-04-13 09:46:35,901 | INFO | train_grpo_train | metrics_logged mode=train step=961 2026-04-13 09:46:41,888 | INFO | train_grpo_train | metrics_logged mode=train step=962 2026-04-13 09:46:48,294 | INFO | train_grpo_train | metrics_logged mode=train step=963 2026-04-13 09:46:54,649 | INFO | train_grpo_train | metrics_logged mode=train step=964 2026-04-13 09:47:05,861 | INFO | train_grpo_train | metrics_logged mode=train step=965 2026-04-13 09:47:12,063 | INFO | train_grpo_train | metrics_logged mode=train step=966 2026-04-13 09:47:18,833 | INFO | train_grpo_train | metrics_logged mode=train step=967 2026-04-13 09:47:25,192 | INFO | train_grpo_train | metrics_logged mode=train step=968 2026-04-13 09:47:31,533 | INFO | train_grpo_train | metrics_logged mode=train step=969 2026-04-13 09:47:42,695 | INFO | train_grpo_train | metrics_logged mode=train step=970 2026-04-13 09:47:48,582 | INFO | train_grpo_train | metrics_logged mode=train step=971 2026-04-13 09:47:55,152 | INFO | train_grpo_train | metrics_logged mode=train step=972 2026-04-13 09:48:01,072 | INFO | train_grpo_train | metrics_logged mode=train step=973 2026-04-13 09:48:07,185 | INFO | train_grpo_train | metrics_logged mode=train step=974 2026-04-13 09:48:18,308 | INFO | train_grpo_train | metrics_logged mode=train step=975 2026-04-13 09:48:24,436 | INFO | train_grpo_train | metrics_logged mode=train step=976 2026-04-13 09:48:30,407 | INFO | train_grpo_train | metrics_logged mode=train step=977 2026-04-13 09:48:36,634 | INFO | train_grpo_train | metrics_logged mode=train step=978 2026-04-13 09:48:42,388 | INFO | train_grpo_train | metrics_logged mode=train step=979 2026-04-13 09:48:49,218 | INFO | train_grpo_train | metrics_logged mode=train step=980 2026-04-13 09:48:55,291 | INFO | train_grpo_train | metrics_logged mode=train step=981 2026-04-13 09:49:01,212 | INFO | train_grpo_train | metrics_logged mode=train step=982 2026-04-13 09:49:08,244 | INFO | train_grpo_train | metrics_logged mode=train step=983 2026-04-13 09:49:14,073 | INFO | train_grpo_train | metrics_logged mode=train step=984 2026-04-13 09:49:20,257 | INFO | train_grpo_train | metrics_logged mode=train step=985 2026-04-13 09:49:31,585 | INFO | train_grpo_train | metrics_logged mode=train step=986 2026-04-13 09:49:38,557 | INFO | train_grpo_train | metrics_logged mode=train step=987 2026-04-13 09:49:49,823 | INFO | train_grpo_train | metrics_logged mode=train step=988 2026-04-13 09:49:55,795 | INFO | train_grpo_train | metrics_logged mode=train step=989 2026-04-13 09:50:03,807 | INFO | train_grpo_train | metrics_logged mode=train step=990 2026-04-13 09:50:09,806 | INFO | train_grpo_train | metrics_logged mode=train step=991 2026-04-13 09:50:16,472 | INFO | train_grpo_train | metrics_logged mode=train step=992 2026-04-13 09:50:22,129 | INFO | train_grpo_train | metrics_logged mode=train step=993 2026-04-13 09:50:34,338 | INFO | train_grpo_train | metrics_logged mode=train step=994 2026-04-13 09:50:45,479 | INFO | train_grpo_train | metrics_logged mode=train step=995 2026-04-13 09:50:51,204 | INFO | train_grpo_train | metrics_logged mode=train step=996 2026-04-13 09:50:57,364 | INFO | train_grpo_train | metrics_logged mode=train step=997 2026-04-13 09:51:03,956 | INFO | train_grpo_train | metrics_logged mode=train step=998 2026-04-13 09:51:10,051 | INFO | train_grpo_train | metrics_logged mode=train step=999 2026-04-13 09:51:16,716 | INFO | train_grpo_train | metrics_logged mode=train step=1000 2026-04-13 09:52:01,608 | INFO | train_grpo_train | metrics_logged mode=eval step=1000 2026-04-13 09:52:11,607 | INFO | train_grpo_train | metrics_logged mode=train step=1001 2026-04-13 09:52:17,992 | INFO | train_grpo_train | metrics_logged mode=train step=1002 2026-04-13 09:52:24,298 | INFO | train_grpo_train | metrics_logged mode=train step=1003 2026-04-13 09:52:35,628 | INFO | train_grpo_train | metrics_logged mode=train step=1004 2026-04-13 09:52:41,359 | INFO | train_grpo_train | metrics_logged mode=train step=1005 2026-04-13 09:52:47,723 | INFO | train_grpo_train | metrics_logged mode=train step=1006 2026-04-13 09:52:53,711 | INFO | train_grpo_train | metrics_logged mode=train step=1007 2026-04-13 09:53:00,036 | INFO | train_grpo_train | metrics_logged mode=train step=1008 2026-04-13 09:53:06,624 | INFO | train_grpo_train | metrics_logged mode=train step=1009 2026-04-13 09:53:13,723 | INFO | train_grpo_train | metrics_logged mode=train step=1010 2026-04-13 09:53:20,099 | INFO | train_grpo_train | metrics_logged mode=train step=1011 2026-04-13 09:53:26,368 | INFO | train_grpo_train | metrics_logged mode=train step=1012 2026-04-13 09:53:33,389 | INFO | train_grpo_train | metrics_logged mode=train step=1013 2026-04-13 09:53:40,469 | INFO | train_grpo_train | metrics_logged mode=train step=1014 2026-04-13 09:53:47,674 | INFO | train_grpo_train | metrics_logged mode=train step=1015 2026-04-13 09:53:54,255 | INFO | train_grpo_train | metrics_logged mode=train step=1016 2026-04-13 09:54:00,840 | INFO | train_grpo_train | metrics_logged mode=train step=1017 2026-04-13 09:54:07,270 | INFO | train_grpo_train | metrics_logged mode=train step=1018 2026-04-13 09:54:14,132 | INFO | train_grpo_train | metrics_logged mode=train step=1019 2026-04-13 09:54:20,654 | INFO | train_grpo_train | metrics_logged mode=train step=1020 2026-04-13 09:54:27,180 | INFO | train_grpo_train | metrics_logged mode=train step=1021 2026-04-13 09:54:33,158 | INFO | train_grpo_train | metrics_logged mode=train step=1022 2026-04-13 09:54:39,347 | INFO | train_grpo_train | metrics_logged mode=train step=1023 2026-04-13 09:54:44,960 | INFO | train_grpo_train | metrics_logged mode=train step=1024 2026-04-13 09:54:50,939 | INFO | train_grpo_train | metrics_logged mode=train step=1025 2026-04-13 09:54:56,858 | INFO | train_grpo_train | metrics_logged mode=train step=1026 2026-04-13 09:55:03,373 | INFO | train_grpo_train | metrics_logged mode=train step=1027 2026-04-13 09:55:09,780 | INFO | train_grpo_train | metrics_logged mode=train step=1028 2026-04-13 09:55:16,300 | INFO | train_grpo_train | metrics_logged mode=train step=1029 2026-04-13 09:55:22,341 | INFO | train_grpo_train | metrics_logged mode=train step=1030 2026-04-13 09:55:28,758 | INFO | train_grpo_train | metrics_logged mode=train step=1031 2026-04-13 09:55:40,024 | INFO | train_grpo_train | metrics_logged mode=train step=1032 2026-04-13 09:55:50,911 | INFO | train_grpo_train | metrics_logged mode=train step=1033 2026-04-13 09:55:57,068 | INFO | train_grpo_train | metrics_logged mode=train step=1034 2026-04-13 09:56:04,038 | INFO | train_grpo_train | metrics_logged mode=train step=1035 2026-04-13 09:56:10,422 | INFO | train_grpo_train | metrics_logged mode=train step=1036 2026-04-13 09:56:16,535 | INFO | train_grpo_train | metrics_logged mode=train step=1037 2026-04-13 09:56:29,913 | INFO | train_grpo_train | metrics_logged mode=train step=1038 2026-04-13 09:56:36,050 | INFO | train_grpo_train | metrics_logged mode=train step=1039 2026-04-13 09:56:42,322 | INFO | train_grpo_train | metrics_logged mode=train step=1040 2026-04-13 09:56:49,173 | INFO | train_grpo_train | metrics_logged mode=train step=1041 2026-04-13 09:56:55,551 | INFO | train_grpo_train | metrics_logged mode=train step=1042 2026-04-13 09:57:02,225 | INFO | train_grpo_train | metrics_logged mode=train step=1043 2026-04-13 09:57:08,076 | INFO | train_grpo_train | metrics_logged mode=train step=1044 2026-04-13 09:57:19,350 | INFO | train_grpo_train | metrics_logged mode=train step=1045 2026-04-13 09:57:30,775 | INFO | train_grpo_train | metrics_logged mode=train step=1046 2026-04-13 09:57:36,324 | INFO | train_grpo_train | metrics_logged mode=train step=1047 2026-04-13 09:57:47,495 | INFO | train_grpo_train | metrics_logged mode=train step=1048 2026-04-13 09:57:58,335 | INFO | train_grpo_train | metrics_logged mode=train step=1049 2026-04-13 09:58:09,413 | INFO | train_grpo_train | metrics_logged mode=train step=1050 2026-04-13 09:59:00,133 | INFO | train_grpo_train | metrics_logged mode=eval step=1050 2026-04-13 09:59:14,266 | INFO | train_grpo_train | metrics_logged mode=train step=1051 2026-04-13 09:59:21,287 | INFO | train_grpo_train | metrics_logged mode=train step=1052 2026-04-13 09:59:27,561 | INFO | train_grpo_train | metrics_logged mode=train step=1053 2026-04-13 09:59:38,649 | INFO | train_grpo_train | metrics_logged mode=train step=1054 2026-04-13 09:59:44,721 | INFO | train_grpo_train | metrics_logged mode=train step=1055 2026-04-13 09:59:56,046 | INFO | train_grpo_train | metrics_logged mode=train step=1056 2026-04-13 10:00:02,630 | INFO | train_grpo_train | metrics_logged mode=train step=1057 2026-04-13 10:00:09,998 | INFO | train_grpo_train | metrics_logged mode=train step=1058 2026-04-13 10:00:16,337 | INFO | train_grpo_train | metrics_logged mode=train step=1059 2026-04-13 10:00:22,592 | INFO | train_grpo_train | metrics_logged mode=train step=1060 2026-04-13 10:00:28,543 | INFO | train_grpo_train | metrics_logged mode=train step=1061 2026-04-13 10:00:34,774 | INFO | train_grpo_train | metrics_logged mode=train step=1062 2026-04-13 10:00:41,165 | INFO | train_grpo_train | metrics_logged mode=train step=1063 2026-04-13 10:00:49,759 | INFO | train_grpo_train | metrics_logged mode=train step=1064 2026-04-13 10:00:55,769 | INFO | train_grpo_train | metrics_logged mode=train step=1065 2026-04-13 10:01:10,630 | INFO | train_grpo_train | metrics_logged mode=train step=1066 2026-04-13 10:01:16,496 | INFO | train_grpo_train | metrics_logged mode=train step=1067 2026-04-13 10:01:22,937 | INFO | train_grpo_train | metrics_logged mode=train step=1068 2026-04-13 10:01:28,872 | INFO | train_grpo_train | metrics_logged mode=train step=1069 2026-04-13 10:01:34,845 | INFO | train_grpo_train | metrics_logged mode=train step=1070 2026-04-13 10:01:41,357 | INFO | train_grpo_train | metrics_logged mode=train step=1071 2026-04-13 10:01:47,556 | INFO | train_grpo_train | metrics_logged mode=train step=1072 2026-04-13 10:01:53,691 | INFO | train_grpo_train | metrics_logged mode=train step=1073 2026-04-13 10:01:59,899 | INFO | train_grpo_train | metrics_logged mode=train step=1074 2026-04-13 10:02:06,015 | INFO | train_grpo_train | metrics_logged mode=train step=1075 2026-04-13 10:02:12,289 | INFO | train_grpo_train | metrics_logged mode=train step=1076 2026-04-13 10:02:24,583 | INFO | train_grpo_train | metrics_logged mode=train step=1077 2026-04-13 10:02:35,658 | INFO | train_grpo_train | metrics_logged mode=train step=1078 2026-04-13 10:02:42,300 | INFO | train_grpo_train | metrics_logged mode=train step=1079 2026-04-13 10:02:48,222 | INFO | train_grpo_train | metrics_logged mode=train step=1080 2026-04-13 10:02:54,797 | INFO | train_grpo_train | metrics_logged mode=train step=1081 2026-04-13 10:03:00,897 | INFO | train_grpo_train | metrics_logged mode=train step=1082 2026-04-13 10:03:07,880 | INFO | train_grpo_train | metrics_logged mode=train step=1083 2026-04-13 10:03:14,955 | INFO | train_grpo_train | metrics_logged mode=train step=1084 2026-04-13 10:03:21,715 | INFO | train_grpo_train | metrics_logged mode=train step=1085 2026-04-13 10:03:28,475 | INFO | train_grpo_train | metrics_logged mode=train step=1086 2026-04-13 10:03:34,356 | INFO | train_grpo_train | metrics_logged mode=train step=1087 2026-04-13 10:03:41,167 | INFO | train_grpo_train | metrics_logged mode=train step=1088 2026-04-13 10:03:47,471 | INFO | train_grpo_train | metrics_logged mode=train step=1089 2026-04-13 10:03:53,362 | INFO | train_grpo_train | metrics_logged mode=train step=1090 2026-04-13 10:03:59,252 | INFO | train_grpo_train | metrics_logged mode=train step=1091 2026-04-13 10:04:06,010 | INFO | train_grpo_train | metrics_logged mode=train step=1092 2026-04-13 10:04:12,766 | INFO | train_grpo_train | metrics_logged mode=train step=1093 2026-04-13 10:04:23,729 | INFO | train_grpo_train | metrics_logged mode=train step=1094 2026-04-13 10:04:30,159 | INFO | train_grpo_train | metrics_logged mode=train step=1095 2026-04-13 10:04:36,945 | INFO | train_grpo_train | metrics_logged mode=train step=1096 2026-04-13 10:04:48,009 | INFO | train_grpo_train | metrics_logged mode=train step=1097 2026-04-13 10:04:53,930 | INFO | train_grpo_train | metrics_logged mode=train step=1098 2026-04-13 10:05:00,757 | INFO | train_grpo_train | metrics_logged mode=train step=1099 2026-04-13 10:05:06,975 | INFO | train_grpo_train | metrics_logged mode=train step=1100 2026-04-13 10:05:45,106 | INFO | train_grpo_train | metrics_logged mode=eval step=1100 2026-04-13 10:05:54,951 | INFO | train_grpo_train | metrics_logged mode=train step=1101 2026-04-13 10:06:01,689 | INFO | train_grpo_train | metrics_logged mode=train step=1102 2026-04-13 10:06:08,377 | INFO | train_grpo_train | metrics_logged mode=train step=1103 2026-04-13 10:06:15,701 | INFO | train_grpo_train | metrics_logged mode=train step=1104 2026-04-13 10:06:22,335 | INFO | train_grpo_train | metrics_logged mode=train step=1105 2026-04-13 10:06:28,059 | INFO | train_grpo_train | metrics_logged mode=train step=1106 2026-04-13 10:06:33,839 | INFO | train_grpo_train | metrics_logged mode=train step=1107 2026-04-13 10:06:39,666 | INFO | train_grpo_train | metrics_logged mode=train step=1108 2026-04-13 10:06:46,234 | INFO | train_grpo_train | metrics_logged mode=train step=1109 2026-04-13 10:06:52,713 | INFO | train_grpo_train | metrics_logged mode=train step=1110 2026-04-13 10:06:58,759 | INFO | train_grpo_train | metrics_logged mode=train step=1111 2026-04-13 10:07:05,064 | INFO | train_grpo_train | metrics_logged mode=train step=1112 2026-04-13 10:07:16,284 | INFO | train_grpo_train | metrics_logged mode=train step=1113 2026-04-13 10:07:22,962 | INFO | train_grpo_train | metrics_logged mode=train step=1114 2026-04-13 10:07:29,090 | INFO | train_grpo_train | metrics_logged mode=train step=1115 2026-04-13 10:07:35,078 | INFO | train_grpo_train | metrics_logged mode=train step=1116 2026-04-13 10:07:41,009 | INFO | train_grpo_train | metrics_logged mode=train step=1117 2026-04-13 10:07:47,861 | INFO | train_grpo_train | metrics_logged mode=train step=1118 2026-04-13 10:07:55,022 | INFO | train_grpo_train | metrics_logged mode=train step=1119 2026-04-13 10:08:02,117 | INFO | train_grpo_train | metrics_logged mode=train step=1120 2026-04-13 10:08:08,613 | INFO | train_grpo_train | metrics_logged mode=train step=1121 2026-04-13 10:08:15,249 | INFO | train_grpo_train | metrics_logged mode=train step=1122 2026-04-13 10:08:21,297 | INFO | train_grpo_train | metrics_logged mode=train step=1123 2026-04-13 10:08:28,108 | INFO | train_grpo_train | metrics_logged mode=train step=1124 2026-04-13 10:08:34,298 | INFO | train_grpo_train | metrics_logged mode=train step=1125 2026-04-13 10:08:40,447 | INFO | train_grpo_train | metrics_logged mode=train step=1126 2026-04-13 10:08:51,349 | INFO | train_grpo_train | metrics_logged mode=train step=1127 2026-04-13 10:09:02,753 | INFO | train_grpo_train | metrics_logged mode=train step=1128 2026-04-13 10:09:13,772 | INFO | train_grpo_train | metrics_logged mode=train step=1129 2026-04-13 10:09:19,722 | INFO | train_grpo_train | metrics_logged mode=train step=1130 2026-04-13 10:09:27,219 | INFO | train_grpo_train | metrics_logged mode=train step=1131 2026-04-13 10:09:33,865 | INFO | train_grpo_train | metrics_logged mode=train step=1132 2026-04-13 10:09:45,487 | INFO | train_grpo_train | metrics_logged mode=train step=1133 2026-04-13 10:09:51,860 | INFO | train_grpo_train | metrics_logged mode=train step=1134 2026-04-13 10:09:58,426 | INFO | train_grpo_train | metrics_logged mode=train step=1135 2026-04-13 10:10:04,445 | INFO | train_grpo_train | metrics_logged mode=train step=1136 2026-04-13 10:10:15,946 | INFO | train_grpo_train | metrics_logged mode=train step=1137 2026-04-13 10:10:21,884 | INFO | train_grpo_train | metrics_logged mode=train step=1138 2026-04-13 10:10:32,836 | INFO | train_grpo_train | metrics_logged mode=train step=1139 2026-04-13 10:10:45,051 | INFO | train_grpo_train | metrics_logged mode=train step=1140 2026-04-13 10:10:50,989 | INFO | train_grpo_train | metrics_logged mode=train step=1141 2026-04-13 10:11:01,012 | INFO | train_grpo_train | metrics_logged mode=train step=1142 2026-04-13 10:11:07,054 | INFO | train_grpo_train | metrics_logged mode=train step=1143 2026-04-13 10:11:13,592 | INFO | train_grpo_train | metrics_logged mode=train step=1144 2026-04-13 10:11:20,641 | INFO | train_grpo_train | metrics_logged mode=train step=1145 2026-04-13 10:11:26,708 | INFO | train_grpo_train | metrics_logged mode=train step=1146 2026-04-13 10:11:33,174 | INFO | train_grpo_train | metrics_logged mode=train step=1147 2026-04-13 10:11:38,990 | INFO | train_grpo_train | metrics_logged mode=train step=1148 2026-04-13 10:11:45,261 | INFO | train_grpo_train | metrics_logged mode=train step=1149 2026-04-13 10:11:51,949 | INFO | train_grpo_train | metrics_logged mode=train step=1150 2026-04-13 10:12:43,433 | INFO | train_grpo_train | metrics_logged mode=eval step=1150 2026-04-13 10:12:52,786 | INFO | train_grpo_train | metrics_logged mode=train step=1151 2026-04-13 10:12:59,442 | INFO | train_grpo_train | metrics_logged mode=train step=1152 2026-04-13 10:13:05,873 | INFO | train_grpo_train | metrics_logged mode=train step=1153 2026-04-13 10:13:17,625 | INFO | train_grpo_train | metrics_logged mode=train step=1154 2026-04-13 10:13:23,775 | INFO | train_grpo_train | metrics_logged mode=train step=1155 2026-04-13 10:13:31,234 | INFO | train_grpo_train | metrics_logged mode=train step=1156 2026-04-13 10:13:37,422 | INFO | train_grpo_train | metrics_logged mode=train step=1157 2026-04-13 10:13:48,642 | INFO | train_grpo_train | metrics_logged mode=train step=1158 2026-04-13 10:13:55,079 | INFO | train_grpo_train | metrics_logged mode=train step=1159 2026-04-13 10:14:01,810 | INFO | train_grpo_train | metrics_logged mode=train step=1160 2026-04-13 10:14:07,720 | INFO | train_grpo_train | metrics_logged mode=train step=1161 2026-04-13 10:14:14,187 | INFO | train_grpo_train | metrics_logged mode=train step=1162 2026-04-13 10:14:20,623 | INFO | train_grpo_train | metrics_logged mode=train step=1163 2026-04-13 10:14:26,325 | INFO | train_grpo_train | metrics_logged mode=train step=1164 2026-04-13 10:14:33,317 | INFO | train_grpo_train | metrics_logged mode=train step=1165 2026-04-13 10:14:40,014 | INFO | train_grpo_train | metrics_logged mode=train step=1166 2026-04-13 10:14:46,082 | INFO | train_grpo_train | metrics_logged mode=train step=1167 2026-04-13 10:14:52,330 | INFO | train_grpo_train | metrics_logged mode=train step=1168 2026-04-13 10:14:58,668 | INFO | train_grpo_train | metrics_logged mode=train step=1169 2026-04-13 10:15:05,291 | INFO | train_grpo_train | metrics_logged mode=train step=1170 2026-04-13 10:15:16,681 | INFO | train_grpo_train | metrics_logged mode=train step=1171 2026-04-13 10:15:24,024 | INFO | train_grpo_train | metrics_logged mode=train step=1172 2026-04-13 10:15:30,547 | INFO | train_grpo_train | metrics_logged mode=train step=1173 2026-04-13 10:15:37,212 | INFO | train_grpo_train | metrics_logged mode=train step=1174 2026-04-13 10:15:44,947 | INFO | train_grpo_train | metrics_logged mode=train step=1175 2026-04-13 10:15:51,238 | INFO | train_grpo_train | metrics_logged mode=train step=1176 2026-04-13 10:15:57,751 | INFO | train_grpo_train | metrics_logged mode=train step=1177 2026-04-13 10:16:04,383 | INFO | train_grpo_train | metrics_logged mode=train step=1178 2026-04-13 10:16:12,569 | INFO | train_grpo_train | metrics_logged mode=train step=1179 2026-04-13 10:16:18,606 | INFO | train_grpo_train | metrics_logged mode=train step=1180 2026-04-13 10:16:25,390 | INFO | train_grpo_train | metrics_logged mode=train step=1181 2026-04-13 10:16:31,937 | INFO | train_grpo_train | metrics_logged mode=train step=1182 2026-04-13 10:16:38,818 | INFO | train_grpo_train | metrics_logged mode=train step=1183 2026-04-13 10:16:45,523 | INFO | train_grpo_train | metrics_logged mode=train step=1184 2026-04-13 10:16:52,079 | INFO | train_grpo_train | metrics_logged mode=train step=1185 2026-04-13 10:17:03,426 | INFO | train_grpo_train | metrics_logged mode=train step=1186 2026-04-13 10:17:15,373 | INFO | train_grpo_train | metrics_logged mode=train step=1187 2026-04-13 10:17:21,694 | INFO | train_grpo_train | metrics_logged mode=train step=1188 2026-04-13 10:17:28,187 | INFO | train_grpo_train | metrics_logged mode=train step=1189 2026-04-13 10:17:34,453 | INFO | train_grpo_train | metrics_logged mode=train step=1190 2026-04-13 10:17:41,582 | INFO | train_grpo_train | metrics_logged mode=train step=1191 2026-04-13 10:17:48,150 | INFO | train_grpo_train | metrics_logged mode=train step=1192 2026-04-13 10:17:54,564 | INFO | train_grpo_train | metrics_logged mode=train step=1193 2026-04-13 10:18:00,377 | INFO | train_grpo_train | metrics_logged mode=train step=1194 2026-04-13 10:18:06,458 | INFO | train_grpo_train | metrics_logged mode=train step=1195 2026-04-13 10:18:12,745 | INFO | train_grpo_train | metrics_logged mode=train step=1196 2026-04-13 10:18:19,178 | INFO | train_grpo_train | metrics_logged mode=train step=1197 2026-04-13 10:18:25,519 | INFO | train_grpo_train | metrics_logged mode=train step=1198 2026-04-13 10:18:31,552 | INFO | train_grpo_train | metrics_logged mode=train step=1199 2026-04-13 10:18:37,701 | INFO | train_grpo_train | metrics_logged mode=train step=1200 2026-04-13 10:19:46,369 | INFO | train_grpo_train | metrics_logged mode=eval step=1200 2026-04-13 10:20:01,473 | INFO | train_grpo_train | metrics_logged mode=train step=1201 2026-04-13 10:20:07,351 | INFO | train_grpo_train | metrics_logged mode=train step=1202 2026-04-13 10:20:13,370 | INFO | train_grpo_train | metrics_logged mode=train step=1203 2026-04-13 10:20:24,456 | INFO | train_grpo_train | metrics_logged mode=train step=1204 2026-04-13 10:20:35,906 | INFO | train_grpo_train | metrics_logged mode=train step=1205 2026-04-13 10:20:42,628 | INFO | train_grpo_train | metrics_logged mode=train step=1206 2026-04-13 10:20:48,633 | INFO | train_grpo_train | metrics_logged mode=train step=1207 2026-04-13 10:21:00,401 | INFO | train_grpo_train | metrics_logged mode=train step=1208 2026-04-13 10:21:12,345 | INFO | train_grpo_train | metrics_logged mode=train step=1209 2026-04-13 10:21:18,175 | INFO | train_grpo_train | metrics_logged mode=train step=1210 2026-04-13 10:21:29,475 | INFO | train_grpo_train | metrics_logged mode=train step=1211 2026-04-13 10:21:36,297 | INFO | train_grpo_train | metrics_logged mode=train step=1212 2026-04-13 10:21:42,266 | INFO | train_grpo_train | metrics_logged mode=train step=1213 2026-04-13 10:21:53,584 | INFO | train_grpo_train | metrics_logged mode=train step=1214 2026-04-13 10:22:00,999 | INFO | train_grpo_train | metrics_logged mode=train step=1215 2026-04-13 10:22:07,288 | INFO | train_grpo_train | metrics_logged mode=train step=1216 2026-04-13 10:22:13,280 | INFO | train_grpo_train | metrics_logged mode=train step=1217 2026-04-13 10:22:19,932 | INFO | train_grpo_train | metrics_logged mode=train step=1218 2026-04-13 10:22:26,326 | INFO | train_grpo_train | metrics_logged mode=train step=1219 2026-04-13 10:22:33,255 | INFO | train_grpo_train | metrics_logged mode=train step=1220 2026-04-13 10:22:39,529 | INFO | train_grpo_train | metrics_logged mode=train step=1221 2026-04-13 10:22:46,257 | INFO | train_grpo_train | metrics_logged mode=train step=1222 2026-04-13 10:22:52,823 | INFO | train_grpo_train | metrics_logged mode=train step=1223 2026-04-13 10:22:59,412 | INFO | train_grpo_train | metrics_logged mode=train step=1224 2026-04-13 10:23:05,603 | INFO | train_grpo_train | metrics_logged mode=train step=1225 2026-04-13 10:23:11,735 | INFO | train_grpo_train | metrics_logged mode=train step=1226 2026-04-13 10:23:22,730 | INFO | train_grpo_train | metrics_logged mode=train step=1227 2026-04-13 10:23:28,807 | INFO | train_grpo_train | metrics_logged mode=train step=1228 2026-04-13 10:23:34,888 | INFO | train_grpo_train | metrics_logged mode=train step=1229 2026-04-13 10:23:46,385 | INFO | train_grpo_train | metrics_logged mode=train step=1230 2026-04-13 10:23:53,140 | INFO | train_grpo_train | metrics_logged mode=train step=1231 2026-04-13 10:24:04,541 | INFO | train_grpo_train | metrics_logged mode=train step=1232 2026-04-13 10:24:15,988 | INFO | train_grpo_train | metrics_logged mode=train step=1233 2026-04-13 10:24:22,105 | INFO | train_grpo_train | metrics_logged mode=train step=1234 2026-04-13 10:24:28,858 | INFO | train_grpo_train | metrics_logged mode=train step=1235 2026-04-13 10:24:35,557 | INFO | train_grpo_train | metrics_logged mode=train step=1236 2026-04-13 10:24:43,486 | INFO | train_grpo_train | metrics_logged mode=train step=1237 2026-04-13 10:24:50,002 | INFO | train_grpo_train | metrics_logged mode=train step=1238 2026-04-13 10:24:57,100 | INFO | train_grpo_train | metrics_logged mode=train step=1239 2026-04-13 10:25:03,325 | INFO | train_grpo_train | metrics_logged mode=train step=1240 2026-04-13 10:25:09,506 | INFO | train_grpo_train | metrics_logged mode=train step=1241 2026-04-13 10:25:20,456 | INFO | train_grpo_train | metrics_logged mode=train step=1242 2026-04-13 10:25:27,381 | INFO | train_grpo_train | metrics_logged mode=train step=1243 2026-04-13 10:25:38,848 | INFO | train_grpo_train | metrics_logged mode=train step=1244 2026-04-13 10:25:44,877 | INFO | train_grpo_train | metrics_logged mode=train step=1245 2026-04-13 10:25:50,640 | INFO | train_grpo_train | metrics_logged mode=train step=1246 2026-04-13 10:26:02,353 | INFO | train_grpo_train | metrics_logged mode=train step=1247 2026-04-13 10:26:09,678 | INFO | train_grpo_train | metrics_logged mode=train step=1248 2026-04-13 10:26:16,718 | INFO | train_grpo_train | metrics_logged mode=train step=1249 2026-04-13 10:26:23,679 | INFO | train_grpo_train | metrics_logged mode=train step=1250 2026-04-13 10:27:16,781 | INFO | train_grpo_train | metrics_logged mode=eval step=1250 2026-04-13 10:27:31,446 | INFO | train_grpo_train | metrics_logged mode=train step=1251 2026-04-13 10:27:43,056 | INFO | train_grpo_train | metrics_logged mode=train step=1252 2026-04-13 10:27:50,192 | INFO | train_grpo_train | metrics_logged mode=train step=1253 2026-04-13 10:28:01,722 | INFO | train_grpo_train | metrics_logged mode=train step=1254 2026-04-13 10:28:08,440 | INFO | train_grpo_train | metrics_logged mode=train step=1255 2026-04-13 10:28:15,009 | INFO | train_grpo_train | metrics_logged mode=train step=1256 2026-04-13 10:28:21,414 | INFO | train_grpo_train | metrics_logged mode=train step=1257 2026-04-13 10:28:27,726 | INFO | train_grpo_train | metrics_logged mode=train step=1258 2026-04-13 10:28:40,562 | INFO | train_grpo_train | metrics_logged mode=train step=1259 2026-04-13 10:28:48,195 | INFO | train_grpo_train | metrics_logged mode=train step=1260 2026-04-13 10:29:00,215 | INFO | train_grpo_train | metrics_logged mode=train step=1261 2026-04-13 10:29:11,697 | INFO | train_grpo_train | metrics_logged mode=train step=1262 2026-04-13 10:29:22,955 | INFO | train_grpo_train | metrics_logged mode=train step=1263 2026-04-13 10:29:29,975 | INFO | train_grpo_train | metrics_logged mode=train step=1264 2026-04-13 10:29:43,172 | INFO | train_grpo_train | metrics_logged mode=train step=1265 2026-04-13 10:29:54,307 | INFO | train_grpo_train | metrics_logged mode=train step=1266 2026-04-13 10:30:00,706 | INFO | train_grpo_train | metrics_logged mode=train step=1267 2026-04-13 10:30:12,586 | INFO | train_grpo_train | metrics_logged mode=train step=1268 2026-04-13 10:30:18,390 | INFO | train_grpo_train | metrics_logged mode=train step=1269 2026-04-13 10:30:25,172 | INFO | train_grpo_train | metrics_logged mode=train step=1270 2026-04-13 10:30:31,832 | INFO | train_grpo_train | metrics_logged mode=train step=1271 2026-04-13 10:30:38,590 | INFO | train_grpo_train | metrics_logged mode=train step=1272 2026-04-13 10:30:50,386 | INFO | train_grpo_train | metrics_logged mode=train step=1273 2026-04-13 10:30:58,952 | INFO | train_grpo_train | metrics_logged mode=train step=1274 2026-04-13 10:31:10,650 | INFO | train_grpo_train | metrics_logged mode=train step=1275 2026-04-13 10:31:18,202 | INFO | train_grpo_train | metrics_logged mode=train step=1276 2026-04-13 10:31:24,415 | INFO | train_grpo_train | metrics_logged mode=train step=1277 2026-04-13 10:31:30,613 | INFO | train_grpo_train | metrics_logged mode=train step=1278 2026-04-13 10:31:36,881 | INFO | train_grpo_train | metrics_logged mode=train step=1279 2026-04-13 10:31:42,886 | INFO | train_grpo_train | metrics_logged mode=train step=1280 2026-04-13 10:31:53,943 | INFO | train_grpo_train | metrics_logged mode=train step=1281 2026-04-13 10:32:00,895 | INFO | train_grpo_train | metrics_logged mode=train step=1282 2026-04-13 10:32:07,048 | INFO | train_grpo_train | metrics_logged mode=train step=1283 2026-04-13 10:32:13,749 | INFO | train_grpo_train | metrics_logged mode=train step=1284 2026-04-13 10:32:20,352 | INFO | train_grpo_train | metrics_logged mode=train step=1285 2026-04-13 10:32:26,589 | INFO | train_grpo_train | metrics_logged mode=train step=1286 2026-04-13 10:32:38,015 | INFO | train_grpo_train | metrics_logged mode=train step=1287 2026-04-13 10:32:49,369 | INFO | train_grpo_train | metrics_logged mode=train step=1288 2026-04-13 10:32:56,103 | INFO | train_grpo_train | metrics_logged mode=train step=1289 2026-04-13 10:33:07,155 | INFO | train_grpo_train | metrics_logged mode=train step=1290 2026-04-13 10:33:13,529 | INFO | train_grpo_train | metrics_logged mode=train step=1291 2026-04-13 10:33:24,640 | INFO | train_grpo_train | metrics_logged mode=train step=1292 2026-04-13 10:33:30,875 | INFO | train_grpo_train | metrics_logged mode=train step=1293 2026-04-13 10:33:37,019 | INFO | train_grpo_train | metrics_logged mode=train step=1294 2026-04-13 10:33:43,948 | INFO | train_grpo_train | metrics_logged mode=train step=1295 2026-04-13 10:33:49,883 | INFO | train_grpo_train | metrics_logged mode=train step=1296 2026-04-13 10:34:00,815 | INFO | train_grpo_train | metrics_logged mode=train step=1297 2026-04-13 10:34:12,163 | INFO | train_grpo_train | metrics_logged mode=train step=1298 2026-04-13 10:34:18,069 | INFO | train_grpo_train | metrics_logged mode=train step=1299 2026-04-13 10:34:29,135 | INFO | train_grpo_train | metrics_logged mode=train step=1300 2026-04-13 10:35:21,967 | INFO | train_grpo_train | metrics_logged mode=eval step=1300 2026-04-13 10:35:37,458 | INFO | train_grpo_train | metrics_logged mode=train step=1301 2026-04-13 10:35:44,459 | INFO | train_grpo_train | metrics_logged mode=train step=1302 2026-04-13 10:35:56,632 | INFO | train_grpo_train | metrics_logged mode=train step=1303 2026-04-13 10:36:03,815 | INFO | train_grpo_train | metrics_logged mode=train step=1304 2026-04-13 10:36:10,307 | INFO | train_grpo_train | metrics_logged mode=train step=1305 2026-04-13 10:36:17,443 | INFO | train_grpo_train | metrics_logged mode=train step=1306 2026-04-13 10:36:23,435 | INFO | train_grpo_train | metrics_logged mode=train step=1307 2026-04-13 10:36:29,954 | INFO | train_grpo_train | metrics_logged mode=train step=1308 2026-04-13 10:36:36,813 | INFO | train_grpo_train | metrics_logged mode=train step=1309 2026-04-13 10:36:47,996 | INFO | train_grpo_train | metrics_logged mode=train step=1310 2026-04-13 10:36:59,455 | INFO | train_grpo_train | metrics_logged mode=train step=1311 2026-04-13 10:37:06,039 | INFO | train_grpo_train | metrics_logged mode=train step=1312 2026-04-13 10:37:12,366 | INFO | train_grpo_train | metrics_logged mode=train step=1313 2026-04-13 10:37:18,710 | INFO | train_grpo_train | metrics_logged mode=train step=1314 2026-04-13 10:37:24,590 | INFO | train_grpo_train | metrics_logged mode=train step=1315 2026-04-13 10:37:35,743 | INFO | train_grpo_train | metrics_logged mode=train step=1316 2026-04-13 10:37:49,520 | INFO | train_grpo_train | metrics_logged mode=train step=1317 2026-04-13 10:37:55,721 | INFO | train_grpo_train | metrics_logged mode=train step=1318 2026-04-13 10:38:02,352 | INFO | train_grpo_train | metrics_logged mode=train step=1319 2026-04-13 10:38:10,003 | INFO | train_grpo_train | metrics_logged mode=train step=1320 2026-04-13 10:38:16,388 | INFO | train_grpo_train | metrics_logged mode=train step=1321 2026-04-13 10:38:23,291 | INFO | train_grpo_train | metrics_logged mode=train step=1322 2026-04-13 10:38:29,755 | INFO | train_grpo_train | metrics_logged mode=train step=1323 2026-04-13 10:38:36,236 | INFO | train_grpo_train | metrics_logged mode=train step=1324 2026-04-13 10:38:43,355 | INFO | train_grpo_train | metrics_logged mode=train step=1325 2026-04-13 10:38:49,666 | INFO | train_grpo_train | metrics_logged mode=train step=1326 2026-04-13 10:38:55,821 | INFO | train_grpo_train | metrics_logged mode=train step=1327 2026-04-13 10:39:02,450 | INFO | train_grpo_train | metrics_logged mode=train step=1328 2026-04-13 10:39:08,913 | INFO | train_grpo_train | metrics_logged mode=train step=1329 2026-04-13 10:39:20,481 | INFO | train_grpo_train | metrics_logged mode=train step=1330 2026-04-13 10:39:27,159 | INFO | train_grpo_train | metrics_logged mode=train step=1331 2026-04-13 10:39:33,611 | INFO | train_grpo_train | metrics_logged mode=train step=1332 2026-04-13 10:39:45,005 | INFO | train_grpo_train | metrics_logged mode=train step=1333 2026-04-13 10:39:52,033 | INFO | train_grpo_train | metrics_logged mode=train step=1334 2026-04-13 10:40:03,492 | INFO | train_grpo_train | metrics_logged mode=train step=1335 2026-04-13 10:40:10,376 | INFO | train_grpo_train | metrics_logged mode=train step=1336 2026-04-13 10:40:16,595 | INFO | train_grpo_train | metrics_logged mode=train step=1337 2026-04-13 10:40:22,689 | INFO | train_grpo_train | metrics_logged mode=train step=1338 2026-04-13 10:40:29,035 | INFO | train_grpo_train | metrics_logged mode=train step=1339 2026-04-13 10:40:37,339 | INFO | train_grpo_train | metrics_logged mode=train step=1340 2026-04-13 10:40:43,299 | INFO | train_grpo_train | metrics_logged mode=train step=1341 2026-04-13 10:40:49,551 | INFO | train_grpo_train | metrics_logged mode=train step=1342 2026-04-13 10:40:55,715 | INFO | train_grpo_train | metrics_logged mode=train step=1343 2026-04-13 10:41:01,760 | INFO | train_grpo_train | metrics_logged mode=train step=1344 2026-04-13 10:41:08,194 | INFO | train_grpo_train | metrics_logged mode=train step=1345 2026-04-13 10:41:14,802 | INFO | train_grpo_train | metrics_logged mode=train step=1346 2026-04-13 10:41:20,972 | INFO | train_grpo_train | metrics_logged mode=train step=1347 2026-04-13 10:41:26,677 | INFO | train_grpo_train | metrics_logged mode=train step=1348 2026-04-13 10:41:33,069 | INFO | train_grpo_train | metrics_logged mode=train step=1349 2026-04-13 10:41:39,159 | INFO | train_grpo_train | metrics_logged mode=train step=1350 2026-04-13 10:42:16,125 | INFO | train_grpo_train | metrics_logged mode=eval step=1350 2026-04-13 10:42:25,215 | INFO | train_grpo_train | metrics_logged mode=train step=1351 2026-04-13 10:42:31,975 | INFO | train_grpo_train | metrics_logged mode=train step=1352 2026-04-13 10:42:43,409 | INFO | train_grpo_train | metrics_logged mode=train step=1353 2026-04-13 10:42:52,993 | INFO | train_grpo_train | metrics_logged mode=train step=1354 2026-04-13 10:42:58,818 | INFO | train_grpo_train | metrics_logged mode=train step=1355 2026-04-13 10:43:04,810 | INFO | train_grpo_train | metrics_logged mode=train step=1356 2026-04-13 10:43:17,026 | INFO | train_grpo_train | metrics_logged mode=train step=1357 2026-04-13 10:43:28,347 | INFO | train_grpo_train | metrics_logged mode=train step=1358 2026-04-13 10:43:33,955 | INFO | train_grpo_train | metrics_logged mode=train step=1359 2026-04-13 10:43:39,750 | INFO | train_grpo_train | metrics_logged mode=train step=1360 2026-04-13 10:43:46,051 | INFO | train_grpo_train | metrics_logged mode=train step=1361 2026-04-13 10:43:52,630 | INFO | train_grpo_train | metrics_logged mode=train step=1362 2026-04-13 10:43:59,205 | INFO | train_grpo_train | metrics_logged mode=train step=1363 2026-04-13 10:44:05,219 | INFO | train_grpo_train | metrics_logged mode=train step=1364 2026-04-13 10:44:11,200 | INFO | train_grpo_train | metrics_logged mode=train step=1365 2026-04-13 10:44:17,334 | INFO | train_grpo_train | metrics_logged mode=train step=1366 2026-04-13 10:44:23,975 | INFO | train_grpo_train | metrics_logged mode=train step=1367 2026-04-13 10:44:30,505 | INFO | train_grpo_train | metrics_logged mode=train step=1368 2026-04-13 10:44:42,254 | INFO | train_grpo_train | metrics_logged mode=train step=1369 2026-04-13 10:44:49,280 | INFO | train_grpo_train | metrics_logged mode=train step=1370 2026-04-13 10:44:54,975 | INFO | train_grpo_train | metrics_logged mode=train step=1371 2026-04-13 10:45:00,955 | INFO | train_grpo_train | metrics_logged mode=train step=1372 2026-04-13 10:45:07,625 | INFO | train_grpo_train | metrics_logged mode=train step=1373 2026-04-13 10:45:14,586 | INFO | train_grpo_train | metrics_logged mode=train step=1374 2026-04-13 10:45:21,557 | INFO | train_grpo_train | metrics_logged mode=train step=1375 2026-04-13 10:45:32,580 | INFO | train_grpo_train | metrics_logged mode=train step=1376 2026-04-13 10:45:44,043 | INFO | train_grpo_train | metrics_logged mode=train step=1377 2026-04-13 10:45:55,417 | INFO | train_grpo_train | metrics_logged mode=train step=1378 2026-04-13 10:46:01,228 | INFO | train_grpo_train | metrics_logged mode=train step=1379 2026-04-13 10:46:08,029 | INFO | train_grpo_train | metrics_logged mode=train step=1380 2026-04-13 10:46:14,441 | INFO | train_grpo_train | metrics_logged mode=train step=1381 2026-04-13 10:46:21,057 | INFO | train_grpo_train | metrics_logged mode=train step=1382 2026-04-13 10:46:28,267 | INFO | train_grpo_train | metrics_logged mode=train step=1383 2026-04-13 10:46:40,438 | INFO | train_grpo_train | metrics_logged mode=train step=1384 2026-04-13 10:46:46,631 | INFO | train_grpo_train | metrics_logged mode=train step=1385 2026-04-13 10:46:53,722 | INFO | train_grpo_train | metrics_logged mode=train step=1386 2026-04-13 10:47:05,054 | INFO | train_grpo_train | metrics_logged mode=train step=1387 2026-04-13 10:47:11,620 | INFO | train_grpo_train | metrics_logged mode=train step=1388 2026-04-13 10:47:22,553 | INFO | train_grpo_train | metrics_logged mode=train step=1389 2026-04-13 10:47:28,406 | INFO | train_grpo_train | metrics_logged mode=train step=1390 2026-04-13 10:47:34,697 | INFO | train_grpo_train | metrics_logged mode=train step=1391 2026-04-13 10:47:40,349 | INFO | train_grpo_train | metrics_logged mode=train step=1392 2026-04-13 10:47:46,406 | INFO | train_grpo_train | metrics_logged mode=train step=1393 2026-04-13 10:47:52,708 | INFO | train_grpo_train | metrics_logged mode=train step=1394 2026-04-13 10:47:58,855 | INFO | train_grpo_train | metrics_logged mode=train step=1395 2026-04-13 10:48:05,758 | INFO | train_grpo_train | metrics_logged mode=train step=1396 2026-04-13 10:48:12,380 | INFO | train_grpo_train | metrics_logged mode=train step=1397 2026-04-13 10:48:18,583 | INFO | train_grpo_train | metrics_logged mode=train step=1398 2026-04-13 10:48:24,971 | INFO | train_grpo_train | metrics_logged mode=train step=1399 2026-04-13 10:48:35,541 | INFO | train_grpo_train | metrics_logged mode=train step=1400 2026-04-13 10:49:13,707 | INFO | train_grpo_train | metrics_logged mode=eval step=1400 2026-04-13 10:49:22,970 | INFO | train_grpo_train | metrics_logged mode=train step=1401 2026-04-13 10:49:30,020 | INFO | train_grpo_train | metrics_logged mode=train step=1402 2026-04-13 10:49:36,305 | INFO | train_grpo_train | metrics_logged mode=train step=1403 2026-04-13 10:49:44,130 | INFO | train_grpo_train | metrics_logged mode=train step=1404 2026-04-13 10:49:50,619 | INFO | train_grpo_train | metrics_logged mode=train step=1405 2026-04-13 10:49:57,123 | INFO | train_grpo_train | metrics_logged mode=train step=1406 2026-04-13 10:50:02,912 | INFO | train_grpo_train | metrics_logged mode=train step=1407 2026-04-13 10:50:09,205 | INFO | train_grpo_train | metrics_logged mode=train step=1408 2026-04-13 10:50:16,147 | INFO | train_grpo_train | metrics_logged mode=train step=1409 2026-04-13 10:50:22,946 | INFO | train_grpo_train | metrics_logged mode=train step=1410 2026-04-13 10:50:29,723 | INFO | train_grpo_train | metrics_logged mode=train step=1411 2026-04-13 10:50:36,727 | INFO | train_grpo_train | metrics_logged mode=train step=1412 2026-04-13 10:50:44,482 | INFO | train_grpo_train | metrics_logged mode=train step=1413 2026-04-13 10:50:50,843 | INFO | train_grpo_train | metrics_logged mode=train step=1414 2026-04-13 10:50:57,190 | INFO | train_grpo_train | metrics_logged mode=train step=1415 2026-04-13 10:51:03,430 | INFO | train_grpo_train | metrics_logged mode=train step=1416 2026-04-13 10:51:09,358 | INFO | train_grpo_train | metrics_logged mode=train step=1417 2026-04-13 10:51:15,589 | INFO | train_grpo_train | metrics_logged mode=train step=1418 2026-04-13 10:51:21,500 | INFO | train_grpo_train | metrics_logged mode=train step=1419 2026-04-13 10:51:27,568 | INFO | train_grpo_train | metrics_logged mode=train step=1420 2026-04-13 10:51:33,864 | INFO | train_grpo_train | metrics_logged mode=train step=1421 2026-04-13 10:51:40,399 | INFO | train_grpo_train | metrics_logged mode=train step=1422 2026-04-13 10:51:47,537 | INFO | train_grpo_train | metrics_logged mode=train step=1423 2026-04-13 10:51:54,092 | INFO | train_grpo_train | metrics_logged mode=train step=1424 2026-04-13 10:52:01,048 | INFO | train_grpo_train | metrics_logged mode=train step=1425 2026-04-13 10:52:08,479 | INFO | train_grpo_train | metrics_logged mode=train step=1426 2026-04-13 10:52:19,873 | INFO | train_grpo_train | metrics_logged mode=train step=1427 2026-04-13 10:52:27,195 | INFO | train_grpo_train | metrics_logged mode=train step=1428 2026-04-13 10:52:34,033 | INFO | train_grpo_train | metrics_logged mode=train step=1429 2026-04-13 10:52:40,380 | INFO | train_grpo_train | metrics_logged mode=train step=1430 2026-04-13 10:52:46,329 | INFO | train_grpo_train | metrics_logged mode=train step=1431 2026-04-13 10:52:57,718 | INFO | train_grpo_train | metrics_logged mode=train step=1432 2026-04-13 10:53:04,021 | INFO | train_grpo_train | metrics_logged mode=train step=1433 2026-04-13 10:53:10,176 | INFO | train_grpo_train | metrics_logged mode=train step=1434 2026-04-13 10:53:16,458 | INFO | train_grpo_train | metrics_logged mode=train step=1435 2026-04-13 10:53:22,087 | INFO | train_grpo_train | metrics_logged mode=train step=1436 2026-04-13 10:53:28,093 | INFO | train_grpo_train | metrics_logged mode=train step=1437 2026-04-13 10:53:34,940 | INFO | train_grpo_train | metrics_logged mode=train step=1438 2026-04-13 10:53:41,482 | INFO | train_grpo_train | metrics_logged mode=train step=1439 2026-04-13 10:53:49,193 | INFO | train_grpo_train | metrics_logged mode=train step=1440 2026-04-13 10:54:00,360 | INFO | train_grpo_train | metrics_logged mode=train step=1441 2026-04-13 10:54:06,440 | INFO | train_grpo_train | metrics_logged mode=train step=1442 2026-04-13 10:54:17,604 | INFO | train_grpo_train | metrics_logged mode=train step=1443 2026-04-13 10:54:24,925 | INFO | train_grpo_train | metrics_logged mode=train step=1444 2026-04-13 10:54:31,136 | INFO | train_grpo_train | metrics_logged mode=train step=1445 2026-04-13 10:54:36,924 | INFO | train_grpo_train | metrics_logged mode=train step=1446 2026-04-13 10:54:42,873 | INFO | train_grpo_train | metrics_logged mode=train step=1447 2026-04-13 10:54:48,721 | INFO | train_grpo_train | metrics_logged mode=train step=1448 2026-04-13 10:54:55,277 | INFO | train_grpo_train | metrics_logged mode=train step=1449 2026-04-13 10:55:02,431 | INFO | train_grpo_train | metrics_logged mode=train step=1450 2026-04-13 10:55:40,133 | INFO | train_grpo_train | metrics_logged mode=eval step=1450 2026-04-13 10:55:48,887 | INFO | train_grpo_train | metrics_logged mode=train step=1451 2026-04-13 10:55:54,506 | INFO | train_grpo_train | metrics_logged mode=train step=1452 2026-04-13 10:56:00,670 | INFO | train_grpo_train | metrics_logged mode=train step=1453 2026-04-13 10:56:08,070 | INFO | train_grpo_train | metrics_logged mode=train step=1454 2026-04-13 10:56:14,640 | INFO | train_grpo_train | metrics_logged mode=train step=1455 2026-04-13 10:56:21,095 | INFO | train_grpo_train | metrics_logged mode=train step=1456 2026-04-13 10:56:28,174 | INFO | train_grpo_train | metrics_logged mode=train step=1457 2026-04-13 10:56:34,734 | INFO | train_grpo_train | metrics_logged mode=train step=1458 2026-04-13 10:56:40,675 | INFO | train_grpo_train | metrics_logged mode=train step=1459 2026-04-13 10:56:47,688 | INFO | train_grpo_train | metrics_logged mode=train step=1460 2026-04-13 10:56:54,267 | INFO | train_grpo_train | metrics_logged mode=train step=1461 2026-04-13 10:57:00,311 | INFO | train_grpo_train | metrics_logged mode=train step=1462 2026-04-13 10:57:06,724 | INFO | train_grpo_train | metrics_logged mode=train step=1463 2026-04-13 10:57:13,931 | INFO | train_grpo_train | metrics_logged mode=train step=1464 2026-04-13 10:57:19,909 | INFO | train_grpo_train | metrics_logged mode=train step=1465 2026-04-13 10:57:26,481 | INFO | train_grpo_train | metrics_logged mode=train step=1466 2026-04-13 10:57:33,285 | INFO | train_grpo_train | metrics_logged mode=train step=1467 2026-04-13 10:57:39,584 | INFO | train_grpo_train | metrics_logged mode=train step=1468 2026-04-13 10:57:47,129 | INFO | train_grpo_train | metrics_logged mode=train step=1469 2026-04-13 10:57:54,244 | INFO | train_grpo_train | metrics_logged mode=train step=1470 2026-04-13 10:58:00,285 | INFO | train_grpo_train | metrics_logged mode=train step=1471 2026-04-13 10:58:06,701 | INFO | train_grpo_train | metrics_logged mode=train step=1472 2026-04-13 10:58:12,726 | INFO | train_grpo_train | metrics_logged mode=train step=1473 2026-04-13 10:58:19,481 | INFO | train_grpo_train | metrics_logged mode=train step=1474 2026-04-13 10:58:27,127 | INFO | train_grpo_train | metrics_logged mode=train step=1475 2026-04-13 10:58:38,904 | INFO | train_grpo_train | metrics_logged mode=train step=1476 2026-04-13 10:58:46,469 | INFO | train_grpo_train | metrics_logged mode=train step=1477 2026-04-13 10:58:57,899 | INFO | train_grpo_train | metrics_logged mode=train step=1478 2026-04-13 10:59:04,028 | INFO | train_grpo_train | metrics_logged mode=train step=1479 2026-04-13 10:59:11,286 | INFO | train_grpo_train | metrics_logged mode=train step=1480 2026-04-13 10:59:18,787 | INFO | train_grpo_train | metrics_logged mode=train step=1481 2026-04-13 10:59:24,926 | INFO | train_grpo_train | metrics_logged mode=train step=1482 2026-04-13 10:59:30,681 | INFO | train_grpo_train | metrics_logged mode=train step=1483 2026-04-13 10:59:37,335 | INFO | train_grpo_train | metrics_logged mode=train step=1484 2026-04-13 10:59:44,368 | INFO | train_grpo_train | metrics_logged mode=train step=1485 2026-04-13 10:59:50,954 | INFO | train_grpo_train | metrics_logged mode=train step=1486 2026-04-13 10:59:58,626 | INFO | train_grpo_train | metrics_logged mode=train step=1487 2026-04-13 11:00:05,280 | INFO | train_grpo_train | metrics_logged mode=train step=1488 2026-04-13 11:00:12,098 | INFO | train_grpo_train | metrics_logged mode=train step=1489 2026-04-13 11:00:18,401 | INFO | train_grpo_train | metrics_logged mode=train step=1490 2026-04-13 11:00:24,200 | INFO | train_grpo_train | metrics_logged mode=train step=1491 2026-04-13 11:00:35,418 | INFO | train_grpo_train | metrics_logged mode=train step=1492 2026-04-13 11:00:42,688 | INFO | train_grpo_train | metrics_logged mode=train step=1493 2026-04-13 11:00:49,023 | INFO | train_grpo_train | metrics_logged mode=train step=1494 2026-04-13 11:00:55,287 | INFO | train_grpo_train | metrics_logged mode=train step=1495 2026-04-13 11:01:08,770 | INFO | train_grpo_train | metrics_logged mode=train step=1496 2026-04-13 11:01:14,620 | INFO | train_grpo_train | metrics_logged mode=train step=1497 2026-04-13 11:01:20,668 | INFO | train_grpo_train | metrics_logged mode=train step=1498 2026-04-13 11:01:27,618 | INFO | train_grpo_train | metrics_logged mode=train step=1499 2026-04-13 11:01:34,270 | INFO | train_grpo_train | metrics_logged mode=train step=1500 2026-04-13 11:02:19,335 | INFO | train_grpo_train | metrics_logged mode=eval step=1500 2026-04-13 11:02:34,577 | INFO | train_grpo_train | metrics_logged mode=train step=1501 2026-04-13 11:02:41,046 | INFO | train_grpo_train | metrics_logged mode=train step=1502 2026-04-13 11:02:47,939 | INFO | train_grpo_train | metrics_logged mode=train step=1503 2026-04-13 11:02:55,096 | INFO | train_grpo_train | metrics_logged mode=train step=1504 2026-04-13 11:03:01,296 | INFO | train_grpo_train | metrics_logged mode=train step=1505 2026-04-13 11:03:08,547 | INFO | train_grpo_train | metrics_logged mode=train step=1506 2026-04-13 11:03:16,852 | INFO | train_grpo_train | metrics_logged mode=train step=1507 2026-04-13 11:03:22,903 | INFO | train_grpo_train | metrics_logged mode=train step=1508 2026-04-13 11:03:29,616 | INFO | train_grpo_train | metrics_logged mode=train step=1509 2026-04-13 11:03:35,722 | INFO | train_grpo_train | metrics_logged mode=train step=1510 2026-04-13 11:03:46,718 | INFO | train_grpo_train | metrics_logged mode=train step=1511 2026-04-13 11:03:52,755 | INFO | train_grpo_train | metrics_logged mode=train step=1512 2026-04-13 11:04:03,909 | INFO | train_grpo_train | metrics_logged mode=train step=1513 2026-04-13 11:04:10,171 | INFO | train_grpo_train | metrics_logged mode=train step=1514 2026-04-13 11:04:16,117 | INFO | train_grpo_train | metrics_logged mode=train step=1515 2026-04-13 11:04:21,978 | INFO | train_grpo_train | metrics_logged mode=train step=1516 2026-04-13 11:04:27,747 | INFO | train_grpo_train | metrics_logged mode=train step=1517 2026-04-13 11:04:34,608 | INFO | train_grpo_train | metrics_logged mode=train step=1518 2026-04-13 11:04:41,332 | INFO | train_grpo_train | metrics_logged mode=train step=1519 2026-04-13 11:04:48,807 | INFO | train_grpo_train | metrics_logged mode=train step=1520 2026-04-13 11:04:54,951 | INFO | train_grpo_train | metrics_logged mode=train step=1521 2026-04-13 11:05:00,925 | INFO | train_grpo_train | metrics_logged mode=train step=1522 2026-04-13 11:05:06,864 | INFO | train_grpo_train | metrics_logged mode=train step=1523 2026-04-13 11:05:14,145 | INFO | train_grpo_train | metrics_logged mode=train step=1524 2026-04-13 11:05:20,242 | INFO | train_grpo_train | metrics_logged mode=train step=1525 2026-04-13 11:05:26,999 | INFO | train_grpo_train | metrics_logged mode=train step=1526 2026-04-13 11:05:33,826 | INFO | train_grpo_train | metrics_logged mode=train step=1527 2026-04-13 11:05:40,751 | INFO | train_grpo_train | metrics_logged mode=train step=1528 2026-04-13 11:05:48,233 | INFO | train_grpo_train | metrics_logged mode=train step=1529 2026-04-13 11:05:59,918 | INFO | train_grpo_train | metrics_logged mode=train step=1530 2026-04-13 11:06:06,359 | INFO | train_grpo_train | metrics_logged mode=train step=1531 2026-04-13 11:06:12,622 | INFO | train_grpo_train | metrics_logged mode=train step=1532 2026-04-13 11:06:19,063 | INFO | train_grpo_train | metrics_logged mode=train step=1533 2026-04-13 11:06:25,639 | INFO | train_grpo_train | metrics_logged mode=train step=1534 2026-04-13 11:06:32,121 | INFO | train_grpo_train | metrics_logged mode=train step=1535 2026-04-13 11:06:38,876 | INFO | train_grpo_train | metrics_logged mode=train step=1536 2026-04-13 11:06:46,255 | INFO | train_grpo_train | metrics_logged mode=train step=1537 2026-04-13 11:06:52,986 | INFO | train_grpo_train | metrics_logged mode=train step=1538 2026-04-13 11:06:59,333 | INFO | train_grpo_train | metrics_logged mode=train step=1539 2026-04-13 11:07:07,342 | INFO | train_grpo_train | metrics_logged mode=train step=1540 2026-04-13 11:07:18,769 | INFO | train_grpo_train | metrics_logged mode=train step=1541 2026-04-13 11:07:24,988 | INFO | train_grpo_train | metrics_logged mode=train step=1542 2026-04-13 11:07:32,909 | INFO | train_grpo_train | metrics_logged mode=train step=1543 2026-04-13 11:07:39,827 | INFO | train_grpo_train | metrics_logged mode=train step=1544 2026-04-13 11:07:46,467 | INFO | train_grpo_train | metrics_logged mode=train step=1545 2026-04-13 11:07:57,683 | INFO | train_grpo_train | metrics_logged mode=train step=1546 2026-04-13 11:08:05,528 | INFO | train_grpo_train | metrics_logged mode=train step=1547 2026-04-13 11:08:13,123 | INFO | train_grpo_train | metrics_logged mode=train step=1548 2026-04-13 11:08:19,215 | INFO | train_grpo_train | metrics_logged mode=train step=1549 2026-04-13 11:08:25,268 | INFO | train_grpo_train | metrics_logged mode=train step=1550 2026-04-13 11:09:20,704 | INFO | train_grpo_train | metrics_logged mode=eval step=1550 2026-04-13 11:09:31,235 | INFO | train_grpo_train | metrics_logged mode=train step=1551 2026-04-13 11:09:37,352 | INFO | train_grpo_train | metrics_logged mode=train step=1552 2026-04-13 11:09:44,177 | INFO | train_grpo_train | metrics_logged mode=train step=1553 2026-04-13 11:09:50,124 | INFO | train_grpo_train | metrics_logged mode=train step=1554 2026-04-13 11:09:57,074 | INFO | train_grpo_train | metrics_logged mode=train step=1555 2026-04-13 11:10:04,639 | INFO | train_grpo_train | metrics_logged mode=train step=1556 2026-04-13 11:10:16,369 | INFO | train_grpo_train | metrics_logged mode=train step=1557 2026-04-13 11:10:27,675 | INFO | train_grpo_train | metrics_logged mode=train step=1558 2026-04-13 11:10:34,024 | INFO | train_grpo_train | metrics_logged mode=train step=1559 2026-04-13 11:10:45,672 | INFO | train_grpo_train | metrics_logged mode=train step=1560 2026-04-13 11:10:52,079 | INFO | train_grpo_train | metrics_logged mode=train step=1561 2026-04-13 11:10:59,241 | INFO | train_grpo_train | metrics_logged mode=train step=1562 2026-04-13 11:11:06,538 | INFO | train_grpo_train | metrics_logged mode=train step=1563 2026-04-13 11:11:12,584 | INFO | train_grpo_train | metrics_logged mode=train step=1564 2026-04-13 11:11:19,551 | INFO | train_grpo_train | metrics_logged mode=train step=1565 2026-04-13 11:11:25,937 | INFO | train_grpo_train | metrics_logged mode=train step=1566 2026-04-13 11:11:32,568 | INFO | train_grpo_train | metrics_logged mode=train step=1567 2026-04-13 11:11:38,881 | INFO | train_grpo_train | metrics_logged mode=train step=1568 2026-04-13 11:11:46,297 | INFO | train_grpo_train | metrics_logged mode=train step=1569 2026-04-13 11:11:53,874 | INFO | train_grpo_train | metrics_logged mode=train step=1570 2026-04-13 11:12:00,365 | INFO | train_grpo_train | metrics_logged mode=train step=1571 2026-04-13 11:12:06,953 | INFO | train_grpo_train | metrics_logged mode=train step=1572 2026-04-13 11:12:13,780 | INFO | train_grpo_train | metrics_logged mode=train step=1573 2026-04-13 11:12:20,576 | INFO | train_grpo_train | metrics_logged mode=train step=1574 2026-04-13 11:12:32,024 | INFO | train_grpo_train | metrics_logged mode=train step=1575 2026-04-13 11:12:38,813 | INFO | train_grpo_train | metrics_logged mode=train step=1576 2026-04-13 11:12:45,661 | INFO | train_grpo_train | metrics_logged mode=train step=1577 2026-04-13 11:12:57,560 | INFO | train_grpo_train | metrics_logged mode=train step=1578 2026-04-13 11:13:04,866 | INFO | train_grpo_train | metrics_logged mode=train step=1579 2026-04-13 11:13:12,188 | INFO | train_grpo_train | metrics_logged mode=train step=1580 2026-04-13 11:13:18,893 | INFO | train_grpo_train | metrics_logged mode=train step=1581 2026-04-13 11:13:25,993 | INFO | train_grpo_train | metrics_logged mode=train step=1582 2026-04-13 11:13:32,244 | INFO | train_grpo_train | metrics_logged mode=train step=1583 2026-04-13 11:13:44,979 | INFO | train_grpo_train | metrics_logged mode=train step=1584 2026-04-13 11:13:52,047 | INFO | train_grpo_train | metrics_logged mode=train step=1585 2026-04-13 11:13:58,353 | INFO | train_grpo_train | metrics_logged mode=train step=1586 2026-04-13 11:14:04,224 | INFO | train_grpo_train | metrics_logged mode=train step=1587 2026-04-13 11:14:15,433 | INFO | train_grpo_train | metrics_logged mode=train step=1588 2026-04-13 11:14:21,865 | INFO | train_grpo_train | metrics_logged mode=train step=1589 2026-04-13 11:14:28,937 | INFO | train_grpo_train | metrics_logged mode=train step=1590 2026-04-13 11:14:34,611 | INFO | train_grpo_train | metrics_logged mode=train step=1591 2026-04-13 11:14:40,808 | INFO | train_grpo_train | metrics_logged mode=train step=1592 2026-04-13 11:14:47,510 | INFO | train_grpo_train | metrics_logged mode=train step=1593 2026-04-13 11:14:56,387 | INFO | train_grpo_train | metrics_logged mode=train step=1594 2026-04-13 11:15:10,940 | INFO | train_grpo_train | metrics_logged mode=train step=1595 2026-04-13 11:15:23,206 | INFO | train_grpo_train | metrics_logged mode=train step=1596 2026-04-13 11:15:31,980 | INFO | train_grpo_train | metrics_logged mode=train step=1597 2026-04-13 11:15:39,552 | INFO | train_grpo_train | metrics_logged mode=train step=1598 2026-04-13 11:15:47,149 | INFO | train_grpo_train | metrics_logged mode=train step=1599 2026-04-13 11:15:59,082 | INFO | train_grpo_train | metrics_logged mode=train step=1600 2026-04-13 11:16:55,181 | INFO | train_grpo_train | metrics_logged mode=eval step=1600 2026-04-13 11:17:09,559 | INFO | train_grpo_train | metrics_logged mode=train step=1601 2026-04-13 11:17:21,333 | INFO | train_grpo_train | metrics_logged mode=train step=1602 2026-04-13 11:17:27,844 | INFO | train_grpo_train | metrics_logged mode=train step=1603 2026-04-13 11:17:34,211 | INFO | train_grpo_train | metrics_logged mode=train step=1604 2026-04-13 11:17:41,428 | INFO | train_grpo_train | metrics_logged mode=train step=1605 2026-04-13 11:17:47,786 | INFO | train_grpo_train | metrics_logged mode=train step=1606 2026-04-13 11:17:53,982 | INFO | train_grpo_train | metrics_logged mode=train step=1607 2026-04-13 11:18:01,452 | INFO | train_grpo_train | metrics_logged mode=train step=1608 2026-04-13 11:18:12,270 | INFO | train_grpo_train | metrics_logged mode=train step=1609 2026-04-13 11:18:23,798 | INFO | train_grpo_train | metrics_logged mode=train step=1610 2026-04-13 11:18:29,682 | INFO | train_grpo_train | metrics_logged mode=train step=1611 2026-04-13 11:18:36,877 | INFO | train_grpo_train | metrics_logged mode=train step=1612 2026-04-13 11:18:49,319 | INFO | train_grpo_train | metrics_logged mode=train step=1613 2026-04-13 11:19:00,532 | INFO | train_grpo_train | metrics_logged mode=train step=1614 2026-04-13 11:19:06,993 | INFO | train_grpo_train | metrics_logged mode=train step=1615 2026-04-13 11:19:12,910 | INFO | train_grpo_train | metrics_logged mode=train step=1616 2026-04-13 11:19:19,413 | INFO | train_grpo_train | metrics_logged mode=train step=1617 2026-04-13 11:19:25,159 | INFO | train_grpo_train | metrics_logged mode=train step=1618 2026-04-13 11:19:36,516 | INFO | train_grpo_train | metrics_logged mode=train step=1619 2026-04-13 11:19:44,518 | INFO | train_grpo_train | metrics_logged mode=train step=1620 2026-04-13 11:19:57,548 | INFO | train_grpo_train | metrics_logged mode=train step=1621 2026-04-13 11:20:03,534 | INFO | train_grpo_train | metrics_logged mode=train step=1622 2026-04-13 11:20:09,424 | INFO | train_grpo_train | metrics_logged mode=train step=1623 2026-04-13 11:20:16,284 | INFO | train_grpo_train | metrics_logged mode=train step=1624 2026-04-13 11:20:22,660 | INFO | train_grpo_train | metrics_logged mode=train step=1625 2026-04-13 11:20:29,968 | INFO | train_grpo_train | metrics_logged mode=train step=1626 2026-04-13 11:20:36,351 | INFO | train_grpo_train | metrics_logged mode=train step=1627 2026-04-13 11:20:42,550 | INFO | train_grpo_train | metrics_logged mode=train step=1628 2026-04-13 11:20:49,191 | INFO | train_grpo_train | metrics_logged mode=train step=1629 2026-04-13 11:20:57,460 | INFO | train_grpo_train | metrics_logged mode=train step=1630 2026-04-13 11:21:03,567 | INFO | train_grpo_train | metrics_logged mode=train step=1631 2026-04-13 11:21:09,741 | INFO | train_grpo_train | metrics_logged mode=train step=1632 2026-04-13 11:21:15,954 | INFO | train_grpo_train | metrics_logged mode=train step=1633 2026-04-13 11:21:28,524 | INFO | train_grpo_train | metrics_logged mode=train step=1634 2026-04-13 11:21:38,031 | INFO | train_grpo_train | metrics_logged mode=train step=1635 2026-04-13 11:21:44,413 | INFO | train_grpo_train | metrics_logged mode=train step=1636 2026-04-13 11:21:53,180 | INFO | train_grpo_train | metrics_logged mode=train step=1637 2026-04-13 11:22:04,519 | INFO | train_grpo_train | metrics_logged mode=train step=1638 2026-04-13 11:22:15,588 | INFO | train_grpo_train | metrics_logged mode=train step=1639 2026-04-13 11:22:21,759 | INFO | train_grpo_train | metrics_logged mode=train step=1640 2026-04-13 11:22:29,412 | INFO | train_grpo_train | metrics_logged mode=train step=1641 2026-04-13 11:22:41,355 | INFO | train_grpo_train | metrics_logged mode=train step=1642 2026-04-13 11:22:53,249 | INFO | train_grpo_train | metrics_logged mode=train step=1643 2026-04-13 11:22:59,946 | INFO | train_grpo_train | metrics_logged mode=train step=1644 2026-04-13 11:23:07,055 | INFO | train_grpo_train | metrics_logged mode=train step=1645 2026-04-13 11:23:13,366 | INFO | train_grpo_train | metrics_logged mode=train step=1646 2026-04-13 11:23:20,159 | INFO | train_grpo_train | metrics_logged mode=train step=1647 2026-04-13 11:23:27,523 | INFO | train_grpo_train | metrics_logged mode=train step=1648 2026-04-13 11:23:33,969 | INFO | train_grpo_train | metrics_logged mode=train step=1649 2026-04-13 11:23:40,434 | INFO | train_grpo_train | metrics_logged mode=train step=1650 2026-04-13 11:24:50,195 | INFO | train_grpo_train | metrics_logged mode=eval step=1650 2026-04-13 11:25:00,158 | INFO | train_grpo_train | metrics_logged mode=train step=1651 2026-04-13 11:25:07,398 | INFO | train_grpo_train | metrics_logged mode=train step=1652 2026-04-13 11:25:19,406 | INFO | train_grpo_train | metrics_logged mode=train step=1653 2026-04-13 11:25:31,652 | INFO | train_grpo_train | metrics_logged mode=train step=1654 2026-04-13 11:25:38,004 | INFO | train_grpo_train | metrics_logged mode=train step=1655 2026-04-13 11:25:50,165 | INFO | train_grpo_train | metrics_logged mode=train step=1656 2026-04-13 11:25:57,188 | INFO | train_grpo_train | metrics_logged mode=train step=1657 2026-04-13 11:26:08,717 | INFO | train_grpo_train | metrics_logged mode=train step=1658 2026-04-13 11:26:15,966 | INFO | train_grpo_train | metrics_logged mode=train step=1659 2026-04-13 11:26:22,159 | INFO | train_grpo_train | metrics_logged mode=train step=1660 2026-04-13 11:26:28,753 | INFO | train_grpo_train | metrics_logged mode=train step=1661 2026-04-13 11:26:36,865 | INFO | train_grpo_train | metrics_logged mode=train step=1662 2026-04-13 11:26:48,361 | INFO | train_grpo_train | metrics_logged mode=train step=1663 2026-04-13 11:26:55,271 | INFO | train_grpo_train | metrics_logged mode=train step=1664 2026-04-13 11:27:02,012 | INFO | train_grpo_train | metrics_logged mode=train step=1665 2026-04-13 11:27:14,563 | INFO | train_grpo_train | metrics_logged mode=train step=1666 2026-04-13 11:27:27,001 | INFO | train_grpo_train | metrics_logged mode=train step=1667 2026-04-13 11:27:38,827 | INFO | train_grpo_train | metrics_logged mode=train step=1668 2026-04-13 11:27:50,666 | INFO | train_grpo_train | metrics_logged mode=train step=1669 2026-04-13 11:27:56,875 | INFO | train_grpo_train | metrics_logged mode=train step=1670 2026-04-13 11:28:05,403 | INFO | train_grpo_train | metrics_logged mode=train step=1671 2026-04-13 11:28:11,531 | INFO | train_grpo_train | metrics_logged mode=train step=1672 2026-04-13 11:28:18,661 | INFO | train_grpo_train | metrics_logged mode=train step=1673 2026-04-13 11:28:25,963 | INFO | train_grpo_train | metrics_logged mode=train step=1674 2026-04-13 11:28:33,625 | INFO | train_grpo_train | metrics_logged mode=train step=1675 2026-04-13 11:28:42,445 | INFO | train_grpo_train | metrics_logged mode=train step=1676 2026-04-13 11:28:48,762 | INFO | train_grpo_train | metrics_logged mode=train step=1677 2026-04-13 11:28:57,391 | INFO | train_grpo_train | metrics_logged mode=train step=1678 2026-04-13 11:29:08,962 | INFO | train_grpo_train | metrics_logged mode=train step=1679 2026-04-13 11:29:15,904 | INFO | train_grpo_train | metrics_logged mode=train step=1680 2026-04-13 11:29:22,175 | INFO | train_grpo_train | metrics_logged mode=train step=1681 2026-04-13 11:29:29,024 | INFO | train_grpo_train | metrics_logged mode=train step=1682 2026-04-13 11:29:35,279 | INFO | train_grpo_train | metrics_logged mode=train step=1683 2026-04-13 11:29:41,907 | INFO | train_grpo_train | metrics_logged mode=train step=1684 2026-04-13 11:29:49,745 | INFO | train_grpo_train | metrics_logged mode=train step=1685 2026-04-13 11:29:57,253 | INFO | train_grpo_train | metrics_logged mode=train step=1686 2026-04-13 11:30:03,910 | INFO | train_grpo_train | metrics_logged mode=train step=1687 2026-04-13 11:30:11,993 | INFO | train_grpo_train | metrics_logged mode=train step=1688 2026-04-13 11:30:18,571 | INFO | train_grpo_train | metrics_logged mode=train step=1689 2026-04-13 11:30:24,873 | INFO | train_grpo_train | metrics_logged mode=train step=1690 2026-04-13 11:30:32,155 | INFO | train_grpo_train | metrics_logged mode=train step=1691 2026-04-13 11:30:38,648 | INFO | train_grpo_train | metrics_logged mode=train step=1692 2026-04-13 11:30:50,084 | INFO | train_grpo_train | metrics_logged mode=train step=1693 2026-04-13 11:30:56,178 | INFO | train_grpo_train | metrics_logged mode=train step=1694 2026-04-13 11:31:03,180 | INFO | train_grpo_train | metrics_logged mode=train step=1695 2026-04-13 11:31:10,598 | INFO | train_grpo_train | metrics_logged mode=train step=1696 2026-04-13 11:31:17,548 | INFO | train_grpo_train | metrics_logged mode=train step=1697 2026-04-13 11:31:23,651 | INFO | train_grpo_train | metrics_logged mode=train step=1698 2026-04-13 11:31:34,930 | INFO | train_grpo_train | metrics_logged mode=train step=1699 2026-04-13 11:31:42,249 | INFO | train_grpo_train | metrics_logged mode=train step=1700 2026-04-13 11:32:34,116 | INFO | train_grpo_train | metrics_logged mode=eval step=1700 2026-04-13 11:32:44,133 | INFO | train_grpo_train | metrics_logged mode=train step=1701 2026-04-13 11:32:51,002 | INFO | train_grpo_train | metrics_logged mode=train step=1702 2026-04-13 11:32:58,716 | INFO | train_grpo_train | metrics_logged mode=train step=1703 2026-04-13 11:33:04,982 | INFO | train_grpo_train | metrics_logged mode=train step=1704 2026-04-13 11:33:10,857 | INFO | train_grpo_train | metrics_logged mode=train step=1705 2026-04-13 11:33:17,683 | INFO | train_grpo_train | metrics_logged mode=train step=1706 2026-04-13 11:33:24,186 | INFO | train_grpo_train | metrics_logged mode=train step=1707 2026-04-13 11:33:30,881 | INFO | train_grpo_train | metrics_logged mode=train step=1708 2026-04-13 11:33:38,045 | INFO | train_grpo_train | metrics_logged mode=train step=1709 2026-04-13 11:33:45,324 | INFO | train_grpo_train | metrics_logged mode=train step=1710 2026-04-13 11:33:56,855 | INFO | train_grpo_train | metrics_logged mode=train step=1711 2026-04-13 11:34:08,453 | INFO | train_grpo_train | metrics_logged mode=train step=1712 2026-04-13 11:34:15,554 | INFO | train_grpo_train | metrics_logged mode=train step=1713 2026-04-13 11:34:21,845 | INFO | train_grpo_train | metrics_logged mode=train step=1714 2026-04-13 11:34:28,047 | INFO | train_grpo_train | metrics_logged mode=train step=1715 2026-04-13 11:34:34,621 | INFO | train_grpo_train | metrics_logged mode=train step=1716 2026-04-13 11:34:40,940 | INFO | train_grpo_train | metrics_logged mode=train step=1717 2026-04-13 11:34:46,966 | INFO | train_grpo_train | metrics_logged mode=train step=1718 2026-04-13 11:34:54,079 | INFO | train_grpo_train | metrics_logged mode=train step=1719 2026-04-13 11:35:01,906 | INFO | train_grpo_train | metrics_logged mode=train step=1720 2026-04-13 11:35:09,053 | INFO | train_grpo_train | metrics_logged mode=train step=1721 2026-04-13 11:35:15,894 | INFO | train_grpo_train | metrics_logged mode=train step=1722 2026-04-13 11:35:22,773 | INFO | train_grpo_train | metrics_logged mode=train step=1723 2026-04-13 11:35:29,792 | INFO | train_grpo_train | metrics_logged mode=train step=1724 2026-04-13 11:35:36,644 | INFO | train_grpo_train | metrics_logged mode=train step=1725 2026-04-13 11:35:44,864 | INFO | train_grpo_train | metrics_logged mode=train step=1726 2026-04-13 11:35:52,865 | INFO | train_grpo_train | metrics_logged mode=train step=1727 2026-04-13 11:36:00,073 | INFO | train_grpo_train | metrics_logged mode=train step=1728 2026-04-13 11:36:06,214 | INFO | train_grpo_train | metrics_logged mode=train step=1729 2026-04-13 11:36:12,275 | INFO | train_grpo_train | metrics_logged mode=train step=1730 2026-04-13 11:36:20,974 | INFO | train_grpo_train | metrics_logged mode=train step=1731 2026-04-13 11:36:28,009 | INFO | train_grpo_train | metrics_logged mode=train step=1732 2026-04-13 11:36:35,141 | INFO | train_grpo_train | metrics_logged mode=train step=1733 2026-04-13 11:36:42,752 | INFO | train_grpo_train | metrics_logged mode=train step=1734 2026-04-13 11:36:49,099 | INFO | train_grpo_train | metrics_logged mode=train step=1735 2026-04-13 11:36:56,231 | INFO | train_grpo_train | metrics_logged mode=train step=1736 2026-04-13 11:37:03,654 | INFO | train_grpo_train | metrics_logged mode=train step=1737 2026-04-13 11:37:11,830 | INFO | train_grpo_train | metrics_logged mode=train step=1738 2026-04-13 11:37:18,493 | INFO | train_grpo_train | metrics_logged mode=train step=1739 2026-04-13 11:37:26,623 | INFO | train_grpo_train | metrics_logged mode=train step=1740 2026-04-13 11:37:33,800 | INFO | train_grpo_train | metrics_logged mode=train step=1741 2026-04-13 11:37:42,463 | INFO | train_grpo_train | metrics_logged mode=train step=1742 2026-04-13 11:37:54,485 | INFO | train_grpo_train | metrics_logged mode=train step=1743 2026-04-13 11:38:00,662 | INFO | train_grpo_train | metrics_logged mode=train step=1744 2026-04-13 11:38:06,476 | INFO | train_grpo_train | metrics_logged mode=train step=1745 2026-04-13 11:38:13,642 | INFO | train_grpo_train | metrics_logged mode=train step=1746 2026-04-13 11:38:25,653 | INFO | train_grpo_train | metrics_logged mode=train step=1747 2026-04-13 11:38:32,457 | INFO | train_grpo_train | metrics_logged mode=train step=1748 2026-04-13 11:38:40,330 | INFO | train_grpo_train | metrics_logged mode=train step=1749 2026-04-13 11:38:47,529 | INFO | train_grpo_train | metrics_logged mode=train step=1750 2026-04-13 11:39:47,401 | INFO | train_grpo_train | metrics_logged mode=eval step=1750 2026-04-13 11:39:59,413 | INFO | train_grpo_train | metrics_logged mode=train step=1751 2026-04-13 11:40:05,565 | INFO | train_grpo_train | metrics_logged mode=train step=1752 2026-04-13 11:40:11,511 | INFO | train_grpo_train | metrics_logged mode=train step=1753 2026-04-13 11:40:23,521 | INFO | train_grpo_train | metrics_logged mode=train step=1754 2026-04-13 11:40:35,107 | INFO | train_grpo_train | metrics_logged mode=train step=1755 2026-04-13 11:40:42,104 | INFO | train_grpo_train | metrics_logged mode=train step=1756 2026-04-13 11:40:48,001 | INFO | train_grpo_train | metrics_logged mode=train step=1757 2026-04-13 11:40:54,287 | INFO | train_grpo_train | metrics_logged mode=train step=1758 2026-04-13 11:41:02,288 | INFO | train_grpo_train | metrics_logged mode=train step=1759 2026-04-13 11:41:08,485 | INFO | train_grpo_train | metrics_logged mode=train step=1760 2026-04-13 11:41:16,332 | INFO | train_grpo_train | metrics_logged mode=train step=1761 2026-04-13 11:41:28,569 | INFO | train_grpo_train | metrics_logged mode=train step=1762 2026-04-13 11:41:36,140 | INFO | train_grpo_train | metrics_logged mode=train step=1763 2026-04-13 11:41:42,768 | INFO | train_grpo_train | metrics_logged mode=train step=1764 2026-04-13 11:41:54,896 | INFO | train_grpo_train | metrics_logged mode=train step=1765 2026-04-13 11:42:01,380 | INFO | train_grpo_train | metrics_logged mode=train step=1766 2026-04-13 11:42:07,416 | INFO | train_grpo_train | metrics_logged mode=train step=1767 2026-04-13 11:42:13,595 | INFO | train_grpo_train | metrics_logged mode=train step=1768 2026-04-13 11:42:21,970 | INFO | train_grpo_train | metrics_logged mode=train step=1769 2026-04-13 11:42:29,047 | INFO | train_grpo_train | metrics_logged mode=train step=1770 2026-04-13 11:42:37,354 | INFO | train_grpo_train | metrics_logged mode=train step=1771 2026-04-13 11:42:44,827 | INFO | train_grpo_train | metrics_logged mode=train step=1772 2026-04-13 11:42:52,320 | INFO | train_grpo_train | metrics_logged mode=train step=1773 2026-04-13 11:42:58,655 | INFO | train_grpo_train | metrics_logged mode=train step=1774 2026-04-13 11:43:05,982 | INFO | train_grpo_train | metrics_logged mode=train step=1775 2026-04-13 11:43:12,054 | INFO | train_grpo_train | metrics_logged mode=train step=1776 2026-04-13 11:43:18,128 | INFO | train_grpo_train | metrics_logged mode=train step=1777 2026-04-13 11:43:25,110 | INFO | train_grpo_train | metrics_logged mode=train step=1778 2026-04-13 11:43:34,142 | INFO | train_grpo_train | metrics_logged mode=train step=1779 2026-04-13 11:43:40,470 | INFO | train_grpo_train | metrics_logged mode=train step=1780 2026-04-13 11:43:48,027 | INFO | train_grpo_train | metrics_logged mode=train step=1781 2026-04-13 11:43:54,958 | INFO | train_grpo_train | metrics_logged mode=train step=1782 2026-04-13 11:44:01,760 | INFO | train_grpo_train | metrics_logged mode=train step=1783 2026-04-13 11:44:08,494 | INFO | train_grpo_train | metrics_logged mode=train step=1784 2026-04-13 11:44:16,625 | INFO | train_grpo_train | metrics_logged mode=train step=1785 2026-04-13 11:44:23,915 | INFO | train_grpo_train | metrics_logged mode=train step=1786 2026-04-13 11:44:31,488 | INFO | train_grpo_train | metrics_logged mode=train step=1787 2026-04-13 11:44:40,192 | INFO | train_grpo_train | metrics_logged mode=train step=1788 2026-04-13 11:44:47,702 | INFO | train_grpo_train | metrics_logged mode=train step=1789 2026-04-13 11:44:53,627 | INFO | train_grpo_train | metrics_logged mode=train step=1790 2026-04-13 11:45:02,837 | INFO | train_grpo_train | metrics_logged mode=train step=1791 2026-04-13 11:45:09,942 | INFO | train_grpo_train | metrics_logged mode=train step=1792 2026-04-13 11:45:16,776 | INFO | train_grpo_train | metrics_logged mode=train step=1793 2026-04-13 11:45:23,947 | INFO | train_grpo_train | metrics_logged mode=train step=1794 2026-04-13 11:45:31,422 | INFO | train_grpo_train | metrics_logged mode=train step=1795 2026-04-13 11:45:39,490 | INFO | train_grpo_train | metrics_logged mode=train step=1796 2026-04-13 11:45:51,039 | INFO | train_grpo_train | metrics_logged mode=train step=1797 2026-04-13 11:45:58,268 | INFO | train_grpo_train | metrics_logged mode=train step=1798 2026-04-13 11:46:06,323 | INFO | train_grpo_train | metrics_logged mode=train step=1799 2026-04-13 11:46:14,770 | INFO | train_grpo_train | metrics_logged mode=train step=1800 2026-04-13 11:47:03,198 | INFO | train_grpo_train | metrics_logged mode=eval step=1800 2026-04-13 11:47:12,926 | INFO | train_grpo_train | metrics_logged mode=train step=1801 2026-04-13 11:47:21,099 | INFO | train_grpo_train | metrics_logged mode=train step=1802 2026-04-13 11:47:28,986 | INFO | train_grpo_train | metrics_logged mode=train step=1803 2026-04-13 11:47:36,172 | INFO | train_grpo_train | metrics_logged mode=train step=1804 2026-04-13 11:47:43,401 | INFO | train_grpo_train | metrics_logged mode=train step=1805 2026-04-13 11:47:52,110 | INFO | train_grpo_train | metrics_logged mode=train step=1806 2026-04-13 11:47:58,035 | INFO | train_grpo_train | metrics_logged mode=train step=1807 2026-04-13 11:48:04,962 | INFO | train_grpo_train | metrics_logged mode=train step=1808 2026-04-13 11:48:12,254 | INFO | train_grpo_train | metrics_logged mode=train step=1809 2026-04-13 11:48:20,523 | INFO | train_grpo_train | metrics_logged mode=train step=1810 2026-04-13 11:48:27,540 | INFO | train_grpo_train | metrics_logged mode=train step=1811 2026-04-13 11:48:33,558 | INFO | train_grpo_train | metrics_logged mode=train step=1812 2026-04-13 11:48:40,058 | INFO | train_grpo_train | metrics_logged mode=train step=1813 2026-04-13 11:48:47,833 | INFO | train_grpo_train | metrics_logged mode=train step=1814 2026-04-13 11:48:54,130 | INFO | train_grpo_train | metrics_logged mode=train step=1815 2026-04-13 11:49:02,000 | INFO | train_grpo_train | metrics_logged mode=train step=1816 2026-04-13 11:49:09,362 | INFO | train_grpo_train | metrics_logged mode=train step=1817 2026-04-13 11:49:15,554 | INFO | train_grpo_train | metrics_logged mode=train step=1818 2026-04-13 11:49:21,992 | INFO | train_grpo_train | metrics_logged mode=train step=1819 2026-04-13 11:49:28,137 | INFO | train_grpo_train | metrics_logged mode=train step=1820 2026-04-13 11:49:34,127 | INFO | train_grpo_train | metrics_logged mode=train step=1821 2026-04-13 11:49:41,597 | INFO | train_grpo_train | metrics_logged mode=train step=1822 2026-04-13 11:49:53,337 | INFO | train_grpo_train | metrics_logged mode=train step=1823 2026-04-13 11:49:59,348 | INFO | train_grpo_train | metrics_logged mode=train step=1824 2026-04-13 11:50:05,712 | INFO | train_grpo_train | metrics_logged mode=train step=1825 2026-04-13 11:50:13,467 | INFO | train_grpo_train | metrics_logged mode=train step=1826 2026-04-13 11:50:26,138 | INFO | train_grpo_train | metrics_logged mode=train step=1827 2026-04-13 11:50:32,037 | INFO | train_grpo_train | metrics_logged mode=train step=1828 2026-04-13 11:50:39,725 | INFO | train_grpo_train | metrics_logged mode=train step=1829 2026-04-13 11:50:47,769 | INFO | train_grpo_train | metrics_logged mode=train step=1830 2026-04-13 11:50:54,975 | INFO | train_grpo_train | metrics_logged mode=train step=1831 2026-04-13 11:51:06,817 | INFO | train_grpo_train | metrics_logged mode=train step=1832 2026-04-13 11:51:14,419 | INFO | train_grpo_train | metrics_logged mode=train step=1833 2026-04-13 11:51:20,652 | INFO | train_grpo_train | metrics_logged mode=train step=1834 2026-04-13 11:51:32,330 | INFO | train_grpo_train | metrics_logged mode=train step=1835 2026-04-13 11:51:38,863 | INFO | train_grpo_train | metrics_logged mode=train step=1836 2026-04-13 11:51:46,617 | INFO | train_grpo_train | metrics_logged mode=train step=1837 2026-04-13 11:51:52,656 | INFO | train_grpo_train | metrics_logged mode=train step=1838 2026-04-13 11:51:58,910 | INFO | train_grpo_train | metrics_logged mode=train step=1839 2026-04-13 11:52:10,449 | INFO | train_grpo_train | metrics_logged mode=train step=1840 2026-04-13 11:52:16,994 | INFO | train_grpo_train | metrics_logged mode=train step=1841 2026-04-13 11:52:28,749 | INFO | train_grpo_train | metrics_logged mode=train step=1842 2026-04-13 11:52:35,499 | INFO | train_grpo_train | metrics_logged mode=train step=1843 2026-04-13 11:52:42,624 | INFO | train_grpo_train | metrics_logged mode=train step=1844 2026-04-13 11:52:54,107 | INFO | train_grpo_train | metrics_logged mode=train step=1845 2026-04-13 11:53:06,163 | INFO | train_grpo_train | metrics_logged mode=train step=1846 2026-04-13 11:53:12,869 | INFO | train_grpo_train | metrics_logged mode=train step=1847 2026-04-13 11:53:18,535 | INFO | train_grpo_train | metrics_logged mode=train step=1848 2026-04-13 11:53:24,955 | INFO | train_grpo_train | metrics_logged mode=train step=1849 2026-04-13 11:53:36,104 | INFO | train_grpo_train | metrics_logged mode=train step=1850 2026-04-13 11:54:32,513 | INFO | train_grpo_train | metrics_logged mode=eval step=1850 2026-04-13 11:54:42,289 | INFO | train_grpo_train | metrics_logged mode=train step=1851 2026-04-13 11:54:48,481 | INFO | train_grpo_train | metrics_logged mode=train step=1852 2026-04-13 11:55:00,281 | INFO | train_grpo_train | metrics_logged mode=train step=1853 2026-04-13 11:55:07,157 | INFO | train_grpo_train | metrics_logged mode=train step=1854 2026-04-13 11:55:18,386 | INFO | train_grpo_train | metrics_logged mode=train step=1855 2026-04-13 11:55:25,215 | INFO | train_grpo_train | metrics_logged mode=train step=1856 2026-04-13 11:55:31,415 | INFO | train_grpo_train | metrics_logged mode=train step=1857 2026-04-13 11:55:39,885 | INFO | train_grpo_train | metrics_logged mode=train step=1858 2026-04-13 11:55:47,589 | INFO | train_grpo_train | metrics_logged mode=train step=1859 2026-04-13 11:55:54,873 | INFO | train_grpo_train | metrics_logged mode=train step=1860 2026-04-13 11:56:02,495 | INFO | train_grpo_train | metrics_logged mode=train step=1861 2026-04-13 11:56:14,214 | INFO | train_grpo_train | metrics_logged mode=train step=1862 2026-04-13 11:56:23,635 | INFO | train_grpo_train | metrics_logged mode=train step=1863 2026-04-13 11:56:30,919 | INFO | train_grpo_train | metrics_logged mode=train step=1864 2026-04-13 11:56:37,562 | INFO | train_grpo_train | metrics_logged mode=train step=1865 2026-04-13 11:56:45,490 | INFO | train_grpo_train | metrics_logged mode=train step=1866 2026-04-13 11:56:51,698 | INFO | train_grpo_train | metrics_logged mode=train step=1867 2026-04-13 11:56:58,544 | INFO | train_grpo_train | metrics_logged mode=train step=1868 2026-04-13 11:57:04,373 | INFO | train_grpo_train | metrics_logged mode=train step=1869 2026-04-13 11:57:10,330 | INFO | train_grpo_train | metrics_logged mode=train step=1870 2026-04-13 11:57:16,749 | INFO | train_grpo_train | metrics_logged mode=train step=1871 2026-04-13 11:57:33,559 | INFO | train_grpo_train | metrics_logged mode=train step=1872 2026-04-13 11:57:45,023 | INFO | train_grpo_train | metrics_logged mode=train step=1873 2026-04-13 11:57:52,050 | INFO | train_grpo_train | metrics_logged mode=train step=1874 2026-04-13 11:57:57,805 | INFO | train_grpo_train | metrics_logged mode=train step=1875 2026-04-13 11:58:05,547 | INFO | train_grpo_train | metrics_logged mode=train step=1876 2026-04-13 11:58:12,442 | INFO | train_grpo_train | metrics_logged mode=train step=1877 2026-04-13 11:58:19,239 | INFO | train_grpo_train | metrics_logged mode=train step=1878 2026-04-13 11:58:26,682 | INFO | train_grpo_train | metrics_logged mode=train step=1879 2026-04-13 11:58:33,627 | INFO | train_grpo_train | metrics_logged mode=train step=1880 2026-04-13 11:58:44,937 | INFO | train_grpo_train | metrics_logged mode=train step=1881 2026-04-13 11:58:51,068 | INFO | train_grpo_train | metrics_logged mode=train step=1882 2026-04-13 11:59:02,509 | INFO | train_grpo_train | metrics_logged mode=train step=1883 2026-04-13 11:59:08,616 | INFO | train_grpo_train | metrics_logged mode=train step=1884 2026-04-13 11:59:14,374 | INFO | train_grpo_train | metrics_logged mode=train step=1885 2026-04-13 11:59:20,899 | INFO | train_grpo_train | metrics_logged mode=train step=1886 2026-04-13 11:59:26,992 | INFO | train_grpo_train | metrics_logged mode=train step=1887 2026-04-13 11:59:34,161 | INFO | train_grpo_train | metrics_logged mode=train step=1888 2026-04-13 11:59:46,006 | INFO | train_grpo_train | metrics_logged mode=train step=1889 2026-04-13 11:59:53,293 | INFO | train_grpo_train | metrics_logged mode=train step=1890 2026-04-13 11:59:59,402 | INFO | train_grpo_train | metrics_logged mode=train step=1891 2026-04-13 12:00:06,098 | INFO | train_grpo_train | metrics_logged mode=train step=1892 2026-04-13 12:00:12,807 | INFO | train_grpo_train | metrics_logged mode=train step=1893 2026-04-13 12:00:20,114 | INFO | train_grpo_train | metrics_logged mode=train step=1894 2026-04-13 12:00:27,207 | INFO | train_grpo_train | metrics_logged mode=train step=1895 2026-04-13 12:00:38,633 | INFO | train_grpo_train | metrics_logged mode=train step=1896 2026-04-13 12:00:44,576 | INFO | train_grpo_train | metrics_logged mode=train step=1897 2026-04-13 12:00:52,659 | INFO | train_grpo_train | metrics_logged mode=train step=1898 2026-04-13 12:00:58,915 | INFO | train_grpo_train | metrics_logged mode=train step=1899 2026-04-13 12:01:05,118 | INFO | train_grpo_train | metrics_logged mode=train step=1900 2026-04-13 12:01:47,608 | INFO | train_grpo_train | metrics_logged mode=eval step=1900 2026-04-13 12:02:02,638 | INFO | train_grpo_train | metrics_logged mode=train step=1901 2026-04-13 12:02:14,716 | INFO | train_grpo_train | metrics_logged mode=train step=1902 2026-04-13 12:02:20,852 | INFO | train_grpo_train | metrics_logged mode=train step=1903 2026-04-13 12:02:27,185 | INFO | train_grpo_train | metrics_logged mode=train step=1904 2026-04-13 12:02:38,855 | INFO | train_grpo_train | metrics_logged mode=train step=1905 2026-04-13 12:02:45,217 | INFO | train_grpo_train | metrics_logged mode=train step=1906 2026-04-13 12:02:56,298 | INFO | train_grpo_train | metrics_logged mode=train step=1907 2026-04-13 12:03:03,219 | INFO | train_grpo_train | metrics_logged mode=train step=1908 2026-04-13 12:03:09,414 | INFO | train_grpo_train | metrics_logged mode=train step=1909 2026-04-13 12:03:16,701 | INFO | train_grpo_train | metrics_logged mode=train step=1910 2026-04-13 12:03:23,430 | INFO | train_grpo_train | metrics_logged mode=train step=1911 2026-04-13 12:03:31,548 | INFO | train_grpo_train | metrics_logged mode=train step=1912 2026-04-13 12:03:38,338 | INFO | train_grpo_train | metrics_logged mode=train step=1913 2026-04-13 12:03:45,099 | INFO | train_grpo_train | metrics_logged mode=train step=1914 2026-04-13 12:03:53,830 | INFO | train_grpo_train | metrics_logged mode=train step=1915 2026-04-13 12:04:01,227 | INFO | train_grpo_train | metrics_logged mode=train step=1916 2026-04-13 12:04:07,326 | INFO | train_grpo_train | metrics_logged mode=train step=1917 2026-04-13 12:04:14,076 | INFO | train_grpo_train | metrics_logged mode=train step=1918 2026-04-13 12:04:20,416 | INFO | train_grpo_train | metrics_logged mode=train step=1919 2026-04-13 12:04:28,556 | INFO | train_grpo_train | metrics_logged mode=train step=1920 2026-04-13 12:04:39,842 | INFO | train_grpo_train | metrics_logged mode=train step=1921 2026-04-13 12:04:51,097 | INFO | train_grpo_train | metrics_logged mode=train step=1922 2026-04-13 12:04:57,621 | INFO | train_grpo_train | metrics_logged mode=train step=1923 2026-04-13 12:05:09,223 | INFO | train_grpo_train | metrics_logged mode=train step=1924 2026-04-13 12:05:15,445 | INFO | train_grpo_train | metrics_logged mode=train step=1925 2026-04-13 12:05:26,781 | INFO | train_grpo_train | metrics_logged mode=train step=1926 2026-04-13 12:05:32,664 | INFO | train_grpo_train | metrics_logged mode=train step=1927 2026-04-13 12:05:38,580 | INFO | train_grpo_train | metrics_logged mode=train step=1928 2026-04-13 12:05:44,705 | INFO | train_grpo_train | metrics_logged mode=train step=1929 2026-04-13 12:05:58,641 | INFO | train_grpo_train | metrics_logged mode=train step=1930 2026-04-13 12:06:04,904 | INFO | train_grpo_train | metrics_logged mode=train step=1931 2026-04-13 12:06:12,138 | INFO | train_grpo_train | metrics_logged mode=train step=1932 2026-04-13 12:06:23,651 | INFO | train_grpo_train | metrics_logged mode=train step=1933 2026-04-13 12:06:31,561 | INFO | train_grpo_train | metrics_logged mode=train step=1934 2026-04-13 12:06:38,271 | INFO | train_grpo_train | metrics_logged mode=train step=1935 2026-04-13 12:06:44,572 | INFO | train_grpo_train | metrics_logged mode=train step=1936 2026-04-13 12:06:51,269 | INFO | train_grpo_train | metrics_logged mode=train step=1937 2026-04-13 12:07:02,738 | INFO | train_grpo_train | metrics_logged mode=train step=1938 2026-04-13 12:07:08,999 | INFO | train_grpo_train | metrics_logged mode=train step=1939 2026-04-13 12:07:21,443 | INFO | train_grpo_train | metrics_logged mode=train step=1940 2026-04-13 12:07:28,473 | INFO | train_grpo_train | metrics_logged mode=train step=1941 2026-04-13 12:07:35,297 | INFO | train_grpo_train | metrics_logged mode=train step=1942 2026-04-13 12:07:43,590 | INFO | train_grpo_train | metrics_logged mode=train step=1943 2026-04-13 12:07:51,746 | INFO | train_grpo_train | metrics_logged mode=train step=1944 2026-04-13 12:07:58,331 | INFO | train_grpo_train | metrics_logged mode=train step=1945 2026-04-13 12:08:04,959 | INFO | train_grpo_train | metrics_logged mode=train step=1946 2026-04-13 12:08:11,328 | INFO | train_grpo_train | metrics_logged mode=train step=1947 2026-04-13 12:08:19,146 | INFO | train_grpo_train | metrics_logged mode=train step=1948 2026-04-13 12:08:26,041 | INFO | train_grpo_train | metrics_logged mode=train step=1949 2026-04-13 12:08:32,838 | INFO | train_grpo_train | metrics_logged mode=train step=1950 2026-04-13 12:09:20,344 | INFO | train_grpo_train | metrics_logged mode=eval step=1950 2026-04-13 12:09:30,327 | INFO | train_grpo_train | metrics_logged mode=train step=1951 2026-04-13 12:09:36,683 | INFO | train_grpo_train | metrics_logged mode=train step=1952 2026-04-13 12:09:43,344 | INFO | train_grpo_train | metrics_logged mode=train step=1953 2026-04-13 12:09:49,980 | INFO | train_grpo_train | metrics_logged mode=train step=1954 2026-04-13 12:09:56,728 | INFO | train_grpo_train | metrics_logged mode=train step=1955 2026-04-13 12:10:02,947 | INFO | train_grpo_train | metrics_logged mode=train step=1956 2026-04-13 12:10:10,813 | INFO | train_grpo_train | metrics_logged mode=train step=1957 2026-04-13 12:10:17,070 | INFO | train_grpo_train | metrics_logged mode=train step=1958 2026-04-13 12:10:23,187 | INFO | train_grpo_train | metrics_logged mode=train step=1959 2026-04-13 12:10:29,267 | INFO | train_grpo_train | metrics_logged mode=train step=1960 2026-04-13 12:10:35,218 | INFO | train_grpo_train | metrics_logged mode=train step=1961 2026-04-13 12:10:42,325 | INFO | train_grpo_train | metrics_logged mode=train step=1962 2026-04-13 12:10:49,249 | INFO | train_grpo_train | metrics_logged mode=train step=1963 2026-04-13 12:10:56,448 | INFO | train_grpo_train | metrics_logged mode=train step=1964 2026-04-13 12:11:02,876 | INFO | train_grpo_train | metrics_logged mode=train step=1965 2026-04-13 12:11:09,083 | INFO | train_grpo_train | metrics_logged mode=train step=1966 2026-04-13 12:11:15,538 | INFO | train_grpo_train | metrics_logged mode=train step=1967 2026-04-13 12:11:27,494 | INFO | train_grpo_train | metrics_logged mode=train step=1968 2026-04-13 12:11:34,999 | INFO | train_grpo_train | metrics_logged mode=train step=1969 2026-04-13 12:11:42,204 | INFO | train_grpo_train | metrics_logged mode=train step=1970 2026-04-13 12:11:48,577 | INFO | train_grpo_train | metrics_logged mode=train step=1971 2026-04-13 12:11:55,231 | INFO | train_grpo_train | metrics_logged mode=train step=1972 2026-04-13 12:12:01,382 | INFO | train_grpo_train | metrics_logged mode=train step=1973 2026-04-13 12:12:07,900 | INFO | train_grpo_train | metrics_logged mode=train step=1974 2026-04-13 12:12:14,888 | INFO | train_grpo_train | metrics_logged mode=train step=1975 2026-04-13 12:12:22,045 | INFO | train_grpo_train | metrics_logged mode=train step=1976 2026-04-13 12:12:29,897 | INFO | train_grpo_train | metrics_logged mode=train step=1977 2026-04-13 12:12:36,291 | INFO | train_grpo_train | metrics_logged mode=train step=1978 2026-04-13 12:12:42,432 | INFO | train_grpo_train | metrics_logged mode=train step=1979 2026-04-13 12:12:49,524 | INFO | train_grpo_train | metrics_logged mode=train step=1980 2026-04-13 12:12:56,565 | INFO | train_grpo_train | metrics_logged mode=train step=1981 2026-04-13 12:13:03,476 | INFO | train_grpo_train | metrics_logged mode=train step=1982 2026-04-13 12:13:15,334 | INFO | train_grpo_train | metrics_logged mode=train step=1983 2026-04-13 12:13:22,600 | INFO | train_grpo_train | metrics_logged mode=train step=1984 2026-04-13 12:13:29,315 | INFO | train_grpo_train | metrics_logged mode=train step=1985 2026-04-13 12:13:35,901 | INFO | train_grpo_train | metrics_logged mode=train step=1986 2026-04-13 12:13:42,308 | INFO | train_grpo_train | metrics_logged mode=train step=1987 2026-04-13 12:13:49,877 | INFO | train_grpo_train | metrics_logged mode=train step=1988 2026-04-13 12:13:56,866 | INFO | train_grpo_train | metrics_logged mode=train step=1989 2026-04-13 12:14:08,268 | INFO | train_grpo_train | metrics_logged mode=train step=1990 2026-04-13 12:14:15,226 | INFO | train_grpo_train | metrics_logged mode=train step=1991 2026-04-13 12:14:22,510 | INFO | train_grpo_train | metrics_logged mode=train step=1992 2026-04-13 12:14:29,180 | INFO | train_grpo_train | metrics_logged mode=train step=1993 2026-04-13 12:14:35,847 | INFO | train_grpo_train | metrics_logged mode=train step=1994 2026-04-13 12:14:42,487 | INFO | train_grpo_train | metrics_logged mode=train step=1995 2026-04-13 12:14:54,047 | INFO | train_grpo_train | metrics_logged mode=train step=1996 2026-04-13 12:15:00,280 | INFO | train_grpo_train | metrics_logged mode=train step=1997 2026-04-13 12:15:07,051 | INFO | train_grpo_train | metrics_logged mode=train step=1998 2026-04-13 12:15:14,007 | INFO | train_grpo_train | metrics_logged mode=train step=1999 2026-04-13 12:15:20,404 | INFO | train_grpo_train | metrics_logged mode=train step=2000 2026-04-13 12:16:12,516 | INFO | train_grpo_train | metrics_logged mode=eval step=2000 2026-04-13 12:16:22,092 | INFO | train_grpo_train | metrics_logged mode=train step=2001 2026-04-13 12:16:29,276 | INFO | train_grpo_train | metrics_logged mode=train step=2002 2026-04-13 12:16:41,295 | INFO | train_grpo_train | metrics_logged mode=train step=2003 2026-04-13 12:16:48,301 | INFO | train_grpo_train | metrics_logged mode=train step=2004 2026-04-13 12:16:56,873 | INFO | train_grpo_train | metrics_logged mode=train step=2005 2026-04-13 12:17:04,790 | INFO | train_grpo_train | metrics_logged mode=train step=2006 2026-04-13 12:17:12,660 | INFO | train_grpo_train | metrics_logged mode=train step=2007 2026-04-13 12:17:23,984 | INFO | train_grpo_train | metrics_logged mode=train step=2008 2026-04-13 12:17:29,912 | INFO | train_grpo_train | metrics_logged mode=train step=2009 2026-04-13 12:17:37,152 | INFO | train_grpo_train | metrics_logged mode=train step=2010 2026-04-13 12:17:43,433 | INFO | train_grpo_train | metrics_logged mode=train step=2011 2026-04-13 12:17:50,260 | INFO | train_grpo_train | metrics_logged mode=train step=2012 2026-04-13 12:17:56,070 | INFO | train_grpo_train | metrics_logged mode=train step=2013 2026-04-13 12:18:02,592 | INFO | train_grpo_train | metrics_logged mode=train step=2014 2026-04-13 12:18:14,361 | INFO | train_grpo_train | metrics_logged mode=train step=2015 2026-04-13 12:18:20,702 | INFO | train_grpo_train | metrics_logged mode=train step=2016 2026-04-13 12:18:28,102 | INFO | train_grpo_train | metrics_logged mode=train step=2017 2026-04-13 12:18:34,559 | INFO | train_grpo_train | metrics_logged mode=train step=2018 2026-04-13 12:18:45,844 | INFO | train_grpo_train | metrics_logged mode=train step=2019 2026-04-13 12:18:53,009 | INFO | train_grpo_train | metrics_logged mode=train step=2020 2026-04-13 12:19:00,345 | INFO | train_grpo_train | metrics_logged mode=train step=2021 2026-04-13 12:19:11,942 | INFO | train_grpo_train | metrics_logged mode=train step=2022 2026-04-13 12:19:18,217 | INFO | train_grpo_train | metrics_logged mode=train step=2023 2026-04-13 12:19:24,682 | INFO | train_grpo_train | metrics_logged mode=train step=2024 2026-04-13 12:19:30,874 | INFO | train_grpo_train | metrics_logged mode=train step=2025 2026-04-13 12:19:37,195 | INFO | train_grpo_train | metrics_logged mode=train step=2026 2026-04-13 12:19:43,572 | INFO | train_grpo_train | metrics_logged mode=train step=2027 2026-04-13 12:19:51,781 | INFO | train_grpo_train | metrics_logged mode=train step=2028 2026-04-13 12:19:59,551 | INFO | train_grpo_train | metrics_logged mode=train step=2029 2026-04-13 12:20:06,488 | INFO | train_grpo_train | metrics_logged mode=train step=2030 2026-04-13 12:20:13,089 | INFO | train_grpo_train | metrics_logged mode=train step=2031 2026-04-13 12:20:19,128 | INFO | train_grpo_train | metrics_logged mode=train step=2032 2026-04-13 12:20:26,913 | INFO | train_grpo_train | metrics_logged mode=train step=2033 2026-04-13 12:20:33,855 | INFO | train_grpo_train | metrics_logged mode=train step=2034 2026-04-13 12:20:40,685 | INFO | train_grpo_train | metrics_logged mode=train step=2035 2026-04-13 12:20:47,736 | INFO | train_grpo_train | metrics_logged mode=train step=2036 2026-04-13 12:20:54,096 | INFO | train_grpo_train | metrics_logged mode=train step=2037 2026-04-13 12:21:00,454 | INFO | train_grpo_train | metrics_logged mode=train step=2038 2026-04-13 12:21:06,667 | INFO | train_grpo_train | metrics_logged mode=train step=2039 2026-04-13 12:21:13,422 | INFO | train_grpo_train | metrics_logged mode=train step=2040 2026-04-13 12:21:21,048 | INFO | train_grpo_train | metrics_logged mode=train step=2041 2026-04-13 12:21:27,577 | INFO | train_grpo_train | metrics_logged mode=train step=2042 2026-04-13 12:21:34,136 | INFO | train_grpo_train | metrics_logged mode=train step=2043 2026-04-13 12:21:41,450 | INFO | train_grpo_train | metrics_logged mode=train step=2044 2026-04-13 12:21:49,293 | INFO | train_grpo_train | metrics_logged mode=train step=2045 2026-04-13 12:21:56,536 | INFO | train_grpo_train | metrics_logged mode=train step=2046 2026-04-13 12:22:07,775 | INFO | train_grpo_train | metrics_logged mode=train step=2047 2026-04-13 12:22:14,294 | INFO | train_grpo_train | metrics_logged mode=train step=2048 2026-04-13 12:22:20,775 | INFO | train_grpo_train | metrics_logged mode=train step=2049 2026-04-13 12:22:28,374 | INFO | train_grpo_train | metrics_logged mode=train step=2050 2026-04-13 12:23:30,157 | INFO | train_grpo_train | metrics_logged mode=eval step=2050 2026-04-13 12:23:40,012 | INFO | train_grpo_train | metrics_logged mode=train step=2051 2026-04-13 12:23:51,934 | INFO | train_grpo_train | metrics_logged mode=train step=2052 2026-04-13 12:23:59,264 | INFO | train_grpo_train | metrics_logged mode=train step=2053 2026-04-13 12:24:06,098 | INFO | train_grpo_train | metrics_logged mode=train step=2054 2026-04-13 12:24:13,626 | INFO | train_grpo_train | metrics_logged mode=train step=2055 2026-04-13 12:24:25,223 | INFO | train_grpo_train | metrics_logged mode=train step=2056 2026-04-13 12:24:31,778 | INFO | train_grpo_train | metrics_logged mode=train step=2057 2026-04-13 12:24:38,154 | INFO | train_grpo_train | metrics_logged mode=train step=2058 2026-04-13 12:24:49,481 | INFO | train_grpo_train | metrics_logged mode=train step=2059 2026-04-13 12:24:55,631 | INFO | train_grpo_train | metrics_logged mode=train step=2060 2026-04-13 12:25:02,188 | INFO | train_grpo_train | metrics_logged mode=train step=2061 2026-04-13 12:25:08,578 | INFO | train_grpo_train | metrics_logged mode=train step=2062 2026-04-13 12:25:21,338 | INFO | train_grpo_train | metrics_logged mode=train step=2063 2026-04-13 12:25:28,484 | INFO | train_grpo_train | metrics_logged mode=train step=2064 2026-04-13 12:25:35,180 | INFO | train_grpo_train | metrics_logged mode=train step=2065 2026-04-13 12:25:41,521 | INFO | train_grpo_train | metrics_logged mode=train step=2066 2026-04-13 12:25:47,815 | INFO | train_grpo_train | metrics_logged mode=train step=2067 2026-04-13 12:25:55,207 | INFO | train_grpo_train | metrics_logged mode=train step=2068 2026-04-13 12:26:01,991 | INFO | train_grpo_train | metrics_logged mode=train step=2069 2026-04-13 12:26:08,081 | INFO | train_grpo_train | metrics_logged mode=train step=2070 2026-04-13 12:26:14,485 | INFO | train_grpo_train | metrics_logged mode=train step=2071 2026-04-13 12:26:21,638 | INFO | train_grpo_train | metrics_logged mode=train step=2072 2026-04-13 12:26:28,386 | INFO | train_grpo_train | metrics_logged mode=train step=2073 2026-04-13 12:26:37,037 | INFO | train_grpo_train | metrics_logged mode=train step=2074 2026-04-13 12:26:43,377 | INFO | train_grpo_train | metrics_logged mode=train step=2075 2026-04-13 12:26:50,680 | INFO | train_grpo_train | metrics_logged mode=train step=2076 2026-04-13 12:26:56,679 | INFO | train_grpo_train | metrics_logged mode=train step=2077 2026-04-13 12:27:04,619 | INFO | train_grpo_train | metrics_logged mode=train step=2078 2026-04-13 12:27:11,158 | INFO | train_grpo_train | metrics_logged mode=train step=2079 2026-04-13 12:27:22,874 | INFO | train_grpo_train | metrics_logged mode=train step=2080 2026-04-13 12:27:34,358 | INFO | train_grpo_train | metrics_logged mode=train step=2081 2026-04-13 12:27:40,552 | INFO | train_grpo_train | metrics_logged mode=train step=2082 2026-04-13 12:27:47,315 | INFO | train_grpo_train | metrics_logged mode=train step=2083 2026-04-13 12:27:54,937 | INFO | train_grpo_train | metrics_logged mode=train step=2084 2026-04-13 12:28:01,714 | INFO | train_grpo_train | metrics_logged mode=train step=2085 2026-04-13 12:28:13,834 | INFO | train_grpo_train | metrics_logged mode=train step=2086 2026-04-13 12:28:20,599 | INFO | train_grpo_train | metrics_logged mode=train step=2087 2026-04-13 12:28:27,634 | INFO | train_grpo_train | metrics_logged mode=train step=2088 2026-04-13 12:28:45,744 | INFO | train_grpo_train | metrics_logged mode=train step=2089 2026-04-13 12:28:53,248 | INFO | train_grpo_train | metrics_logged mode=train step=2090 2026-04-13 12:28:59,577 | INFO | train_grpo_train | metrics_logged mode=train step=2091 2026-04-13 12:29:05,655 | INFO | train_grpo_train | metrics_logged mode=train step=2092 2026-04-13 12:29:12,599 | INFO | train_grpo_train | metrics_logged mode=train step=2093 2026-04-13 12:29:18,679 | INFO | train_grpo_train | metrics_logged mode=train step=2094 2026-04-13 12:29:30,006 | INFO | train_grpo_train | metrics_logged mode=train step=2095 2026-04-13 12:29:35,728 | INFO | train_grpo_train | metrics_logged mode=train step=2096 2026-04-13 12:29:47,354 | INFO | train_grpo_train | metrics_logged mode=train step=2097 2026-04-13 12:29:58,695 | INFO | train_grpo_train | metrics_logged mode=train step=2098 2026-04-13 12:30:05,047 | INFO | train_grpo_train | metrics_logged mode=train step=2099 2026-04-13 12:30:12,182 | INFO | train_grpo_train | metrics_logged mode=train step=2100 2026-04-13 12:31:14,552 | INFO | train_grpo_train | metrics_logged mode=eval step=2100 2026-04-13 12:31:30,065 | INFO | train_grpo_train | metrics_logged mode=train step=2101 2026-04-13 12:31:42,227 | INFO | train_grpo_train | metrics_logged mode=train step=2102 2026-04-13 12:31:48,489 | INFO | train_grpo_train | metrics_logged mode=train step=2103 2026-04-13 12:31:55,359 | INFO | train_grpo_train | metrics_logged mode=train step=2104 2026-04-13 12:32:02,062 | INFO | train_grpo_train | metrics_logged mode=train step=2105 2026-04-13 12:32:09,804 | INFO | train_grpo_train | metrics_logged mode=train step=2106 2026-04-13 12:32:17,179 | INFO | train_grpo_train | metrics_logged mode=train step=2107 2026-04-13 12:32:24,183 | INFO | train_grpo_train | metrics_logged mode=train step=2108 2026-04-13 12:32:30,828 | INFO | train_grpo_train | metrics_logged mode=train step=2109 2026-04-13 12:32:37,449 | INFO | train_grpo_train | metrics_logged mode=train step=2110 2026-04-13 12:32:44,744 | INFO | train_grpo_train | metrics_logged mode=train step=2111 2026-04-13 12:32:51,300 | INFO | train_grpo_train | metrics_logged mode=train step=2112 2026-04-13 12:32:57,376 | INFO | train_grpo_train | metrics_logged mode=train step=2113 2026-04-13 12:33:08,685 | INFO | train_grpo_train | metrics_logged mode=train step=2114 2026-04-13 12:33:14,912 | INFO | train_grpo_train | metrics_logged mode=train step=2115 2026-04-13 12:33:21,596 | INFO | train_grpo_train | metrics_logged mode=train step=2116 2026-04-13 12:33:28,114 | INFO | train_grpo_train | metrics_logged mode=train step=2117 2026-04-13 12:33:40,197 | INFO | train_grpo_train | metrics_logged mode=train step=2118 2026-04-13 12:33:47,657 | INFO | train_grpo_train | metrics_logged mode=train step=2119 2026-04-13 12:33:54,271 | INFO | train_grpo_train | metrics_logged mode=train step=2120 2026-04-13 12:34:00,632 | INFO | train_grpo_train | metrics_logged mode=train step=2121 2026-04-13 12:34:07,476 | INFO | train_grpo_train | metrics_logged mode=train step=2122 2026-04-13 12:34:14,202 | INFO | train_grpo_train | metrics_logged mode=train step=2123 2026-04-13 12:34:21,655 | INFO | train_grpo_train | metrics_logged mode=train step=2124 2026-04-13 12:34:29,127 | INFO | train_grpo_train | metrics_logged mode=train step=2125 2026-04-13 12:34:40,987 | INFO | train_grpo_train | metrics_logged mode=train step=2126 2026-04-13 12:34:47,634 | INFO | train_grpo_train | metrics_logged mode=train step=2127 2026-04-13 12:35:01,839 | INFO | train_grpo_train | metrics_logged mode=train step=2128 2026-04-13 12:35:08,841 | INFO | train_grpo_train | metrics_logged mode=train step=2129 2026-04-13 12:35:15,869 | INFO | train_grpo_train | metrics_logged mode=train step=2130 2026-04-13 12:35:23,479 | INFO | train_grpo_train | metrics_logged mode=train step=2131 2026-04-13 12:35:29,877 | INFO | train_grpo_train | metrics_logged mode=train step=2132 2026-04-13 12:35:36,165 | INFO | train_grpo_train | metrics_logged mode=train step=2133 2026-04-13 12:35:48,380 | INFO | train_grpo_train | metrics_logged mode=train step=2134 2026-04-13 12:36:01,375 | INFO | train_grpo_train | metrics_logged mode=train step=2135 2026-04-13 12:36:08,841 | INFO | train_grpo_train | metrics_logged mode=train step=2136 2026-04-13 12:36:15,465 | INFO | train_grpo_train | metrics_logged mode=train step=2137 2026-04-13 12:36:22,875 | INFO | train_grpo_train | metrics_logged mode=train step=2138 2026-04-13 12:36:28,821 | INFO | train_grpo_train | metrics_logged mode=train step=2139 2026-04-13 12:36:35,670 | INFO | train_grpo_train | metrics_logged mode=train step=2140 2026-04-13 12:36:42,340 | INFO | train_grpo_train | metrics_logged mode=train step=2141 2026-04-13 12:36:49,964 | INFO | train_grpo_train | metrics_logged mode=train step=2142 2026-04-13 12:36:56,604 | INFO | train_grpo_train | metrics_logged mode=train step=2143 2026-04-13 12:37:03,555 | INFO | train_grpo_train | metrics_logged mode=train step=2144 2026-04-13 12:37:15,882 | INFO | train_grpo_train | metrics_logged mode=train step=2145 2026-04-13 12:37:24,160 | INFO | train_grpo_train | metrics_logged mode=train step=2146 2026-04-13 12:37:30,478 | INFO | train_grpo_train | metrics_logged mode=train step=2147 2026-04-13 12:37:37,467 | INFO | train_grpo_train | metrics_logged mode=train step=2148 2026-04-13 12:37:44,070 | INFO | train_grpo_train | metrics_logged mode=train step=2149 2026-04-13 12:37:50,852 | INFO | train_grpo_train | metrics_logged mode=train step=2150 2026-04-13 12:38:37,355 | INFO | train_grpo_train | metrics_logged mode=eval step=2150 2026-04-13 12:38:47,534 | INFO | train_grpo_train | metrics_logged mode=train step=2151