2026-04-13 12:43:53,675 | INFO | train_grpo_train | mode=train 2026-04-13 12:45:42,026 | 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 12:45:42,027 | 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 12:45:42,027 | INFO | train_grpo_train | active_rewards=['meter', 'count_adherence', 'hard_gate', 'judge_quality', 'repeat_soft', 'total_composite'] 2026-04-13 12:45:42,027 | 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 12:45:42,027 | INFO | train_grpo_train | output_repo=Shaer-AI/Shaer-adapters-grpo-short1k-no-trio-v4 2026-04-13 12:45:42,027 | 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 12:45:42,027 | 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 12:45:42,027 | INFO | train_grpo_train | trainable_params=159907840 total_params=7160467456 trainable_ratio=0.022332 2026-04-13 12:45:42,027 | INFO | train_grpo_train | resume_decision={"timestamp_utc": "2026-04-13T12:45:23Z", "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 12:45:42,027 | INFO | train_grpo_train | starting trainer.train() 2026-04-13 12:45:48,978 | INFO | train_grpo_train | metrics_logged mode=train step=1 2026-04-13 12:45:56,591 | INFO | train_grpo_train | metrics_logged mode=train step=2 2026-04-13 12:46:02,699 | INFO | train_grpo_train | metrics_logged mode=train step=3 2026-04-13 12:46:08,576 | INFO | train_grpo_train | metrics_logged mode=train step=4 2026-04-13 12:46:15,898 | INFO | train_grpo_train | metrics_logged mode=train step=5 2026-04-13 12:46:23,201 | INFO | train_grpo_train | metrics_logged mode=train step=6 2026-04-13 12:46:31,004 | INFO | train_grpo_train | metrics_logged mode=train step=7 2026-04-13 12:46:36,965 | INFO | train_grpo_train | metrics_logged mode=train step=8 2026-04-13 12:46:45,358 | INFO | train_grpo_train | metrics_logged mode=train step=9 2026-04-13 12:46:52,336 | INFO | train_grpo_train | metrics_logged mode=train step=10 2026-04-13 12:46:58,826 | INFO | train_grpo_train | metrics_logged mode=train step=11 2026-04-13 12:47:04,601 | INFO | train_grpo_train | metrics_logged mode=train step=12 2026-04-13 12:47:10,379 | INFO | train_grpo_train | metrics_logged mode=train step=13 2026-04-13 12:47:17,519 | INFO | train_grpo_train | metrics_logged mode=train step=14 2026-04-13 12:47:23,542 | INFO | train_grpo_train | metrics_logged mode=train step=15 2026-04-13 12:47:29,400 | INFO | train_grpo_train | metrics_logged mode=train step=16 2026-04-13 12:47:35,085 | INFO | train_grpo_train | metrics_logged mode=train step=17 2026-04-13 12:47:40,694 | INFO | train_grpo_train | metrics_logged mode=train step=18 2026-04-13 12:47:47,094 | INFO | train_grpo_train | metrics_logged mode=train step=19 2026-04-13 12:47:53,648 | INFO | train_grpo_train | metrics_logged mode=train step=20 2026-04-13 12:47:59,529 | INFO | train_grpo_train | metrics_logged mode=train step=21 2026-04-13 12:48:05,530 | INFO | train_grpo_train | metrics_logged mode=train step=22 2026-04-13 12:48:11,327 | INFO | train_grpo_train | metrics_logged mode=train step=23 2026-04-13 12:48:17,974 | INFO | train_grpo_train | metrics_logged mode=train step=24 2026-04-13 12:48:25,198 | INFO | train_grpo_train | metrics_logged mode=train step=25 2026-04-13 12:48:31,352 | INFO | train_grpo_train | metrics_logged mode=train step=26 2026-04-13 12:48:38,650 | INFO | train_grpo_train | metrics_logged mode=train step=27 2026-04-13 12:48:44,812 | INFO | train_grpo_train | metrics_logged mode=train step=28 2026-04-13 12:48:52,585 | INFO | train_grpo_train | metrics_logged mode=train step=29 2026-04-13 12:48:58,668 | INFO | train_grpo_train | metrics_logged mode=train step=30 2026-04-13 12:49:04,931 | INFO | train_grpo_train | metrics_logged mode=train step=31 2026-04-13 12:49:10,422 | INFO | train_grpo_train | metrics_logged mode=train step=32 2026-04-13 12:49:16,588 | INFO | train_grpo_train | metrics_logged mode=train step=33 2026-04-13 12:49:22,781 | INFO | train_grpo_train | metrics_logged mode=train step=34 2026-04-13 12:49:28,594 | INFO | train_grpo_train | metrics_logged mode=train step=35 2026-04-13 12:49:34,881 | INFO | train_grpo_train | metrics_logged mode=train step=36 2026-04-13 12:49:40,916 | INFO | train_grpo_train | metrics_logged mode=train step=37 2026-04-13 12:49:46,867 | INFO | train_grpo_train | metrics_logged mode=train step=38 2026-04-13 12:49:52,969 | INFO | train_grpo_train | metrics_logged mode=train step=39 2026-04-13 12:49:59,089 | INFO | train_grpo_train | metrics_logged mode=train step=40 2026-04-13 12:50:05,064 | INFO | train_grpo_train | metrics_logged mode=train step=41 2026-04-13 12:50:11,062 | INFO | train_grpo_train | metrics_logged mode=train step=42 2026-04-13 12:50:17,794 | INFO | train_grpo_train | metrics_logged mode=train step=43 2026-04-13 12:50:24,908 | INFO | train_grpo_train | metrics_logged mode=train step=44 2026-04-13 12:50:30,978 | INFO | train_grpo_train | metrics_logged mode=train step=45 2026-04-13 12:50:36,876 | INFO | train_grpo_train | metrics_logged mode=train step=46 2026-04-13 12:50:42,935 | INFO | train_grpo_train | metrics_logged mode=train step=47 2026-04-13 12:50:48,839 | INFO | train_grpo_train | metrics_logged mode=train step=48 2026-04-13 12:50:56,538 | INFO | train_grpo_train | metrics_logged mode=train step=49 2026-04-13 12:51:03,897 | INFO | train_grpo_train | metrics_logged mode=train step=50 2026-04-13 12:52:02,196 | INFO | train_grpo_train | metrics_logged mode=eval step=50 2026-04-13 12:52:11,231 | INFO | train_grpo_train | metrics_logged mode=train step=51 2026-04-13 12:52:18,789 | INFO | train_grpo_train | metrics_logged mode=train step=52 2026-04-13 12:52:25,374 | INFO | train_grpo_train | metrics_logged mode=train step=53 2026-04-13 12:52:33,420 | INFO | train_grpo_train | metrics_logged mode=train step=54 2026-04-13 12:52:39,726 | INFO | train_grpo_train | metrics_logged mode=train step=55 2026-04-13 12:52:48,186 | INFO | train_grpo_train | metrics_logged mode=train step=56 2026-04-13 12:52:55,172 | INFO | train_grpo_train | metrics_logged mode=train step=57 2026-04-13 12:53:02,102 | INFO | train_grpo_train | metrics_logged mode=train step=58 2026-04-13 12:53:08,731 | INFO | train_grpo_train | metrics_logged mode=train step=59 2026-04-13 12:53:15,009 | INFO | train_grpo_train | metrics_logged mode=train step=60 2026-04-13 12:53:21,624 | INFO | train_grpo_train | metrics_logged mode=train step=61 2026-04-13 12:53:29,421 | INFO | train_grpo_train | metrics_logged mode=train step=62 2026-04-13 12:53:36,291 | INFO | train_grpo_train | metrics_logged mode=train step=63 2026-04-13 12:53:43,039 | INFO | train_grpo_train | metrics_logged mode=train step=64 2026-04-13 12:53:49,490 | INFO | train_grpo_train | metrics_logged mode=train step=65 2026-04-13 12:53:59,956 | INFO | train_grpo_train | metrics_logged mode=train step=66 2026-04-13 12:54:06,749 | INFO | train_grpo_train | metrics_logged mode=train step=67 2026-04-13 12:54:12,758 | INFO | train_grpo_train | metrics_logged mode=train step=68 2026-04-13 12:54:18,963 | INFO | train_grpo_train | metrics_logged mode=train step=69 2026-04-13 12:54:25,658 | INFO | train_grpo_train | metrics_logged mode=train step=70 2026-04-13 12:54:32,138 | INFO | train_grpo_train | metrics_logged mode=train step=71 2026-04-13 12:54:38,672 | INFO | train_grpo_train | metrics_logged mode=train step=72 2026-04-13 12:54:44,989 | INFO | train_grpo_train | metrics_logged mode=train step=73 2026-04-13 12:54:51,224 | INFO | train_grpo_train | metrics_logged mode=train step=74 2026-04-13 12:54:58,014 | INFO | train_grpo_train | metrics_logged mode=train step=75 2026-04-13 12:55:03,897 | INFO | train_grpo_train | metrics_logged mode=train step=76 2026-04-13 12:55:10,150 | INFO | train_grpo_train | metrics_logged mode=train step=77 2026-04-13 12:55:17,096 | INFO | train_grpo_train | metrics_logged mode=train step=78 2026-04-13 12:55:23,623 | INFO | train_grpo_train | metrics_logged mode=train step=79 2026-04-13 12:55:30,093 | INFO | train_grpo_train | metrics_logged mode=train step=80 2026-04-13 12:55:37,037 | INFO | train_grpo_train | metrics_logged mode=train step=81 2026-04-13 12:55:43,383 | INFO | train_grpo_train | metrics_logged mode=train step=82 2026-04-13 12:55:49,582 | INFO | train_grpo_train | metrics_logged mode=train step=83 2026-04-13 12:55:55,884 | INFO | train_grpo_train | metrics_logged mode=train step=84 2026-04-13 12:56:01,663 | INFO | train_grpo_train | metrics_logged mode=train step=85 2026-04-13 12:56:08,171 | INFO | train_grpo_train | metrics_logged mode=train step=86 2026-04-13 12:56:13,903 | INFO | train_grpo_train | metrics_logged mode=train step=87 2026-04-13 12:56:20,513 | INFO | train_grpo_train | metrics_logged mode=train step=88 2026-04-13 12:56:27,428 | INFO | train_grpo_train | metrics_logged mode=train step=89 2026-04-13 12:56:33,210 | INFO | train_grpo_train | metrics_logged mode=train step=90 2026-04-13 12:56:39,897 | INFO | train_grpo_train | metrics_logged mode=train step=91 2026-04-13 12:56:46,247 | INFO | train_grpo_train | metrics_logged mode=train step=92 2026-04-13 12:56:52,679 | INFO | train_grpo_train | metrics_logged mode=train step=93 2026-04-13 12:56:58,861 | INFO | train_grpo_train | metrics_logged mode=train step=94 2026-04-13 12:57:05,859 | INFO | train_grpo_train | metrics_logged mode=train step=95 2026-04-13 12:57:11,957 | INFO | train_grpo_train | metrics_logged mode=train step=96 2026-04-13 12:57:17,851 | INFO | train_grpo_train | metrics_logged mode=train step=97 2026-04-13 12:57:24,145 | INFO | train_grpo_train | metrics_logged mode=train step=98 2026-04-13 12:57:30,207 | INFO | train_grpo_train | metrics_logged mode=train step=99 2026-04-13 12:57:36,537 | INFO | train_grpo_train | metrics_logged mode=train step=100 2026-04-13 12:58:15,967 | INFO | train_grpo_train | metrics_logged mode=eval step=100 2026-04-13 12:58:25,223 | INFO | train_grpo_train | metrics_logged mode=train step=101 2026-04-13 12:58:32,785 | INFO | train_grpo_train | metrics_logged mode=train step=102 2026-04-13 12:58:39,106 | INFO | train_grpo_train | metrics_logged mode=train step=103 2026-04-13 12:58:45,377 | INFO | train_grpo_train | metrics_logged mode=train step=104 2026-04-13 12:58:52,123 | INFO | train_grpo_train | metrics_logged mode=train step=105 2026-04-13 12:58:58,798 | INFO | train_grpo_train | metrics_logged mode=train step=106 2026-04-13 12:59:04,883 | INFO | train_grpo_train | metrics_logged mode=train step=107 2026-04-13 12:59:10,926 | INFO | train_grpo_train | metrics_logged mode=train step=108 2026-04-13 12:59:17,454 | INFO | train_grpo_train | metrics_logged mode=train step=109 2026-04-13 12:59:23,493 | INFO | train_grpo_train | metrics_logged mode=train step=110 2026-04-13 12:59:30,885 | INFO | train_grpo_train | metrics_logged mode=train step=111 2026-04-13 12:59:36,670 | INFO | train_grpo_train | metrics_logged mode=train step=112 2026-04-13 12:59:42,945 | INFO | train_grpo_train | metrics_logged mode=train step=113 2026-04-13 12:59:49,243 | INFO | train_grpo_train | metrics_logged mode=train step=114 2026-04-13 12:59:55,852 | INFO | train_grpo_train | metrics_logged mode=train step=115 2026-04-13 13:00:01,971 | INFO | train_grpo_train | metrics_logged mode=train step=116 2026-04-13 13:00:08,243 | INFO | train_grpo_train | metrics_logged mode=train step=117 2026-04-13 13:00:15,748 | INFO | train_grpo_train | metrics_logged mode=train step=118 2026-04-13 13:00:22,353 | INFO | train_grpo_train | metrics_logged mode=train step=119 2026-04-13 13:00:30,229 | INFO | train_grpo_train | metrics_logged mode=train step=120 2026-04-13 13:00:38,274 | INFO | train_grpo_train | metrics_logged mode=train step=121 2026-04-13 13:00:45,853 | INFO | train_grpo_train | metrics_logged mode=train step=122 2026-04-13 13:00:53,279 | INFO | train_grpo_train | metrics_logged mode=train step=123 2026-04-13 13:00:59,133 | INFO | train_grpo_train | metrics_logged mode=train step=124 2026-04-13 13:01:06,055 | INFO | train_grpo_train | metrics_logged mode=train step=125 2026-04-13 13:01:15,921 | INFO | train_grpo_train | metrics_logged mode=train step=126 2026-04-13 13:01:22,411 | INFO | train_grpo_train | metrics_logged mode=train step=127 2026-04-13 13:01:29,080 | INFO | train_grpo_train | metrics_logged mode=train step=128 2026-04-13 13:01:35,502 | INFO | train_grpo_train | metrics_logged mode=train step=129 2026-04-13 13:01:42,514 | INFO | train_grpo_train | metrics_logged mode=train step=130 2026-04-13 13:01:48,463 | INFO | train_grpo_train | metrics_logged mode=train step=131 2026-04-13 13:01:56,260 | INFO | train_grpo_train | metrics_logged mode=train step=132 2026-04-13 13:02:03,261 | INFO | train_grpo_train | metrics_logged mode=train step=133 2026-04-13 13:02:10,427 | INFO | train_grpo_train | metrics_logged mode=train step=134 2026-04-13 13:02:17,380 | INFO | train_grpo_train | metrics_logged mode=train step=135 2026-04-13 13:02:24,959 | INFO | train_grpo_train | metrics_logged mode=train step=136 2026-04-13 13:02:31,272 | INFO | train_grpo_train | metrics_logged mode=train step=137 2026-04-13 13:02:37,060 | INFO | train_grpo_train | metrics_logged mode=train step=138 2026-04-13 13:02:42,996 | INFO | train_grpo_train | metrics_logged mode=train step=139 2026-04-13 13:02:49,466 | INFO | train_grpo_train | metrics_logged mode=train step=140 2026-04-13 13:02:58,889 | INFO | train_grpo_train | metrics_logged mode=train step=141 2026-04-13 13:03:04,859 | INFO | train_grpo_train | metrics_logged mode=train step=142 2026-04-13 13:03:11,995 | INFO | train_grpo_train | metrics_logged mode=train step=143 2026-04-13 13:03:18,154 | INFO | train_grpo_train | metrics_logged mode=train step=144 2026-04-13 13:03:24,729 | INFO | train_grpo_train | metrics_logged mode=train step=145 2026-04-13 13:03:30,757 | INFO | train_grpo_train | metrics_logged mode=train step=146 2026-04-13 13:03:37,069 | INFO | train_grpo_train | metrics_logged mode=train step=147 2026-04-13 13:03:44,057 | INFO | train_grpo_train | metrics_logged mode=train step=148 2026-04-13 13:03:51,465 | INFO | train_grpo_train | metrics_logged mode=train step=149 2026-04-13 13:03:58,422 | INFO | train_grpo_train | metrics_logged mode=train step=150 2026-04-13 13:04:39,260 | INFO | train_grpo_train | metrics_logged mode=eval step=150 2026-04-13 13:04:47,310 | INFO | train_grpo_train | metrics_logged mode=train step=151 2026-04-13 13:04:54,461 | INFO | train_grpo_train | metrics_logged mode=train step=152 2026-04-13 13:05:00,257 | INFO | train_grpo_train | metrics_logged mode=train step=153 2026-04-13 13:05:06,505 | INFO | train_grpo_train | metrics_logged mode=train step=154 2026-04-13 13:05:12,493 | INFO | train_grpo_train | metrics_logged mode=train step=155 2026-04-13 13:05:18,467 | INFO | train_grpo_train | metrics_logged mode=train step=156 2026-04-13 13:05:24,366 | INFO | train_grpo_train | metrics_logged mode=train step=157 2026-04-13 13:05:30,386 | INFO | train_grpo_train | metrics_logged mode=train step=158 2026-04-13 13:05:36,391 | INFO | train_grpo_train | metrics_logged mode=train step=159 2026-04-13 13:05:42,246 | INFO | train_grpo_train | metrics_logged mode=train step=160 2026-04-13 13:05:48,171 | INFO | train_grpo_train | metrics_logged mode=train step=161 2026-04-13 13:05:54,201 | INFO | train_grpo_train | metrics_logged mode=train step=162 2026-04-13 13:06:00,105 | INFO | train_grpo_train | metrics_logged mode=train step=163 2026-04-13 13:06:06,799 | INFO | train_grpo_train | metrics_logged mode=train step=164 2026-04-13 13:06:12,510 | INFO | train_grpo_train | metrics_logged mode=train step=165 2026-04-13 13:06:18,843 | INFO | train_grpo_train | metrics_logged mode=train step=166 2026-04-13 13:06:25,190 | INFO | train_grpo_train | metrics_logged mode=train step=167 2026-04-13 13:06:31,164 | INFO | train_grpo_train | metrics_logged mode=train step=168 2026-04-13 13:06:37,799 | INFO | train_grpo_train | metrics_logged mode=train step=169 2026-04-13 13:06:43,756 | INFO | train_grpo_train | metrics_logged mode=train step=170 2026-04-13 13:06:49,968 | INFO | train_grpo_train | metrics_logged mode=train step=171 2026-04-13 13:06:55,918 | INFO | train_grpo_train | metrics_logged mode=train step=172 2026-04-13 13:07:01,714 | INFO | train_grpo_train | metrics_logged mode=train step=173 2026-04-13 13:07:07,706 | INFO | train_grpo_train | metrics_logged mode=train step=174 2026-04-13 13:07:13,991 | INFO | train_grpo_train | metrics_logged mode=train step=175 2026-04-13 13:07:19,779 | INFO | train_grpo_train | metrics_logged mode=train step=176 2026-04-13 13:07:25,822 | INFO | train_grpo_train | metrics_logged mode=train step=177 2026-04-13 13:07:33,305 | INFO | train_grpo_train | metrics_logged mode=train step=178 2026-04-13 13:07:39,659 | INFO | train_grpo_train | metrics_logged mode=train step=179 2026-04-13 13:07:46,133 | INFO | train_grpo_train | metrics_logged mode=train step=180 2026-04-13 13:07:52,238 | INFO | train_grpo_train | metrics_logged mode=train step=181 2026-04-13 13:07:58,387 | INFO | train_grpo_train | metrics_logged mode=train step=182 2026-04-13 13:08:04,190 | INFO | train_grpo_train | metrics_logged mode=train step=183 2026-04-13 13:08:10,081 | INFO | train_grpo_train | metrics_logged mode=train step=184 2026-04-13 13:08:15,979 | INFO | train_grpo_train | metrics_logged mode=train step=185 2026-04-13 13:08:22,206 | INFO | train_grpo_train | metrics_logged mode=train step=186 2026-04-13 13:08:29,450 | INFO | train_grpo_train | metrics_logged mode=train step=187 2026-04-13 13:08:35,860 | INFO | train_grpo_train | metrics_logged mode=train step=188 2026-04-13 13:08:41,580 | INFO | train_grpo_train | metrics_logged mode=train step=189 2026-04-13 13:08:47,896 | INFO | train_grpo_train | metrics_logged mode=train step=190 2026-04-13 13:08:55,175 | INFO | train_grpo_train | metrics_logged mode=train step=191 2026-04-13 13:09:01,019 | INFO | train_grpo_train | metrics_logged mode=train step=192 2026-04-13 13:09:09,902 | INFO | train_grpo_train | metrics_logged mode=train step=193 2026-04-13 13:09:20,972 | INFO | train_grpo_train | metrics_logged mode=train step=194 2026-04-13 13:09:27,103 | INFO | train_grpo_train | metrics_logged mode=train step=195 2026-04-13 13:09:32,684 | INFO | train_grpo_train | metrics_logged mode=train step=196 2026-04-13 13:09:38,551 | INFO | train_grpo_train | metrics_logged mode=train step=197 2026-04-13 13:09:44,520 | INFO | train_grpo_train | metrics_logged mode=train step=198 2026-04-13 13:09:50,372 | INFO | train_grpo_train | metrics_logged mode=train step=199 2026-04-13 13:10:00,968 | INFO | train_grpo_train | metrics_logged mode=train step=200 2026-04-13 13:10:58,989 | INFO | train_grpo_train | metrics_logged mode=eval step=200