2026-04-12 15:23:22,570 | INFO | train_grpo_train | mode=train 2026-04-12 15:25:19,508 | INFO | train_grpo_train | dataset_id=Shaer-AI/ashaar-enhanced-desc-baseform-final-sft-lte20-min500-splits-grpo-meter-count-v1 train_size=24897 eval_size=104 2026-04-12 15:25:19,509 | INFO | train_grpo_train | source_dataset_id=Shaer-AI/ashaar-with-enhanced-descriptions-baseform-final-sft-lte20-min500-splits test_size=204 hard_diagnostic_size=3126 2026-04-12 15:25:19,509 | INFO | train_grpo_train | active_rewards=['meter', 'count_adherence', 'arabic_clean', 'hard_gate', 'arabic_floor', 'count_floor', 'lexical_plausibility', 'judge_quality', 'repeat_penalty', 'repeat_floor', 'near_duplicate_penalty', 'opening_diversity', 'distinct_2', 'total_composite'] 2026-04-12 15:25:19,509 | INFO | train_grpo_train | reward_weights={'meter': 0.0, 'count_adherence': 0.0, 'arabic_clean': 0.0, 'hard_gate': 0.0, 'arabic_floor': 0.0, 'count_floor': 0.0, 'lexical_plausibility': 0.0, 'judge_quality': 0.0, 'repeat_penalty': 0.0, 'repeat_floor': 0.0, 'near_duplicate_penalty': 0.0, 'opening_diversity': 0.0, 'distinct_2': 0.0, 'total_composite': 1.0} 2026-04-12 15:25:19,509 | INFO | train_grpo_train | output_repo=Shaer-AI/Shaer-adapters-grpo-friend-v1 2026-04-12 15:25:19,509 | INFO | train_grpo_train | train_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_drop_trio/cap_3000/selected_manifest.csv 2026-04-12 15:25:19,509 | INFO | train_grpo_train | hard_diagnostic_manifest_path=/root/workspace/Shaer/grpo/outputs/curated_meter_count_drop_trio/hard_diagnostic_cap_256/selected_manifest.csv 2026-04-12 15:25:19,509 | INFO | train_grpo_train | trainable_params=159907840 total_params=7160467456 trainable_ratio=0.022332 2026-04-12 15:25:19,509 | INFO | train_grpo_train | resume_decision={"timestamp_utc": "2026-04-12T15:25:00Z", "resume_mode": "fresh", "requested_spec": "", "result": "fresh", "reason": "explicit_fresh", "local_resume_path": null, "remote_repo": null, "remote_prefix": null, "compatibility": "unchecked", "config_fingerprint": "429b334e6c80dfa9b81f2594e6165bdb27e9289404e07f5b1493fe2fe6227203"} 2026-04-12 15:25:19,509 | INFO | train_grpo_train | starting trainer.train() 2026-04-12 15:25:26,556 | INFO | train_grpo_train | metrics_logged mode=train step=1 2026-04-12 15:25:36,455 | INFO | train_grpo_train | metrics_logged mode=train step=2 2026-04-12 15:25:44,675 | INFO | train_grpo_train | metrics_logged mode=train step=3 2026-04-12 15:25:56,461 | INFO | train_grpo_train | metrics_logged mode=train step=4 2026-04-12 15:26:05,324 | INFO | train_grpo_train | metrics_logged mode=train step=5 2026-04-12 15:26:14,563 | INFO | train_grpo_train | metrics_logged mode=train step=6 2026-04-12 15:26:23,776 | INFO | train_grpo_train | metrics_logged mode=train step=7 2026-04-12 15:26:37,271 | INFO | train_grpo_train | metrics_logged mode=train step=8 2026-04-12 15:26:48,133 | INFO | train_grpo_train | metrics_logged mode=train step=9 2026-04-12 15:26:58,369 | INFO | train_grpo_train | metrics_logged mode=train step=10 2026-04-12 15:27:06,948 | INFO | train_grpo_train | metrics_logged mode=train step=11 2026-04-12 15:27:21,196 | INFO | train_grpo_train | metrics_logged mode=train step=12 2026-04-12 15:27:30,804 | INFO | train_grpo_train | metrics_logged mode=train step=13 2026-04-12 15:27:40,412 | INFO | train_grpo_train | metrics_logged mode=train step=14 2026-04-12 15:27:50,233 | INFO | train_grpo_train | metrics_logged mode=train step=15 2026-04-12 15:28:06,334 | INFO | train_grpo_train | metrics_logged mode=train step=16 2026-04-12 15:28:15,756 | INFO | train_grpo_train | metrics_logged mode=train step=17 2026-04-12 15:28:26,774 | INFO | train_grpo_train | metrics_logged mode=train step=18 2026-04-12 15:28:42,237 | INFO | train_grpo_train | metrics_logged mode=train step=19 2026-04-12 15:28:52,967 | INFO | train_grpo_train | metrics_logged mode=train step=20 2026-04-12 15:29:03,637 | INFO | train_grpo_train | metrics_logged mode=train step=21 2026-04-12 15:29:13,704 | INFO | train_grpo_train | metrics_logged mode=train step=22 2026-04-12 15:29:30,023 | INFO | train_grpo_train | metrics_logged mode=train step=23 2026-04-12 15:29:42,156 | INFO | train_grpo_train | metrics_logged mode=train step=24 2026-04-12 15:29:56,689 | INFO | train_grpo_train | metrics_logged mode=train step=25 2026-04-12 15:30:07,112 | INFO | train_grpo_train | metrics_logged mode=train step=26 2026-04-12 15:30:23,014 | INFO | train_grpo_train | metrics_logged mode=train step=27 2026-04-12 15:30:33,308 | INFO | train_grpo_train | metrics_logged mode=train step=28 2026-04-12 15:30:46,367 | INFO | train_grpo_train | metrics_logged mode=train step=29 2026-04-12 15:30:57,375 | INFO | train_grpo_train | metrics_logged mode=train step=30 2026-04-12 15:31:08,594 | INFO | train_grpo_train | metrics_logged mode=train step=31 2026-04-12 15:31:18,996 | INFO | train_grpo_train | metrics_logged mode=train step=32 2026-04-12 15:31:31,415 | INFO | train_grpo_train | metrics_logged mode=train step=33 2026-04-12 15:31:42,468 | INFO | train_grpo_train | metrics_logged mode=train step=34 2026-04-12 15:31:57,918 | INFO | train_grpo_train | metrics_logged mode=train step=35 2026-04-12 15:32:14,479 | INFO | train_grpo_train | metrics_logged mode=train step=36 2026-04-12 15:32:25,839 | INFO | train_grpo_train | metrics_logged mode=train step=37 2026-04-12 15:32:35,875 | INFO | train_grpo_train | metrics_logged mode=train step=38 2026-04-12 15:32:51,316 | INFO | train_grpo_train | metrics_logged mode=train step=39 2026-04-12 15:33:02,149 | INFO | train_grpo_train | metrics_logged mode=train step=40 2026-04-12 15:33:08,556 | INFO | train_grpo_train | metrics_logged mode=train step=41 2026-04-12 15:33:23,478 | INFO | train_grpo_train | metrics_logged mode=train step=42 2026-04-12 15:33:34,532 | INFO | train_grpo_train | metrics_logged mode=train step=43 2026-04-12 15:33:45,093 | INFO | train_grpo_train | metrics_logged mode=train step=44 2026-04-12 15:33:55,941 | INFO | train_grpo_train | metrics_logged mode=train step=45 2026-04-12 15:34:05,889 | INFO | train_grpo_train | metrics_logged mode=train step=46 2026-04-12 15:34:16,001 | INFO | train_grpo_train | metrics_logged mode=train step=47 2026-04-12 15:34:27,813 | INFO | train_grpo_train | metrics_logged mode=train step=48 2026-04-12 15:34:39,112 | INFO | train_grpo_train | metrics_logged mode=train step=49 2026-04-12 15:34:49,201 | INFO | train_grpo_train | metrics_logged mode=train step=50 2026-04-12 15:37:32,865 | INFO | train_grpo_train | metrics_logged mode=eval step=50 2026-04-12 15:37:47,465 | INFO | train_grpo_train | metrics_logged mode=train step=51 2026-04-12 15:37:57,683 | INFO | train_grpo_train | metrics_logged mode=train step=52 2026-04-12 15:38:09,803 | INFO | train_grpo_train | metrics_logged mode=train step=53 2026-04-12 15:38:20,650 | INFO | train_grpo_train | metrics_logged mode=train step=54 2026-04-12 15:38:36,459 | INFO | train_grpo_train | metrics_logged mode=train step=55 2026-04-12 15:38:45,901 | INFO | train_grpo_train | metrics_logged mode=train step=56 2026-04-12 15:38:56,557 | INFO | train_grpo_train | metrics_logged mode=train step=57 2026-04-12 15:39:06,416 | INFO | train_grpo_train | metrics_logged mode=train step=58 2026-04-12 15:39:14,971 | INFO | train_grpo_train | metrics_logged mode=train step=59 2026-04-12 15:39:26,323 | INFO | train_grpo_train | metrics_logged mode=train step=60 2026-04-12 15:39:38,345 | INFO | train_grpo_train | metrics_logged mode=train step=61 2026-04-12 15:39:49,455 | INFO | train_grpo_train | metrics_logged mode=train step=62 2026-04-12 15:39:59,484 | INFO | train_grpo_train | metrics_logged mode=train step=63 2026-04-12 15:40:10,429 | INFO | train_grpo_train | metrics_logged mode=train step=64 2026-04-12 15:40:21,491 | INFO | train_grpo_train | metrics_logged mode=train step=65 2026-04-12 15:40:30,014 | INFO | train_grpo_train | metrics_logged mode=train step=66 2026-04-12 15:40:40,784 | INFO | train_grpo_train | metrics_logged mode=train step=67 2026-04-12 15:40:50,504 | INFO | train_grpo_train | metrics_logged mode=train step=68 2026-04-12 15:40:57,817 | INFO | train_grpo_train | metrics_logged mode=train step=69 2026-04-12 15:41:14,678 | INFO | train_grpo_train | metrics_logged mode=train step=70 2026-04-12 15:41:24,430 | INFO | train_grpo_train | metrics_logged mode=train step=71 2026-04-12 15:41:36,368 | INFO | train_grpo_train | metrics_logged mode=train step=72 2026-04-12 15:41:46,630 | INFO | train_grpo_train | metrics_logged mode=train step=73 2026-04-12 15:41:56,026 | INFO | train_grpo_train | metrics_logged mode=train step=74 2026-04-12 15:42:12,416 | INFO | train_grpo_train | metrics_logged mode=train step=75 2026-04-12 15:42:23,813 | INFO | train_grpo_train | metrics_logged mode=train step=76 2026-04-12 15:42:35,678 | INFO | train_grpo_train | metrics_logged mode=train step=77 2026-04-12 15:42:47,998 | INFO | train_grpo_train | metrics_logged mode=train step=78 2026-04-12 15:43:00,117 | INFO | train_grpo_train | metrics_logged mode=train step=79 2026-04-12 15:43:08,943 | INFO | train_grpo_train | metrics_logged mode=train step=80 2026-04-12 15:43:18,638 | INFO | train_grpo_train | metrics_logged mode=train step=81 2026-04-12 15:43:28,022 | INFO | train_grpo_train | metrics_logged mode=train step=82 2026-04-12 15:43:37,977 | INFO | train_grpo_train | metrics_logged mode=train step=83 2026-04-12 15:43:48,008 | INFO | train_grpo_train | metrics_logged mode=train step=84 2026-04-12 15:43:56,493 | INFO | train_grpo_train | metrics_logged mode=train step=85 2026-04-12 15:44:06,466 | INFO | train_grpo_train | metrics_logged mode=train step=86 2026-04-12 15:44:16,570 | INFO | train_grpo_train | metrics_logged mode=train step=87 2026-04-12 15:44:27,269 | INFO | train_grpo_train | metrics_logged mode=train step=88 2026-04-12 15:44:36,923 | INFO | train_grpo_train | metrics_logged mode=train step=89 2026-04-12 15:44:48,357 | INFO | train_grpo_train | metrics_logged mode=train step=90 2026-04-12 15:45:00,092 | INFO | train_grpo_train | metrics_logged mode=train step=91 2026-04-12 15:45:12,720 | INFO | train_grpo_train | metrics_logged mode=train step=92 2026-04-12 15:45:23,749 | INFO | train_grpo_train | metrics_logged mode=train step=93 2026-04-12 15:45:32,791 | INFO | train_grpo_train | metrics_logged mode=train step=94 2026-04-12 15:45:42,655 | INFO | train_grpo_train | metrics_logged mode=train step=95 2026-04-12 15:45:53,249 | INFO | train_grpo_train | metrics_logged mode=train step=96 2026-04-12 15:46:01,954 | INFO | train_grpo_train | metrics_logged mode=train step=97 2026-04-12 15:46:11,923 | INFO | train_grpo_train | metrics_logged mode=train step=98 2026-04-12 15:46:21,193 | INFO | train_grpo_train | metrics_logged mode=train step=99 2026-04-12 15:46:31,245 | INFO | train_grpo_train | metrics_logged mode=train step=100 2026-04-12 15:49:05,410 | INFO | train_grpo_train | metrics_logged mode=eval step=100