INFO __main__ Thu, 25 Jun 2026 14:38:32 Writing config to /rep/nhamad/ArabicNER/B1/args.json INFO numexpr.utils Thu, 25 Jun 2026 14:38:33 Note: NumExpr detected 16 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 8. INFO numexpr.utils Thu, 25 Jun 2026 14:38:33 NumExpr defaulting to 8 threads. INFO arabiner.utils.data Thu, 25 Jun 2026 14:38:34 3508 batches found INFO arabiner.utils.data Thu, 25 Jun 2026 14:38:34 393 batches found INFO arabiner.utils.data Thu, 25 Jun 2026 14:38:34 786 batches found INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:43 Epoch 0 | Batch 10/3508 | Timestep 10 | LR 0.0000100000 | Loss 18.421261 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:45 Epoch 0 | Batch 20/3508 | Timestep 20 | LR 0.0000100000 | Loss 13.482733 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:46 Epoch 0 | Batch 30/3508 | Timestep 30 | LR 0.0000100000 | Loss 10.449072 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:49 Epoch 0 | Batch 40/3508 | Timestep 40 | LR 0.0000100000 | Loss 9.463489 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:51 Epoch 0 | Batch 50/3508 | Timestep 50 | LR 0.0000100000 | Loss 7.723367 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:53 Epoch 0 | Batch 60/3508 | Timestep 60 | LR 0.0000100000 | Loss 6.930207 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:55 Epoch 0 | Batch 70/3508 | Timestep 70 | LR 0.0000100000 | Loss 6.289130 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:57 Epoch 0 | Batch 80/3508 | Timestep 80 | LR 0.0000100000 | Loss 5.888531 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:38:59 Epoch 0 | Batch 90/3508 | Timestep 90 | LR 0.0000100000 | Loss 5.380591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:01 Epoch 0 | Batch 100/3508 | Timestep 100 | LR 0.0000100000 | Loss 4.984424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:04 Epoch 0 | Batch 110/3508 | Timestep 110 | LR 0.0000100000 | Loss 4.769996 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:05 Epoch 0 | Batch 120/3508 | Timestep 120 | LR 0.0000100000 | Loss 4.503316 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:07 Epoch 0 | Batch 130/3508 | Timestep 130 | LR 0.0000100000 | Loss 4.440650 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:09 Epoch 0 | Batch 140/3508 | Timestep 140 | LR 0.0000100000 | Loss 4.127453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:12 Epoch 0 | Batch 150/3508 | Timestep 150 | LR 0.0000100000 | Loss 3.755969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:14 Epoch 0 | Batch 160/3508 | Timestep 160 | LR 0.0000100000 | Loss 3.942947 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:17 Epoch 0 | Batch 170/3508 | Timestep 170 | LR 0.0000100000 | Loss 3.416827 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:18 Epoch 0 | Batch 180/3508 | Timestep 180 | LR 0.0000100000 | Loss 3.226857 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:21 Epoch 0 | Batch 190/3508 | Timestep 190 | LR 0.0000100000 | Loss 3.134721 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:23 Epoch 0 | Batch 200/3508 | Timestep 200 | LR 0.0000100000 | Loss 2.970428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:25 Epoch 0 | Batch 210/3508 | Timestep 210 | LR 0.0000100000 | Loss 2.740522 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:26 Epoch 0 | Batch 220/3508 | Timestep 220 | LR 0.0000100000 | Loss 2.775716 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:29 Epoch 0 | Batch 230/3508 | Timestep 230 | LR 0.0000100000 | Loss 2.376278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:31 Epoch 0 | Batch 240/3508 | Timestep 240 | LR 0.0000100000 | Loss 2.202651 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:33 Epoch 0 | Batch 250/3508 | Timestep 250 | LR 0.0000100000 | Loss 1.995128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:35 Epoch 0 | Batch 260/3508 | Timestep 260 | LR 0.0000100000 | Loss 1.967013 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:37 Epoch 0 | Batch 270/3508 | Timestep 270 | LR 0.0000100000 | Loss 1.900507 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:39 Epoch 0 | Batch 280/3508 | Timestep 280 | LR 0.0000100000 | Loss 1.674596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:41 Epoch 0 | Batch 290/3508 | Timestep 290 | LR 0.0000100000 | Loss 1.591545 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:44 Epoch 0 | Batch 300/3508 | Timestep 300 | LR 0.0000100000 | Loss 1.476819 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:46 Epoch 0 | Batch 310/3508 | Timestep 310 | LR 0.0000100000 | Loss 1.386812 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:48 Epoch 0 | Batch 320/3508 | Timestep 320 | LR 0.0000100000 | Loss 1.370275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:50 Epoch 0 | Batch 330/3508 | Timestep 330 | LR 0.0000100000 | Loss 1.313471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:51 Epoch 0 | Batch 340/3508 | Timestep 340 | LR 0.0000100000 | Loss 1.283865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:54 Epoch 0 | Batch 350/3508 | Timestep 350 | LR 0.0000100000 | Loss 1.256528 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:56 Epoch 0 | Batch 360/3508 | Timestep 360 | LR 0.0000100000 | Loss 1.217415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:39:59 Epoch 0 | Batch 370/3508 | Timestep 370 | LR 0.0000100000 | Loss 1.066910 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:01 Epoch 0 | Batch 380/3508 | Timestep 380 | LR 0.0000100000 | Loss 1.242293 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:04 Epoch 0 | Batch 390/3508 | Timestep 390 | LR 0.0000100000 | Loss 1.101511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:06 Epoch 0 | Batch 400/3508 | Timestep 400 | LR 0.0000100000 | Loss 0.930241 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:08 Epoch 0 | Batch 410/3508 | Timestep 410 | LR 0.0000100000 | Loss 1.063064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:10 Epoch 0 | Batch 420/3508 | Timestep 420 | LR 0.0000100000 | Loss 1.202270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:12 Epoch 0 | Batch 430/3508 | Timestep 430 | LR 0.0000100000 | Loss 1.719405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:14 Epoch 0 | Batch 440/3508 | Timestep 440 | LR 0.0000100000 | Loss 0.839282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:16 Epoch 0 | Batch 450/3508 | Timestep 450 | LR 0.0000100000 | Loss 1.214336 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:18 Epoch 0 | Batch 460/3508 | Timestep 460 | LR 0.0000100000 | Loss 0.835159 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:20 Epoch 0 | Batch 470/3508 | Timestep 470 | LR 0.0000100000 | Loss 1.192278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:23 Epoch 0 | Batch 480/3508 | Timestep 480 | LR 0.0000100000 | Loss 1.108158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:25 Epoch 0 | Batch 490/3508 | Timestep 490 | LR 0.0000100000 | Loss 0.765008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:27 Epoch 0 | Batch 500/3508 | Timestep 500 | LR 0.0000100000 | Loss 0.931902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:29 Epoch 0 | Batch 510/3508 | Timestep 510 | LR 0.0000100000 | Loss 0.775845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:32 Epoch 0 | Batch 520/3508 | Timestep 520 | LR 0.0000100000 | Loss 0.923960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:33 Epoch 0 | Batch 530/3508 | Timestep 530 | LR 0.0000100000 | Loss 0.804765 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:36 Epoch 0 | Batch 540/3508 | Timestep 540 | LR 0.0000100000 | Loss 0.705818 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:38 Epoch 0 | Batch 550/3508 | Timestep 550 | LR 0.0000100000 | Loss 1.037187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:40 Epoch 0 | Batch 560/3508 | Timestep 560 | LR 0.0000100000 | Loss 0.646076 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:42 Epoch 0 | Batch 570/3508 | Timestep 570 | LR 0.0000100000 | Loss 0.728444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:44 Epoch 0 | Batch 580/3508 | Timestep 580 | LR 0.0000100000 | Loss 1.021091 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:46 Epoch 0 | Batch 590/3508 | Timestep 590 | LR 0.0000100000 | Loss 0.724517 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:49 Epoch 0 | Batch 600/3508 | Timestep 600 | LR 0.0000100000 | Loss 1.196997 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:51 Epoch 0 | Batch 610/3508 | Timestep 610 | LR 0.0000100000 | Loss 1.052049 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:53 Epoch 0 | Batch 620/3508 | Timestep 620 | LR 0.0000100000 | Loss 0.795397 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:55 Epoch 0 | Batch 630/3508 | Timestep 630 | LR 0.0000100000 | Loss 0.563280 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:57 Epoch 0 | Batch 640/3508 | Timestep 640 | LR 0.0000100000 | Loss 0.760264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:40:59 Epoch 0 | Batch 650/3508 | Timestep 650 | LR 0.0000100000 | Loss 0.734218 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:01 Epoch 0 | Batch 660/3508 | Timestep 660 | LR 0.0000100000 | Loss 0.582849 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:03 Epoch 0 | Batch 670/3508 | Timestep 670 | LR 0.0000100000 | Loss 0.786081 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:05 Epoch 0 | Batch 680/3508 | Timestep 680 | LR 0.0000100000 | Loss 0.949600 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:08 Epoch 0 | Batch 690/3508 | Timestep 690 | LR 0.0000100000 | Loss 0.627011 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:10 Epoch 0 | Batch 700/3508 | Timestep 700 | LR 0.0000100000 | Loss 0.588722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:12 Epoch 0 | Batch 710/3508 | Timestep 710 | LR 0.0000100000 | Loss 0.731466 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:14 Epoch 0 | Batch 720/3508 | Timestep 720 | LR 0.0000100000 | Loss 0.943644 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:16 Epoch 0 | Batch 730/3508 | Timestep 730 | LR 0.0000100000 | Loss 0.576719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:18 Epoch 0 | Batch 740/3508 | Timestep 740 | LR 0.0000100000 | Loss 0.639502 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:20 Epoch 0 | Batch 750/3508 | Timestep 750 | LR 0.0000100000 | Loss 0.669845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:22 Epoch 0 | Batch 760/3508 | Timestep 760 | LR 0.0000100000 | Loss 0.775660 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:25 Epoch 0 | Batch 770/3508 | Timestep 770 | LR 0.0000100000 | Loss 0.644048 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:27 Epoch 0 | Batch 780/3508 | Timestep 780 | LR 0.0000100000 | Loss 0.458562 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:29 Epoch 0 | Batch 790/3508 | Timestep 790 | LR 0.0000100000 | Loss 0.699470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:31 Epoch 0 | Batch 800/3508 | Timestep 800 | LR 0.0000100000 | Loss 0.632752 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:33 Epoch 0 | Batch 810/3508 | Timestep 810 | LR 0.0000100000 | Loss 0.499906 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:35 Epoch 0 | Batch 820/3508 | Timestep 820 | LR 0.0000100000 | Loss 0.815810 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:38 Epoch 0 | Batch 830/3508 | Timestep 830 | LR 0.0000100000 | Loss 0.629120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:40 Epoch 0 | Batch 840/3508 | Timestep 840 | LR 0.0000100000 | Loss 0.732662 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:42 Epoch 0 | Batch 850/3508 | Timestep 850 | LR 0.0000100000 | Loss 0.534516 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:44 Epoch 0 | Batch 860/3508 | Timestep 860 | LR 0.0000100000 | Loss 0.334794 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:46 Epoch 0 | Batch 870/3508 | Timestep 870 | LR 0.0000100000 | Loss 0.381489 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:48 Epoch 0 | Batch 880/3508 | Timestep 880 | LR 0.0000100000 | Loss 0.510589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:51 Epoch 0 | Batch 890/3508 | Timestep 890 | LR 0.0000100000 | Loss 0.374068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:52 Epoch 0 | Batch 900/3508 | Timestep 900 | LR 0.0000100000 | Loss 0.664418 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:54 Epoch 0 | Batch 910/3508 | Timestep 910 | LR 0.0000100000 | Loss 0.469853 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:56 Epoch 0 | Batch 920/3508 | Timestep 920 | LR 0.0000100000 | Loss 0.453842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:41:58 Epoch 0 | Batch 930/3508 | Timestep 930 | LR 0.0000100000 | Loss 0.286488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:00 Epoch 0 | Batch 940/3508 | Timestep 940 | LR 0.0000100000 | Loss 0.379617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:02 Epoch 0 | Batch 950/3508 | Timestep 950 | LR 0.0000100000 | Loss 0.414524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:04 Epoch 0 | Batch 960/3508 | Timestep 960 | LR 0.0000100000 | Loss 0.492834 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:06 Epoch 0 | Batch 970/3508 | Timestep 970 | LR 0.0000100000 | Loss 0.278866 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:09 Epoch 0 | Batch 980/3508 | Timestep 980 | LR 0.0000100000 | Loss 0.394528 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:11 Epoch 0 | Batch 990/3508 | Timestep 990 | LR 0.0000100000 | Loss 0.308044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:13 Epoch 0 | Batch 1000/3508 | Timestep 1000 | LR 0.0000100000 | Loss 0.299930 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:15 Epoch 0 | Batch 1010/3508 | Timestep 1010 | LR 0.0000100000 | Loss 0.416058 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:17 Epoch 0 | Batch 1020/3508 | Timestep 1020 | LR 0.0000100000 | Loss 0.478223 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:19 Epoch 0 | Batch 1030/3508 | Timestep 1030 | LR 0.0000100000 | Loss 0.348856 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:21 Epoch 0 | Batch 1040/3508 | Timestep 1040 | LR 0.0000100000 | Loss 0.376010 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:23 Epoch 0 | Batch 1050/3508 | Timestep 1050 | LR 0.0000100000 | Loss 0.500895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:25 Epoch 0 | Batch 1060/3508 | Timestep 1060 | LR 0.0000100000 | Loss 0.317837 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:27 Epoch 0 | Batch 1070/3508 | Timestep 1070 | LR 0.0000100000 | Loss 0.473263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:29 Epoch 0 | Batch 1080/3508 | Timestep 1080 | LR 0.0000100000 | Loss 0.588898 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:31 Epoch 0 | Batch 1090/3508 | Timestep 1090 | LR 0.0000100000 | Loss 0.328383 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:33 Epoch 0 | Batch 1100/3508 | Timestep 1100 | LR 0.0000100000 | Loss 0.477758 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:35 Epoch 0 | Batch 1110/3508 | Timestep 1110 | LR 0.0000100000 | Loss 0.435319 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:38 Epoch 0 | Batch 1120/3508 | Timestep 1120 | LR 0.0000100000 | Loss 0.361470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:40 Epoch 0 | Batch 1130/3508 | Timestep 1130 | LR 0.0000100000 | Loss 0.458173 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:42 Epoch 0 | Batch 1140/3508 | Timestep 1140 | LR 0.0000100000 | Loss 0.392734 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:44 Epoch 0 | Batch 1150/3508 | Timestep 1150 | LR 0.0000100000 | Loss 0.355744 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:46 Epoch 0 | Batch 1160/3508 | Timestep 1160 | LR 0.0000100000 | Loss 0.444596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:48 Epoch 0 | Batch 1170/3508 | Timestep 1170 | LR 0.0000100000 | Loss 0.218895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:50 Epoch 0 | Batch 1180/3508 | Timestep 1180 | LR 0.0000100000 | Loss 0.292920 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:52 Epoch 0 | Batch 1190/3508 | Timestep 1190 | LR 0.0000100000 | Loss 0.270714 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:54 Epoch 0 | Batch 1200/3508 | Timestep 1200 | LR 0.0000100000 | Loss 0.218071 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:56 Epoch 0 | Batch 1210/3508 | Timestep 1210 | LR 0.0000100000 | Loss 0.267703 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:42:59 Epoch 0 | Batch 1220/3508 | Timestep 1220 | LR 0.0000100000 | Loss 0.424700 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:02 Epoch 0 | Batch 1230/3508 | Timestep 1230 | LR 0.0000100000 | Loss 0.234112 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:04 Epoch 0 | Batch 1240/3508 | Timestep 1240 | LR 0.0000100000 | Loss 0.344069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:06 Epoch 0 | Batch 1250/3508 | Timestep 1250 | LR 0.0000100000 | Loss 0.231832 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:08 Epoch 0 | Batch 1260/3508 | Timestep 1260 | LR 0.0000100000 | Loss 0.302587 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:10 Epoch 0 | Batch 1270/3508 | Timestep 1270 | LR 0.0000100000 | Loss 0.294705 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:12 Epoch 0 | Batch 1280/3508 | Timestep 1280 | LR 0.0000100000 | Loss 0.474142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:14 Epoch 0 | Batch 1290/3508 | Timestep 1290 | LR 0.0000100000 | Loss 0.277408 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:16 Epoch 0 | Batch 1300/3508 | Timestep 1300 | LR 0.0000100000 | Loss 0.330018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:18 Epoch 0 | Batch 1310/3508 | Timestep 1310 | LR 0.0000100000 | Loss 0.161695 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:21 Epoch 0 | Batch 1320/3508 | Timestep 1320 | LR 0.0000100000 | Loss 0.239454 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:23 Epoch 0 | Batch 1330/3508 | Timestep 1330 | LR 0.0000100000 | Loss 0.390940 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:25 Epoch 0 | Batch 1340/3508 | Timestep 1340 | LR 0.0000100000 | Loss 0.461736 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:27 Epoch 0 | Batch 1350/3508 | Timestep 1350 | LR 0.0000100000 | Loss 0.313943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:29 Epoch 0 | Batch 1360/3508 | Timestep 1360 | LR 0.0000100000 | Loss 0.328886 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:32 Epoch 0 | Batch 1370/3508 | Timestep 1370 | LR 0.0000100000 | Loss 0.287381 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:34 Epoch 0 | Batch 1380/3508 | Timestep 1380 | LR 0.0000100000 | Loss 0.236470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:36 Epoch 0 | Batch 1390/3508 | Timestep 1390 | LR 0.0000100000 | Loss 0.201380 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:39 Epoch 0 | Batch 1400/3508 | Timestep 1400 | LR 0.0000100000 | Loss 0.329474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:41 Epoch 0 | Batch 1410/3508 | Timestep 1410 | LR 0.0000100000 | Loss 0.236665 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:43 Epoch 0 | Batch 1420/3508 | Timestep 1420 | LR 0.0000100000 | Loss 0.393382 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:46 Epoch 0 | Batch 1430/3508 | Timestep 1430 | LR 0.0000100000 | Loss 0.158374 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:48 Epoch 0 | Batch 1440/3508 | Timestep 1440 | LR 0.0000100000 | Loss 0.232099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:50 Epoch 0 | Batch 1450/3508 | Timestep 1450 | LR 0.0000100000 | Loss 0.287317 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:52 Epoch 0 | Batch 1460/3508 | Timestep 1460 | LR 0.0000100000 | Loss 0.483737 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:55 Epoch 0 | Batch 1470/3508 | Timestep 1470 | LR 0.0000100000 | Loss 0.312652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:56 Epoch 0 | Batch 1480/3508 | Timestep 1480 | LR 0.0000100000 | Loss 0.348487 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:43:59 Epoch 0 | Batch 1490/3508 | Timestep 1490 | LR 0.0000100000 | Loss 0.271972 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:00 Epoch 0 | Batch 1500/3508 | Timestep 1500 | LR 0.0000100000 | Loss 0.265290 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:02 Epoch 0 | Batch 1510/3508 | Timestep 1510 | LR 0.0000100000 | Loss 0.397472 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:04 Epoch 0 | Batch 1520/3508 | Timestep 1520 | LR 0.0000100000 | Loss 0.225735 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:06 Epoch 0 | Batch 1530/3508 | Timestep 1530 | LR 0.0000100000 | Loss 0.227448 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:09 Epoch 0 | Batch 1540/3508 | Timestep 1540 | LR 0.0000100000 | Loss 0.422743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:11 Epoch 0 | Batch 1550/3508 | Timestep 1550 | LR 0.0000100000 | Loss 0.201234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:13 Epoch 0 | Batch 1560/3508 | Timestep 1560 | LR 0.0000100000 | Loss 0.202846 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:16 Epoch 0 | Batch 1570/3508 | Timestep 1570 | LR 0.0000100000 | Loss 0.407456 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:18 Epoch 0 | Batch 1580/3508 | Timestep 1580 | LR 0.0000100000 | Loss 0.143019 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:20 Epoch 0 | Batch 1590/3508 | Timestep 1590 | LR 0.0000100000 | Loss 0.158460 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:22 Epoch 0 | Batch 1600/3508 | Timestep 1600 | LR 0.0000100000 | Loss 0.136717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:25 Epoch 0 | Batch 1610/3508 | Timestep 1610 | LR 0.0000100000 | Loss 0.380284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:26 Epoch 0 | Batch 1620/3508 | Timestep 1620 | LR 0.0000100000 | Loss 0.220044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:29 Epoch 0 | Batch 1630/3508 | Timestep 1630 | LR 0.0000100000 | Loss 0.276995 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:32 Epoch 0 | Batch 1640/3508 | Timestep 1640 | LR 0.0000100000 | Loss 0.143591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:34 Epoch 0 | Batch 1650/3508 | Timestep 1650 | LR 0.0000100000 | Loss 0.285462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:36 Epoch 0 | Batch 1660/3508 | Timestep 1660 | LR 0.0000100000 | Loss 0.139128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:38 Epoch 0 | Batch 1670/3508 | Timestep 1670 | LR 0.0000100000 | Loss 0.191378 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:40 Epoch 0 | Batch 1680/3508 | Timestep 1680 | LR 0.0000100000 | Loss 0.159805 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:42 Epoch 0 | Batch 1690/3508 | Timestep 1690 | LR 0.0000100000 | Loss 0.257088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:45 Epoch 0 | Batch 1700/3508 | Timestep 1700 | LR 0.0000100000 | Loss 0.138807 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:47 Epoch 0 | Batch 1710/3508 | Timestep 1710 | LR 0.0000100000 | Loss 0.176992 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:49 Epoch 0 | Batch 1720/3508 | Timestep 1720 | LR 0.0000100000 | Loss 0.170508 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:51 Epoch 0 | Batch 1730/3508 | Timestep 1730 | LR 0.0000100000 | Loss 0.209144 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:53 Epoch 0 | Batch 1740/3508 | Timestep 1740 | LR 0.0000100000 | Loss 0.119737 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:55 Epoch 0 | Batch 1750/3508 | Timestep 1750 | LR 0.0000100000 | Loss 0.199599 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:57 Epoch 0 | Batch 1760/3508 | Timestep 1760 | LR 0.0000100000 | Loss 0.184987 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:44:59 Epoch 0 | Batch 1770/3508 | Timestep 1770 | LR 0.0000100000 | Loss 0.178044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:01 Epoch 0 | Batch 1780/3508 | Timestep 1780 | LR 0.0000100000 | Loss 0.274327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:03 Epoch 0 | Batch 1790/3508 | Timestep 1790 | LR 0.0000100000 | Loss 0.222232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:05 Epoch 0 | Batch 1800/3508 | Timestep 1800 | LR 0.0000100000 | Loss 0.261060 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:08 Epoch 0 | Batch 1810/3508 | Timestep 1810 | LR 0.0000100000 | Loss 0.220815 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:10 Epoch 0 | Batch 1820/3508 | Timestep 1820 | LR 0.0000100000 | Loss 0.103589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:12 Epoch 0 | Batch 1830/3508 | Timestep 1830 | LR 0.0000100000 | Loss 0.138684 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:14 Epoch 0 | Batch 1840/3508 | Timestep 1840 | LR 0.0000100000 | Loss 0.154112 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:15 Epoch 0 | Batch 1850/3508 | Timestep 1850 | LR 0.0000100000 | Loss 0.243694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:18 Epoch 0 | Batch 1860/3508 | Timestep 1860 | LR 0.0000100000 | Loss 0.178489 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:20 Epoch 0 | Batch 1870/3508 | Timestep 1870 | LR 0.0000100000 | Loss 0.153693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:21 Epoch 0 | Batch 1880/3508 | Timestep 1880 | LR 0.0000100000 | Loss 0.170853 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:23 Epoch 0 | Batch 1890/3508 | Timestep 1890 | LR 0.0000100000 | Loss 0.160458 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:26 Epoch 0 | Batch 1900/3508 | Timestep 1900 | LR 0.0000100000 | Loss 0.250789 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:27 Epoch 0 | Batch 1910/3508 | Timestep 1910 | LR 0.0000100000 | Loss 0.214943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:30 Epoch 0 | Batch 1920/3508 | Timestep 1920 | LR 0.0000100000 | Loss 0.179548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:32 Epoch 0 | Batch 1930/3508 | Timestep 1930 | LR 0.0000100000 | Loss 0.127557 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:33 Epoch 0 | Batch 1940/3508 | Timestep 1940 | LR 0.0000100000 | Loss 0.173325 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:36 Epoch 0 | Batch 1950/3508 | Timestep 1950 | LR 0.0000100000 | Loss 0.058229 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:38 Epoch 0 | Batch 1960/3508 | Timestep 1960 | LR 0.0000100000 | Loss 0.103927 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:40 Epoch 0 | Batch 1970/3508 | Timestep 1970 | LR 0.0000100000 | Loss 0.176596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:42 Epoch 0 | Batch 1980/3508 | Timestep 1980 | LR 0.0000100000 | Loss 0.210136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:44 Epoch 0 | Batch 1990/3508 | Timestep 1990 | LR 0.0000100000 | Loss 0.271262 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:46 Epoch 0 | Batch 2000/3508 | Timestep 2000 | LR 0.0000100000 | Loss 0.251992 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:48 Epoch 0 | Batch 2010/3508 | Timestep 2010 | LR 0.0000100000 | Loss 0.104582 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:51 Epoch 0 | Batch 2020/3508 | Timestep 2020 | LR 0.0000100000 | Loss 0.101737 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:54 Epoch 0 | Batch 2030/3508 | Timestep 2030 | LR 0.0000100000 | Loss 0.381257 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:56 Epoch 0 | Batch 2040/3508 | Timestep 2040 | LR 0.0000100000 | Loss 0.169717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:45:58 Epoch 0 | Batch 2050/3508 | Timestep 2050 | LR 0.0000100000 | Loss 0.102571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:00 Epoch 0 | Batch 2060/3508 | Timestep 2060 | LR 0.0000100000 | Loss 0.231591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:02 Epoch 0 | Batch 2070/3508 | Timestep 2070 | LR 0.0000100000 | Loss 0.216738 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:04 Epoch 0 | Batch 2080/3508 | Timestep 2080 | LR 0.0000100000 | Loss 0.132408 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:06 Epoch 0 | Batch 2090/3508 | Timestep 2090 | LR 0.0000100000 | Loss 0.288706 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:08 Epoch 0 | Batch 2100/3508 | Timestep 2100 | LR 0.0000100000 | Loss 0.125545 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:11 Epoch 0 | Batch 2110/3508 | Timestep 2110 | LR 0.0000100000 | Loss 0.175854 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:13 Epoch 0 | Batch 2120/3508 | Timestep 2120 | LR 0.0000100000 | Loss 0.165045 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:15 Epoch 0 | Batch 2130/3508 | Timestep 2130 | LR 0.0000100000 | Loss 0.200003 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:18 Epoch 0 | Batch 2140/3508 | Timestep 2140 | LR 0.0000100000 | Loss 0.225177 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:20 Epoch 0 | Batch 2150/3508 | Timestep 2150 | LR 0.0000100000 | Loss 0.211964 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:22 Epoch 0 | Batch 2160/3508 | Timestep 2160 | LR 0.0000100000 | Loss 0.426713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:24 Epoch 0 | Batch 2170/3508 | Timestep 2170 | LR 0.0000100000 | Loss 0.084196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:26 Epoch 0 | Batch 2180/3508 | Timestep 2180 | LR 0.0000100000 | Loss 0.194393 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:28 Epoch 0 | Batch 2190/3508 | Timestep 2190 | LR 0.0000100000 | Loss 0.132028 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:30 Epoch 0 | Batch 2200/3508 | Timestep 2200 | LR 0.0000100000 | Loss 0.231781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:32 Epoch 0 | Batch 2210/3508 | Timestep 2210 | LR 0.0000100000 | Loss 0.117348 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:34 Epoch 0 | Batch 2220/3508 | Timestep 2220 | LR 0.0000100000 | Loss 0.189314 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:36 Epoch 0 | Batch 2230/3508 | Timestep 2230 | LR 0.0000100000 | Loss 0.187164 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:38 Epoch 0 | Batch 2240/3508 | Timestep 2240 | LR 0.0000100000 | Loss 0.173546 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:40 Epoch 0 | Batch 2250/3508 | Timestep 2250 | LR 0.0000100000 | Loss 0.113964 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:42 Epoch 0 | Batch 2260/3508 | Timestep 2260 | LR 0.0000100000 | Loss 0.108129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:45 Epoch 0 | Batch 2270/3508 | Timestep 2270 | LR 0.0000100000 | Loss 0.105286 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:47 Epoch 0 | Batch 2280/3508 | Timestep 2280 | LR 0.0000100000 | Loss 0.126092 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:49 Epoch 0 | Batch 2290/3508 | Timestep 2290 | LR 0.0000100000 | Loss 0.134214 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:51 Epoch 0 | Batch 2300/3508 | Timestep 2300 | LR 0.0000100000 | Loss 0.127667 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:53 Epoch 0 | Batch 2310/3508 | Timestep 2310 | LR 0.0000100000 | Loss 0.092079 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:56 Epoch 0 | Batch 2320/3508 | Timestep 2320 | LR 0.0000100000 | Loss 0.284222 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:46:58 Epoch 0 | Batch 2330/3508 | Timestep 2330 | LR 0.0000100000 | Loss 0.103289 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:00 Epoch 0 | Batch 2340/3508 | Timestep 2340 | LR 0.0000100000 | Loss 0.149556 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:02 Epoch 0 | Batch 2350/3508 | Timestep 2350 | LR 0.0000100000 | Loss 0.129209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:05 Epoch 0 | Batch 2360/3508 | Timestep 2360 | LR 0.0000100000 | Loss 0.211974 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:06 Epoch 0 | Batch 2370/3508 | Timestep 2370 | LR 0.0000100000 | Loss 0.118339 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:09 Epoch 0 | Batch 2380/3508 | Timestep 2380 | LR 0.0000100000 | Loss 0.151394 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:11 Epoch 0 | Batch 2390/3508 | Timestep 2390 | LR 0.0000100000 | Loss 0.098579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:13 Epoch 0 | Batch 2400/3508 | Timestep 2400 | LR 0.0000100000 | Loss 0.164117 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:15 Epoch 0 | Batch 2410/3508 | Timestep 2410 | LR 0.0000100000 | Loss 0.179187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:17 Epoch 0 | Batch 2420/3508 | Timestep 2420 | LR 0.0000100000 | Loss 0.110925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:19 Epoch 0 | Batch 2430/3508 | Timestep 2430 | LR 0.0000100000 | Loss 0.135022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:21 Epoch 0 | Batch 2440/3508 | Timestep 2440 | LR 0.0000100000 | Loss 0.218131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:23 Epoch 0 | Batch 2450/3508 | Timestep 2450 | LR 0.0000100000 | Loss 0.084184 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:25 Epoch 0 | Batch 2460/3508 | Timestep 2460 | LR 0.0000100000 | Loss 0.122537 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:28 Epoch 0 | Batch 2470/3508 | Timestep 2470 | LR 0.0000100000 | Loss 0.103425 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:30 Epoch 0 | Batch 2480/3508 | Timestep 2480 | LR 0.0000100000 | Loss 0.070004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:32 Epoch 0 | Batch 2490/3508 | Timestep 2490 | LR 0.0000100000 | Loss 0.128902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:35 Epoch 0 | Batch 2500/3508 | Timestep 2500 | LR 0.0000100000 | Loss 0.076263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:38 Epoch 0 | Batch 2510/3508 | Timestep 2510 | LR 0.0000100000 | Loss 0.132210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:39 Epoch 0 | Batch 2520/3508 | Timestep 2520 | LR 0.0000100000 | Loss 0.154574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:41 Epoch 0 | Batch 2530/3508 | Timestep 2530 | LR 0.0000100000 | Loss 0.093719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:44 Epoch 0 | Batch 2540/3508 | Timestep 2540 | LR 0.0000100000 | Loss 0.122099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:46 Epoch 0 | Batch 2550/3508 | Timestep 2550 | LR 0.0000100000 | Loss 0.098302 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:48 Epoch 0 | Batch 2560/3508 | Timestep 2560 | LR 0.0000100000 | Loss 0.287530 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:51 Epoch 0 | Batch 2570/3508 | Timestep 2570 | LR 0.0000100000 | Loss 0.118695 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:53 Epoch 0 | Batch 2580/3508 | Timestep 2580 | LR 0.0000100000 | Loss 0.089827 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:55 Epoch 0 | Batch 2590/3508 | Timestep 2590 | LR 0.0000100000 | Loss 0.287178 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:57 Epoch 0 | Batch 2600/3508 | Timestep 2600 | LR 0.0000100000 | Loss 0.116791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:47:59 Epoch 0 | Batch 2610/3508 | Timestep 2610 | LR 0.0000100000 | Loss 0.107309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:00 Epoch 0 | Batch 2620/3508 | Timestep 2620 | LR 0.0000100000 | Loss 0.220082 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:02 Epoch 0 | Batch 2630/3508 | Timestep 2630 | LR 0.0000100000 | Loss 0.108887 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:04 Epoch 0 | Batch 2640/3508 | Timestep 2640 | LR 0.0000100000 | Loss 0.109007 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:06 Epoch 0 | Batch 2650/3508 | Timestep 2650 | LR 0.0000100000 | Loss 0.081563 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:09 Epoch 0 | Batch 2660/3508 | Timestep 2660 | LR 0.0000100000 | Loss 0.080681 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:11 Epoch 0 | Batch 2670/3508 | Timestep 2670 | LR 0.0000100000 | Loss 0.090694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:14 Epoch 0 | Batch 2680/3508 | Timestep 2680 | LR 0.0000100000 | Loss 0.122807 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:17 Epoch 0 | Batch 2690/3508 | Timestep 2690 | LR 0.0000100000 | Loss 0.060976 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:19 Epoch 0 | Batch 2700/3508 | Timestep 2700 | LR 0.0000100000 | Loss 0.151805 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:21 Epoch 0 | Batch 2710/3508 | Timestep 2710 | LR 0.0000100000 | Loss 0.098570 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:23 Epoch 0 | Batch 2720/3508 | Timestep 2720 | LR 0.0000100000 | Loss 0.062641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:25 Epoch 0 | Batch 2730/3508 | Timestep 2730 | LR 0.0000100000 | Loss 0.101835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:28 Epoch 0 | Batch 2740/3508 | Timestep 2740 | LR 0.0000100000 | Loss 0.089485 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:29 Epoch 0 | Batch 2750/3508 | Timestep 2750 | LR 0.0000100000 | Loss 0.134802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:31 Epoch 0 | Batch 2760/3508 | Timestep 2760 | LR 0.0000100000 | Loss 0.134474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:33 Epoch 0 | Batch 2770/3508 | Timestep 2770 | LR 0.0000100000 | Loss 0.124711 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:36 Epoch 0 | Batch 2780/3508 | Timestep 2780 | LR 0.0000100000 | Loss 0.136844 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:38 Epoch 0 | Batch 2790/3508 | Timestep 2790 | LR 0.0000100000 | Loss 0.140460 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:40 Epoch 0 | Batch 2800/3508 | Timestep 2800 | LR 0.0000100000 | Loss 0.117843 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:42 Epoch 0 | Batch 2810/3508 | Timestep 2810 | LR 0.0000100000 | Loss 0.236626 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:44 Epoch 0 | Batch 2820/3508 | Timestep 2820 | LR 0.0000100000 | Loss 0.122715 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:46 Epoch 0 | Batch 2830/3508 | Timestep 2830 | LR 0.0000100000 | Loss 0.104177 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:48 Epoch 0 | Batch 2840/3508 | Timestep 2840 | LR 0.0000100000 | Loss 0.113655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:50 Epoch 0 | Batch 2850/3508 | Timestep 2850 | LR 0.0000100000 | Loss 0.120262 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:53 Epoch 0 | Batch 2860/3508 | Timestep 2860 | LR 0.0000100000 | Loss 0.103743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:55 Epoch 0 | Batch 2870/3508 | Timestep 2870 | LR 0.0000100000 | Loss 0.275170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:57 Epoch 0 | Batch 2880/3508 | Timestep 2880 | LR 0.0000100000 | Loss 0.089254 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:48:59 Epoch 0 | Batch 2890/3508 | Timestep 2890 | LR 0.0000100000 | Loss 0.085958 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:01 Epoch 0 | Batch 2900/3508 | Timestep 2900 | LR 0.0000100000 | Loss 0.189544 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:04 Epoch 0 | Batch 2910/3508 | Timestep 2910 | LR 0.0000100000 | Loss 0.108275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:06 Epoch 0 | Batch 2920/3508 | Timestep 2920 | LR 0.0000100000 | Loss 0.059936 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:07 Epoch 0 | Batch 2930/3508 | Timestep 2930 | LR 0.0000100000 | Loss 0.074621 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:10 Epoch 0 | Batch 2940/3508 | Timestep 2940 | LR 0.0000100000 | Loss 0.080248 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:12 Epoch 0 | Batch 2950/3508 | Timestep 2950 | LR 0.0000100000 | Loss 0.120238 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:15 Epoch 0 | Batch 2960/3508 | Timestep 2960 | LR 0.0000100000 | Loss 0.055732 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:17 Epoch 0 | Batch 2970/3508 | Timestep 2970 | LR 0.0000100000 | Loss 0.128066 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:19 Epoch 0 | Batch 2980/3508 | Timestep 2980 | LR 0.0000100000 | Loss 0.112003 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:21 Epoch 0 | Batch 2990/3508 | Timestep 2990 | LR 0.0000100000 | Loss 0.062921 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:23 Epoch 0 | Batch 3000/3508 | Timestep 3000 | LR 0.0000100000 | Loss 0.120446 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:25 Epoch 0 | Batch 3010/3508 | Timestep 3010 | LR 0.0000100000 | Loss 0.073963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:27 Epoch 0 | Batch 3020/3508 | Timestep 3020 | LR 0.0000100000 | Loss 0.067656 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:29 Epoch 0 | Batch 3030/3508 | Timestep 3030 | LR 0.0000100000 | Loss 0.093249 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:31 Epoch 0 | Batch 3040/3508 | Timestep 3040 | LR 0.0000100000 | Loss 0.102169 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:33 Epoch 0 | Batch 3050/3508 | Timestep 3050 | LR 0.0000100000 | Loss 0.123446 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:35 Epoch 0 | Batch 3060/3508 | Timestep 3060 | LR 0.0000100000 | Loss 0.090118 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:37 Epoch 0 | Batch 3070/3508 | Timestep 3070 | LR 0.0000100000 | Loss 0.058930 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:40 Epoch 0 | Batch 3080/3508 | Timestep 3080 | LR 0.0000100000 | Loss 0.050384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:41 Epoch 0 | Batch 3090/3508 | Timestep 3090 | LR 0.0000100000 | Loss 0.071284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:44 Epoch 0 | Batch 3100/3508 | Timestep 3100 | LR 0.0000100000 | Loss 0.066397 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:45 Epoch 0 | Batch 3110/3508 | Timestep 3110 | LR 0.0000100000 | Loss 0.210367 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:47 Epoch 0 | Batch 3120/3508 | Timestep 3120 | LR 0.0000100000 | Loss 0.106667 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:50 Epoch 0 | Batch 3130/3508 | Timestep 3130 | LR 0.0000100000 | Loss 0.120204 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:52 Epoch 0 | Batch 3140/3508 | Timestep 3140 | LR 0.0000100000 | Loss 0.088404 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:54 Epoch 0 | Batch 3150/3508 | Timestep 3150 | LR 0.0000100000 | Loss 0.121598 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:56 Epoch 0 | Batch 3160/3508 | Timestep 3160 | LR 0.0000100000 | Loss 0.051869 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:49:58 Epoch 0 | Batch 3170/3508 | Timestep 3170 | LR 0.0000100000 | Loss 0.229874 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:00 Epoch 0 | Batch 3180/3508 | Timestep 3180 | LR 0.0000100000 | Loss 0.278785 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:03 Epoch 0 | Batch 3190/3508 | Timestep 3190 | LR 0.0000100000 | Loss 0.088462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:04 Epoch 0 | Batch 3200/3508 | Timestep 3200 | LR 0.0000100000 | Loss 0.194701 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:07 Epoch 0 | Batch 3210/3508 | Timestep 3210 | LR 0.0000100000 | Loss 0.105330 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:09 Epoch 0 | Batch 3220/3508 | Timestep 3220 | LR 0.0000100000 | Loss 0.076508 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:11 Epoch 0 | Batch 3230/3508 | Timestep 3230 | LR 0.0000100000 | Loss 0.198674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:13 Epoch 0 | Batch 3240/3508 | Timestep 3240 | LR 0.0000100000 | Loss 0.121020 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:15 Epoch 0 | Batch 3250/3508 | Timestep 3250 | LR 0.0000100000 | Loss 0.091799 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:17 Epoch 0 | Batch 3260/3508 | Timestep 3260 | LR 0.0000100000 | Loss 0.069134 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:19 Epoch 0 | Batch 3270/3508 | Timestep 3270 | LR 0.0000100000 | Loss 0.123135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:21 Epoch 0 | Batch 3280/3508 | Timestep 3280 | LR 0.0000100000 | Loss 0.133718 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:23 Epoch 0 | Batch 3290/3508 | Timestep 3290 | LR 0.0000100000 | Loss 0.051024 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:26 Epoch 0 | Batch 3300/3508 | Timestep 3300 | LR 0.0000100000 | Loss 0.076426 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:27 Epoch 0 | Batch 3310/3508 | Timestep 3310 | LR 0.0000100000 | Loss 0.142130 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:30 Epoch 0 | Batch 3320/3508 | Timestep 3320 | LR 0.0000100000 | Loss 0.141675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:32 Epoch 0 | Batch 3330/3508 | Timestep 3330 | LR 0.0000100000 | Loss 0.098166 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:34 Epoch 0 | Batch 3340/3508 | Timestep 3340 | LR 0.0000100000 | Loss 0.053008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:36 Epoch 0 | Batch 3350/3508 | Timestep 3350 | LR 0.0000100000 | Loss 0.096392 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:39 Epoch 0 | Batch 3360/3508 | Timestep 3360 | LR 0.0000100000 | Loss 0.095251 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:41 Epoch 0 | Batch 3370/3508 | Timestep 3370 | LR 0.0000100000 | Loss 0.074323 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:44 Epoch 0 | Batch 3380/3508 | Timestep 3380 | LR 0.0000100000 | Loss 0.058902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:46 Epoch 0 | Batch 3390/3508 | Timestep 3390 | LR 0.0000100000 | Loss 0.065458 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:48 Epoch 0 | Batch 3400/3508 | Timestep 3400 | LR 0.0000100000 | Loss 0.079608 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:50 Epoch 0 | Batch 3410/3508 | Timestep 3410 | LR 0.0000100000 | Loss 0.067476 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:52 Epoch 0 | Batch 3420/3508 | Timestep 3420 | LR 0.0000100000 | Loss 0.050451 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:54 Epoch 0 | Batch 3430/3508 | Timestep 3430 | LR 0.0000100000 | Loss 0.087531 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:56 Epoch 0 | Batch 3440/3508 | Timestep 3440 | LR 0.0000100000 | Loss 0.068575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:50:58 Epoch 0 | Batch 3450/3508 | Timestep 3450 | LR 0.0000100000 | Loss 0.096131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:00 Epoch 0 | Batch 3460/3508 | Timestep 3460 | LR 0.0000100000 | Loss 0.057031 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:02 Epoch 0 | Batch 3470/3508 | Timestep 3470 | LR 0.0000100000 | Loss 0.207045 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:04 Epoch 0 | Batch 3480/3508 | Timestep 3480 | LR 0.0000100000 | Loss 0.085097 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:07 Epoch 0 | Batch 3490/3508 | Timestep 3490 | LR 0.0000100000 | Loss 0.048872 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:09 Epoch 0 | Batch 3500/3508 | Timestep 3500 | LR 0.0000100000 | Loss 0.103414 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:10 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 14:51:43 precision recall f1-score support CARDINAL 0.6479 0.5786 0.6113 159 CURR 1.0000 0.1364 0.2400 22 DATE 0.9046 0.9143 0.9094 1669 EVENT 0.6575 0.5901 0.6220 283 FAC 0.3763 0.2966 0.3318 118 GPE 0.9343 0.9374 0.9359 2140 LANGUAGE 0.0000 0.0000 0.0000 16 LAW 0.2188 0.3684 0.2745 19 LOC 0.6667 0.2889 0.4031 90 MONEY 0.5833 0.7000 0.6364 20 NORP 0.5241 0.5972 0.5583 509 OCC 0.7407 0.7601 0.7502 496 ORDINAL 0.7871 0.7960 0.7915 446 ORG 0.8768 0.8580 0.8673 1866 PERCENT 1.0000 1.0000 1.0000 12 PERS 0.8826 0.8527 0.8674 679 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.0000 0.0000 0.0000 3 TIME 0.0000 0.0000 0.0000 31 UNIT 0.0000 0.0000 0.0000 4 WEBSITE 0.2759 0.1000 0.1468 80 micro avg 0.8383 0.8203 0.8292 8670 macro avg 0.5275 0.4655 0.4736 8670 weighted avg 0.8299 0.8203 0.8227 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:53 Epoch 0 | Timestep 3508 | Train Loss 0.748496 | Val Loss 0.120205 | F1 0.829194 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:51:54 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 25 Jun 2026 14:52:16 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Thu, 25 Jun 2026 14:52:37 Predictions written to /rep/nhamad/ArabicNER/B1/predictions.txt INFO root Thu, 25 Jun 2026 14:53:00 precision recall f1-score support CARDINAL 0.6633 0.5963 0.6280 327 CURR 0.1429 0.0263 0.0444 38 DATE 0.9045 0.9278 0.9160 3173 EVENT 0.6111 0.5903 0.6005 559 FAC 0.4639 0.3182 0.3775 242 GPE 0.9181 0.9258 0.9219 4311 LANGUAGE 0.0000 0.0000 0.0000 44 LAW 0.4054 0.5172 0.4545 29 LOC 0.6118 0.2385 0.3432 218 MONEY 0.6757 0.8333 0.7463 30 NORP 0.5468 0.6179 0.5802 992 OCC 0.7165 0.7179 0.7172 1035 ORDINAL 0.8002 0.8435 0.8213 850 ORG 0.8439 0.8491 0.8465 3738 PERCENT 0.8333 0.7812 0.8065 32 PERS 0.8740 0.8540 0.8639 1568 PRODUCT 0.0000 0.0000 0.0000 19 QUANTITY 0.0000 0.0000 0.0000 9 TIME 0.0000 0.0000 0.0000 78 UNIT 0.0000 0.0000 0.0000 11 WEBSITE 0.4118 0.1207 0.1867 116 micro avg 0.8298 0.8184 0.8240 17419 macro avg 0.4963 0.4647 0.4693 17419 weighted avg 0.8171 0.8184 0.8156 17419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:21 Epoch 0 | Timestep 3508 | Test Loss 0.125657 | F1 0.824036 INFO arabiner.trainers.BaseTrainer Thu, 25 Jun 2026 14:53:21 Saving checkpoint to /rep/nhamad/ArabicNER/B1/checkpoints/checkpoint_0.pt INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:24 Epoch 1 | Batch 2/3508 | Timestep 3510 | LR 0.0000100000 | Loss 0.125501 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:26 Epoch 1 | Batch 12/3508 | Timestep 3520 | LR 0.0000100000 | Loss 0.073842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:29 Epoch 1 | Batch 22/3508 | Timestep 3530 | LR 0.0000100000 | Loss 0.095799 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:31 Epoch 1 | Batch 32/3508 | Timestep 3540 | LR 0.0000100000 | Loss 0.079846 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:34 Epoch 1 | Batch 42/3508 | Timestep 3550 | LR 0.0000100000 | Loss 0.066441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:35 Epoch 1 | Batch 52/3508 | Timestep 3560 | LR 0.0000100000 | Loss 0.087736 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:38 Epoch 1 | Batch 62/3508 | Timestep 3570 | LR 0.0000100000 | Loss 0.104116 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:40 Epoch 1 | Batch 72/3508 | Timestep 3580 | LR 0.0000100000 | Loss 0.071137 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:42 Epoch 1 | Batch 82/3508 | Timestep 3590 | LR 0.0000100000 | Loss 0.124525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:44 Epoch 1 | Batch 92/3508 | Timestep 3600 | LR 0.0000100000 | Loss 0.086817 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:46 Epoch 1 | Batch 102/3508 | Timestep 3610 | LR 0.0000100000 | Loss 0.036614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:48 Epoch 1 | Batch 112/3508 | Timestep 3620 | LR 0.0000100000 | Loss 0.166224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:51 Epoch 1 | Batch 122/3508 | Timestep 3630 | LR 0.0000100000 | Loss 0.103949 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:53 Epoch 1 | Batch 132/3508 | Timestep 3640 | LR 0.0000100000 | Loss 0.089376 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:55 Epoch 1 | Batch 142/3508 | Timestep 3650 | LR 0.0000100000 | Loss 0.075564 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:57 Epoch 1 | Batch 152/3508 | Timestep 3660 | LR 0.0000100000 | Loss 0.116258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:53:59 Epoch 1 | Batch 162/3508 | Timestep 3670 | LR 0.0000100000 | Loss 0.052499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:01 Epoch 1 | Batch 172/3508 | Timestep 3680 | LR 0.0000100000 | Loss 0.148563 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:04 Epoch 1 | Batch 182/3508 | Timestep 3690 | LR 0.0000100000 | Loss 0.147129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:06 Epoch 1 | Batch 192/3508 | Timestep 3700 | LR 0.0000100000 | Loss 0.032316 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:08 Epoch 1 | Batch 202/3508 | Timestep 3710 | LR 0.0000100000 | Loss 0.154708 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:10 Epoch 1 | Batch 212/3508 | Timestep 3720 | LR 0.0000100000 | Loss 0.054090 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:12 Epoch 1 | Batch 222/3508 | Timestep 3730 | LR 0.0000100000 | Loss 0.099150 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:14 Epoch 1 | Batch 232/3508 | Timestep 3740 | LR 0.0000100000 | Loss 0.059570 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:16 Epoch 1 | Batch 242/3508 | Timestep 3750 | LR 0.0000100000 | Loss 0.084064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:18 Epoch 1 | Batch 252/3508 | Timestep 3760 | LR 0.0000100000 | Loss 0.046322 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:20 Epoch 1 | Batch 262/3508 | Timestep 3770 | LR 0.0000100000 | Loss 0.035043 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:22 Epoch 1 | Batch 272/3508 | Timestep 3780 | LR 0.0000100000 | Loss 0.113002 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:24 Epoch 1 | Batch 282/3508 | Timestep 3790 | LR 0.0000100000 | Loss 0.085788 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:27 Epoch 1 | Batch 292/3508 | Timestep 3800 | LR 0.0000100000 | Loss 0.087714 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:29 Epoch 1 | Batch 302/3508 | Timestep 3810 | LR 0.0000100000 | Loss 0.058501 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:31 Epoch 1 | Batch 312/3508 | Timestep 3820 | LR 0.0000100000 | Loss 0.066437 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:33 Epoch 1 | Batch 322/3508 | Timestep 3830 | LR 0.0000100000 | Loss 0.135219 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:36 Epoch 1 | Batch 332/3508 | Timestep 3840 | LR 0.0000100000 | Loss 0.089876 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:38 Epoch 1 | Batch 342/3508 | Timestep 3850 | LR 0.0000100000 | Loss 0.083424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:41 Epoch 1 | Batch 352/3508 | Timestep 3860 | LR 0.0000100000 | Loss 0.062641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:43 Epoch 1 | Batch 362/3508 | Timestep 3870 | LR 0.0000100000 | Loss 0.073600 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:45 Epoch 1 | Batch 372/3508 | Timestep 3880 | LR 0.0000100000 | Loss 0.090225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:48 Epoch 1 | Batch 382/3508 | Timestep 3890 | LR 0.0000100000 | Loss 0.097835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:50 Epoch 1 | Batch 392/3508 | Timestep 3900 | LR 0.0000100000 | Loss 0.071094 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:53 Epoch 1 | Batch 402/3508 | Timestep 3910 | LR 0.0000100000 | Loss 0.078288 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:55 Epoch 1 | Batch 412/3508 | Timestep 3920 | LR 0.0000100000 | Loss 0.098888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:57 Epoch 1 | Batch 422/3508 | Timestep 3930 | LR 0.0000100000 | Loss 0.074311 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:54:59 Epoch 1 | Batch 432/3508 | Timestep 3940 | LR 0.0000100000 | Loss 0.123679 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:01 Epoch 1 | Batch 442/3508 | Timestep 3950 | LR 0.0000100000 | Loss 0.136286 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:03 Epoch 1 | Batch 452/3508 | Timestep 3960 | LR 0.0000100000 | Loss 0.287951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:05 Epoch 1 | Batch 462/3508 | Timestep 3970 | LR 0.0000100000 | Loss 0.159872 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:07 Epoch 1 | Batch 472/3508 | Timestep 3980 | LR 0.0000100000 | Loss 0.080670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:09 Epoch 1 | Batch 482/3508 | Timestep 3990 | LR 0.0000100000 | Loss 0.064071 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:11 Epoch 1 | Batch 492/3508 | Timestep 4000 | LR 0.0000100000 | Loss 0.070576 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:13 Epoch 1 | Batch 502/3508 | Timestep 4010 | LR 0.0000100000 | Loss 0.044258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:15 Epoch 1 | Batch 512/3508 | Timestep 4020 | LR 0.0000100000 | Loss 0.149009 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:18 Epoch 1 | Batch 522/3508 | Timestep 4030 | LR 0.0000100000 | Loss 0.073614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:20 Epoch 1 | Batch 532/3508 | Timestep 4040 | LR 0.0000100000 | Loss 0.029126 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:22 Epoch 1 | Batch 542/3508 | Timestep 4050 | LR 0.0000100000 | Loss 0.100188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:24 Epoch 1 | Batch 552/3508 | Timestep 4060 | LR 0.0000100000 | Loss 0.074650 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:26 Epoch 1 | Batch 562/3508 | Timestep 4070 | LR 0.0000100000 | Loss 0.051871 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:28 Epoch 1 | Batch 572/3508 | Timestep 4080 | LR 0.0000100000 | Loss 0.074341 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:31 Epoch 1 | Batch 582/3508 | Timestep 4090 | LR 0.0000100000 | Loss 0.175523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:33 Epoch 1 | Batch 592/3508 | Timestep 4100 | LR 0.0000100000 | Loss 0.123324 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:35 Epoch 1 | Batch 602/3508 | Timestep 4110 | LR 0.0000100000 | Loss 0.050194 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:37 Epoch 1 | Batch 612/3508 | Timestep 4120 | LR 0.0000100000 | Loss 0.036770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:39 Epoch 1 | Batch 622/3508 | Timestep 4130 | LR 0.0000100000 | Loss 0.082840 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:41 Epoch 1 | Batch 632/3508 | Timestep 4140 | LR 0.0000100000 | Loss 0.174911 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:43 Epoch 1 | Batch 642/3508 | Timestep 4150 | LR 0.0000100000 | Loss 0.061610 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:45 Epoch 1 | Batch 652/3508 | Timestep 4160 | LR 0.0000100000 | Loss 0.054411 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:48 Epoch 1 | Batch 662/3508 | Timestep 4170 | LR 0.0000100000 | Loss 0.037641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:50 Epoch 1 | Batch 672/3508 | Timestep 4180 | LR 0.0000100000 | Loss 0.052851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:51 Epoch 1 | Batch 682/3508 | Timestep 4190 | LR 0.0000100000 | Loss 0.060016 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:54 Epoch 1 | Batch 692/3508 | Timestep 4200 | LR 0.0000100000 | Loss 0.101762 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:56 Epoch 1 | Batch 702/3508 | Timestep 4210 | LR 0.0000100000 | Loss 0.123793 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:55:58 Epoch 1 | Batch 712/3508 | Timestep 4220 | LR 0.0000100000 | Loss 0.071669 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:00 Epoch 1 | Batch 722/3508 | Timestep 4230 | LR 0.0000100000 | Loss 0.074858 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:02 Epoch 1 | Batch 732/3508 | Timestep 4240 | LR 0.0000100000 | Loss 0.024743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:04 Epoch 1 | Batch 742/3508 | Timestep 4250 | LR 0.0000100000 | Loss 0.034325 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:07 Epoch 1 | Batch 752/3508 | Timestep 4260 | LR 0.0000100000 | Loss 0.074950 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:09 Epoch 1 | Batch 762/3508 | Timestep 4270 | LR 0.0000100000 | Loss 0.083167 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:12 Epoch 1 | Batch 772/3508 | Timestep 4280 | LR 0.0000100000 | Loss 0.139136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:14 Epoch 1 | Batch 782/3508 | Timestep 4290 | LR 0.0000100000 | Loss 0.038702 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:16 Epoch 1 | Batch 792/3508 | Timestep 4300 | LR 0.0000100000 | Loss 0.040908 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:18 Epoch 1 | Batch 802/3508 | Timestep 4310 | LR 0.0000100000 | Loss 0.040602 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:20 Epoch 1 | Batch 812/3508 | Timestep 4320 | LR 0.0000100000 | Loss 0.070757 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:22 Epoch 1 | Batch 822/3508 | Timestep 4330 | LR 0.0000100000 | Loss 0.088563 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:24 Epoch 1 | Batch 832/3508 | Timestep 4340 | LR 0.0000100000 | Loss 0.061623 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:26 Epoch 1 | Batch 842/3508 | Timestep 4350 | LR 0.0000100000 | Loss 0.165426 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:28 Epoch 1 | Batch 852/3508 | Timestep 4360 | LR 0.0000100000 | Loss 0.122012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:30 Epoch 1 | Batch 862/3508 | Timestep 4370 | LR 0.0000100000 | Loss 0.060644 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:32 Epoch 1 | Batch 872/3508 | Timestep 4380 | LR 0.0000100000 | Loss 0.072066 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:35 Epoch 1 | Batch 882/3508 | Timestep 4390 | LR 0.0000100000 | Loss 0.019672 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:37 Epoch 1 | Batch 892/3508 | Timestep 4400 | LR 0.0000100000 | Loss 0.117901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:39 Epoch 1 | Batch 902/3508 | Timestep 4410 | LR 0.0000100000 | Loss 0.070347 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:41 Epoch 1 | Batch 912/3508 | Timestep 4420 | LR 0.0000100000 | Loss 0.041453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:43 Epoch 1 | Batch 922/3508 | Timestep 4430 | LR 0.0000100000 | Loss 0.029189 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:45 Epoch 1 | Batch 932/3508 | Timestep 4440 | LR 0.0000100000 | Loss 0.097518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:48 Epoch 1 | Batch 942/3508 | Timestep 4450 | LR 0.0000100000 | Loss 0.171673 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:50 Epoch 1 | Batch 952/3508 | Timestep 4460 | LR 0.0000100000 | Loss 0.065876 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:52 Epoch 1 | Batch 962/3508 | Timestep 4470 | LR 0.0000100000 | Loss 0.029295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:54 Epoch 1 | Batch 972/3508 | Timestep 4480 | LR 0.0000100000 | Loss 0.084203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:56 Epoch 1 | Batch 982/3508 | Timestep 4490 | LR 0.0000100000 | Loss 0.075247 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:56:58 Epoch 1 | Batch 992/3508 | Timestep 4500 | LR 0.0000100000 | Loss 0.101307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:00 Epoch 1 | Batch 1002/3508 | Timestep 4510 | LR 0.0000100000 | Loss 0.051679 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:02 Epoch 1 | Batch 1012/3508 | Timestep 4520 | LR 0.0000100000 | Loss 0.083831 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:04 Epoch 1 | Batch 1022/3508 | Timestep 4530 | LR 0.0000100000 | Loss 0.036053 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:06 Epoch 1 | Batch 1032/3508 | Timestep 4540 | LR 0.0000100000 | Loss 0.030683 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:08 Epoch 1 | Batch 1042/3508 | Timestep 4550 | LR 0.0000100000 | Loss 0.089796 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:10 Epoch 1 | Batch 1052/3508 | Timestep 4560 | LR 0.0000100000 | Loss 0.056587 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:12 Epoch 1 | Batch 1062/3508 | Timestep 4570 | LR 0.0000100000 | Loss 0.073082 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:14 Epoch 1 | Batch 1072/3508 | Timestep 4580 | LR 0.0000100000 | Loss 0.061260 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:16 Epoch 1 | Batch 1082/3508 | Timestep 4590 | LR 0.0000100000 | Loss 0.044052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:18 Epoch 1 | Batch 1092/3508 | Timestep 4600 | LR 0.0000100000 | Loss 0.100443 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:19 Epoch 1 | Batch 1102/3508 | Timestep 4610 | LR 0.0000100000 | Loss 0.086786 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:22 Epoch 1 | Batch 1112/3508 | Timestep 4620 | LR 0.0000100000 | Loss 0.106221 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:23 Epoch 1 | Batch 1122/3508 | Timestep 4630 | LR 0.0000100000 | Loss 0.049675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:26 Epoch 1 | Batch 1132/3508 | Timestep 4640 | LR 0.0000100000 | Loss 0.190556 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:29 Epoch 1 | Batch 1142/3508 | Timestep 4650 | LR 0.0000100000 | Loss 0.076006 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:31 Epoch 1 | Batch 1152/3508 | Timestep 4660 | LR 0.0000100000 | Loss 0.027040 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:33 Epoch 1 | Batch 1162/3508 | Timestep 4670 | LR 0.0000100000 | Loss 0.057622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:36 Epoch 1 | Batch 1172/3508 | Timestep 4680 | LR 0.0000100000 | Loss 0.021902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:38 Epoch 1 | Batch 1182/3508 | Timestep 4690 | LR 0.0000100000 | Loss 0.060832 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:40 Epoch 1 | Batch 1192/3508 | Timestep 4700 | LR 0.0000100000 | Loss 0.102770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:42 Epoch 1 | Batch 1202/3508 | Timestep 4710 | LR 0.0000100000 | Loss 0.055525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:45 Epoch 1 | Batch 1212/3508 | Timestep 4720 | LR 0.0000100000 | Loss 0.032461 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:47 Epoch 1 | Batch 1222/3508 | Timestep 4730 | LR 0.0000100000 | Loss 0.044881 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:49 Epoch 1 | Batch 1232/3508 | Timestep 4740 | LR 0.0000100000 | Loss 0.130870 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:51 Epoch 1 | Batch 1242/3508 | Timestep 4750 | LR 0.0000100000 | Loss 0.078270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:53 Epoch 1 | Batch 1252/3508 | Timestep 4760 | LR 0.0000100000 | Loss 0.051526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:55 Epoch 1 | Batch 1262/3508 | Timestep 4770 | LR 0.0000100000 | Loss 0.096227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:57 Epoch 1 | Batch 1272/3508 | Timestep 4780 | LR 0.0000100000 | Loss 0.091951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:57:59 Epoch 1 | Batch 1282/3508 | Timestep 4790 | LR 0.0000100000 | Loss 0.059262 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:01 Epoch 1 | Batch 1292/3508 | Timestep 4800 | LR 0.0000100000 | Loss 0.142138 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:03 Epoch 1 | Batch 1302/3508 | Timestep 4810 | LR 0.0000100000 | Loss 0.030694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:05 Epoch 1 | Batch 1312/3508 | Timestep 4820 | LR 0.0000100000 | Loss 0.076462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:07 Epoch 1 | Batch 1322/3508 | Timestep 4830 | LR 0.0000100000 | Loss 0.050467 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:10 Epoch 1 | Batch 1332/3508 | Timestep 4840 | LR 0.0000100000 | Loss 0.055829 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:12 Epoch 1 | Batch 1342/3508 | Timestep 4850 | LR 0.0000100000 | Loss 0.050424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:14 Epoch 1 | Batch 1352/3508 | Timestep 4860 | LR 0.0000100000 | Loss 0.136504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:16 Epoch 1 | Batch 1362/3508 | Timestep 4870 | LR 0.0000100000 | Loss 0.027039 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:18 Epoch 1 | Batch 1372/3508 | Timestep 4880 | LR 0.0000100000 | Loss 0.046163 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:20 Epoch 1 | Batch 1382/3508 | Timestep 4890 | LR 0.0000100000 | Loss 0.077099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:22 Epoch 1 | Batch 1392/3508 | Timestep 4900 | LR 0.0000100000 | Loss 0.039574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:24 Epoch 1 | Batch 1402/3508 | Timestep 4910 | LR 0.0000100000 | Loss 0.055709 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:26 Epoch 1 | Batch 1412/3508 | Timestep 4920 | LR 0.0000100000 | Loss 0.090299 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:29 Epoch 1 | Batch 1422/3508 | Timestep 4930 | LR 0.0000100000 | Loss 0.090677 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:30 Epoch 1 | Batch 1432/3508 | Timestep 4940 | LR 0.0000100000 | Loss 0.100359 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:32 Epoch 1 | Batch 1442/3508 | Timestep 4950 | LR 0.0000100000 | Loss 0.114754 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:34 Epoch 1 | Batch 1452/3508 | Timestep 4960 | LR 0.0000100000 | Loss 0.022188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:37 Epoch 1 | Batch 1462/3508 | Timestep 4970 | LR 0.0000100000 | Loss 0.052083 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:39 Epoch 1 | Batch 1472/3508 | Timestep 4980 | LR 0.0000100000 | Loss 0.098907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:41 Epoch 1 | Batch 1482/3508 | Timestep 4990 | LR 0.0000100000 | Loss 0.077851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:44 Epoch 1 | Batch 1492/3508 | Timestep 5000 | LR 0.0000100000 | Loss 0.037144 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:46 Epoch 1 | Batch 1502/3508 | Timestep 5010 | LR 0.0000100000 | Loss 0.071483 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:47 Epoch 1 | Batch 1512/3508 | Timestep 5020 | LR 0.0000100000 | Loss 0.097335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:49 Epoch 1 | Batch 1522/3508 | Timestep 5030 | LR 0.0000100000 | Loss 0.083622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:51 Epoch 1 | Batch 1532/3508 | Timestep 5040 | LR 0.0000100000 | Loss 0.078607 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:53 Epoch 1 | Batch 1542/3508 | Timestep 5050 | LR 0.0000100000 | Loss 0.062863 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:55 Epoch 1 | Batch 1552/3508 | Timestep 5060 | LR 0.0000100000 | Loss 0.059397 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:57 Epoch 1 | Batch 1562/3508 | Timestep 5070 | LR 0.0000100000 | Loss 0.086158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:58:59 Epoch 1 | Batch 1572/3508 | Timestep 5080 | LR 0.0000100000 | Loss 0.052851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:01 Epoch 1 | Batch 1582/3508 | Timestep 5090 | LR 0.0000100000 | Loss 0.074877 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:03 Epoch 1 | Batch 1592/3508 | Timestep 5100 | LR 0.0000100000 | Loss 0.101809 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:05 Epoch 1 | Batch 1602/3508 | Timestep 5110 | LR 0.0000100000 | Loss 0.122506 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:07 Epoch 1 | Batch 1612/3508 | Timestep 5120 | LR 0.0000100000 | Loss 0.036646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:09 Epoch 1 | Batch 1622/3508 | Timestep 5130 | LR 0.0000100000 | Loss 0.081203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:11 Epoch 1 | Batch 1632/3508 | Timestep 5140 | LR 0.0000100000 | Loss 0.051867 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:13 Epoch 1 | Batch 1642/3508 | Timestep 5150 | LR 0.0000100000 | Loss 0.074916 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:15 Epoch 1 | Batch 1652/3508 | Timestep 5160 | LR 0.0000100000 | Loss 0.061452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:17 Epoch 1 | Batch 1662/3508 | Timestep 5170 | LR 0.0000100000 | Loss 0.021076 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:20 Epoch 1 | Batch 1672/3508 | Timestep 5180 | LR 0.0000100000 | Loss 0.047587 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:21 Epoch 1 | Batch 1682/3508 | Timestep 5190 | LR 0.0000100000 | Loss 0.046277 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:23 Epoch 1 | Batch 1692/3508 | Timestep 5200 | LR 0.0000100000 | Loss 0.057943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:25 Epoch 1 | Batch 1702/3508 | Timestep 5210 | LR 0.0000100000 | Loss 0.050019 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:28 Epoch 1 | Batch 1712/3508 | Timestep 5220 | LR 0.0000100000 | Loss 0.094278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:30 Epoch 1 | Batch 1722/3508 | Timestep 5230 | LR 0.0000100000 | Loss 0.093553 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:32 Epoch 1 | Batch 1732/3508 | Timestep 5240 | LR 0.0000100000 | Loss 0.065504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:34 Epoch 1 | Batch 1742/3508 | Timestep 5250 | LR 0.0000100000 | Loss 0.100156 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:36 Epoch 1 | Batch 1752/3508 | Timestep 5260 | LR 0.0000100000 | Loss 0.032588 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:39 Epoch 1 | Batch 1762/3508 | Timestep 5270 | LR 0.0000100000 | Loss 0.082560 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:42 Epoch 1 | Batch 1772/3508 | Timestep 5280 | LR 0.0000100000 | Loss 0.035022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:44 Epoch 1 | Batch 1782/3508 | Timestep 5290 | LR 0.0000100000 | Loss 0.060293 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:46 Epoch 1 | Batch 1792/3508 | Timestep 5300 | LR 0.0000100000 | Loss 0.095224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:48 Epoch 1 | Batch 1802/3508 | Timestep 5310 | LR 0.0000100000 | Loss 0.097383 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:51 Epoch 1 | Batch 1812/3508 | Timestep 5320 | LR 0.0000100000 | Loss 0.035559 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:53 Epoch 1 | Batch 1822/3508 | Timestep 5330 | LR 0.0000100000 | Loss 0.031058 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:55 Epoch 1 | Batch 1832/3508 | Timestep 5340 | LR 0.0000100000 | Loss 0.015893 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:57 Epoch 1 | Batch 1842/3508 | Timestep 5350 | LR 0.0000100000 | Loss 0.048194 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 14:59:59 Epoch 1 | Batch 1852/3508 | Timestep 5360 | LR 0.0000100000 | Loss 0.089085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:01 Epoch 1 | Batch 1862/3508 | Timestep 5370 | LR 0.0000100000 | Loss 0.066913 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:04 Epoch 1 | Batch 1872/3508 | Timestep 5380 | LR 0.0000100000 | Loss 0.046529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:06 Epoch 1 | Batch 1882/3508 | Timestep 5390 | LR 0.0000100000 | Loss 0.069227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:09 Epoch 1 | Batch 1892/3508 | Timestep 5400 | LR 0.0000100000 | Loss 0.044712 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:11 Epoch 1 | Batch 1902/3508 | Timestep 5410 | LR 0.0000100000 | Loss 0.053879 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:13 Epoch 1 | Batch 1912/3508 | Timestep 5420 | LR 0.0000100000 | Loss 0.018827 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:16 Epoch 1 | Batch 1922/3508 | Timestep 5430 | LR 0.0000100000 | Loss 0.127126 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:18 Epoch 1 | Batch 1932/3508 | Timestep 5440 | LR 0.0000100000 | Loss 0.070890 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:20 Epoch 1 | Batch 1942/3508 | Timestep 5450 | LR 0.0000100000 | Loss 0.020311 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:22 Epoch 1 | Batch 1952/3508 | Timestep 5460 | LR 0.0000100000 | Loss 0.094046 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:24 Epoch 1 | Batch 1962/3508 | Timestep 5470 | LR 0.0000100000 | Loss 0.023408 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:26 Epoch 1 | Batch 1972/3508 | Timestep 5480 | LR 0.0000100000 | Loss 0.063146 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:28 Epoch 1 | Batch 1982/3508 | Timestep 5490 | LR 0.0000100000 | Loss 0.070693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:30 Epoch 1 | Batch 1992/3508 | Timestep 5500 | LR 0.0000100000 | Loss 0.075970 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:32 Epoch 1 | Batch 2002/3508 | Timestep 5510 | LR 0.0000100000 | Loss 0.079779 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:34 Epoch 1 | Batch 2012/3508 | Timestep 5520 | LR 0.0000100000 | Loss 0.092268 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:35 Epoch 1 | Batch 2022/3508 | Timestep 5530 | LR 0.0000100000 | Loss 0.121065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:38 Epoch 1 | Batch 2032/3508 | Timestep 5540 | LR 0.0000100000 | Loss 0.043941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:40 Epoch 1 | Batch 2042/3508 | Timestep 5550 | LR 0.0000100000 | Loss 0.028232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:42 Epoch 1 | Batch 2052/3508 | Timestep 5560 | LR 0.0000100000 | Loss 0.080641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:45 Epoch 1 | Batch 2062/3508 | Timestep 5570 | LR 0.0000100000 | Loss 0.114435 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:47 Epoch 1 | Batch 2072/3508 | Timestep 5580 | LR 0.0000100000 | Loss 0.046661 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:49 Epoch 1 | Batch 2082/3508 | Timestep 5590 | LR 0.0000100000 | Loss 0.052633 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:52 Epoch 1 | Batch 2092/3508 | Timestep 5600 | LR 0.0000100000 | Loss 0.165471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:53 Epoch 1 | Batch 2102/3508 | Timestep 5610 | LR 0.0000100000 | Loss 0.044400 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:56 Epoch 1 | Batch 2112/3508 | Timestep 5620 | LR 0.0000100000 | Loss 0.036274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:58 Epoch 1 | Batch 2122/3508 | Timestep 5630 | LR 0.0000100000 | Loss 0.082197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:00:59 Epoch 1 | Batch 2132/3508 | Timestep 5640 | LR 0.0000100000 | Loss 0.142867 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:02 Epoch 1 | Batch 2142/3508 | Timestep 5650 | LR 0.0000100000 | Loss 0.040904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:03 Epoch 1 | Batch 2152/3508 | Timestep 5660 | LR 0.0000100000 | Loss 0.056127 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:05 Epoch 1 | Batch 2162/3508 | Timestep 5670 | LR 0.0000100000 | Loss 0.085471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:07 Epoch 1 | Batch 2172/3508 | Timestep 5680 | LR 0.0000100000 | Loss 0.039879 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:09 Epoch 1 | Batch 2182/3508 | Timestep 5690 | LR 0.0000100000 | Loss 0.086820 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:11 Epoch 1 | Batch 2192/3508 | Timestep 5700 | LR 0.0000100000 | Loss 0.080926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:13 Epoch 1 | Batch 2202/3508 | Timestep 5710 | LR 0.0000100000 | Loss 0.028642 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:15 Epoch 1 | Batch 2212/3508 | Timestep 5720 | LR 0.0000100000 | Loss 0.057743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:17 Epoch 1 | Batch 2222/3508 | Timestep 5730 | LR 0.0000100000 | Loss 0.041539 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:20 Epoch 1 | Batch 2232/3508 | Timestep 5740 | LR 0.0000100000 | Loss 0.060086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:22 Epoch 1 | Batch 2242/3508 | Timestep 5750 | LR 0.0000100000 | Loss 0.190904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:24 Epoch 1 | Batch 2252/3508 | Timestep 5760 | LR 0.0000100000 | Loss 0.110199 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:26 Epoch 1 | Batch 2262/3508 | Timestep 5770 | LR 0.0000100000 | Loss 0.132717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:28 Epoch 1 | Batch 2272/3508 | Timestep 5780 | LR 0.0000100000 | Loss 0.069480 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:30 Epoch 1 | Batch 2282/3508 | Timestep 5790 | LR 0.0000100000 | Loss 0.104423 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:32 Epoch 1 | Batch 2292/3508 | Timestep 5800 | LR 0.0000100000 | Loss 0.059648 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:34 Epoch 1 | Batch 2302/3508 | Timestep 5810 | LR 0.0000100000 | Loss 0.021728 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:36 Epoch 1 | Batch 2312/3508 | Timestep 5820 | LR 0.0000100000 | Loss 0.059196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:38 Epoch 1 | Batch 2322/3508 | Timestep 5830 | LR 0.0000100000 | Loss 0.052497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:41 Epoch 1 | Batch 2332/3508 | Timestep 5840 | LR 0.0000100000 | Loss 0.061856 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:43 Epoch 1 | Batch 2342/3508 | Timestep 5850 | LR 0.0000100000 | Loss 0.033952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:44 Epoch 1 | Batch 2352/3508 | Timestep 5860 | LR 0.0000100000 | Loss 0.064955 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:46 Epoch 1 | Batch 2362/3508 | Timestep 5870 | LR 0.0000100000 | Loss 0.024164 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:49 Epoch 1 | Batch 2372/3508 | Timestep 5880 | LR 0.0000100000 | Loss 0.032128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:51 Epoch 1 | Batch 2382/3508 | Timestep 5890 | LR 0.0000100000 | Loss 0.096805 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:54 Epoch 1 | Batch 2392/3508 | Timestep 5900 | LR 0.0000100000 | Loss 0.039492 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:56 Epoch 1 | Batch 2402/3508 | Timestep 5910 | LR 0.0000100000 | Loss 0.086473 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:01:58 Epoch 1 | Batch 2412/3508 | Timestep 5920 | LR 0.0000100000 | Loss 0.071847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:00 Epoch 1 | Batch 2422/3508 | Timestep 5930 | LR 0.0000100000 | Loss 0.018376 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:02 Epoch 1 | Batch 2432/3508 | Timestep 5940 | LR 0.0000100000 | Loss 0.067062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:04 Epoch 1 | Batch 2442/3508 | Timestep 5950 | LR 0.0000100000 | Loss 0.027512 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:06 Epoch 1 | Batch 2452/3508 | Timestep 5960 | LR 0.0000100000 | Loss 0.016925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:08 Epoch 1 | Batch 2462/3508 | Timestep 5970 | LR 0.0000100000 | Loss 0.089600 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:10 Epoch 1 | Batch 2472/3508 | Timestep 5980 | LR 0.0000100000 | Loss 0.083577 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:12 Epoch 1 | Batch 2482/3508 | Timestep 5990 | LR 0.0000100000 | Loss 0.066012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:15 Epoch 1 | Batch 2492/3508 | Timestep 6000 | LR 0.0000100000 | Loss 0.029275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:17 Epoch 1 | Batch 2502/3508 | Timestep 6010 | LR 0.0000100000 | Loss 0.040308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:19 Epoch 1 | Batch 2512/3508 | Timestep 6020 | LR 0.0000100000 | Loss 0.102980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:22 Epoch 1 | Batch 2522/3508 | Timestep 6030 | LR 0.0000100000 | Loss 0.054431 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:24 Epoch 1 | Batch 2532/3508 | Timestep 6040 | LR 0.0000100000 | Loss 0.049995 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:26 Epoch 1 | Batch 2542/3508 | Timestep 6050 | LR 0.0000100000 | Loss 0.026102 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:28 Epoch 1 | Batch 2552/3508 | Timestep 6060 | LR 0.0000100000 | Loss 0.075483 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:30 Epoch 1 | Batch 2562/3508 | Timestep 6070 | LR 0.0000100000 | Loss 0.047003 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:32 Epoch 1 | Batch 2572/3508 | Timestep 6080 | LR 0.0000100000 | Loss 0.028228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:34 Epoch 1 | Batch 2582/3508 | Timestep 6090 | LR 0.0000100000 | Loss 0.059500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:36 Epoch 1 | Batch 2592/3508 | Timestep 6100 | LR 0.0000100000 | Loss 0.090521 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:39 Epoch 1 | Batch 2602/3508 | Timestep 6110 | LR 0.0000100000 | Loss 0.075155 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:41 Epoch 1 | Batch 2612/3508 | Timestep 6120 | LR 0.0000100000 | Loss 0.041433 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:43 Epoch 1 | Batch 2622/3508 | Timestep 6130 | LR 0.0000100000 | Loss 0.043080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:44 Epoch 1 | Batch 2632/3508 | Timestep 6140 | LR 0.0000100000 | Loss 0.027630 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:46 Epoch 1 | Batch 2642/3508 | Timestep 6150 | LR 0.0000100000 | Loss 0.053225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:49 Epoch 1 | Batch 2652/3508 | Timestep 6160 | LR 0.0000100000 | Loss 0.020637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:51 Epoch 1 | Batch 2662/3508 | Timestep 6170 | LR 0.0000100000 | Loss 0.111327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:53 Epoch 1 | Batch 2672/3508 | Timestep 6180 | LR 0.0000100000 | Loss 0.051410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:55 Epoch 1 | Batch 2682/3508 | Timestep 6190 | LR 0.0000100000 | Loss 0.013690 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:02:58 Epoch 1 | Batch 2692/3508 | Timestep 6200 | LR 0.0000100000 | Loss 0.071070 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:00 Epoch 1 | Batch 2702/3508 | Timestep 6210 | LR 0.0000100000 | Loss 0.041873 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:03 Epoch 1 | Batch 2712/3508 | Timestep 6220 | LR 0.0000100000 | Loss 0.034706 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:05 Epoch 1 | Batch 2722/3508 | Timestep 6230 | LR 0.0000100000 | Loss 0.035282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:07 Epoch 1 | Batch 2732/3508 | Timestep 6240 | LR 0.0000100000 | Loss 0.049169 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:10 Epoch 1 | Batch 2742/3508 | Timestep 6250 | LR 0.0000100000 | Loss 0.061110 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:13 Epoch 1 | Batch 2752/3508 | Timestep 6260 | LR 0.0000100000 | Loss 0.027985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:15 Epoch 1 | Batch 2762/3508 | Timestep 6270 | LR 0.0000100000 | Loss 0.068345 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:17 Epoch 1 | Batch 2772/3508 | Timestep 6280 | LR 0.0000100000 | Loss 0.115707 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:19 Epoch 1 | Batch 2782/3508 | Timestep 6290 | LR 0.0000100000 | Loss 0.022760 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:22 Epoch 1 | Batch 2792/3508 | Timestep 6300 | LR 0.0000100000 | Loss 0.036129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:23 Epoch 1 | Batch 2802/3508 | Timestep 6310 | LR 0.0000100000 | Loss 0.075975 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:26 Epoch 1 | Batch 2812/3508 | Timestep 6320 | LR 0.0000100000 | Loss 0.024020 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:28 Epoch 1 | Batch 2822/3508 | Timestep 6330 | LR 0.0000100000 | Loss 0.061414 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:30 Epoch 1 | Batch 2832/3508 | Timestep 6340 | LR 0.0000100000 | Loss 0.031138 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:33 Epoch 1 | Batch 2842/3508 | Timestep 6350 | LR 0.0000100000 | Loss 0.090050 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:35 Epoch 1 | Batch 2852/3508 | Timestep 6360 | LR 0.0000100000 | Loss 0.041146 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:37 Epoch 1 | Batch 2862/3508 | Timestep 6370 | LR 0.0000100000 | Loss 0.082026 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:39 Epoch 1 | Batch 2872/3508 | Timestep 6380 | LR 0.0000100000 | Loss 0.050747 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:41 Epoch 1 | Batch 2882/3508 | Timestep 6390 | LR 0.0000100000 | Loss 0.052476 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:43 Epoch 1 | Batch 2892/3508 | Timestep 6400 | LR 0.0000100000 | Loss 0.023158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:46 Epoch 1 | Batch 2902/3508 | Timestep 6410 | LR 0.0000100000 | Loss 0.088952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:48 Epoch 1 | Batch 2912/3508 | Timestep 6420 | LR 0.0000100000 | Loss 0.030038 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:50 Epoch 1 | Batch 2922/3508 | Timestep 6430 | LR 0.0000100000 | Loss 0.017376 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:52 Epoch 1 | Batch 2932/3508 | Timestep 6440 | LR 0.0000100000 | Loss 0.058875 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:54 Epoch 1 | Batch 2942/3508 | Timestep 6450 | LR 0.0000100000 | Loss 0.050604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:57 Epoch 1 | Batch 2952/3508 | Timestep 6460 | LR 0.0000100000 | Loss 0.089981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:03:58 Epoch 1 | Batch 2962/3508 | Timestep 6470 | LR 0.0000100000 | Loss 0.035406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:00 Epoch 1 | Batch 2972/3508 | Timestep 6480 | LR 0.0000100000 | Loss 0.045308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:03 Epoch 1 | Batch 2982/3508 | Timestep 6490 | LR 0.0000100000 | Loss 0.027385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:05 Epoch 1 | Batch 2992/3508 | Timestep 6500 | LR 0.0000100000 | Loss 0.075442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:08 Epoch 1 | Batch 3002/3508 | Timestep 6510 | LR 0.0000100000 | Loss 0.037015 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:10 Epoch 1 | Batch 3012/3508 | Timestep 6520 | LR 0.0000100000 | Loss 0.050349 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:13 Epoch 1 | Batch 3022/3508 | Timestep 6530 | LR 0.0000100000 | Loss 0.107331 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:15 Epoch 1 | Batch 3032/3508 | Timestep 6540 | LR 0.0000100000 | Loss 0.012977 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:17 Epoch 1 | Batch 3042/3508 | Timestep 6550 | LR 0.0000100000 | Loss 0.090353 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:19 Epoch 1 | Batch 3052/3508 | Timestep 6560 | LR 0.0000100000 | Loss 0.056726 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:21 Epoch 1 | Batch 3062/3508 | Timestep 6570 | LR 0.0000100000 | Loss 0.062794 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:23 Epoch 1 | Batch 3072/3508 | Timestep 6580 | LR 0.0000100000 | Loss 0.084634 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:26 Epoch 1 | Batch 3082/3508 | Timestep 6590 | LR 0.0000100000 | Loss 0.043652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:28 Epoch 1 | Batch 3092/3508 | Timestep 6600 | LR 0.0000100000 | Loss 0.133619 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:29 Epoch 1 | Batch 3102/3508 | Timestep 6610 | LR 0.0000100000 | Loss 0.046540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:31 Epoch 1 | Batch 3112/3508 | Timestep 6620 | LR 0.0000100000 | Loss 0.145031 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:34 Epoch 1 | Batch 3122/3508 | Timestep 6630 | LR 0.0000100000 | Loss 0.069256 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:36 Epoch 1 | Batch 3132/3508 | Timestep 6640 | LR 0.0000100000 | Loss 0.049188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:38 Epoch 1 | Batch 3142/3508 | Timestep 6650 | LR 0.0000100000 | Loss 0.028013 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:41 Epoch 1 | Batch 3152/3508 | Timestep 6660 | LR 0.0000100000 | Loss 0.027018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:43 Epoch 1 | Batch 3162/3508 | Timestep 6670 | LR 0.0000100000 | Loss 0.037467 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:45 Epoch 1 | Batch 3172/3508 | Timestep 6680 | LR 0.0000100000 | Loss 0.027403 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:47 Epoch 1 | Batch 3182/3508 | Timestep 6690 | LR 0.0000100000 | Loss 0.007835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:49 Epoch 1 | Batch 3192/3508 | Timestep 6700 | LR 0.0000100000 | Loss 0.118716 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:51 Epoch 1 | Batch 3202/3508 | Timestep 6710 | LR 0.0000100000 | Loss 0.037230 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:53 Epoch 1 | Batch 3212/3508 | Timestep 6720 | LR 0.0000100000 | Loss 0.042934 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:55 Epoch 1 | Batch 3222/3508 | Timestep 6730 | LR 0.0000100000 | Loss 0.090116 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:04:58 Epoch 1 | Batch 3232/3508 | Timestep 6740 | LR 0.0000100000 | Loss 0.029282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:00 Epoch 1 | Batch 3242/3508 | Timestep 6750 | LR 0.0000100000 | Loss 0.116720 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:02 Epoch 1 | Batch 3252/3508 | Timestep 6760 | LR 0.0000100000 | Loss 0.083384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:05 Epoch 1 | Batch 3262/3508 | Timestep 6770 | LR 0.0000100000 | Loss 0.018497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:07 Epoch 1 | Batch 3272/3508 | Timestep 6780 | LR 0.0000100000 | Loss 0.024398 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:09 Epoch 1 | Batch 3282/3508 | Timestep 6790 | LR 0.0000100000 | Loss 0.063641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:11 Epoch 1 | Batch 3292/3508 | Timestep 6800 | LR 0.0000100000 | Loss 0.029632 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:14 Epoch 1 | Batch 3302/3508 | Timestep 6810 | LR 0.0000100000 | Loss 0.032764 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:16 Epoch 1 | Batch 3312/3508 | Timestep 6820 | LR 0.0000100000 | Loss 0.085335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:18 Epoch 1 | Batch 3322/3508 | Timestep 6830 | LR 0.0000100000 | Loss 0.055565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:20 Epoch 1 | Batch 3332/3508 | Timestep 6840 | LR 0.0000100000 | Loss 0.017788 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:22 Epoch 1 | Batch 3342/3508 | Timestep 6850 | LR 0.0000100000 | Loss 0.113157 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:24 Epoch 1 | Batch 3352/3508 | Timestep 6860 | LR 0.0000100000 | Loss 0.096140 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:26 Epoch 1 | Batch 3362/3508 | Timestep 6870 | LR 0.0000100000 | Loss 0.012120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:28 Epoch 1 | Batch 3372/3508 | Timestep 6880 | LR 0.0000100000 | Loss 0.065962 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:31 Epoch 1 | Batch 3382/3508 | Timestep 6890 | LR 0.0000100000 | Loss 0.076204 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:33 Epoch 1 | Batch 3392/3508 | Timestep 6900 | LR 0.0000100000 | Loss 0.092324 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:36 Epoch 1 | Batch 3402/3508 | Timestep 6910 | LR 0.0000100000 | Loss 0.035584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:38 Epoch 1 | Batch 3412/3508 | Timestep 6920 | LR 0.0000100000 | Loss 0.075641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:40 Epoch 1 | Batch 3422/3508 | Timestep 6930 | LR 0.0000100000 | Loss 0.088935 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:42 Epoch 1 | Batch 3432/3508 | Timestep 6940 | LR 0.0000100000 | Loss 0.120263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:44 Epoch 1 | Batch 3442/3508 | Timestep 6950 | LR 0.0000100000 | Loss 0.035160 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:46 Epoch 1 | Batch 3452/3508 | Timestep 6960 | LR 0.0000100000 | Loss 0.020952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:47 Epoch 1 | Batch 3462/3508 | Timestep 6970 | LR 0.0000100000 | Loss 0.057940 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:50 Epoch 1 | Batch 3472/3508 | Timestep 6980 | LR 0.0000100000 | Loss 0.027344 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:51 Epoch 1 | Batch 3482/3508 | Timestep 6990 | LR 0.0000100000 | Loss 0.065831 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:54 Epoch 1 | Batch 3492/3508 | Timestep 7000 | LR 0.0000100000 | Loss 0.057568 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:55 Epoch 1 | Batch 3502/3508 | Timestep 7010 | LR 0.0000100000 | Loss 0.052320 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:05:56 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 15:06:29 precision recall f1-score support CARDINAL 0.7987 0.7736 0.7859 159 CURR 0.7391 0.7727 0.7556 22 DATE 0.9089 0.9323 0.9204 1669 EVENT 0.6634 0.7244 0.6926 283 FAC 0.6397 0.7373 0.6850 118 GPE 0.9377 0.9640 0.9507 2140 LANGUAGE 1.0000 0.4375 0.6087 16 LAW 0.4286 0.7895 0.5556 19 LOC 0.7353 0.5556 0.6329 90 MONEY 0.6818 0.7500 0.7143 20 NORP 0.5934 0.6739 0.6311 509 OCC 0.7014 0.8286 0.7597 496 ORDINAL 0.8806 0.9260 0.9027 446 ORG 0.8824 0.9169 0.8993 1866 PERCENT 0.7500 1.0000 0.8571 12 PERS 0.9095 0.9175 0.9135 679 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.3333 0.3333 0.3333 3 TIME 0.6333 0.6129 0.6230 31 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.4186 0.4500 0.4337 80 micro avg 0.8508 0.8893 0.8696 8670 macro avg 0.6969 0.7070 0.6911 8670 weighted avg 0.8544 0.8893 0.8706 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:06:39 Epoch 1 | Timestep 7016 | Train Loss 0.069926 | Val Loss 0.066639 | F1 0.869614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:06:39 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 25 Jun 2026 15:07:02 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Thu, 25 Jun 2026 15:07:19 Predictions written to /rep/nhamad/ArabicNER/B1/predictions.txt INFO root Thu, 25 Jun 2026 15:07:43 precision recall f1-score support CARDINAL 0.7800 0.8349 0.8065 327 CURR 0.5227 0.6053 0.5610 38 DATE 0.9241 0.9480 0.9359 3173 EVENT 0.6833 0.7335 0.7075 559 FAC 0.6939 0.7025 0.6982 242 GPE 0.9122 0.9571 0.9341 4311 LANGUAGE 0.9000 0.4091 0.5625 44 LAW 0.5000 0.6897 0.5797 29 LOC 0.7397 0.4954 0.5934 218 MONEY 0.6471 0.7333 0.6875 30 NORP 0.6201 0.7107 0.6623 992 OCC 0.7012 0.8300 0.7602 1035 ORDINAL 0.8626 0.9012 0.8815 850 ORG 0.8552 0.9056 0.8797 3738 PERCENT 0.8387 0.8125 0.8254 32 PERS 0.9127 0.9062 0.9094 1568 PRODUCT 0.5556 0.2632 0.3571 19 QUANTITY 0.0667 0.1111 0.0833 9 TIME 0.6364 0.5385 0.5833 78 UNIT 0.8750 0.6364 0.7368 11 WEBSITE 0.3607 0.3793 0.3697 116 micro avg 0.8449 0.8863 0.8651 17419 macro avg 0.6947 0.6716 0.6721 17419 weighted avg 0.8477 0.8863 0.8655 17419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:03 Epoch 1 | Timestep 7016 | Test Loss 0.070924 | F1 0.865124 INFO arabiner.trainers.BaseTrainer Thu, 25 Jun 2026 15:08:03 Saving checkpoint to /rep/nhamad/ArabicNER/B1/checkpoints/checkpoint_1.pt INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:07 Epoch 2 | Batch 4/3508 | Timestep 7020 | LR 0.0000100000 | Loss 0.054217 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:09 Epoch 2 | Batch 14/3508 | Timestep 7030 | LR 0.0000100000 | Loss 0.124004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:11 Epoch 2 | Batch 24/3508 | Timestep 7040 | LR 0.0000100000 | Loss 0.028521 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:13 Epoch 2 | Batch 34/3508 | Timestep 7050 | LR 0.0000100000 | Loss 0.056744 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:16 Epoch 2 | Batch 44/3508 | Timestep 7060 | LR 0.0000100000 | Loss 0.072323 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:19 Epoch 2 | Batch 54/3508 | Timestep 7070 | LR 0.0000100000 | Loss 0.027745 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:20 Epoch 2 | Batch 64/3508 | Timestep 7080 | LR 0.0000100000 | Loss 0.030997 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:22 Epoch 2 | Batch 74/3508 | Timestep 7090 | LR 0.0000100000 | Loss 0.045024 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:24 Epoch 2 | Batch 84/3508 | Timestep 7100 | LR 0.0000100000 | Loss 0.019574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:26 Epoch 2 | Batch 94/3508 | Timestep 7110 | LR 0.0000100000 | Loss 0.082278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:28 Epoch 2 | Batch 104/3508 | Timestep 7120 | LR 0.0000100000 | Loss 0.058105 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:30 Epoch 2 | Batch 114/3508 | Timestep 7130 | LR 0.0000100000 | Loss 0.033809 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:32 Epoch 2 | Batch 124/3508 | Timestep 7140 | LR 0.0000100000 | Loss 0.019741 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:35 Epoch 2 | Batch 134/3508 | Timestep 7150 | LR 0.0000100000 | Loss 0.083673 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:37 Epoch 2 | Batch 144/3508 | Timestep 7160 | LR 0.0000100000 | Loss 0.037278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:39 Epoch 2 | Batch 154/3508 | Timestep 7170 | LR 0.0000100000 | Loss 0.049704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:41 Epoch 2 | Batch 164/3508 | Timestep 7180 | LR 0.0000100000 | Loss 0.016933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:42 Epoch 2 | Batch 174/3508 | Timestep 7190 | LR 0.0000100000 | Loss 0.044197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:45 Epoch 2 | Batch 184/3508 | Timestep 7200 | LR 0.0000100000 | Loss 0.088761 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:46 Epoch 2 | Batch 194/3508 | Timestep 7210 | LR 0.0000100000 | Loss 0.031016 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:48 Epoch 2 | Batch 204/3508 | Timestep 7220 | LR 0.0000100000 | Loss 0.108931 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:50 Epoch 2 | Batch 214/3508 | Timestep 7230 | LR 0.0000100000 | Loss 0.070815 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:52 Epoch 2 | Batch 224/3508 | Timestep 7240 | LR 0.0000100000 | Loss 0.020686 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:55 Epoch 2 | Batch 234/3508 | Timestep 7250 | LR 0.0000100000 | Loss 0.053522 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:57 Epoch 2 | Batch 244/3508 | Timestep 7260 | LR 0.0000100000 | Loss 0.051820 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:08:59 Epoch 2 | Batch 254/3508 | Timestep 7270 | LR 0.0000100000 | Loss 0.025901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:01 Epoch 2 | Batch 264/3508 | Timestep 7280 | LR 0.0000100000 | Loss 0.028246 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:03 Epoch 2 | Batch 274/3508 | Timestep 7290 | LR 0.0000100000 | Loss 0.055531 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:06 Epoch 2 | Batch 284/3508 | Timestep 7300 | LR 0.0000100000 | Loss 0.027270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:09 Epoch 2 | Batch 294/3508 | Timestep 7310 | LR 0.0000100000 | Loss 0.045884 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:10 Epoch 2 | Batch 304/3508 | Timestep 7320 | LR 0.0000100000 | Loss 0.081643 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:13 Epoch 2 | Batch 314/3508 | Timestep 7330 | LR 0.0000100000 | Loss 0.045947 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:15 Epoch 2 | Batch 324/3508 | Timestep 7340 | LR 0.0000100000 | Loss 0.049525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:17 Epoch 2 | Batch 334/3508 | Timestep 7350 | LR 0.0000100000 | Loss 0.038341 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:19 Epoch 2 | Batch 344/3508 | Timestep 7360 | LR 0.0000100000 | Loss 0.029359 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:21 Epoch 2 | Batch 354/3508 | Timestep 7370 | LR 0.0000100000 | Loss 0.075256 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:23 Epoch 2 | Batch 364/3508 | Timestep 7380 | LR 0.0000100000 | Loss 0.027804 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:26 Epoch 2 | Batch 374/3508 | Timestep 7390 | LR 0.0000100000 | Loss 0.046030 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:28 Epoch 2 | Batch 384/3508 | Timestep 7400 | LR 0.0000100000 | Loss 0.036343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:31 Epoch 2 | Batch 394/3508 | Timestep 7410 | LR 0.0000100000 | Loss 0.019652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:33 Epoch 2 | Batch 404/3508 | Timestep 7420 | LR 0.0000100000 | Loss 0.025676 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:35 Epoch 2 | Batch 414/3508 | Timestep 7430 | LR 0.0000100000 | Loss 0.050327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:38 Epoch 2 | Batch 424/3508 | Timestep 7440 | LR 0.0000100000 | Loss 0.045997 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:40 Epoch 2 | Batch 434/3508 | Timestep 7450 | LR 0.0000100000 | Loss 0.181232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:42 Epoch 2 | Batch 444/3508 | Timestep 7460 | LR 0.0000100000 | Loss 0.046844 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:44 Epoch 2 | Batch 454/3508 | Timestep 7470 | LR 0.0000100000 | Loss 0.017237 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:46 Epoch 2 | Batch 464/3508 | Timestep 7480 | LR 0.0000100000 | Loss 0.036845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:48 Epoch 2 | Batch 474/3508 | Timestep 7490 | LR 0.0000100000 | Loss 0.029912 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:50 Epoch 2 | Batch 484/3508 | Timestep 7500 | LR 0.0000100000 | Loss 0.059639 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:52 Epoch 2 | Batch 494/3508 | Timestep 7510 | LR 0.0000100000 | Loss 0.038266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:55 Epoch 2 | Batch 504/3508 | Timestep 7520 | LR 0.0000100000 | Loss 0.067044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:09:57 Epoch 2 | Batch 514/3508 | Timestep 7530 | LR 0.0000100000 | Loss 0.055308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:00 Epoch 2 | Batch 524/3508 | Timestep 7540 | LR 0.0000100000 | Loss 0.042864 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:02 Epoch 2 | Batch 534/3508 | Timestep 7550 | LR 0.0000100000 | Loss 0.036517 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:04 Epoch 2 | Batch 544/3508 | Timestep 7560 | LR 0.0000100000 | Loss 0.064390 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:07 Epoch 2 | Batch 554/3508 | Timestep 7570 | LR 0.0000100000 | Loss 0.021090 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:09 Epoch 2 | Batch 564/3508 | Timestep 7580 | LR 0.0000100000 | Loss 0.071980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:10 Epoch 2 | Batch 574/3508 | Timestep 7590 | LR 0.0000100000 | Loss 0.014206 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:13 Epoch 2 | Batch 584/3508 | Timestep 7600 | LR 0.0000100000 | Loss 0.027693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:15 Epoch 2 | Batch 594/3508 | Timestep 7610 | LR 0.0000100000 | Loss 0.045877 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:18 Epoch 2 | Batch 604/3508 | Timestep 7620 | LR 0.0000100000 | Loss 0.069307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:20 Epoch 2 | Batch 614/3508 | Timestep 7630 | LR 0.0000100000 | Loss 0.017441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:22 Epoch 2 | Batch 624/3508 | Timestep 7640 | LR 0.0000100000 | Loss 0.029024 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:24 Epoch 2 | Batch 634/3508 | Timestep 7650 | LR 0.0000100000 | Loss 0.025062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:26 Epoch 2 | Batch 644/3508 | Timestep 7660 | LR 0.0000100000 | Loss 0.043972 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:29 Epoch 2 | Batch 654/3508 | Timestep 7670 | LR 0.0000100000 | Loss 0.040010 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:32 Epoch 2 | Batch 664/3508 | Timestep 7680 | LR 0.0000100000 | Loss 0.044771 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:34 Epoch 2 | Batch 674/3508 | Timestep 7690 | LR 0.0000100000 | Loss 0.049666 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:36 Epoch 2 | Batch 684/3508 | Timestep 7700 | LR 0.0000100000 | Loss 0.057315 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:39 Epoch 2 | Batch 694/3508 | Timestep 7710 | LR 0.0000100000 | Loss 0.023001 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:41 Epoch 2 | Batch 704/3508 | Timestep 7720 | LR 0.0000100000 | Loss 0.083938 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:43 Epoch 2 | Batch 714/3508 | Timestep 7730 | LR 0.0000100000 | Loss 0.020120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:45 Epoch 2 | Batch 724/3508 | Timestep 7740 | LR 0.0000100000 | Loss 0.021533 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:48 Epoch 2 | Batch 734/3508 | Timestep 7750 | LR 0.0000100000 | Loss 0.023556 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:50 Epoch 2 | Batch 744/3508 | Timestep 7760 | LR 0.0000100000 | Loss 0.028191 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:52 Epoch 2 | Batch 754/3508 | Timestep 7770 | LR 0.0000100000 | Loss 0.093246 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:54 Epoch 2 | Batch 764/3508 | Timestep 7780 | LR 0.0000100000 | Loss 0.072050 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:56 Epoch 2 | Batch 774/3508 | Timestep 7790 | LR 0.0000100000 | Loss 0.038028 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:10:58 Epoch 2 | Batch 784/3508 | Timestep 7800 | LR 0.0000100000 | Loss 0.049974 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:00 Epoch 2 | Batch 794/3508 | Timestep 7810 | LR 0.0000100000 | Loss 0.031694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:02 Epoch 2 | Batch 804/3508 | Timestep 7820 | LR 0.0000100000 | Loss 0.091613 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:04 Epoch 2 | Batch 814/3508 | Timestep 7830 | LR 0.0000100000 | Loss 0.031699 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:06 Epoch 2 | Batch 824/3508 | Timestep 7840 | LR 0.0000100000 | Loss 0.016562 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:08 Epoch 2 | Batch 834/3508 | Timestep 7850 | LR 0.0000100000 | Loss 0.061131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:10 Epoch 2 | Batch 844/3508 | Timestep 7860 | LR 0.0000100000 | Loss 0.033643 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:12 Epoch 2 | Batch 854/3508 | Timestep 7870 | LR 0.0000100000 | Loss 0.019089 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:14 Epoch 2 | Batch 864/3508 | Timestep 7880 | LR 0.0000100000 | Loss 0.122203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:16 Epoch 2 | Batch 874/3508 | Timestep 7890 | LR 0.0000100000 | Loss 0.059102 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:20 Epoch 2 | Batch 884/3508 | Timestep 7900 | LR 0.0000100000 | Loss 0.109624 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:21 Epoch 2 | Batch 894/3508 | Timestep 7910 | LR 0.0000100000 | Loss 0.019524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:24 Epoch 2 | Batch 904/3508 | Timestep 7920 | LR 0.0000100000 | Loss 0.041759 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:26 Epoch 2 | Batch 914/3508 | Timestep 7930 | LR 0.0000100000 | Loss 0.055530 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:28 Epoch 2 | Batch 924/3508 | Timestep 7940 | LR 0.0000100000 | Loss 0.015772 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:30 Epoch 2 | Batch 934/3508 | Timestep 7950 | LR 0.0000100000 | Loss 0.015135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:32 Epoch 2 | Batch 944/3508 | Timestep 7960 | LR 0.0000100000 | Loss 0.079018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:34 Epoch 2 | Batch 954/3508 | Timestep 7970 | LR 0.0000100000 | Loss 0.026429 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:37 Epoch 2 | Batch 964/3508 | Timestep 7980 | LR 0.0000100000 | Loss 0.081478 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:39 Epoch 2 | Batch 974/3508 | Timestep 7990 | LR 0.0000100000 | Loss 0.043720 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:41 Epoch 2 | Batch 984/3508 | Timestep 8000 | LR 0.0000100000 | Loss 0.024131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:43 Epoch 2 | Batch 994/3508 | Timestep 8010 | LR 0.0000100000 | Loss 0.062384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:45 Epoch 2 | Batch 1004/3508 | Timestep 8020 | LR 0.0000100000 | Loss 0.055056 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:47 Epoch 2 | Batch 1014/3508 | Timestep 8030 | LR 0.0000100000 | Loss 0.011948 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:50 Epoch 2 | Batch 1024/3508 | Timestep 8040 | LR 0.0000100000 | Loss 0.036736 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:52 Epoch 2 | Batch 1034/3508 | Timestep 8050 | LR 0.0000100000 | Loss 0.015400 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:55 Epoch 2 | Batch 1044/3508 | Timestep 8060 | LR 0.0000100000 | Loss 0.021064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:57 Epoch 2 | Batch 1054/3508 | Timestep 8070 | LR 0.0000100000 | Loss 0.009852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:11:59 Epoch 2 | Batch 1064/3508 | Timestep 8080 | LR 0.0000100000 | Loss 0.043443 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:01 Epoch 2 | Batch 1074/3508 | Timestep 8090 | LR 0.0000100000 | Loss 0.055628 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:04 Epoch 2 | Batch 1084/3508 | Timestep 8100 | LR 0.0000100000 | Loss 0.032560 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:06 Epoch 2 | Batch 1094/3508 | Timestep 8110 | LR 0.0000100000 | Loss 0.101330 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:08 Epoch 2 | Batch 1104/3508 | Timestep 8120 | LR 0.0000100000 | Loss 0.043126 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:10 Epoch 2 | Batch 1114/3508 | Timestep 8130 | LR 0.0000100000 | Loss 0.027739 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:13 Epoch 2 | Batch 1124/3508 | Timestep 8140 | LR 0.0000100000 | Loss 0.041932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:14 Epoch 2 | Batch 1134/3508 | Timestep 8150 | LR 0.0000100000 | Loss 0.073749 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:17 Epoch 2 | Batch 1144/3508 | Timestep 8160 | LR 0.0000100000 | Loss 0.053518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:19 Epoch 2 | Batch 1154/3508 | Timestep 8170 | LR 0.0000100000 | Loss 0.077683 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:21 Epoch 2 | Batch 1164/3508 | Timestep 8180 | LR 0.0000100000 | Loss 0.047263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:23 Epoch 2 | Batch 1174/3508 | Timestep 8190 | LR 0.0000100000 | Loss 0.054062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:25 Epoch 2 | Batch 1184/3508 | Timestep 8200 | LR 0.0000100000 | Loss 0.040498 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:27 Epoch 2 | Batch 1194/3508 | Timestep 8210 | LR 0.0000100000 | Loss 0.044379 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:30 Epoch 2 | Batch 1204/3508 | Timestep 8220 | LR 0.0000100000 | Loss 0.076133 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:32 Epoch 2 | Batch 1214/3508 | Timestep 8230 | LR 0.0000100000 | Loss 0.033585 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:34 Epoch 2 | Batch 1224/3508 | Timestep 8240 | LR 0.0000100000 | Loss 0.039100 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:38 Epoch 2 | Batch 1234/3508 | Timestep 8250 | LR 0.0000100000 | Loss 0.005244 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:40 Epoch 2 | Batch 1244/3508 | Timestep 8260 | LR 0.0000100000 | Loss 0.020505 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:42 Epoch 2 | Batch 1254/3508 | Timestep 8270 | LR 0.0000100000 | Loss 0.040897 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:44 Epoch 2 | Batch 1264/3508 | Timestep 8280 | LR 0.0000100000 | Loss 0.050217 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:46 Epoch 2 | Batch 1274/3508 | Timestep 8290 | LR 0.0000100000 | Loss 0.057452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:48 Epoch 2 | Batch 1284/3508 | Timestep 8300 | LR 0.0000100000 | Loss 0.032172 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:50 Epoch 2 | Batch 1294/3508 | Timestep 8310 | LR 0.0000100000 | Loss 0.037390 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:52 Epoch 2 | Batch 1304/3508 | Timestep 8320 | LR 0.0000100000 | Loss 0.043899 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:54 Epoch 2 | Batch 1314/3508 | Timestep 8330 | LR 0.0000100000 | Loss 0.041290 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:56 Epoch 2 | Batch 1324/3508 | Timestep 8340 | LR 0.0000100000 | Loss 0.060279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:12:58 Epoch 2 | Batch 1334/3508 | Timestep 8350 | LR 0.0000100000 | Loss 0.040088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:00 Epoch 2 | Batch 1344/3508 | Timestep 8360 | LR 0.0000100000 | Loss 0.030559 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:03 Epoch 2 | Batch 1354/3508 | Timestep 8370 | LR 0.0000100000 | Loss 0.086446 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:05 Epoch 2 | Batch 1364/3508 | Timestep 8380 | LR 0.0000100000 | Loss 0.006692 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:07 Epoch 2 | Batch 1374/3508 | Timestep 8390 | LR 0.0000100000 | Loss 0.037013 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:09 Epoch 2 | Batch 1384/3508 | Timestep 8400 | LR 0.0000100000 | Loss 0.026405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:12 Epoch 2 | Batch 1394/3508 | Timestep 8410 | LR 0.0000100000 | Loss 0.024332 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:15 Epoch 2 | Batch 1404/3508 | Timestep 8420 | LR 0.0000100000 | Loss 0.032074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:17 Epoch 2 | Batch 1414/3508 | Timestep 8430 | LR 0.0000100000 | Loss 0.018953 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:19 Epoch 2 | Batch 1424/3508 | Timestep 8440 | LR 0.0000100000 | Loss 0.082902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:21 Epoch 2 | Batch 1434/3508 | Timestep 8450 | LR 0.0000100000 | Loss 0.035997 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:23 Epoch 2 | Batch 1444/3508 | Timestep 8460 | LR 0.0000100000 | Loss 0.039334 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:25 Epoch 2 | Batch 1454/3508 | Timestep 8470 | LR 0.0000100000 | Loss 0.035637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:27 Epoch 2 | Batch 1464/3508 | Timestep 8480 | LR 0.0000100000 | Loss 0.071414 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:28 Epoch 2 | Batch 1474/3508 | Timestep 8490 | LR 0.0000100000 | Loss 0.060609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:30 Epoch 2 | Batch 1484/3508 | Timestep 8500 | LR 0.0000100000 | Loss 0.044242 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:32 Epoch 2 | Batch 1494/3508 | Timestep 8510 | LR 0.0000100000 | Loss 0.062825 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:34 Epoch 2 | Batch 1504/3508 | Timestep 8520 | LR 0.0000100000 | Loss 0.039593 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:36 Epoch 2 | Batch 1514/3508 | Timestep 8530 | LR 0.0000100000 | Loss 0.060250 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:38 Epoch 2 | Batch 1524/3508 | Timestep 8540 | LR 0.0000100000 | Loss 0.014747 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:41 Epoch 2 | Batch 1534/3508 | Timestep 8550 | LR 0.0000100000 | Loss 0.024887 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:42 Epoch 2 | Batch 1544/3508 | Timestep 8560 | LR 0.0000100000 | Loss 0.038623 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:44 Epoch 2 | Batch 1554/3508 | Timestep 8570 | LR 0.0000100000 | Loss 0.076727 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:47 Epoch 2 | Batch 1564/3508 | Timestep 8580 | LR 0.0000100000 | Loss 0.121168 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:49 Epoch 2 | Batch 1574/3508 | Timestep 8590 | LR 0.0000100000 | Loss 0.077296 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:51 Epoch 2 | Batch 1584/3508 | Timestep 8600 | LR 0.0000100000 | Loss 0.045197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:52 Epoch 2 | Batch 1594/3508 | Timestep 8610 | LR 0.0000100000 | Loss 0.029381 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:54 Epoch 2 | Batch 1604/3508 | Timestep 8620 | LR 0.0000100000 | Loss 0.088546 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:57 Epoch 2 | Batch 1614/3508 | Timestep 8630 | LR 0.0000100000 | Loss 0.017606 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:13:59 Epoch 2 | Batch 1624/3508 | Timestep 8640 | LR 0.0000100000 | Loss 0.041580 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:01 Epoch 2 | Batch 1634/3508 | Timestep 8650 | LR 0.0000100000 | Loss 0.015435 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:03 Epoch 2 | Batch 1644/3508 | Timestep 8660 | LR 0.0000100000 | Loss 0.048675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:05 Epoch 2 | Batch 1654/3508 | Timestep 8670 | LR 0.0000100000 | Loss 0.011484 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:07 Epoch 2 | Batch 1664/3508 | Timestep 8680 | LR 0.0000100000 | Loss 0.069571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:09 Epoch 2 | Batch 1674/3508 | Timestep 8690 | LR 0.0000100000 | Loss 0.048335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:11 Epoch 2 | Batch 1684/3508 | Timestep 8700 | LR 0.0000100000 | Loss 0.017456 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:13 Epoch 2 | Batch 1694/3508 | Timestep 8710 | LR 0.0000100000 | Loss 0.035753 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:15 Epoch 2 | Batch 1704/3508 | Timestep 8720 | LR 0.0000100000 | Loss 0.187861 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:18 Epoch 2 | Batch 1714/3508 | Timestep 8730 | LR 0.0000100000 | Loss 0.076387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:20 Epoch 2 | Batch 1724/3508 | Timestep 8740 | LR 0.0000100000 | Loss 0.050600 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:22 Epoch 2 | Batch 1734/3508 | Timestep 8750 | LR 0.0000100000 | Loss 0.041661 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:24 Epoch 2 | Batch 1744/3508 | Timestep 8760 | LR 0.0000100000 | Loss 0.006603 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:26 Epoch 2 | Batch 1754/3508 | Timestep 8770 | LR 0.0000100000 | Loss 0.075227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:28 Epoch 2 | Batch 1764/3508 | Timestep 8780 | LR 0.0000100000 | Loss 0.022356 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:30 Epoch 2 | Batch 1774/3508 | Timestep 8790 | LR 0.0000100000 | Loss 0.060826 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:32 Epoch 2 | Batch 1784/3508 | Timestep 8800 | LR 0.0000100000 | Loss 0.017544 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:34 Epoch 2 | Batch 1794/3508 | Timestep 8810 | LR 0.0000100000 | Loss 0.045744 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:36 Epoch 2 | Batch 1804/3508 | Timestep 8820 | LR 0.0000100000 | Loss 0.026141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:38 Epoch 2 | Batch 1814/3508 | Timestep 8830 | LR 0.0000100000 | Loss 0.095266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:40 Epoch 2 | Batch 1824/3508 | Timestep 8840 | LR 0.0000100000 | Loss 0.101324 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:43 Epoch 2 | Batch 1834/3508 | Timestep 8850 | LR 0.0000100000 | Loss 0.040080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:45 Epoch 2 | Batch 1844/3508 | Timestep 8860 | LR 0.0000100000 | Loss 0.070450 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:47 Epoch 2 | Batch 1854/3508 | Timestep 8870 | LR 0.0000100000 | Loss 0.050518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:49 Epoch 2 | Batch 1864/3508 | Timestep 8880 | LR 0.0000100000 | Loss 0.059147 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:52 Epoch 2 | Batch 1874/3508 | Timestep 8890 | LR 0.0000100000 | Loss 0.058404 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:54 Epoch 2 | Batch 1884/3508 | Timestep 8900 | LR 0.0000100000 | Loss 0.028524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:56 Epoch 2 | Batch 1894/3508 | Timestep 8910 | LR 0.0000100000 | Loss 0.031264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:14:58 Epoch 2 | Batch 1904/3508 | Timestep 8920 | LR 0.0000100000 | Loss 0.052575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:00 Epoch 2 | Batch 1914/3508 | Timestep 8930 | LR 0.0000100000 | Loss 0.067227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:01 Epoch 2 | Batch 1924/3508 | Timestep 8940 | LR 0.0000100000 | Loss 0.040743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:04 Epoch 2 | Batch 1934/3508 | Timestep 8950 | LR 0.0000100000 | Loss 0.040247 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:06 Epoch 2 | Batch 1944/3508 | Timestep 8960 | LR 0.0000100000 | Loss 0.013608 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:08 Epoch 2 | Batch 1954/3508 | Timestep 8970 | LR 0.0000100000 | Loss 0.038716 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:10 Epoch 2 | Batch 1964/3508 | Timestep 8980 | LR 0.0000100000 | Loss 0.032755 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:12 Epoch 2 | Batch 1974/3508 | Timestep 8990 | LR 0.0000100000 | Loss 0.062186 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:14 Epoch 2 | Batch 1984/3508 | Timestep 9000 | LR 0.0000100000 | Loss 0.048575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:17 Epoch 2 | Batch 1994/3508 | Timestep 9010 | LR 0.0000100000 | Loss 0.017863 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:19 Epoch 2 | Batch 2004/3508 | Timestep 9020 | LR 0.0000100000 | Loss 0.036894 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:22 Epoch 2 | Batch 2014/3508 | Timestep 9030 | LR 0.0000100000 | Loss 0.017962 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:24 Epoch 2 | Batch 2024/3508 | Timestep 9040 | LR 0.0000100000 | Loss 0.013987 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:26 Epoch 2 | Batch 2034/3508 | Timestep 9050 | LR 0.0000100000 | Loss 0.033006 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:28 Epoch 2 | Batch 2044/3508 | Timestep 9060 | LR 0.0000100000 | Loss 0.069224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:30 Epoch 2 | Batch 2054/3508 | Timestep 9070 | LR 0.0000100000 | Loss 0.037901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:33 Epoch 2 | Batch 2064/3508 | Timestep 9080 | LR 0.0000100000 | Loss 0.067849 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:35 Epoch 2 | Batch 2074/3508 | Timestep 9090 | LR 0.0000100000 | Loss 0.018034 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:37 Epoch 2 | Batch 2084/3508 | Timestep 9100 | LR 0.0000100000 | Loss 0.047815 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:39 Epoch 2 | Batch 2094/3508 | Timestep 9110 | LR 0.0000100000 | Loss 0.037608 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:41 Epoch 2 | Batch 2104/3508 | Timestep 9120 | LR 0.0000100000 | Loss 0.070577 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:43 Epoch 2 | Batch 2114/3508 | Timestep 9130 | LR 0.0000100000 | Loss 0.025115 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:46 Epoch 2 | Batch 2124/3508 | Timestep 9140 | LR 0.0000100000 | Loss 0.026365 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:48 Epoch 2 | Batch 2134/3508 | Timestep 9150 | LR 0.0000100000 | Loss 0.021111 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:50 Epoch 2 | Batch 2144/3508 | Timestep 9160 | LR 0.0000100000 | Loss 0.026428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:52 Epoch 2 | Batch 2154/3508 | Timestep 9170 | LR 0.0000100000 | Loss 0.018357 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:54 Epoch 2 | Batch 2164/3508 | Timestep 9180 | LR 0.0000100000 | Loss 0.024527 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:56 Epoch 2 | Batch 2174/3508 | Timestep 9190 | LR 0.0000100000 | Loss 0.006003 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:15:58 Epoch 2 | Batch 2184/3508 | Timestep 9200 | LR 0.0000100000 | Loss 0.013502 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:00 Epoch 2 | Batch 2194/3508 | Timestep 9210 | LR 0.0000100000 | Loss 0.022483 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:03 Epoch 2 | Batch 2204/3508 | Timestep 9220 | LR 0.0000100000 | Loss 0.061010 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:05 Epoch 2 | Batch 2214/3508 | Timestep 9230 | LR 0.0000100000 | Loss 0.021712 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:06 Epoch 2 | Batch 2224/3508 | Timestep 9240 | LR 0.0000100000 | Loss 0.025968 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:09 Epoch 2 | Batch 2234/3508 | Timestep 9250 | LR 0.0000100000 | Loss 0.043549 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:11 Epoch 2 | Batch 2244/3508 | Timestep 9260 | LR 0.0000100000 | Loss 0.023073 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:13 Epoch 2 | Batch 2254/3508 | Timestep 9270 | LR 0.0000100000 | Loss 0.014529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:14 Epoch 2 | Batch 2264/3508 | Timestep 9280 | LR 0.0000100000 | Loss 0.030014 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:17 Epoch 2 | Batch 2274/3508 | Timestep 9290 | LR 0.0000100000 | Loss 0.021929 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:18 Epoch 2 | Batch 2284/3508 | Timestep 9300 | LR 0.0000100000 | Loss 0.076588 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:21 Epoch 2 | Batch 2294/3508 | Timestep 9310 | LR 0.0000100000 | Loss 0.048380 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:22 Epoch 2 | Batch 2304/3508 | Timestep 9320 | LR 0.0000100000 | Loss 0.027443 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:24 Epoch 2 | Batch 2314/3508 | Timestep 9330 | LR 0.0000100000 | Loss 0.088481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:26 Epoch 2 | Batch 2324/3508 | Timestep 9340 | LR 0.0000100000 | Loss 0.043248 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:29 Epoch 2 | Batch 2334/3508 | Timestep 9350 | LR 0.0000100000 | Loss 0.033511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:31 Epoch 2 | Batch 2344/3508 | Timestep 9360 | LR 0.0000100000 | Loss 0.018895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:33 Epoch 2 | Batch 2354/3508 | Timestep 9370 | LR 0.0000100000 | Loss 0.038548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:35 Epoch 2 | Batch 2364/3508 | Timestep 9380 | LR 0.0000100000 | Loss 0.021256 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:37 Epoch 2 | Batch 2374/3508 | Timestep 9390 | LR 0.0000100000 | Loss 0.074025 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:39 Epoch 2 | Batch 2384/3508 | Timestep 9400 | LR 0.0000100000 | Loss 0.048960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:41 Epoch 2 | Batch 2394/3508 | Timestep 9410 | LR 0.0000100000 | Loss 0.044427 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:43 Epoch 2 | Batch 2404/3508 | Timestep 9420 | LR 0.0000100000 | Loss 0.020072 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:45 Epoch 2 | Batch 2414/3508 | Timestep 9430 | LR 0.0000100000 | Loss 0.077690 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:47 Epoch 2 | Batch 2424/3508 | Timestep 9440 | LR 0.0000100000 | Loss 0.081167 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:49 Epoch 2 | Batch 2434/3508 | Timestep 9450 | LR 0.0000100000 | Loss 0.018387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:51 Epoch 2 | Batch 2444/3508 | Timestep 9460 | LR 0.0000100000 | Loss 0.051933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:53 Epoch 2 | Batch 2454/3508 | Timestep 9470 | LR 0.0000100000 | Loss 0.029288 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:56 Epoch 2 | Batch 2464/3508 | Timestep 9480 | LR 0.0000100000 | Loss 0.043250 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:16:58 Epoch 2 | Batch 2474/3508 | Timestep 9490 | LR 0.0000100000 | Loss 0.064000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:00 Epoch 2 | Batch 2484/3508 | Timestep 9500 | LR 0.0000100000 | Loss 0.035925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:02 Epoch 2 | Batch 2494/3508 | Timestep 9510 | LR 0.0000100000 | Loss 0.033583 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:04 Epoch 2 | Batch 2504/3508 | Timestep 9520 | LR 0.0000100000 | Loss 0.061900 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:06 Epoch 2 | Batch 2514/3508 | Timestep 9530 | LR 0.0000100000 | Loss 0.075858 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:09 Epoch 2 | Batch 2524/3508 | Timestep 9540 | LR 0.0000100000 | Loss 0.066584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:11 Epoch 2 | Batch 2534/3508 | Timestep 9550 | LR 0.0000100000 | Loss 0.042385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:13 Epoch 2 | Batch 2544/3508 | Timestep 9560 | LR 0.0000100000 | Loss 0.033514 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:15 Epoch 2 | Batch 2554/3508 | Timestep 9570 | LR 0.0000100000 | Loss 0.052701 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:18 Epoch 2 | Batch 2564/3508 | Timestep 9580 | LR 0.0000100000 | Loss 0.018384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:20 Epoch 2 | Batch 2574/3508 | Timestep 9590 | LR 0.0000100000 | Loss 0.030675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:22 Epoch 2 | Batch 2584/3508 | Timestep 9600 | LR 0.0000100000 | Loss 0.035050 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:24 Epoch 2 | Batch 2594/3508 | Timestep 9610 | LR 0.0000100000 | Loss 0.031072 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:25 Epoch 2 | Batch 2604/3508 | Timestep 9620 | LR 0.0000100000 | Loss 0.073290 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:28 Epoch 2 | Batch 2614/3508 | Timestep 9630 | LR 0.0000100000 | Loss 0.029209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:30 Epoch 2 | Batch 2624/3508 | Timestep 9640 | LR 0.0000100000 | Loss 0.045184 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:31 Epoch 2 | Batch 2634/3508 | Timestep 9650 | LR 0.0000100000 | Loss 0.124466 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:34 Epoch 2 | Batch 2644/3508 | Timestep 9660 | LR 0.0000100000 | Loss 0.008718 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:36 Epoch 2 | Batch 2654/3508 | Timestep 9670 | LR 0.0000100000 | Loss 0.007557 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:39 Epoch 2 | Batch 2664/3508 | Timestep 9680 | LR 0.0000100000 | Loss 0.039068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:40 Epoch 2 | Batch 2674/3508 | Timestep 9690 | LR 0.0000100000 | Loss 0.016934 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:42 Epoch 2 | Batch 2684/3508 | Timestep 9700 | LR 0.0000100000 | Loss 0.021675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:44 Epoch 2 | Batch 2694/3508 | Timestep 9710 | LR 0.0000100000 | Loss 0.161043 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:47 Epoch 2 | Batch 2704/3508 | Timestep 9720 | LR 0.0000100000 | Loss 0.035124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:49 Epoch 2 | Batch 2714/3508 | Timestep 9730 | LR 0.0000100000 | Loss 0.034190 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:51 Epoch 2 | Batch 2724/3508 | Timestep 9740 | LR 0.0000100000 | Loss 0.038647 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:53 Epoch 2 | Batch 2734/3508 | Timestep 9750 | LR 0.0000100000 | Loss 0.036638 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:55 Epoch 2 | Batch 2744/3508 | Timestep 9760 | LR 0.0000100000 | Loss 0.026956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:17:58 Epoch 2 | Batch 2754/3508 | Timestep 9770 | LR 0.0000100000 | Loss 0.055755 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:01 Epoch 2 | Batch 2764/3508 | Timestep 9780 | LR 0.0000100000 | Loss 0.029481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:03 Epoch 2 | Batch 2774/3508 | Timestep 9790 | LR 0.0000100000 | Loss 0.050021 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:05 Epoch 2 | Batch 2784/3508 | Timestep 9800 | LR 0.0000100000 | Loss 0.011136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:07 Epoch 2 | Batch 2794/3508 | Timestep 9810 | LR 0.0000100000 | Loss 0.058826 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:09 Epoch 2 | Batch 2804/3508 | Timestep 9820 | LR 0.0000100000 | Loss 0.021029 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:11 Epoch 2 | Batch 2814/3508 | Timestep 9830 | LR 0.0000100000 | Loss 0.051577 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:13 Epoch 2 | Batch 2824/3508 | Timestep 9840 | LR 0.0000100000 | Loss 0.056346 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:15 Epoch 2 | Batch 2834/3508 | Timestep 9850 | LR 0.0000100000 | Loss 0.032951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:17 Epoch 2 | Batch 2844/3508 | Timestep 9860 | LR 0.0000100000 | Loss 0.018789 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:19 Epoch 2 | Batch 2854/3508 | Timestep 9870 | LR 0.0000100000 | Loss 0.029565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:22 Epoch 2 | Batch 2864/3508 | Timestep 9880 | LR 0.0000100000 | Loss 0.063128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:24 Epoch 2 | Batch 2874/3508 | Timestep 9890 | LR 0.0000100000 | Loss 0.025470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:26 Epoch 2 | Batch 2884/3508 | Timestep 9900 | LR 0.0000100000 | Loss 0.050341 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:28 Epoch 2 | Batch 2894/3508 | Timestep 9910 | LR 0.0000100000 | Loss 0.019540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:30 Epoch 2 | Batch 2904/3508 | Timestep 9920 | LR 0.0000100000 | Loss 0.032197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:32 Epoch 2 | Batch 2914/3508 | Timestep 9930 | LR 0.0000100000 | Loss 0.030487 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:35 Epoch 2 | Batch 2924/3508 | Timestep 9940 | LR 0.0000100000 | Loss 0.031018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:37 Epoch 2 | Batch 2934/3508 | Timestep 9950 | LR 0.0000100000 | Loss 0.028212 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:39 Epoch 2 | Batch 2944/3508 | Timestep 9960 | LR 0.0000100000 | Loss 0.036946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:41 Epoch 2 | Batch 2954/3508 | Timestep 9970 | LR 0.0000100000 | Loss 0.038301 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:44 Epoch 2 | Batch 2964/3508 | Timestep 9980 | LR 0.0000100000 | Loss 0.034722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:45 Epoch 2 | Batch 2974/3508 | Timestep 9990 | LR 0.0000100000 | Loss 0.037059 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:48 Epoch 2 | Batch 2984/3508 | Timestep 10000 | LR 0.0000100000 | Loss 0.045907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:50 Epoch 2 | Batch 2994/3508 | Timestep 10010 | LR 0.0000100000 | Loss 0.015440 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:52 Epoch 2 | Batch 3004/3508 | Timestep 10020 | LR 0.0000100000 | Loss 0.020541 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:54 Epoch 2 | Batch 3014/3508 | Timestep 10030 | LR 0.0000100000 | Loss 0.119357 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:56 Epoch 2 | Batch 3024/3508 | Timestep 10040 | LR 0.0000100000 | Loss 0.035790 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:18:59 Epoch 2 | Batch 3034/3508 | Timestep 10050 | LR 0.0000100000 | Loss 0.031132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:01 Epoch 2 | Batch 3044/3508 | Timestep 10060 | LR 0.0000100000 | Loss 0.019584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:03 Epoch 2 | Batch 3054/3508 | Timestep 10070 | LR 0.0000100000 | Loss 0.028923 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:05 Epoch 2 | Batch 3064/3508 | Timestep 10080 | LR 0.0000100000 | Loss 0.019121 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:07 Epoch 2 | Batch 3074/3508 | Timestep 10090 | LR 0.0000100000 | Loss 0.035452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:09 Epoch 2 | Batch 3084/3508 | Timestep 10100 | LR 0.0000100000 | Loss 0.026153 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:12 Epoch 2 | Batch 3094/3508 | Timestep 10110 | LR 0.0000100000 | Loss 0.033981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:14 Epoch 2 | Batch 3104/3508 | Timestep 10120 | LR 0.0000100000 | Loss 0.022166 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:15 Epoch 2 | Batch 3114/3508 | Timestep 10130 | LR 0.0000100000 | Loss 0.039263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:17 Epoch 2 | Batch 3124/3508 | Timestep 10140 | LR 0.0000100000 | Loss 0.028881 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:20 Epoch 2 | Batch 3134/3508 | Timestep 10150 | LR 0.0000100000 | Loss 0.021103 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:22 Epoch 2 | Batch 3144/3508 | Timestep 10160 | LR 0.0000100000 | Loss 0.034796 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:24 Epoch 2 | Batch 3154/3508 | Timestep 10170 | LR 0.0000100000 | Loss 0.022541 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:27 Epoch 2 | Batch 3164/3508 | Timestep 10180 | LR 0.0000100000 | Loss 0.009822 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:28 Epoch 2 | Batch 3174/3508 | Timestep 10190 | LR 0.0000100000 | Loss 0.041160 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:30 Epoch 2 | Batch 3184/3508 | Timestep 10200 | LR 0.0000100000 | Loss 0.039942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:33 Epoch 2 | Batch 3194/3508 | Timestep 10210 | LR 0.0000100000 | Loss 0.022822 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:35 Epoch 2 | Batch 3204/3508 | Timestep 10220 | LR 0.0000100000 | Loss 0.044182 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:37 Epoch 2 | Batch 3214/3508 | Timestep 10230 | LR 0.0000100000 | Loss 0.071231 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:39 Epoch 2 | Batch 3224/3508 | Timestep 10240 | LR 0.0000100000 | Loss 0.142343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:42 Epoch 2 | Batch 3234/3508 | Timestep 10250 | LR 0.0000100000 | Loss 0.010231 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:44 Epoch 2 | Batch 3244/3508 | Timestep 10260 | LR 0.0000100000 | Loss 0.020137 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:46 Epoch 2 | Batch 3254/3508 | Timestep 10270 | LR 0.0000100000 | Loss 0.030779 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:48 Epoch 2 | Batch 3264/3508 | Timestep 10280 | LR 0.0000100000 | Loss 0.035121 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:51 Epoch 2 | Batch 3274/3508 | Timestep 10290 | LR 0.0000100000 | Loss 0.044188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:53 Epoch 2 | Batch 3284/3508 | Timestep 10300 | LR 0.0000100000 | Loss 0.029749 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:55 Epoch 2 | Batch 3294/3508 | Timestep 10310 | LR 0.0000100000 | Loss 0.024146 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:57 Epoch 2 | Batch 3304/3508 | Timestep 10320 | LR 0.0000100000 | Loss 0.014742 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:19:59 Epoch 2 | Batch 3314/3508 | Timestep 10330 | LR 0.0000100000 | Loss 0.019578 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:01 Epoch 2 | Batch 3324/3508 | Timestep 10340 | LR 0.0000100000 | Loss 0.008264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:03 Epoch 2 | Batch 3334/3508 | Timestep 10350 | LR 0.0000100000 | Loss 0.053835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:06 Epoch 2 | Batch 3344/3508 | Timestep 10360 | LR 0.0000100000 | Loss 0.012320 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:08 Epoch 2 | Batch 3354/3508 | Timestep 10370 | LR 0.0000100000 | Loss 0.093875 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:10 Epoch 2 | Batch 3364/3508 | Timestep 10380 | LR 0.0000100000 | Loss 0.026637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:12 Epoch 2 | Batch 3374/3508 | Timestep 10390 | LR 0.0000100000 | Loss 0.026533 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:14 Epoch 2 | Batch 3384/3508 | Timestep 10400 | LR 0.0000100000 | Loss 0.087913 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:16 Epoch 2 | Batch 3394/3508 | Timestep 10410 | LR 0.0000100000 | Loss 0.015726 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:18 Epoch 2 | Batch 3404/3508 | Timestep 10420 | LR 0.0000100000 | Loss 0.017342 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:21 Epoch 2 | Batch 3414/3508 | Timestep 10430 | LR 0.0000100000 | Loss 0.029078 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:23 Epoch 2 | Batch 3424/3508 | Timestep 10440 | LR 0.0000100000 | Loss 0.035474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:25 Epoch 2 | Batch 3434/3508 | Timestep 10450 | LR 0.0000100000 | Loss 0.015382 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:27 Epoch 2 | Batch 3444/3508 | Timestep 10460 | LR 0.0000100000 | Loss 0.010062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:29 Epoch 2 | Batch 3454/3508 | Timestep 10470 | LR 0.0000100000 | Loss 0.029536 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:31 Epoch 2 | Batch 3464/3508 | Timestep 10480 | LR 0.0000100000 | Loss 0.151052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:34 Epoch 2 | Batch 3474/3508 | Timestep 10490 | LR 0.0000100000 | Loss 0.019727 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:36 Epoch 2 | Batch 3484/3508 | Timestep 10500 | LR 0.0000100000 | Loss 0.054846 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:38 Epoch 2 | Batch 3494/3508 | Timestep 10510 | LR 0.0000100000 | Loss 0.014841 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:40 Epoch 2 | Batch 3504/3508 | Timestep 10520 | LR 0.0000100000 | Loss 0.020208 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:20:41 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 15:21:14 precision recall f1-score support CARDINAL 0.8333 0.7862 0.8091 159 CURR 0.7391 0.7727 0.7556 22 DATE 0.9257 0.9335 0.9296 1669 EVENT 0.6134 0.7456 0.6730 283 FAC 0.5758 0.8051 0.6714 118 GPE 0.9590 0.9621 0.9606 2140 LANGUAGE 0.6667 0.6250 0.6452 16 LAW 0.3590 0.7368 0.4828 19 LOC 0.7442 0.7111 0.7273 90 MONEY 0.7083 0.8500 0.7727 20 NORP 0.6336 0.7407 0.6830 509 OCC 0.8171 0.8468 0.8317 496 ORDINAL 0.8861 0.9417 0.9130 446 ORG 0.8841 0.9400 0.9112 1866 PERCENT 0.8571 1.0000 0.9231 12 PERS 0.9243 0.9529 0.9384 679 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.2857 0.6667 0.4000 3 TIME 0.7333 0.7097 0.7213 31 UNIT 0.4286 0.7500 0.5455 4 WEBSITE 0.3776 0.4625 0.4157 80 micro avg 0.8640 0.9070 0.8850 8670 macro avg 0.6644 0.7590 0.7005 8670 weighted avg 0.8711 0.9070 0.8878 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:21:24 Epoch 2 | Timestep 10524 | Train Loss 0.044994 | Val Loss 0.053792 | F1 0.884988 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:21:24 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 25 Jun 2026 15:21:47 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Thu, 25 Jun 2026 15:22:03 Predictions written to /rep/nhamad/ArabicNER/B1/predictions.txt INFO root Thu, 25 Jun 2026 15:22:26 precision recall f1-score support CARDINAL 0.8383 0.8563 0.8472 327 CURR 0.5208 0.6579 0.5814 38 DATE 0.9386 0.9499 0.9442 3173 EVENT 0.6416 0.7782 0.7033 559 FAC 0.5915 0.7479 0.6606 242 GPE 0.9464 0.9585 0.9524 4311 LANGUAGE 0.8286 0.6591 0.7342 44 LAW 0.4130 0.6552 0.5067 29 LOC 0.7376 0.6835 0.7095 218 MONEY 0.7714 0.9000 0.8308 30 NORP 0.6369 0.7550 0.6910 992 OCC 0.8255 0.8319 0.8287 1035 ORDINAL 0.8891 0.9341 0.9111 850 ORG 0.8506 0.9262 0.8868 3738 PERCENT 0.9118 0.9688 0.9394 32 PERS 0.9080 0.9375 0.9225 1568 PRODUCT 0.2308 0.1579 0.1875 19 QUANTITY 0.2778 0.5556 0.3704 9 TIME 0.6957 0.6154 0.6531 78 UNIT 0.4286 0.8182 0.5625 11 WEBSITE 0.4218 0.5345 0.4715 116 micro avg 0.8596 0.9062 0.8823 17419 macro avg 0.6812 0.7563 0.7093 17419 weighted avg 0.8655 0.9062 0.8846 17419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:46 Epoch 2 | Timestep 10524 | Test Loss 0.056694 | F1 0.882263 INFO arabiner.trainers.BaseTrainer Thu, 25 Jun 2026 15:22:46 Saving checkpoint to /rep/nhamad/ArabicNER/B1/checkpoints/checkpoint_2.pt INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:50 Epoch 3 | Batch 6/3508 | Timestep 10530 | LR 0.0000100000 | Loss 0.014942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:53 Epoch 3 | Batch 16/3508 | Timestep 10540 | LR 0.0000100000 | Loss 0.026783 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:54 Epoch 3 | Batch 26/3508 | Timestep 10550 | LR 0.0000100000 | Loss 0.028870 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:56 Epoch 3 | Batch 36/3508 | Timestep 10560 | LR 0.0000100000 | Loss 0.011601 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:22:58 Epoch 3 | Batch 46/3508 | Timestep 10570 | LR 0.0000100000 | Loss 0.062283 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:01 Epoch 3 | Batch 56/3508 | Timestep 10580 | LR 0.0000100000 | Loss 0.021183 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:03 Epoch 3 | Batch 66/3508 | Timestep 10590 | LR 0.0000100000 | Loss 0.018018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:05 Epoch 3 | Batch 76/3508 | Timestep 10600 | LR 0.0000100000 | Loss 0.086803 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:07 Epoch 3 | Batch 86/3508 | Timestep 10610 | LR 0.0000100000 | Loss 0.046017 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:09 Epoch 3 | Batch 96/3508 | Timestep 10620 | LR 0.0000100000 | Loss 0.024037 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:11 Epoch 3 | Batch 106/3508 | Timestep 10630 | LR 0.0000100000 | Loss 0.025442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:13 Epoch 3 | Batch 116/3508 | Timestep 10640 | LR 0.0000100000 | Loss 0.058697 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:15 Epoch 3 | Batch 126/3508 | Timestep 10650 | LR 0.0000100000 | Loss 0.036472 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:17 Epoch 3 | Batch 136/3508 | Timestep 10660 | LR 0.0000100000 | Loss 0.016295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:20 Epoch 3 | Batch 146/3508 | Timestep 10670 | LR 0.0000100000 | Loss 0.037332 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:23 Epoch 3 | Batch 156/3508 | Timestep 10680 | LR 0.0000100000 | Loss 0.042124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:25 Epoch 3 | Batch 166/3508 | Timestep 10690 | LR 0.0000100000 | Loss 0.040857 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:26 Epoch 3 | Batch 176/3508 | Timestep 10700 | LR 0.0000100000 | Loss 0.070705 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:29 Epoch 3 | Batch 186/3508 | Timestep 10710 | LR 0.0000100000 | Loss 0.081772 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:31 Epoch 3 | Batch 196/3508 | Timestep 10720 | LR 0.0000100000 | Loss 0.073113 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:33 Epoch 3 | Batch 206/3508 | Timestep 10730 | LR 0.0000100000 | Loss 0.027053 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:36 Epoch 3 | Batch 216/3508 | Timestep 10740 | LR 0.0000100000 | Loss 0.045500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:38 Epoch 3 | Batch 226/3508 | Timestep 10750 | LR 0.0000100000 | Loss 0.020597 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:40 Epoch 3 | Batch 236/3508 | Timestep 10760 | LR 0.0000100000 | Loss 0.031513 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:43 Epoch 3 | Batch 246/3508 | Timestep 10770 | LR 0.0000100000 | Loss 0.041176 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:45 Epoch 3 | Batch 256/3508 | Timestep 10780 | LR 0.0000100000 | Loss 0.073470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:48 Epoch 3 | Batch 266/3508 | Timestep 10790 | LR 0.0000100000 | Loss 0.026532 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:50 Epoch 3 | Batch 276/3508 | Timestep 10800 | LR 0.0000100000 | Loss 0.037310 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:52 Epoch 3 | Batch 286/3508 | Timestep 10810 | LR 0.0000100000 | Loss 0.063462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:54 Epoch 3 | Batch 296/3508 | Timestep 10820 | LR 0.0000100000 | Loss 0.033141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:56 Epoch 3 | Batch 306/3508 | Timestep 10830 | LR 0.0000100000 | Loss 0.011328 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:23:58 Epoch 3 | Batch 316/3508 | Timestep 10840 | LR 0.0000100000 | Loss 0.016481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:00 Epoch 3 | Batch 326/3508 | Timestep 10850 | LR 0.0000100000 | Loss 0.024784 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:02 Epoch 3 | Batch 336/3508 | Timestep 10860 | LR 0.0000100000 | Loss 0.029314 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:03 Epoch 3 | Batch 346/3508 | Timestep 10870 | LR 0.0000100000 | Loss 0.034516 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:06 Epoch 3 | Batch 356/3508 | Timestep 10880 | LR 0.0000100000 | Loss 0.045200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:08 Epoch 3 | Batch 366/3508 | Timestep 10890 | LR 0.0000100000 | Loss 0.022086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:10 Epoch 3 | Batch 376/3508 | Timestep 10900 | LR 0.0000100000 | Loss 0.074602 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:13 Epoch 3 | Batch 386/3508 | Timestep 10910 | LR 0.0000100000 | Loss 0.004778 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:15 Epoch 3 | Batch 396/3508 | Timestep 10920 | LR 0.0000100000 | Loss 0.074727 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:17 Epoch 3 | Batch 406/3508 | Timestep 10930 | LR 0.0000100000 | Loss 0.059622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:19 Epoch 3 | Batch 416/3508 | Timestep 10940 | LR 0.0000100000 | Loss 0.041954 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:21 Epoch 3 | Batch 426/3508 | Timestep 10950 | LR 0.0000100000 | Loss 0.025571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:24 Epoch 3 | Batch 436/3508 | Timestep 10960 | LR 0.0000100000 | Loss 0.016230 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:26 Epoch 3 | Batch 446/3508 | Timestep 10970 | LR 0.0000100000 | Loss 0.074154 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:28 Epoch 3 | Batch 456/3508 | Timestep 10980 | LR 0.0000100000 | Loss 0.047191 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:31 Epoch 3 | Batch 466/3508 | Timestep 10990 | LR 0.0000100000 | Loss 0.017601 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:33 Epoch 3 | Batch 476/3508 | Timestep 11000 | LR 0.0000100000 | Loss 0.030498 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:34 Epoch 3 | Batch 486/3508 | Timestep 11010 | LR 0.0000100000 | Loss 0.014926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:36 Epoch 3 | Batch 496/3508 | Timestep 11020 | LR 0.0000100000 | Loss 0.058706 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:39 Epoch 3 | Batch 506/3508 | Timestep 11030 | LR 0.0000100000 | Loss 0.021933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:41 Epoch 3 | Batch 516/3508 | Timestep 11040 | LR 0.0000100000 | Loss 0.017176 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:43 Epoch 3 | Batch 526/3508 | Timestep 11050 | LR 0.0000100000 | Loss 0.073999 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:45 Epoch 3 | Batch 536/3508 | Timestep 11060 | LR 0.0000100000 | Loss 0.044321 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:48 Epoch 3 | Batch 546/3508 | Timestep 11070 | LR 0.0000100000 | Loss 0.044986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:50 Epoch 3 | Batch 556/3508 | Timestep 11080 | LR 0.0000100000 | Loss 0.059012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:52 Epoch 3 | Batch 566/3508 | Timestep 11090 | LR 0.0000100000 | Loss 0.045459 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:54 Epoch 3 | Batch 576/3508 | Timestep 11100 | LR 0.0000100000 | Loss 0.027587 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:56 Epoch 3 | Batch 586/3508 | Timestep 11110 | LR 0.0000100000 | Loss 0.041627 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:24:59 Epoch 3 | Batch 596/3508 | Timestep 11120 | LR 0.0000100000 | Loss 0.062333 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:01 Epoch 3 | Batch 606/3508 | Timestep 11130 | LR 0.0000100000 | Loss 0.023395 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:03 Epoch 3 | Batch 616/3508 | Timestep 11140 | LR 0.0000100000 | Loss 0.014347 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:06 Epoch 3 | Batch 626/3508 | Timestep 11150 | LR 0.0000100000 | Loss 0.024974 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:08 Epoch 3 | Batch 636/3508 | Timestep 11160 | LR 0.0000100000 | Loss 0.049228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:10 Epoch 3 | Batch 646/3508 | Timestep 11170 | LR 0.0000100000 | Loss 0.033179 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:12 Epoch 3 | Batch 656/3508 | Timestep 11180 | LR 0.0000100000 | Loss 0.070085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:15 Epoch 3 | Batch 666/3508 | Timestep 11190 | LR 0.0000100000 | Loss 0.013810 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:17 Epoch 3 | Batch 676/3508 | Timestep 11200 | LR 0.0000100000 | Loss 0.073678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:19 Epoch 3 | Batch 686/3508 | Timestep 11210 | LR 0.0000100000 | Loss 0.011740 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:21 Epoch 3 | Batch 696/3508 | Timestep 11220 | LR 0.0000100000 | Loss 0.045682 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:23 Epoch 3 | Batch 706/3508 | Timestep 11230 | LR 0.0000100000 | Loss 0.142139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:25 Epoch 3 | Batch 716/3508 | Timestep 11240 | LR 0.0000100000 | Loss 0.047468 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:27 Epoch 3 | Batch 726/3508 | Timestep 11250 | LR 0.0000100000 | Loss 0.021491 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:30 Epoch 3 | Batch 736/3508 | Timestep 11260 | LR 0.0000100000 | Loss 0.034069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:32 Epoch 3 | Batch 746/3508 | Timestep 11270 | LR 0.0000100000 | Loss 0.030903 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:34 Epoch 3 | Batch 756/3508 | Timestep 11280 | LR 0.0000100000 | Loss 0.013086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:36 Epoch 3 | Batch 766/3508 | Timestep 11290 | LR 0.0000100000 | Loss 0.039271 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:39 Epoch 3 | Batch 776/3508 | Timestep 11300 | LR 0.0000100000 | Loss 0.028156 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:41 Epoch 3 | Batch 786/3508 | Timestep 11310 | LR 0.0000100000 | Loss 0.009932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:43 Epoch 3 | Batch 796/3508 | Timestep 11320 | LR 0.0000100000 | Loss 0.025143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:45 Epoch 3 | Batch 806/3508 | Timestep 11330 | LR 0.0000100000 | Loss 0.074008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:47 Epoch 3 | Batch 816/3508 | Timestep 11340 | LR 0.0000100000 | Loss 0.008299 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:49 Epoch 3 | Batch 826/3508 | Timestep 11350 | LR 0.0000100000 | Loss 0.013433 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:51 Epoch 3 | Batch 836/3508 | Timestep 11360 | LR 0.0000100000 | Loss 0.015551 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:53 Epoch 3 | Batch 846/3508 | Timestep 11370 | LR 0.0000100000 | Loss 0.016782 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:56 Epoch 3 | Batch 856/3508 | Timestep 11380 | LR 0.0000100000 | Loss 0.010473 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:25:58 Epoch 3 | Batch 866/3508 | Timestep 11390 | LR 0.0000100000 | Loss 0.007893 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:00 Epoch 3 | Batch 876/3508 | Timestep 11400 | LR 0.0000100000 | Loss 0.039266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:02 Epoch 3 | Batch 886/3508 | Timestep 11410 | LR 0.0000100000 | Loss 0.023305 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:04 Epoch 3 | Batch 896/3508 | Timestep 11420 | LR 0.0000100000 | Loss 0.033886 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:06 Epoch 3 | Batch 906/3508 | Timestep 11430 | LR 0.0000100000 | Loss 0.042544 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:08 Epoch 3 | Batch 916/3508 | Timestep 11440 | LR 0.0000100000 | Loss 0.016562 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:10 Epoch 3 | Batch 926/3508 | Timestep 11450 | LR 0.0000100000 | Loss 0.035782 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:12 Epoch 3 | Batch 936/3508 | Timestep 11460 | LR 0.0000100000 | Loss 0.023244 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:14 Epoch 3 | Batch 946/3508 | Timestep 11470 | LR 0.0000100000 | Loss 0.024203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:16 Epoch 3 | Batch 956/3508 | Timestep 11480 | LR 0.0000100000 | Loss 0.074743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:18 Epoch 3 | Batch 966/3508 | Timestep 11490 | LR 0.0000100000 | Loss 0.053341 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:21 Epoch 3 | Batch 976/3508 | Timestep 11500 | LR 0.0000100000 | Loss 0.008558 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:23 Epoch 3 | Batch 986/3508 | Timestep 11510 | LR 0.0000100000 | Loss 0.084723 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:24 Epoch 3 | Batch 996/3508 | Timestep 11520 | LR 0.0000100000 | Loss 0.037877 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:26 Epoch 3 | Batch 1006/3508 | Timestep 11530 | LR 0.0000100000 | Loss 0.040327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:29 Epoch 3 | Batch 1016/3508 | Timestep 11540 | LR 0.0000100000 | Loss 0.015526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:30 Epoch 3 | Batch 1026/3508 | Timestep 11550 | LR 0.0000100000 | Loss 0.018445 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:33 Epoch 3 | Batch 1036/3508 | Timestep 11560 | LR 0.0000100000 | Loss 0.046671 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:35 Epoch 3 | Batch 1046/3508 | Timestep 11570 | LR 0.0000100000 | Loss 0.065128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:37 Epoch 3 | Batch 1056/3508 | Timestep 11580 | LR 0.0000100000 | Loss 0.008426 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:40 Epoch 3 | Batch 1066/3508 | Timestep 11590 | LR 0.0000100000 | Loss 0.007497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:42 Epoch 3 | Batch 1076/3508 | Timestep 11600 | LR 0.0000100000 | Loss 0.023639 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:44 Epoch 3 | Batch 1086/3508 | Timestep 11610 | LR 0.0000100000 | Loss 0.017552 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:46 Epoch 3 | Batch 1096/3508 | Timestep 11620 | LR 0.0000100000 | Loss 0.018674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:48 Epoch 3 | Batch 1106/3508 | Timestep 11630 | LR 0.0000100000 | Loss 0.035069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:50 Epoch 3 | Batch 1116/3508 | Timestep 11640 | LR 0.0000100000 | Loss 0.026767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:52 Epoch 3 | Batch 1126/3508 | Timestep 11650 | LR 0.0000100000 | Loss 0.020773 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:54 Epoch 3 | Batch 1136/3508 | Timestep 11660 | LR 0.0000100000 | Loss 0.019359 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:56 Epoch 3 | Batch 1146/3508 | Timestep 11670 | LR 0.0000100000 | Loss 0.053555 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:26:58 Epoch 3 | Batch 1156/3508 | Timestep 11680 | LR 0.0000100000 | Loss 0.024604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:01 Epoch 3 | Batch 1166/3508 | Timestep 11690 | LR 0.0000100000 | Loss 0.018832 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:03 Epoch 3 | Batch 1176/3508 | Timestep 11700 | LR 0.0000100000 | Loss 0.023485 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:05 Epoch 3 | Batch 1186/3508 | Timestep 11710 | LR 0.0000100000 | Loss 0.044259 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:08 Epoch 3 | Batch 1196/3508 | Timestep 11720 | LR 0.0000100000 | Loss 0.008252 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:10 Epoch 3 | Batch 1206/3508 | Timestep 11730 | LR 0.0000100000 | Loss 0.025162 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:12 Epoch 3 | Batch 1216/3508 | Timestep 11740 | LR 0.0000100000 | Loss 0.054529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:14 Epoch 3 | Batch 1226/3508 | Timestep 11750 | LR 0.0000100000 | Loss 0.083966 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:16 Epoch 3 | Batch 1236/3508 | Timestep 11760 | LR 0.0000100000 | Loss 0.024919 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:18 Epoch 3 | Batch 1246/3508 | Timestep 11770 | LR 0.0000100000 | Loss 0.039135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:20 Epoch 3 | Batch 1256/3508 | Timestep 11780 | LR 0.0000100000 | Loss 0.013180 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:22 Epoch 3 | Batch 1266/3508 | Timestep 11790 | LR 0.0000100000 | Loss 0.044362 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:24 Epoch 3 | Batch 1276/3508 | Timestep 11800 | LR 0.0000100000 | Loss 0.030743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:26 Epoch 3 | Batch 1286/3508 | Timestep 11810 | LR 0.0000100000 | Loss 0.022729 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:28 Epoch 3 | Batch 1296/3508 | Timestep 11820 | LR 0.0000100000 | Loss 0.065749 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:30 Epoch 3 | Batch 1306/3508 | Timestep 11830 | LR 0.0000100000 | Loss 0.069061 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:32 Epoch 3 | Batch 1316/3508 | Timestep 11840 | LR 0.0000100000 | Loss 0.021510 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:34 Epoch 3 | Batch 1326/3508 | Timestep 11850 | LR 0.0000100000 | Loss 0.141295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:36 Epoch 3 | Batch 1336/3508 | Timestep 11860 | LR 0.0000100000 | Loss 0.008302 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:38 Epoch 3 | Batch 1346/3508 | Timestep 11870 | LR 0.0000100000 | Loss 0.031079 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:41 Epoch 3 | Batch 1356/3508 | Timestep 11880 | LR 0.0000100000 | Loss 0.016605 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:43 Epoch 3 | Batch 1366/3508 | Timestep 11890 | LR 0.0000100000 | Loss 0.051509 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:45 Epoch 3 | Batch 1376/3508 | Timestep 11900 | LR 0.0000100000 | Loss 0.020052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:48 Epoch 3 | Batch 1386/3508 | Timestep 11910 | LR 0.0000100000 | Loss 0.026856 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:50 Epoch 3 | Batch 1396/3508 | Timestep 11920 | LR 0.0000100000 | Loss 0.016631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:52 Epoch 3 | Batch 1406/3508 | Timestep 11930 | LR 0.0000100000 | Loss 0.006509 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:54 Epoch 3 | Batch 1416/3508 | Timestep 11940 | LR 0.0000100000 | Loss 0.012192 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:56 Epoch 3 | Batch 1426/3508 | Timestep 11950 | LR 0.0000100000 | Loss 0.056573 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:27:58 Epoch 3 | Batch 1436/3508 | Timestep 11960 | LR 0.0000100000 | Loss 0.029303 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:00 Epoch 3 | Batch 1446/3508 | Timestep 11970 | LR 0.0000100000 | Loss 0.026678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:02 Epoch 3 | Batch 1456/3508 | Timestep 11980 | LR 0.0000100000 | Loss 0.007240 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:04 Epoch 3 | Batch 1466/3508 | Timestep 11990 | LR 0.0000100000 | Loss 0.008507 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:06 Epoch 3 | Batch 1476/3508 | Timestep 12000 | LR 0.0000100000 | Loss 0.016358 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:09 Epoch 3 | Batch 1486/3508 | Timestep 12010 | LR 0.0000100000 | Loss 0.055565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:11 Epoch 3 | Batch 1496/3508 | Timestep 12020 | LR 0.0000100000 | Loss 0.031942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:12 Epoch 3 | Batch 1506/3508 | Timestep 12030 | LR 0.0000100000 | Loss 0.064179 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:14 Epoch 3 | Batch 1516/3508 | Timestep 12040 | LR 0.0000100000 | Loss 0.024058 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:16 Epoch 3 | Batch 1526/3508 | Timestep 12050 | LR 0.0000100000 | Loss 0.047958 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:18 Epoch 3 | Batch 1536/3508 | Timestep 12060 | LR 0.0000100000 | Loss 0.009459 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:21 Epoch 3 | Batch 1546/3508 | Timestep 12070 | LR 0.0000100000 | Loss 0.027546 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:23 Epoch 3 | Batch 1556/3508 | Timestep 12080 | LR 0.0000100000 | Loss 0.020590 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:25 Epoch 3 | Batch 1566/3508 | Timestep 12090 | LR 0.0000100000 | Loss 0.046117 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:27 Epoch 3 | Batch 1576/3508 | Timestep 12100 | LR 0.0000100000 | Loss 0.029386 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:28 Epoch 3 | Batch 1586/3508 | Timestep 12110 | LR 0.0000100000 | Loss 0.025119 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:31 Epoch 3 | Batch 1596/3508 | Timestep 12120 | LR 0.0000100000 | Loss 0.005443 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:33 Epoch 3 | Batch 1606/3508 | Timestep 12130 | LR 0.0000100000 | Loss 0.011791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:35 Epoch 3 | Batch 1616/3508 | Timestep 12140 | LR 0.0000100000 | Loss 0.021595 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:37 Epoch 3 | Batch 1626/3508 | Timestep 12150 | LR 0.0000100000 | Loss 0.023872 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:40 Epoch 3 | Batch 1636/3508 | Timestep 12160 | LR 0.0000100000 | Loss 0.017663 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:42 Epoch 3 | Batch 1646/3508 | Timestep 12170 | LR 0.0000100000 | Loss 0.055700 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:44 Epoch 3 | Batch 1656/3508 | Timestep 12180 | LR 0.0000100000 | Loss 0.032067 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:46 Epoch 3 | Batch 1666/3508 | Timestep 12190 | LR 0.0000100000 | Loss 0.007951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:48 Epoch 3 | Batch 1676/3508 | Timestep 12200 | LR 0.0000100000 | Loss 0.016511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:51 Epoch 3 | Batch 1686/3508 | Timestep 12210 | LR 0.0000100000 | Loss 0.094196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:53 Epoch 3 | Batch 1696/3508 | Timestep 12220 | LR 0.0000100000 | Loss 0.023658 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:55 Epoch 3 | Batch 1706/3508 | Timestep 12230 | LR 0.0000100000 | Loss 0.008134 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:57 Epoch 3 | Batch 1716/3508 | Timestep 12240 | LR 0.0000100000 | Loss 0.010880 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:28:59 Epoch 3 | Batch 1726/3508 | Timestep 12250 | LR 0.0000100000 | Loss 0.009097 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:01 Epoch 3 | Batch 1736/3508 | Timestep 12260 | LR 0.0000100000 | Loss 0.018691 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:03 Epoch 3 | Batch 1746/3508 | Timestep 12270 | LR 0.0000100000 | Loss 0.027436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:06 Epoch 3 | Batch 1756/3508 | Timestep 12280 | LR 0.0000100000 | Loss 0.023548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:07 Epoch 3 | Batch 1766/3508 | Timestep 12290 | LR 0.0000100000 | Loss 0.036188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:10 Epoch 3 | Batch 1776/3508 | Timestep 12300 | LR 0.0000100000 | Loss 0.006326 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:12 Epoch 3 | Batch 1786/3508 | Timestep 12310 | LR 0.0000100000 | Loss 0.059315 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:14 Epoch 3 | Batch 1796/3508 | Timestep 12320 | LR 0.0000100000 | Loss 0.027506 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:16 Epoch 3 | Batch 1806/3508 | Timestep 12330 | LR 0.0000100000 | Loss 0.056410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:19 Epoch 3 | Batch 1816/3508 | Timestep 12340 | LR 0.0000100000 | Loss 0.032773 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:21 Epoch 3 | Batch 1826/3508 | Timestep 12350 | LR 0.0000100000 | Loss 0.013708 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:23 Epoch 3 | Batch 1836/3508 | Timestep 12360 | LR 0.0000100000 | Loss 0.012511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:25 Epoch 3 | Batch 1846/3508 | Timestep 12370 | LR 0.0000100000 | Loss 0.030804 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:27 Epoch 3 | Batch 1856/3508 | Timestep 12380 | LR 0.0000100000 | Loss 0.015960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:29 Epoch 3 | Batch 1866/3508 | Timestep 12390 | LR 0.0000100000 | Loss 0.023765 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:31 Epoch 3 | Batch 1876/3508 | Timestep 12400 | LR 0.0000100000 | Loss 0.017450 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:33 Epoch 3 | Batch 1886/3508 | Timestep 12410 | LR 0.0000100000 | Loss 0.017888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:35 Epoch 3 | Batch 1896/3508 | Timestep 12420 | LR 0.0000100000 | Loss 0.035239 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:37 Epoch 3 | Batch 1906/3508 | Timestep 12430 | LR 0.0000100000 | Loss 0.037005 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:39 Epoch 3 | Batch 1916/3508 | Timestep 12440 | LR 0.0000100000 | Loss 0.018172 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:41 Epoch 3 | Batch 1926/3508 | Timestep 12450 | LR 0.0000100000 | Loss 0.007374 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:43 Epoch 3 | Batch 1936/3508 | Timestep 12460 | LR 0.0000100000 | Loss 0.002784 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:45 Epoch 3 | Batch 1946/3508 | Timestep 12470 | LR 0.0000100000 | Loss 0.018525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:48 Epoch 3 | Batch 1956/3508 | Timestep 12480 | LR 0.0000100000 | Loss 0.009282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:49 Epoch 3 | Batch 1966/3508 | Timestep 12490 | LR 0.0000100000 | Loss 0.051427 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:52 Epoch 3 | Batch 1976/3508 | Timestep 12500 | LR 0.0000100000 | Loss 0.033225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:54 Epoch 3 | Batch 1986/3508 | Timestep 12510 | LR 0.0000100000 | Loss 0.011500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:56 Epoch 3 | Batch 1996/3508 | Timestep 12520 | LR 0.0000100000 | Loss 0.044491 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:29:58 Epoch 3 | Batch 2006/3508 | Timestep 12530 | LR 0.0000100000 | Loss 0.034837 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:00 Epoch 3 | Batch 2016/3508 | Timestep 12540 | LR 0.0000100000 | Loss 0.023852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:02 Epoch 3 | Batch 2026/3508 | Timestep 12550 | LR 0.0000100000 | Loss 0.084912 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:05 Epoch 3 | Batch 2036/3508 | Timestep 12560 | LR 0.0000100000 | Loss 0.042985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:07 Epoch 3 | Batch 2046/3508 | Timestep 12570 | LR 0.0000100000 | Loss 0.028415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:09 Epoch 3 | Batch 2056/3508 | Timestep 12580 | LR 0.0000100000 | Loss 0.025180 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:11 Epoch 3 | Batch 2066/3508 | Timestep 12590 | LR 0.0000100000 | Loss 0.043173 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:13 Epoch 3 | Batch 2076/3508 | Timestep 12600 | LR 0.0000100000 | Loss 0.048904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:15 Epoch 3 | Batch 2086/3508 | Timestep 12610 | LR 0.0000100000 | Loss 0.010259 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:17 Epoch 3 | Batch 2096/3508 | Timestep 12620 | LR 0.0000100000 | Loss 0.039210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:19 Epoch 3 | Batch 2106/3508 | Timestep 12630 | LR 0.0000100000 | Loss 0.024024 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:21 Epoch 3 | Batch 2116/3508 | Timestep 12640 | LR 0.0000100000 | Loss 0.012494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:24 Epoch 3 | Batch 2126/3508 | Timestep 12650 | LR 0.0000100000 | Loss 0.030057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:25 Epoch 3 | Batch 2136/3508 | Timestep 12660 | LR 0.0000100000 | Loss 0.049869 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:27 Epoch 3 | Batch 2146/3508 | Timestep 12670 | LR 0.0000100000 | Loss 0.005560 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:29 Epoch 3 | Batch 2156/3508 | Timestep 12680 | LR 0.0000100000 | Loss 0.028875 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:31 Epoch 3 | Batch 2166/3508 | Timestep 12690 | LR 0.0000100000 | Loss 0.022494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:34 Epoch 3 | Batch 2176/3508 | Timestep 12700 | LR 0.0000100000 | Loss 0.006833 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:36 Epoch 3 | Batch 2186/3508 | Timestep 12710 | LR 0.0000100000 | Loss 0.056986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:38 Epoch 3 | Batch 2196/3508 | Timestep 12720 | LR 0.0000100000 | Loss 0.015142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:40 Epoch 3 | Batch 2206/3508 | Timestep 12730 | LR 0.0000100000 | Loss 0.046277 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:43 Epoch 3 | Batch 2216/3508 | Timestep 12740 | LR 0.0000100000 | Loss 0.034252 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:45 Epoch 3 | Batch 2226/3508 | Timestep 12750 | LR 0.0000100000 | Loss 0.011563 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:48 Epoch 3 | Batch 2236/3508 | Timestep 12760 | LR 0.0000100000 | Loss 0.029569 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:50 Epoch 3 | Batch 2246/3508 | Timestep 12770 | LR 0.0000100000 | Loss 0.015039 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:52 Epoch 3 | Batch 2256/3508 | Timestep 12780 | LR 0.0000100000 | Loss 0.075357 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:54 Epoch 3 | Batch 2266/3508 | Timestep 12790 | LR 0.0000100000 | Loss 0.004047 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:57 Epoch 3 | Batch 2276/3508 | Timestep 12800 | LR 0.0000100000 | Loss 0.012220 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:30:59 Epoch 3 | Batch 2286/3508 | Timestep 12810 | LR 0.0000100000 | Loss 0.024141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:00 Epoch 3 | Batch 2296/3508 | Timestep 12820 | LR 0.0000100000 | Loss 0.061575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:02 Epoch 3 | Batch 2306/3508 | Timestep 12830 | LR 0.0000100000 | Loss 0.063905 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:04 Epoch 3 | Batch 2316/3508 | Timestep 12840 | LR 0.0000100000 | Loss 0.010667 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:07 Epoch 3 | Batch 2326/3508 | Timestep 12850 | LR 0.0000100000 | Loss 0.005158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:08 Epoch 3 | Batch 2336/3508 | Timestep 12860 | LR 0.0000100000 | Loss 0.021361 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:11 Epoch 3 | Batch 2346/3508 | Timestep 12870 | LR 0.0000100000 | Loss 0.045711 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:13 Epoch 3 | Batch 2356/3508 | Timestep 12880 | LR 0.0000100000 | Loss 0.018625 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:14 Epoch 3 | Batch 2366/3508 | Timestep 12890 | LR 0.0000100000 | Loss 0.049772 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:16 Epoch 3 | Batch 2376/3508 | Timestep 12900 | LR 0.0000100000 | Loss 0.014703 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:19 Epoch 3 | Batch 2386/3508 | Timestep 12910 | LR 0.0000100000 | Loss 0.005268 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:21 Epoch 3 | Batch 2396/3508 | Timestep 12920 | LR 0.0000100000 | Loss 0.026012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:23 Epoch 3 | Batch 2406/3508 | Timestep 12930 | LR 0.0000100000 | Loss 0.019706 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:25 Epoch 3 | Batch 2416/3508 | Timestep 12940 | LR 0.0000100000 | Loss 0.029473 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:28 Epoch 3 | Batch 2426/3508 | Timestep 12950 | LR 0.0000100000 | Loss 0.055727 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:30 Epoch 3 | Batch 2436/3508 | Timestep 12960 | LR 0.0000100000 | Loss 0.037892 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:32 Epoch 3 | Batch 2446/3508 | Timestep 12970 | LR 0.0000100000 | Loss 0.011351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:34 Epoch 3 | Batch 2456/3508 | Timestep 12980 | LR 0.0000100000 | Loss 0.012428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:36 Epoch 3 | Batch 2466/3508 | Timestep 12990 | LR 0.0000100000 | Loss 0.013074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:38 Epoch 3 | Batch 2476/3508 | Timestep 13000 | LR 0.0000100000 | Loss 0.052741 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:40 Epoch 3 | Batch 2486/3508 | Timestep 13010 | LR 0.0000100000 | Loss 0.032571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:42 Epoch 3 | Batch 2496/3508 | Timestep 13020 | LR 0.0000100000 | Loss 0.026699 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:45 Epoch 3 | Batch 2506/3508 | Timestep 13030 | LR 0.0000100000 | Loss 0.058291 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:47 Epoch 3 | Batch 2516/3508 | Timestep 13040 | LR 0.0000100000 | Loss 0.025377 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:50 Epoch 3 | Batch 2526/3508 | Timestep 13050 | LR 0.0000100000 | Loss 0.049037 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:52 Epoch 3 | Batch 2536/3508 | Timestep 13060 | LR 0.0000100000 | Loss 0.006207 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:54 Epoch 3 | Batch 2546/3508 | Timestep 13070 | LR 0.0000100000 | Loss 0.059130 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:56 Epoch 3 | Batch 2556/3508 | Timestep 13080 | LR 0.0000100000 | Loss 0.012106 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:31:58 Epoch 3 | Batch 2566/3508 | Timestep 13090 | LR 0.0000100000 | Loss 0.015591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:00 Epoch 3 | Batch 2576/3508 | Timestep 13100 | LR 0.0000100000 | Loss 0.009413 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:02 Epoch 3 | Batch 2586/3508 | Timestep 13110 | LR 0.0000100000 | Loss 0.031317 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:04 Epoch 3 | Batch 2596/3508 | Timestep 13120 | LR 0.0000100000 | Loss 0.027470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:06 Epoch 3 | Batch 2606/3508 | Timestep 13130 | LR 0.0000100000 | Loss 0.029972 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:08 Epoch 3 | Batch 2616/3508 | Timestep 13140 | LR 0.0000100000 | Loss 0.090918 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:11 Epoch 3 | Batch 2626/3508 | Timestep 13150 | LR 0.0000100000 | Loss 0.043560 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:13 Epoch 3 | Batch 2636/3508 | Timestep 13160 | LR 0.0000100000 | Loss 0.081386 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:15 Epoch 3 | Batch 2646/3508 | Timestep 13170 | LR 0.0000100000 | Loss 0.055320 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:17 Epoch 3 | Batch 2656/3508 | Timestep 13180 | LR 0.0000100000 | Loss 0.024192 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:20 Epoch 3 | Batch 2666/3508 | Timestep 13190 | LR 0.0000100000 | Loss 0.047755 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:22 Epoch 3 | Batch 2676/3508 | Timestep 13200 | LR 0.0000100000 | Loss 0.035636 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:25 Epoch 3 | Batch 2686/3508 | Timestep 13210 | LR 0.0000100000 | Loss 0.011249 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:27 Epoch 3 | Batch 2696/3508 | Timestep 13220 | LR 0.0000100000 | Loss 0.023987 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:29 Epoch 3 | Batch 2706/3508 | Timestep 13230 | LR 0.0000100000 | Loss 0.054343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:31 Epoch 3 | Batch 2716/3508 | Timestep 13240 | LR 0.0000100000 | Loss 0.036165 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:33 Epoch 3 | Batch 2726/3508 | Timestep 13250 | LR 0.0000100000 | Loss 0.014753 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:36 Epoch 3 | Batch 2736/3508 | Timestep 13260 | LR 0.0000100000 | Loss 0.045715 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:38 Epoch 3 | Batch 2746/3508 | Timestep 13270 | LR 0.0000100000 | Loss 0.072850 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:40 Epoch 3 | Batch 2756/3508 | Timestep 13280 | LR 0.0000100000 | Loss 0.140899 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:42 Epoch 3 | Batch 2766/3508 | Timestep 13290 | LR 0.0000100000 | Loss 0.011809 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:45 Epoch 3 | Batch 2776/3508 | Timestep 13300 | LR 0.0000100000 | Loss 0.025136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:47 Epoch 3 | Batch 2786/3508 | Timestep 13310 | LR 0.0000100000 | Loss 0.005478 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:49 Epoch 3 | Batch 2796/3508 | Timestep 13320 | LR 0.0000100000 | Loss 0.008385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:51 Epoch 3 | Batch 2806/3508 | Timestep 13330 | LR 0.0000100000 | Loss 0.048564 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:53 Epoch 3 | Batch 2816/3508 | Timestep 13340 | LR 0.0000100000 | Loss 0.053295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:56 Epoch 3 | Batch 2826/3508 | Timestep 13350 | LR 0.0000100000 | Loss 0.044064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:32:58 Epoch 3 | Batch 2836/3508 | Timestep 13360 | LR 0.0000100000 | Loss 0.046503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:00 Epoch 3 | Batch 2846/3508 | Timestep 13370 | LR 0.0000100000 | Loss 0.084732 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:03 Epoch 3 | Batch 2856/3508 | Timestep 13380 | LR 0.0000100000 | Loss 0.101515 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:05 Epoch 3 | Batch 2866/3508 | Timestep 13390 | LR 0.0000100000 | Loss 0.082304 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:07 Epoch 3 | Batch 2876/3508 | Timestep 13400 | LR 0.0000100000 | Loss 0.023165 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:09 Epoch 3 | Batch 2886/3508 | Timestep 13410 | LR 0.0000100000 | Loss 0.023729 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:11 Epoch 3 | Batch 2896/3508 | Timestep 13420 | LR 0.0000100000 | Loss 0.039309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:14 Epoch 3 | Batch 2906/3508 | Timestep 13430 | LR 0.0000100000 | Loss 0.032981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:16 Epoch 3 | Batch 2916/3508 | Timestep 13440 | LR 0.0000100000 | Loss 0.053217 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:18 Epoch 3 | Batch 2926/3508 | Timestep 13450 | LR 0.0000100000 | Loss 0.036977 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:20 Epoch 3 | Batch 2936/3508 | Timestep 13460 | LR 0.0000100000 | Loss 0.047845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:22 Epoch 3 | Batch 2946/3508 | Timestep 13470 | LR 0.0000100000 | Loss 0.006473 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:24 Epoch 3 | Batch 2956/3508 | Timestep 13480 | LR 0.0000100000 | Loss 0.023517 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:26 Epoch 3 | Batch 2966/3508 | Timestep 13490 | LR 0.0000100000 | Loss 0.024900 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:29 Epoch 3 | Batch 2976/3508 | Timestep 13500 | LR 0.0000100000 | Loss 0.028715 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:31 Epoch 3 | Batch 2986/3508 | Timestep 13510 | LR 0.0000100000 | Loss 0.021608 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:33 Epoch 3 | Batch 2996/3508 | Timestep 13520 | LR 0.0000100000 | Loss 0.029335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:35 Epoch 3 | Batch 3006/3508 | Timestep 13530 | LR 0.0000100000 | Loss 0.010688 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:38 Epoch 3 | Batch 3016/3508 | Timestep 13540 | LR 0.0000100000 | Loss 0.036869 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:39 Epoch 3 | Batch 3026/3508 | Timestep 13550 | LR 0.0000100000 | Loss 0.008616 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:42 Epoch 3 | Batch 3036/3508 | Timestep 13560 | LR 0.0000100000 | Loss 0.025746 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:44 Epoch 3 | Batch 3046/3508 | Timestep 13570 | LR 0.0000100000 | Loss 0.054000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:46 Epoch 3 | Batch 3056/3508 | Timestep 13580 | LR 0.0000100000 | Loss 0.041900 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:48 Epoch 3 | Batch 3066/3508 | Timestep 13590 | LR 0.0000100000 | Loss 0.021655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:50 Epoch 3 | Batch 3076/3508 | Timestep 13600 | LR 0.0000100000 | Loss 0.014358 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:53 Epoch 3 | Batch 3086/3508 | Timestep 13610 | LR 0.0000100000 | Loss 0.003287 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:55 Epoch 3 | Batch 3096/3508 | Timestep 13620 | LR 0.0000100000 | Loss 0.034730 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:33:57 Epoch 3 | Batch 3106/3508 | Timestep 13630 | LR 0.0000100000 | Loss 0.007062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:00 Epoch 3 | Batch 3116/3508 | Timestep 13640 | LR 0.0000100000 | Loss 0.041848 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:02 Epoch 3 | Batch 3126/3508 | Timestep 13650 | LR 0.0000100000 | Loss 0.005613 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:04 Epoch 3 | Batch 3136/3508 | Timestep 13660 | LR 0.0000100000 | Loss 0.014083 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:06 Epoch 3 | Batch 3146/3508 | Timestep 13670 | LR 0.0000100000 | Loss 0.005428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:08 Epoch 3 | Batch 3156/3508 | Timestep 13680 | LR 0.0000100000 | Loss 0.026825 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:10 Epoch 3 | Batch 3166/3508 | Timestep 13690 | LR 0.0000100000 | Loss 0.101791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:12 Epoch 3 | Batch 3176/3508 | Timestep 13700 | LR 0.0000100000 | Loss 0.063444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:14 Epoch 3 | Batch 3186/3508 | Timestep 13710 | LR 0.0000100000 | Loss 0.019155 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:16 Epoch 3 | Batch 3196/3508 | Timestep 13720 | LR 0.0000100000 | Loss 0.049415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:18 Epoch 3 | Batch 3206/3508 | Timestep 13730 | LR 0.0000100000 | Loss 0.043625 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:20 Epoch 3 | Batch 3216/3508 | Timestep 13740 | LR 0.0000100000 | Loss 0.029989 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:22 Epoch 3 | Batch 3226/3508 | Timestep 13750 | LR 0.0000100000 | Loss 0.006719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:24 Epoch 3 | Batch 3236/3508 | Timestep 13760 | LR 0.0000100000 | Loss 0.034208 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:26 Epoch 3 | Batch 3246/3508 | Timestep 13770 | LR 0.0000100000 | Loss 0.028553 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:28 Epoch 3 | Batch 3256/3508 | Timestep 13780 | LR 0.0000100000 | Loss 0.057530 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:30 Epoch 3 | Batch 3266/3508 | Timestep 13790 | LR 0.0000100000 | Loss 0.010398 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:32 Epoch 3 | Batch 3276/3508 | Timestep 13800 | LR 0.0000100000 | Loss 0.028483 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:34 Epoch 3 | Batch 3286/3508 | Timestep 13810 | LR 0.0000100000 | Loss 0.022654 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:36 Epoch 3 | Batch 3296/3508 | Timestep 13820 | LR 0.0000100000 | Loss 0.061674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:39 Epoch 3 | Batch 3306/3508 | Timestep 13830 | LR 0.0000100000 | Loss 0.028415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:41 Epoch 3 | Batch 3316/3508 | Timestep 13840 | LR 0.0000100000 | Loss 0.017505 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:43 Epoch 3 | Batch 3326/3508 | Timestep 13850 | LR 0.0000100000 | Loss 0.057237 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:45 Epoch 3 | Batch 3336/3508 | Timestep 13860 | LR 0.0000100000 | Loss 0.021188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:48 Epoch 3 | Batch 3346/3508 | Timestep 13870 | LR 0.0000100000 | Loss 0.019500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:49 Epoch 3 | Batch 3356/3508 | Timestep 13880 | LR 0.0000100000 | Loss 0.008548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:51 Epoch 3 | Batch 3366/3508 | Timestep 13890 | LR 0.0000100000 | Loss 0.045956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:54 Epoch 3 | Batch 3376/3508 | Timestep 13900 | LR 0.0000100000 | Loss 0.025610 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:56 Epoch 3 | Batch 3386/3508 | Timestep 13910 | LR 0.0000100000 | Loss 0.007307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:34:58 Epoch 3 | Batch 3396/3508 | Timestep 13920 | LR 0.0000100000 | Loss 0.063181 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:00 Epoch 3 | Batch 3406/3508 | Timestep 13930 | LR 0.0000100000 | Loss 0.022938 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:02 Epoch 3 | Batch 3416/3508 | Timestep 13940 | LR 0.0000100000 | Loss 0.023904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:04 Epoch 3 | Batch 3426/3508 | Timestep 13950 | LR 0.0000100000 | Loss 0.029940 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:07 Epoch 3 | Batch 3436/3508 | Timestep 13960 | LR 0.0000100000 | Loss 0.048669 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:09 Epoch 3 | Batch 3446/3508 | Timestep 13970 | LR 0.0000100000 | Loss 0.009309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:11 Epoch 3 | Batch 3456/3508 | Timestep 13980 | LR 0.0000100000 | Loss 0.010982 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:14 Epoch 3 | Batch 3466/3508 | Timestep 13990 | LR 0.0000100000 | Loss 0.061957 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:15 Epoch 3 | Batch 3476/3508 | Timestep 14000 | LR 0.0000100000 | Loss 0.024331 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:18 Epoch 3 | Batch 3486/3508 | Timestep 14010 | LR 0.0000100000 | Loss 0.019801 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:20 Epoch 3 | Batch 3496/3508 | Timestep 14020 | LR 0.0000100000 | Loss 0.102582 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:23 Epoch 3 | Batch 3506/3508 | Timestep 14030 | LR 0.0000100000 | Loss 0.019452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:35:23 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 15:35:56 precision recall f1-score support CARDINAL 0.7927 0.8176 0.8050 159 CURR 0.6538 0.7727 0.7083 22 DATE 0.9323 0.9413 0.9368 1669 EVENT 0.6916 0.7527 0.7208 283 FAC 0.6786 0.8051 0.7364 118 GPE 0.9484 0.9706 0.9594 2140 LANGUAGE 0.6316 0.7500 0.6857 16 LAW 0.3421 0.6842 0.4561 19 LOC 0.7442 0.7111 0.7273 90 MONEY 0.7200 0.9000 0.8000 20 NORP 0.6497 0.7544 0.6982 509 OCC 0.8124 0.8730 0.8416 496 ORDINAL 0.9028 0.9372 0.9197 446 ORG 0.9094 0.9411 0.9249 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9178 0.9543 0.9357 679 PRODUCT 0.5000 0.1250 0.2000 8 QUANTITY 0.3333 0.6667 0.4444 3 TIME 0.6053 0.7419 0.6667 31 UNIT 0.7500 0.7500 0.7500 4 WEBSITE 0.5000 0.4625 0.4805 80 micro avg 0.8767 0.9143 0.8951 8670 macro avg 0.7114 0.7767 0.7313 8670 weighted avg 0.8805 0.9143 0.8965 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:36:06 Epoch 3 | Timestep 14032 | Train Loss 0.033912 | Val Loss 0.051879 | F1 0.895099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:36:06 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 25 Jun 2026 15:36:29 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Thu, 25 Jun 2026 15:36:46 Predictions written to /rep/nhamad/ArabicNER/B1/predictions.txt INFO root Thu, 25 Jun 2026 15:37:09 precision recall f1-score support CARDINAL 0.8034 0.8624 0.8319 327 CURR 0.5294 0.7105 0.6067 38 DATE 0.9351 0.9540 0.9445 3173 EVENT 0.7119 0.7782 0.7436 559 FAC 0.6953 0.7355 0.7149 242 GPE 0.9295 0.9627 0.9458 4311 LANGUAGE 0.7561 0.7045 0.7294 44 LAW 0.4681 0.7586 0.5789 29 LOC 0.7644 0.7294 0.7465 218 MONEY 0.7368 0.9333 0.8235 30 NORP 0.6581 0.7762 0.7123 992 OCC 0.8149 0.8676 0.8404 1035 ORDINAL 0.9119 0.9376 0.9246 850 ORG 0.8914 0.9286 0.9096 3738 PERCENT 0.9394 0.9688 0.9538 32 PERS 0.9187 0.9439 0.9311 1568 PRODUCT 0.7000 0.3684 0.4828 19 QUANTITY 0.3000 0.6667 0.4138 9 TIME 0.6824 0.7436 0.7117 78 UNIT 0.4118 0.6364 0.5000 11 WEBSITE 0.4034 0.4138 0.4085 116 micro avg 0.8724 0.9135 0.8925 17419 macro avg 0.7125 0.7800 0.7359 17419 weighted avg 0.8757 0.9135 0.8937 17419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:29 Epoch 3 | Timestep 14032 | Test Loss 0.054514 | F1 0.892454 INFO arabiner.trainers.BaseTrainer Thu, 25 Jun 2026 15:37:29 Saving checkpoint to /rep/nhamad/ArabicNER/B1/checkpoints/checkpoint_3.pt INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:33 Epoch 4 | Batch 8/3508 | Timestep 14040 | LR 0.0000100000 | Loss 0.014764 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:35 Epoch 4 | Batch 18/3508 | Timestep 14050 | LR 0.0000100000 | Loss 0.017583 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:38 Epoch 4 | Batch 28/3508 | Timestep 14060 | LR 0.0000100000 | Loss 0.023969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:40 Epoch 4 | Batch 38/3508 | Timestep 14070 | LR 0.0000100000 | Loss 0.066495 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:42 Epoch 4 | Batch 48/3508 | Timestep 14080 | LR 0.0000100000 | Loss 0.009679 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:44 Epoch 4 | Batch 58/3508 | Timestep 14090 | LR 0.0000100000 | Loss 0.003579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:47 Epoch 4 | Batch 68/3508 | Timestep 14100 | LR 0.0000100000 | Loss 0.029806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:48 Epoch 4 | Batch 78/3508 | Timestep 14110 | LR 0.0000100000 | Loss 0.035629 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:50 Epoch 4 | Batch 88/3508 | Timestep 14120 | LR 0.0000100000 | Loss 0.007773 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:52 Epoch 4 | Batch 98/3508 | Timestep 14130 | LR 0.0000100000 | Loss 0.023938 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:54 Epoch 4 | Batch 108/3508 | Timestep 14140 | LR 0.0000100000 | Loss 0.031576 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:56 Epoch 4 | Batch 118/3508 | Timestep 14150 | LR 0.0000100000 | Loss 0.016999 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:37:58 Epoch 4 | Batch 128/3508 | Timestep 14160 | LR 0.0000100000 | Loss 0.006923 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:00 Epoch 4 | Batch 138/3508 | Timestep 14170 | LR 0.0000100000 | Loss 0.003420 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:03 Epoch 4 | Batch 148/3508 | Timestep 14180 | LR 0.0000100000 | Loss 0.017692 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:05 Epoch 4 | Batch 158/3508 | Timestep 14190 | LR 0.0000100000 | Loss 0.030179 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:07 Epoch 4 | Batch 168/3508 | Timestep 14200 | LR 0.0000100000 | Loss 0.036919 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:09 Epoch 4 | Batch 178/3508 | Timestep 14210 | LR 0.0000100000 | Loss 0.031852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:11 Epoch 4 | Batch 188/3508 | Timestep 14220 | LR 0.0000100000 | Loss 0.018337 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:13 Epoch 4 | Batch 198/3508 | Timestep 14230 | LR 0.0000100000 | Loss 0.040492 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:15 Epoch 4 | Batch 208/3508 | Timestep 14240 | LR 0.0000100000 | Loss 0.051830 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:18 Epoch 4 | Batch 218/3508 | Timestep 14250 | LR 0.0000100000 | Loss 0.010631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:20 Epoch 4 | Batch 228/3508 | Timestep 14260 | LR 0.0000100000 | Loss 0.011008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:22 Epoch 4 | Batch 238/3508 | Timestep 14270 | LR 0.0000100000 | Loss 0.015603 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:24 Epoch 4 | Batch 248/3508 | Timestep 14280 | LR 0.0000100000 | Loss 0.009214 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:27 Epoch 4 | Batch 258/3508 | Timestep 14290 | LR 0.0000100000 | Loss 0.015666 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:29 Epoch 4 | Batch 268/3508 | Timestep 14300 | LR 0.0000100000 | Loss 0.007470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:31 Epoch 4 | Batch 278/3508 | Timestep 14310 | LR 0.0000100000 | Loss 0.056250 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:33 Epoch 4 | Batch 288/3508 | Timestep 14320 | LR 0.0000100000 | Loss 0.020922 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:35 Epoch 4 | Batch 298/3508 | Timestep 14330 | LR 0.0000100000 | Loss 0.015440 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:38 Epoch 4 | Batch 308/3508 | Timestep 14340 | LR 0.0000100000 | Loss 0.020524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:40 Epoch 4 | Batch 318/3508 | Timestep 14350 | LR 0.0000100000 | Loss 0.016218 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:42 Epoch 4 | Batch 328/3508 | Timestep 14360 | LR 0.0000100000 | Loss 0.010053 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:44 Epoch 4 | Batch 338/3508 | Timestep 14370 | LR 0.0000100000 | Loss 0.022488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:46 Epoch 4 | Batch 348/3508 | Timestep 14380 | LR 0.0000100000 | Loss 0.067444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:48 Epoch 4 | Batch 358/3508 | Timestep 14390 | LR 0.0000100000 | Loss 0.019590 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:50 Epoch 4 | Batch 368/3508 | Timestep 14400 | LR 0.0000100000 | Loss 0.025684 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:52 Epoch 4 | Batch 378/3508 | Timestep 14410 | LR 0.0000100000 | Loss 0.046562 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:55 Epoch 4 | Batch 388/3508 | Timestep 14420 | LR 0.0000100000 | Loss 0.009997 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:57 Epoch 4 | Batch 398/3508 | Timestep 14430 | LR 0.0000100000 | Loss 0.005760 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:38:59 Epoch 4 | Batch 408/3508 | Timestep 14440 | LR 0.0000100000 | Loss 0.021592 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:01 Epoch 4 | Batch 418/3508 | Timestep 14450 | LR 0.0000100000 | Loss 0.022181 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:03 Epoch 4 | Batch 428/3508 | Timestep 14460 | LR 0.0000100000 | Loss 0.063112 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:05 Epoch 4 | Batch 438/3508 | Timestep 14470 | LR 0.0000100000 | Loss 0.014300 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:08 Epoch 4 | Batch 448/3508 | Timestep 14480 | LR 0.0000100000 | Loss 0.006857 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:10 Epoch 4 | Batch 458/3508 | Timestep 14490 | LR 0.0000100000 | Loss 0.115606 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:12 Epoch 4 | Batch 468/3508 | Timestep 14500 | LR 0.0000100000 | Loss 0.007027 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:14 Epoch 4 | Batch 478/3508 | Timestep 14510 | LR 0.0000100000 | Loss 0.016334 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:16 Epoch 4 | Batch 488/3508 | Timestep 14520 | LR 0.0000100000 | Loss 0.024032 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:18 Epoch 4 | Batch 498/3508 | Timestep 14530 | LR 0.0000100000 | Loss 0.020109 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:20 Epoch 4 | Batch 508/3508 | Timestep 14540 | LR 0.0000100000 | Loss 0.020278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:22 Epoch 4 | Batch 518/3508 | Timestep 14550 | LR 0.0000100000 | Loss 0.010414 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:24 Epoch 4 | Batch 528/3508 | Timestep 14560 | LR 0.0000100000 | Loss 0.038065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:27 Epoch 4 | Batch 538/3508 | Timestep 14570 | LR 0.0000100000 | Loss 0.007340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:29 Epoch 4 | Batch 548/3508 | Timestep 14580 | LR 0.0000100000 | Loss 0.020687 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:31 Epoch 4 | Batch 558/3508 | Timestep 14590 | LR 0.0000100000 | Loss 0.019961 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:33 Epoch 4 | Batch 568/3508 | Timestep 14600 | LR 0.0000100000 | Loss 0.012257 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:36 Epoch 4 | Batch 578/3508 | Timestep 14610 | LR 0.0000100000 | Loss 0.042610 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:38 Epoch 4 | Batch 588/3508 | Timestep 14620 | LR 0.0000100000 | Loss 0.021452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:40 Epoch 4 | Batch 598/3508 | Timestep 14630 | LR 0.0000100000 | Loss 0.067895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:42 Epoch 4 | Batch 608/3508 | Timestep 14640 | LR 0.0000100000 | Loss 0.017551 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:45 Epoch 4 | Batch 618/3508 | Timestep 14650 | LR 0.0000100000 | Loss 0.017453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:47 Epoch 4 | Batch 628/3508 | Timestep 14660 | LR 0.0000100000 | Loss 0.029635 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:49 Epoch 4 | Batch 638/3508 | Timestep 14670 | LR 0.0000100000 | Loss 0.025953 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:51 Epoch 4 | Batch 648/3508 | Timestep 14680 | LR 0.0000100000 | Loss 0.014892 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:53 Epoch 4 | Batch 658/3508 | Timestep 14690 | LR 0.0000100000 | Loss 0.042225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:56 Epoch 4 | Batch 668/3508 | Timestep 14700 | LR 0.0000100000 | Loss 0.006864 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:39:58 Epoch 4 | Batch 678/3508 | Timestep 14710 | LR 0.0000100000 | Loss 0.009836 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:00 Epoch 4 | Batch 688/3508 | Timestep 14720 | LR 0.0000100000 | Loss 0.029220 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:02 Epoch 4 | Batch 698/3508 | Timestep 14730 | LR 0.0000100000 | Loss 0.012142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:04 Epoch 4 | Batch 708/3508 | Timestep 14740 | LR 0.0000100000 | Loss 0.031586 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:06 Epoch 4 | Batch 718/3508 | Timestep 14750 | LR 0.0000100000 | Loss 0.016894 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:08 Epoch 4 | Batch 728/3508 | Timestep 14760 | LR 0.0000100000 | Loss 0.005324 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:10 Epoch 4 | Batch 738/3508 | Timestep 14770 | LR 0.0000100000 | Loss 0.023996 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:12 Epoch 4 | Batch 748/3508 | Timestep 14780 | LR 0.0000100000 | Loss 0.016170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:14 Epoch 4 | Batch 758/3508 | Timestep 14790 | LR 0.0000100000 | Loss 0.046756 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:16 Epoch 4 | Batch 768/3508 | Timestep 14800 | LR 0.0000100000 | Loss 0.052135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:18 Epoch 4 | Batch 778/3508 | Timestep 14810 | LR 0.0000100000 | Loss 0.008523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:20 Epoch 4 | Batch 788/3508 | Timestep 14820 | LR 0.0000100000 | Loss 0.029296 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:23 Epoch 4 | Batch 798/3508 | Timestep 14830 | LR 0.0000100000 | Loss 0.036830 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:24 Epoch 4 | Batch 808/3508 | Timestep 14840 | LR 0.0000100000 | Loss 0.008848 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:26 Epoch 4 | Batch 818/3508 | Timestep 14850 | LR 0.0000100000 | Loss 0.000633 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:29 Epoch 4 | Batch 828/3508 | Timestep 14860 | LR 0.0000100000 | Loss 0.015993 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:32 Epoch 4 | Batch 838/3508 | Timestep 14870 | LR 0.0000100000 | Loss 0.014225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:34 Epoch 4 | Batch 848/3508 | Timestep 14880 | LR 0.0000100000 | Loss 0.032584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:36 Epoch 4 | Batch 858/3508 | Timestep 14890 | LR 0.0000100000 | Loss 0.031091 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:38 Epoch 4 | Batch 868/3508 | Timestep 14900 | LR 0.0000100000 | Loss 0.016529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:40 Epoch 4 | Batch 878/3508 | Timestep 14910 | LR 0.0000100000 | Loss 0.010819 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:42 Epoch 4 | Batch 888/3508 | Timestep 14920 | LR 0.0000100000 | Loss 0.005950 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:44 Epoch 4 | Batch 898/3508 | Timestep 14930 | LR 0.0000100000 | Loss 0.021007 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:47 Epoch 4 | Batch 908/3508 | Timestep 14940 | LR 0.0000100000 | Loss 0.078075 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:49 Epoch 4 | Batch 918/3508 | Timestep 14950 | LR 0.0000100000 | Loss 0.037275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:51 Epoch 4 | Batch 928/3508 | Timestep 14960 | LR 0.0000100000 | Loss 0.022691 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:54 Epoch 4 | Batch 938/3508 | Timestep 14970 | LR 0.0000100000 | Loss 0.043778 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:56 Epoch 4 | Batch 948/3508 | Timestep 14980 | LR 0.0000100000 | Loss 0.133748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:40:58 Epoch 4 | Batch 958/3508 | Timestep 14990 | LR 0.0000100000 | Loss 0.010151 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:00 Epoch 4 | Batch 968/3508 | Timestep 15000 | LR 0.0000100000 | Loss 0.011171 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:03 Epoch 4 | Batch 978/3508 | Timestep 15010 | LR 0.0000100000 | Loss 0.024802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:05 Epoch 4 | Batch 988/3508 | Timestep 15020 | LR 0.0000100000 | Loss 0.010856 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:07 Epoch 4 | Batch 998/3508 | Timestep 15030 | LR 0.0000100000 | Loss 0.016474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:09 Epoch 4 | Batch 1008/3508 | Timestep 15040 | LR 0.0000100000 | Loss 0.003837 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:11 Epoch 4 | Batch 1018/3508 | Timestep 15050 | LR 0.0000100000 | Loss 0.016829 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:13 Epoch 4 | Batch 1028/3508 | Timestep 15060 | LR 0.0000100000 | Loss 0.050513 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:16 Epoch 4 | Batch 1038/3508 | Timestep 15070 | LR 0.0000100000 | Loss 0.015723 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:17 Epoch 4 | Batch 1048/3508 | Timestep 15080 | LR 0.0000100000 | Loss 0.022714 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:20 Epoch 4 | Batch 1058/3508 | Timestep 15090 | LR 0.0000100000 | Loss 0.027494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:22 Epoch 4 | Batch 1068/3508 | Timestep 15100 | LR 0.0000100000 | Loss 0.017835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:25 Epoch 4 | Batch 1078/3508 | Timestep 15110 | LR 0.0000100000 | Loss 0.024597 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:27 Epoch 4 | Batch 1088/3508 | Timestep 15120 | LR 0.0000100000 | Loss 0.071503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:29 Epoch 4 | Batch 1098/3508 | Timestep 15130 | LR 0.0000100000 | Loss 0.021715 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:32 Epoch 4 | Batch 1108/3508 | Timestep 15140 | LR 0.0000100000 | Loss 0.031412 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:34 Epoch 4 | Batch 1118/3508 | Timestep 15150 | LR 0.0000100000 | Loss 0.004830 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:36 Epoch 4 | Batch 1128/3508 | Timestep 15160 | LR 0.0000100000 | Loss 0.026143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:38 Epoch 4 | Batch 1138/3508 | Timestep 15170 | LR 0.0000100000 | Loss 0.046919 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:41 Epoch 4 | Batch 1148/3508 | Timestep 15180 | LR 0.0000100000 | Loss 0.006112 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:43 Epoch 4 | Batch 1158/3508 | Timestep 15190 | LR 0.0000100000 | Loss 0.017286 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:45 Epoch 4 | Batch 1168/3508 | Timestep 15200 | LR 0.0000100000 | Loss 0.006992 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:47 Epoch 4 | Batch 1178/3508 | Timestep 15210 | LR 0.0000100000 | Loss 0.043759 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:50 Epoch 4 | Batch 1188/3508 | Timestep 15220 | LR 0.0000100000 | Loss 0.023563 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:52 Epoch 4 | Batch 1198/3508 | Timestep 15230 | LR 0.0000100000 | Loss 0.007682 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:54 Epoch 4 | Batch 1208/3508 | Timestep 15240 | LR 0.0000100000 | Loss 0.033043 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:56 Epoch 4 | Batch 1218/3508 | Timestep 15250 | LR 0.0000100000 | Loss 0.008915 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:41:58 Epoch 4 | Batch 1228/3508 | Timestep 15260 | LR 0.0000100000 | Loss 0.024187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:00 Epoch 4 | Batch 1238/3508 | Timestep 15270 | LR 0.0000100000 | Loss 0.040380 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:02 Epoch 4 | Batch 1248/3508 | Timestep 15280 | LR 0.0000100000 | Loss 0.021453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:04 Epoch 4 | Batch 1258/3508 | Timestep 15290 | LR 0.0000100000 | Loss 0.067649 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:06 Epoch 4 | Batch 1268/3508 | Timestep 15300 | LR 0.0000100000 | Loss 0.016266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:08 Epoch 4 | Batch 1278/3508 | Timestep 15310 | LR 0.0000100000 | Loss 0.014358 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:10 Epoch 4 | Batch 1288/3508 | Timestep 15320 | LR 0.0000100000 | Loss 0.015282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:12 Epoch 4 | Batch 1298/3508 | Timestep 15330 | LR 0.0000100000 | Loss 0.041285 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:14 Epoch 4 | Batch 1308/3508 | Timestep 15340 | LR 0.0000100000 | Loss 0.015914 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:16 Epoch 4 | Batch 1318/3508 | Timestep 15350 | LR 0.0000100000 | Loss 0.052508 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:17 Epoch 4 | Batch 1328/3508 | Timestep 15360 | LR 0.0000100000 | Loss 0.031292 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:20 Epoch 4 | Batch 1338/3508 | Timestep 15370 | LR 0.0000100000 | Loss 0.033679 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:22 Epoch 4 | Batch 1348/3508 | Timestep 15380 | LR 0.0000100000 | Loss 0.009912 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:24 Epoch 4 | Batch 1358/3508 | Timestep 15390 | LR 0.0000100000 | Loss 0.014134 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:26 Epoch 4 | Batch 1368/3508 | Timestep 15400 | LR 0.0000100000 | Loss 0.029359 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:28 Epoch 4 | Batch 1378/3508 | Timestep 15410 | LR 0.0000100000 | Loss 0.020866 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:31 Epoch 4 | Batch 1388/3508 | Timestep 15420 | LR 0.0000100000 | Loss 0.021869 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:33 Epoch 4 | Batch 1398/3508 | Timestep 15430 | LR 0.0000100000 | Loss 0.016803 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:35 Epoch 4 | Batch 1408/3508 | Timestep 15440 | LR 0.0000100000 | Loss 0.018546 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:37 Epoch 4 | Batch 1418/3508 | Timestep 15450 | LR 0.0000100000 | Loss 0.022372 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:40 Epoch 4 | Batch 1428/3508 | Timestep 15460 | LR 0.0000100000 | Loss 0.025604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:42 Epoch 4 | Batch 1438/3508 | Timestep 15470 | LR 0.0000100000 | Loss 0.051585 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:44 Epoch 4 | Batch 1448/3508 | Timestep 15480 | LR 0.0000100000 | Loss 0.030247 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:46 Epoch 4 | Batch 1458/3508 | Timestep 15490 | LR 0.0000100000 | Loss 0.020739 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:48 Epoch 4 | Batch 1468/3508 | Timestep 15500 | LR 0.0000100000 | Loss 0.018716 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:50 Epoch 4 | Batch 1478/3508 | Timestep 15510 | LR 0.0000100000 | Loss 0.046988 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:53 Epoch 4 | Batch 1488/3508 | Timestep 15520 | LR 0.0000100000 | Loss 0.014528 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:55 Epoch 4 | Batch 1498/3508 | Timestep 15530 | LR 0.0000100000 | Loss 0.023267 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:57 Epoch 4 | Batch 1508/3508 | Timestep 15540 | LR 0.0000100000 | Loss 0.010956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:42:59 Epoch 4 | Batch 1518/3508 | Timestep 15550 | LR 0.0000100000 | Loss 0.025138 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:01 Epoch 4 | Batch 1528/3508 | Timestep 15560 | LR 0.0000100000 | Loss 0.006102 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:04 Epoch 4 | Batch 1538/3508 | Timestep 15570 | LR 0.0000100000 | Loss 0.021194 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:06 Epoch 4 | Batch 1548/3508 | Timestep 15580 | LR 0.0000100000 | Loss 0.020954 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:07 Epoch 4 | Batch 1558/3508 | Timestep 15590 | LR 0.0000100000 | Loss 0.026420 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:09 Epoch 4 | Batch 1568/3508 | Timestep 15600 | LR 0.0000100000 | Loss 0.016196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:11 Epoch 4 | Batch 1578/3508 | Timestep 15610 | LR 0.0000100000 | Loss 0.004990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:13 Epoch 4 | Batch 1588/3508 | Timestep 15620 | LR 0.0000100000 | Loss 0.135735 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:15 Epoch 4 | Batch 1598/3508 | Timestep 15630 | LR 0.0000100000 | Loss 0.029809 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:17 Epoch 4 | Batch 1608/3508 | Timestep 15640 | LR 0.0000100000 | Loss 0.025468 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:19 Epoch 4 | Batch 1618/3508 | Timestep 15650 | LR 0.0000100000 | Loss 0.019028 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:21 Epoch 4 | Batch 1628/3508 | Timestep 15660 | LR 0.0000100000 | Loss 0.013861 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:23 Epoch 4 | Batch 1638/3508 | Timestep 15670 | LR 0.0000100000 | Loss 0.037572 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:25 Epoch 4 | Batch 1648/3508 | Timestep 15680 | LR 0.0000100000 | Loss 0.018946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:27 Epoch 4 | Batch 1658/3508 | Timestep 15690 | LR 0.0000100000 | Loss 0.037970 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:29 Epoch 4 | Batch 1668/3508 | Timestep 15700 | LR 0.0000100000 | Loss 0.005619 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:31 Epoch 4 | Batch 1678/3508 | Timestep 15710 | LR 0.0000100000 | Loss 0.014631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:33 Epoch 4 | Batch 1688/3508 | Timestep 15720 | LR 0.0000100000 | Loss 0.037104 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:35 Epoch 4 | Batch 1698/3508 | Timestep 15730 | LR 0.0000100000 | Loss 0.012838 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:37 Epoch 4 | Batch 1708/3508 | Timestep 15740 | LR 0.0000100000 | Loss 0.034031 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:39 Epoch 4 | Batch 1718/3508 | Timestep 15750 | LR 0.0000100000 | Loss 0.037155 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:41 Epoch 4 | Batch 1728/3508 | Timestep 15760 | LR 0.0000100000 | Loss 0.016435 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:43 Epoch 4 | Batch 1738/3508 | Timestep 15770 | LR 0.0000100000 | Loss 0.005178 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:46 Epoch 4 | Batch 1748/3508 | Timestep 15780 | LR 0.0000100000 | Loss 0.027198 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:48 Epoch 4 | Batch 1758/3508 | Timestep 15790 | LR 0.0000100000 | Loss 0.069368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:50 Epoch 4 | Batch 1768/3508 | Timestep 15800 | LR 0.0000100000 | Loss 0.009389 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:52 Epoch 4 | Batch 1778/3508 | Timestep 15810 | LR 0.0000100000 | Loss 0.006670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:55 Epoch 4 | Batch 1788/3508 | Timestep 15820 | LR 0.0000100000 | Loss 0.016497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:57 Epoch 4 | Batch 1798/3508 | Timestep 15830 | LR 0.0000100000 | Loss 0.077557 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:43:59 Epoch 4 | Batch 1808/3508 | Timestep 15840 | LR 0.0000100000 | Loss 0.029928 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:01 Epoch 4 | Batch 1818/3508 | Timestep 15850 | LR 0.0000100000 | Loss 0.052282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:03 Epoch 4 | Batch 1828/3508 | Timestep 15860 | LR 0.0000100000 | Loss 0.047540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:06 Epoch 4 | Batch 1838/3508 | Timestep 15870 | LR 0.0000100000 | Loss 0.065907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:08 Epoch 4 | Batch 1848/3508 | Timestep 15880 | LR 0.0000100000 | Loss 0.032132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:10 Epoch 4 | Batch 1858/3508 | Timestep 15890 | LR 0.0000100000 | Loss 0.037848 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:12 Epoch 4 | Batch 1868/3508 | Timestep 15900 | LR 0.0000100000 | Loss 0.061798 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:14 Epoch 4 | Batch 1878/3508 | Timestep 15910 | LR 0.0000100000 | Loss 0.046504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:17 Epoch 4 | Batch 1888/3508 | Timestep 15920 | LR 0.0000100000 | Loss 0.010911 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:19 Epoch 4 | Batch 1898/3508 | Timestep 15930 | LR 0.0000100000 | Loss 0.078617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:21 Epoch 4 | Batch 1908/3508 | Timestep 15940 | LR 0.0000100000 | Loss 0.008143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:23 Epoch 4 | Batch 1918/3508 | Timestep 15950 | LR 0.0000100000 | Loss 0.017332 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:25 Epoch 4 | Batch 1928/3508 | Timestep 15960 | LR 0.0000100000 | Loss 0.050210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:27 Epoch 4 | Batch 1938/3508 | Timestep 15970 | LR 0.0000100000 | Loss 0.008652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:29 Epoch 4 | Batch 1948/3508 | Timestep 15980 | LR 0.0000100000 | Loss 0.019728 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:32 Epoch 4 | Batch 1958/3508 | Timestep 15990 | LR 0.0000100000 | Loss 0.044623 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:34 Epoch 4 | Batch 1968/3508 | Timestep 16000 | LR 0.0000100000 | Loss 0.022503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:36 Epoch 4 | Batch 1978/3508 | Timestep 16010 | LR 0.0000100000 | Loss 0.017227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:38 Epoch 4 | Batch 1988/3508 | Timestep 16020 | LR 0.0000100000 | Loss 0.009847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:40 Epoch 4 | Batch 1998/3508 | Timestep 16030 | LR 0.0000100000 | Loss 0.005656 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:42 Epoch 4 | Batch 2008/3508 | Timestep 16040 | LR 0.0000100000 | Loss 0.047025 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:44 Epoch 4 | Batch 2018/3508 | Timestep 16050 | LR 0.0000100000 | Loss 0.027259 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:47 Epoch 4 | Batch 2028/3508 | Timestep 16060 | LR 0.0000100000 | Loss 0.013708 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:49 Epoch 4 | Batch 2038/3508 | Timestep 16070 | LR 0.0000100000 | Loss 0.051994 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:52 Epoch 4 | Batch 2048/3508 | Timestep 16080 | LR 0.0000100000 | Loss 0.011852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:54 Epoch 4 | Batch 2058/3508 | Timestep 16090 | LR 0.0000100000 | Loss 0.023100 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:56 Epoch 4 | Batch 2068/3508 | Timestep 16100 | LR 0.0000100000 | Loss 0.012388 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:44:58 Epoch 4 | Batch 2078/3508 | Timestep 16110 | LR 0.0000100000 | Loss 0.022027 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:00 Epoch 4 | Batch 2088/3508 | Timestep 16120 | LR 0.0000100000 | Loss 0.017101 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:03 Epoch 4 | Batch 2098/3508 | Timestep 16130 | LR 0.0000100000 | Loss 0.006393 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:05 Epoch 4 | Batch 2108/3508 | Timestep 16140 | LR 0.0000100000 | Loss 0.028298 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:07 Epoch 4 | Batch 2118/3508 | Timestep 16150 | LR 0.0000100000 | Loss 0.127733 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:09 Epoch 4 | Batch 2128/3508 | Timestep 16160 | LR 0.0000100000 | Loss 0.021722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:12 Epoch 4 | Batch 2138/3508 | Timestep 16170 | LR 0.0000100000 | Loss 0.029222 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:14 Epoch 4 | Batch 2148/3508 | Timestep 16180 | LR 0.0000100000 | Loss 0.054713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:17 Epoch 4 | Batch 2158/3508 | Timestep 16190 | LR 0.0000100000 | Loss 0.008779 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:18 Epoch 4 | Batch 2168/3508 | Timestep 16200 | LR 0.0000100000 | Loss 0.003396 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:21 Epoch 4 | Batch 2178/3508 | Timestep 16210 | LR 0.0000100000 | Loss 0.020008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:23 Epoch 4 | Batch 2188/3508 | Timestep 16220 | LR 0.0000100000 | Loss 0.070772 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:25 Epoch 4 | Batch 2198/3508 | Timestep 16230 | LR 0.0000100000 | Loss 0.030075 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:27 Epoch 4 | Batch 2208/3508 | Timestep 16240 | LR 0.0000100000 | Loss 0.019851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:29 Epoch 4 | Batch 2218/3508 | Timestep 16250 | LR 0.0000100000 | Loss 0.065894 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:32 Epoch 4 | Batch 2228/3508 | Timestep 16260 | LR 0.0000100000 | Loss 0.009525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:34 Epoch 4 | Batch 2238/3508 | Timestep 16270 | LR 0.0000100000 | Loss 0.005106 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:36 Epoch 4 | Batch 2248/3508 | Timestep 16280 | LR 0.0000100000 | Loss 0.013810 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:38 Epoch 4 | Batch 2258/3508 | Timestep 16290 | LR 0.0000100000 | Loss 0.016224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:40 Epoch 4 | Batch 2268/3508 | Timestep 16300 | LR 0.0000100000 | Loss 0.018743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:42 Epoch 4 | Batch 2278/3508 | Timestep 16310 | LR 0.0000100000 | Loss 0.017297 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:45 Epoch 4 | Batch 2288/3508 | Timestep 16320 | LR 0.0000100000 | Loss 0.014500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:47 Epoch 4 | Batch 2298/3508 | Timestep 16330 | LR 0.0000100000 | Loss 0.032474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:49 Epoch 4 | Batch 2308/3508 | Timestep 16340 | LR 0.0000100000 | Loss 0.039378 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:51 Epoch 4 | Batch 2318/3508 | Timestep 16350 | LR 0.0000100000 | Loss 0.028433 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:52 Epoch 4 | Batch 2328/3508 | Timestep 16360 | LR 0.0000100000 | Loss 0.020157 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:54 Epoch 4 | Batch 2338/3508 | Timestep 16370 | LR 0.0000100000 | Loss 0.017017 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:57 Epoch 4 | Batch 2348/3508 | Timestep 16380 | LR 0.0000100000 | Loss 0.007636 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:45:59 Epoch 4 | Batch 2358/3508 | Timestep 16390 | LR 0.0000100000 | Loss 0.005071 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:01 Epoch 4 | Batch 2368/3508 | Timestep 16400 | LR 0.0000100000 | Loss 0.016609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:02 Epoch 4 | Batch 2378/3508 | Timestep 16410 | LR 0.0000100000 | Loss 0.023942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:04 Epoch 4 | Batch 2388/3508 | Timestep 16420 | LR 0.0000100000 | Loss 0.045562 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:06 Epoch 4 | Batch 2398/3508 | Timestep 16430 | LR 0.0000100000 | Loss 0.016027 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:08 Epoch 4 | Batch 2408/3508 | Timestep 16440 | LR 0.0000100000 | Loss 0.088858 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:10 Epoch 4 | Batch 2418/3508 | Timestep 16450 | LR 0.0000100000 | Loss 0.030556 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:12 Epoch 4 | Batch 2428/3508 | Timestep 16460 | LR 0.0000100000 | Loss 0.025289 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:15 Epoch 4 | Batch 2438/3508 | Timestep 16470 | LR 0.0000100000 | Loss 0.058088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:17 Epoch 4 | Batch 2448/3508 | Timestep 16480 | LR 0.0000100000 | Loss 0.007761 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:19 Epoch 4 | Batch 2458/3508 | Timestep 16490 | LR 0.0000100000 | Loss 0.021680 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:22 Epoch 4 | Batch 2468/3508 | Timestep 16500 | LR 0.0000100000 | Loss 0.005430 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:24 Epoch 4 | Batch 2478/3508 | Timestep 16510 | LR 0.0000100000 | Loss 0.003256 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:26 Epoch 4 | Batch 2488/3508 | Timestep 16520 | LR 0.0000100000 | Loss 0.018891 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:28 Epoch 4 | Batch 2498/3508 | Timestep 16530 | LR 0.0000100000 | Loss 0.033295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:30 Epoch 4 | Batch 2508/3508 | Timestep 16540 | LR 0.0000100000 | Loss 0.039222 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:32 Epoch 4 | Batch 2518/3508 | Timestep 16550 | LR 0.0000100000 | Loss 0.029633 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:34 Epoch 4 | Batch 2528/3508 | Timestep 16560 | LR 0.0000100000 | Loss 0.057662 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:36 Epoch 4 | Batch 2538/3508 | Timestep 16570 | LR 0.0000100000 | Loss 0.053037 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:38 Epoch 4 | Batch 2548/3508 | Timestep 16580 | LR 0.0000100000 | Loss 0.019701 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:40 Epoch 4 | Batch 2558/3508 | Timestep 16590 | LR 0.0000100000 | Loss 0.048617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:42 Epoch 4 | Batch 2568/3508 | Timestep 16600 | LR 0.0000100000 | Loss 0.027057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:44 Epoch 4 | Batch 2578/3508 | Timestep 16610 | LR 0.0000100000 | Loss 0.031761 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:47 Epoch 4 | Batch 2588/3508 | Timestep 16620 | LR 0.0000100000 | Loss 0.011017 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:49 Epoch 4 | Batch 2598/3508 | Timestep 16630 | LR 0.0000100000 | Loss 0.009794 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:51 Epoch 4 | Batch 2608/3508 | Timestep 16640 | LR 0.0000100000 | Loss 0.034224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:55 Epoch 4 | Batch 2618/3508 | Timestep 16650 | LR 0.0000100000 | Loss 0.016340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:57 Epoch 4 | Batch 2628/3508 | Timestep 16660 | LR 0.0000100000 | Loss 0.021347 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:46:59 Epoch 4 | Batch 2638/3508 | Timestep 16670 | LR 0.0000100000 | Loss 0.014201 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:01 Epoch 4 | Batch 2648/3508 | Timestep 16680 | LR 0.0000100000 | Loss 0.001335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:03 Epoch 4 | Batch 2658/3508 | Timestep 16690 | LR 0.0000100000 | Loss 0.010270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:06 Epoch 4 | Batch 2668/3508 | Timestep 16700 | LR 0.0000100000 | Loss 0.006657 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:08 Epoch 4 | Batch 2678/3508 | Timestep 16710 | LR 0.0000100000 | Loss 0.020033 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:10 Epoch 4 | Batch 2688/3508 | Timestep 16720 | LR 0.0000100000 | Loss 0.034413 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:12 Epoch 4 | Batch 2698/3508 | Timestep 16730 | LR 0.0000100000 | Loss 0.019065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:14 Epoch 4 | Batch 2708/3508 | Timestep 16740 | LR 0.0000100000 | Loss 0.025897 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:16 Epoch 4 | Batch 2718/3508 | Timestep 16750 | LR 0.0000100000 | Loss 0.044227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:18 Epoch 4 | Batch 2728/3508 | Timestep 16760 | LR 0.0000100000 | Loss 0.025926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:21 Epoch 4 | Batch 2738/3508 | Timestep 16770 | LR 0.0000100000 | Loss 0.021593 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:23 Epoch 4 | Batch 2748/3508 | Timestep 16780 | LR 0.0000100000 | Loss 0.040601 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:25 Epoch 4 | Batch 2758/3508 | Timestep 16790 | LR 0.0000100000 | Loss 0.027836 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:27 Epoch 4 | Batch 2768/3508 | Timestep 16800 | LR 0.0000100000 | Loss 0.024814 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:29 Epoch 4 | Batch 2778/3508 | Timestep 16810 | LR 0.0000100000 | Loss 0.009526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:32 Epoch 4 | Batch 2788/3508 | Timestep 16820 | LR 0.0000100000 | Loss 0.004335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:34 Epoch 4 | Batch 2798/3508 | Timestep 16830 | LR 0.0000100000 | Loss 0.062532 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:36 Epoch 4 | Batch 2808/3508 | Timestep 16840 | LR 0.0000100000 | Loss 0.010069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:38 Epoch 4 | Batch 2818/3508 | Timestep 16850 | LR 0.0000100000 | Loss 0.022992 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:40 Epoch 4 | Batch 2828/3508 | Timestep 16860 | LR 0.0000100000 | Loss 0.073617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:41 Epoch 4 | Batch 2838/3508 | Timestep 16870 | LR 0.0000100000 | Loss 0.008427 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:44 Epoch 4 | Batch 2848/3508 | Timestep 16880 | LR 0.0000100000 | Loss 0.017835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:46 Epoch 4 | Batch 2858/3508 | Timestep 16890 | LR 0.0000100000 | Loss 0.010823 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:48 Epoch 4 | Batch 2868/3508 | Timestep 16900 | LR 0.0000100000 | Loss 0.024689 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:50 Epoch 4 | Batch 2878/3508 | Timestep 16910 | LR 0.0000100000 | Loss 0.015235 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:52 Epoch 4 | Batch 2888/3508 | Timestep 16920 | LR 0.0000100000 | Loss 0.034095 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:54 Epoch 4 | Batch 2898/3508 | Timestep 16930 | LR 0.0000100000 | Loss 0.036391 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:56 Epoch 4 | Batch 2908/3508 | Timestep 16940 | LR 0.0000100000 | Loss 0.070274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:47:58 Epoch 4 | Batch 2918/3508 | Timestep 16950 | LR 0.0000100000 | Loss 0.029802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:01 Epoch 4 | Batch 2928/3508 | Timestep 16960 | LR 0.0000100000 | Loss 0.027149 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:03 Epoch 4 | Batch 2938/3508 | Timestep 16970 | LR 0.0000100000 | Loss 0.010068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:04 Epoch 4 | Batch 2948/3508 | Timestep 16980 | LR 0.0000100000 | Loss 0.016245 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:07 Epoch 4 | Batch 2958/3508 | Timestep 16990 | LR 0.0000100000 | Loss 0.006077 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:09 Epoch 4 | Batch 2968/3508 | Timestep 17000 | LR 0.0000100000 | Loss 0.017141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:11 Epoch 4 | Batch 2978/3508 | Timestep 17010 | LR 0.0000100000 | Loss 0.074029 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:13 Epoch 4 | Batch 2988/3508 | Timestep 17020 | LR 0.0000100000 | Loss 0.011073 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:15 Epoch 4 | Batch 2998/3508 | Timestep 17030 | LR 0.0000100000 | Loss 0.009777 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:17 Epoch 4 | Batch 3008/3508 | Timestep 17040 | LR 0.0000100000 | Loss 0.050932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:19 Epoch 4 | Batch 3018/3508 | Timestep 17050 | LR 0.0000100000 | Loss 0.042975 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:21 Epoch 4 | Batch 3028/3508 | Timestep 17060 | LR 0.0000100000 | Loss 0.006427 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:23 Epoch 4 | Batch 3038/3508 | Timestep 17070 | LR 0.0000100000 | Loss 0.010116 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:26 Epoch 4 | Batch 3048/3508 | Timestep 17080 | LR 0.0000100000 | Loss 0.060340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:27 Epoch 4 | Batch 3058/3508 | Timestep 17090 | LR 0.0000100000 | Loss 0.016401 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:30 Epoch 4 | Batch 3068/3508 | Timestep 17100 | LR 0.0000100000 | Loss 0.011763 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:32 Epoch 4 | Batch 3078/3508 | Timestep 17110 | LR 0.0000100000 | Loss 0.041055 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:34 Epoch 4 | Batch 3088/3508 | Timestep 17120 | LR 0.0000100000 | Loss 0.020241 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:36 Epoch 4 | Batch 3098/3508 | Timestep 17130 | LR 0.0000100000 | Loss 0.020107 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:38 Epoch 4 | Batch 3108/3508 | Timestep 17140 | LR 0.0000100000 | Loss 0.017499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:40 Epoch 4 | Batch 3118/3508 | Timestep 17150 | LR 0.0000100000 | Loss 0.007234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:43 Epoch 4 | Batch 3128/3508 | Timestep 17160 | LR 0.0000100000 | Loss 0.017235 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:45 Epoch 4 | Batch 3138/3508 | Timestep 17170 | LR 0.0000100000 | Loss 0.008654 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:47 Epoch 4 | Batch 3148/3508 | Timestep 17180 | LR 0.0000100000 | Loss 0.011743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:49 Epoch 4 | Batch 3158/3508 | Timestep 17190 | LR 0.0000100000 | Loss 0.012352 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:52 Epoch 4 | Batch 3168/3508 | Timestep 17200 | LR 0.0000100000 | Loss 0.025586 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:53 Epoch 4 | Batch 3178/3508 | Timestep 17210 | LR 0.0000100000 | Loss 0.013501 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:56 Epoch 4 | Batch 3188/3508 | Timestep 17220 | LR 0.0000100000 | Loss 0.053263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:57 Epoch 4 | Batch 3198/3508 | Timestep 17230 | LR 0.0000100000 | Loss 0.027552 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:48:59 Epoch 4 | Batch 3208/3508 | Timestep 17240 | LR 0.0000100000 | Loss 0.019463 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:01 Epoch 4 | Batch 3218/3508 | Timestep 17250 | LR 0.0000100000 | Loss 0.029571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:03 Epoch 4 | Batch 3228/3508 | Timestep 17260 | LR 0.0000100000 | Loss 0.008107 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:06 Epoch 4 | Batch 3238/3508 | Timestep 17270 | LR 0.0000100000 | Loss 0.057660 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:08 Epoch 4 | Batch 3248/3508 | Timestep 17280 | LR 0.0000100000 | Loss 0.021915 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:10 Epoch 4 | Batch 3258/3508 | Timestep 17290 | LR 0.0000100000 | Loss 0.010326 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:13 Epoch 4 | Batch 3268/3508 | Timestep 17300 | LR 0.0000100000 | Loss 0.011780 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:15 Epoch 4 | Batch 3278/3508 | Timestep 17310 | LR 0.0000100000 | Loss 0.015696 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:17 Epoch 4 | Batch 3288/3508 | Timestep 17320 | LR 0.0000100000 | Loss 0.014607 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:19 Epoch 4 | Batch 3298/3508 | Timestep 17330 | LR 0.0000100000 | Loss 0.031167 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:21 Epoch 4 | Batch 3308/3508 | Timestep 17340 | LR 0.0000100000 | Loss 0.023941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:23 Epoch 4 | Batch 3318/3508 | Timestep 17350 | LR 0.0000100000 | Loss 0.037265 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:25 Epoch 4 | Batch 3328/3508 | Timestep 17360 | LR 0.0000100000 | Loss 0.038468 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:27 Epoch 4 | Batch 3338/3508 | Timestep 17370 | LR 0.0000100000 | Loss 0.017883 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:30 Epoch 4 | Batch 3348/3508 | Timestep 17380 | LR 0.0000100000 | Loss 0.005368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:31 Epoch 4 | Batch 3358/3508 | Timestep 17390 | LR 0.0000100000 | Loss 0.022271 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:33 Epoch 4 | Batch 3368/3508 | Timestep 17400 | LR 0.0000100000 | Loss 0.007872 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:35 Epoch 4 | Batch 3378/3508 | Timestep 17410 | LR 0.0000100000 | Loss 0.018803 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:37 Epoch 4 | Batch 3388/3508 | Timestep 17420 | LR 0.0000100000 | Loss 0.053920 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:40 Epoch 4 | Batch 3398/3508 | Timestep 17430 | LR 0.0000100000 | Loss 0.024707 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:42 Epoch 4 | Batch 3408/3508 | Timestep 17440 | LR 0.0000100000 | Loss 0.009707 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:44 Epoch 4 | Batch 3418/3508 | Timestep 17450 | LR 0.0000100000 | Loss 0.029179 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:47 Epoch 4 | Batch 3428/3508 | Timestep 17460 | LR 0.0000100000 | Loss 0.012216 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:49 Epoch 4 | Batch 3438/3508 | Timestep 17470 | LR 0.0000100000 | Loss 0.009270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:51 Epoch 4 | Batch 3448/3508 | Timestep 17480 | LR 0.0000100000 | Loss 0.007786 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:53 Epoch 4 | Batch 3458/3508 | Timestep 17490 | LR 0.0000100000 | Loss 0.033985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:55 Epoch 4 | Batch 3468/3508 | Timestep 17500 | LR 0.0000100000 | Loss 0.024589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:57 Epoch 4 | Batch 3478/3508 | Timestep 17510 | LR 0.0000100000 | Loss 0.023041 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:49:59 Epoch 4 | Batch 3488/3508 | Timestep 17520 | LR 0.0000100000 | Loss 0.022161 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:02 Epoch 4 | Batch 3498/3508 | Timestep 17530 | LR 0.0000100000 | Loss 0.037493 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:04 Epoch 4 | Batch 3508/3508 | Timestep 17540 | LR 0.0000100000 | Loss 0.001794 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:04 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 15:50:38 precision recall f1-score support CARDINAL 0.8865 0.7862 0.8333 159 CURR 0.5862 0.7727 0.6667 22 DATE 0.9301 0.9413 0.9357 1669 EVENT 0.6380 0.7597 0.6935 283 FAC 0.6857 0.8136 0.7442 118 GPE 0.9740 0.9631 0.9685 2140 LANGUAGE 0.6842 0.8125 0.7429 16 LAW 0.4545 0.7895 0.5769 19 LOC 0.7083 0.7556 0.7312 90 MONEY 0.6800 0.8500 0.7556 20 NORP 0.6736 0.7583 0.7135 509 OCC 0.8045 0.8710 0.8364 496 ORDINAL 0.9132 0.9439 0.9283 446 ORG 0.8943 0.9480 0.9204 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9415 0.9485 0.9450 679 PRODUCT 0.6000 0.3750 0.4615 8 QUANTITY 0.4000 0.6667 0.5000 3 TIME 0.6410 0.8065 0.7143 31 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.5385 0.6125 0.5731 80 micro avg 0.8813 0.9163 0.8984 8670 macro avg 0.7408 0.8059 0.7647 8670 weighted avg 0.8870 0.9163 0.9006 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:48 Epoch 4 | Timestep 17540 | Train Loss 0.027001 | Val Loss 0.052248 | F1 0.898439 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:50 Epoch 5 | Batch 10/3508 | Timestep 17550 | LR 0.0000100000 | Loss 0.057127 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:52 Epoch 5 | Batch 20/3508 | Timestep 17560 | LR 0.0000100000 | Loss 0.019513 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:55 Epoch 5 | Batch 30/3508 | Timestep 17570 | LR 0.0000100000 | Loss 0.027809 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:57 Epoch 5 | Batch 40/3508 | Timestep 17580 | LR 0.0000100000 | Loss 0.009423 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:50:59 Epoch 5 | Batch 50/3508 | Timestep 17590 | LR 0.0000100000 | Loss 0.003611 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:02 Epoch 5 | Batch 60/3508 | Timestep 17600 | LR 0.0000100000 | Loss 0.020898 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:04 Epoch 5 | Batch 70/3508 | Timestep 17610 | LR 0.0000100000 | Loss 0.014980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:06 Epoch 5 | Batch 80/3508 | Timestep 17620 | LR 0.0000100000 | Loss 0.018488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:08 Epoch 5 | Batch 90/3508 | Timestep 17630 | LR 0.0000100000 | Loss 0.037195 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:10 Epoch 5 | Batch 100/3508 | Timestep 17640 | LR 0.0000100000 | Loss 0.009352 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:13 Epoch 5 | Batch 110/3508 | Timestep 17650 | LR 0.0000100000 | Loss 0.007485 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:15 Epoch 5 | Batch 120/3508 | Timestep 17660 | LR 0.0000100000 | Loss 0.027466 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:16 Epoch 5 | Batch 130/3508 | Timestep 17670 | LR 0.0000100000 | Loss 0.013991 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:19 Epoch 5 | Batch 140/3508 | Timestep 17680 | LR 0.0000100000 | Loss 0.043481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:21 Epoch 5 | Batch 150/3508 | Timestep 17690 | LR 0.0000100000 | Loss 0.045118 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:23 Epoch 5 | Batch 160/3508 | Timestep 17700 | LR 0.0000100000 | Loss 0.016133 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:25 Epoch 5 | Batch 170/3508 | Timestep 17710 | LR 0.0000100000 | Loss 0.012558 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:26 Epoch 5 | Batch 180/3508 | Timestep 17720 | LR 0.0000100000 | Loss 0.020596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:28 Epoch 5 | Batch 190/3508 | Timestep 17730 | LR 0.0000100000 | Loss 0.016155 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:30 Epoch 5 | Batch 200/3508 | Timestep 17740 | LR 0.0000100000 | Loss 0.007767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:32 Epoch 5 | Batch 210/3508 | Timestep 17750 | LR 0.0000100000 | Loss 0.014407 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:35 Epoch 5 | Batch 220/3508 | Timestep 17760 | LR 0.0000100000 | Loss 0.017547 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:37 Epoch 5 | Batch 230/3508 | Timestep 17770 | LR 0.0000100000 | Loss 0.007198 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:39 Epoch 5 | Batch 240/3508 | Timestep 17780 | LR 0.0000100000 | Loss 0.015941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:41 Epoch 5 | Batch 250/3508 | Timestep 17790 | LR 0.0000100000 | Loss 0.020553 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:43 Epoch 5 | Batch 260/3508 | Timestep 17800 | LR 0.0000100000 | Loss 0.015476 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:45 Epoch 5 | Batch 270/3508 | Timestep 17810 | LR 0.0000100000 | Loss 0.040852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:48 Epoch 5 | Batch 280/3508 | Timestep 17820 | LR 0.0000100000 | Loss 0.019811 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:50 Epoch 5 | Batch 290/3508 | Timestep 17830 | LR 0.0000100000 | Loss 0.015042 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:52 Epoch 5 | Batch 300/3508 | Timestep 17840 | LR 0.0000100000 | Loss 0.003471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:53 Epoch 5 | Batch 310/3508 | Timestep 17850 | LR 0.0000100000 | Loss 0.018897 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:55 Epoch 5 | Batch 320/3508 | Timestep 17860 | LR 0.0000100000 | Loss 0.025196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:51:58 Epoch 5 | Batch 330/3508 | Timestep 17870 | LR 0.0000100000 | Loss 0.025068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:00 Epoch 5 | Batch 340/3508 | Timestep 17880 | LR 0.0000100000 | Loss 0.012687 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:02 Epoch 5 | Batch 350/3508 | Timestep 17890 | LR 0.0000100000 | Loss 0.002298 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:04 Epoch 5 | Batch 360/3508 | Timestep 17900 | LR 0.0000100000 | Loss 0.033007 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:06 Epoch 5 | Batch 370/3508 | Timestep 17910 | LR 0.0000100000 | Loss 0.036883 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:09 Epoch 5 | Batch 380/3508 | Timestep 17920 | LR 0.0000100000 | Loss 0.011124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:11 Epoch 5 | Batch 390/3508 | Timestep 17930 | LR 0.0000100000 | Loss 0.019344 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:13 Epoch 5 | Batch 400/3508 | Timestep 17940 | LR 0.0000100000 | Loss 0.014402 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:14 Epoch 5 | Batch 410/3508 | Timestep 17950 | LR 0.0000100000 | Loss 0.006797 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:17 Epoch 5 | Batch 420/3508 | Timestep 17960 | LR 0.0000100000 | Loss 0.007065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:19 Epoch 5 | Batch 430/3508 | Timestep 17970 | LR 0.0000100000 | Loss 0.012281 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:21 Epoch 5 | Batch 440/3508 | Timestep 17980 | LR 0.0000100000 | Loss 0.024002 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:23 Epoch 5 | Batch 450/3508 | Timestep 17990 | LR 0.0000100000 | Loss 0.021619 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:26 Epoch 5 | Batch 460/3508 | Timestep 18000 | LR 0.0000100000 | Loss 0.021249 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:28 Epoch 5 | Batch 470/3508 | Timestep 18010 | LR 0.0000100000 | Loss 0.009899 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:29 Epoch 5 | Batch 480/3508 | Timestep 18020 | LR 0.0000100000 | Loss 0.027848 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:32 Epoch 5 | Batch 490/3508 | Timestep 18030 | LR 0.0000100000 | Loss 0.004317 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:34 Epoch 5 | Batch 500/3508 | Timestep 18040 | LR 0.0000100000 | Loss 0.034627 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:36 Epoch 5 | Batch 510/3508 | Timestep 18050 | LR 0.0000100000 | Loss 0.087132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:38 Epoch 5 | Batch 520/3508 | Timestep 18060 | LR 0.0000100000 | Loss 0.005519 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:40 Epoch 5 | Batch 530/3508 | Timestep 18070 | LR 0.0000100000 | Loss 0.013400 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:43 Epoch 5 | Batch 540/3508 | Timestep 18080 | LR 0.0000100000 | Loss 0.007525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:45 Epoch 5 | Batch 550/3508 | Timestep 18090 | LR 0.0000100000 | Loss 0.027096 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:47 Epoch 5 | Batch 560/3508 | Timestep 18100 | LR 0.0000100000 | Loss 0.017056 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:49 Epoch 5 | Batch 570/3508 | Timestep 18110 | LR 0.0000100000 | Loss 0.011773 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:52 Epoch 5 | Batch 580/3508 | Timestep 18120 | LR 0.0000100000 | Loss 0.003390 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:54 Epoch 5 | Batch 590/3508 | Timestep 18130 | LR 0.0000100000 | Loss 0.012319 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:56 Epoch 5 | Batch 600/3508 | Timestep 18140 | LR 0.0000100000 | Loss 0.002184 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:52:58 Epoch 5 | Batch 610/3508 | Timestep 18150 | LR 0.0000100000 | Loss 0.013534 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:00 Epoch 5 | Batch 620/3508 | Timestep 18160 | LR 0.0000100000 | Loss 0.025065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:02 Epoch 5 | Batch 630/3508 | Timestep 18170 | LR 0.0000100000 | Loss 0.034582 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:05 Epoch 5 | Batch 640/3508 | Timestep 18180 | LR 0.0000100000 | Loss 0.002696 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:07 Epoch 5 | Batch 650/3508 | Timestep 18190 | LR 0.0000100000 | Loss 0.032909 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:09 Epoch 5 | Batch 660/3508 | Timestep 18200 | LR 0.0000100000 | Loss 0.034012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:11 Epoch 5 | Batch 670/3508 | Timestep 18210 | LR 0.0000100000 | Loss 0.014365 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:14 Epoch 5 | Batch 680/3508 | Timestep 18220 | LR 0.0000100000 | Loss 0.004529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:17 Epoch 5 | Batch 690/3508 | Timestep 18230 | LR 0.0000100000 | Loss 0.007131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:18 Epoch 5 | Batch 700/3508 | Timestep 18240 | LR 0.0000100000 | Loss 0.006311 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:21 Epoch 5 | Batch 710/3508 | Timestep 18250 | LR 0.0000100000 | Loss 0.013947 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:23 Epoch 5 | Batch 720/3508 | Timestep 18260 | LR 0.0000100000 | Loss 0.031748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:25 Epoch 5 | Batch 730/3508 | Timestep 18270 | LR 0.0000100000 | Loss 0.002190 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:28 Epoch 5 | Batch 740/3508 | Timestep 18280 | LR 0.0000100000 | Loss 0.062749 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:30 Epoch 5 | Batch 750/3508 | Timestep 18290 | LR 0.0000100000 | Loss 0.019411 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:33 Epoch 5 | Batch 760/3508 | Timestep 18300 | LR 0.0000100000 | Loss 0.009378 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:36 Epoch 5 | Batch 770/3508 | Timestep 18310 | LR 0.0000100000 | Loss 0.006274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:38 Epoch 5 | Batch 780/3508 | Timestep 18320 | LR 0.0000100000 | Loss 0.020643 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:40 Epoch 5 | Batch 790/3508 | Timestep 18330 | LR 0.0000100000 | Loss 0.020005 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:42 Epoch 5 | Batch 800/3508 | Timestep 18340 | LR 0.0000100000 | Loss 0.033319 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:44 Epoch 5 | Batch 810/3508 | Timestep 18350 | LR 0.0000100000 | Loss 0.015943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:46 Epoch 5 | Batch 820/3508 | Timestep 18360 | LR 0.0000100000 | Loss 0.014774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:48 Epoch 5 | Batch 830/3508 | Timestep 18370 | LR 0.0000100000 | Loss 0.009217 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:50 Epoch 5 | Batch 840/3508 | Timestep 18380 | LR 0.0000100000 | Loss 0.013630 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:52 Epoch 5 | Batch 850/3508 | Timestep 18390 | LR 0.0000100000 | Loss 0.003110 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:54 Epoch 5 | Batch 860/3508 | Timestep 18400 | LR 0.0000100000 | Loss 0.024299 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:56 Epoch 5 | Batch 870/3508 | Timestep 18410 | LR 0.0000100000 | Loss 0.009425 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:53:58 Epoch 5 | Batch 880/3508 | Timestep 18420 | LR 0.0000100000 | Loss 0.033418 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:00 Epoch 5 | Batch 890/3508 | Timestep 18430 | LR 0.0000100000 | Loss 0.036273 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:02 Epoch 5 | Batch 900/3508 | Timestep 18440 | LR 0.0000100000 | Loss 0.009686 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:05 Epoch 5 | Batch 910/3508 | Timestep 18450 | LR 0.0000100000 | Loss 0.030838 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:07 Epoch 5 | Batch 920/3508 | Timestep 18460 | LR 0.0000100000 | Loss 0.020284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:09 Epoch 5 | Batch 930/3508 | Timestep 18470 | LR 0.0000100000 | Loss 0.017328 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:11 Epoch 5 | Batch 940/3508 | Timestep 18480 | LR 0.0000100000 | Loss 0.057956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:13 Epoch 5 | Batch 950/3508 | Timestep 18490 | LR 0.0000100000 | Loss 0.017410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:15 Epoch 5 | Batch 960/3508 | Timestep 18500 | LR 0.0000100000 | Loss 0.024325 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:17 Epoch 5 | Batch 970/3508 | Timestep 18510 | LR 0.0000100000 | Loss 0.002604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:19 Epoch 5 | Batch 980/3508 | Timestep 18520 | LR 0.0000100000 | Loss 0.027155 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:22 Epoch 5 | Batch 990/3508 | Timestep 18530 | LR 0.0000100000 | Loss 0.044851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:24 Epoch 5 | Batch 1000/3508 | Timestep 18540 | LR 0.0000100000 | Loss 0.010743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:26 Epoch 5 | Batch 1010/3508 | Timestep 18550 | LR 0.0000100000 | Loss 0.063996 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:29 Epoch 5 | Batch 1020/3508 | Timestep 18560 | LR 0.0000100000 | Loss 0.026240 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:31 Epoch 5 | Batch 1030/3508 | Timestep 18570 | LR 0.0000100000 | Loss 0.028405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:33 Epoch 5 | Batch 1040/3508 | Timestep 18580 | LR 0.0000100000 | Loss 0.002810 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:35 Epoch 5 | Batch 1050/3508 | Timestep 18590 | LR 0.0000100000 | Loss 0.005008 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:37 Epoch 5 | Batch 1060/3508 | Timestep 18600 | LR 0.0000100000 | Loss 0.003784 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:39 Epoch 5 | Batch 1070/3508 | Timestep 18610 | LR 0.0000100000 | Loss 0.003101 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:41 Epoch 5 | Batch 1080/3508 | Timestep 18620 | LR 0.0000100000 | Loss 0.038622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:43 Epoch 5 | Batch 1090/3508 | Timestep 18630 | LR 0.0000100000 | Loss 0.005748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:46 Epoch 5 | Batch 1100/3508 | Timestep 18640 | LR 0.0000100000 | Loss 0.003409 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:48 Epoch 5 | Batch 1110/3508 | Timestep 18650 | LR 0.0000100000 | Loss 0.026589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:50 Epoch 5 | Batch 1120/3508 | Timestep 18660 | LR 0.0000100000 | Loss 0.007784 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:52 Epoch 5 | Batch 1130/3508 | Timestep 18670 | LR 0.0000100000 | Loss 0.058398 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:54 Epoch 5 | Batch 1140/3508 | Timestep 18680 | LR 0.0000100000 | Loss 0.009688 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:56 Epoch 5 | Batch 1150/3508 | Timestep 18690 | LR 0.0000100000 | Loss 0.009838 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:54:58 Epoch 5 | Batch 1160/3508 | Timestep 18700 | LR 0.0000100000 | Loss 0.024453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:01 Epoch 5 | Batch 1170/3508 | Timestep 18710 | LR 0.0000100000 | Loss 0.022137 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:03 Epoch 5 | Batch 1180/3508 | Timestep 18720 | LR 0.0000100000 | Loss 0.038227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:05 Epoch 5 | Batch 1190/3508 | Timestep 18730 | LR 0.0000100000 | Loss 0.035015 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:07 Epoch 5 | Batch 1200/3508 | Timestep 18740 | LR 0.0000100000 | Loss 0.014568 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:09 Epoch 5 | Batch 1210/3508 | Timestep 18750 | LR 0.0000100000 | Loss 0.010387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:12 Epoch 5 | Batch 1220/3508 | Timestep 18760 | LR 0.0000100000 | Loss 0.011132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:15 Epoch 5 | Batch 1230/3508 | Timestep 18770 | LR 0.0000100000 | Loss 0.039678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:18 Epoch 5 | Batch 1240/3508 | Timestep 18780 | LR 0.0000100000 | Loss 0.003547 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:20 Epoch 5 | Batch 1250/3508 | Timestep 18790 | LR 0.0000100000 | Loss 0.008512 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:22 Epoch 5 | Batch 1260/3508 | Timestep 18800 | LR 0.0000100000 | Loss 0.010023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:24 Epoch 5 | Batch 1270/3508 | Timestep 18810 | LR 0.0000100000 | Loss 0.051382 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:26 Epoch 5 | Batch 1280/3508 | Timestep 18820 | LR 0.0000100000 | Loss 0.007682 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:29 Epoch 5 | Batch 1290/3508 | Timestep 18830 | LR 0.0000100000 | Loss 0.020697 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:31 Epoch 5 | Batch 1300/3508 | Timestep 18840 | LR 0.0000100000 | Loss 0.019376 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:33 Epoch 5 | Batch 1310/3508 | Timestep 18850 | LR 0.0000100000 | Loss 0.004814 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:35 Epoch 5 | Batch 1320/3508 | Timestep 18860 | LR 0.0000100000 | Loss 0.017508 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:37 Epoch 5 | Batch 1330/3508 | Timestep 18870 | LR 0.0000100000 | Loss 0.013284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:39 Epoch 5 | Batch 1340/3508 | Timestep 18880 | LR 0.0000100000 | Loss 0.060599 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:41 Epoch 5 | Batch 1350/3508 | Timestep 18890 | LR 0.0000100000 | Loss 0.022466 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:44 Epoch 5 | Batch 1360/3508 | Timestep 18900 | LR 0.0000100000 | Loss 0.006624 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:46 Epoch 5 | Batch 1370/3508 | Timestep 18910 | LR 0.0000100000 | Loss 0.003182 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:48 Epoch 5 | Batch 1380/3508 | Timestep 18920 | LR 0.0000100000 | Loss 0.004886 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:50 Epoch 5 | Batch 1390/3508 | Timestep 18930 | LR 0.0000100000 | Loss 0.016294 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:52 Epoch 5 | Batch 1400/3508 | Timestep 18940 | LR 0.0000100000 | Loss 0.003925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:54 Epoch 5 | Batch 1410/3508 | Timestep 18950 | LR 0.0000100000 | Loss 0.012379 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:56 Epoch 5 | Batch 1420/3508 | Timestep 18960 | LR 0.0000100000 | Loss 0.011644 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:55:58 Epoch 5 | Batch 1430/3508 | Timestep 18970 | LR 0.0000100000 | Loss 0.010520 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:01 Epoch 5 | Batch 1440/3508 | Timestep 18980 | LR 0.0000100000 | Loss 0.029793 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:03 Epoch 5 | Batch 1450/3508 | Timestep 18990 | LR 0.0000100000 | Loss 0.029981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:05 Epoch 5 | Batch 1460/3508 | Timestep 19000 | LR 0.0000100000 | Loss 0.014060 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:07 Epoch 5 | Batch 1470/3508 | Timestep 19010 | LR 0.0000100000 | Loss 0.007943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:09 Epoch 5 | Batch 1480/3508 | Timestep 19020 | LR 0.0000100000 | Loss 0.008170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:11 Epoch 5 | Batch 1490/3508 | Timestep 19030 | LR 0.0000100000 | Loss 0.022769 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:13 Epoch 5 | Batch 1500/3508 | Timestep 19040 | LR 0.0000100000 | Loss 0.039837 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:15 Epoch 5 | Batch 1510/3508 | Timestep 19050 | LR 0.0000100000 | Loss 0.005143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:17 Epoch 5 | Batch 1520/3508 | Timestep 19060 | LR 0.0000100000 | Loss 0.038137 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:19 Epoch 5 | Batch 1530/3508 | Timestep 19070 | LR 0.0000100000 | Loss 0.008565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:21 Epoch 5 | Batch 1540/3508 | Timestep 19080 | LR 0.0000100000 | Loss 0.069103 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:23 Epoch 5 | Batch 1550/3508 | Timestep 19090 | LR 0.0000100000 | Loss 0.011263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:25 Epoch 5 | Batch 1560/3508 | Timestep 19100 | LR 0.0000100000 | Loss 0.049344 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:27 Epoch 5 | Batch 1570/3508 | Timestep 19110 | LR 0.0000100000 | Loss 0.003844 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:29 Epoch 5 | Batch 1580/3508 | Timestep 19120 | LR 0.0000100000 | Loss 0.048842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:32 Epoch 5 | Batch 1590/3508 | Timestep 19130 | LR 0.0000100000 | Loss 0.016609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:34 Epoch 5 | Batch 1600/3508 | Timestep 19140 | LR 0.0000100000 | Loss 0.026418 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:35 Epoch 5 | Batch 1610/3508 | Timestep 19150 | LR 0.0000100000 | Loss 0.003561 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:38 Epoch 5 | Batch 1620/3508 | Timestep 19160 | LR 0.0000100000 | Loss 0.007247 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:40 Epoch 5 | Batch 1630/3508 | Timestep 19170 | LR 0.0000100000 | Loss 0.016340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:42 Epoch 5 | Batch 1640/3508 | Timestep 19180 | LR 0.0000100000 | Loss 0.019135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:45 Epoch 5 | Batch 1650/3508 | Timestep 19190 | LR 0.0000100000 | Loss 0.024999 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:47 Epoch 5 | Batch 1660/3508 | Timestep 19200 | LR 0.0000100000 | Loss 0.010570 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:49 Epoch 5 | Batch 1670/3508 | Timestep 19210 | LR 0.0000100000 | Loss 0.033986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:51 Epoch 5 | Batch 1680/3508 | Timestep 19220 | LR 0.0000100000 | Loss 0.004758 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:54 Epoch 5 | Batch 1690/3508 | Timestep 19230 | LR 0.0000100000 | Loss 0.032510 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:56 Epoch 5 | Batch 1700/3508 | Timestep 19240 | LR 0.0000100000 | Loss 0.032690 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:56:58 Epoch 5 | Batch 1710/3508 | Timestep 19250 | LR 0.0000100000 | Loss 0.021463 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:00 Epoch 5 | Batch 1720/3508 | Timestep 19260 | LR 0.0000100000 | Loss 0.012394 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:02 Epoch 5 | Batch 1730/3508 | Timestep 19270 | LR 0.0000100000 | Loss 0.035109 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:04 Epoch 5 | Batch 1740/3508 | Timestep 19280 | LR 0.0000100000 | Loss 0.012441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:07 Epoch 5 | Batch 1750/3508 | Timestep 19290 | LR 0.0000100000 | Loss 0.027865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:09 Epoch 5 | Batch 1760/3508 | Timestep 19300 | LR 0.0000100000 | Loss 0.035234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:11 Epoch 5 | Batch 1770/3508 | Timestep 19310 | LR 0.0000100000 | Loss 0.025565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:13 Epoch 5 | Batch 1780/3508 | Timestep 19320 | LR 0.0000100000 | Loss 0.015913 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:15 Epoch 5 | Batch 1790/3508 | Timestep 19330 | LR 0.0000100000 | Loss 0.008962 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:17 Epoch 5 | Batch 1800/3508 | Timestep 19340 | LR 0.0000100000 | Loss 0.011966 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:20 Epoch 5 | Batch 1810/3508 | Timestep 19350 | LR 0.0000100000 | Loss 0.054245 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:22 Epoch 5 | Batch 1820/3508 | Timestep 19360 | LR 0.0000100000 | Loss 0.036094 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:24 Epoch 5 | Batch 1830/3508 | Timestep 19370 | LR 0.0000100000 | Loss 0.021735 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:26 Epoch 5 | Batch 1840/3508 | Timestep 19380 | LR 0.0000100000 | Loss 0.009967 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:28 Epoch 5 | Batch 1850/3508 | Timestep 19390 | LR 0.0000100000 | Loss 0.003519 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:31 Epoch 5 | Batch 1860/3508 | Timestep 19400 | LR 0.0000100000 | Loss 0.016655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:33 Epoch 5 | Batch 1870/3508 | Timestep 19410 | LR 0.0000100000 | Loss 0.008878 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:35 Epoch 5 | Batch 1880/3508 | Timestep 19420 | LR 0.0000100000 | Loss 0.052075 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:36 Epoch 5 | Batch 1890/3508 | Timestep 19430 | LR 0.0000100000 | Loss 0.045068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:38 Epoch 5 | Batch 1900/3508 | Timestep 19440 | LR 0.0000100000 | Loss 0.008756 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:41 Epoch 5 | Batch 1910/3508 | Timestep 19450 | LR 0.0000100000 | Loss 0.011011 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:42 Epoch 5 | Batch 1920/3508 | Timestep 19460 | LR 0.0000100000 | Loss 0.007629 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:45 Epoch 5 | Batch 1930/3508 | Timestep 19470 | LR 0.0000100000 | Loss 0.001703 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:47 Epoch 5 | Batch 1940/3508 | Timestep 19480 | LR 0.0000100000 | Loss 0.015453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:48 Epoch 5 | Batch 1950/3508 | Timestep 19490 | LR 0.0000100000 | Loss 0.016156 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:50 Epoch 5 | Batch 1960/3508 | Timestep 19500 | LR 0.0000100000 | Loss 0.008471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:52 Epoch 5 | Batch 1970/3508 | Timestep 19510 | LR 0.0000100000 | Loss 0.010434 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:54 Epoch 5 | Batch 1980/3508 | Timestep 19520 | LR 0.0000100000 | Loss 0.006986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:56 Epoch 5 | Batch 1990/3508 | Timestep 19530 | LR 0.0000100000 | Loss 0.027199 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:57:58 Epoch 5 | Batch 2000/3508 | Timestep 19540 | LR 0.0000100000 | Loss 0.029124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:00 Epoch 5 | Batch 2010/3508 | Timestep 19550 | LR 0.0000100000 | Loss 0.008502 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:02 Epoch 5 | Batch 2020/3508 | Timestep 19560 | LR 0.0000100000 | Loss 0.004650 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:04 Epoch 5 | Batch 2030/3508 | Timestep 19570 | LR 0.0000100000 | Loss 0.014604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:06 Epoch 5 | Batch 2040/3508 | Timestep 19580 | LR 0.0000100000 | Loss 0.015889 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:08 Epoch 5 | Batch 2050/3508 | Timestep 19590 | LR 0.0000100000 | Loss 0.015999 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:10 Epoch 5 | Batch 2060/3508 | Timestep 19600 | LR 0.0000100000 | Loss 0.010959 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:12 Epoch 5 | Batch 2070/3508 | Timestep 19610 | LR 0.0000100000 | Loss 0.004802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:15 Epoch 5 | Batch 2080/3508 | Timestep 19620 | LR 0.0000100000 | Loss 0.031232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:17 Epoch 5 | Batch 2090/3508 | Timestep 19630 | LR 0.0000100000 | Loss 0.034003 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:19 Epoch 5 | Batch 2100/3508 | Timestep 19640 | LR 0.0000100000 | Loss 0.019105 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:21 Epoch 5 | Batch 2110/3508 | Timestep 19650 | LR 0.0000100000 | Loss 0.006620 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:23 Epoch 5 | Batch 2120/3508 | Timestep 19660 | LR 0.0000100000 | Loss 0.018615 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:26 Epoch 5 | Batch 2130/3508 | Timestep 19670 | LR 0.0000100000 | Loss 0.029448 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:28 Epoch 5 | Batch 2140/3508 | Timestep 19680 | LR 0.0000100000 | Loss 0.030164 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:30 Epoch 5 | Batch 2150/3508 | Timestep 19690 | LR 0.0000100000 | Loss 0.038611 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:32 Epoch 5 | Batch 2160/3508 | Timestep 19700 | LR 0.0000100000 | Loss 0.020181 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:35 Epoch 5 | Batch 2170/3508 | Timestep 19710 | LR 0.0000100000 | Loss 0.001104 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:37 Epoch 5 | Batch 2180/3508 | Timestep 19720 | LR 0.0000100000 | Loss 0.089507 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:39 Epoch 5 | Batch 2190/3508 | Timestep 19730 | LR 0.0000100000 | Loss 0.046599 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:41 Epoch 5 | Batch 2200/3508 | Timestep 19740 | LR 0.0000100000 | Loss 0.006312 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:43 Epoch 5 | Batch 2210/3508 | Timestep 19750 | LR 0.0000100000 | Loss 0.021037 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:46 Epoch 5 | Batch 2220/3508 | Timestep 19760 | LR 0.0000100000 | Loss 0.028847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:48 Epoch 5 | Batch 2230/3508 | Timestep 19770 | LR 0.0000100000 | Loss 0.041339 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:50 Epoch 5 | Batch 2240/3508 | Timestep 19780 | LR 0.0000100000 | Loss 0.014246 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:52 Epoch 5 | Batch 2250/3508 | Timestep 19790 | LR 0.0000100000 | Loss 0.028385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:54 Epoch 5 | Batch 2260/3508 | Timestep 19800 | LR 0.0000100000 | Loss 0.015410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:56 Epoch 5 | Batch 2270/3508 | Timestep 19810 | LR 0.0000100000 | Loss 0.044355 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:58:58 Epoch 5 | Batch 2280/3508 | Timestep 19820 | LR 0.0000100000 | Loss 0.005753 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:00 Epoch 5 | Batch 2290/3508 | Timestep 19830 | LR 0.0000100000 | Loss 0.004114 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:02 Epoch 5 | Batch 2300/3508 | Timestep 19840 | LR 0.0000100000 | Loss 0.036086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:05 Epoch 5 | Batch 2310/3508 | Timestep 19850 | LR 0.0000100000 | Loss 0.016958 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:07 Epoch 5 | Batch 2320/3508 | Timestep 19860 | LR 0.0000100000 | Loss 0.014075 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:09 Epoch 5 | Batch 2330/3508 | Timestep 19870 | LR 0.0000100000 | Loss 0.015243 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:11 Epoch 5 | Batch 2340/3508 | Timestep 19880 | LR 0.0000100000 | Loss 0.013453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:13 Epoch 5 | Batch 2350/3508 | Timestep 19890 | LR 0.0000100000 | Loss 0.010655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:16 Epoch 5 | Batch 2360/3508 | Timestep 19900 | LR 0.0000100000 | Loss 0.015724 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:18 Epoch 5 | Batch 2370/3508 | Timestep 19910 | LR 0.0000100000 | Loss 0.040969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:20 Epoch 5 | Batch 2380/3508 | Timestep 19920 | LR 0.0000100000 | Loss 0.009504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:23 Epoch 5 | Batch 2390/3508 | Timestep 19930 | LR 0.0000100000 | Loss 0.020893 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:26 Epoch 5 | Batch 2400/3508 | Timestep 19940 | LR 0.0000100000 | Loss 0.027882 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:28 Epoch 5 | Batch 2410/3508 | Timestep 19950 | LR 0.0000100000 | Loss 0.018240 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:30 Epoch 5 | Batch 2420/3508 | Timestep 19960 | LR 0.0000100000 | Loss 0.014166 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:32 Epoch 5 | Batch 2430/3508 | Timestep 19970 | LR 0.0000100000 | Loss 0.068499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:34 Epoch 5 | Batch 2440/3508 | Timestep 19980 | LR 0.0000100000 | Loss 0.034063 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:37 Epoch 5 | Batch 2450/3508 | Timestep 19990 | LR 0.0000100000 | Loss 0.020971 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:39 Epoch 5 | Batch 2460/3508 | Timestep 20000 | LR 0.0000100000 | Loss 0.001762 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:41 Epoch 5 | Batch 2470/3508 | Timestep 20010 | LR 0.0000100000 | Loss 0.058704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:43 Epoch 5 | Batch 2480/3508 | Timestep 20020 | LR 0.0000100000 | Loss 0.053069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:45 Epoch 5 | Batch 2490/3508 | Timestep 20030 | LR 0.0000100000 | Loss 0.004521 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:47 Epoch 5 | Batch 2500/3508 | Timestep 20040 | LR 0.0000100000 | Loss 0.007743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:49 Epoch 5 | Batch 2510/3508 | Timestep 20050 | LR 0.0000100000 | Loss 0.019300 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:51 Epoch 5 | Batch 2520/3508 | Timestep 20060 | LR 0.0000100000 | Loss 0.019178 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:53 Epoch 5 | Batch 2530/3508 | Timestep 20070 | LR 0.0000100000 | Loss 0.010210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:55 Epoch 5 | Batch 2540/3508 | Timestep 20080 | LR 0.0000100000 | Loss 0.031097 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 15:59:58 Epoch 5 | Batch 2550/3508 | Timestep 20090 | LR 0.0000100000 | Loss 0.024211 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:00 Epoch 5 | Batch 2560/3508 | Timestep 20100 | LR 0.0000100000 | Loss 0.019592 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:02 Epoch 5 | Batch 2570/3508 | Timestep 20110 | LR 0.0000100000 | Loss 0.013364 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:04 Epoch 5 | Batch 2580/3508 | Timestep 20120 | LR 0.0000100000 | Loss 0.006775 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:07 Epoch 5 | Batch 2590/3508 | Timestep 20130 | LR 0.0000100000 | Loss 0.015644 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:09 Epoch 5 | Batch 2600/3508 | Timestep 20140 | LR 0.0000100000 | Loss 0.003197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:10 Epoch 5 | Batch 2610/3508 | Timestep 20150 | LR 0.0000100000 | Loss 0.006868 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:12 Epoch 5 | Batch 2620/3508 | Timestep 20160 | LR 0.0000100000 | Loss 0.008042 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:15 Epoch 5 | Batch 2630/3508 | Timestep 20170 | LR 0.0000100000 | Loss 0.018709 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:17 Epoch 5 | Batch 2640/3508 | Timestep 20180 | LR 0.0000100000 | Loss 0.016632 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:19 Epoch 5 | Batch 2650/3508 | Timestep 20190 | LR 0.0000100000 | Loss 0.055741 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:21 Epoch 5 | Batch 2660/3508 | Timestep 20200 | LR 0.0000100000 | Loss 0.006111 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:23 Epoch 5 | Batch 2670/3508 | Timestep 20210 | LR 0.0000100000 | Loss 0.016441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:26 Epoch 5 | Batch 2680/3508 | Timestep 20220 | LR 0.0000100000 | Loss 0.012757 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:28 Epoch 5 | Batch 2690/3508 | Timestep 20230 | LR 0.0000100000 | Loss 0.009385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:30 Epoch 5 | Batch 2700/3508 | Timestep 20240 | LR 0.0000100000 | Loss 0.018039 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:32 Epoch 5 | Batch 2710/3508 | Timestep 20250 | LR 0.0000100000 | Loss 0.017669 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:34 Epoch 5 | Batch 2720/3508 | Timestep 20260 | LR 0.0000100000 | Loss 0.012208 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:36 Epoch 5 | Batch 2730/3508 | Timestep 20270 | LR 0.0000100000 | Loss 0.006697 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:38 Epoch 5 | Batch 2740/3508 | Timestep 20280 | LR 0.0000100000 | Loss 0.066905 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:40 Epoch 5 | Batch 2750/3508 | Timestep 20290 | LR 0.0000100000 | Loss 0.003044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:43 Epoch 5 | Batch 2760/3508 | Timestep 20300 | LR 0.0000100000 | Loss 0.038444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:45 Epoch 5 | Batch 2770/3508 | Timestep 20310 | LR 0.0000100000 | Loss 0.034086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:47 Epoch 5 | Batch 2780/3508 | Timestep 20320 | LR 0.0000100000 | Loss 0.016335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:49 Epoch 5 | Batch 2790/3508 | Timestep 20330 | LR 0.0000100000 | Loss 0.011523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:51 Epoch 5 | Batch 2800/3508 | Timestep 20340 | LR 0.0000100000 | Loss 0.013110 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:54 Epoch 5 | Batch 2810/3508 | Timestep 20350 | LR 0.0000100000 | Loss 0.014638 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:56 Epoch 5 | Batch 2820/3508 | Timestep 20360 | LR 0.0000100000 | Loss 0.014946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:57 Epoch 5 | Batch 2830/3508 | Timestep 20370 | LR 0.0000100000 | Loss 0.021548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:00:59 Epoch 5 | Batch 2840/3508 | Timestep 20380 | LR 0.0000100000 | Loss 0.003982 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:02 Epoch 5 | Batch 2850/3508 | Timestep 20390 | LR 0.0000100000 | Loss 0.019581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:04 Epoch 5 | Batch 2860/3508 | Timestep 20400 | LR 0.0000100000 | Loss 0.019399 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:06 Epoch 5 | Batch 2870/3508 | Timestep 20410 | LR 0.0000100000 | Loss 0.039194 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:08 Epoch 5 | Batch 2880/3508 | Timestep 20420 | LR 0.0000100000 | Loss 0.019807 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:10 Epoch 5 | Batch 2890/3508 | Timestep 20430 | LR 0.0000100000 | Loss 0.038267 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:12 Epoch 5 | Batch 2900/3508 | Timestep 20440 | LR 0.0000100000 | Loss 0.027985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:14 Epoch 5 | Batch 2910/3508 | Timestep 20450 | LR 0.0000100000 | Loss 0.021925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:16 Epoch 5 | Batch 2920/3508 | Timestep 20460 | LR 0.0000100000 | Loss 0.047526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:18 Epoch 5 | Batch 2930/3508 | Timestep 20470 | LR 0.0000100000 | Loss 0.042227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:20 Epoch 5 | Batch 2940/3508 | Timestep 20480 | LR 0.0000100000 | Loss 0.072972 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:23 Epoch 5 | Batch 2950/3508 | Timestep 20490 | LR 0.0000100000 | Loss 0.037761 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:25 Epoch 5 | Batch 2960/3508 | Timestep 20500 | LR 0.0000100000 | Loss 0.025500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:28 Epoch 5 | Batch 2970/3508 | Timestep 20510 | LR 0.0000100000 | Loss 0.010316 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:30 Epoch 5 | Batch 2980/3508 | Timestep 20520 | LR 0.0000100000 | Loss 0.033193 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:32 Epoch 5 | Batch 2990/3508 | Timestep 20530 | LR 0.0000100000 | Loss 0.070670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:34 Epoch 5 | Batch 3000/3508 | Timestep 20540 | LR 0.0000100000 | Loss 0.022987 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:36 Epoch 5 | Batch 3010/3508 | Timestep 20550 | LR 0.0000100000 | Loss 0.014225 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:39 Epoch 5 | Batch 3020/3508 | Timestep 20560 | LR 0.0000100000 | Loss 0.028364 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:40 Epoch 5 | Batch 3030/3508 | Timestep 20570 | LR 0.0000100000 | Loss 0.046173 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:42 Epoch 5 | Batch 3040/3508 | Timestep 20580 | LR 0.0000100000 | Loss 0.015865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:45 Epoch 5 | Batch 3050/3508 | Timestep 20590 | LR 0.0000100000 | Loss 0.012941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:47 Epoch 5 | Batch 3060/3508 | Timestep 20600 | LR 0.0000100000 | Loss 0.014259 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:49 Epoch 5 | Batch 3070/3508 | Timestep 20610 | LR 0.0000100000 | Loss 0.001808 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:51 Epoch 5 | Batch 3080/3508 | Timestep 20620 | LR 0.0000100000 | Loss 0.013387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:53 Epoch 5 | Batch 3090/3508 | Timestep 20630 | LR 0.0000100000 | Loss 0.064942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:55 Epoch 5 | Batch 3100/3508 | Timestep 20640 | LR 0.0000100000 | Loss 0.033806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:01:57 Epoch 5 | Batch 3110/3508 | Timestep 20650 | LR 0.0000100000 | Loss 0.008465 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:00 Epoch 5 | Batch 3120/3508 | Timestep 20660 | LR 0.0000100000 | Loss 0.020310 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:02 Epoch 5 | Batch 3130/3508 | Timestep 20670 | LR 0.0000100000 | Loss 0.017831 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:05 Epoch 5 | Batch 3140/3508 | Timestep 20680 | LR 0.0000100000 | Loss 0.016996 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:07 Epoch 5 | Batch 3150/3508 | Timestep 20690 | LR 0.0000100000 | Loss 0.035936 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:09 Epoch 5 | Batch 3160/3508 | Timestep 20700 | LR 0.0000100000 | Loss 0.005981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:11 Epoch 5 | Batch 3170/3508 | Timestep 20710 | LR 0.0000100000 | Loss 0.017900 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:13 Epoch 5 | Batch 3180/3508 | Timestep 20720 | LR 0.0000100000 | Loss 0.012622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:15 Epoch 5 | Batch 3190/3508 | Timestep 20730 | LR 0.0000100000 | Loss 0.051494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:17 Epoch 5 | Batch 3200/3508 | Timestep 20740 | LR 0.0000100000 | Loss 0.015704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:19 Epoch 5 | Batch 3210/3508 | Timestep 20750 | LR 0.0000100000 | Loss 0.019787 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:21 Epoch 5 | Batch 3220/3508 | Timestep 20760 | LR 0.0000100000 | Loss 0.020775 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:23 Epoch 5 | Batch 3230/3508 | Timestep 20770 | LR 0.0000100000 | Loss 0.003845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:25 Epoch 5 | Batch 3240/3508 | Timestep 20780 | LR 0.0000100000 | Loss 0.007445 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:27 Epoch 5 | Batch 3250/3508 | Timestep 20790 | LR 0.0000100000 | Loss 0.038490 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:29 Epoch 5 | Batch 3260/3508 | Timestep 20800 | LR 0.0000100000 | Loss 0.014053 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:31 Epoch 5 | Batch 3270/3508 | Timestep 20810 | LR 0.0000100000 | Loss 0.028435 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:33 Epoch 5 | Batch 3280/3508 | Timestep 20820 | LR 0.0000100000 | Loss 0.038540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:35 Epoch 5 | Batch 3290/3508 | Timestep 20830 | LR 0.0000100000 | Loss 0.011610 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:37 Epoch 5 | Batch 3300/3508 | Timestep 20840 | LR 0.0000100000 | Loss 0.023129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:39 Epoch 5 | Batch 3310/3508 | Timestep 20850 | LR 0.0000100000 | Loss 0.057213 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:41 Epoch 5 | Batch 3320/3508 | Timestep 20860 | LR 0.0000100000 | Loss 0.022274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:44 Epoch 5 | Batch 3330/3508 | Timestep 20870 | LR 0.0000100000 | Loss 0.014046 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:46 Epoch 5 | Batch 3340/3508 | Timestep 20880 | LR 0.0000100000 | Loss 0.017228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:47 Epoch 5 | Batch 3350/3508 | Timestep 20890 | LR 0.0000100000 | Loss 0.020031 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:50 Epoch 5 | Batch 3360/3508 | Timestep 20900 | LR 0.0000100000 | Loss 0.011187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:52 Epoch 5 | Batch 3370/3508 | Timestep 20910 | LR 0.0000100000 | Loss 0.041120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:54 Epoch 5 | Batch 3380/3508 | Timestep 20920 | LR 0.0000100000 | Loss 0.028474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:56 Epoch 5 | Batch 3390/3508 | Timestep 20930 | LR 0.0000100000 | Loss 0.005851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:02:58 Epoch 5 | Batch 3400/3508 | Timestep 20940 | LR 0.0000100000 | Loss 0.002660 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:00 Epoch 5 | Batch 3410/3508 | Timestep 20950 | LR 0.0000100000 | Loss 0.035763 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:02 Epoch 5 | Batch 3420/3508 | Timestep 20960 | LR 0.0000100000 | Loss 0.004271 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:04 Epoch 5 | Batch 3430/3508 | Timestep 20970 | LR 0.0000100000 | Loss 0.029654 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:07 Epoch 5 | Batch 3440/3508 | Timestep 20980 | LR 0.0000100000 | Loss 0.023729 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:09 Epoch 5 | Batch 3450/3508 | Timestep 20990 | LR 0.0000100000 | Loss 0.026705 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:11 Epoch 5 | Batch 3460/3508 | Timestep 21000 | LR 0.0000100000 | Loss 0.004841 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:13 Epoch 5 | Batch 3470/3508 | Timestep 21010 | LR 0.0000100000 | Loss 0.007132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:15 Epoch 5 | Batch 3480/3508 | Timestep 21020 | LR 0.0000100000 | Loss 0.014960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:17 Epoch 5 | Batch 3490/3508 | Timestep 21030 | LR 0.0000100000 | Loss 0.061066 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:19 Epoch 5 | Batch 3500/3508 | Timestep 21040 | LR 0.0000100000 | Loss 0.011323 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:03:21 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 16:03:54 precision recall f1-score support CARDINAL 0.8205 0.8050 0.8127 159 CURR 0.5667 0.7727 0.6538 22 DATE 0.9368 0.9419 0.9393 1669 EVENT 0.6342 0.7597 0.6913 283 FAC 0.6601 0.8559 0.7454 118 GPE 0.9616 0.9724 0.9670 2140 LANGUAGE 0.7500 0.7500 0.7500 16 LAW 0.4444 0.8421 0.5818 19 LOC 0.7059 0.8000 0.7500 90 MONEY 0.6923 0.9000 0.7826 20 NORP 0.6352 0.7662 0.6946 509 OCC 0.8340 0.8810 0.8569 496 ORDINAL 0.9097 0.9484 0.9286 446 ORG 0.9193 0.9277 0.9234 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9278 0.9647 0.9458 679 PRODUCT 0.4167 0.6250 0.5000 8 QUANTITY 0.4000 0.6667 0.5000 3 TIME 0.5909 0.8387 0.6933 31 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.5275 0.6000 0.5614 80 micro avg 0.8790 0.9186 0.8984 8670 macro avg 0.7265 0.8271 0.7664 8670 weighted avg 0.8867 0.9186 0.9014 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:04:04 Epoch 5 | Timestep 21048 | Train Loss 0.022292 | Val Loss 0.051725 | F1 0.898364 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:04:04 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 25 Jun 2026 16:04:27 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Thu, 25 Jun 2026 16:04:43 Predictions written to /rep/nhamad/ArabicNER/B1/predictions.txt INFO root Thu, 25 Jun 2026 16:05:08 precision recall f1-score support CARDINAL 0.8473 0.8654 0.8563 327 CURR 0.5102 0.6579 0.5747 38 DATE 0.9463 0.9559 0.9511 3173 EVENT 0.6826 0.8193 0.7447 559 FAC 0.6486 0.7934 0.7138 242 GPE 0.9505 0.9671 0.9587 4311 LANGUAGE 0.8857 0.7045 0.7848 44 LAW 0.3860 0.7586 0.5116 29 LOC 0.7860 0.8257 0.8054 218 MONEY 0.7714 0.9000 0.8308 30 NORP 0.6630 0.7893 0.7207 992 OCC 0.8303 0.8841 0.8563 1035 ORDINAL 0.9164 0.9541 0.9349 850 ORG 0.9026 0.9345 0.9182 3738 PERCENT 0.9688 0.9688 0.9688 32 PERS 0.9072 0.9420 0.9243 1568 PRODUCT 0.6111 0.5789 0.5946 19 QUANTITY 0.4375 0.7778 0.5600 9 TIME 0.6211 0.7564 0.6821 78 UNIT 0.6923 0.8182 0.7500 11 WEBSITE 0.5643 0.6810 0.6172 116 micro avg 0.8806 0.9240 0.9018 17419 macro avg 0.7395 0.8254 0.7742 17419 weighted avg 0.8864 0.9240 0.9042 17419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:28 Epoch 5 | Timestep 21048 | Test Loss 0.050663 | F1 0.901782 INFO arabiner.trainers.BaseTrainer Thu, 25 Jun 2026 16:05:28 Saving checkpoint to /rep/nhamad/ArabicNER/B1/checkpoints/checkpoint_5.pt INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:31 Epoch 6 | Batch 2/3508 | Timestep 21050 | LR 0.0000100000 | Loss 0.006674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:33 Epoch 6 | Batch 12/3508 | Timestep 21060 | LR 0.0000100000 | Loss 0.025845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:35 Epoch 6 | Batch 22/3508 | Timestep 21070 | LR 0.0000100000 | Loss 0.005965 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:36 Epoch 6 | Batch 32/3508 | Timestep 21080 | LR 0.0000100000 | Loss 0.063845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:38 Epoch 6 | Batch 42/3508 | Timestep 21090 | LR 0.0000100000 | Loss 0.005010 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:41 Epoch 6 | Batch 52/3508 | Timestep 21100 | LR 0.0000100000 | Loss 0.026020 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:43 Epoch 6 | Batch 62/3508 | Timestep 21110 | LR 0.0000100000 | Loss 0.010477 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:46 Epoch 6 | Batch 72/3508 | Timestep 21120 | LR 0.0000100000 | Loss 0.002019 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:48 Epoch 6 | Batch 82/3508 | Timestep 21130 | LR 0.0000100000 | Loss 0.009956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:50 Epoch 6 | Batch 92/3508 | Timestep 21140 | LR 0.0000100000 | Loss 0.015293 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:52 Epoch 6 | Batch 102/3508 | Timestep 21150 | LR 0.0000100000 | Loss 0.003694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:54 Epoch 6 | Batch 112/3508 | Timestep 21160 | LR 0.0000100000 | Loss 0.020086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:05:57 Epoch 6 | Batch 122/3508 | Timestep 21170 | LR 0.0000100000 | Loss 0.004363 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:00 Epoch 6 | Batch 132/3508 | Timestep 21180 | LR 0.0000100000 | Loss 0.012488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:02 Epoch 6 | Batch 142/3508 | Timestep 21190 | LR 0.0000100000 | Loss 0.038381 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:04 Epoch 6 | Batch 152/3508 | Timestep 21200 | LR 0.0000100000 | Loss 0.012887 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:06 Epoch 6 | Batch 162/3508 | Timestep 21210 | LR 0.0000100000 | Loss 0.011486 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:08 Epoch 6 | Batch 172/3508 | Timestep 21220 | LR 0.0000100000 | Loss 0.011525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:10 Epoch 6 | Batch 182/3508 | Timestep 21230 | LR 0.0000100000 | Loss 0.001998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:12 Epoch 6 | Batch 192/3508 | Timestep 21240 | LR 0.0000100000 | Loss 0.009236 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:14 Epoch 6 | Batch 202/3508 | Timestep 21250 | LR 0.0000100000 | Loss 0.040579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:16 Epoch 6 | Batch 212/3508 | Timestep 21260 | LR 0.0000100000 | Loss 0.041575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:18 Epoch 6 | Batch 222/3508 | Timestep 21270 | LR 0.0000100000 | Loss 0.003604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:20 Epoch 6 | Batch 232/3508 | Timestep 21280 | LR 0.0000100000 | Loss 0.003380 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:23 Epoch 6 | Batch 242/3508 | Timestep 21290 | LR 0.0000100000 | Loss 0.004614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:25 Epoch 6 | Batch 252/3508 | Timestep 21300 | LR 0.0000100000 | Loss 0.016463 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:28 Epoch 6 | Batch 262/3508 | Timestep 21310 | LR 0.0000100000 | Loss 0.010179 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:30 Epoch 6 | Batch 272/3508 | Timestep 21320 | LR 0.0000100000 | Loss 0.023022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:33 Epoch 6 | Batch 282/3508 | Timestep 21330 | LR 0.0000100000 | Loss 0.047216 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:34 Epoch 6 | Batch 292/3508 | Timestep 21340 | LR 0.0000100000 | Loss 0.005401 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:36 Epoch 6 | Batch 302/3508 | Timestep 21350 | LR 0.0000100000 | Loss 0.009625 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:38 Epoch 6 | Batch 312/3508 | Timestep 21360 | LR 0.0000100000 | Loss 0.016343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:40 Epoch 6 | Batch 322/3508 | Timestep 21370 | LR 0.0000100000 | Loss 0.021700 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:42 Epoch 6 | Batch 332/3508 | Timestep 21380 | LR 0.0000100000 | Loss 0.005865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:45 Epoch 6 | Batch 342/3508 | Timestep 21390 | LR 0.0000100000 | Loss 0.019004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:48 Epoch 6 | Batch 352/3508 | Timestep 21400 | LR 0.0000100000 | Loss 0.007251 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:50 Epoch 6 | Batch 362/3508 | Timestep 21410 | LR 0.0000100000 | Loss 0.020662 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:52 Epoch 6 | Batch 372/3508 | Timestep 21420 | LR 0.0000100000 | Loss 0.001400 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:55 Epoch 6 | Batch 382/3508 | Timestep 21430 | LR 0.0000100000 | Loss 0.016616 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:57 Epoch 6 | Batch 392/3508 | Timestep 21440 | LR 0.0000100000 | Loss 0.047430 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:06:59 Epoch 6 | Batch 402/3508 | Timestep 21450 | LR 0.0000100000 | Loss 0.000879 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:01 Epoch 6 | Batch 412/3508 | Timestep 21460 | LR 0.0000100000 | Loss 0.019883 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:04 Epoch 6 | Batch 422/3508 | Timestep 21470 | LR 0.0000100000 | Loss 0.039295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:06 Epoch 6 | Batch 432/3508 | Timestep 21480 | LR 0.0000100000 | Loss 0.012153 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:08 Epoch 6 | Batch 442/3508 | Timestep 21490 | LR 0.0000100000 | Loss 0.007767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:10 Epoch 6 | Batch 452/3508 | Timestep 21500 | LR 0.0000100000 | Loss 0.019237 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:12 Epoch 6 | Batch 462/3508 | Timestep 21510 | LR 0.0000100000 | Loss 0.002817 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:16 Epoch 6 | Batch 472/3508 | Timestep 21520 | LR 0.0000100000 | Loss 0.031152 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:18 Epoch 6 | Batch 482/3508 | Timestep 21530 | LR 0.0000100000 | Loss 0.005959 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:20 Epoch 6 | Batch 492/3508 | Timestep 21540 | LR 0.0000100000 | Loss 0.016735 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:22 Epoch 6 | Batch 502/3508 | Timestep 21550 | LR 0.0000100000 | Loss 0.005258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:24 Epoch 6 | Batch 512/3508 | Timestep 21560 | LR 0.0000100000 | Loss 0.017899 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:26 Epoch 6 | Batch 522/3508 | Timestep 21570 | LR 0.0000100000 | Loss 0.008261 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:28 Epoch 6 | Batch 532/3508 | Timestep 21580 | LR 0.0000100000 | Loss 0.018431 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:30 Epoch 6 | Batch 542/3508 | Timestep 21590 | LR 0.0000100000 | Loss 0.004456 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:33 Epoch 6 | Batch 552/3508 | Timestep 21600 | LR 0.0000100000 | Loss 0.018944 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:34 Epoch 6 | Batch 562/3508 | Timestep 21610 | LR 0.0000100000 | Loss 0.016557 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:37 Epoch 6 | Batch 572/3508 | Timestep 21620 | LR 0.0000100000 | Loss 0.007952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:39 Epoch 6 | Batch 582/3508 | Timestep 21630 | LR 0.0000100000 | Loss 0.003963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:41 Epoch 6 | Batch 592/3508 | Timestep 21640 | LR 0.0000100000 | Loss 0.016692 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:43 Epoch 6 | Batch 602/3508 | Timestep 21650 | LR 0.0000100000 | Loss 0.001553 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:45 Epoch 6 | Batch 612/3508 | Timestep 21660 | LR 0.0000100000 | Loss 0.018722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:47 Epoch 6 | Batch 622/3508 | Timestep 21670 | LR 0.0000100000 | Loss 0.011180 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:49 Epoch 6 | Batch 632/3508 | Timestep 21680 | LR 0.0000100000 | Loss 0.013604 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:51 Epoch 6 | Batch 642/3508 | Timestep 21690 | LR 0.0000100000 | Loss 0.013598 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:53 Epoch 6 | Batch 652/3508 | Timestep 21700 | LR 0.0000100000 | Loss 0.044609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:55 Epoch 6 | Batch 662/3508 | Timestep 21710 | LR 0.0000100000 | Loss 0.026367 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:07:58 Epoch 6 | Batch 672/3508 | Timestep 21720 | LR 0.0000100000 | Loss 0.013284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:00 Epoch 6 | Batch 682/3508 | Timestep 21730 | LR 0.0000100000 | Loss 0.027229 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:02 Epoch 6 | Batch 692/3508 | Timestep 21740 | LR 0.0000100000 | Loss 0.005952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:04 Epoch 6 | Batch 702/3508 | Timestep 21750 | LR 0.0000100000 | Loss 0.001239 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:06 Epoch 6 | Batch 712/3508 | Timestep 21760 | LR 0.0000100000 | Loss 0.002335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:08 Epoch 6 | Batch 722/3508 | Timestep 21770 | LR 0.0000100000 | Loss 0.007215 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:10 Epoch 6 | Batch 732/3508 | Timestep 21780 | LR 0.0000100000 | Loss 0.011860 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:12 Epoch 6 | Batch 742/3508 | Timestep 21790 | LR 0.0000100000 | Loss 0.003954 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:14 Epoch 6 | Batch 752/3508 | Timestep 21800 | LR 0.0000100000 | Loss 0.015150 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:16 Epoch 6 | Batch 762/3508 | Timestep 21810 | LR 0.0000100000 | Loss 0.005425 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:18 Epoch 6 | Batch 772/3508 | Timestep 21820 | LR 0.0000100000 | Loss 0.002438 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:20 Epoch 6 | Batch 782/3508 | Timestep 21830 | LR 0.0000100000 | Loss 0.018471 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:22 Epoch 6 | Batch 792/3508 | Timestep 21840 | LR 0.0000100000 | Loss 0.020265 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:24 Epoch 6 | Batch 802/3508 | Timestep 21850 | LR 0.0000100000 | Loss 0.030411 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:26 Epoch 6 | Batch 812/3508 | Timestep 21860 | LR 0.0000100000 | Loss 0.011641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:28 Epoch 6 | Batch 822/3508 | Timestep 21870 | LR 0.0000100000 | Loss 0.022006 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:29 Epoch 6 | Batch 832/3508 | Timestep 21880 | LR 0.0000100000 | Loss 0.012022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:31 Epoch 6 | Batch 842/3508 | Timestep 21890 | LR 0.0000100000 | Loss 0.001264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:34 Epoch 6 | Batch 852/3508 | Timestep 21900 | LR 0.0000100000 | Loss 0.066700 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:36 Epoch 6 | Batch 862/3508 | Timestep 21910 | LR 0.0000100000 | Loss 0.005125 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:38 Epoch 6 | Batch 872/3508 | Timestep 21920 | LR 0.0000100000 | Loss 0.013947 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:40 Epoch 6 | Batch 882/3508 | Timestep 21930 | LR 0.0000100000 | Loss 0.013928 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:42 Epoch 6 | Batch 892/3508 | Timestep 21940 | LR 0.0000100000 | Loss 0.010918 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:44 Epoch 6 | Batch 902/3508 | Timestep 21950 | LR 0.0000100000 | Loss 0.008329 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:47 Epoch 6 | Batch 912/3508 | Timestep 21960 | LR 0.0000100000 | Loss 0.015929 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:49 Epoch 6 | Batch 922/3508 | Timestep 21970 | LR 0.0000100000 | Loss 0.009652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:52 Epoch 6 | Batch 932/3508 | Timestep 21980 | LR 0.0000100000 | Loss 0.015441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:54 Epoch 6 | Batch 942/3508 | Timestep 21990 | LR 0.0000100000 | Loss 0.024942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:56 Epoch 6 | Batch 952/3508 | Timestep 22000 | LR 0.0000100000 | Loss 0.003016 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:08:58 Epoch 6 | Batch 962/3508 | Timestep 22010 | LR 0.0000100000 | Loss 0.015101 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:00 Epoch 6 | Batch 972/3508 | Timestep 22020 | LR 0.0000100000 | Loss 0.020864 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:02 Epoch 6 | Batch 982/3508 | Timestep 22030 | LR 0.0000100000 | Loss 0.015949 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:04 Epoch 6 | Batch 992/3508 | Timestep 22040 | LR 0.0000100000 | Loss 0.043238 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:06 Epoch 6 | Batch 1002/3508 | Timestep 22050 | LR 0.0000100000 | Loss 0.022848 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:08 Epoch 6 | Batch 1012/3508 | Timestep 22060 | LR 0.0000100000 | Loss 0.060825 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:10 Epoch 6 | Batch 1022/3508 | Timestep 22070 | LR 0.0000100000 | Loss 0.017771 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:12 Epoch 6 | Batch 1032/3508 | Timestep 22080 | LR 0.0000100000 | Loss 0.002680 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:14 Epoch 6 | Batch 1042/3508 | Timestep 22090 | LR 0.0000100000 | Loss 0.030345 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:17 Epoch 6 | Batch 1052/3508 | Timestep 22100 | LR 0.0000100000 | Loss 0.015495 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:19 Epoch 6 | Batch 1062/3508 | Timestep 22110 | LR 0.0000100000 | Loss 0.018142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:21 Epoch 6 | Batch 1072/3508 | Timestep 22120 | LR 0.0000100000 | Loss 0.004375 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:24 Epoch 6 | Batch 1082/3508 | Timestep 22130 | LR 0.0000100000 | Loss 0.015579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:25 Epoch 6 | Batch 1092/3508 | Timestep 22140 | LR 0.0000100000 | Loss 0.005851 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:27 Epoch 6 | Batch 1102/3508 | Timestep 22150 | LR 0.0000100000 | Loss 0.010188 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:30 Epoch 6 | Batch 1112/3508 | Timestep 22160 | LR 0.0000100000 | Loss 0.016632 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:32 Epoch 6 | Batch 1122/3508 | Timestep 22170 | LR 0.0000100000 | Loss 0.009633 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:33 Epoch 6 | Batch 1132/3508 | Timestep 22180 | LR 0.0000100000 | Loss 0.004189 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:35 Epoch 6 | Batch 1142/3508 | Timestep 22190 | LR 0.0000100000 | Loss 0.013146 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:38 Epoch 6 | Batch 1152/3508 | Timestep 22200 | LR 0.0000100000 | Loss 0.002896 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:39 Epoch 6 | Batch 1162/3508 | Timestep 22210 | LR 0.0000100000 | Loss 0.008993 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:42 Epoch 6 | Batch 1172/3508 | Timestep 22220 | LR 0.0000100000 | Loss 0.011983 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:44 Epoch 6 | Batch 1182/3508 | Timestep 22230 | LR 0.0000100000 | Loss 0.024704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:46 Epoch 6 | Batch 1192/3508 | Timestep 22240 | LR 0.0000100000 | Loss 0.008888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:48 Epoch 6 | Batch 1202/3508 | Timestep 22250 | LR 0.0000100000 | Loss 0.008227 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:50 Epoch 6 | Batch 1212/3508 | Timestep 22260 | LR 0.0000100000 | Loss 0.007592 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:52 Epoch 6 | Batch 1222/3508 | Timestep 22270 | LR 0.0000100000 | Loss 0.009960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:54 Epoch 6 | Batch 1232/3508 | Timestep 22280 | LR 0.0000100000 | Loss 0.006025 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:56 Epoch 6 | Batch 1242/3508 | Timestep 22290 | LR 0.0000100000 | Loss 0.012939 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:09:58 Epoch 6 | Batch 1252/3508 | Timestep 22300 | LR 0.0000100000 | Loss 0.013954 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:00 Epoch 6 | Batch 1262/3508 | Timestep 22310 | LR 0.0000100000 | Loss 0.023525 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:01 Epoch 6 | Batch 1272/3508 | Timestep 22320 | LR 0.0000100000 | Loss 0.019693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:03 Epoch 6 | Batch 1282/3508 | Timestep 22330 | LR 0.0000100000 | Loss 0.009023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:05 Epoch 6 | Batch 1292/3508 | Timestep 22340 | LR 0.0000100000 | Loss 0.047644 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:07 Epoch 6 | Batch 1302/3508 | Timestep 22350 | LR 0.0000100000 | Loss 0.030214 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:09 Epoch 6 | Batch 1312/3508 | Timestep 22360 | LR 0.0000100000 | Loss 0.047558 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:11 Epoch 6 | Batch 1322/3508 | Timestep 22370 | LR 0.0000100000 | Loss 0.002021 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:14 Epoch 6 | Batch 1332/3508 | Timestep 22380 | LR 0.0000100000 | Loss 0.015132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:16 Epoch 6 | Batch 1342/3508 | Timestep 22390 | LR 0.0000100000 | Loss 0.003564 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:18 Epoch 6 | Batch 1352/3508 | Timestep 22400 | LR 0.0000100000 | Loss 0.008524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:20 Epoch 6 | Batch 1362/3508 | Timestep 22410 | LR 0.0000100000 | Loss 0.021241 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:21 Epoch 6 | Batch 1372/3508 | Timestep 22420 | LR 0.0000100000 | Loss 0.014117 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:24 Epoch 6 | Batch 1382/3508 | Timestep 22430 | LR 0.0000100000 | Loss 0.013088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:26 Epoch 6 | Batch 1392/3508 | Timestep 22440 | LR 0.0000100000 | Loss 0.012584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:28 Epoch 6 | Batch 1402/3508 | Timestep 22450 | LR 0.0000100000 | Loss 0.064327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:30 Epoch 6 | Batch 1412/3508 | Timestep 22460 | LR 0.0000100000 | Loss 0.002298 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:33 Epoch 6 | Batch 1422/3508 | Timestep 22470 | LR 0.0000100000 | Loss 0.007080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:35 Epoch 6 | Batch 1432/3508 | Timestep 22480 | LR 0.0000100000 | Loss 0.022389 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:37 Epoch 6 | Batch 1442/3508 | Timestep 22490 | LR 0.0000100000 | Loss 0.003416 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:39 Epoch 6 | Batch 1452/3508 | Timestep 22500 | LR 0.0000100000 | Loss 0.032090 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:41 Epoch 6 | Batch 1462/3508 | Timestep 22510 | LR 0.0000100000 | Loss 0.005694 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:44 Epoch 6 | Batch 1472/3508 | Timestep 22520 | LR 0.0000100000 | Loss 0.052538 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:46 Epoch 6 | Batch 1482/3508 | Timestep 22530 | LR 0.0000100000 | Loss 0.056453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:48 Epoch 6 | Batch 1492/3508 | Timestep 22540 | LR 0.0000100000 | Loss 0.010717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:51 Epoch 6 | Batch 1502/3508 | Timestep 22550 | LR 0.0000100000 | Loss 0.017989 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:53 Epoch 6 | Batch 1512/3508 | Timestep 22560 | LR 0.0000100000 | Loss 0.024791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:56 Epoch 6 | Batch 1522/3508 | Timestep 22570 | LR 0.0000100000 | Loss 0.011986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:10:58 Epoch 6 | Batch 1532/3508 | Timestep 22580 | LR 0.0000100000 | Loss 0.014770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:00 Epoch 6 | Batch 1542/3508 | Timestep 22590 | LR 0.0000100000 | Loss 0.005406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:03 Epoch 6 | Batch 1552/3508 | Timestep 22600 | LR 0.0000100000 | Loss 0.033050 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:05 Epoch 6 | Batch 1562/3508 | Timestep 22610 | LR 0.0000100000 | Loss 0.003926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:07 Epoch 6 | Batch 1572/3508 | Timestep 22620 | LR 0.0000100000 | Loss 0.015990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:09 Epoch 6 | Batch 1582/3508 | Timestep 22630 | LR 0.0000100000 | Loss 0.014205 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:12 Epoch 6 | Batch 1592/3508 | Timestep 22640 | LR 0.0000100000 | Loss 0.034221 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:13 Epoch 6 | Batch 1602/3508 | Timestep 22650 | LR 0.0000100000 | Loss 0.008389 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:15 Epoch 6 | Batch 1612/3508 | Timestep 22660 | LR 0.0000100000 | Loss 0.010892 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:17 Epoch 6 | Batch 1622/3508 | Timestep 22670 | LR 0.0000100000 | Loss 0.023207 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:19 Epoch 6 | Batch 1632/3508 | Timestep 22680 | LR 0.0000100000 | Loss 0.004776 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:21 Epoch 6 | Batch 1642/3508 | Timestep 22690 | LR 0.0000100000 | Loss 0.042170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:23 Epoch 6 | Batch 1652/3508 | Timestep 22700 | LR 0.0000100000 | Loss 0.011308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:25 Epoch 6 | Batch 1662/3508 | Timestep 22710 | LR 0.0000100000 | Loss 0.010145 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:27 Epoch 6 | Batch 1672/3508 | Timestep 22720 | LR 0.0000100000 | Loss 0.026401 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:29 Epoch 6 | Batch 1682/3508 | Timestep 22730 | LR 0.0000100000 | Loss 0.016572 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:32 Epoch 6 | Batch 1692/3508 | Timestep 22740 | LR 0.0000100000 | Loss 0.082319 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:34 Epoch 6 | Batch 1702/3508 | Timestep 22750 | LR 0.0000100000 | Loss 0.011054 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:35 Epoch 6 | Batch 1712/3508 | Timestep 22760 | LR 0.0000100000 | Loss 0.008436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:37 Epoch 6 | Batch 1722/3508 | Timestep 22770 | LR 0.0000100000 | Loss 0.006645 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:40 Epoch 6 | Batch 1732/3508 | Timestep 22780 | LR 0.0000100000 | Loss 0.004038 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:42 Epoch 6 | Batch 1742/3508 | Timestep 22790 | LR 0.0000100000 | Loss 0.015695 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:44 Epoch 6 | Batch 1752/3508 | Timestep 22800 | LR 0.0000100000 | Loss 0.030924 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:47 Epoch 6 | Batch 1762/3508 | Timestep 22810 | LR 0.0000100000 | Loss 0.021237 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:49 Epoch 6 | Batch 1772/3508 | Timestep 22820 | LR 0.0000100000 | Loss 0.024915 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:51 Epoch 6 | Batch 1782/3508 | Timestep 22830 | LR 0.0000100000 | Loss 0.014243 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:53 Epoch 6 | Batch 1792/3508 | Timestep 22840 | LR 0.0000100000 | Loss 0.008946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:55 Epoch 6 | Batch 1802/3508 | Timestep 22850 | LR 0.0000100000 | Loss 0.055895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:57 Epoch 6 | Batch 1812/3508 | Timestep 22860 | LR 0.0000100000 | Loss 0.081258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:11:59 Epoch 6 | Batch 1822/3508 | Timestep 22870 | LR 0.0000100000 | Loss 0.014086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:01 Epoch 6 | Batch 1832/3508 | Timestep 22880 | LR 0.0000100000 | Loss 0.033100 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:03 Epoch 6 | Batch 1842/3508 | Timestep 22890 | LR 0.0000100000 | Loss 0.006372 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:05 Epoch 6 | Batch 1852/3508 | Timestep 22900 | LR 0.0000100000 | Loss 0.023165 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:07 Epoch 6 | Batch 1862/3508 | Timestep 22910 | LR 0.0000100000 | Loss 0.004260 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:09 Epoch 6 | Batch 1872/3508 | Timestep 22920 | LR 0.0000100000 | Loss 0.006885 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:10 Epoch 6 | Batch 1882/3508 | Timestep 22930 | LR 0.0000100000 | Loss 0.015181 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:12 Epoch 6 | Batch 1892/3508 | Timestep 22940 | LR 0.0000100000 | Loss 0.103620 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:14 Epoch 6 | Batch 1902/3508 | Timestep 22950 | LR 0.0000100000 | Loss 0.007842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:16 Epoch 6 | Batch 1912/3508 | Timestep 22960 | LR 0.0000100000 | Loss 0.013935 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:19 Epoch 6 | Batch 1922/3508 | Timestep 22970 | LR 0.0000100000 | Loss 0.010861 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:21 Epoch 6 | Batch 1932/3508 | Timestep 22980 | LR 0.0000100000 | Loss 0.014490 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:23 Epoch 6 | Batch 1942/3508 | Timestep 22990 | LR 0.0000100000 | Loss 0.005437 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:25 Epoch 6 | Batch 1952/3508 | Timestep 23000 | LR 0.0000100000 | Loss 0.024368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:28 Epoch 6 | Batch 1962/3508 | Timestep 23010 | LR 0.0000100000 | Loss 0.007470 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:30 Epoch 6 | Batch 1972/3508 | Timestep 23020 | LR 0.0000100000 | Loss 0.008781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:32 Epoch 6 | Batch 1982/3508 | Timestep 23030 | LR 0.0000100000 | Loss 0.031433 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:34 Epoch 6 | Batch 1992/3508 | Timestep 23040 | LR 0.0000100000 | Loss 0.006296 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:36 Epoch 6 | Batch 2002/3508 | Timestep 23050 | LR 0.0000100000 | Loss 0.003924 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:38 Epoch 6 | Batch 2012/3508 | Timestep 23060 | LR 0.0000100000 | Loss 0.003770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:40 Epoch 6 | Batch 2022/3508 | Timestep 23070 | LR 0.0000100000 | Loss 0.008275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:43 Epoch 6 | Batch 2032/3508 | Timestep 23080 | LR 0.0000100000 | Loss 0.046772 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:45 Epoch 6 | Batch 2042/3508 | Timestep 23090 | LR 0.0000100000 | Loss 0.009097 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:47 Epoch 6 | Batch 2052/3508 | Timestep 23100 | LR 0.0000100000 | Loss 0.009731 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:50 Epoch 6 | Batch 2062/3508 | Timestep 23110 | LR 0.0000100000 | Loss 0.005537 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:51 Epoch 6 | Batch 2072/3508 | Timestep 23120 | LR 0.0000100000 | Loss 0.025266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:54 Epoch 6 | Batch 2082/3508 | Timestep 23130 | LR 0.0000100000 | Loss 0.043183 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:56 Epoch 6 | Batch 2092/3508 | Timestep 23140 | LR 0.0000100000 | Loss 0.012767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:12:58 Epoch 6 | Batch 2102/3508 | Timestep 23150 | LR 0.0000100000 | Loss 0.009491 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:00 Epoch 6 | Batch 2112/3508 | Timestep 23160 | LR 0.0000100000 | Loss 0.030195 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:02 Epoch 6 | Batch 2122/3508 | Timestep 23170 | LR 0.0000100000 | Loss 0.016499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:04 Epoch 6 | Batch 2132/3508 | Timestep 23180 | LR 0.0000100000 | Loss 0.045321 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:06 Epoch 6 | Batch 2142/3508 | Timestep 23190 | LR 0.0000100000 | Loss 0.027892 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:08 Epoch 6 | Batch 2152/3508 | Timestep 23200 | LR 0.0000100000 | Loss 0.020453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:10 Epoch 6 | Batch 2162/3508 | Timestep 23210 | LR 0.0000100000 | Loss 0.027143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:13 Epoch 6 | Batch 2172/3508 | Timestep 23220 | LR 0.0000100000 | Loss 0.006384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:15 Epoch 6 | Batch 2182/3508 | Timestep 23230 | LR 0.0000100000 | Loss 0.011141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:17 Epoch 6 | Batch 2192/3508 | Timestep 23240 | LR 0.0000100000 | Loss 0.032373 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:19 Epoch 6 | Batch 2202/3508 | Timestep 23250 | LR 0.0000100000 | Loss 0.041230 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:21 Epoch 6 | Batch 2212/3508 | Timestep 23260 | LR 0.0000100000 | Loss 0.003056 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:23 Epoch 6 | Batch 2222/3508 | Timestep 23270 | LR 0.0000100000 | Loss 0.026647 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:25 Epoch 6 | Batch 2232/3508 | Timestep 23280 | LR 0.0000100000 | Loss 0.012475 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:27 Epoch 6 | Batch 2242/3508 | Timestep 23290 | LR 0.0000100000 | Loss 0.033214 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:30 Epoch 6 | Batch 2252/3508 | Timestep 23300 | LR 0.0000100000 | Loss 0.022330 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:31 Epoch 6 | Batch 2262/3508 | Timestep 23310 | LR 0.0000100000 | Loss 0.004022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:34 Epoch 6 | Batch 2272/3508 | Timestep 23320 | LR 0.0000100000 | Loss 0.030153 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:36 Epoch 6 | Batch 2282/3508 | Timestep 23330 | LR 0.0000100000 | Loss 0.043358 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:38 Epoch 6 | Batch 2292/3508 | Timestep 23340 | LR 0.0000100000 | Loss 0.015268 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:40 Epoch 6 | Batch 2302/3508 | Timestep 23350 | LR 0.0000100000 | Loss 0.041057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:42 Epoch 6 | Batch 2312/3508 | Timestep 23360 | LR 0.0000100000 | Loss 0.029983 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:44 Epoch 6 | Batch 2322/3508 | Timestep 23370 | LR 0.0000100000 | Loss 0.013907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:46 Epoch 6 | Batch 2332/3508 | Timestep 23380 | LR 0.0000100000 | Loss 0.008391 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:49 Epoch 6 | Batch 2342/3508 | Timestep 23390 | LR 0.0000100000 | Loss 0.030906 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:51 Epoch 6 | Batch 2352/3508 | Timestep 23400 | LR 0.0000100000 | Loss 0.068404 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:53 Epoch 6 | Batch 2362/3508 | Timestep 23410 | LR 0.0000100000 | Loss 0.014297 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:55 Epoch 6 | Batch 2372/3508 | Timestep 23420 | LR 0.0000100000 | Loss 0.003828 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:57 Epoch 6 | Batch 2382/3508 | Timestep 23430 | LR 0.0000100000 | Loss 0.057292 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:13:59 Epoch 6 | Batch 2392/3508 | Timestep 23440 | LR 0.0000100000 | Loss 0.007354 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:01 Epoch 6 | Batch 2402/3508 | Timestep 23450 | LR 0.0000100000 | Loss 0.005725 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:03 Epoch 6 | Batch 2412/3508 | Timestep 23460 | LR 0.0000100000 | Loss 0.005907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:06 Epoch 6 | Batch 2422/3508 | Timestep 23470 | LR 0.0000100000 | Loss 0.022183 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:08 Epoch 6 | Batch 2432/3508 | Timestep 23480 | LR 0.0000100000 | Loss 0.014052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:10 Epoch 6 | Batch 2442/3508 | Timestep 23490 | LR 0.0000100000 | Loss 0.009054 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:12 Epoch 6 | Batch 2452/3508 | Timestep 23500 | LR 0.0000100000 | Loss 0.029667 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:15 Epoch 6 | Batch 2462/3508 | Timestep 23510 | LR 0.0000100000 | Loss 0.015969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:17 Epoch 6 | Batch 2472/3508 | Timestep 23520 | LR 0.0000100000 | Loss 0.024350 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:19 Epoch 6 | Batch 2482/3508 | Timestep 23530 | LR 0.0000100000 | Loss 0.011384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:21 Epoch 6 | Batch 2492/3508 | Timestep 23540 | LR 0.0000100000 | Loss 0.018250 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:23 Epoch 6 | Batch 2502/3508 | Timestep 23550 | LR 0.0000100000 | Loss 0.010178 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:26 Epoch 6 | Batch 2512/3508 | Timestep 23560 | LR 0.0000100000 | Loss 0.007120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:27 Epoch 6 | Batch 2522/3508 | Timestep 23570 | LR 0.0000100000 | Loss 0.027450 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:30 Epoch 6 | Batch 2532/3508 | Timestep 23580 | LR 0.0000100000 | Loss 0.019653 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:32 Epoch 6 | Batch 2542/3508 | Timestep 23590 | LR 0.0000100000 | Loss 0.019786 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:34 Epoch 6 | Batch 2552/3508 | Timestep 23600 | LR 0.0000100000 | Loss 0.008001 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:36 Epoch 6 | Batch 2562/3508 | Timestep 23610 | LR 0.0000100000 | Loss 0.027983 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:38 Epoch 6 | Batch 2572/3508 | Timestep 23620 | LR 0.0000100000 | Loss 0.002868 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:40 Epoch 6 | Batch 2582/3508 | Timestep 23630 | LR 0.0000100000 | Loss 0.016791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:42 Epoch 6 | Batch 2592/3508 | Timestep 23640 | LR 0.0000100000 | Loss 0.002999 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:44 Epoch 6 | Batch 2602/3508 | Timestep 23650 | LR 0.0000100000 | Loss 0.033210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:46 Epoch 6 | Batch 2612/3508 | Timestep 23660 | LR 0.0000100000 | Loss 0.014484 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:49 Epoch 6 | Batch 2622/3508 | Timestep 23670 | LR 0.0000100000 | Loss 0.025310 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:51 Epoch 6 | Batch 2632/3508 | Timestep 23680 | LR 0.0000100000 | Loss 0.014430 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:53 Epoch 6 | Batch 2642/3508 | Timestep 23690 | LR 0.0000100000 | Loss 0.005317 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:55 Epoch 6 | Batch 2652/3508 | Timestep 23700 | LR 0.0000100000 | Loss 0.045617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:57 Epoch 6 | Batch 2662/3508 | Timestep 23710 | LR 0.0000100000 | Loss 0.011731 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:14:59 Epoch 6 | Batch 2672/3508 | Timestep 23720 | LR 0.0000100000 | Loss 0.007551 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:02 Epoch 6 | Batch 2682/3508 | Timestep 23730 | LR 0.0000100000 | Loss 0.006596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:04 Epoch 6 | Batch 2692/3508 | Timestep 23740 | LR 0.0000100000 | Loss 0.040950 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:07 Epoch 6 | Batch 2702/3508 | Timestep 23750 | LR 0.0000100000 | Loss 0.014529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:09 Epoch 6 | Batch 2712/3508 | Timestep 23760 | LR 0.0000100000 | Loss 0.002036 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:11 Epoch 6 | Batch 2722/3508 | Timestep 23770 | LR 0.0000100000 | Loss 0.034311 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:13 Epoch 6 | Batch 2732/3508 | Timestep 23780 | LR 0.0000100000 | Loss 0.006346 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:16 Epoch 6 | Batch 2742/3508 | Timestep 23790 | LR 0.0000100000 | Loss 0.031864 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:17 Epoch 6 | Batch 2752/3508 | Timestep 23800 | LR 0.0000100000 | Loss 0.037128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:20 Epoch 6 | Batch 2762/3508 | Timestep 23810 | LR 0.0000100000 | Loss 0.023141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:22 Epoch 6 | Batch 2772/3508 | Timestep 23820 | LR 0.0000100000 | Loss 0.077317 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:24 Epoch 6 | Batch 2782/3508 | Timestep 23830 | LR 0.0000100000 | Loss 0.026978 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:27 Epoch 6 | Batch 2792/3508 | Timestep 23840 | LR 0.0000100000 | Loss 0.079952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:29 Epoch 6 | Batch 2802/3508 | Timestep 23850 | LR 0.0000100000 | Loss 0.004074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:31 Epoch 6 | Batch 2812/3508 | Timestep 23860 | LR 0.0000100000 | Loss 0.042581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:34 Epoch 6 | Batch 2822/3508 | Timestep 23870 | LR 0.0000100000 | Loss 0.029896 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:37 Epoch 6 | Batch 2832/3508 | Timestep 23880 | LR 0.0000100000 | Loss 0.032026 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:39 Epoch 6 | Batch 2842/3508 | Timestep 23890 | LR 0.0000100000 | Loss 0.024308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:42 Epoch 6 | Batch 2852/3508 | Timestep 23900 | LR 0.0000100000 | Loss 0.026436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:44 Epoch 6 | Batch 2862/3508 | Timestep 23910 | LR 0.0000100000 | Loss 0.017547 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:46 Epoch 6 | Batch 2872/3508 | Timestep 23920 | LR 0.0000100000 | Loss 0.006631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:48 Epoch 6 | Batch 2882/3508 | Timestep 23930 | LR 0.0000100000 | Loss 0.009170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:50 Epoch 6 | Batch 2892/3508 | Timestep 23940 | LR 0.0000100000 | Loss 0.021203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:52 Epoch 6 | Batch 2902/3508 | Timestep 23950 | LR 0.0000100000 | Loss 0.003152 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:54 Epoch 6 | Batch 2912/3508 | Timestep 23960 | LR 0.0000100000 | Loss 0.003531 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:56 Epoch 6 | Batch 2922/3508 | Timestep 23970 | LR 0.0000100000 | Loss 0.004928 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:15:58 Epoch 6 | Batch 2932/3508 | Timestep 23980 | LR 0.0000100000 | Loss 0.022500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:00 Epoch 6 | Batch 2942/3508 | Timestep 23990 | LR 0.0000100000 | Loss 0.012483 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:02 Epoch 6 | Batch 2952/3508 | Timestep 24000 | LR 0.0000100000 | Loss 0.016453 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:04 Epoch 6 | Batch 2962/3508 | Timestep 24010 | LR 0.0000100000 | Loss 0.014324 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:07 Epoch 6 | Batch 2972/3508 | Timestep 24020 | LR 0.0000100000 | Loss 0.006426 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:08 Epoch 6 | Batch 2982/3508 | Timestep 24030 | LR 0.0000100000 | Loss 0.002438 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:10 Epoch 6 | Batch 2992/3508 | Timestep 24040 | LR 0.0000100000 | Loss 0.021830 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:12 Epoch 6 | Batch 3002/3508 | Timestep 24050 | LR 0.0000100000 | Loss 0.016580 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:14 Epoch 6 | Batch 3012/3508 | Timestep 24060 | LR 0.0000100000 | Loss 0.007718 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:16 Epoch 6 | Batch 3022/3508 | Timestep 24070 | LR 0.0000100000 | Loss 0.037237 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:18 Epoch 6 | Batch 3032/3508 | Timestep 24080 | LR 0.0000100000 | Loss 0.019463 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:21 Epoch 6 | Batch 3042/3508 | Timestep 24090 | LR 0.0000100000 | Loss 0.017774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:23 Epoch 6 | Batch 3052/3508 | Timestep 24100 | LR 0.0000100000 | Loss 0.048370 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:26 Epoch 6 | Batch 3062/3508 | Timestep 24110 | LR 0.0000100000 | Loss 0.007129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:28 Epoch 6 | Batch 3072/3508 | Timestep 24120 | LR 0.0000100000 | Loss 0.014014 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:30 Epoch 6 | Batch 3082/3508 | Timestep 24130 | LR 0.0000100000 | Loss 0.021004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:31 Epoch 6 | Batch 3092/3508 | Timestep 24140 | LR 0.0000100000 | Loss 0.024279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:34 Epoch 6 | Batch 3102/3508 | Timestep 24150 | LR 0.0000100000 | Loss 0.017554 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:36 Epoch 6 | Batch 3112/3508 | Timestep 24160 | LR 0.0000100000 | Loss 0.016594 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:38 Epoch 6 | Batch 3122/3508 | Timestep 24170 | LR 0.0000100000 | Loss 0.013200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:40 Epoch 6 | Batch 3132/3508 | Timestep 24180 | LR 0.0000100000 | Loss 0.057442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:42 Epoch 6 | Batch 3142/3508 | Timestep 24190 | LR 0.0000100000 | Loss 0.006778 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:44 Epoch 6 | Batch 3152/3508 | Timestep 24200 | LR 0.0000100000 | Loss 0.027120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:46 Epoch 6 | Batch 3162/3508 | Timestep 24210 | LR 0.0000100000 | Loss 0.010051 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:48 Epoch 6 | Batch 3172/3508 | Timestep 24220 | LR 0.0000100000 | Loss 0.014596 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:50 Epoch 6 | Batch 3182/3508 | Timestep 24230 | LR 0.0000100000 | Loss 0.023984 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:52 Epoch 6 | Batch 3192/3508 | Timestep 24240 | LR 0.0000100000 | Loss 0.005248 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:54 Epoch 6 | Batch 3202/3508 | Timestep 24250 | LR 0.0000100000 | Loss 0.048420 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:56 Epoch 6 | Batch 3212/3508 | Timestep 24260 | LR 0.0000100000 | Loss 0.011033 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:16:58 Epoch 6 | Batch 3222/3508 | Timestep 24270 | LR 0.0000100000 | Loss 0.031598 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:01 Epoch 6 | Batch 3232/3508 | Timestep 24280 | LR 0.0000100000 | Loss 0.002332 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:03 Epoch 6 | Batch 3242/3508 | Timestep 24290 | LR 0.0000100000 | Loss 0.020083 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:05 Epoch 6 | Batch 3252/3508 | Timestep 24300 | LR 0.0000100000 | Loss 0.012798 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:07 Epoch 6 | Batch 3262/3508 | Timestep 24310 | LR 0.0000100000 | Loss 0.021388 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:09 Epoch 6 | Batch 3272/3508 | Timestep 24320 | LR 0.0000100000 | Loss 0.010409 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:11 Epoch 6 | Batch 3282/3508 | Timestep 24330 | LR 0.0000100000 | Loss 0.017240 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:13 Epoch 6 | Batch 3292/3508 | Timestep 24340 | LR 0.0000100000 | Loss 0.008169 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:15 Epoch 6 | Batch 3302/3508 | Timestep 24350 | LR 0.0000100000 | Loss 0.034266 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:17 Epoch 6 | Batch 3312/3508 | Timestep 24360 | LR 0.0000100000 | Loss 0.012632 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:19 Epoch 6 | Batch 3322/3508 | Timestep 24370 | LR 0.0000100000 | Loss 0.002248 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:21 Epoch 6 | Batch 3332/3508 | Timestep 24380 | LR 0.0000100000 | Loss 0.031371 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:23 Epoch 6 | Batch 3342/3508 | Timestep 24390 | LR 0.0000100000 | Loss 0.014941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:25 Epoch 6 | Batch 3352/3508 | Timestep 24400 | LR 0.0000100000 | Loss 0.026203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:28 Epoch 6 | Batch 3362/3508 | Timestep 24410 | LR 0.0000100000 | Loss 0.070717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:30 Epoch 6 | Batch 3372/3508 | Timestep 24420 | LR 0.0000100000 | Loss 0.011807 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:32 Epoch 6 | Batch 3382/3508 | Timestep 24430 | LR 0.0000100000 | Loss 0.013688 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:34 Epoch 6 | Batch 3392/3508 | Timestep 24440 | LR 0.0000100000 | Loss 0.009881 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:36 Epoch 6 | Batch 3402/3508 | Timestep 24450 | LR 0.0000100000 | Loss 0.010943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:38 Epoch 6 | Batch 3412/3508 | Timestep 24460 | LR 0.0000100000 | Loss 0.016571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:40 Epoch 6 | Batch 3422/3508 | Timestep 24470 | LR 0.0000100000 | Loss 0.009163 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:43 Epoch 6 | Batch 3432/3508 | Timestep 24480 | LR 0.0000100000 | Loss 0.013825 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:45 Epoch 6 | Batch 3442/3508 | Timestep 24490 | LR 0.0000100000 | Loss 0.019351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:47 Epoch 6 | Batch 3452/3508 | Timestep 24500 | LR 0.0000100000 | Loss 0.013211 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:49 Epoch 6 | Batch 3462/3508 | Timestep 24510 | LR 0.0000100000 | Loss 0.022086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:51 Epoch 6 | Batch 3472/3508 | Timestep 24520 | LR 0.0000100000 | Loss 0.028062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:53 Epoch 6 | Batch 3482/3508 | Timestep 24530 | LR 0.0000100000 | Loss 0.028288 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:55 Epoch 6 | Batch 3492/3508 | Timestep 24540 | LR 0.0000100000 | Loss 0.019023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:57 Epoch 6 | Batch 3502/3508 | Timestep 24550 | LR 0.0000100000 | Loss 0.040876 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:17:58 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 16:18:32 precision recall f1-score support CARDINAL 0.8280 0.8176 0.8228 159 CURR 0.5484 0.7727 0.6415 22 DATE 0.9379 0.9407 0.9393 1669 EVENT 0.6125 0.7986 0.6933 283 FAC 0.6667 0.8136 0.7328 118 GPE 0.9648 0.9729 0.9688 2140 LANGUAGE 0.6190 0.8125 0.7027 16 LAW 0.5000 0.7895 0.6122 19 LOC 0.7143 0.8333 0.7692 90 MONEY 0.7500 0.9000 0.8182 20 NORP 0.7089 0.7033 0.7061 509 OCC 0.8216 0.8730 0.8465 496 ORDINAL 0.9249 0.9395 0.9321 446 ORG 0.9200 0.9362 0.9280 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9307 0.9499 0.9402 679 PRODUCT 0.4167 0.6250 0.5000 8 QUANTITY 0.3333 0.6667 0.4444 3 TIME 0.6250 0.6452 0.6349 31 UNIT 0.6000 0.7500 0.6667 4 WEBSITE 0.4717 0.6250 0.5376 80 micro avg 0.8853 0.9153 0.9001 8670 macro avg 0.7056 0.8174 0.7523 8670 weighted avg 0.8914 0.9153 0.9025 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:42 Epoch 6 | Timestep 24556 | Train Loss 0.018366 | Val Loss 0.052715 | F1 0.900079 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:42 Epoch 7 | Batch 4/3508 | Timestep 24560 | LR 0.0000100000 | Loss 0.022733 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:44 Epoch 7 | Batch 14/3508 | Timestep 24570 | LR 0.0000100000 | Loss 0.013263 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:47 Epoch 7 | Batch 24/3508 | Timestep 24580 | LR 0.0000100000 | Loss 0.012129 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:48 Epoch 7 | Batch 34/3508 | Timestep 24590 | LR 0.0000100000 | Loss 0.070567 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:51 Epoch 7 | Batch 44/3508 | Timestep 24600 | LR 0.0000100000 | Loss 0.014738 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:53 Epoch 7 | Batch 54/3508 | Timestep 24610 | LR 0.0000100000 | Loss 0.010015 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:55 Epoch 7 | Batch 64/3508 | Timestep 24620 | LR 0.0000100000 | Loss 0.005882 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:57 Epoch 7 | Batch 74/3508 | Timestep 24630 | LR 0.0000100000 | Loss 0.003892 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:18:59 Epoch 7 | Batch 84/3508 | Timestep 24640 | LR 0.0000100000 | Loss 0.004021 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:01 Epoch 7 | Batch 94/3508 | Timestep 24650 | LR 0.0000100000 | Loss 0.002158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:04 Epoch 7 | Batch 104/3508 | Timestep 24660 | LR 0.0000100000 | Loss 0.027061 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:06 Epoch 7 | Batch 114/3508 | Timestep 24670 | LR 0.0000100000 | Loss 0.006893 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:08 Epoch 7 | Batch 124/3508 | Timestep 24680 | LR 0.0000100000 | Loss 0.025455 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:11 Epoch 7 | Batch 134/3508 | Timestep 24690 | LR 0.0000100000 | Loss 0.004329 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:13 Epoch 7 | Batch 144/3508 | Timestep 24700 | LR 0.0000100000 | Loss 0.011044 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:15 Epoch 7 | Batch 154/3508 | Timestep 24710 | LR 0.0000100000 | Loss 0.019561 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:17 Epoch 7 | Batch 164/3508 | Timestep 24720 | LR 0.0000100000 | Loss 0.007921 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:19 Epoch 7 | Batch 174/3508 | Timestep 24730 | LR 0.0000100000 | Loss 0.026091 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:21 Epoch 7 | Batch 184/3508 | Timestep 24740 | LR 0.0000100000 | Loss 0.001000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:23 Epoch 7 | Batch 194/3508 | Timestep 24750 | LR 0.0000100000 | Loss 0.006088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:25 Epoch 7 | Batch 204/3508 | Timestep 24760 | LR 0.0000100000 | Loss 0.006328 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:27 Epoch 7 | Batch 214/3508 | Timestep 24770 | LR 0.0000100000 | Loss 0.006819 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:29 Epoch 7 | Batch 224/3508 | Timestep 24780 | LR 0.0000100000 | Loss 0.009559 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:31 Epoch 7 | Batch 234/3508 | Timestep 24790 | LR 0.0000100000 | Loss 0.018007 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:33 Epoch 7 | Batch 244/3508 | Timestep 24800 | LR 0.0000100000 | Loss 0.033200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:36 Epoch 7 | Batch 254/3508 | Timestep 24810 | LR 0.0000100000 | Loss 0.017455 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:38 Epoch 7 | Batch 264/3508 | Timestep 24820 | LR 0.0000100000 | Loss 0.051758 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:40 Epoch 7 | Batch 274/3508 | Timestep 24830 | LR 0.0000100000 | Loss 0.009340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:42 Epoch 7 | Batch 284/3508 | Timestep 24840 | LR 0.0000100000 | Loss 0.018953 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:44 Epoch 7 | Batch 294/3508 | Timestep 24850 | LR 0.0000100000 | Loss 0.016308 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:46 Epoch 7 | Batch 304/3508 | Timestep 24860 | LR 0.0000100000 | Loss 0.009344 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:49 Epoch 7 | Batch 314/3508 | Timestep 24870 | LR 0.0000100000 | Loss 0.010829 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:51 Epoch 7 | Batch 324/3508 | Timestep 24880 | LR 0.0000100000 | Loss 0.026177 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:53 Epoch 7 | Batch 334/3508 | Timestep 24890 | LR 0.0000100000 | Loss 0.004006 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:55 Epoch 7 | Batch 344/3508 | Timestep 24900 | LR 0.0000100000 | Loss 0.020351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:57 Epoch 7 | Batch 354/3508 | Timestep 24910 | LR 0.0000100000 | Loss 0.022569 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:19:59 Epoch 7 | Batch 364/3508 | Timestep 24920 | LR 0.0000100000 | Loss 0.070923 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:02 Epoch 7 | Batch 374/3508 | Timestep 24930 | LR 0.0000100000 | Loss 0.009972 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:03 Epoch 7 | Batch 384/3508 | Timestep 24940 | LR 0.0000100000 | Loss 0.006291 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:06 Epoch 7 | Batch 394/3508 | Timestep 24950 | LR 0.0000100000 | Loss 0.009771 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:08 Epoch 7 | Batch 404/3508 | Timestep 24960 | LR 0.0000100000 | Loss 0.011607 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:11 Epoch 7 | Batch 414/3508 | Timestep 24970 | LR 0.0000100000 | Loss 0.006076 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:13 Epoch 7 | Batch 424/3508 | Timestep 24980 | LR 0.0000100000 | Loss 0.020882 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:15 Epoch 7 | Batch 434/3508 | Timestep 24990 | LR 0.0000100000 | Loss 0.022750 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:17 Epoch 7 | Batch 444/3508 | Timestep 25000 | LR 0.0000100000 | Loss 0.030963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:19 Epoch 7 | Batch 454/3508 | Timestep 25010 | LR 0.0000100000 | Loss 0.019407 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:21 Epoch 7 | Batch 464/3508 | Timestep 25020 | LR 0.0000100000 | Loss 0.002824 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:24 Epoch 7 | Batch 474/3508 | Timestep 25030 | LR 0.0000100000 | Loss 0.008601 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:26 Epoch 7 | Batch 484/3508 | Timestep 25040 | LR 0.0000100000 | Loss 0.010515 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:28 Epoch 7 | Batch 494/3508 | Timestep 25050 | LR 0.0000100000 | Loss 0.011398 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:30 Epoch 7 | Batch 504/3508 | Timestep 25060 | LR 0.0000100000 | Loss 0.020234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:32 Epoch 7 | Batch 514/3508 | Timestep 25070 | LR 0.0000100000 | Loss 0.013034 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:34 Epoch 7 | Batch 524/3508 | Timestep 25080 | LR 0.0000100000 | Loss 0.017394 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:37 Epoch 7 | Batch 534/3508 | Timestep 25090 | LR 0.0000100000 | Loss 0.007369 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:39 Epoch 7 | Batch 544/3508 | Timestep 25100 | LR 0.0000100000 | Loss 0.008523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:41 Epoch 7 | Batch 554/3508 | Timestep 25110 | LR 0.0000100000 | Loss 0.002431 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:43 Epoch 7 | Batch 564/3508 | Timestep 25120 | LR 0.0000100000 | Loss 0.044021 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:45 Epoch 7 | Batch 574/3508 | Timestep 25130 | LR 0.0000100000 | Loss 0.009890 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:47 Epoch 7 | Batch 584/3508 | Timestep 25140 | LR 0.0000100000 | Loss 0.023200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:50 Epoch 7 | Batch 594/3508 | Timestep 25150 | LR 0.0000100000 | Loss 0.016337 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:52 Epoch 7 | Batch 604/3508 | Timestep 25160 | LR 0.0000100000 | Loss 0.011713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:54 Epoch 7 | Batch 614/3508 | Timestep 25170 | LR 0.0000100000 | Loss 0.026444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:57 Epoch 7 | Batch 624/3508 | Timestep 25180 | LR 0.0000100000 | Loss 0.045318 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:20:59 Epoch 7 | Batch 634/3508 | Timestep 25190 | LR 0.0000100000 | Loss 0.006615 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:01 Epoch 7 | Batch 644/3508 | Timestep 25200 | LR 0.0000100000 | Loss 0.037795 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:03 Epoch 7 | Batch 654/3508 | Timestep 25210 | LR 0.0000100000 | Loss 0.002529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:05 Epoch 7 | Batch 664/3508 | Timestep 25220 | LR 0.0000100000 | Loss 0.016279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:07 Epoch 7 | Batch 674/3508 | Timestep 25230 | LR 0.0000100000 | Loss 0.013056 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:10 Epoch 7 | Batch 684/3508 | Timestep 25240 | LR 0.0000100000 | Loss 0.030719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:12 Epoch 7 | Batch 694/3508 | Timestep 25250 | LR 0.0000100000 | Loss 0.016846 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:14 Epoch 7 | Batch 704/3508 | Timestep 25260 | LR 0.0000100000 | Loss 0.010926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:16 Epoch 7 | Batch 714/3508 | Timestep 25270 | LR 0.0000100000 | Loss 0.020286 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:18 Epoch 7 | Batch 724/3508 | Timestep 25280 | LR 0.0000100000 | Loss 0.030085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:21 Epoch 7 | Batch 734/3508 | Timestep 25290 | LR 0.0000100000 | Loss 0.002498 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:23 Epoch 7 | Batch 744/3508 | Timestep 25300 | LR 0.0000100000 | Loss 0.034543 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:25 Epoch 7 | Batch 754/3508 | Timestep 25310 | LR 0.0000100000 | Loss 0.003062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:28 Epoch 7 | Batch 764/3508 | Timestep 25320 | LR 0.0000100000 | Loss 0.015385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:29 Epoch 7 | Batch 774/3508 | Timestep 25330 | LR 0.0000100000 | Loss 0.015990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:31 Epoch 7 | Batch 784/3508 | Timestep 25340 | LR 0.0000100000 | Loss 0.032327 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:34 Epoch 7 | Batch 794/3508 | Timestep 25350 | LR 0.0000100000 | Loss 0.032416 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:36 Epoch 7 | Batch 804/3508 | Timestep 25360 | LR 0.0000100000 | Loss 0.011449 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:38 Epoch 7 | Batch 814/3508 | Timestep 25370 | LR 0.0000100000 | Loss 0.024152 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:41 Epoch 7 | Batch 824/3508 | Timestep 25380 | LR 0.0000100000 | Loss 0.010284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:43 Epoch 7 | Batch 834/3508 | Timestep 25390 | LR 0.0000100000 | Loss 0.005207 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:45 Epoch 7 | Batch 844/3508 | Timestep 25400 | LR 0.0000100000 | Loss 0.030540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:47 Epoch 7 | Batch 854/3508 | Timestep 25410 | LR 0.0000100000 | Loss 0.009063 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:49 Epoch 7 | Batch 864/3508 | Timestep 25420 | LR 0.0000100000 | Loss 0.006232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:51 Epoch 7 | Batch 874/3508 | Timestep 25430 | LR 0.0000100000 | Loss 0.015570 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:53 Epoch 7 | Batch 884/3508 | Timestep 25440 | LR 0.0000100000 | Loss 0.016005 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:55 Epoch 7 | Batch 894/3508 | Timestep 25450 | LR 0.0000100000 | Loss 0.031768 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:57 Epoch 7 | Batch 904/3508 | Timestep 25460 | LR 0.0000100000 | Loss 0.023159 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:21:59 Epoch 7 | Batch 914/3508 | Timestep 25470 | LR 0.0000100000 | Loss 0.008351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:01 Epoch 7 | Batch 924/3508 | Timestep 25480 | LR 0.0000100000 | Loss 0.012442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:03 Epoch 7 | Batch 934/3508 | Timestep 25490 | LR 0.0000100000 | Loss 0.034990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:05 Epoch 7 | Batch 944/3508 | Timestep 25500 | LR 0.0000100000 | Loss 0.029322 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:07 Epoch 7 | Batch 954/3508 | Timestep 25510 | LR 0.0000100000 | Loss 0.028095 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:10 Epoch 7 | Batch 964/3508 | Timestep 25520 | LR 0.0000100000 | Loss 0.003626 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:11 Epoch 7 | Batch 974/3508 | Timestep 25530 | LR 0.0000100000 | Loss 0.005699 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:14 Epoch 7 | Batch 984/3508 | Timestep 25540 | LR 0.0000100000 | Loss 0.012144 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:16 Epoch 7 | Batch 994/3508 | Timestep 25550 | LR 0.0000100000 | Loss 0.032840 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:18 Epoch 7 | Batch 1004/3508 | Timestep 25560 | LR 0.0000100000 | Loss 0.032279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:19 Epoch 7 | Batch 1014/3508 | Timestep 25570 | LR 0.0000100000 | Loss 0.034433 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:21 Epoch 7 | Batch 1024/3508 | Timestep 25580 | LR 0.0000100000 | Loss 0.016606 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:23 Epoch 7 | Batch 1034/3508 | Timestep 25590 | LR 0.0000100000 | Loss 0.028246 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:25 Epoch 7 | Batch 1044/3508 | Timestep 25600 | LR 0.0000100000 | Loss 0.044410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:27 Epoch 7 | Batch 1054/3508 | Timestep 25610 | LR 0.0000100000 | Loss 0.025940 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:29 Epoch 7 | Batch 1064/3508 | Timestep 25620 | LR 0.0000100000 | Loss 0.019177 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:31 Epoch 7 | Batch 1074/3508 | Timestep 25630 | LR 0.0000100000 | Loss 0.011279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:33 Epoch 7 | Batch 1084/3508 | Timestep 25640 | LR 0.0000100000 | Loss 0.000418 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:35 Epoch 7 | Batch 1094/3508 | Timestep 25650 | LR 0.0000100000 | Loss 0.009672 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:37 Epoch 7 | Batch 1104/3508 | Timestep 25660 | LR 0.0000100000 | Loss 0.008466 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:39 Epoch 7 | Batch 1114/3508 | Timestep 25670 | LR 0.0000100000 | Loss 0.006403 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:41 Epoch 7 | Batch 1124/3508 | Timestep 25680 | LR 0.0000100000 | Loss 0.009419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:43 Epoch 7 | Batch 1134/3508 | Timestep 25690 | LR 0.0000100000 | Loss 0.011659 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:46 Epoch 7 | Batch 1144/3508 | Timestep 25700 | LR 0.0000100000 | Loss 0.012865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:48 Epoch 7 | Batch 1154/3508 | Timestep 25710 | LR 0.0000100000 | Loss 0.026252 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:50 Epoch 7 | Batch 1164/3508 | Timestep 25720 | LR 0.0000100000 | Loss 0.020573 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:52 Epoch 7 | Batch 1174/3508 | Timestep 25730 | LR 0.0000100000 | Loss 0.060829 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:54 Epoch 7 | Batch 1184/3508 | Timestep 25740 | LR 0.0000100000 | Loss 0.004944 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:56 Epoch 7 | Batch 1194/3508 | Timestep 25750 | LR 0.0000100000 | Loss 0.014935 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:22:58 Epoch 7 | Batch 1204/3508 | Timestep 25760 | LR 0.0000100000 | Loss 0.016574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:00 Epoch 7 | Batch 1214/3508 | Timestep 25770 | LR 0.0000100000 | Loss 0.001474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:02 Epoch 7 | Batch 1224/3508 | Timestep 25780 | LR 0.0000100000 | Loss 0.007960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:03 Epoch 7 | Batch 1234/3508 | Timestep 25790 | LR 0.0000100000 | Loss 0.118964 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:06 Epoch 7 | Batch 1244/3508 | Timestep 25800 | LR 0.0000100000 | Loss 0.040297 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:08 Epoch 7 | Batch 1254/3508 | Timestep 25810 | LR 0.0000100000 | Loss 0.026739 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:10 Epoch 7 | Batch 1264/3508 | Timestep 25820 | LR 0.0000100000 | Loss 0.022641 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:12 Epoch 7 | Batch 1274/3508 | Timestep 25830 | LR 0.0000100000 | Loss 0.014427 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:14 Epoch 7 | Batch 1284/3508 | Timestep 25840 | LR 0.0000100000 | Loss 0.015124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:17 Epoch 7 | Batch 1294/3508 | Timestep 25850 | LR 0.0000100000 | Loss 0.001095 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:19 Epoch 7 | Batch 1304/3508 | Timestep 25860 | LR 0.0000100000 | Loss 0.029210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:21 Epoch 7 | Batch 1314/3508 | Timestep 25870 | LR 0.0000100000 | Loss 0.011926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:23 Epoch 7 | Batch 1324/3508 | Timestep 25880 | LR 0.0000100000 | Loss 0.006708 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:25 Epoch 7 | Batch 1334/3508 | Timestep 25890 | LR 0.0000100000 | Loss 0.016124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:28 Epoch 7 | Batch 1344/3508 | Timestep 25900 | LR 0.0000100000 | Loss 0.062333 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:29 Epoch 7 | Batch 1354/3508 | Timestep 25910 | LR 0.0000100000 | Loss 0.024446 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:31 Epoch 7 | Batch 1364/3508 | Timestep 25920 | LR 0.0000100000 | Loss 0.018718 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:33 Epoch 7 | Batch 1374/3508 | Timestep 25930 | LR 0.0000100000 | Loss 0.015431 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:35 Epoch 7 | Batch 1384/3508 | Timestep 25940 | LR 0.0000100000 | Loss 0.009861 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:38 Epoch 7 | Batch 1394/3508 | Timestep 25950 | LR 0.0000100000 | Loss 0.033385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:40 Epoch 7 | Batch 1404/3508 | Timestep 25960 | LR 0.0000100000 | Loss 0.016880 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:42 Epoch 7 | Batch 1414/3508 | Timestep 25970 | LR 0.0000100000 | Loss 0.004209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:44 Epoch 7 | Batch 1424/3508 | Timestep 25980 | LR 0.0000100000 | Loss 0.031425 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:46 Epoch 7 | Batch 1434/3508 | Timestep 25990 | LR 0.0000100000 | Loss 0.025114 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:48 Epoch 7 | Batch 1444/3508 | Timestep 26000 | LR 0.0000100000 | Loss 0.010932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:50 Epoch 7 | Batch 1454/3508 | Timestep 26010 | LR 0.0000100000 | Loss 0.015642 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:52 Epoch 7 | Batch 1464/3508 | Timestep 26020 | LR 0.0000100000 | Loss 0.007386 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:54 Epoch 7 | Batch 1474/3508 | Timestep 26030 | LR 0.0000100000 | Loss 0.003316 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:57 Epoch 7 | Batch 1484/3508 | Timestep 26040 | LR 0.0000100000 | Loss 0.005673 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:23:59 Epoch 7 | Batch 1494/3508 | Timestep 26050 | LR 0.0000100000 | Loss 0.025150 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:01 Epoch 7 | Batch 1504/3508 | Timestep 26060 | LR 0.0000100000 | Loss 0.012004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:03 Epoch 7 | Batch 1514/3508 | Timestep 26070 | LR 0.0000100000 | Loss 0.028331 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:05 Epoch 7 | Batch 1524/3508 | Timestep 26080 | LR 0.0000100000 | Loss 0.015715 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:08 Epoch 7 | Batch 1534/3508 | Timestep 26090 | LR 0.0000100000 | Loss 0.012636 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:10 Epoch 7 | Batch 1544/3508 | Timestep 26100 | LR 0.0000100000 | Loss 0.023550 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:12 Epoch 7 | Batch 1554/3508 | Timestep 26110 | LR 0.0000100000 | Loss 0.019207 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:14 Epoch 7 | Batch 1564/3508 | Timestep 26120 | LR 0.0000100000 | Loss 0.012599 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:17 Epoch 7 | Batch 1574/3508 | Timestep 26130 | LR 0.0000100000 | Loss 0.007889 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:19 Epoch 7 | Batch 1584/3508 | Timestep 26140 | LR 0.0000100000 | Loss 0.016125 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:21 Epoch 7 | Batch 1594/3508 | Timestep 26150 | LR 0.0000100000 | Loss 0.009980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:24 Epoch 7 | Batch 1604/3508 | Timestep 26160 | LR 0.0000100000 | Loss 0.008077 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:26 Epoch 7 | Batch 1614/3508 | Timestep 26170 | LR 0.0000100000 | Loss 0.025918 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:28 Epoch 7 | Batch 1624/3508 | Timestep 26180 | LR 0.0000100000 | Loss 0.006497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:30 Epoch 7 | Batch 1634/3508 | Timestep 26190 | LR 0.0000100000 | Loss 0.033255 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:32 Epoch 7 | Batch 1644/3508 | Timestep 26200 | LR 0.0000100000 | Loss 0.014115 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:35 Epoch 7 | Batch 1654/3508 | Timestep 26210 | LR 0.0000100000 | Loss 0.021595 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:37 Epoch 7 | Batch 1664/3508 | Timestep 26220 | LR 0.0000100000 | Loss 0.013273 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:39 Epoch 7 | Batch 1674/3508 | Timestep 26230 | LR 0.0000100000 | Loss 0.018591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:41 Epoch 7 | Batch 1684/3508 | Timestep 26240 | LR 0.0000100000 | Loss 0.065579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:43 Epoch 7 | Batch 1694/3508 | Timestep 26250 | LR 0.0000100000 | Loss 0.005965 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:45 Epoch 7 | Batch 1704/3508 | Timestep 26260 | LR 0.0000100000 | Loss 0.007264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:47 Epoch 7 | Batch 1714/3508 | Timestep 26270 | LR 0.0000100000 | Loss 0.045051 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:49 Epoch 7 | Batch 1724/3508 | Timestep 26280 | LR 0.0000100000 | Loss 0.028876 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:51 Epoch 7 | Batch 1734/3508 | Timestep 26290 | LR 0.0000100000 | Loss 0.008655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:54 Epoch 7 | Batch 1744/3508 | Timestep 26300 | LR 0.0000100000 | Loss 0.010122 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:56 Epoch 7 | Batch 1754/3508 | Timestep 26310 | LR 0.0000100000 | Loss 0.016571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:24:57 Epoch 7 | Batch 1764/3508 | Timestep 26320 | LR 0.0000100000 | Loss 0.010384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:00 Epoch 7 | Batch 1774/3508 | Timestep 26330 | LR 0.0000100000 | Loss 0.012334 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:02 Epoch 7 | Batch 1784/3508 | Timestep 26340 | LR 0.0000100000 | Loss 0.011329 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:04 Epoch 7 | Batch 1794/3508 | Timestep 26350 | LR 0.0000100000 | Loss 0.004533 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:07 Epoch 7 | Batch 1804/3508 | Timestep 26360 | LR 0.0000100000 | Loss 0.024234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:09 Epoch 7 | Batch 1814/3508 | Timestep 26370 | LR 0.0000100000 | Loss 0.005912 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:11 Epoch 7 | Batch 1824/3508 | Timestep 26380 | LR 0.0000100000 | Loss 0.021877 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:13 Epoch 7 | Batch 1834/3508 | Timestep 26390 | LR 0.0000100000 | Loss 0.022469 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:15 Epoch 7 | Batch 1844/3508 | Timestep 26400 | LR 0.0000100000 | Loss 0.053087 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:17 Epoch 7 | Batch 1854/3508 | Timestep 26410 | LR 0.0000100000 | Loss 0.006467 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:19 Epoch 7 | Batch 1864/3508 | Timestep 26420 | LR 0.0000100000 | Loss 0.007990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:21 Epoch 7 | Batch 1874/3508 | Timestep 26430 | LR 0.0000100000 | Loss 0.025955 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:23 Epoch 7 | Batch 1884/3508 | Timestep 26440 | LR 0.0000100000 | Loss 0.014626 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:25 Epoch 7 | Batch 1894/3508 | Timestep 26450 | LR 0.0000100000 | Loss 0.002966 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:27 Epoch 7 | Batch 1904/3508 | Timestep 26460 | LR 0.0000100000 | Loss 0.024458 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:29 Epoch 7 | Batch 1914/3508 | Timestep 26470 | LR 0.0000100000 | Loss 0.015409 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:32 Epoch 7 | Batch 1924/3508 | Timestep 26480 | LR 0.0000100000 | Loss 0.028659 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:34 Epoch 7 | Batch 1934/3508 | Timestep 26490 | LR 0.0000100000 | Loss 0.011905 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:36 Epoch 7 | Batch 1944/3508 | Timestep 26500 | LR 0.0000100000 | Loss 0.005640 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:38 Epoch 7 | Batch 1954/3508 | Timestep 26510 | LR 0.0000100000 | Loss 0.025552 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:40 Epoch 7 | Batch 1964/3508 | Timestep 26520 | LR 0.0000100000 | Loss 0.023605 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:43 Epoch 7 | Batch 1974/3508 | Timestep 26530 | LR 0.0000100000 | Loss 0.004333 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:44 Epoch 7 | Batch 1984/3508 | Timestep 26540 | LR 0.0000100000 | Loss 0.016406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:47 Epoch 7 | Batch 1994/3508 | Timestep 26550 | LR 0.0000100000 | Loss 0.004890 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:49 Epoch 7 | Batch 2004/3508 | Timestep 26560 | LR 0.0000100000 | Loss 0.041989 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:51 Epoch 7 | Batch 2014/3508 | Timestep 26570 | LR 0.0000100000 | Loss 0.025589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:53 Epoch 7 | Batch 2024/3508 | Timestep 26580 | LR 0.0000100000 | Loss 0.018209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:55 Epoch 7 | Batch 2034/3508 | Timestep 26590 | LR 0.0000100000 | Loss 0.034730 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:57 Epoch 7 | Batch 2044/3508 | Timestep 26600 | LR 0.0000100000 | Loss 0.010174 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:25:59 Epoch 7 | Batch 2054/3508 | Timestep 26610 | LR 0.0000100000 | Loss 0.029993 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:01 Epoch 7 | Batch 2064/3508 | Timestep 26620 | LR 0.0000100000 | Loss 0.014432 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:03 Epoch 7 | Batch 2074/3508 | Timestep 26630 | LR 0.0000100000 | Loss 0.022488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:06 Epoch 7 | Batch 2084/3508 | Timestep 26640 | LR 0.0000100000 | Loss 0.006074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:08 Epoch 7 | Batch 2094/3508 | Timestep 26650 | LR 0.0000100000 | Loss 0.006220 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:10 Epoch 7 | Batch 2104/3508 | Timestep 26660 | LR 0.0000100000 | Loss 0.017558 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:13 Epoch 7 | Batch 2114/3508 | Timestep 26670 | LR 0.0000100000 | Loss 0.016646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:15 Epoch 7 | Batch 2124/3508 | Timestep 26680 | LR 0.0000100000 | Loss 0.006357 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:17 Epoch 7 | Batch 2134/3508 | Timestep 26690 | LR 0.0000100000 | Loss 0.017351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:19 Epoch 7 | Batch 2144/3508 | Timestep 26700 | LR 0.0000100000 | Loss 0.016147 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:21 Epoch 7 | Batch 2154/3508 | Timestep 26710 | LR 0.0000100000 | Loss 0.040549 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:23 Epoch 7 | Batch 2164/3508 | Timestep 26720 | LR 0.0000100000 | Loss 0.009867 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:25 Epoch 7 | Batch 2174/3508 | Timestep 26730 | LR 0.0000100000 | Loss 0.047566 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:28 Epoch 7 | Batch 2184/3508 | Timestep 26740 | LR 0.0000100000 | Loss 0.023831 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:30 Epoch 7 | Batch 2194/3508 | Timestep 26750 | LR 0.0000100000 | Loss 0.001500 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:32 Epoch 7 | Batch 2204/3508 | Timestep 26760 | LR 0.0000100000 | Loss 0.024842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:34 Epoch 7 | Batch 2214/3508 | Timestep 26770 | LR 0.0000100000 | Loss 0.003070 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:36 Epoch 7 | Batch 2224/3508 | Timestep 26780 | LR 0.0000100000 | Loss 0.026154 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:39 Epoch 7 | Batch 2234/3508 | Timestep 26790 | LR 0.0000100000 | Loss 0.006799 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:40 Epoch 7 | Batch 2244/3508 | Timestep 26800 | LR 0.0000100000 | Loss 0.007381 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:43 Epoch 7 | Batch 2254/3508 | Timestep 26810 | LR 0.0000100000 | Loss 0.021570 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:45 Epoch 7 | Batch 2264/3508 | Timestep 26820 | LR 0.0000100000 | Loss 0.027825 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:48 Epoch 7 | Batch 2274/3508 | Timestep 26830 | LR 0.0000100000 | Loss 0.003098 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:49 Epoch 7 | Batch 2284/3508 | Timestep 26840 | LR 0.0000100000 | Loss 0.002459 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:52 Epoch 7 | Batch 2294/3508 | Timestep 26850 | LR 0.0000100000 | Loss 0.015933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:54 Epoch 7 | Batch 2304/3508 | Timestep 26860 | LR 0.0000100000 | Loss 0.028508 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:56 Epoch 7 | Batch 2314/3508 | Timestep 26870 | LR 0.0000100000 | Loss 0.010384 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:26:58 Epoch 7 | Batch 2324/3508 | Timestep 26880 | LR 0.0000100000 | Loss 0.011200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:00 Epoch 7 | Batch 2334/3508 | Timestep 26890 | LR 0.0000100000 | Loss 0.011852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:02 Epoch 7 | Batch 2344/3508 | Timestep 26900 | LR 0.0000100000 | Loss 0.007361 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:04 Epoch 7 | Batch 2354/3508 | Timestep 26910 | LR 0.0000100000 | Loss 0.006134 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:07 Epoch 7 | Batch 2364/3508 | Timestep 26920 | LR 0.0000100000 | Loss 0.008185 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:09 Epoch 7 | Batch 2374/3508 | Timestep 26930 | LR 0.0000100000 | Loss 0.009475 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:11 Epoch 7 | Batch 2384/3508 | Timestep 26940 | LR 0.0000100000 | Loss 0.015906 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:13 Epoch 7 | Batch 2394/3508 | Timestep 26950 | LR 0.0000100000 | Loss 0.018961 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:16 Epoch 7 | Batch 2404/3508 | Timestep 26960 | LR 0.0000100000 | Loss 0.015374 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:18 Epoch 7 | Batch 2414/3508 | Timestep 26970 | LR 0.0000100000 | Loss 0.047571 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:20 Epoch 7 | Batch 2424/3508 | Timestep 26980 | LR 0.0000100000 | Loss 0.011874 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:22 Epoch 7 | Batch 2434/3508 | Timestep 26990 | LR 0.0000100000 | Loss 0.004601 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:25 Epoch 7 | Batch 2444/3508 | Timestep 27000 | LR 0.0000100000 | Loss 0.020528 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:27 Epoch 7 | Batch 2454/3508 | Timestep 27010 | LR 0.0000100000 | Loss 0.029959 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:29 Epoch 7 | Batch 2464/3508 | Timestep 27020 | LR 0.0000100000 | Loss 0.014853 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:31 Epoch 7 | Batch 2474/3508 | Timestep 27030 | LR 0.0000100000 | Loss 0.017854 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:33 Epoch 7 | Batch 2484/3508 | Timestep 27040 | LR 0.0000100000 | Loss 0.003624 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:35 Epoch 7 | Batch 2494/3508 | Timestep 27050 | LR 0.0000100000 | Loss 0.033881 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:37 Epoch 7 | Batch 2504/3508 | Timestep 27060 | LR 0.0000100000 | Loss 0.038666 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:39 Epoch 7 | Batch 2514/3508 | Timestep 27070 | LR 0.0000100000 | Loss 0.007122 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:41 Epoch 7 | Batch 2524/3508 | Timestep 27080 | LR 0.0000100000 | Loss 0.019943 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:43 Epoch 7 | Batch 2534/3508 | Timestep 27090 | LR 0.0000100000 | Loss 0.007228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:44 Epoch 7 | Batch 2544/3508 | Timestep 27100 | LR 0.0000100000 | Loss 0.004699 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:46 Epoch 7 | Batch 2554/3508 | Timestep 27110 | LR 0.0000100000 | Loss 0.013456 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:48 Epoch 7 | Batch 2564/3508 | Timestep 27120 | LR 0.0000100000 | Loss 0.004318 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:51 Epoch 7 | Batch 2574/3508 | Timestep 27130 | LR 0.0000100000 | Loss 0.004456 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:53 Epoch 7 | Batch 2584/3508 | Timestep 27140 | LR 0.0000100000 | Loss 0.009434 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:55 Epoch 7 | Batch 2594/3508 | Timestep 27150 | LR 0.0000100000 | Loss 0.029969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:27:58 Epoch 7 | Batch 2604/3508 | Timestep 27160 | LR 0.0000100000 | Loss 0.004973 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:00 Epoch 7 | Batch 2614/3508 | Timestep 27170 | LR 0.0000100000 | Loss 0.007353 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:02 Epoch 7 | Batch 2624/3508 | Timestep 27180 | LR 0.0000100000 | Loss 0.009579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:04 Epoch 7 | Batch 2634/3508 | Timestep 27190 | LR 0.0000100000 | Loss 0.004228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:07 Epoch 7 | Batch 2644/3508 | Timestep 27200 | LR 0.0000100000 | Loss 0.028898 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:09 Epoch 7 | Batch 2654/3508 | Timestep 27210 | LR 0.0000100000 | Loss 0.012510 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:11 Epoch 7 | Batch 2664/3508 | Timestep 27220 | LR 0.0000100000 | Loss 0.002316 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:13 Epoch 7 | Batch 2674/3508 | Timestep 27230 | LR 0.0000100000 | Loss 0.006072 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:15 Epoch 7 | Batch 2684/3508 | Timestep 27240 | LR 0.0000100000 | Loss 0.010273 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:17 Epoch 7 | Batch 2694/3508 | Timestep 27250 | LR 0.0000100000 | Loss 0.006805 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:20 Epoch 7 | Batch 2704/3508 | Timestep 27260 | LR 0.0000100000 | Loss 0.011723 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:22 Epoch 7 | Batch 2714/3508 | Timestep 27270 | LR 0.0000100000 | Loss 0.038289 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:24 Epoch 7 | Batch 2724/3508 | Timestep 27280 | LR 0.0000100000 | Loss 0.009069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:26 Epoch 7 | Batch 2734/3508 | Timestep 27290 | LR 0.0000100000 | Loss 0.017836 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:28 Epoch 7 | Batch 2744/3508 | Timestep 27300 | LR 0.0000100000 | Loss 0.013238 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:30 Epoch 7 | Batch 2754/3508 | Timestep 27310 | LR 0.0000100000 | Loss 0.007351 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:32 Epoch 7 | Batch 2764/3508 | Timestep 27320 | LR 0.0000100000 | Loss 0.013315 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:34 Epoch 7 | Batch 2774/3508 | Timestep 27330 | LR 0.0000100000 | Loss 0.006311 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:36 Epoch 7 | Batch 2784/3508 | Timestep 27340 | LR 0.0000100000 | Loss 0.024448 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:38 Epoch 7 | Batch 2794/3508 | Timestep 27350 | LR 0.0000100000 | Loss 0.002831 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:41 Epoch 7 | Batch 2804/3508 | Timestep 27360 | LR 0.0000100000 | Loss 0.018837 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:43 Epoch 7 | Batch 2814/3508 | Timestep 27370 | LR 0.0000100000 | Loss 0.038982 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:45 Epoch 7 | Batch 2824/3508 | Timestep 27380 | LR 0.0000100000 | Loss 0.021753 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:47 Epoch 7 | Batch 2834/3508 | Timestep 27390 | LR 0.0000100000 | Loss 0.007552 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:49 Epoch 7 | Batch 2844/3508 | Timestep 27400 | LR 0.0000100000 | Loss 0.011100 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:51 Epoch 7 | Batch 2854/3508 | Timestep 27410 | LR 0.0000100000 | Loss 0.014239 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:53 Epoch 7 | Batch 2864/3508 | Timestep 27420 | LR 0.0000100000 | Loss 0.018515 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:55 Epoch 7 | Batch 2874/3508 | Timestep 27430 | LR 0.0000100000 | Loss 0.011652 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:57 Epoch 7 | Batch 2884/3508 | Timestep 27440 | LR 0.0000100000 | Loss 0.031589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:28:59 Epoch 7 | Batch 2894/3508 | Timestep 27450 | LR 0.0000100000 | Loss 0.009796 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:02 Epoch 7 | Batch 2904/3508 | Timestep 27460 | LR 0.0000100000 | Loss 0.003713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:04 Epoch 7 | Batch 2914/3508 | Timestep 27470 | LR 0.0000100000 | Loss 0.013723 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:06 Epoch 7 | Batch 2924/3508 | Timestep 27480 | LR 0.0000100000 | Loss 0.026829 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:08 Epoch 7 | Batch 2934/3508 | Timestep 27490 | LR 0.0000100000 | Loss 0.015904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:10 Epoch 7 | Batch 2944/3508 | Timestep 27500 | LR 0.0000100000 | Loss 0.035364 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:12 Epoch 7 | Batch 2954/3508 | Timestep 27510 | LR 0.0000100000 | Loss 0.018113 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:14 Epoch 7 | Batch 2964/3508 | Timestep 27520 | LR 0.0000100000 | Loss 0.046572 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:16 Epoch 7 | Batch 2974/3508 | Timestep 27530 | LR 0.0000100000 | Loss 0.013099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:18 Epoch 7 | Batch 2984/3508 | Timestep 27540 | LR 0.0000100000 | Loss 0.002529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:20 Epoch 7 | Batch 2994/3508 | Timestep 27550 | LR 0.0000100000 | Loss 0.012550 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:22 Epoch 7 | Batch 3004/3508 | Timestep 27560 | LR 0.0000100000 | Loss 0.018880 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:25 Epoch 7 | Batch 3014/3508 | Timestep 27570 | LR 0.0000100000 | Loss 0.002186 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:27 Epoch 7 | Batch 3024/3508 | Timestep 27580 | LR 0.0000100000 | Loss 0.020637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:29 Epoch 7 | Batch 3034/3508 | Timestep 27590 | LR 0.0000100000 | Loss 0.002118 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:32 Epoch 7 | Batch 3044/3508 | Timestep 27600 | LR 0.0000100000 | Loss 0.033678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:34 Epoch 7 | Batch 3054/3508 | Timestep 27610 | LR 0.0000100000 | Loss 0.027690 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:36 Epoch 7 | Batch 3064/3508 | Timestep 27620 | LR 0.0000100000 | Loss 0.018974 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:38 Epoch 7 | Batch 3074/3508 | Timestep 27630 | LR 0.0000100000 | Loss 0.015283 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:41 Epoch 7 | Batch 3084/3508 | Timestep 27640 | LR 0.0000100000 | Loss 0.073806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:43 Epoch 7 | Batch 3094/3508 | Timestep 27650 | LR 0.0000100000 | Loss 0.007128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:45 Epoch 7 | Batch 3104/3508 | Timestep 27660 | LR 0.0000100000 | Loss 0.010955 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:47 Epoch 7 | Batch 3114/3508 | Timestep 27670 | LR 0.0000100000 | Loss 0.020017 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:49 Epoch 7 | Batch 3124/3508 | Timestep 27680 | LR 0.0000100000 | Loss 0.042721 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:51 Epoch 7 | Batch 3134/3508 | Timestep 27690 | LR 0.0000100000 | Loss 0.006158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:54 Epoch 7 | Batch 3144/3508 | Timestep 27700 | LR 0.0000100000 | Loss 0.014617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:56 Epoch 7 | Batch 3154/3508 | Timestep 27710 | LR 0.0000100000 | Loss 0.002440 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:29:59 Epoch 7 | Batch 3164/3508 | Timestep 27720 | LR 0.0000100000 | Loss 0.025286 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:01 Epoch 7 | Batch 3174/3508 | Timestep 27730 | LR 0.0000100000 | Loss 0.002343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:03 Epoch 7 | Batch 3184/3508 | Timestep 27740 | LR 0.0000100000 | Loss 0.015148 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:05 Epoch 7 | Batch 3194/3508 | Timestep 27750 | LR 0.0000100000 | Loss 0.034802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:07 Epoch 7 | Batch 3204/3508 | Timestep 27760 | LR 0.0000100000 | Loss 0.011589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:10 Epoch 7 | Batch 3214/3508 | Timestep 27770 | LR 0.0000100000 | Loss 0.008067 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:12 Epoch 7 | Batch 3224/3508 | Timestep 27780 | LR 0.0000100000 | Loss 0.019114 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:14 Epoch 7 | Batch 3234/3508 | Timestep 27790 | LR 0.0000100000 | Loss 0.004378 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:16 Epoch 7 | Batch 3244/3508 | Timestep 27800 | LR 0.0000100000 | Loss 0.058159 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:18 Epoch 7 | Batch 3254/3508 | Timestep 27810 | LR 0.0000100000 | Loss 0.017803 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:21 Epoch 7 | Batch 3264/3508 | Timestep 27820 | LR 0.0000100000 | Loss 0.004489 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:23 Epoch 7 | Batch 3274/3508 | Timestep 27830 | LR 0.0000100000 | Loss 0.020088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:25 Epoch 7 | Batch 3284/3508 | Timestep 27840 | LR 0.0000100000 | Loss 0.041061 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:27 Epoch 7 | Batch 3294/3508 | Timestep 27850 | LR 0.0000100000 | Loss 0.012748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:29 Epoch 7 | Batch 3304/3508 | Timestep 27860 | LR 0.0000100000 | Loss 0.007560 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:31 Epoch 7 | Batch 3314/3508 | Timestep 27870 | LR 0.0000100000 | Loss 0.008537 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:33 Epoch 7 | Batch 3324/3508 | Timestep 27880 | LR 0.0000100000 | Loss 0.009246 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:35 Epoch 7 | Batch 3334/3508 | Timestep 27890 | LR 0.0000100000 | Loss 0.008804 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:38 Epoch 7 | Batch 3344/3508 | Timestep 27900 | LR 0.0000100000 | Loss 0.019096 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:40 Epoch 7 | Batch 3354/3508 | Timestep 27910 | LR 0.0000100000 | Loss 0.006506 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:42 Epoch 7 | Batch 3364/3508 | Timestep 27920 | LR 0.0000100000 | Loss 0.006476 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:44 Epoch 7 | Batch 3374/3508 | Timestep 27930 | LR 0.0000100000 | Loss 0.014906 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:46 Epoch 7 | Batch 3384/3508 | Timestep 27940 | LR 0.0000100000 | Loss 0.041561 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:49 Epoch 7 | Batch 3394/3508 | Timestep 27950 | LR 0.0000100000 | Loss 0.046635 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:51 Epoch 7 | Batch 3404/3508 | Timestep 27960 | LR 0.0000100000 | Loss 0.019952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:53 Epoch 7 | Batch 3414/3508 | Timestep 27970 | LR 0.0000100000 | Loss 0.006664 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:56 Epoch 7 | Batch 3424/3508 | Timestep 27980 | LR 0.0000100000 | Loss 0.003406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:30:58 Epoch 7 | Batch 3434/3508 | Timestep 27990 | LR 0.0000100000 | Loss 0.013209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:00 Epoch 7 | Batch 3444/3508 | Timestep 28000 | LR 0.0000100000 | Loss 0.062838 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:03 Epoch 7 | Batch 3454/3508 | Timestep 28010 | LR 0.0000100000 | Loss 0.003998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:05 Epoch 7 | Batch 3464/3508 | Timestep 28020 | LR 0.0000100000 | Loss 0.001974 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:07 Epoch 7 | Batch 3474/3508 | Timestep 28030 | LR 0.0000100000 | Loss 0.005274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:09 Epoch 7 | Batch 3484/3508 | Timestep 28040 | LR 0.0000100000 | Loss 0.014594 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:12 Epoch 7 | Batch 3494/3508 | Timestep 28050 | LR 0.0000100000 | Loss 0.033001 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:14 Epoch 7 | Batch 3504/3508 | Timestep 28060 | LR 0.0000100000 | Loss 0.016922 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:15 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 16:31:48 precision recall f1-score support CARDINAL 0.8323 0.8113 0.8217 159 CURR 0.7826 0.8182 0.8000 22 DATE 0.9328 0.9395 0.9361 1669 EVENT 0.6698 0.7668 0.7150 283 FAC 0.6875 0.8390 0.7557 118 GPE 0.9665 0.9696 0.9680 2140 LANGUAGE 0.6190 0.8125 0.7027 16 LAW 0.3939 0.6842 0.5000 19 LOC 0.7087 0.8111 0.7565 90 MONEY 0.7391 0.8500 0.7907 20 NORP 0.7203 0.7387 0.7294 509 OCC 0.8359 0.8730 0.8540 496 ORDINAL 0.9116 0.9484 0.9297 446 ORG 0.9171 0.9432 0.9300 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9408 0.9588 0.9497 679 PRODUCT 0.8333 0.6250 0.7143 8 QUANTITY 0.3333 0.6667 0.4444 3 TIME 0.5098 0.8387 0.6341 31 UNIT 0.6000 0.7500 0.6667 4 WEBSITE 0.5213 0.6125 0.5632 80 micro avg 0.8902 0.9183 0.9041 8670 macro avg 0.7323 0.8218 0.7677 8670 weighted avg 0.8948 0.9183 0.9059 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:58 Epoch 7 | Timestep 28064 | Train Loss 0.015874 | Val Loss 0.053138 | F1 0.904054 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:31:59 Epoch 8 | Batch 6/3508 | Timestep 28070 | LR 0.0000100000 | Loss 0.022459 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:01 Epoch 8 | Batch 16/3508 | Timestep 28080 | LR 0.0000100000 | Loss 0.005770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:03 Epoch 8 | Batch 26/3508 | Timestep 28090 | LR 0.0000100000 | Loss 0.019842 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:05 Epoch 8 | Batch 36/3508 | Timestep 28100 | LR 0.0000100000 | Loss 0.009975 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:07 Epoch 8 | Batch 46/3508 | Timestep 28110 | LR 0.0000100000 | Loss 0.009290 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:09 Epoch 8 | Batch 56/3508 | Timestep 28120 | LR 0.0000100000 | Loss 0.076963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:11 Epoch 8 | Batch 66/3508 | Timestep 28130 | LR 0.0000100000 | Loss 0.018904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:13 Epoch 8 | Batch 76/3508 | Timestep 28140 | LR 0.0000100000 | Loss 0.011404 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:16 Epoch 8 | Batch 86/3508 | Timestep 28150 | LR 0.0000100000 | Loss 0.039467 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:18 Epoch 8 | Batch 96/3508 | Timestep 28160 | LR 0.0000100000 | Loss 0.008074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:20 Epoch 8 | Batch 106/3508 | Timestep 28170 | LR 0.0000100000 | Loss 0.030100 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:22 Epoch 8 | Batch 116/3508 | Timestep 28180 | LR 0.0000100000 | Loss 0.008621 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:24 Epoch 8 | Batch 126/3508 | Timestep 28190 | LR 0.0000100000 | Loss 0.042891 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:26 Epoch 8 | Batch 136/3508 | Timestep 28200 | LR 0.0000100000 | Loss 0.014966 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:28 Epoch 8 | Batch 146/3508 | Timestep 28210 | LR 0.0000100000 | Loss 0.014241 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:30 Epoch 8 | Batch 156/3508 | Timestep 28220 | LR 0.0000100000 | Loss 0.003120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:32 Epoch 8 | Batch 166/3508 | Timestep 28230 | LR 0.0000100000 | Loss 0.012440 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:34 Epoch 8 | Batch 176/3508 | Timestep 28240 | LR 0.0000100000 | Loss 0.013158 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:36 Epoch 8 | Batch 186/3508 | Timestep 28250 | LR 0.0000100000 | Loss 0.011415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:37 Epoch 8 | Batch 196/3508 | Timestep 28260 | LR 0.0000100000 | Loss 0.026320 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:40 Epoch 8 | Batch 206/3508 | Timestep 28270 | LR 0.0000100000 | Loss 0.005716 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:42 Epoch 8 | Batch 216/3508 | Timestep 28280 | LR 0.0000100000 | Loss 0.015855 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:44 Epoch 8 | Batch 226/3508 | Timestep 28290 | LR 0.0000100000 | Loss 0.009782 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:47 Epoch 8 | Batch 236/3508 | Timestep 28300 | LR 0.0000100000 | Loss 0.015696 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:49 Epoch 8 | Batch 246/3508 | Timestep 28310 | LR 0.0000100000 | Loss 0.002759 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:51 Epoch 8 | Batch 256/3508 | Timestep 28320 | LR 0.0000100000 | Loss 0.033609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:53 Epoch 8 | Batch 266/3508 | Timestep 28330 | LR 0.0000100000 | Loss 0.007212 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:55 Epoch 8 | Batch 276/3508 | Timestep 28340 | LR 0.0000100000 | Loss 0.004761 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:32:58 Epoch 8 | Batch 286/3508 | Timestep 28350 | LR 0.0000100000 | Loss 0.003951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:00 Epoch 8 | Batch 296/3508 | Timestep 28360 | LR 0.0000100000 | Loss 0.010142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:02 Epoch 8 | Batch 306/3508 | Timestep 28370 | LR 0.0000100000 | Loss 0.002981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:05 Epoch 8 | Batch 316/3508 | Timestep 28380 | LR 0.0000100000 | Loss 0.004712 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:07 Epoch 8 | Batch 326/3508 | Timestep 28390 | LR 0.0000100000 | Loss 0.013853 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:09 Epoch 8 | Batch 336/3508 | Timestep 28400 | LR 0.0000100000 | Loss 0.015007 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:11 Epoch 8 | Batch 346/3508 | Timestep 28410 | LR 0.0000100000 | Loss 0.006639 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:13 Epoch 8 | Batch 356/3508 | Timestep 28420 | LR 0.0000100000 | Loss 0.001251 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:15 Epoch 8 | Batch 366/3508 | Timestep 28430 | LR 0.0000100000 | Loss 0.006025 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:18 Epoch 8 | Batch 376/3508 | Timestep 28440 | LR 0.0000100000 | Loss 0.000834 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:20 Epoch 8 | Batch 386/3508 | Timestep 28450 | LR 0.0000100000 | Loss 0.015437 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:22 Epoch 8 | Batch 396/3508 | Timestep 28460 | LR 0.0000100000 | Loss 0.003369 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:24 Epoch 8 | Batch 406/3508 | Timestep 28470 | LR 0.0000100000 | Loss 0.002617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:27 Epoch 8 | Batch 416/3508 | Timestep 28480 | LR 0.0000100000 | Loss 0.009657 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:30 Epoch 8 | Batch 426/3508 | Timestep 28490 | LR 0.0000100000 | Loss 0.010847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:31 Epoch 8 | Batch 436/3508 | Timestep 28500 | LR 0.0000100000 | Loss 0.009412 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:34 Epoch 8 | Batch 446/3508 | Timestep 28510 | LR 0.0000100000 | Loss 0.015139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:36 Epoch 8 | Batch 456/3508 | Timestep 28520 | LR 0.0000100000 | Loss 0.001465 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:38 Epoch 8 | Batch 466/3508 | Timestep 28530 | LR 0.0000100000 | Loss 0.004170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:40 Epoch 8 | Batch 476/3508 | Timestep 28540 | LR 0.0000100000 | Loss 0.015820 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:43 Epoch 8 | Batch 486/3508 | Timestep 28550 | LR 0.0000100000 | Loss 0.022844 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:45 Epoch 8 | Batch 496/3508 | Timestep 28560 | LR 0.0000100000 | Loss 0.014000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:46 Epoch 8 | Batch 506/3508 | Timestep 28570 | LR 0.0000100000 | Loss 0.003070 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:48 Epoch 8 | Batch 516/3508 | Timestep 28580 | LR 0.0000100000 | Loss 0.001980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:50 Epoch 8 | Batch 526/3508 | Timestep 28590 | LR 0.0000100000 | Loss 0.006195 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:52 Epoch 8 | Batch 536/3508 | Timestep 28600 | LR 0.0000100000 | Loss 0.007434 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:54 Epoch 8 | Batch 546/3508 | Timestep 28610 | LR 0.0000100000 | Loss 0.009063 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:57 Epoch 8 | Batch 556/3508 | Timestep 28620 | LR 0.0000100000 | Loss 0.004279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:33:58 Epoch 8 | Batch 566/3508 | Timestep 28630 | LR 0.0000100000 | Loss 0.013676 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:01 Epoch 8 | Batch 576/3508 | Timestep 28640 | LR 0.0000100000 | Loss 0.018274 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:03 Epoch 8 | Batch 586/3508 | Timestep 28650 | LR 0.0000100000 | Loss 0.011235 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:05 Epoch 8 | Batch 596/3508 | Timestep 28660 | LR 0.0000100000 | Loss 0.007294 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:07 Epoch 8 | Batch 606/3508 | Timestep 28670 | LR 0.0000100000 | Loss 0.009918 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:09 Epoch 8 | Batch 616/3508 | Timestep 28680 | LR 0.0000100000 | Loss 0.008911 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:11 Epoch 8 | Batch 626/3508 | Timestep 28690 | LR 0.0000100000 | Loss 0.016574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:13 Epoch 8 | Batch 636/3508 | Timestep 28700 | LR 0.0000100000 | Loss 0.010793 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:16 Epoch 8 | Batch 646/3508 | Timestep 28710 | LR 0.0000100000 | Loss 0.019788 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:18 Epoch 8 | Batch 656/3508 | Timestep 28720 | LR 0.0000100000 | Loss 0.002871 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:20 Epoch 8 | Batch 666/3508 | Timestep 28730 | LR 0.0000100000 | Loss 0.003424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:23 Epoch 8 | Batch 676/3508 | Timestep 28740 | LR 0.0000100000 | Loss 0.005065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:25 Epoch 8 | Batch 686/3508 | Timestep 28750 | LR 0.0000100000 | Loss 0.012109 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:27 Epoch 8 | Batch 696/3508 | Timestep 28760 | LR 0.0000100000 | Loss 0.007067 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:29 Epoch 8 | Batch 706/3508 | Timestep 28770 | LR 0.0000100000 | Loss 0.027413 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:31 Epoch 8 | Batch 716/3508 | Timestep 28780 | LR 0.0000100000 | Loss 0.017633 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:33 Epoch 8 | Batch 726/3508 | Timestep 28790 | LR 0.0000100000 | Loss 0.029276 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:35 Epoch 8 | Batch 736/3508 | Timestep 28800 | LR 0.0000100000 | Loss 0.025469 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:38 Epoch 8 | Batch 746/3508 | Timestep 28810 | LR 0.0000100000 | Loss 0.017955 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:40 Epoch 8 | Batch 756/3508 | Timestep 28820 | LR 0.0000100000 | Loss 0.044187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:43 Epoch 8 | Batch 766/3508 | Timestep 28830 | LR 0.0000100000 | Loss 0.019307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:45 Epoch 8 | Batch 776/3508 | Timestep 28840 | LR 0.0000100000 | Loss 0.007576 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:47 Epoch 8 | Batch 786/3508 | Timestep 28850 | LR 0.0000100000 | Loss 0.021010 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:49 Epoch 8 | Batch 796/3508 | Timestep 28860 | LR 0.0000100000 | Loss 0.019082 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:52 Epoch 8 | Batch 806/3508 | Timestep 28870 | LR 0.0000100000 | Loss 0.018436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:54 Epoch 8 | Batch 816/3508 | Timestep 28880 | LR 0.0000100000 | Loss 0.033139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:57 Epoch 8 | Batch 826/3508 | Timestep 28890 | LR 0.0000100000 | Loss 0.011232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:34:59 Epoch 8 | Batch 836/3508 | Timestep 28900 | LR 0.0000100000 | Loss 0.009800 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:00 Epoch 8 | Batch 846/3508 | Timestep 28910 | LR 0.0000100000 | Loss 0.004822 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:03 Epoch 8 | Batch 856/3508 | Timestep 28920 | LR 0.0000100000 | Loss 0.008365 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:05 Epoch 8 | Batch 866/3508 | Timestep 28930 | LR 0.0000100000 | Loss 0.010083 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:07 Epoch 8 | Batch 876/3508 | Timestep 28940 | LR 0.0000100000 | Loss 0.021228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:09 Epoch 8 | Batch 886/3508 | Timestep 28950 | LR 0.0000100000 | Loss 0.058486 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:11 Epoch 8 | Batch 896/3508 | Timestep 28960 | LR 0.0000100000 | Loss 0.004367 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:13 Epoch 8 | Batch 906/3508 | Timestep 28970 | LR 0.0000100000 | Loss 0.016315 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:16 Epoch 8 | Batch 916/3508 | Timestep 28980 | LR 0.0000100000 | Loss 0.000436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:18 Epoch 8 | Batch 926/3508 | Timestep 28990 | LR 0.0000100000 | Loss 0.014435 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:20 Epoch 8 | Batch 936/3508 | Timestep 29000 | LR 0.0000100000 | Loss 0.003204 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:22 Epoch 8 | Batch 946/3508 | Timestep 29010 | LR 0.0000100000 | Loss 0.002651 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:24 Epoch 8 | Batch 956/3508 | Timestep 29020 | LR 0.0000100000 | Loss 0.004035 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:26 Epoch 8 | Batch 966/3508 | Timestep 29030 | LR 0.0000100000 | Loss 0.005808 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:28 Epoch 8 | Batch 976/3508 | Timestep 29040 | LR 0.0000100000 | Loss 0.003239 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:30 Epoch 8 | Batch 986/3508 | Timestep 29050 | LR 0.0000100000 | Loss 0.012405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:32 Epoch 8 | Batch 996/3508 | Timestep 29060 | LR 0.0000100000 | Loss 0.001971 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:34 Epoch 8 | Batch 1006/3508 | Timestep 29070 | LR 0.0000100000 | Loss 0.011806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:37 Epoch 8 | Batch 1016/3508 | Timestep 29080 | LR 0.0000100000 | Loss 0.005823 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:39 Epoch 8 | Batch 1026/3508 | Timestep 29090 | LR 0.0000100000 | Loss 0.010559 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:41 Epoch 8 | Batch 1036/3508 | Timestep 29100 | LR 0.0000100000 | Loss 0.007073 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:43 Epoch 8 | Batch 1046/3508 | Timestep 29110 | LR 0.0000100000 | Loss 0.007352 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:45 Epoch 8 | Batch 1056/3508 | Timestep 29120 | LR 0.0000100000 | Loss 0.010616 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:48 Epoch 8 | Batch 1066/3508 | Timestep 29130 | LR 0.0000100000 | Loss 0.012495 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:50 Epoch 8 | Batch 1076/3508 | Timestep 29140 | LR 0.0000100000 | Loss 0.019698 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:52 Epoch 8 | Batch 1086/3508 | Timestep 29150 | LR 0.0000100000 | Loss 0.007793 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:55 Epoch 8 | Batch 1096/3508 | Timestep 29160 | LR 0.0000100000 | Loss 0.007688 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:57 Epoch 8 | Batch 1106/3508 | Timestep 29170 | LR 0.0000100000 | Loss 0.005795 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:35:59 Epoch 8 | Batch 1116/3508 | Timestep 29180 | LR 0.0000100000 | Loss 0.012145 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:01 Epoch 8 | Batch 1126/3508 | Timestep 29190 | LR 0.0000100000 | Loss 0.025693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:03 Epoch 8 | Batch 1136/3508 | Timestep 29200 | LR 0.0000100000 | Loss 0.005962 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:05 Epoch 8 | Batch 1146/3508 | Timestep 29210 | LR 0.0000100000 | Loss 0.010131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:07 Epoch 8 | Batch 1156/3508 | Timestep 29220 | LR 0.0000100000 | Loss 0.011026 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:09 Epoch 8 | Batch 1166/3508 | Timestep 29230 | LR 0.0000100000 | Loss 0.015578 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:11 Epoch 8 | Batch 1176/3508 | Timestep 29240 | LR 0.0000100000 | Loss 0.032236 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:14 Epoch 8 | Batch 1186/3508 | Timestep 29250 | LR 0.0000100000 | Loss 0.015022 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:16 Epoch 8 | Batch 1196/3508 | Timestep 29260 | LR 0.0000100000 | Loss 0.002777 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:18 Epoch 8 | Batch 1206/3508 | Timestep 29270 | LR 0.0000100000 | Loss 0.034922 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:20 Epoch 8 | Batch 1216/3508 | Timestep 29280 | LR 0.0000100000 | Loss 0.004143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:22 Epoch 8 | Batch 1226/3508 | Timestep 29290 | LR 0.0000100000 | Loss 0.015497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:24 Epoch 8 | Batch 1236/3508 | Timestep 29300 | LR 0.0000100000 | Loss 0.004593 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:26 Epoch 8 | Batch 1246/3508 | Timestep 29310 | LR 0.0000100000 | Loss 0.021159 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:29 Epoch 8 | Batch 1256/3508 | Timestep 29320 | LR 0.0000100000 | Loss 0.007283 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:31 Epoch 8 | Batch 1266/3508 | Timestep 29330 | LR 0.0000100000 | Loss 0.010258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:34 Epoch 8 | Batch 1276/3508 | Timestep 29340 | LR 0.0000100000 | Loss 0.003744 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:35 Epoch 8 | Batch 1286/3508 | Timestep 29350 | LR 0.0000100000 | Loss 0.003774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:38 Epoch 8 | Batch 1296/3508 | Timestep 29360 | LR 0.0000100000 | Loss 0.002518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:40 Epoch 8 | Batch 1306/3508 | Timestep 29370 | LR 0.0000100000 | Loss 0.002241 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:42 Epoch 8 | Batch 1316/3508 | Timestep 29380 | LR 0.0000100000 | Loss 0.001040 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:44 Epoch 8 | Batch 1326/3508 | Timestep 29390 | LR 0.0000100000 | Loss 0.001826 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:46 Epoch 8 | Batch 1336/3508 | Timestep 29400 | LR 0.0000100000 | Loss 0.024082 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:48 Epoch 8 | Batch 1346/3508 | Timestep 29410 | LR 0.0000100000 | Loss 0.037066 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:50 Epoch 8 | Batch 1356/3508 | Timestep 29420 | LR 0.0000100000 | Loss 0.000454 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:53 Epoch 8 | Batch 1366/3508 | Timestep 29430 | LR 0.0000100000 | Loss 0.010080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:55 Epoch 8 | Batch 1376/3508 | Timestep 29440 | LR 0.0000100000 | Loss 0.019697 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:36:57 Epoch 8 | Batch 1386/3508 | Timestep 29450 | LR 0.0000100000 | Loss 0.045074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:00 Epoch 8 | Batch 1396/3508 | Timestep 29460 | LR 0.0000100000 | Loss 0.003814 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:02 Epoch 8 | Batch 1406/3508 | Timestep 29470 | LR 0.0000100000 | Loss 0.008023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:04 Epoch 8 | Batch 1416/3508 | Timestep 29480 | LR 0.0000100000 | Loss 0.003068 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:06 Epoch 8 | Batch 1426/3508 | Timestep 29490 | LR 0.0000100000 | Loss 0.006314 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:08 Epoch 8 | Batch 1436/3508 | Timestep 29500 | LR 0.0000100000 | Loss 0.004843 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:10 Epoch 8 | Batch 1446/3508 | Timestep 29510 | LR 0.0000100000 | Loss 0.005395 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:12 Epoch 8 | Batch 1456/3508 | Timestep 29520 | LR 0.0000100000 | Loss 0.012255 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:14 Epoch 8 | Batch 1466/3508 | Timestep 29530 | LR 0.0000100000 | Loss 0.009510 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:17 Epoch 8 | Batch 1476/3508 | Timestep 29540 | LR 0.0000100000 | Loss 0.004338 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:18 Epoch 8 | Batch 1486/3508 | Timestep 29550 | LR 0.0000100000 | Loss 0.009121 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:20 Epoch 8 | Batch 1496/3508 | Timestep 29560 | LR 0.0000100000 | Loss 0.002228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:22 Epoch 8 | Batch 1506/3508 | Timestep 29570 | LR 0.0000100000 | Loss 0.021821 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:24 Epoch 8 | Batch 1516/3508 | Timestep 29580 | LR 0.0000100000 | Loss 0.010686 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:26 Epoch 8 | Batch 1526/3508 | Timestep 29590 | LR 0.0000100000 | Loss 0.007424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:29 Epoch 8 | Batch 1536/3508 | Timestep 29600 | LR 0.0000100000 | Loss 0.009738 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:31 Epoch 8 | Batch 1546/3508 | Timestep 29610 | LR 0.0000100000 | Loss 0.002856 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:33 Epoch 8 | Batch 1556/3508 | Timestep 29620 | LR 0.0000100000 | Loss 0.016064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:34 Epoch 8 | Batch 1566/3508 | Timestep 29630 | LR 0.0000100000 | Loss 0.015587 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:36 Epoch 8 | Batch 1576/3508 | Timestep 29640 | LR 0.0000100000 | Loss 0.006105 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:39 Epoch 8 | Batch 1586/3508 | Timestep 29650 | LR 0.0000100000 | Loss 0.014965 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:41 Epoch 8 | Batch 1596/3508 | Timestep 29660 | LR 0.0000100000 | Loss 0.002299 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:43 Epoch 8 | Batch 1606/3508 | Timestep 29670 | LR 0.0000100000 | Loss 0.023097 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:45 Epoch 8 | Batch 1616/3508 | Timestep 29680 | LR 0.0000100000 | Loss 0.004201 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:47 Epoch 8 | Batch 1626/3508 | Timestep 29690 | LR 0.0000100000 | Loss 0.010784 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:49 Epoch 8 | Batch 1636/3508 | Timestep 29700 | LR 0.0000100000 | Loss 0.008615 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:51 Epoch 8 | Batch 1646/3508 | Timestep 29710 | LR 0.0000100000 | Loss 0.009284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:53 Epoch 8 | Batch 1656/3508 | Timestep 29720 | LR 0.0000100000 | Loss 0.024923 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:55 Epoch 8 | Batch 1666/3508 | Timestep 29730 | LR 0.0000100000 | Loss 0.012529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:56 Epoch 8 | Batch 1676/3508 | Timestep 29740 | LR 0.0000100000 | Loss 0.006234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:37:58 Epoch 8 | Batch 1686/3508 | Timestep 29750 | LR 0.0000100000 | Loss 0.033549 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:01 Epoch 8 | Batch 1696/3508 | Timestep 29760 | LR 0.0000100000 | Loss 0.001632 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:03 Epoch 8 | Batch 1706/3508 | Timestep 29770 | LR 0.0000100000 | Loss 0.005885 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:05 Epoch 8 | Batch 1716/3508 | Timestep 29780 | LR 0.0000100000 | Loss 0.008415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:07 Epoch 8 | Batch 1726/3508 | Timestep 29790 | LR 0.0000100000 | Loss 0.026896 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:09 Epoch 8 | Batch 1736/3508 | Timestep 29800 | LR 0.0000100000 | Loss 0.015242 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:11 Epoch 8 | Batch 1746/3508 | Timestep 29810 | LR 0.0000100000 | Loss 0.011800 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:13 Epoch 8 | Batch 1756/3508 | Timestep 29820 | LR 0.0000100000 | Loss 0.003521 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:15 Epoch 8 | Batch 1766/3508 | Timestep 29830 | LR 0.0000100000 | Loss 0.003709 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:18 Epoch 8 | Batch 1776/3508 | Timestep 29840 | LR 0.0000100000 | Loss 0.003478 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:20 Epoch 8 | Batch 1786/3508 | Timestep 29850 | LR 0.0000100000 | Loss 0.014477 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:23 Epoch 8 | Batch 1796/3508 | Timestep 29860 | LR 0.0000100000 | Loss 0.020320 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:25 Epoch 8 | Batch 1806/3508 | Timestep 29870 | LR 0.0000100000 | Loss 0.001079 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:27 Epoch 8 | Batch 1816/3508 | Timestep 29880 | LR 0.0000100000 | Loss 0.007532 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:29 Epoch 8 | Batch 1826/3508 | Timestep 29890 | LR 0.0000100000 | Loss 0.008085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:31 Epoch 8 | Batch 1836/3508 | Timestep 29900 | LR 0.0000100000 | Loss 0.019971 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:33 Epoch 8 | Batch 1846/3508 | Timestep 29910 | LR 0.0000100000 | Loss 0.004550 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:34 Epoch 8 | Batch 1856/3508 | Timestep 29920 | LR 0.0000100000 | Loss 0.017110 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:37 Epoch 8 | Batch 1866/3508 | Timestep 29930 | LR 0.0000100000 | Loss 0.005511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:39 Epoch 8 | Batch 1876/3508 | Timestep 29940 | LR 0.0000100000 | Loss 0.013209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:41 Epoch 8 | Batch 1886/3508 | Timestep 29950 | LR 0.0000100000 | Loss 0.003719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:43 Epoch 8 | Batch 1896/3508 | Timestep 29960 | LR 0.0000100000 | Loss 0.029998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:45 Epoch 8 | Batch 1906/3508 | Timestep 29970 | LR 0.0000100000 | Loss 0.063441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:47 Epoch 8 | Batch 1916/3508 | Timestep 29980 | LR 0.0000100000 | Loss 0.018780 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:49 Epoch 8 | Batch 1926/3508 | Timestep 29990 | LR 0.0000100000 | Loss 0.046103 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:51 Epoch 8 | Batch 1936/3508 | Timestep 30000 | LR 0.0000100000 | Loss 0.012013 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:54 Epoch 8 | Batch 1946/3508 | Timestep 30010 | LR 0.0000100000 | Loss 0.016448 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:57 Epoch 8 | Batch 1956/3508 | Timestep 30020 | LR 0.0000100000 | Loss 0.005385 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:38:59 Epoch 8 | Batch 1966/3508 | Timestep 30030 | LR 0.0000100000 | Loss 0.015858 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:01 Epoch 8 | Batch 1976/3508 | Timestep 30040 | LR 0.0000100000 | Loss 0.009763 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:03 Epoch 8 | Batch 1986/3508 | Timestep 30050 | LR 0.0000100000 | Loss 0.025052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:06 Epoch 8 | Batch 1996/3508 | Timestep 30060 | LR 0.0000100000 | Loss 0.008659 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:07 Epoch 8 | Batch 2006/3508 | Timestep 30070 | LR 0.0000100000 | Loss 0.009157 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:09 Epoch 8 | Batch 2016/3508 | Timestep 30080 | LR 0.0000100000 | Loss 0.020126 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:11 Epoch 8 | Batch 2026/3508 | Timestep 30090 | LR 0.0000100000 | Loss 0.009135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:13 Epoch 8 | Batch 2036/3508 | Timestep 30100 | LR 0.0000100000 | Loss 0.004356 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:15 Epoch 8 | Batch 2046/3508 | Timestep 30110 | LR 0.0000100000 | Loss 0.014182 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:18 Epoch 8 | Batch 2056/3508 | Timestep 30120 | LR 0.0000100000 | Loss 0.011332 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:20 Epoch 8 | Batch 2066/3508 | Timestep 30130 | LR 0.0000100000 | Loss 0.025490 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:22 Epoch 8 | Batch 2076/3508 | Timestep 30140 | LR 0.0000100000 | Loss 0.021511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:24 Epoch 8 | Batch 2086/3508 | Timestep 30150 | LR 0.0000100000 | Loss 0.015356 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:26 Epoch 8 | Batch 2096/3508 | Timestep 30160 | LR 0.0000100000 | Loss 0.007929 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:29 Epoch 8 | Batch 2106/3508 | Timestep 30170 | LR 0.0000100000 | Loss 0.007161 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:31 Epoch 8 | Batch 2116/3508 | Timestep 30180 | LR 0.0000100000 | Loss 0.015798 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:33 Epoch 8 | Batch 2126/3508 | Timestep 30190 | LR 0.0000100000 | Loss 0.001748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:35 Epoch 8 | Batch 2136/3508 | Timestep 30200 | LR 0.0000100000 | Loss 0.011790 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:37 Epoch 8 | Batch 2146/3508 | Timestep 30210 | LR 0.0000100000 | Loss 0.004162 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:39 Epoch 8 | Batch 2156/3508 | Timestep 30220 | LR 0.0000100000 | Loss 0.006136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:42 Epoch 8 | Batch 2166/3508 | Timestep 30230 | LR 0.0000100000 | Loss 0.003137 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:44 Epoch 8 | Batch 2176/3508 | Timestep 30240 | LR 0.0000100000 | Loss 0.007088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:46 Epoch 8 | Batch 2186/3508 | Timestep 30250 | LR 0.0000100000 | Loss 0.006014 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:48 Epoch 8 | Batch 2196/3508 | Timestep 30260 | LR 0.0000100000 | Loss 0.008076 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:51 Epoch 8 | Batch 2206/3508 | Timestep 30270 | LR 0.0000100000 | Loss 0.015405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:52 Epoch 8 | Batch 2216/3508 | Timestep 30280 | LR 0.0000100000 | Loss 0.010461 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:54 Epoch 8 | Batch 2226/3508 | Timestep 30290 | LR 0.0000100000 | Loss 0.021005 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:56 Epoch 8 | Batch 2236/3508 | Timestep 30300 | LR 0.0000100000 | Loss 0.010253 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:39:58 Epoch 8 | Batch 2246/3508 | Timestep 30310 | LR 0.0000100000 | Loss 0.013602 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:00 Epoch 8 | Batch 2256/3508 | Timestep 30320 | LR 0.0000100000 | Loss 0.004558 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:03 Epoch 8 | Batch 2266/3508 | Timestep 30330 | LR 0.0000100000 | Loss 0.002202 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:05 Epoch 8 | Batch 2276/3508 | Timestep 30340 | LR 0.0000100000 | Loss 0.000622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:07 Epoch 8 | Batch 2286/3508 | Timestep 30350 | LR 0.0000100000 | Loss 0.007307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:09 Epoch 8 | Batch 2296/3508 | Timestep 30360 | LR 0.0000100000 | Loss 0.007420 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:11 Epoch 8 | Batch 2306/3508 | Timestep 30370 | LR 0.0000100000 | Loss 0.003609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:13 Epoch 8 | Batch 2316/3508 | Timestep 30380 | LR 0.0000100000 | Loss 0.007285 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:15 Epoch 8 | Batch 2326/3508 | Timestep 30390 | LR 0.0000100000 | Loss 0.006673 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:17 Epoch 8 | Batch 2336/3508 | Timestep 30400 | LR 0.0000100000 | Loss 0.001474 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:19 Epoch 8 | Batch 2346/3508 | Timestep 30410 | LR 0.0000100000 | Loss 0.013095 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:21 Epoch 8 | Batch 2356/3508 | Timestep 30420 | LR 0.0000100000 | Loss 0.004593 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:23 Epoch 8 | Batch 2366/3508 | Timestep 30430 | LR 0.0000100000 | Loss 0.002122 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:25 Epoch 8 | Batch 2376/3508 | Timestep 30440 | LR 0.0000100000 | Loss 0.011116 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:27 Epoch 8 | Batch 2386/3508 | Timestep 30450 | LR 0.0000100000 | Loss 0.001281 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:29 Epoch 8 | Batch 2396/3508 | Timestep 30460 | LR 0.0000100000 | Loss 0.037817 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:31 Epoch 8 | Batch 2406/3508 | Timestep 30470 | LR 0.0000100000 | Loss 0.010138 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:33 Epoch 8 | Batch 2416/3508 | Timestep 30480 | LR 0.0000100000 | Loss 0.027529 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:35 Epoch 8 | Batch 2426/3508 | Timestep 30490 | LR 0.0000100000 | Loss 0.003452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:37 Epoch 8 | Batch 2436/3508 | Timestep 30500 | LR 0.0000100000 | Loss 0.002968 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:39 Epoch 8 | Batch 2446/3508 | Timestep 30510 | LR 0.0000100000 | Loss 0.004503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:41 Epoch 8 | Batch 2456/3508 | Timestep 30520 | LR 0.0000100000 | Loss 0.013231 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:43 Epoch 8 | Batch 2466/3508 | Timestep 30530 | LR 0.0000100000 | Loss 0.007832 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:45 Epoch 8 | Batch 2476/3508 | Timestep 30540 | LR 0.0000100000 | Loss 0.011936 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:48 Epoch 8 | Batch 2486/3508 | Timestep 30550 | LR 0.0000100000 | Loss 0.025767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:49 Epoch 8 | Batch 2496/3508 | Timestep 30560 | LR 0.0000100000 | Loss 0.026631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:51 Epoch 8 | Batch 2506/3508 | Timestep 30570 | LR 0.0000100000 | Loss 0.004393 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:54 Epoch 8 | Batch 2516/3508 | Timestep 30580 | LR 0.0000100000 | Loss 0.028509 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:57 Epoch 8 | Batch 2526/3508 | Timestep 30590 | LR 0.0000100000 | Loss 0.038404 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:40:59 Epoch 8 | Batch 2536/3508 | Timestep 30600 | LR 0.0000100000 | Loss 0.005579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:01 Epoch 8 | Batch 2546/3508 | Timestep 30610 | LR 0.0000100000 | Loss 0.005863 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:03 Epoch 8 | Batch 2556/3508 | Timestep 30620 | LR 0.0000100000 | Loss 0.013961 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:05 Epoch 8 | Batch 2566/3508 | Timestep 30630 | LR 0.0000100000 | Loss 0.032903 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:07 Epoch 8 | Batch 2576/3508 | Timestep 30640 | LR 0.0000100000 | Loss 0.007086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:10 Epoch 8 | Batch 2586/3508 | Timestep 30650 | LR 0.0000100000 | Loss 0.029574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:12 Epoch 8 | Batch 2596/3508 | Timestep 30660 | LR 0.0000100000 | Loss 0.008206 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:14 Epoch 8 | Batch 2606/3508 | Timestep 30670 | LR 0.0000100000 | Loss 0.009309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:16 Epoch 8 | Batch 2616/3508 | Timestep 30680 | LR 0.0000100000 | Loss 0.007781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:18 Epoch 8 | Batch 2626/3508 | Timestep 30690 | LR 0.0000100000 | Loss 0.006767 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:20 Epoch 8 | Batch 2636/3508 | Timestep 30700 | LR 0.0000100000 | Loss 0.026235 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:21 Epoch 8 | Batch 2646/3508 | Timestep 30710 | LR 0.0000100000 | Loss 0.007540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:24 Epoch 8 | Batch 2656/3508 | Timestep 30720 | LR 0.0000100000 | Loss 0.005000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:26 Epoch 8 | Batch 2666/3508 | Timestep 30730 | LR 0.0000100000 | Loss 0.027343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:28 Epoch 8 | Batch 2676/3508 | Timestep 30740 | LR 0.0000100000 | Loss 0.007368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:31 Epoch 8 | Batch 2686/3508 | Timestep 30750 | LR 0.0000100000 | Loss 0.024366 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:33 Epoch 8 | Batch 2696/3508 | Timestep 30760 | LR 0.0000100000 | Loss 0.010356 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:35 Epoch 8 | Batch 2706/3508 | Timestep 30770 | LR 0.0000100000 | Loss 0.008713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:36 Epoch 8 | Batch 2716/3508 | Timestep 30780 | LR 0.0000100000 | Loss 0.001000 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:38 Epoch 8 | Batch 2726/3508 | Timestep 30790 | LR 0.0000100000 | Loss 0.029057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:41 Epoch 8 | Batch 2736/3508 | Timestep 30800 | LR 0.0000100000 | Loss 0.000963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:43 Epoch 8 | Batch 2746/3508 | Timestep 30810 | LR 0.0000100000 | Loss 0.006142 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:45 Epoch 8 | Batch 2756/3508 | Timestep 30820 | LR 0.0000100000 | Loss 0.006061 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:48 Epoch 8 | Batch 2766/3508 | Timestep 30830 | LR 0.0000100000 | Loss 0.008789 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:50 Epoch 8 | Batch 2776/3508 | Timestep 30840 | LR 0.0000100000 | Loss 0.013982 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:52 Epoch 8 | Batch 2786/3508 | Timestep 30850 | LR 0.0000100000 | Loss 0.027026 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:54 Epoch 8 | Batch 2796/3508 | Timestep 30860 | LR 0.0000100000 | Loss 0.016173 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:56 Epoch 8 | Batch 2806/3508 | Timestep 30870 | LR 0.0000100000 | Loss 0.014941 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:41:58 Epoch 8 | Batch 2816/3508 | Timestep 30880 | LR 0.0000100000 | Loss 0.022002 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:00 Epoch 8 | Batch 2826/3508 | Timestep 30890 | LR 0.0000100000 | Loss 0.006605 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:02 Epoch 8 | Batch 2836/3508 | Timestep 30900 | LR 0.0000100000 | Loss 0.010209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:04 Epoch 8 | Batch 2846/3508 | Timestep 30910 | LR 0.0000100000 | Loss 0.020080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:06 Epoch 8 | Batch 2856/3508 | Timestep 30920 | LR 0.0000100000 | Loss 0.004232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:09 Epoch 8 | Batch 2866/3508 | Timestep 30930 | LR 0.0000100000 | Loss 0.008623 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:11 Epoch 8 | Batch 2876/3508 | Timestep 30940 | LR 0.0000100000 | Loss 0.003719 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:14 Epoch 8 | Batch 2886/3508 | Timestep 30950 | LR 0.0000100000 | Loss 0.008222 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:16 Epoch 8 | Batch 2896/3508 | Timestep 30960 | LR 0.0000100000 | Loss 0.063952 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:18 Epoch 8 | Batch 2906/3508 | Timestep 30970 | LR 0.0000100000 | Loss 0.028540 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:20 Epoch 8 | Batch 2916/3508 | Timestep 30980 | LR 0.0000100000 | Loss 0.006128 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:23 Epoch 8 | Batch 2926/3508 | Timestep 30990 | LR 0.0000100000 | Loss 0.013396 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:25 Epoch 8 | Batch 2936/3508 | Timestep 31000 | LR 0.0000100000 | Loss 0.006933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:27 Epoch 8 | Batch 2946/3508 | Timestep 31010 | LR 0.0000100000 | Loss 0.000438 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:28 Epoch 8 | Batch 2956/3508 | Timestep 31020 | LR 0.0000100000 | Loss 0.007818 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:30 Epoch 8 | Batch 2966/3508 | Timestep 31030 | LR 0.0000100000 | Loss 0.006530 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:32 Epoch 8 | Batch 2976/3508 | Timestep 31040 | LR 0.0000100000 | Loss 0.011411 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:34 Epoch 8 | Batch 2986/3508 | Timestep 31050 | LR 0.0000100000 | Loss 0.010354 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:37 Epoch 8 | Batch 2996/3508 | Timestep 31060 | LR 0.0000100000 | Loss 0.012480 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:39 Epoch 8 | Batch 3006/3508 | Timestep 31070 | LR 0.0000100000 | Loss 0.005135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:41 Epoch 8 | Batch 3016/3508 | Timestep 31080 | LR 0.0000100000 | Loss 0.022581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:43 Epoch 8 | Batch 3026/3508 | Timestep 31090 | LR 0.0000100000 | Loss 0.083873 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:45 Epoch 8 | Batch 3036/3508 | Timestep 31100 | LR 0.0000100000 | Loss 0.003672 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:47 Epoch 8 | Batch 3046/3508 | Timestep 31110 | LR 0.0000100000 | Loss 0.049475 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:49 Epoch 8 | Batch 3056/3508 | Timestep 31120 | LR 0.0000100000 | Loss 0.017124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:52 Epoch 8 | Batch 3066/3508 | Timestep 31130 | LR 0.0000100000 | Loss 0.013813 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:54 Epoch 8 | Batch 3076/3508 | Timestep 31140 | LR 0.0000100000 | Loss 0.006015 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:57 Epoch 8 | Batch 3086/3508 | Timestep 31150 | LR 0.0000100000 | Loss 0.003907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:42:59 Epoch 8 | Batch 3096/3508 | Timestep 31160 | LR 0.0000100000 | Loss 0.020025 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:02 Epoch 8 | Batch 3106/3508 | Timestep 31170 | LR 0.0000100000 | Loss 0.002495 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:04 Epoch 8 | Batch 3116/3508 | Timestep 31180 | LR 0.0000100000 | Loss 0.004654 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:06 Epoch 8 | Batch 3126/3508 | Timestep 31190 | LR 0.0000100000 | Loss 0.020334 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:09 Epoch 8 | Batch 3136/3508 | Timestep 31200 | LR 0.0000100000 | Loss 0.006103 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:11 Epoch 8 | Batch 3146/3508 | Timestep 31210 | LR 0.0000100000 | Loss 0.016358 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:13 Epoch 8 | Batch 3156/3508 | Timestep 31220 | LR 0.0000100000 | Loss 0.014048 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:15 Epoch 8 | Batch 3166/3508 | Timestep 31230 | LR 0.0000100000 | Loss 0.022186 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:17 Epoch 8 | Batch 3176/3508 | Timestep 31240 | LR 0.0000100000 | Loss 0.024040 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:19 Epoch 8 | Batch 3186/3508 | Timestep 31250 | LR 0.0000100000 | Loss 0.001036 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:21 Epoch 8 | Batch 3196/3508 | Timestep 31260 | LR 0.0000100000 | Loss 0.022083 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:23 Epoch 8 | Batch 3206/3508 | Timestep 31270 | LR 0.0000100000 | Loss 0.028748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:25 Epoch 8 | Batch 3216/3508 | Timestep 31280 | LR 0.0000100000 | Loss 0.012121 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:28 Epoch 8 | Batch 3226/3508 | Timestep 31290 | LR 0.0000100000 | Loss 0.008723 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:31 Epoch 8 | Batch 3236/3508 | Timestep 31300 | LR 0.0000100000 | Loss 0.007046 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:33 Epoch 8 | Batch 3246/3508 | Timestep 31310 | LR 0.0000100000 | Loss 0.001528 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:35 Epoch 8 | Batch 3256/3508 | Timestep 31320 | LR 0.0000100000 | Loss 0.010779 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:38 Epoch 8 | Batch 3266/3508 | Timestep 31330 | LR 0.0000100000 | Loss 0.003544 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:40 Epoch 8 | Batch 3276/3508 | Timestep 31340 | LR 0.0000100000 | Loss 0.013149 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:42 Epoch 8 | Batch 3286/3508 | Timestep 31350 | LR 0.0000100000 | Loss 0.038171 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:44 Epoch 8 | Batch 3296/3508 | Timestep 31360 | LR 0.0000100000 | Loss 0.010532 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:46 Epoch 8 | Batch 3306/3508 | Timestep 31370 | LR 0.0000100000 | Loss 0.014518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:49 Epoch 8 | Batch 3316/3508 | Timestep 31380 | LR 0.0000100000 | Loss 0.012812 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:51 Epoch 8 | Batch 3326/3508 | Timestep 31390 | LR 0.0000100000 | Loss 0.001846 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:53 Epoch 8 | Batch 3336/3508 | Timestep 31400 | LR 0.0000100000 | Loss 0.010346 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:55 Epoch 8 | Batch 3346/3508 | Timestep 31410 | LR 0.0000100000 | Loss 0.028107 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:43:57 Epoch 8 | Batch 3356/3508 | Timestep 31420 | LR 0.0000100000 | Loss 0.017436 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:00 Epoch 8 | Batch 3366/3508 | Timestep 31430 | LR 0.0000100000 | Loss 0.007791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:02 Epoch 8 | Batch 3376/3508 | Timestep 31440 | LR 0.0000100000 | Loss 0.019074 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:05 Epoch 8 | Batch 3386/3508 | Timestep 31450 | LR 0.0000100000 | Loss 0.010811 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:07 Epoch 8 | Batch 3396/3508 | Timestep 31460 | LR 0.0000100000 | Loss 0.001946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:08 Epoch 8 | Batch 3406/3508 | Timestep 31470 | LR 0.0000100000 | Loss 0.006430 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:11 Epoch 8 | Batch 3416/3508 | Timestep 31480 | LR 0.0000100000 | Loss 0.020813 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:12 Epoch 8 | Batch 3426/3508 | Timestep 31490 | LR 0.0000100000 | Loss 0.032599 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:15 Epoch 8 | Batch 3436/3508 | Timestep 31500 | LR 0.0000100000 | Loss 0.010230 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:17 Epoch 8 | Batch 3446/3508 | Timestep 31510 | LR 0.0000100000 | Loss 0.001261 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:18 Epoch 8 | Batch 3456/3508 | Timestep 31520 | LR 0.0000100000 | Loss 0.001482 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:20 Epoch 8 | Batch 3466/3508 | Timestep 31530 | LR 0.0000100000 | Loss 0.022172 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:23 Epoch 8 | Batch 3476/3508 | Timestep 31540 | LR 0.0000100000 | Loss 0.010986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:24 Epoch 8 | Batch 3486/3508 | Timestep 31550 | LR 0.0000100000 | Loss 0.015728 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:27 Epoch 8 | Batch 3496/3508 | Timestep 31560 | LR 0.0000100000 | Loss 0.007306 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:29 Epoch 8 | Batch 3506/3508 | Timestep 31570 | LR 0.0000100000 | Loss 0.022212 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:44:29 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 16:45:02 precision recall f1-score support CARDINAL 0.8723 0.7736 0.8200 159 CURR 0.8333 0.9091 0.8696 22 DATE 0.9396 0.9419 0.9408 1669 EVENT 0.7526 0.7633 0.7579 283 FAC 0.7059 0.8136 0.7559 118 GPE 0.9640 0.9752 0.9696 2140 LANGUAGE 0.6000 0.7500 0.6667 16 LAW 0.4706 0.8421 0.6038 19 LOC 0.7103 0.8444 0.7716 90 MONEY 0.7083 0.8500 0.7727 20 NORP 0.6416 0.7878 0.7072 509 OCC 0.8004 0.8810 0.8388 496 ORDINAL 0.9336 0.9462 0.9399 446 ORG 0.9202 0.9330 0.9266 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9393 0.9573 0.9482 679 PRODUCT 0.6667 0.7500 0.7059 8 QUANTITY 0.3333 0.6667 0.4444 3 TIME 0.7059 0.7742 0.7385 31 UNIT 0.7500 0.7500 0.7500 4 WEBSITE 0.4407 0.6500 0.5253 80 micro avg 0.8870 0.9210 0.9037 8670 macro avg 0.7434 0.8362 0.7816 8670 weighted avg 0.8943 0.9210 0.9065 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:12 Epoch 8 | Timestep 31572 | Train Loss 0.013545 | Val Loss 0.054194 | F1 0.903689 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:14 Epoch 9 | Batch 8/3508 | Timestep 31580 | LR 0.0000100000 | Loss 0.002197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:17 Epoch 9 | Batch 18/3508 | Timestep 31590 | LR 0.0000100000 | Loss 0.003315 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:19 Epoch 9 | Batch 28/3508 | Timestep 31600 | LR 0.0000100000 | Loss 0.006693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:21 Epoch 9 | Batch 38/3508 | Timestep 31610 | LR 0.0000100000 | Loss 0.026348 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:23 Epoch 9 | Batch 48/3508 | Timestep 31620 | LR 0.0000100000 | Loss 0.003955 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:25 Epoch 9 | Batch 58/3508 | Timestep 31630 | LR 0.0000100000 | Loss 0.011343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:26 Epoch 9 | Batch 68/3508 | Timestep 31640 | LR 0.0000100000 | Loss 0.038753 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:28 Epoch 9 | Batch 78/3508 | Timestep 31650 | LR 0.0000100000 | Loss 0.002722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:30 Epoch 9 | Batch 88/3508 | Timestep 31660 | LR 0.0000100000 | Loss 0.001260 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:32 Epoch 9 | Batch 98/3508 | Timestep 31670 | LR 0.0000100000 | Loss 0.004847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:34 Epoch 9 | Batch 108/3508 | Timestep 31680 | LR 0.0000100000 | Loss 0.003443 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:36 Epoch 9 | Batch 118/3508 | Timestep 31690 | LR 0.0000100000 | Loss 0.007511 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:38 Epoch 9 | Batch 128/3508 | Timestep 31700 | LR 0.0000100000 | Loss 0.033288 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:41 Epoch 9 | Batch 138/3508 | Timestep 31710 | LR 0.0000100000 | Loss 0.002087 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:44 Epoch 9 | Batch 148/3508 | Timestep 31720 | LR 0.0000100000 | Loss 0.010275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:46 Epoch 9 | Batch 158/3508 | Timestep 31730 | LR 0.0000100000 | Loss 0.016720 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:48 Epoch 9 | Batch 168/3508 | Timestep 31740 | LR 0.0000100000 | Loss 0.011994 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:50 Epoch 9 | Batch 178/3508 | Timestep 31750 | LR 0.0000100000 | Loss 0.018033 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:52 Epoch 9 | Batch 188/3508 | Timestep 31760 | LR 0.0000100000 | Loss 0.020926 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:53 Epoch 9 | Batch 198/3508 | Timestep 31770 | LR 0.0000100000 | Loss 0.012289 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:56 Epoch 9 | Batch 208/3508 | Timestep 31780 | LR 0.0000100000 | Loss 0.007021 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:45:58 Epoch 9 | Batch 218/3508 | Timestep 31790 | LR 0.0000100000 | Loss 0.035565 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:00 Epoch 9 | Batch 228/3508 | Timestep 31800 | LR 0.0000100000 | Loss 0.022752 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:02 Epoch 9 | Batch 238/3508 | Timestep 31810 | LR 0.0000100000 | Loss 0.003739 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:04 Epoch 9 | Batch 248/3508 | Timestep 31820 | LR 0.0000100000 | Loss 0.023370 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:06 Epoch 9 | Batch 258/3508 | Timestep 31830 | LR 0.0000100000 | Loss 0.035087 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:08 Epoch 9 | Batch 268/3508 | Timestep 31840 | LR 0.0000100000 | Loss 0.008181 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:11 Epoch 9 | Batch 278/3508 | Timestep 31850 | LR 0.0000100000 | Loss 0.021387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:13 Epoch 9 | Batch 288/3508 | Timestep 31860 | LR 0.0000100000 | Loss 0.023655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:15 Epoch 9 | Batch 298/3508 | Timestep 31870 | LR 0.0000100000 | Loss 0.003042 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:17 Epoch 9 | Batch 308/3508 | Timestep 31880 | LR 0.0000100000 | Loss 0.006233 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:19 Epoch 9 | Batch 318/3508 | Timestep 31890 | LR 0.0000100000 | Loss 0.006523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:21 Epoch 9 | Batch 328/3508 | Timestep 31900 | LR 0.0000100000 | Loss 0.004598 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:23 Epoch 9 | Batch 338/3508 | Timestep 31910 | LR 0.0000100000 | Loss 0.014065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:26 Epoch 9 | Batch 348/3508 | Timestep 31920 | LR 0.0000100000 | Loss 0.017464 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:28 Epoch 9 | Batch 358/3508 | Timestep 31930 | LR 0.0000100000 | Loss 0.034085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:30 Epoch 9 | Batch 368/3508 | Timestep 31940 | LR 0.0000100000 | Loss 0.005609 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:32 Epoch 9 | Batch 378/3508 | Timestep 31950 | LR 0.0000100000 | Loss 0.001581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:34 Epoch 9 | Batch 388/3508 | Timestep 31960 | LR 0.0000100000 | Loss 0.005195 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:36 Epoch 9 | Batch 398/3508 | Timestep 31970 | LR 0.0000100000 | Loss 0.005766 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:39 Epoch 9 | Batch 408/3508 | Timestep 31980 | LR 0.0000100000 | Loss 0.002481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:41 Epoch 9 | Batch 418/3508 | Timestep 31990 | LR 0.0000100000 | Loss 0.006499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:43 Epoch 9 | Batch 428/3508 | Timestep 32000 | LR 0.0000100000 | Loss 0.027919 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:45 Epoch 9 | Batch 438/3508 | Timestep 32010 | LR 0.0000100000 | Loss 0.007130 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:47 Epoch 9 | Batch 448/3508 | Timestep 32020 | LR 0.0000100000 | Loss 0.013909 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:49 Epoch 9 | Batch 458/3508 | Timestep 32030 | LR 0.0000100000 | Loss 0.004398 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:51 Epoch 9 | Batch 468/3508 | Timestep 32040 | LR 0.0000100000 | Loss 0.031199 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:54 Epoch 9 | Batch 478/3508 | Timestep 32050 | LR 0.0000100000 | Loss 0.010987 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:56 Epoch 9 | Batch 488/3508 | Timestep 32060 | LR 0.0000100000 | Loss 0.000674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:46:58 Epoch 9 | Batch 498/3508 | Timestep 32070 | LR 0.0000100000 | Loss 0.004043 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:01 Epoch 9 | Batch 508/3508 | Timestep 32080 | LR 0.0000100000 | Loss 0.036428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:03 Epoch 9 | Batch 518/3508 | Timestep 32090 | LR 0.0000100000 | Loss 0.001526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:05 Epoch 9 | Batch 528/3508 | Timestep 32100 | LR 0.0000100000 | Loss 0.004743 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:07 Epoch 9 | Batch 538/3508 | Timestep 32110 | LR 0.0000100000 | Loss 0.001946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:10 Epoch 9 | Batch 548/3508 | Timestep 32120 | LR 0.0000100000 | Loss 0.025828 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:13 Epoch 9 | Batch 558/3508 | Timestep 32130 | LR 0.0000100000 | Loss 0.005680 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:15 Epoch 9 | Batch 568/3508 | Timestep 32140 | LR 0.0000100000 | Loss 0.002706 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:17 Epoch 9 | Batch 578/3508 | Timestep 32150 | LR 0.0000100000 | Loss 0.008854 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:19 Epoch 9 | Batch 588/3508 | Timestep 32160 | LR 0.0000100000 | Loss 0.009425 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:21 Epoch 9 | Batch 598/3508 | Timestep 32170 | LR 0.0000100000 | Loss 0.015698 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:24 Epoch 9 | Batch 608/3508 | Timestep 32180 | LR 0.0000100000 | Loss 0.013593 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:26 Epoch 9 | Batch 618/3508 | Timestep 32190 | LR 0.0000100000 | Loss 0.018310 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:29 Epoch 9 | Batch 628/3508 | Timestep 32200 | LR 0.0000100000 | Loss 0.007491 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:31 Epoch 9 | Batch 638/3508 | Timestep 32210 | LR 0.0000100000 | Loss 0.014931 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:33 Epoch 9 | Batch 648/3508 | Timestep 32220 | LR 0.0000100000 | Loss 0.008439 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:35 Epoch 9 | Batch 658/3508 | Timestep 32230 | LR 0.0000100000 | Loss 0.004934 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:38 Epoch 9 | Batch 668/3508 | Timestep 32240 | LR 0.0000100000 | Loss 0.007799 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:40 Epoch 9 | Batch 678/3508 | Timestep 32250 | LR 0.0000100000 | Loss 0.002785 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:42 Epoch 9 | Batch 688/3508 | Timestep 32260 | LR 0.0000100000 | Loss 0.014794 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:44 Epoch 9 | Batch 698/3508 | Timestep 32270 | LR 0.0000100000 | Loss 0.007748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:46 Epoch 9 | Batch 708/3508 | Timestep 32280 | LR 0.0000100000 | Loss 0.018096 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:49 Epoch 9 | Batch 718/3508 | Timestep 32290 | LR 0.0000100000 | Loss 0.001090 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:50 Epoch 9 | Batch 728/3508 | Timestep 32300 | LR 0.0000100000 | Loss 0.013428 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:53 Epoch 9 | Batch 738/3508 | Timestep 32310 | LR 0.0000100000 | Loss 0.008355 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:55 Epoch 9 | Batch 748/3508 | Timestep 32320 | LR 0.0000100000 | Loss 0.007062 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:57 Epoch 9 | Batch 758/3508 | Timestep 32330 | LR 0.0000100000 | Loss 0.006648 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:47:59 Epoch 9 | Batch 768/3508 | Timestep 32340 | LR 0.0000100000 | Loss 0.023835 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:01 Epoch 9 | Batch 778/3508 | Timestep 32350 | LR 0.0000100000 | Loss 0.000754 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:03 Epoch 9 | Batch 788/3508 | Timestep 32360 | LR 0.0000100000 | Loss 0.005462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:05 Epoch 9 | Batch 798/3508 | Timestep 32370 | LR 0.0000100000 | Loss 0.001432 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:07 Epoch 9 | Batch 808/3508 | Timestep 32380 | LR 0.0000100000 | Loss 0.012664 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:10 Epoch 9 | Batch 818/3508 | Timestep 32390 | LR 0.0000100000 | Loss 0.008932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:12 Epoch 9 | Batch 828/3508 | Timestep 32400 | LR 0.0000100000 | Loss 0.000339 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:14 Epoch 9 | Batch 838/3508 | Timestep 32410 | LR 0.0000100000 | Loss 0.022171 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:16 Epoch 9 | Batch 848/3508 | Timestep 32420 | LR 0.0000100000 | Loss 0.003981 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:19 Epoch 9 | Batch 858/3508 | Timestep 32430 | LR 0.0000100000 | Loss 0.007018 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:21 Epoch 9 | Batch 868/3508 | Timestep 32440 | LR 0.0000100000 | Loss 0.010469 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:23 Epoch 9 | Batch 878/3508 | Timestep 32450 | LR 0.0000100000 | Loss 0.007852 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:25 Epoch 9 | Batch 888/3508 | Timestep 32460 | LR 0.0000100000 | Loss 0.019089 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:28 Epoch 9 | Batch 898/3508 | Timestep 32470 | LR 0.0000100000 | Loss 0.012462 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:30 Epoch 9 | Batch 908/3508 | Timestep 32480 | LR 0.0000100000 | Loss 0.034424 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:32 Epoch 9 | Batch 918/3508 | Timestep 32490 | LR 0.0000100000 | Loss 0.009950 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:35 Epoch 9 | Batch 928/3508 | Timestep 32500 | LR 0.0000100000 | Loss 0.017774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:37 Epoch 9 | Batch 938/3508 | Timestep 32510 | LR 0.0000100000 | Loss 0.025085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:38 Epoch 9 | Batch 948/3508 | Timestep 32520 | LR 0.0000100000 | Loss 0.038667 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:41 Epoch 9 | Batch 958/3508 | Timestep 32530 | LR 0.0000100000 | Loss 0.003284 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:43 Epoch 9 | Batch 968/3508 | Timestep 32540 | LR 0.0000100000 | Loss 0.007292 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:45 Epoch 9 | Batch 978/3508 | Timestep 32550 | LR 0.0000100000 | Loss 0.008143 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:47 Epoch 9 | Batch 988/3508 | Timestep 32560 | LR 0.0000100000 | Loss 0.005875 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:49 Epoch 9 | Batch 998/3508 | Timestep 32570 | LR 0.0000100000 | Loss 0.005353 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:51 Epoch 9 | Batch 1008/3508 | Timestep 32580 | LR 0.0000100000 | Loss 0.006945 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:53 Epoch 9 | Batch 1018/3508 | Timestep 32590 | LR 0.0000100000 | Loss 0.030405 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:55 Epoch 9 | Batch 1028/3508 | Timestep 32600 | LR 0.0000100000 | Loss 0.013088 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:57 Epoch 9 | Batch 1038/3508 | Timestep 32610 | LR 0.0000100000 | Loss 0.001610 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:48:59 Epoch 9 | Batch 1048/3508 | Timestep 32620 | LR 0.0000100000 | Loss 0.003888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:02 Epoch 9 | Batch 1058/3508 | Timestep 32630 | LR 0.0000100000 | Loss 0.001397 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:04 Epoch 9 | Batch 1068/3508 | Timestep 32640 | LR 0.0000100000 | Loss 0.009579 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:06 Epoch 9 | Batch 1078/3508 | Timestep 32650 | LR 0.0000100000 | Loss 0.003922 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:08 Epoch 9 | Batch 1088/3508 | Timestep 32660 | LR 0.0000100000 | Loss 0.000766 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:11 Epoch 9 | Batch 1098/3508 | Timestep 32670 | LR 0.0000100000 | Loss 0.003201 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:14 Epoch 9 | Batch 1108/3508 | Timestep 32680 | LR 0.0000100000 | Loss 0.006023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:16 Epoch 9 | Batch 1118/3508 | Timestep 32690 | LR 0.0000100000 | Loss 0.018273 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:18 Epoch 9 | Batch 1128/3508 | Timestep 32700 | LR 0.0000100000 | Loss 0.002342 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:20 Epoch 9 | Batch 1138/3508 | Timestep 32710 | LR 0.0000100000 | Loss 0.004760 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:22 Epoch 9 | Batch 1148/3508 | Timestep 32720 | LR 0.0000100000 | Loss 0.009418 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:24 Epoch 9 | Batch 1158/3508 | Timestep 32730 | LR 0.0000100000 | Loss 0.011685 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:27 Epoch 9 | Batch 1168/3508 | Timestep 32740 | LR 0.0000100000 | Loss 0.004671 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:28 Epoch 9 | Batch 1178/3508 | Timestep 32750 | LR 0.0000100000 | Loss 0.006575 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:30 Epoch 9 | Batch 1188/3508 | Timestep 32760 | LR 0.0000100000 | Loss 0.006581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:33 Epoch 9 | Batch 1198/3508 | Timestep 32770 | LR 0.0000100000 | Loss 0.002486 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:35 Epoch 9 | Batch 1208/3508 | Timestep 32780 | LR 0.0000100000 | Loss 0.007438 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:37 Epoch 9 | Batch 1218/3508 | Timestep 32790 | LR 0.0000100000 | Loss 0.007932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:39 Epoch 9 | Batch 1228/3508 | Timestep 32800 | LR 0.0000100000 | Loss 0.004379 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:42 Epoch 9 | Batch 1238/3508 | Timestep 32810 | LR 0.0000100000 | Loss 0.013874 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:44 Epoch 9 | Batch 1248/3508 | Timestep 32820 | LR 0.0000100000 | Loss 0.007574 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:46 Epoch 9 | Batch 1258/3508 | Timestep 32830 | LR 0.0000100000 | Loss 0.001568 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:48 Epoch 9 | Batch 1268/3508 | Timestep 32840 | LR 0.0000100000 | Loss 0.035183 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:50 Epoch 9 | Batch 1278/3508 | Timestep 32850 | LR 0.0000100000 | Loss 0.016494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:53 Epoch 9 | Batch 1288/3508 | Timestep 32860 | LR 0.0000100000 | Loss 0.002117 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:55 Epoch 9 | Batch 1298/3508 | Timestep 32870 | LR 0.0000100000 | Loss 0.015969 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:49:58 Epoch 9 | Batch 1308/3508 | Timestep 32880 | LR 0.0000100000 | Loss 0.014387 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:00 Epoch 9 | Batch 1318/3508 | Timestep 32890 | LR 0.0000100000 | Loss 0.016674 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:02 Epoch 9 | Batch 1328/3508 | Timestep 32900 | LR 0.0000100000 | Loss 0.004219 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:04 Epoch 9 | Batch 1338/3508 | Timestep 32910 | LR 0.0000100000 | Loss 0.004920 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:06 Epoch 9 | Batch 1348/3508 | Timestep 32920 | LR 0.0000100000 | Loss 0.011631 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:09 Epoch 9 | Batch 1358/3508 | Timestep 32930 | LR 0.0000100000 | Loss 0.003669 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:11 Epoch 9 | Batch 1368/3508 | Timestep 32940 | LR 0.0000100000 | Loss 0.002550 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:13 Epoch 9 | Batch 1378/3508 | Timestep 32950 | LR 0.0000100000 | Loss 0.014895 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:15 Epoch 9 | Batch 1388/3508 | Timestep 32960 | LR 0.0000100000 | Loss 0.013730 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:17 Epoch 9 | Batch 1398/3508 | Timestep 32970 | LR 0.0000100000 | Loss 0.013473 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:19 Epoch 9 | Batch 1408/3508 | Timestep 32980 | LR 0.0000100000 | Loss 0.004153 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:21 Epoch 9 | Batch 1418/3508 | Timestep 32990 | LR 0.0000100000 | Loss 0.010277 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:23 Epoch 9 | Batch 1428/3508 | Timestep 33000 | LR 0.0000100000 | Loss 0.000717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:25 Epoch 9 | Batch 1438/3508 | Timestep 33010 | LR 0.0000100000 | Loss 0.013901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:27 Epoch 9 | Batch 1448/3508 | Timestep 33020 | LR 0.0000100000 | Loss 0.012746 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:29 Epoch 9 | Batch 1458/3508 | Timestep 33030 | LR 0.0000100000 | Loss 0.003697 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:32 Epoch 9 | Batch 1468/3508 | Timestep 33040 | LR 0.0000100000 | Loss 0.032171 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:34 Epoch 9 | Batch 1478/3508 | Timestep 33050 | LR 0.0000100000 | Loss 0.014615 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:36 Epoch 9 | Batch 1488/3508 | Timestep 33060 | LR 0.0000100000 | Loss 0.002154 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:38 Epoch 9 | Batch 1498/3508 | Timestep 33070 | LR 0.0000100000 | Loss 0.021818 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:40 Epoch 9 | Batch 1508/3508 | Timestep 33080 | LR 0.0000100000 | Loss 0.008712 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:42 Epoch 9 | Batch 1518/3508 | Timestep 33090 | LR 0.0000100000 | Loss 0.001461 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:45 Epoch 9 | Batch 1528/3508 | Timestep 33100 | LR 0.0000100000 | Loss 0.010750 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:47 Epoch 9 | Batch 1538/3508 | Timestep 33110 | LR 0.0000100000 | Loss 0.004458 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:50 Epoch 9 | Batch 1548/3508 | Timestep 33120 | LR 0.0000100000 | Loss 0.021932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:52 Epoch 9 | Batch 1558/3508 | Timestep 33130 | LR 0.0000100000 | Loss 0.001847 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:54 Epoch 9 | Batch 1568/3508 | Timestep 33140 | LR 0.0000100000 | Loss 0.002713 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:56 Epoch 9 | Batch 1578/3508 | Timestep 33150 | LR 0.0000100000 | Loss 0.015646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:50:59 Epoch 9 | Batch 1588/3508 | Timestep 33160 | LR 0.0000100000 | Loss 0.017600 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:01 Epoch 9 | Batch 1598/3508 | Timestep 33170 | LR 0.0000100000 | Loss 0.018533 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:03 Epoch 9 | Batch 1608/3508 | Timestep 33180 | LR 0.0000100000 | Loss 0.002242 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:05 Epoch 9 | Batch 1618/3508 | Timestep 33190 | LR 0.0000100000 | Loss 0.012503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:07 Epoch 9 | Batch 1628/3508 | Timestep 33200 | LR 0.0000100000 | Loss 0.002646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:10 Epoch 9 | Batch 1638/3508 | Timestep 33210 | LR 0.0000100000 | Loss 0.011806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:12 Epoch 9 | Batch 1648/3508 | Timestep 33220 | LR 0.0000100000 | Loss 0.008707 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:14 Epoch 9 | Batch 1658/3508 | Timestep 33230 | LR 0.0000100000 | Loss 0.000797 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:16 Epoch 9 | Batch 1668/3508 | Timestep 33240 | LR 0.0000100000 | Loss 0.005275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:18 Epoch 9 | Batch 1678/3508 | Timestep 33250 | LR 0.0000100000 | Loss 0.006911 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:20 Epoch 9 | Batch 1688/3508 | Timestep 33260 | LR 0.0000100000 | Loss 0.003998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:22 Epoch 9 | Batch 1698/3508 | Timestep 33270 | LR 0.0000100000 | Loss 0.021678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:24 Epoch 9 | Batch 1708/3508 | Timestep 33280 | LR 0.0000100000 | Loss 0.002945 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:26 Epoch 9 | Batch 1718/3508 | Timestep 33290 | LR 0.0000100000 | Loss 0.008956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:28 Epoch 9 | Batch 1728/3508 | Timestep 33300 | LR 0.0000100000 | Loss 0.009258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:30 Epoch 9 | Batch 1738/3508 | Timestep 33310 | LR 0.0000100000 | Loss 0.027993 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:32 Epoch 9 | Batch 1748/3508 | Timestep 33320 | LR 0.0000100000 | Loss 0.002613 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:35 Epoch 9 | Batch 1758/3508 | Timestep 33330 | LR 0.0000100000 | Loss 0.004811 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:37 Epoch 9 | Batch 1768/3508 | Timestep 33340 | LR 0.0000100000 | Loss 0.046454 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:38 Epoch 9 | Batch 1778/3508 | Timestep 33350 | LR 0.0000100000 | Loss 0.031551 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:41 Epoch 9 | Batch 1788/3508 | Timestep 33360 | LR 0.0000100000 | Loss 0.057622 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:43 Epoch 9 | Batch 1798/3508 | Timestep 33370 | LR 0.0000100000 | Loss 0.014087 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:45 Epoch 9 | Batch 1808/3508 | Timestep 33380 | LR 0.0000100000 | Loss 0.068968 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:47 Epoch 9 | Batch 1818/3508 | Timestep 33390 | LR 0.0000100000 | Loss 0.005298 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:49 Epoch 9 | Batch 1828/3508 | Timestep 33400 | LR 0.0000100000 | Loss 0.018296 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:52 Epoch 9 | Batch 1838/3508 | Timestep 33410 | LR 0.0000100000 | Loss 0.022099 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:54 Epoch 9 | Batch 1848/3508 | Timestep 33420 | LR 0.0000100000 | Loss 0.005998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:56 Epoch 9 | Batch 1858/3508 | Timestep 33430 | LR 0.0000100000 | Loss 0.009494 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:51:58 Epoch 9 | Batch 1868/3508 | Timestep 33440 | LR 0.0000100000 | Loss 0.008160 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:00 Epoch 9 | Batch 1878/3508 | Timestep 33450 | LR 0.0000100000 | Loss 0.010845 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:02 Epoch 9 | Batch 1888/3508 | Timestep 33460 | LR 0.0000100000 | Loss 0.012233 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:04 Epoch 9 | Batch 1898/3508 | Timestep 33470 | LR 0.0000100000 | Loss 0.037345 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:06 Epoch 9 | Batch 1908/3508 | Timestep 33480 | LR 0.0000100000 | Loss 0.020416 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:08 Epoch 9 | Batch 1918/3508 | Timestep 33490 | LR 0.0000100000 | Loss 0.019814 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:10 Epoch 9 | Batch 1928/3508 | Timestep 33500 | LR 0.0000100000 | Loss 0.004647 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:12 Epoch 9 | Batch 1938/3508 | Timestep 33510 | LR 0.0000100000 | Loss 0.014664 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:14 Epoch 9 | Batch 1948/3508 | Timestep 33520 | LR 0.0000100000 | Loss 0.018577 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:16 Epoch 9 | Batch 1958/3508 | Timestep 33530 | LR 0.0000100000 | Loss 0.028710 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:18 Epoch 9 | Batch 1968/3508 | Timestep 33540 | LR 0.0000100000 | Loss 0.002212 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:20 Epoch 9 | Batch 1978/3508 | Timestep 33550 | LR 0.0000100000 | Loss 0.010423 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:22 Epoch 9 | Batch 1988/3508 | Timestep 33560 | LR 0.0000100000 | Loss 0.004354 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:24 Epoch 9 | Batch 1998/3508 | Timestep 33570 | LR 0.0000100000 | Loss 0.001151 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:26 Epoch 9 | Batch 2008/3508 | Timestep 33580 | LR 0.0000100000 | Loss 0.007293 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:28 Epoch 9 | Batch 2018/3508 | Timestep 33590 | LR 0.0000100000 | Loss 0.010159 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:31 Epoch 9 | Batch 2028/3508 | Timestep 33600 | LR 0.0000100000 | Loss 0.019827 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:33 Epoch 9 | Batch 2038/3508 | Timestep 33610 | LR 0.0000100000 | Loss 0.001157 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:34 Epoch 9 | Batch 2048/3508 | Timestep 33620 | LR 0.0000100000 | Loss 0.018434 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:37 Epoch 9 | Batch 2058/3508 | Timestep 33630 | LR 0.0000100000 | Loss 0.009748 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:40 Epoch 9 | Batch 2068/3508 | Timestep 33640 | LR 0.0000100000 | Loss 0.005378 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:42 Epoch 9 | Batch 2078/3508 | Timestep 33650 | LR 0.0000100000 | Loss 0.002818 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:44 Epoch 9 | Batch 2088/3508 | Timestep 33660 | LR 0.0000100000 | Loss 0.029323 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:46 Epoch 9 | Batch 2098/3508 | Timestep 33670 | LR 0.0000100000 | Loss 0.010442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:48 Epoch 9 | Batch 2108/3508 | Timestep 33680 | LR 0.0000100000 | Loss 0.012802 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:50 Epoch 9 | Batch 2118/3508 | Timestep 33690 | LR 0.0000100000 | Loss 0.011081 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:53 Epoch 9 | Batch 2128/3508 | Timestep 33700 | LR 0.0000100000 | Loss 0.005046 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:55 Epoch 9 | Batch 2138/3508 | Timestep 33710 | LR 0.0000100000 | Loss 0.006820 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:57 Epoch 9 | Batch 2148/3508 | Timestep 33720 | LR 0.0000100000 | Loss 0.011369 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:52:59 Epoch 9 | Batch 2158/3508 | Timestep 33730 | LR 0.0000100000 | Loss 0.020775 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:02 Epoch 9 | Batch 2168/3508 | Timestep 33740 | LR 0.0000100000 | Loss 0.006764 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:04 Epoch 9 | Batch 2178/3508 | Timestep 33750 | LR 0.0000100000 | Loss 0.006620 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:07 Epoch 9 | Batch 2188/3508 | Timestep 33760 | LR 0.0000100000 | Loss 0.008605 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:08 Epoch 9 | Batch 2198/3508 | Timestep 33770 | LR 0.0000100000 | Loss 0.004135 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:10 Epoch 9 | Batch 2208/3508 | Timestep 33780 | LR 0.0000100000 | Loss 0.013270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:13 Epoch 9 | Batch 2218/3508 | Timestep 33790 | LR 0.0000100000 | Loss 0.003731 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:15 Epoch 9 | Batch 2228/3508 | Timestep 33800 | LR 0.0000100000 | Loss 0.003170 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:17 Epoch 9 | Batch 2238/3508 | Timestep 33810 | LR 0.0000100000 | Loss 0.000493 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:20 Epoch 9 | Batch 2248/3508 | Timestep 33820 | LR 0.0000100000 | Loss 0.013439 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:22 Epoch 9 | Batch 2258/3508 | Timestep 33830 | LR 0.0000100000 | Loss 0.004806 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:24 Epoch 9 | Batch 2268/3508 | Timestep 33840 | LR 0.0000100000 | Loss 0.034210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:26 Epoch 9 | Batch 2278/3508 | Timestep 33850 | LR 0.0000100000 | Loss 0.001415 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:29 Epoch 9 | Batch 2288/3508 | Timestep 33860 | LR 0.0000100000 | Loss 0.002768 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:31 Epoch 9 | Batch 2298/3508 | Timestep 33870 | LR 0.0000100000 | Loss 0.017995 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:33 Epoch 9 | Batch 2308/3508 | Timestep 33880 | LR 0.0000100000 | Loss 0.035803 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:36 Epoch 9 | Batch 2318/3508 | Timestep 33890 | LR 0.0000100000 | Loss 0.009214 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:38 Epoch 9 | Batch 2328/3508 | Timestep 33900 | LR 0.0000100000 | Loss 0.018406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:40 Epoch 9 | Batch 2338/3508 | Timestep 33910 | LR 0.0000100000 | Loss 0.014687 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:42 Epoch 9 | Batch 2348/3508 | Timestep 33920 | LR 0.0000100000 | Loss 0.006495 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:44 Epoch 9 | Batch 2358/3508 | Timestep 33930 | LR 0.0000100000 | Loss 0.002521 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:46 Epoch 9 | Batch 2368/3508 | Timestep 33940 | LR 0.0000100000 | Loss 0.006468 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:48 Epoch 9 | Batch 2378/3508 | Timestep 33950 | LR 0.0000100000 | Loss 0.002191 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:51 Epoch 9 | Batch 2388/3508 | Timestep 33960 | LR 0.0000100000 | Loss 0.007331 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:53 Epoch 9 | Batch 2398/3508 | Timestep 33970 | LR 0.0000100000 | Loss 0.020210 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:54 Epoch 9 | Batch 2408/3508 | Timestep 33980 | LR 0.0000100000 | Loss 0.004637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:56 Epoch 9 | Batch 2418/3508 | Timestep 33990 | LR 0.0000100000 | Loss 0.006309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:53:58 Epoch 9 | Batch 2428/3508 | Timestep 34000 | LR 0.0000100000 | Loss 0.018781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:00 Epoch 9 | Batch 2438/3508 | Timestep 34010 | LR 0.0000100000 | Loss 0.021826 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:02 Epoch 9 | Batch 2448/3508 | Timestep 34020 | LR 0.0000100000 | Loss 0.018258 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:05 Epoch 9 | Batch 2458/3508 | Timestep 34030 | LR 0.0000100000 | Loss 0.003922 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:07 Epoch 9 | Batch 2468/3508 | Timestep 34040 | LR 0.0000100000 | Loss 0.010383 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:10 Epoch 9 | Batch 2478/3508 | Timestep 34050 | LR 0.0000100000 | Loss 0.028648 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:12 Epoch 9 | Batch 2488/3508 | Timestep 34060 | LR 0.0000100000 | Loss 0.009541 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:14 Epoch 9 | Batch 2498/3508 | Timestep 34070 | LR 0.0000100000 | Loss 0.007309 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:16 Epoch 9 | Batch 2508/3508 | Timestep 34080 | LR 0.0000100000 | Loss 0.016669 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:18 Epoch 9 | Batch 2518/3508 | Timestep 34090 | LR 0.0000100000 | Loss 0.006695 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:20 Epoch 9 | Batch 2528/3508 | Timestep 34100 | LR 0.0000100000 | Loss 0.004646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:22 Epoch 9 | Batch 2538/3508 | Timestep 34110 | LR 0.0000100000 | Loss 0.008249 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:24 Epoch 9 | Batch 2548/3508 | Timestep 34120 | LR 0.0000100000 | Loss 0.009630 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:26 Epoch 9 | Batch 2558/3508 | Timestep 34130 | LR 0.0000100000 | Loss 0.001507 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:29 Epoch 9 | Batch 2568/3508 | Timestep 34140 | LR 0.0000100000 | Loss 0.003193 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:31 Epoch 9 | Batch 2578/3508 | Timestep 34150 | LR 0.0000100000 | Loss 0.020380 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:33 Epoch 9 | Batch 2588/3508 | Timestep 34160 | LR 0.0000100000 | Loss 0.002774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:35 Epoch 9 | Batch 2598/3508 | Timestep 34170 | LR 0.0000100000 | Loss 0.004439 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:37 Epoch 9 | Batch 2608/3508 | Timestep 34180 | LR 0.0000100000 | Loss 0.010176 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:40 Epoch 9 | Batch 2618/3508 | Timestep 34190 | LR 0.0000100000 | Loss 0.005934 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:42 Epoch 9 | Batch 2628/3508 | Timestep 34200 | LR 0.0000100000 | Loss 0.009775 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:43 Epoch 9 | Batch 2638/3508 | Timestep 34210 | LR 0.0000100000 | Loss 0.002193 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:46 Epoch 9 | Batch 2648/3508 | Timestep 34220 | LR 0.0000100000 | Loss 0.009343 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:48 Epoch 9 | Batch 2658/3508 | Timestep 34230 | LR 0.0000100000 | Loss 0.002254 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:50 Epoch 9 | Batch 2668/3508 | Timestep 34240 | LR 0.0000100000 | Loss 0.020257 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:52 Epoch 9 | Batch 2678/3508 | Timestep 34250 | LR 0.0000100000 | Loss 0.014998 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:55 Epoch 9 | Batch 2688/3508 | Timestep 34260 | LR 0.0000100000 | Loss 0.014232 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:57 Epoch 9 | Batch 2698/3508 | Timestep 34270 | LR 0.0000100000 | Loss 0.006251 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:54:58 Epoch 9 | Batch 2708/3508 | Timestep 34280 | LR 0.0000100000 | Loss 0.012243 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:00 Epoch 9 | Batch 2718/3508 | Timestep 34290 | LR 0.0000100000 | Loss 0.012455 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:02 Epoch 9 | Batch 2728/3508 | Timestep 34300 | LR 0.0000100000 | Loss 0.006281 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:04 Epoch 9 | Batch 2738/3508 | Timestep 34310 | LR 0.0000100000 | Loss 0.011883 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:06 Epoch 9 | Batch 2748/3508 | Timestep 34320 | LR 0.0000100000 | Loss 0.011688 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:08 Epoch 9 | Batch 2758/3508 | Timestep 34330 | LR 0.0000100000 | Loss 0.011552 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:11 Epoch 9 | Batch 2768/3508 | Timestep 34340 | LR 0.0000100000 | Loss 0.014177 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:12 Epoch 9 | Batch 2778/3508 | Timestep 34350 | LR 0.0000100000 | Loss 0.001482 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:15 Epoch 9 | Batch 2788/3508 | Timestep 34360 | LR 0.0000100000 | Loss 0.008196 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:17 Epoch 9 | Batch 2798/3508 | Timestep 34370 | LR 0.0000100000 | Loss 0.005559 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:19 Epoch 9 | Batch 2808/3508 | Timestep 34380 | LR 0.0000100000 | Loss 0.002338 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:21 Epoch 9 | Batch 2818/3508 | Timestep 34390 | LR 0.0000100000 | Loss 0.000588 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:23 Epoch 9 | Batch 2828/3508 | Timestep 34400 | LR 0.0000100000 | Loss 0.011614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:25 Epoch 9 | Batch 2838/3508 | Timestep 34410 | LR 0.0000100000 | Loss 0.029780 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:27 Epoch 9 | Batch 2848/3508 | Timestep 34420 | LR 0.0000100000 | Loss 0.003110 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:29 Epoch 9 | Batch 2858/3508 | Timestep 34430 | LR 0.0000100000 | Loss 0.005945 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:31 Epoch 9 | Batch 2868/3508 | Timestep 34440 | LR 0.0000100000 | Loss 0.002273 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:33 Epoch 9 | Batch 2878/3508 | Timestep 34450 | LR 0.0000100000 | Loss 0.017791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:36 Epoch 9 | Batch 2888/3508 | Timestep 34460 | LR 0.0000100000 | Loss 0.009064 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:38 Epoch 9 | Batch 2898/3508 | Timestep 34470 | LR 0.0000100000 | Loss 0.005901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:40 Epoch 9 | Batch 2908/3508 | Timestep 34480 | LR 0.0000100000 | Loss 0.004004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:42 Epoch 9 | Batch 2918/3508 | Timestep 34490 | LR 0.0000100000 | Loss 0.006627 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:45 Epoch 9 | Batch 2928/3508 | Timestep 34500 | LR 0.0000100000 | Loss 0.005368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:46 Epoch 9 | Batch 2938/3508 | Timestep 34510 | LR 0.0000100000 | Loss 0.002946 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:48 Epoch 9 | Batch 2948/3508 | Timestep 34520 | LR 0.0000100000 | Loss 0.008330 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:51 Epoch 9 | Batch 2958/3508 | Timestep 34530 | LR 0.0000100000 | Loss 0.006821 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:53 Epoch 9 | Batch 2968/3508 | Timestep 34540 | LR 0.0000100000 | Loss 0.016169 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:55 Epoch 9 | Batch 2978/3508 | Timestep 34550 | LR 0.0000100000 | Loss 0.003242 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:57 Epoch 9 | Batch 2988/3508 | Timestep 34560 | LR 0.0000100000 | Loss 0.024104 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:55:59 Epoch 9 | Batch 2998/3508 | Timestep 34570 | LR 0.0000100000 | Loss 0.007783 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:01 Epoch 9 | Batch 3008/3508 | Timestep 34580 | LR 0.0000100000 | Loss 0.027055 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:03 Epoch 9 | Batch 3018/3508 | Timestep 34590 | LR 0.0000100000 | Loss 0.011423 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:04 Epoch 9 | Batch 3028/3508 | Timestep 34600 | LR 0.0000100000 | Loss 0.004606 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:06 Epoch 9 | Batch 3038/3508 | Timestep 34610 | LR 0.0000100000 | Loss 0.010503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:09 Epoch 9 | Batch 3048/3508 | Timestep 34620 | LR 0.0000100000 | Loss 0.003178 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:11 Epoch 9 | Batch 3058/3508 | Timestep 34630 | LR 0.0000100000 | Loss 0.005780 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:14 Epoch 9 | Batch 3068/3508 | Timestep 34640 | LR 0.0000100000 | Loss 0.010824 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:16 Epoch 9 | Batch 3078/3508 | Timestep 34650 | LR 0.0000100000 | Loss 0.007676 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:18 Epoch 9 | Batch 3088/3508 | Timestep 34660 | LR 0.0000100000 | Loss 0.019276 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:20 Epoch 9 | Batch 3098/3508 | Timestep 34670 | LR 0.0000100000 | Loss 0.022518 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:22 Epoch 9 | Batch 3108/3508 | Timestep 34680 | LR 0.0000100000 | Loss 0.005359 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:25 Epoch 9 | Batch 3118/3508 | Timestep 34690 | LR 0.0000100000 | Loss 0.006542 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:27 Epoch 9 | Batch 3128/3508 | Timestep 34700 | LR 0.0000100000 | Loss 0.014566 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:30 Epoch 9 | Batch 3138/3508 | Timestep 34710 | LR 0.0000100000 | Loss 0.020509 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:32 Epoch 9 | Batch 3148/3508 | Timestep 34720 | LR 0.0000100000 | Loss 0.007866 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:34 Epoch 9 | Batch 3158/3508 | Timestep 34730 | LR 0.0000100000 | Loss 0.019393 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:37 Epoch 9 | Batch 3168/3508 | Timestep 34740 | LR 0.0000100000 | Loss 0.007125 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:39 Epoch 9 | Batch 3178/3508 | Timestep 34750 | LR 0.0000100000 | Loss 0.011729 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:41 Epoch 9 | Batch 3188/3508 | Timestep 34760 | LR 0.0000100000 | Loss 0.042116 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:43 Epoch 9 | Batch 3198/3508 | Timestep 34770 | LR 0.0000100000 | Loss 0.005864 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:44 Epoch 9 | Batch 3208/3508 | Timestep 34780 | LR 0.0000100000 | Loss 0.021426 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:47 Epoch 9 | Batch 3218/3508 | Timestep 34790 | LR 0.0000100000 | Loss 0.012442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:49 Epoch 9 | Batch 3228/3508 | Timestep 34800 | LR 0.0000100000 | Loss 0.001133 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:51 Epoch 9 | Batch 3238/3508 | Timestep 34810 | LR 0.0000100000 | Loss 0.002200 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:53 Epoch 9 | Batch 3248/3508 | Timestep 34820 | LR 0.0000100000 | Loss 0.027911 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:55 Epoch 9 | Batch 3258/3508 | Timestep 34830 | LR 0.0000100000 | Loss 0.006186 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:57 Epoch 9 | Batch 3268/3508 | Timestep 34840 | LR 0.0000100000 | Loss 0.006951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:56:59 Epoch 9 | Batch 3278/3508 | Timestep 34850 | LR 0.0000100000 | Loss 0.040419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:01 Epoch 9 | Batch 3288/3508 | Timestep 34860 | LR 0.0000100000 | Loss 0.001031 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:03 Epoch 9 | Batch 3298/3508 | Timestep 34870 | LR 0.0000100000 | Loss 0.020058 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:05 Epoch 9 | Batch 3308/3508 | Timestep 34880 | LR 0.0000100000 | Loss 0.001984 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:07 Epoch 9 | Batch 3318/3508 | Timestep 34890 | LR 0.0000100000 | Loss 0.001335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:09 Epoch 9 | Batch 3328/3508 | Timestep 34900 | LR 0.0000100000 | Loss 0.007307 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:11 Epoch 9 | Batch 3338/3508 | Timestep 34910 | LR 0.0000100000 | Loss 0.018256 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:13 Epoch 9 | Batch 3348/3508 | Timestep 34920 | LR 0.0000100000 | Loss 0.010303 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:16 Epoch 9 | Batch 3358/3508 | Timestep 34930 | LR 0.0000100000 | Loss 0.023033 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:18 Epoch 9 | Batch 3368/3508 | Timestep 34940 | LR 0.0000100000 | Loss 0.006290 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:21 Epoch 9 | Batch 3378/3508 | Timestep 34950 | LR 0.0000100000 | Loss 0.005925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:22 Epoch 9 | Batch 3388/3508 | Timestep 34960 | LR 0.0000100000 | Loss 0.010944 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:24 Epoch 9 | Batch 3398/3508 | Timestep 34970 | LR 0.0000100000 | Loss 0.020561 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:26 Epoch 9 | Batch 3408/3508 | Timestep 34980 | LR 0.0000100000 | Loss 0.012490 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:28 Epoch 9 | Batch 3418/3508 | Timestep 34990 | LR 0.0000100000 | Loss 0.000513 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:30 Epoch 9 | Batch 3428/3508 | Timestep 35000 | LR 0.0000100000 | Loss 0.009638 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:32 Epoch 9 | Batch 3438/3508 | Timestep 35010 | LR 0.0000100000 | Loss 0.024395 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:34 Epoch 9 | Batch 3448/3508 | Timestep 35020 | LR 0.0000100000 | Loss 0.010493 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:36 Epoch 9 | Batch 3458/3508 | Timestep 35030 | LR 0.0000100000 | Loss 0.005704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:38 Epoch 9 | Batch 3468/3508 | Timestep 35040 | LR 0.0000100000 | Loss 0.001642 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:40 Epoch 9 | Batch 3478/3508 | Timestep 35050 | LR 0.0000100000 | Loss 0.011442 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:43 Epoch 9 | Batch 3488/3508 | Timestep 35060 | LR 0.0000100000 | Loss 0.034916 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:44 Epoch 9 | Batch 3498/3508 | Timestep 35070 | LR 0.0000100000 | Loss 0.037645 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:47 Epoch 9 | Batch 3508/3508 | Timestep 35080 | LR 0.0000100000 | Loss 0.001488 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:57:47 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 16:58:20 precision recall f1-score support CARDINAL 0.8767 0.8050 0.8393 159 CURR 0.7308 0.8636 0.7917 22 DATE 0.9466 0.9449 0.9457 1669 EVENT 0.6822 0.7739 0.7252 283 FAC 0.6786 0.8051 0.7364 118 GPE 0.9709 0.9659 0.9684 2140 LANGUAGE 0.6316 0.7500 0.6857 16 LAW 0.5333 0.8421 0.6531 19 LOC 0.7404 0.8556 0.7938 90 MONEY 0.6957 0.8000 0.7442 20 NORP 0.7159 0.7426 0.7290 509 OCC 0.8394 0.8851 0.8616 496 ORDINAL 0.9025 0.9552 0.9281 446 ORG 0.9108 0.9411 0.9257 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9557 0.9529 0.9543 679 PRODUCT 0.6667 0.5000 0.5714 8 QUANTITY 0.3333 0.6667 0.4444 3 TIME 0.7241 0.6774 0.7000 31 UNIT 0.6000 0.7500 0.6667 4 WEBSITE 0.6049 0.6125 0.6087 80 micro avg 0.8975 0.9185 0.9079 8670 macro avg 0.7459 0.8138 0.7730 8670 weighted avg 0.9007 0.9185 0.9091 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:30 Epoch 9 | Timestep 35080 | Train Loss 0.011593 | Val Loss 0.055235 | F1 0.907878 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:32 Epoch 10 | Batch 10/3508 | Timestep 35090 | LR 0.0000100000 | Loss 0.001819 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:34 Epoch 10 | Batch 20/3508 | Timestep 35100 | LR 0.0000100000 | Loss 0.001461 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:36 Epoch 10 | Batch 30/3508 | Timestep 35110 | LR 0.0000100000 | Loss 0.010086 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:39 Epoch 10 | Batch 40/3508 | Timestep 35120 | LR 0.0000100000 | Loss 0.005699 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:41 Epoch 10 | Batch 50/3508 | Timestep 35130 | LR 0.0000100000 | Loss 0.003057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:43 Epoch 10 | Batch 60/3508 | Timestep 35140 | LR 0.0000100000 | Loss 0.021124 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:45 Epoch 10 | Batch 70/3508 | Timestep 35150 | LR 0.0000100000 | Loss 0.004546 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:47 Epoch 10 | Batch 80/3508 | Timestep 35160 | LR 0.0000100000 | Loss 0.001896 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:48 Epoch 10 | Batch 90/3508 | Timestep 35170 | LR 0.0000100000 | Loss 0.003647 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:50 Epoch 10 | Batch 100/3508 | Timestep 35180 | LR 0.0000100000 | Loss 0.007024 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:52 Epoch 10 | Batch 110/3508 | Timestep 35190 | LR 0.0000100000 | Loss 0.003649 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:54 Epoch 10 | Batch 120/3508 | Timestep 35200 | LR 0.0000100000 | Loss 0.003191 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:57 Epoch 10 | Batch 130/3508 | Timestep 35210 | LR 0.0000100000 | Loss 0.003431 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:58:59 Epoch 10 | Batch 140/3508 | Timestep 35220 | LR 0.0000100000 | Loss 0.006929 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:01 Epoch 10 | Batch 150/3508 | Timestep 35230 | LR 0.0000100000 | Loss 0.004119 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:04 Epoch 10 | Batch 160/3508 | Timestep 35240 | LR 0.0000100000 | Loss 0.017073 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:06 Epoch 10 | Batch 170/3508 | Timestep 35250 | LR 0.0000100000 | Loss 0.025704 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:08 Epoch 10 | Batch 180/3508 | Timestep 35260 | LR 0.0000100000 | Loss 0.017139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:10 Epoch 10 | Batch 190/3508 | Timestep 35270 | LR 0.0000100000 | Loss 0.011345 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:12 Epoch 10 | Batch 200/3508 | Timestep 35280 | LR 0.0000100000 | Loss 0.003449 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:14 Epoch 10 | Batch 210/3508 | Timestep 35290 | LR 0.0000100000 | Loss 0.004059 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:16 Epoch 10 | Batch 220/3508 | Timestep 35300 | LR 0.0000100000 | Loss 0.025094 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:18 Epoch 10 | Batch 230/3508 | Timestep 35310 | LR 0.0000100000 | Loss 0.009990 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:20 Epoch 10 | Batch 240/3508 | Timestep 35320 | LR 0.0000100000 | Loss 0.010804 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:22 Epoch 10 | Batch 250/3508 | Timestep 35330 | LR 0.0000100000 | Loss 0.007850 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:25 Epoch 10 | Batch 260/3508 | Timestep 35340 | LR 0.0000100000 | Loss 0.021399 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:27 Epoch 10 | Batch 270/3508 | Timestep 35350 | LR 0.0000100000 | Loss 0.009026 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:29 Epoch 10 | Batch 280/3508 | Timestep 35360 | LR 0.0000100000 | Loss 0.012372 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:31 Epoch 10 | Batch 290/3508 | Timestep 35370 | LR 0.0000100000 | Loss 0.000951 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:33 Epoch 10 | Batch 300/3508 | Timestep 35380 | LR 0.0000100000 | Loss 0.003985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:35 Epoch 10 | Batch 310/3508 | Timestep 35390 | LR 0.0000100000 | Loss 0.003319 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:37 Epoch 10 | Batch 320/3508 | Timestep 35400 | LR 0.0000100000 | Loss 0.018499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:40 Epoch 10 | Batch 330/3508 | Timestep 35410 | LR 0.0000100000 | Loss 0.010770 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:42 Epoch 10 | Batch 340/3508 | Timestep 35420 | LR 0.0000100000 | Loss 0.022295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:44 Epoch 10 | Batch 350/3508 | Timestep 35430 | LR 0.0000100000 | Loss 0.015814 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:46 Epoch 10 | Batch 360/3508 | Timestep 35440 | LR 0.0000100000 | Loss 0.003703 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:48 Epoch 10 | Batch 370/3508 | Timestep 35450 | LR 0.0000100000 | Loss 0.007913 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:50 Epoch 10 | Batch 380/3508 | Timestep 35460 | LR 0.0000100000 | Loss 0.012678 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:53 Epoch 10 | Batch 390/3508 | Timestep 35470 | LR 0.0000100000 | Loss 0.009730 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:55 Epoch 10 | Batch 400/3508 | Timestep 35480 | LR 0.0000100000 | Loss 0.004463 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:57 Epoch 10 | Batch 410/3508 | Timestep 35490 | LR 0.0000100000 | Loss 0.010590 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 16:59:59 Epoch 10 | Batch 420/3508 | Timestep 35500 | LR 0.0000100000 | Loss 0.010243 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:01 Epoch 10 | Batch 430/3508 | Timestep 35510 | LR 0.0000100000 | Loss 0.022522 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:04 Epoch 10 | Batch 440/3508 | Timestep 35520 | LR 0.0000100000 | Loss 0.014107 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:06 Epoch 10 | Batch 450/3508 | Timestep 35530 | LR 0.0000100000 | Loss 0.005547 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:08 Epoch 10 | Batch 460/3508 | Timestep 35540 | LR 0.0000100000 | Loss 0.003548 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:10 Epoch 10 | Batch 470/3508 | Timestep 35550 | LR 0.0000100000 | Loss 0.033826 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:12 Epoch 10 | Batch 480/3508 | Timestep 35560 | LR 0.0000100000 | Loss 0.002862 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:15 Epoch 10 | Batch 490/3508 | Timestep 35570 | LR 0.0000100000 | Loss 0.005921 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:17 Epoch 10 | Batch 500/3508 | Timestep 35580 | LR 0.0000100000 | Loss 0.002882 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:19 Epoch 10 | Batch 510/3508 | Timestep 35590 | LR 0.0000100000 | Loss 0.007255 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:20 Epoch 10 | Batch 520/3508 | Timestep 35600 | LR 0.0000100000 | Loss 0.049777 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:23 Epoch 10 | Batch 530/3508 | Timestep 35610 | LR 0.0000100000 | Loss 0.015901 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:25 Epoch 10 | Batch 540/3508 | Timestep 35620 | LR 0.0000100000 | Loss 0.016925 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:28 Epoch 10 | Batch 550/3508 | Timestep 35630 | LR 0.0000100000 | Loss 0.015915 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:30 Epoch 10 | Batch 560/3508 | Timestep 35640 | LR 0.0000100000 | Loss 0.006187 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:32 Epoch 10 | Batch 570/3508 | Timestep 35650 | LR 0.0000100000 | Loss 0.005932 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:34 Epoch 10 | Batch 580/3508 | Timestep 35660 | LR 0.0000100000 | Loss 0.006841 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:36 Epoch 10 | Batch 590/3508 | Timestep 35670 | LR 0.0000100000 | Loss 0.033496 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:38 Epoch 10 | Batch 600/3508 | Timestep 35680 | LR 0.0000100000 | Loss 0.008734 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:41 Epoch 10 | Batch 610/3508 | Timestep 35690 | LR 0.0000100000 | Loss 0.019480 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:43 Epoch 10 | Batch 620/3508 | Timestep 35700 | LR 0.0000100000 | Loss 0.005920 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:45 Epoch 10 | Batch 630/3508 | Timestep 35710 | LR 0.0000100000 | Loss 0.007381 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:47 Epoch 10 | Batch 640/3508 | Timestep 35720 | LR 0.0000100000 | Loss 0.009468 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:50 Epoch 10 | Batch 650/3508 | Timestep 35730 | LR 0.0000100000 | Loss 0.010512 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:51 Epoch 10 | Batch 660/3508 | Timestep 35740 | LR 0.0000100000 | Loss 0.004747 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:53 Epoch 10 | Batch 670/3508 | Timestep 35750 | LR 0.0000100000 | Loss 0.013202 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:55 Epoch 10 | Batch 680/3508 | Timestep 35760 | LR 0.0000100000 | Loss 0.001823 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:57 Epoch 10 | Batch 690/3508 | Timestep 35770 | LR 0.0000100000 | Loss 0.001184 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:00:59 Epoch 10 | Batch 700/3508 | Timestep 35780 | LR 0.0000100000 | Loss 0.008634 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:01 Epoch 10 | Batch 710/3508 | Timestep 35790 | LR 0.0000100000 | Loss 0.004016 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:03 Epoch 10 | Batch 720/3508 | Timestep 35800 | LR 0.0000100000 | Loss 0.001130 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:05 Epoch 10 | Batch 730/3508 | Timestep 35810 | LR 0.0000100000 | Loss 0.007781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:08 Epoch 10 | Batch 740/3508 | Timestep 35820 | LR 0.0000100000 | Loss 0.002374 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:10 Epoch 10 | Batch 750/3508 | Timestep 35830 | LR 0.0000100000 | Loss 0.016873 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:12 Epoch 10 | Batch 760/3508 | Timestep 35840 | LR 0.0000100000 | Loss 0.000642 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:15 Epoch 10 | Batch 770/3508 | Timestep 35850 | LR 0.0000100000 | Loss 0.014580 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:17 Epoch 10 | Batch 780/3508 | Timestep 35860 | LR 0.0000100000 | Loss 0.014709 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:19 Epoch 10 | Batch 790/3508 | Timestep 35870 | LR 0.0000100000 | Loss 0.002004 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:21 Epoch 10 | Batch 800/3508 | Timestep 35880 | LR 0.0000100000 | Loss 0.013780 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:23 Epoch 10 | Batch 810/3508 | Timestep 35890 | LR 0.0000100000 | Loss 0.006357 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:25 Epoch 10 | Batch 820/3508 | Timestep 35900 | LR 0.0000100000 | Loss 0.015950 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:27 Epoch 10 | Batch 830/3508 | Timestep 35910 | LR 0.0000100000 | Loss 0.005963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:29 Epoch 10 | Batch 840/3508 | Timestep 35920 | LR 0.0000100000 | Loss 0.006091 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:31 Epoch 10 | Batch 850/3508 | Timestep 35930 | LR 0.0000100000 | Loss 0.002460 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:33 Epoch 10 | Batch 860/3508 | Timestep 35940 | LR 0.0000100000 | Loss 0.067839 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:35 Epoch 10 | Batch 870/3508 | Timestep 35950 | LR 0.0000100000 | Loss 0.001189 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:37 Epoch 10 | Batch 880/3508 | Timestep 35960 | LR 0.0000100000 | Loss 0.002663 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:40 Epoch 10 | Batch 890/3508 | Timestep 35970 | LR 0.0000100000 | Loss 0.003617 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:42 Epoch 10 | Batch 900/3508 | Timestep 35980 | LR 0.0000100000 | Loss 0.021301 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:44 Epoch 10 | Batch 910/3508 | Timestep 35990 | LR 0.0000100000 | Loss 0.016904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:46 Epoch 10 | Batch 920/3508 | Timestep 36000 | LR 0.0000100000 | Loss 0.003931 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:48 Epoch 10 | Batch 930/3508 | Timestep 36010 | LR 0.0000100000 | Loss 0.008107 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:50 Epoch 10 | Batch 940/3508 | Timestep 36020 | LR 0.0000100000 | Loss 0.004167 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:53 Epoch 10 | Batch 950/3508 | Timestep 36030 | LR 0.0000100000 | Loss 0.000886 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:55 Epoch 10 | Batch 960/3508 | Timestep 36040 | LR 0.0000100000 | Loss 0.007608 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:57 Epoch 10 | Batch 970/3508 | Timestep 36050 | LR 0.0000100000 | Loss 0.000741 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:01:59 Epoch 10 | Batch 980/3508 | Timestep 36060 | LR 0.0000100000 | Loss 0.012218 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:02 Epoch 10 | Batch 990/3508 | Timestep 36070 | LR 0.0000100000 | Loss 0.028918 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:03 Epoch 10 | Batch 1000/3508 | Timestep 36080 | LR 0.0000100000 | Loss 0.009451 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:06 Epoch 10 | Batch 1010/3508 | Timestep 36090 | LR 0.0000100000 | Loss 0.008819 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:08 Epoch 10 | Batch 1020/3508 | Timestep 36100 | LR 0.0000100000 | Loss 0.009635 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:10 Epoch 10 | Batch 1030/3508 | Timestep 36110 | LR 0.0000100000 | Loss 0.005689 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:12 Epoch 10 | Batch 1040/3508 | Timestep 36120 | LR 0.0000100000 | Loss 0.000524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:14 Epoch 10 | Batch 1050/3508 | Timestep 36130 | LR 0.0000100000 | Loss 0.009687 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:17 Epoch 10 | Batch 1060/3508 | Timestep 36140 | LR 0.0000100000 | Loss 0.003700 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:19 Epoch 10 | Batch 1070/3508 | Timestep 36150 | LR 0.0000100000 | Loss 0.001732 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:21 Epoch 10 | Batch 1080/3508 | Timestep 36160 | LR 0.0000100000 | Loss 0.003160 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:23 Epoch 10 | Batch 1090/3508 | Timestep 36170 | LR 0.0000100000 | Loss 0.019228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:25 Epoch 10 | Batch 1100/3508 | Timestep 36180 | LR 0.0000100000 | Loss 0.000907 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:27 Epoch 10 | Batch 1110/3508 | Timestep 36190 | LR 0.0000100000 | Loss 0.013992 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:29 Epoch 10 | Batch 1120/3508 | Timestep 36200 | LR 0.0000100000 | Loss 0.007523 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:31 Epoch 10 | Batch 1130/3508 | Timestep 36210 | LR 0.0000100000 | Loss 0.003360 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:33 Epoch 10 | Batch 1140/3508 | Timestep 36220 | LR 0.0000100000 | Loss 0.011680 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:35 Epoch 10 | Batch 1150/3508 | Timestep 36230 | LR 0.0000100000 | Loss 0.022517 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:37 Epoch 10 | Batch 1160/3508 | Timestep 36240 | LR 0.0000100000 | Loss 0.011524 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:39 Epoch 10 | Batch 1170/3508 | Timestep 36250 | LR 0.0000100000 | Loss 0.005711 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:41 Epoch 10 | Batch 1180/3508 | Timestep 36260 | LR 0.0000100000 | Loss 0.003550 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:43 Epoch 10 | Batch 1190/3508 | Timestep 36270 | LR 0.0000100000 | Loss 0.002391 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:45 Epoch 10 | Batch 1200/3508 | Timestep 36280 | LR 0.0000100000 | Loss 0.005727 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:48 Epoch 10 | Batch 1210/3508 | Timestep 36290 | LR 0.0000100000 | Loss 0.012504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:50 Epoch 10 | Batch 1220/3508 | Timestep 36300 | LR 0.0000100000 | Loss 0.043333 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:53 Epoch 10 | Batch 1230/3508 | Timestep 36310 | LR 0.0000100000 | Loss 0.001131 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:54 Epoch 10 | Batch 1240/3508 | Timestep 36320 | LR 0.0000100000 | Loss 0.019209 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:56 Epoch 10 | Batch 1250/3508 | Timestep 36330 | LR 0.0000100000 | Loss 0.012076 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:02:58 Epoch 10 | Batch 1260/3508 | Timestep 36340 | LR 0.0000100000 | Loss 0.001672 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:00 Epoch 10 | Batch 1270/3508 | Timestep 36350 | LR 0.0000100000 | Loss 0.011452 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:02 Epoch 10 | Batch 1280/3508 | Timestep 36360 | LR 0.0000100000 | Loss 0.006503 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:04 Epoch 10 | Batch 1290/3508 | Timestep 36370 | LR 0.0000100000 | Loss 0.008774 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:07 Epoch 10 | Batch 1300/3508 | Timestep 36380 | LR 0.0000100000 | Loss 0.019499 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:08 Epoch 10 | Batch 1310/3508 | Timestep 36390 | LR 0.0000100000 | Loss 0.002985 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:11 Epoch 10 | Batch 1320/3508 | Timestep 36400 | LR 0.0000100000 | Loss 0.014279 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:13 Epoch 10 | Batch 1330/3508 | Timestep 36410 | LR 0.0000100000 | Loss 0.010276 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:16 Epoch 10 | Batch 1340/3508 | Timestep 36420 | LR 0.0000100000 | Loss 0.013854 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:18 Epoch 10 | Batch 1350/3508 | Timestep 36430 | LR 0.0000100000 | Loss 0.002566 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:20 Epoch 10 | Batch 1360/3508 | Timestep 36440 | LR 0.0000100000 | Loss 0.014757 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:23 Epoch 10 | Batch 1370/3508 | Timestep 36450 | LR 0.0000100000 | Loss 0.020222 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:26 Epoch 10 | Batch 1380/3508 | Timestep 36460 | LR 0.0000100000 | Loss 0.001340 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:28 Epoch 10 | Batch 1390/3508 | Timestep 36470 | LR 0.0000100000 | Loss 0.019152 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:30 Epoch 10 | Batch 1400/3508 | Timestep 36480 | LR 0.0000100000 | Loss 0.005335 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:32 Epoch 10 | Batch 1410/3508 | Timestep 36490 | LR 0.0000100000 | Loss 0.010816 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:34 Epoch 10 | Batch 1420/3508 | Timestep 36500 | LR 0.0000100000 | Loss 0.004139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:36 Epoch 10 | Batch 1430/3508 | Timestep 36510 | LR 0.0000100000 | Loss 0.004444 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:39 Epoch 10 | Batch 1440/3508 | Timestep 36520 | LR 0.0000100000 | Loss 0.011729 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:41 Epoch 10 | Batch 1450/3508 | Timestep 36530 | LR 0.0000100000 | Loss 0.005839 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:43 Epoch 10 | Batch 1460/3508 | Timestep 36540 | LR 0.0000100000 | Loss 0.022253 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:45 Epoch 10 | Batch 1470/3508 | Timestep 36550 | LR 0.0000100000 | Loss 0.011413 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:47 Epoch 10 | Batch 1480/3508 | Timestep 36560 | LR 0.0000100000 | Loss 0.035449 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:50 Epoch 10 | Batch 1490/3508 | Timestep 36570 | LR 0.0000100000 | Loss 0.010085 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:51 Epoch 10 | Batch 1500/3508 | Timestep 36580 | LR 0.0000100000 | Loss 0.007122 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:53 Epoch 10 | Batch 1510/3508 | Timestep 36590 | LR 0.0000100000 | Loss 0.015636 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:55 Epoch 10 | Batch 1520/3508 | Timestep 36600 | LR 0.0000100000 | Loss 0.014467 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:57 Epoch 10 | Batch 1530/3508 | Timestep 36610 | LR 0.0000100000 | Loss 0.001888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:03:59 Epoch 10 | Batch 1540/3508 | Timestep 36620 | LR 0.0000100000 | Loss 0.005554 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:02 Epoch 10 | Batch 1550/3508 | Timestep 36630 | LR 0.0000100000 | Loss 0.017034 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:04 Epoch 10 | Batch 1560/3508 | Timestep 36640 | LR 0.0000100000 | Loss 0.002843 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:06 Epoch 10 | Batch 1570/3508 | Timestep 36650 | LR 0.0000100000 | Loss 0.007910 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:08 Epoch 10 | Batch 1580/3508 | Timestep 36660 | LR 0.0000100000 | Loss 0.004708 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:10 Epoch 10 | Batch 1590/3508 | Timestep 36670 | LR 0.0000100000 | Loss 0.003885 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:12 Epoch 10 | Batch 1600/3508 | Timestep 36680 | LR 0.0000100000 | Loss 0.015542 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:14 Epoch 10 | Batch 1610/3508 | Timestep 36690 | LR 0.0000100000 | Loss 0.019481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:16 Epoch 10 | Batch 1620/3508 | Timestep 36700 | LR 0.0000100000 | Loss 0.001297 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:18 Epoch 10 | Batch 1630/3508 | Timestep 36710 | LR 0.0000100000 | Loss 0.010691 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:20 Epoch 10 | Batch 1640/3508 | Timestep 36720 | LR 0.0000100000 | Loss 0.000986 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:23 Epoch 10 | Batch 1650/3508 | Timestep 36730 | LR 0.0000100000 | Loss 0.003379 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:25 Epoch 10 | Batch 1660/3508 | Timestep 36740 | LR 0.0000100000 | Loss 0.005164 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:26 Epoch 10 | Batch 1670/3508 | Timestep 36750 | LR 0.0000100000 | Loss 0.010120 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:30 Epoch 10 | Batch 1680/3508 | Timestep 36760 | LR 0.0000100000 | Loss 0.004235 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:32 Epoch 10 | Batch 1690/3508 | Timestep 36770 | LR 0.0000100000 | Loss 0.002526 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:34 Epoch 10 | Batch 1700/3508 | Timestep 36780 | LR 0.0000100000 | Loss 0.009904 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:36 Epoch 10 | Batch 1710/3508 | Timestep 36790 | LR 0.0000100000 | Loss 0.006278 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:38 Epoch 10 | Batch 1720/3508 | Timestep 36800 | LR 0.0000100000 | Loss 0.005481 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:40 Epoch 10 | Batch 1730/3508 | Timestep 36810 | LR 0.0000100000 | Loss 0.033039 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:42 Epoch 10 | Batch 1740/3508 | Timestep 36820 | LR 0.0000100000 | Loss 0.017422 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:44 Epoch 10 | Batch 1750/3508 | Timestep 36830 | LR 0.0000100000 | Loss 0.016782 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:47 Epoch 10 | Batch 1760/3508 | Timestep 36840 | LR 0.0000100000 | Loss 0.013346 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:50 Epoch 10 | Batch 1770/3508 | Timestep 36850 | LR 0.0000100000 | Loss 0.024878 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:52 Epoch 10 | Batch 1780/3508 | Timestep 36860 | LR 0.0000100000 | Loss 0.009680 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:54 Epoch 10 | Batch 1790/3508 | Timestep 36870 | LR 0.0000100000 | Loss 0.004781 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:56 Epoch 10 | Batch 1800/3508 | Timestep 36880 | LR 0.0000100000 | Loss 0.010933 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:04:59 Epoch 10 | Batch 1810/3508 | Timestep 36890 | LR 0.0000100000 | Loss 0.022368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:00 Epoch 10 | Batch 1820/3508 | Timestep 36900 | LR 0.0000100000 | Loss 0.000549 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:03 Epoch 10 | Batch 1830/3508 | Timestep 36910 | LR 0.0000100000 | Loss 0.005383 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:05 Epoch 10 | Batch 1840/3508 | Timestep 36920 | LR 0.0000100000 | Loss 0.036493 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:07 Epoch 10 | Batch 1850/3508 | Timestep 36930 | LR 0.0000100000 | Loss 0.003666 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:09 Epoch 10 | Batch 1860/3508 | Timestep 36940 | LR 0.0000100000 | Loss 0.001658 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:11 Epoch 10 | Batch 1870/3508 | Timestep 36950 | LR 0.0000100000 | Loss 0.029141 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:13 Epoch 10 | Batch 1880/3508 | Timestep 36960 | LR 0.0000100000 | Loss 0.006127 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:15 Epoch 10 | Batch 1890/3508 | Timestep 36970 | LR 0.0000100000 | Loss 0.003660 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:17 Epoch 10 | Batch 1900/3508 | Timestep 36980 | LR 0.0000100000 | Loss 0.001341 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:19 Epoch 10 | Batch 1910/3508 | Timestep 36990 | LR 0.0000100000 | Loss 0.002136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:21 Epoch 10 | Batch 1920/3508 | Timestep 37000 | LR 0.0000100000 | Loss 0.003891 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:23 Epoch 10 | Batch 1930/3508 | Timestep 37010 | LR 0.0000100000 | Loss 0.003614 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:25 Epoch 10 | Batch 1940/3508 | Timestep 37020 | LR 0.0000100000 | Loss 0.019300 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:27 Epoch 10 | Batch 1950/3508 | Timestep 37030 | LR 0.0000100000 | Loss 0.010965 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:30 Epoch 10 | Batch 1960/3508 | Timestep 37040 | LR 0.0000100000 | Loss 0.010440 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:32 Epoch 10 | Batch 1970/3508 | Timestep 37050 | LR 0.0000100000 | Loss 0.007858 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:34 Epoch 10 | Batch 1980/3508 | Timestep 37060 | LR 0.0000100000 | Loss 0.012899 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:36 Epoch 10 | Batch 1990/3508 | Timestep 37070 | LR 0.0000100000 | Loss 0.013865 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:38 Epoch 10 | Batch 2000/3508 | Timestep 37080 | LR 0.0000100000 | Loss 0.011670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:40 Epoch 10 | Batch 2010/3508 | Timestep 37090 | LR 0.0000100000 | Loss 0.003410 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:43 Epoch 10 | Batch 2020/3508 | Timestep 37100 | LR 0.0000100000 | Loss 0.005247 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:45 Epoch 10 | Batch 2030/3508 | Timestep 37110 | LR 0.0000100000 | Loss 0.003566 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:47 Epoch 10 | Batch 2040/3508 | Timestep 37120 | LR 0.0000100000 | Loss 0.012030 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:49 Epoch 10 | Batch 2050/3508 | Timestep 37130 | LR 0.0000100000 | Loss 0.007136 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:51 Epoch 10 | Batch 2060/3508 | Timestep 37140 | LR 0.0000100000 | Loss 0.002294 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:53 Epoch 10 | Batch 2070/3508 | Timestep 37150 | LR 0.0000100000 | Loss 0.006646 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:55 Epoch 10 | Batch 2080/3508 | Timestep 37160 | LR 0.0000100000 | Loss 0.005162 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:57 Epoch 10 | Batch 2090/3508 | Timestep 37170 | LR 0.0000100000 | Loss 0.015642 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:05:59 Epoch 10 | Batch 2100/3508 | Timestep 37180 | LR 0.0000100000 | Loss 0.014376 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:01 Epoch 10 | Batch 2110/3508 | Timestep 37190 | LR 0.0000100000 | Loss 0.007655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:02 Epoch 10 | Batch 2120/3508 | Timestep 37200 | LR 0.0000100000 | Loss 0.019717 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:04 Epoch 10 | Batch 2130/3508 | Timestep 37210 | LR 0.0000100000 | Loss 0.009634 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:06 Epoch 10 | Batch 2140/3508 | Timestep 37220 | LR 0.0000100000 | Loss 0.004231 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:08 Epoch 10 | Batch 2150/3508 | Timestep 37230 | LR 0.0000100000 | Loss 0.004501 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:10 Epoch 10 | Batch 2160/3508 | Timestep 37240 | LR 0.0000100000 | Loss 0.003254 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:12 Epoch 10 | Batch 2170/3508 | Timestep 37250 | LR 0.0000100000 | Loss 0.007973 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:14 Epoch 10 | Batch 2180/3508 | Timestep 37260 | LR 0.0000100000 | Loss 0.015365 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:17 Epoch 10 | Batch 2190/3508 | Timestep 37270 | LR 0.0000100000 | Loss 0.003375 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:19 Epoch 10 | Batch 2200/3508 | Timestep 37280 | LR 0.0000100000 | Loss 0.005080 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:22 Epoch 10 | Batch 2210/3508 | Timestep 37290 | LR 0.0000100000 | Loss 0.003478 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:23 Epoch 10 | Batch 2220/3508 | Timestep 37300 | LR 0.0000100000 | Loss 0.011002 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:25 Epoch 10 | Batch 2230/3508 | Timestep 37310 | LR 0.0000100000 | Loss 0.006197 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:28 Epoch 10 | Batch 2240/3508 | Timestep 37320 | LR 0.0000100000 | Loss 0.011791 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:30 Epoch 10 | Batch 2250/3508 | Timestep 37330 | LR 0.0000100000 | Loss 0.020295 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:32 Epoch 10 | Batch 2260/3508 | Timestep 37340 | LR 0.0000100000 | Loss 0.000980 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:34 Epoch 10 | Batch 2270/3508 | Timestep 37350 | LR 0.0000100000 | Loss 0.000630 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:36 Epoch 10 | Batch 2280/3508 | Timestep 37360 | LR 0.0000100000 | Loss 0.006805 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:38 Epoch 10 | Batch 2290/3508 | Timestep 37370 | LR 0.0000100000 | Loss 0.005968 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:41 Epoch 10 | Batch 2300/3508 | Timestep 37380 | LR 0.0000100000 | Loss 0.005902 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:42 Epoch 10 | Batch 2310/3508 | Timestep 37390 | LR 0.0000100000 | Loss 0.011325 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:45 Epoch 10 | Batch 2320/3508 | Timestep 37400 | LR 0.0000100000 | Loss 0.029053 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:46 Epoch 10 | Batch 2330/3508 | Timestep 37410 | LR 0.0000100000 | Loss 0.002282 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:48 Epoch 10 | Batch 2340/3508 | Timestep 37420 | LR 0.0000100000 | Loss 0.002724 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:51 Epoch 10 | Batch 2350/3508 | Timestep 37430 | LR 0.0000100000 | Loss 0.004863 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:53 Epoch 10 | Batch 2360/3508 | Timestep 37440 | LR 0.0000100000 | Loss 0.017834 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:55 Epoch 10 | Batch 2370/3508 | Timestep 37450 | LR 0.0000100000 | Loss 0.046664 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:57 Epoch 10 | Batch 2380/3508 | Timestep 37460 | LR 0.0000100000 | Loss 0.008075 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:06:59 Epoch 10 | Batch 2390/3508 | Timestep 37470 | LR 0.0000100000 | Loss 0.004218 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:01 Epoch 10 | Batch 2400/3508 | Timestep 37480 | LR 0.0000100000 | Loss 0.020095 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:04 Epoch 10 | Batch 2410/3508 | Timestep 37490 | LR 0.0000100000 | Loss 0.000408 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:07 Epoch 10 | Batch 2420/3508 | Timestep 37500 | LR 0.0000100000 | Loss 0.001102 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:08 Epoch 10 | Batch 2430/3508 | Timestep 37510 | LR 0.0000100000 | Loss 0.002752 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:11 Epoch 10 | Batch 2440/3508 | Timestep 37520 | LR 0.0000100000 | Loss 0.004983 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:13 Epoch 10 | Batch 2450/3508 | Timestep 37530 | LR 0.0000100000 | Loss 0.004722 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:15 Epoch 10 | Batch 2460/3508 | Timestep 37540 | LR 0.0000100000 | Loss 0.000970 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:17 Epoch 10 | Batch 2470/3508 | Timestep 37550 | LR 0.0000100000 | Loss 0.010412 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:20 Epoch 10 | Batch 2480/3508 | Timestep 37560 | LR 0.0000100000 | Loss 0.011659 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:23 Epoch 10 | Batch 2490/3508 | Timestep 37570 | LR 0.0000100000 | Loss 0.007913 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:25 Epoch 10 | Batch 2500/3508 | Timestep 37580 | LR 0.0000100000 | Loss 0.009352 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:27 Epoch 10 | Batch 2510/3508 | Timestep 37590 | LR 0.0000100000 | Loss 0.007942 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:29 Epoch 10 | Batch 2520/3508 | Timestep 37600 | LR 0.0000100000 | Loss 0.012581 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:31 Epoch 10 | Batch 2530/3508 | Timestep 37610 | LR 0.0000100000 | Loss 0.008449 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:33 Epoch 10 | Batch 2540/3508 | Timestep 37620 | LR 0.0000100000 | Loss 0.001125 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:36 Epoch 10 | Batch 2550/3508 | Timestep 37630 | LR 0.0000100000 | Loss 0.001199 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:38 Epoch 10 | Batch 2560/3508 | Timestep 37640 | LR 0.0000100000 | Loss 0.010497 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:40 Epoch 10 | Batch 2570/3508 | Timestep 37650 | LR 0.0000100000 | Loss 0.010645 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:42 Epoch 10 | Batch 2580/3508 | Timestep 37660 | LR 0.0000100000 | Loss 0.015921 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:44 Epoch 10 | Batch 2590/3508 | Timestep 37670 | LR 0.0000100000 | Loss 0.001484 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:46 Epoch 10 | Batch 2600/3508 | Timestep 37680 | LR 0.0000100000 | Loss 0.018908 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:49 Epoch 10 | Batch 2610/3508 | Timestep 37690 | LR 0.0000100000 | Loss 0.002956 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:51 Epoch 10 | Batch 2620/3508 | Timestep 37700 | LR 0.0000100000 | Loss 0.010504 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:53 Epoch 10 | Batch 2630/3508 | Timestep 37710 | LR 0.0000100000 | Loss 0.007349 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:56 Epoch 10 | Batch 2640/3508 | Timestep 37720 | LR 0.0000100000 | Loss 0.025336 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:57 Epoch 10 | Batch 2650/3508 | Timestep 37730 | LR 0.0000100000 | Loss 0.001507 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:07:59 Epoch 10 | Batch 2660/3508 | Timestep 37740 | LR 0.0000100000 | Loss 0.002775 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:02 Epoch 10 | Batch 2670/3508 | Timestep 37750 | LR 0.0000100000 | Loss 0.009557 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:04 Epoch 10 | Batch 2680/3508 | Timestep 37760 | LR 0.0000100000 | Loss 0.016118 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:06 Epoch 10 | Batch 2690/3508 | Timestep 37770 | LR 0.0000100000 | Loss 0.008800 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:08 Epoch 10 | Batch 2700/3508 | Timestep 37780 | LR 0.0000100000 | Loss 0.006132 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:11 Epoch 10 | Batch 2710/3508 | Timestep 37790 | LR 0.0000100000 | Loss 0.004506 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:13 Epoch 10 | Batch 2720/3508 | Timestep 37800 | LR 0.0000100000 | Loss 0.005167 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:15 Epoch 10 | Batch 2730/3508 | Timestep 37810 | LR 0.0000100000 | Loss 0.005455 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:17 Epoch 10 | Batch 2740/3508 | Timestep 37820 | LR 0.0000100000 | Loss 0.006337 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:19 Epoch 10 | Batch 2750/3508 | Timestep 37830 | LR 0.0000100000 | Loss 0.004012 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:21 Epoch 10 | Batch 2760/3508 | Timestep 37840 | LR 0.0000100000 | Loss 0.014684 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:23 Epoch 10 | Batch 2770/3508 | Timestep 37850 | LR 0.0000100000 | Loss 0.005739 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:25 Epoch 10 | Batch 2780/3508 | Timestep 37860 | LR 0.0000100000 | Loss 0.020422 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:27 Epoch 10 | Batch 2790/3508 | Timestep 37870 | LR 0.0000100000 | Loss 0.017827 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:30 Epoch 10 | Batch 2800/3508 | Timestep 37880 | LR 0.0000100000 | Loss 0.004589 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:32 Epoch 10 | Batch 2810/3508 | Timestep 37890 | LR 0.0000100000 | Loss 0.003271 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:34 Epoch 10 | Batch 2820/3508 | Timestep 37900 | LR 0.0000100000 | Loss 0.014228 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:36 Epoch 10 | Batch 2830/3508 | Timestep 37910 | LR 0.0000100000 | Loss 0.012419 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:38 Epoch 10 | Batch 2840/3508 | Timestep 37920 | LR 0.0000100000 | Loss 0.002769 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:40 Epoch 10 | Batch 2850/3508 | Timestep 37930 | LR 0.0000100000 | Loss 0.020109 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:42 Epoch 10 | Batch 2860/3508 | Timestep 37940 | LR 0.0000100000 | Loss 0.003816 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:44 Epoch 10 | Batch 2870/3508 | Timestep 37950 | LR 0.0000100000 | Loss 0.006666 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:46 Epoch 10 | Batch 2880/3508 | Timestep 37960 | LR 0.0000100000 | Loss 0.019229 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:48 Epoch 10 | Batch 2890/3508 | Timestep 37970 | LR 0.0000100000 | Loss 0.014264 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:51 Epoch 10 | Batch 2900/3508 | Timestep 37980 | LR 0.0000100000 | Loss 0.002822 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:53 Epoch 10 | Batch 2910/3508 | Timestep 37990 | LR 0.0000100000 | Loss 0.009195 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:55 Epoch 10 | Batch 2920/3508 | Timestep 38000 | LR 0.0000100000 | Loss 0.016065 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:57 Epoch 10 | Batch 2930/3508 | Timestep 38010 | LR 0.0000100000 | Loss 0.005052 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:08:59 Epoch 10 | Batch 2940/3508 | Timestep 38020 | LR 0.0000100000 | Loss 0.014394 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:02 Epoch 10 | Batch 2950/3508 | Timestep 38030 | LR 0.0000100000 | Loss 0.002993 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:04 Epoch 10 | Batch 2960/3508 | Timestep 38040 | LR 0.0000100000 | Loss 0.005936 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:06 Epoch 10 | Batch 2970/3508 | Timestep 38050 | LR 0.0000100000 | Loss 0.021960 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:09 Epoch 10 | Batch 2980/3508 | Timestep 38060 | LR 0.0000100000 | Loss 0.004111 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:10 Epoch 10 | Batch 2990/3508 | Timestep 38070 | LR 0.0000100000 | Loss 0.007798 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:12 Epoch 10 | Batch 3000/3508 | Timestep 38080 | LR 0.0000100000 | Loss 0.011656 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:15 Epoch 10 | Batch 3010/3508 | Timestep 38090 | LR 0.0000100000 | Loss 0.014730 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:17 Epoch 10 | Batch 3020/3508 | Timestep 38100 | LR 0.0000100000 | Loss 0.008655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:20 Epoch 10 | Batch 3030/3508 | Timestep 38110 | LR 0.0000100000 | Loss 0.004584 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:22 Epoch 10 | Batch 3040/3508 | Timestep 38120 | LR 0.0000100000 | Loss 0.017769 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:24 Epoch 10 | Batch 3050/3508 | Timestep 38130 | LR 0.0000100000 | Loss 0.002621 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:26 Epoch 10 | Batch 3060/3508 | Timestep 38140 | LR 0.0000100000 | Loss 0.011057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:29 Epoch 10 | Batch 3070/3508 | Timestep 38150 | LR 0.0000100000 | Loss 0.000612 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:31 Epoch 10 | Batch 3080/3508 | Timestep 38160 | LR 0.0000100000 | Loss 0.004637 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:33 Epoch 10 | Batch 3090/3508 | Timestep 38170 | LR 0.0000100000 | Loss 0.019224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:35 Epoch 10 | Batch 3100/3508 | Timestep 38180 | LR 0.0000100000 | Loss 0.007069 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:37 Epoch 10 | Batch 3110/3508 | Timestep 38190 | LR 0.0000100000 | Loss 0.004476 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:39 Epoch 10 | Batch 3120/3508 | Timestep 38200 | LR 0.0000100000 | Loss 0.018810 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:41 Epoch 10 | Batch 3130/3508 | Timestep 38210 | LR 0.0000100000 | Loss 0.015620 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:43 Epoch 10 | Batch 3140/3508 | Timestep 38220 | LR 0.0000100000 | Loss 0.002301 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:45 Epoch 10 | Batch 3150/3508 | Timestep 38230 | LR 0.0000100000 | Loss 0.007199 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:47 Epoch 10 | Batch 3160/3508 | Timestep 38240 | LR 0.0000100000 | Loss 0.005103 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:50 Epoch 10 | Batch 3170/3508 | Timestep 38250 | LR 0.0000100000 | Loss 0.026275 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:52 Epoch 10 | Batch 3180/3508 | Timestep 38260 | LR 0.0000100000 | Loss 0.007430 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:55 Epoch 10 | Batch 3190/3508 | Timestep 38270 | LR 0.0000100000 | Loss 0.006591 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:56 Epoch 10 | Batch 3200/3508 | Timestep 38280 | LR 0.0000100000 | Loss 0.004104 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:09:59 Epoch 10 | Batch 3210/3508 | Timestep 38290 | LR 0.0000100000 | Loss 0.033139 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:01 Epoch 10 | Batch 3220/3508 | Timestep 38300 | LR 0.0000100000 | Loss 0.012606 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:02 Epoch 10 | Batch 3230/3508 | Timestep 38310 | LR 0.0000100000 | Loss 0.001566 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:04 Epoch 10 | Batch 3240/3508 | Timestep 38320 | LR 0.0000100000 | Loss 0.007190 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:07 Epoch 10 | Batch 3250/3508 | Timestep 38330 | LR 0.0000100000 | Loss 0.011093 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:09 Epoch 10 | Batch 3260/3508 | Timestep 38340 | LR 0.0000100000 | Loss 0.005441 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:12 Epoch 10 | Batch 3270/3508 | Timestep 38350 | LR 0.0000100000 | Loss 0.051234 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:14 Epoch 10 | Batch 3280/3508 | Timestep 38360 | LR 0.0000100000 | Loss 0.008693 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:16 Epoch 10 | Batch 3290/3508 | Timestep 38370 | LR 0.0000100000 | Loss 0.008121 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:18 Epoch 10 | Batch 3300/3508 | Timestep 38380 | LR 0.0000100000 | Loss 0.001034 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:20 Epoch 10 | Batch 3310/3508 | Timestep 38390 | LR 0.0000100000 | Loss 0.017057 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:22 Epoch 10 | Batch 3320/3508 | Timestep 38400 | LR 0.0000100000 | Loss 0.002533 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:24 Epoch 10 | Batch 3330/3508 | Timestep 38410 | LR 0.0000100000 | Loss 0.003927 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:26 Epoch 10 | Batch 3340/3508 | Timestep 38420 | LR 0.0000100000 | Loss 0.002224 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:28 Epoch 10 | Batch 3350/3508 | Timestep 38430 | LR 0.0000100000 | Loss 0.005329 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:30 Epoch 10 | Batch 3360/3508 | Timestep 38440 | LR 0.0000100000 | Loss 0.013153 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:32 Epoch 10 | Batch 3370/3508 | Timestep 38450 | LR 0.0000100000 | Loss 0.014270 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:34 Epoch 10 | Batch 3380/3508 | Timestep 38460 | LR 0.0000100000 | Loss 0.021203 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:37 Epoch 10 | Batch 3390/3508 | Timestep 38470 | LR 0.0000100000 | Loss 0.007975 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:39 Epoch 10 | Batch 3400/3508 | Timestep 38480 | LR 0.0000100000 | Loss 0.014084 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:41 Epoch 10 | Batch 3410/3508 | Timestep 38490 | LR 0.0000100000 | Loss 0.008368 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:43 Epoch 10 | Batch 3420/3508 | Timestep 38500 | LR 0.0000100000 | Loss 0.018023 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:46 Epoch 10 | Batch 3430/3508 | Timestep 38510 | LR 0.0000100000 | Loss 0.006406 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:48 Epoch 10 | Batch 3440/3508 | Timestep 38520 | LR 0.0000100000 | Loss 0.009569 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:50 Epoch 10 | Batch 3450/3508 | Timestep 38530 | LR 0.0000100000 | Loss 0.007408 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:52 Epoch 10 | Batch 3460/3508 | Timestep 38540 | LR 0.0000100000 | Loss 0.000269 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:53 Epoch 10 | Batch 3470/3508 | Timestep 38550 | LR 0.0000100000 | Loss 0.001655 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:56 Epoch 10 | Batch 3480/3508 | Timestep 38560 | LR 0.0000100000 | Loss 0.020963 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:10:58 Epoch 10 | Batch 3490/3508 | Timestep 38570 | LR 0.0000100000 | Loss 0.014675 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:11:00 Epoch 10 | Batch 3500/3508 | Timestep 38580 | LR 0.0000100000 | Loss 0.001888 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:11:02 ** Evaluating on validation dataset ** INFO root Thu, 25 Jun 2026 17:11:34 precision recall f1-score support CARDINAL 0.8431 0.8113 0.8269 159 CURR 0.7143 0.9091 0.8000 22 DATE 0.9357 0.9419 0.9388 1669 EVENT 0.7176 0.7633 0.7397 283 FAC 0.7313 0.8305 0.7778 118 GPE 0.9624 0.9692 0.9658 2140 LANGUAGE 0.4194 0.8125 0.5532 16 LAW 0.4848 0.8421 0.6154 19 LOC 0.6818 0.8333 0.7500 90 MONEY 0.7391 0.8500 0.7907 20 NORP 0.6736 0.7623 0.7152 509 OCC 0.8405 0.8710 0.8554 496 ORDINAL 0.9354 0.9417 0.9385 446 ORG 0.9298 0.9373 0.9335 1866 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9396 0.9617 0.9505 679 PRODUCT 0.4000 0.5000 0.4444 8 QUANTITY 0.2857 0.6667 0.4000 3 TIME 0.6098 0.8065 0.6944 31 UNIT 0.4286 0.7500 0.5455 4 WEBSITE 0.5444 0.6125 0.5765 80 micro avg 0.8921 0.9189 0.9053 8670 macro avg 0.7019 0.8273 0.7511 8670 weighted avg 0.8975 0.9189 0.9075 8670 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:11:45 Epoch 10 | Timestep 38588 | Train Loss 0.010169 | Val Loss 0.057604 | F1 0.905289 INFO arabiner.trainers.BertNestedTrainer Thu, 25 Jun 2026 17:11:45 Early termination triggered