INFO ArabicNER.arabiner.bin.train Thu, 14 May 2026 11:05:02 Writing config to /content/Wojood/args.json INFO arabiner.utils.data Thu, 14 May 2026 11:05:03 2891 batches found INFO arabiner.utils.data Thu, 14 May 2026 11:05:03 413 batches found INFO arabiner.utils.data Thu, 14 May 2026 11:05:04 826 batches found INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:14 Epoch 0 | Batch 10/2891 | Timestep 10 | LR 0.0000100000 | Loss 2.324883 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:15 Epoch 0 | Batch 20/2891 | Timestep 20 | LR 0.0000100000 | Loss 1.173435 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:16 Epoch 0 | Batch 30/2891 | Timestep 30 | LR 0.0000100000 | Loss 0.526411 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:18 Epoch 0 | Batch 40/2891 | Timestep 40 | LR 0.0000100000 | Loss 0.609557 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:20 Epoch 0 | Batch 50/2891 | Timestep 50 | LR 0.0000100000 | Loss 0.358552 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:21 Epoch 0 | Batch 60/2891 | Timestep 60 | LR 0.0000100000 | Loss 0.488899 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:22 Epoch 0 | Batch 70/2891 | Timestep 70 | LR 0.0000100000 | Loss 0.561547 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:24 Epoch 0 | Batch 80/2891 | Timestep 80 | LR 0.0000100000 | Loss 0.577988 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:25 Epoch 0 | Batch 90/2891 | Timestep 90 | LR 0.0000100000 | Loss 0.389383 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:27 Epoch 0 | Batch 100/2891 | Timestep 100 | LR 0.0000100000 | Loss 0.714398 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:28 Epoch 0 | Batch 110/2891 | Timestep 110 | LR 0.0000100000 | Loss 0.350789 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:30 Epoch 0 | Batch 120/2891 | Timestep 120 | LR 0.0000100000 | Loss 0.602607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:31 Epoch 0 | Batch 130/2891 | Timestep 130 | LR 0.0000100000 | Loss 0.232268 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:32 Epoch 0 | Batch 140/2891 | Timestep 140 | LR 0.0000100000 | Loss 0.563817 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:34 Epoch 0 | Batch 150/2891 | Timestep 150 | LR 0.0000100000 | Loss 0.499102 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:36 Epoch 0 | Batch 160/2891 | Timestep 160 | LR 0.0000100000 | Loss 0.234192 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:37 Epoch 0 | Batch 170/2891 | Timestep 170 | LR 0.0000100000 | Loss 0.483134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:38 Epoch 0 | Batch 180/2891 | Timestep 180 | LR 0.0000100000 | Loss 0.603189 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:40 Epoch 0 | Batch 190/2891 | Timestep 190 | LR 0.0000100000 | Loss 0.285065 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:42 Epoch 0 | Batch 200/2891 | Timestep 200 | LR 0.0000100000 | Loss 0.412713 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:43 Epoch 0 | Batch 210/2891 | Timestep 210 | LR 0.0000100000 | Loss 0.204796 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:45 Epoch 0 | Batch 220/2891 | Timestep 220 | LR 0.0000100000 | Loss 0.359098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:46 Epoch 0 | Batch 230/2891 | Timestep 230 | LR 0.0000100000 | Loss 0.236311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:48 Epoch 0 | Batch 240/2891 | Timestep 240 | LR 0.0000100000 | Loss 0.220326 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:50 Epoch 0 | Batch 250/2891 | Timestep 250 | LR 0.0000100000 | Loss 0.190427 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:51 Epoch 0 | Batch 260/2891 | Timestep 260 | LR 0.0000100000 | Loss 0.410046 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:53 Epoch 0 | Batch 270/2891 | Timestep 270 | LR 0.0000100000 | Loss 0.255216 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:54 Epoch 0 | Batch 280/2891 | Timestep 280 | LR 0.0000100000 | Loss 0.397995 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:55 Epoch 0 | Batch 290/2891 | Timestep 290 | LR 0.0000100000 | Loss 0.216170 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:57 Epoch 0 | Batch 300/2891 | Timestep 300 | LR 0.0000100000 | Loss 0.156881 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:05:59 Epoch 0 | Batch 310/2891 | Timestep 310 | LR 0.0000100000 | Loss 0.281735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:00 Epoch 0 | Batch 320/2891 | Timestep 320 | LR 0.0000100000 | Loss 0.177287 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:02 Epoch 0 | Batch 330/2891 | Timestep 330 | LR 0.0000100000 | Loss 0.178486 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:03 Epoch 0 | Batch 340/2891 | Timestep 340 | LR 0.0000100000 | Loss 0.305974 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:05 Epoch 0 | Batch 350/2891 | Timestep 350 | LR 0.0000100000 | Loss 0.275403 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:07 Epoch 0 | Batch 360/2891 | Timestep 360 | LR 0.0000100000 | Loss 0.053450 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:08 Epoch 0 | Batch 370/2891 | Timestep 370 | LR 0.0000100000 | Loss 0.273982 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:10 Epoch 0 | Batch 380/2891 | Timestep 380 | LR 0.0000100000 | Loss 0.360873 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:11 Epoch 0 | Batch 390/2891 | Timestep 390 | LR 0.0000100000 | Loss 0.229149 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:13 Epoch 0 | Batch 400/2891 | Timestep 400 | LR 0.0000100000 | Loss 0.151315 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:14 Epoch 0 | Batch 410/2891 | Timestep 410 | LR 0.0000100000 | Loss 0.114798 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:16 Epoch 0 | Batch 420/2891 | Timestep 420 | LR 0.0000100000 | Loss 0.194792 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:18 Epoch 0 | Batch 430/2891 | Timestep 430 | LR 0.0000100000 | Loss 0.072028 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:19 Epoch 0 | Batch 440/2891 | Timestep 440 | LR 0.0000100000 | Loss 0.302875 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:21 Epoch 0 | Batch 450/2891 | Timestep 450 | LR 0.0000100000 | Loss 0.140062 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:22 Epoch 0 | Batch 460/2891 | Timestep 460 | LR 0.0000100000 | Loss 0.232378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:24 Epoch 0 | Batch 470/2891 | Timestep 470 | LR 0.0000100000 | Loss 0.423773 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:25 Epoch 0 | Batch 480/2891 | Timestep 480 | LR 0.0000100000 | Loss 0.270559 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:27 Epoch 0 | Batch 490/2891 | Timestep 490 | LR 0.0000100000 | Loss 0.162064 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:28 Epoch 0 | Batch 500/2891 | Timestep 500 | LR 0.0000100000 | Loss 0.103830 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:30 Epoch 0 | Batch 510/2891 | Timestep 510 | LR 0.0000100000 | Loss 0.479498 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:31 Epoch 0 | Batch 520/2891 | Timestep 520 | LR 0.0000100000 | Loss 0.083901 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:33 Epoch 0 | Batch 530/2891 | Timestep 530 | LR 0.0000100000 | Loss 0.237902 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:34 Epoch 0 | Batch 540/2891 | Timestep 540 | LR 0.0000100000 | Loss 0.171042 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:36 Epoch 0 | Batch 550/2891 | Timestep 550 | LR 0.0000100000 | Loss 0.106831 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:37 Epoch 0 | Batch 560/2891 | Timestep 560 | LR 0.0000100000 | Loss 0.145911 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:39 Epoch 0 | Batch 570/2891 | Timestep 570 | LR 0.0000100000 | Loss 0.074921 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:41 Epoch 0 | Batch 580/2891 | Timestep 580 | LR 0.0000100000 | Loss 0.128396 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:42 Epoch 0 | Batch 590/2891 | Timestep 590 | LR 0.0000100000 | Loss 0.069802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:44 Epoch 0 | Batch 600/2891 | Timestep 600 | LR 0.0000100000 | Loss 0.174573 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:45 Epoch 0 | Batch 610/2891 | Timestep 610 | LR 0.0000100000 | Loss 0.083392 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:47 Epoch 0 | Batch 620/2891 | Timestep 620 | LR 0.0000100000 | Loss 0.108246 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:49 Epoch 0 | Batch 630/2891 | Timestep 630 | LR 0.0000100000 | Loss 0.296989 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:51 Epoch 0 | Batch 640/2891 | Timestep 640 | LR 0.0000100000 | Loss 0.156572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:53 Epoch 0 | Batch 650/2891 | Timestep 650 | LR 0.0000100000 | Loss 0.160135 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:54 Epoch 0 | Batch 660/2891 | Timestep 660 | LR 0.0000100000 | Loss 0.168749 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:56 Epoch 0 | Batch 670/2891 | Timestep 670 | LR 0.0000100000 | Loss 0.179080 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:57 Epoch 0 | Batch 680/2891 | Timestep 680 | LR 0.0000100000 | Loss 0.151059 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:06:59 Epoch 0 | Batch 690/2891 | Timestep 690 | LR 0.0000100000 | Loss 0.180666 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:02 Epoch 0 | Batch 700/2891 | Timestep 700 | LR 0.0000100000 | Loss 0.209137 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:04 Epoch 0 | Batch 710/2891 | Timestep 710 | LR 0.0000100000 | Loss 0.115366 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:05 Epoch 0 | Batch 720/2891 | Timestep 720 | LR 0.0000100000 | Loss 0.151726 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:07 Epoch 0 | Batch 730/2891 | Timestep 730 | LR 0.0000100000 | Loss 0.073436 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:09 Epoch 0 | Batch 740/2891 | Timestep 740 | LR 0.0000100000 | Loss 0.142909 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:11 Epoch 0 | Batch 750/2891 | Timestep 750 | LR 0.0000100000 | Loss 0.080303 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:12 Epoch 0 | Batch 760/2891 | Timestep 760 | LR 0.0000100000 | Loss 0.091182 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:14 Epoch 0 | Batch 770/2891 | Timestep 770 | LR 0.0000100000 | Loss 0.092305 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:15 Epoch 0 | Batch 780/2891 | Timestep 780 | LR 0.0000100000 | Loss 0.066391 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:17 Epoch 0 | Batch 790/2891 | Timestep 790 | LR 0.0000100000 | Loss 0.089149 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:19 Epoch 0 | Batch 800/2891 | Timestep 800 | LR 0.0000100000 | Loss 0.104559 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:21 Epoch 0 | Batch 810/2891 | Timestep 810 | LR 0.0000100000 | Loss 0.098502 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:22 Epoch 0 | Batch 820/2891 | Timestep 820 | LR 0.0000100000 | Loss 0.112207 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:24 Epoch 0 | Batch 830/2891 | Timestep 830 | LR 0.0000100000 | Loss 0.044806 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:25 Epoch 0 | Batch 840/2891 | Timestep 840 | LR 0.0000100000 | Loss 0.204599 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:28 Epoch 0 | Batch 850/2891 | Timestep 850 | LR 0.0000100000 | Loss 0.083173 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:30 Epoch 0 | Batch 860/2891 | Timestep 860 | LR 0.0000100000 | Loss 0.363307 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:31 Epoch 0 | Batch 870/2891 | Timestep 870 | LR 0.0000100000 | Loss 0.069636 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:33 Epoch 0 | Batch 880/2891 | Timestep 880 | LR 0.0000100000 | Loss 0.089232 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:34 Epoch 0 | Batch 890/2891 | Timestep 890 | LR 0.0000100000 | Loss 0.039814 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:36 Epoch 0 | Batch 900/2891 | Timestep 900 | LR 0.0000100000 | Loss 0.051466 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:38 Epoch 0 | Batch 910/2891 | Timestep 910 | LR 0.0000100000 | Loss 0.079264 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:39 Epoch 0 | Batch 920/2891 | Timestep 920 | LR 0.0000100000 | Loss 0.094196 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:41 Epoch 0 | Batch 930/2891 | Timestep 930 | LR 0.0000100000 | Loss 0.051281 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:43 Epoch 0 | Batch 940/2891 | Timestep 940 | LR 0.0000100000 | Loss 0.135192 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:45 Epoch 0 | Batch 950/2891 | Timestep 950 | LR 0.0000100000 | Loss 0.135706 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:46 Epoch 0 | Batch 960/2891 | Timestep 960 | LR 0.0000100000 | Loss 0.132293 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:48 Epoch 0 | Batch 970/2891 | Timestep 970 | LR 0.0000100000 | Loss 0.286269 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:50 Epoch 0 | Batch 980/2891 | Timestep 980 | LR 0.0000100000 | Loss 0.133657 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:51 Epoch 0 | Batch 990/2891 | Timestep 990 | LR 0.0000100000 | Loss 0.205298 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:53 Epoch 0 | Batch 1000/2891 | Timestep 1000 | LR 0.0000100000 | Loss 0.064546 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:55 Epoch 0 | Batch 1010/2891 | Timestep 1010 | LR 0.0000100000 | Loss 0.093120 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:57 Epoch 0 | Batch 1020/2891 | Timestep 1020 | LR 0.0000100000 | Loss 0.066364 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:07:58 Epoch 0 | Batch 1030/2891 | Timestep 1030 | LR 0.0000100000 | Loss 0.070373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:00 Epoch 0 | Batch 1040/2891 | Timestep 1040 | LR 0.0000100000 | Loss 0.106973 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:02 Epoch 0 | Batch 1050/2891 | Timestep 1050 | LR 0.0000100000 | Loss 0.067055 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:04 Epoch 0 | Batch 1060/2891 | Timestep 1060 | LR 0.0000100000 | Loss 0.064841 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:06 Epoch 0 | Batch 1070/2891 | Timestep 1070 | LR 0.0000100000 | Loss 0.139184 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:07 Epoch 0 | Batch 1080/2891 | Timestep 1080 | LR 0.0000100000 | Loss 0.081060 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:09 Epoch 0 | Batch 1090/2891 | Timestep 1090 | LR 0.0000100000 | Loss 0.087996 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:10 Epoch 0 | Batch 1100/2891 | Timestep 1100 | LR 0.0000100000 | Loss 0.161751 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:12 Epoch 0 | Batch 1110/2891 | Timestep 1110 | LR 0.0000100000 | Loss 0.072989 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:14 Epoch 0 | Batch 1120/2891 | Timestep 1120 | LR 0.0000100000 | Loss 0.063771 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:15 Epoch 0 | Batch 1130/2891 | Timestep 1130 | LR 0.0000100000 | Loss 0.028263 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:17 Epoch 0 | Batch 1140/2891 | Timestep 1140 | LR 0.0000100000 | Loss 0.024461 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:19 Epoch 0 | Batch 1150/2891 | Timestep 1150 | LR 0.0000100000 | Loss 0.063418 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:20 Epoch 0 | Batch 1160/2891 | Timestep 1160 | LR 0.0000100000 | Loss 0.133489 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:22 Epoch 0 | Batch 1170/2891 | Timestep 1170 | LR 0.0000100000 | Loss 0.089338 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:23 Epoch 0 | Batch 1180/2891 | Timestep 1180 | LR 0.0000100000 | Loss 0.096870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:25 Epoch 0 | Batch 1190/2891 | Timestep 1190 | LR 0.0000100000 | Loss 0.073647 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:27 Epoch 0 | Batch 1200/2891 | Timestep 1200 | LR 0.0000100000 | Loss 0.137294 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:28 Epoch 0 | Batch 1210/2891 | Timestep 1210 | LR 0.0000100000 | Loss 0.155405 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:30 Epoch 0 | Batch 1220/2891 | Timestep 1220 | LR 0.0000100000 | Loss 0.023442 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:32 Epoch 0 | Batch 1230/2891 | Timestep 1230 | LR 0.0000100000 | Loss 0.037761 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:34 Epoch 0 | Batch 1240/2891 | Timestep 1240 | LR 0.0000100000 | Loss 0.058547 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:36 Epoch 0 | Batch 1250/2891 | Timestep 1250 | LR 0.0000100000 | Loss 0.035465 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:37 Epoch 0 | Batch 1260/2891 | Timestep 1260 | LR 0.0000100000 | Loss 0.012367 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:39 Epoch 0 | Batch 1270/2891 | Timestep 1270 | LR 0.0000100000 | Loss 0.057364 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:40 Epoch 0 | Batch 1280/2891 | Timestep 1280 | LR 0.0000100000 | Loss 0.104329 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:42 Epoch 0 | Batch 1290/2891 | Timestep 1290 | LR 0.0000100000 | Loss 0.149924 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:43 Epoch 0 | Batch 1300/2891 | Timestep 1300 | LR 0.0000100000 | Loss 0.053464 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:45 Epoch 0 | Batch 1310/2891 | Timestep 1310 | LR 0.0000100000 | Loss 0.088354 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:46 Epoch 0 | Batch 1320/2891 | Timestep 1320 | LR 0.0000100000 | Loss 0.085797 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:48 Epoch 0 | Batch 1330/2891 | Timestep 1330 | LR 0.0000100000 | Loss 0.044324 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:50 Epoch 0 | Batch 1340/2891 | Timestep 1340 | LR 0.0000100000 | Loss 0.107639 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:52 Epoch 0 | Batch 1350/2891 | Timestep 1350 | LR 0.0000100000 | Loss 0.022019 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:54 Epoch 0 | Batch 1360/2891 | Timestep 1360 | LR 0.0000100000 | Loss 0.093993 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:56 Epoch 0 | Batch 1370/2891 | Timestep 1370 | LR 0.0000100000 | Loss 0.081961 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:57 Epoch 0 | Batch 1380/2891 | Timestep 1380 | LR 0.0000100000 | Loss 0.045395 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:08:59 Epoch 0 | Batch 1390/2891 | Timestep 1390 | LR 0.0000100000 | Loss 0.051098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:01 Epoch 0 | Batch 1400/2891 | Timestep 1400 | LR 0.0000100000 | Loss 0.066549 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:03 Epoch 0 | Batch 1410/2891 | Timestep 1410 | LR 0.0000100000 | Loss 0.121778 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:04 Epoch 0 | Batch 1420/2891 | Timestep 1420 | LR 0.0000100000 | Loss 0.185669 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:06 Epoch 0 | Batch 1430/2891 | Timestep 1430 | LR 0.0000100000 | Loss 0.086549 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:08 Epoch 0 | Batch 1440/2891 | Timestep 1440 | LR 0.0000100000 | Loss 0.057761 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:09 Epoch 0 | Batch 1450/2891 | Timestep 1450 | LR 0.0000100000 | Loss 0.048745 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:11 Epoch 0 | Batch 1460/2891 | Timestep 1460 | LR 0.0000100000 | Loss 0.090151 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:12 Epoch 0 | Batch 1470/2891 | Timestep 1470 | LR 0.0000100000 | Loss 0.030489 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:14 Epoch 0 | Batch 1480/2891 | Timestep 1480 | LR 0.0000100000 | Loss 0.067024 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:15 Epoch 0 | Batch 1490/2891 | Timestep 1490 | LR 0.0000100000 | Loss 0.040100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:17 Epoch 0 | Batch 1500/2891 | Timestep 1500 | LR 0.0000100000 | Loss 0.165679 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:18 Epoch 0 | Batch 1510/2891 | Timestep 1510 | LR 0.0000100000 | Loss 0.012572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:20 Epoch 0 | Batch 1520/2891 | Timestep 1520 | LR 0.0000100000 | Loss 0.082719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:22 Epoch 0 | Batch 1530/2891 | Timestep 1530 | LR 0.0000100000 | Loss 0.040662 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:23 Epoch 0 | Batch 1540/2891 | Timestep 1540 | LR 0.0000100000 | Loss 0.202092 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:25 Epoch 0 | Batch 1550/2891 | Timestep 1550 | LR 0.0000100000 | Loss 0.109800 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:27 Epoch 0 | Batch 1560/2891 | Timestep 1560 | LR 0.0000100000 | Loss 0.060711 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:29 Epoch 0 | Batch 1570/2891 | Timestep 1570 | LR 0.0000100000 | Loss 0.071127 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:30 Epoch 0 | Batch 1580/2891 | Timestep 1580 | LR 0.0000100000 | Loss 0.060952 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:32 Epoch 0 | Batch 1590/2891 | Timestep 1590 | LR 0.0000100000 | Loss 0.055091 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:33 Epoch 0 | Batch 1600/2891 | Timestep 1600 | LR 0.0000100000 | Loss 0.059727 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:35 Epoch 0 | Batch 1610/2891 | Timestep 1610 | LR 0.0000100000 | Loss 0.084826 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:36 Epoch 0 | Batch 1620/2891 | Timestep 1620 | LR 0.0000100000 | Loss 0.077607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:38 Epoch 0 | Batch 1630/2891 | Timestep 1630 | LR 0.0000100000 | Loss 0.074160 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:39 Epoch 0 | Batch 1640/2891 | Timestep 1640 | LR 0.0000100000 | Loss 0.040397 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:41 Epoch 0 | Batch 1650/2891 | Timestep 1650 | LR 0.0000100000 | Loss 0.065164 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:42 Epoch 0 | Batch 1660/2891 | Timestep 1660 | LR 0.0000100000 | Loss 0.063965 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:44 Epoch 0 | Batch 1670/2891 | Timestep 1670 | LR 0.0000100000 | Loss 0.123811 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:46 Epoch 0 | Batch 1680/2891 | Timestep 1680 | LR 0.0000100000 | Loss 0.099223 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:48 Epoch 0 | Batch 1690/2891 | Timestep 1690 | LR 0.0000100000 | Loss 0.255820 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:50 Epoch 0 | Batch 1700/2891 | Timestep 1700 | LR 0.0000100000 | Loss 0.070330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:51 Epoch 0 | Batch 1710/2891 | Timestep 1710 | LR 0.0000100000 | Loss 0.054425 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:53 Epoch 0 | Batch 1720/2891 | Timestep 1720 | LR 0.0000100000 | Loss 0.078046 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:55 Epoch 0 | Batch 1730/2891 | Timestep 1730 | LR 0.0000100000 | Loss 0.111457 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:57 Epoch 0 | Batch 1740/2891 | Timestep 1740 | LR 0.0000100000 | Loss 0.065000 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:09:59 Epoch 0 | Batch 1750/2891 | Timestep 1750 | LR 0.0000100000 | Loss 0.077976 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:00 Epoch 0 | Batch 1760/2891 | Timestep 1760 | LR 0.0000100000 | Loss 0.049378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:02 Epoch 0 | Batch 1770/2891 | Timestep 1770 | LR 0.0000100000 | Loss 0.123357 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:04 Epoch 0 | Batch 1780/2891 | Timestep 1780 | LR 0.0000100000 | Loss 0.039880 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:06 Epoch 0 | Batch 1790/2891 | Timestep 1790 | LR 0.0000100000 | Loss 0.071150 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:07 Epoch 0 | Batch 1800/2891 | Timestep 1800 | LR 0.0000100000 | Loss 0.019623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:09 Epoch 0 | Batch 1810/2891 | Timestep 1810 | LR 0.0000100000 | Loss 0.060628 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:10 Epoch 0 | Batch 1820/2891 | Timestep 1820 | LR 0.0000100000 | Loss 0.055253 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:12 Epoch 0 | Batch 1830/2891 | Timestep 1830 | LR 0.0000100000 | Loss 0.169611 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:14 Epoch 0 | Batch 1840/2891 | Timestep 1840 | LR 0.0000100000 | Loss 0.067191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:16 Epoch 0 | Batch 1850/2891 | Timestep 1850 | LR 0.0000100000 | Loss 0.050017 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:18 Epoch 0 | Batch 1860/2891 | Timestep 1860 | LR 0.0000100000 | Loss 0.096305 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:19 Epoch 0 | Batch 1870/2891 | Timestep 1870 | LR 0.0000100000 | Loss 0.075100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:20 Epoch 0 | Batch 1880/2891 | Timestep 1880 | LR 0.0000100000 | Loss 0.060584 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:22 Epoch 0 | Batch 1890/2891 | Timestep 1890 | LR 0.0000100000 | Loss 0.049696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:24 Epoch 0 | Batch 1900/2891 | Timestep 1900 | LR 0.0000100000 | Loss 0.018711 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:25 Epoch 0 | Batch 1910/2891 | Timestep 1910 | LR 0.0000100000 | Loss 0.049190 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:27 Epoch 0 | Batch 1920/2891 | Timestep 1920 | LR 0.0000100000 | Loss 0.058994 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:29 Epoch 0 | Batch 1930/2891 | Timestep 1930 | LR 0.0000100000 | Loss 0.032352 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:30 Epoch 0 | Batch 1940/2891 | Timestep 1940 | LR 0.0000100000 | Loss 0.081602 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:32 Epoch 0 | Batch 1950/2891 | Timestep 1950 | LR 0.0000100000 | Loss 0.040913 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:34 Epoch 0 | Batch 1960/2891 | Timestep 1960 | LR 0.0000100000 | Loss 0.051735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:35 Epoch 0 | Batch 1970/2891 | Timestep 1970 | LR 0.0000100000 | Loss 0.025297 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:37 Epoch 0 | Batch 1980/2891 | Timestep 1980 | LR 0.0000100000 | Loss 0.093813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:39 Epoch 0 | Batch 1990/2891 | Timestep 1990 | LR 0.0000100000 | Loss 0.068172 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:40 Epoch 0 | Batch 2000/2891 | Timestep 2000 | LR 0.0000100000 | Loss 0.039009 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:42 Epoch 0 | Batch 2010/2891 | Timestep 2010 | LR 0.0000100000 | Loss 0.067149 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:44 Epoch 0 | Batch 2020/2891 | Timestep 2020 | LR 0.0000100000 | Loss 0.044105 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:45 Epoch 0 | Batch 2030/2891 | Timestep 2030 | LR 0.0000100000 | Loss 0.128876 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:47 Epoch 0 | Batch 2040/2891 | Timestep 2040 | LR 0.0000100000 | Loss 0.054065 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:48 Epoch 0 | Batch 2050/2891 | Timestep 2050 | LR 0.0000100000 | Loss 0.111539 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:50 Epoch 0 | Batch 2060/2891 | Timestep 2060 | LR 0.0000100000 | Loss 0.056852 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:52 Epoch 0 | Batch 2070/2891 | Timestep 2070 | LR 0.0000100000 | Loss 0.086574 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:53 Epoch 0 | Batch 2080/2891 | Timestep 2080 | LR 0.0000100000 | Loss 0.111362 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:55 Epoch 0 | Batch 2090/2891 | Timestep 2090 | LR 0.0000100000 | Loss 0.024738 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:57 Epoch 0 | Batch 2100/2891 | Timestep 2100 | LR 0.0000100000 | Loss 0.065134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:10:59 Epoch 0 | Batch 2110/2891 | Timestep 2110 | LR 0.0000100000 | Loss 0.090304 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:00 Epoch 0 | Batch 2120/2891 | Timestep 2120 | LR 0.0000100000 | Loss 0.073050 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:02 Epoch 0 | Batch 2130/2891 | Timestep 2130 | LR 0.0000100000 | Loss 0.041780 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:03 Epoch 0 | Batch 2140/2891 | Timestep 2140 | LR 0.0000100000 | Loss 0.058543 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:05 Epoch 0 | Batch 2150/2891 | Timestep 2150 | LR 0.0000100000 | Loss 0.106721 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:07 Epoch 0 | Batch 2160/2891 | Timestep 2160 | LR 0.0000100000 | Loss 0.041482 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:09 Epoch 0 | Batch 2170/2891 | Timestep 2170 | LR 0.0000100000 | Loss 0.055083 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:10 Epoch 0 | Batch 2180/2891 | Timestep 2180 | LR 0.0000100000 | Loss 0.037021 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:12 Epoch 0 | Batch 2190/2891 | Timestep 2190 | LR 0.0000100000 | Loss 0.065379 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:14 Epoch 0 | Batch 2200/2891 | Timestep 2200 | LR 0.0000100000 | Loss 0.120449 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:15 Epoch 0 | Batch 2210/2891 | Timestep 2210 | LR 0.0000100000 | Loss 0.100461 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:17 Epoch 0 | Batch 2220/2891 | Timestep 2220 | LR 0.0000100000 | Loss 0.095903 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:19 Epoch 0 | Batch 2230/2891 | Timestep 2230 | LR 0.0000100000 | Loss 0.024430 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:21 Epoch 0 | Batch 2240/2891 | Timestep 2240 | LR 0.0000100000 | Loss 0.031274 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:22 Epoch 0 | Batch 2250/2891 | Timestep 2250 | LR 0.0000100000 | Loss 0.093718 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:24 Epoch 0 | Batch 2260/2891 | Timestep 2260 | LR 0.0000100000 | Loss 0.103833 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:25 Epoch 0 | Batch 2270/2891 | Timestep 2270 | LR 0.0000100000 | Loss 0.102133 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:27 Epoch 0 | Batch 2280/2891 | Timestep 2280 | LR 0.0000100000 | Loss 0.042873 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:28 Epoch 0 | Batch 2290/2891 | Timestep 2290 | LR 0.0000100000 | Loss 0.010205 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:30 Epoch 0 | Batch 2300/2891 | Timestep 2300 | LR 0.0000100000 | Loss 0.063982 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:31 Epoch 0 | Batch 2310/2891 | Timestep 2310 | LR 0.0000100000 | Loss 0.106870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:33 Epoch 0 | Batch 2320/2891 | Timestep 2320 | LR 0.0000100000 | Loss 0.084345 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:35 Epoch 0 | Batch 2330/2891 | Timestep 2330 | LR 0.0000100000 | Loss 0.046307 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:36 Epoch 0 | Batch 2340/2891 | Timestep 2340 | LR 0.0000100000 | Loss 0.064596 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:37 Epoch 0 | Batch 2350/2891 | Timestep 2350 | LR 0.0000100000 | Loss 0.056822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:39 Epoch 0 | Batch 2360/2891 | Timestep 2360 | LR 0.0000100000 | Loss 0.051045 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:40 Epoch 0 | Batch 2370/2891 | Timestep 2370 | LR 0.0000100000 | Loss 0.072354 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:43 Epoch 0 | Batch 2380/2891 | Timestep 2380 | LR 0.0000100000 | Loss 0.029403 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:44 Epoch 0 | Batch 2390/2891 | Timestep 2390 | LR 0.0000100000 | Loss 0.041573 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:46 Epoch 0 | Batch 2400/2891 | Timestep 2400 | LR 0.0000100000 | Loss 0.025309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:48 Epoch 0 | Batch 2410/2891 | Timestep 2410 | LR 0.0000100000 | Loss 0.049630 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:50 Epoch 0 | Batch 2420/2891 | Timestep 2420 | LR 0.0000100000 | Loss 0.012814 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:52 Epoch 0 | Batch 2430/2891 | Timestep 2430 | LR 0.0000100000 | Loss 0.056403 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:54 Epoch 0 | Batch 2440/2891 | Timestep 2440 | LR 0.0000100000 | Loss 0.035599 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:56 Epoch 0 | Batch 2450/2891 | Timestep 2450 | LR 0.0000100000 | Loss 0.036358 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:57 Epoch 0 | Batch 2460/2891 | Timestep 2460 | LR 0.0000100000 | Loss 0.049590 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:11:59 Epoch 0 | Batch 2470/2891 | Timestep 2470 | LR 0.0000100000 | Loss 0.052084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:00 Epoch 0 | Batch 2480/2891 | Timestep 2480 | LR 0.0000100000 | Loss 0.159574 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:02 Epoch 0 | Batch 2490/2891 | Timestep 2490 | LR 0.0000100000 | Loss 0.039765 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:04 Epoch 0 | Batch 2500/2891 | Timestep 2500 | LR 0.0000100000 | Loss 0.113804 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:05 Epoch 0 | Batch 2510/2891 | Timestep 2510 | LR 0.0000100000 | Loss 0.069425 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:07 Epoch 0 | Batch 2520/2891 | Timestep 2520 | LR 0.0000100000 | Loss 0.041828 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:08 Epoch 0 | Batch 2530/2891 | Timestep 2530 | LR 0.0000100000 | Loss 0.065913 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:10 Epoch 0 | Batch 2540/2891 | Timestep 2540 | LR 0.0000100000 | Loss 0.044034 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:11 Epoch 0 | Batch 2550/2891 | Timestep 2550 | LR 0.0000100000 | Loss 0.024255 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:13 Epoch 0 | Batch 2560/2891 | Timestep 2560 | LR 0.0000100000 | Loss 0.033266 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:14 Epoch 0 | Batch 2570/2891 | Timestep 2570 | LR 0.0000100000 | Loss 0.072450 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:16 Epoch 0 | Batch 2580/2891 | Timestep 2580 | LR 0.0000100000 | Loss 0.066311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:18 Epoch 0 | Batch 2590/2891 | Timestep 2590 | LR 0.0000100000 | Loss 0.029023 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:19 Epoch 0 | Batch 2600/2891 | Timestep 2600 | LR 0.0000100000 | Loss 0.060315 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:21 Epoch 0 | Batch 2610/2891 | Timestep 2610 | LR 0.0000100000 | Loss 0.115692 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:24 Epoch 0 | Batch 2620/2891 | Timestep 2620 | LR 0.0000100000 | Loss 0.023126 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:25 Epoch 0 | Batch 2630/2891 | Timestep 2630 | LR 0.0000100000 | Loss 0.035032 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:27 Epoch 0 | Batch 2640/2891 | Timestep 2640 | LR 0.0000100000 | Loss 0.058549 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:29 Epoch 0 | Batch 2650/2891 | Timestep 2650 | LR 0.0000100000 | Loss 0.065725 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:30 Epoch 0 | Batch 2660/2891 | Timestep 2660 | LR 0.0000100000 | Loss 0.054394 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:32 Epoch 0 | Batch 2670/2891 | Timestep 2670 | LR 0.0000100000 | Loss 0.046271 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:34 Epoch 0 | Batch 2680/2891 | Timestep 2680 | LR 0.0000100000 | Loss 0.076627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:36 Epoch 0 | Batch 2690/2891 | Timestep 2690 | LR 0.0000100000 | Loss 0.035933 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:37 Epoch 0 | Batch 2700/2891 | Timestep 2700 | LR 0.0000100000 | Loss 0.046500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:39 Epoch 0 | Batch 2710/2891 | Timestep 2710 | LR 0.0000100000 | Loss 0.075187 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:41 Epoch 0 | Batch 2720/2891 | Timestep 2720 | LR 0.0000100000 | Loss 0.089574 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:42 Epoch 0 | Batch 2730/2891 | Timestep 2730 | LR 0.0000100000 | Loss 0.122791 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:44 Epoch 0 | Batch 2740/2891 | Timestep 2740 | LR 0.0000100000 | Loss 0.022900 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:45 Epoch 0 | Batch 2750/2891 | Timestep 2750 | LR 0.0000100000 | Loss 0.028421 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:48 Epoch 0 | Batch 2760/2891 | Timestep 2760 | LR 0.0000100000 | Loss 0.021831 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:49 Epoch 0 | Batch 2770/2891 | Timestep 2770 | LR 0.0000100000 | Loss 0.224735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:51 Epoch 0 | Batch 2780/2891 | Timestep 2780 | LR 0.0000100000 | Loss 0.038382 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:52 Epoch 0 | Batch 2790/2891 | Timestep 2790 | LR 0.0000100000 | Loss 0.050125 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:54 Epoch 0 | Batch 2800/2891 | Timestep 2800 | LR 0.0000100000 | Loss 0.042013 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:56 Epoch 0 | Batch 2810/2891 | Timestep 2810 | LR 0.0000100000 | Loss 0.091747 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:57 Epoch 0 | Batch 2820/2891 | Timestep 2820 | LR 0.0000100000 | Loss 0.117390 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:12:59 Epoch 0 | Batch 2830/2891 | Timestep 2830 | LR 0.0000100000 | Loss 0.116276 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:01 Epoch 0 | Batch 2840/2891 | Timestep 2840 | LR 0.0000100000 | Loss 0.034872 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:03 Epoch 0 | Batch 2850/2891 | Timestep 2850 | LR 0.0000100000 | Loss 0.045876 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:04 Epoch 0 | Batch 2860/2891 | Timestep 2860 | LR 0.0000100000 | Loss 0.099194 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:06 Epoch 0 | Batch 2870/2891 | Timestep 2870 | LR 0.0000100000 | Loss 0.073135 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:07 Epoch 0 | Batch 2880/2891 | Timestep 2880 | LR 0.0000100000 | Loss 0.051502 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:09 Epoch 0 | Batch 2890/2891 | Timestep 2890 | LR 0.0000100000 | Loss 0.057918 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:09 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:13:26 precision recall f1-score support CARDINAL 0.6687 0.6529 0.6607 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.8767 0.9114 0.8937 1592 EVENT 0.5655 0.6738 0.6149 282 FAC 0.4366 0.6739 0.5299 92 GPE 0.8098 0.8991 0.8521 1051 LANGUAGE 0.0000 0.0000 0.0000 16 LAW 0.5800 0.6170 0.5979 47 LOC 0.3830 0.2432 0.2975 74 MONEY 0.2812 0.4091 0.3333 22 NORP 0.5863 0.5551 0.5703 508 OCC 0.8083 0.7957 0.8020 514 ORDINAL 0.8337 0.8562 0.8448 445 ORG 0.8497 0.8631 0.8563 1578 PERCENT 0.0000 0.0000 0.0000 12 PERS 0.9071 0.9396 0.9231 613 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.0000 0.0000 0.0000 3 TIME 0.0000 0.0000 0.0000 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.4898 0.3000 0.3721 80 micro avg 0.7982 0.8188 0.8084 7143 macro avg 0.4322 0.4472 0.4357 7143 weighted avg 0.7899 0.8188 0.8029 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:26 Epoch 0 | Timestep 2891 | Train Loss 0.139515 | Val Loss 0.059531 | F1 0.808375 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:13:26 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 14 May 2026 11:13:44 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, 14 May 2026 11:13:58 Predictions written to /content/Wojood/predictions.txt INFO root Thu, 14 May 2026 11:14:00 precision recall f1-score support CARDINAL 0.6833 0.7214 0.7019 341 CURR 0.0000 0.0000 0.0000 8 DATE 0.8806 0.9306 0.9049 3028 EVENT 0.5674 0.6891 0.6223 550 FAC 0.4604 0.6465 0.5378 198 GPE 0.8015 0.8957 0.8460 2254 LANGUAGE 0.0000 0.0000 0.0000 44 LAW 0.5938 0.6333 0.6129 90 LOC 0.4043 0.2159 0.2815 176 MONEY 0.2381 0.4545 0.3125 33 NORP 0.6222 0.5767 0.5986 1011 OCC 0.8086 0.7745 0.7912 1091 ORDINAL 0.8280 0.8661 0.8466 889 ORG 0.8556 0.8545 0.8550 3182 PERCENT 0.0000 0.0000 0.0000 33 PERS 0.8909 0.9199 0.9052 1411 PRODUCT 0.0000 0.0000 0.0000 17 QUANTITY 0.0000 0.0000 0.0000 9 TIME 0.0000 0.0000 0.0000 84 UNIT 0.0000 0.0000 0.0000 2 WEBSITE 0.3846 0.2586 0.3093 116 micro avg 0.8013 0.8200 0.8105 14567 macro avg 0.4295 0.4494 0.4346 14567 weighted avg 0.7904 0.8200 0.8035 14567 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:01 Epoch 0 | Timestep 2891 | Test Loss 0.062910 | F1 0.810545 INFO arabiner.trainers.BaseTrainer Thu, 14 May 2026 11:14:01 Saving checkpoint to /content/Wojood/checkpoints/checkpoint_0.pt INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:13 Epoch 1 | Batch 9/2891 | Timestep 2900 | LR 0.0000100000 | Loss 0.085988 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:15 Epoch 1 | Batch 19/2891 | Timestep 2910 | LR 0.0000100000 | Loss 0.070590 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:16 Epoch 1 | Batch 29/2891 | Timestep 2920 | LR 0.0000100000 | Loss 0.009482 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:19 Epoch 1 | Batch 39/2891 | Timestep 2930 | LR 0.0000100000 | Loss 0.062373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:20 Epoch 1 | Batch 49/2891 | Timestep 2940 | LR 0.0000100000 | Loss 0.027805 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:22 Epoch 1 | Batch 59/2891 | Timestep 2950 | LR 0.0000100000 | Loss 0.039979 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:24 Epoch 1 | Batch 69/2891 | Timestep 2960 | LR 0.0000100000 | Loss 0.042819 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:25 Epoch 1 | Batch 79/2891 | Timestep 2970 | LR 0.0000100000 | Loss 0.052615 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:27 Epoch 1 | Batch 89/2891 | Timestep 2980 | LR 0.0000100000 | Loss 0.055231 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:29 Epoch 1 | Batch 99/2891 | Timestep 2990 | LR 0.0000100000 | Loss 0.053582 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:31 Epoch 1 | Batch 109/2891 | Timestep 3000 | LR 0.0000100000 | Loss 0.052597 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:32 Epoch 1 | Batch 119/2891 | Timestep 3010 | LR 0.0000100000 | Loss 0.057910 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:34 Epoch 1 | Batch 129/2891 | Timestep 3020 | LR 0.0000100000 | Loss 0.131076 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:36 Epoch 1 | Batch 139/2891 | Timestep 3030 | LR 0.0000100000 | Loss 0.081900 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:38 Epoch 1 | Batch 149/2891 | Timestep 3040 | LR 0.0000100000 | Loss 0.020071 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:39 Epoch 1 | Batch 159/2891 | Timestep 3050 | LR 0.0000100000 | Loss 0.052607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:41 Epoch 1 | Batch 169/2891 | Timestep 3060 | LR 0.0000100000 | Loss 0.062031 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:42 Epoch 1 | Batch 179/2891 | Timestep 3070 | LR 0.0000100000 | Loss 0.108479 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:44 Epoch 1 | Batch 189/2891 | Timestep 3080 | LR 0.0000100000 | Loss 0.128752 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:46 Epoch 1 | Batch 199/2891 | Timestep 3090 | LR 0.0000100000 | Loss 0.026824 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:48 Epoch 1 | Batch 209/2891 | Timestep 3100 | LR 0.0000100000 | Loss 0.098518 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:50 Epoch 1 | Batch 219/2891 | Timestep 3110 | LR 0.0000100000 | Loss 0.052072 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:52 Epoch 1 | Batch 229/2891 | Timestep 3120 | LR 0.0000100000 | Loss 0.110353 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:55 Epoch 1 | Batch 239/2891 | Timestep 3130 | LR 0.0000100000 | Loss 0.045553 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:56 Epoch 1 | Batch 249/2891 | Timestep 3140 | LR 0.0000100000 | Loss 0.080020 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:58 Epoch 1 | Batch 259/2891 | Timestep 3150 | LR 0.0000100000 | Loss 0.024744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:14:59 Epoch 1 | Batch 269/2891 | Timestep 3160 | LR 0.0000100000 | Loss 0.036180 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:01 Epoch 1 | Batch 279/2891 | Timestep 3170 | LR 0.0000100000 | Loss 0.068602 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:03 Epoch 1 | Batch 289/2891 | Timestep 3180 | LR 0.0000100000 | Loss 0.057120 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:05 Epoch 1 | Batch 299/2891 | Timestep 3190 | LR 0.0000100000 | Loss 0.117499 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:07 Epoch 1 | Batch 309/2891 | Timestep 3200 | LR 0.0000100000 | Loss 0.025323 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:08 Epoch 1 | Batch 319/2891 | Timestep 3210 | LR 0.0000100000 | Loss 0.037517 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:10 Epoch 1 | Batch 329/2891 | Timestep 3220 | LR 0.0000100000 | Loss 0.023134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:11 Epoch 1 | Batch 339/2891 | Timestep 3230 | LR 0.0000100000 | Loss 0.088458 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:13 Epoch 1 | Batch 349/2891 | Timestep 3240 | LR 0.0000100000 | Loss 0.066165 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:14 Epoch 1 | Batch 359/2891 | Timestep 3250 | LR 0.0000100000 | Loss 0.049990 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:16 Epoch 1 | Batch 369/2891 | Timestep 3260 | LR 0.0000100000 | Loss 0.051012 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:18 Epoch 1 | Batch 379/2891 | Timestep 3270 | LR 0.0000100000 | Loss 0.019658 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:19 Epoch 1 | Batch 389/2891 | Timestep 3280 | LR 0.0000100000 | Loss 0.097040 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:21 Epoch 1 | Batch 399/2891 | Timestep 3290 | LR 0.0000100000 | Loss 0.032496 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:23 Epoch 1 | Batch 409/2891 | Timestep 3300 | LR 0.0000100000 | Loss 0.030137 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:24 Epoch 1 | Batch 419/2891 | Timestep 3310 | LR 0.0000100000 | Loss 0.017560 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:26 Epoch 1 | Batch 429/2891 | Timestep 3320 | LR 0.0000100000 | Loss 0.059771 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:28 Epoch 1 | Batch 439/2891 | Timestep 3330 | LR 0.0000100000 | Loss 0.014743 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:29 Epoch 1 | Batch 449/2891 | Timestep 3340 | LR 0.0000100000 | Loss 0.027231 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:31 Epoch 1 | Batch 459/2891 | Timestep 3350 | LR 0.0000100000 | Loss 0.046157 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:33 Epoch 1 | Batch 469/2891 | Timestep 3360 | LR 0.0000100000 | Loss 0.064179 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:35 Epoch 1 | Batch 479/2891 | Timestep 3370 | LR 0.0000100000 | Loss 0.014556 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:36 Epoch 1 | Batch 489/2891 | Timestep 3380 | LR 0.0000100000 | Loss 0.050403 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:38 Epoch 1 | Batch 499/2891 | Timestep 3390 | LR 0.0000100000 | Loss 0.044151 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:40 Epoch 1 | Batch 509/2891 | Timestep 3400 | LR 0.0000100000 | Loss 0.083148 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:42 Epoch 1 | Batch 519/2891 | Timestep 3410 | LR 0.0000100000 | Loss 0.043500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:44 Epoch 1 | Batch 529/2891 | Timestep 3420 | LR 0.0000100000 | Loss 0.050474 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:45 Epoch 1 | Batch 539/2891 | Timestep 3430 | LR 0.0000100000 | Loss 0.026391 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:47 Epoch 1 | Batch 549/2891 | Timestep 3440 | LR 0.0000100000 | Loss 0.014053 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:49 Epoch 1 | Batch 559/2891 | Timestep 3450 | LR 0.0000100000 | Loss 0.033117 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:50 Epoch 1 | Batch 569/2891 | Timestep 3460 | LR 0.0000100000 | Loss 0.045344 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:52 Epoch 1 | Batch 579/2891 | Timestep 3470 | LR 0.0000100000 | Loss 0.076757 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:54 Epoch 1 | Batch 589/2891 | Timestep 3480 | LR 0.0000100000 | Loss 0.023449 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:56 Epoch 1 | Batch 599/2891 | Timestep 3490 | LR 0.0000100000 | Loss 0.016402 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:57 Epoch 1 | Batch 609/2891 | Timestep 3500 | LR 0.0000100000 | Loss 0.080605 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:15:59 Epoch 1 | Batch 619/2891 | Timestep 3510 | LR 0.0000100000 | Loss 0.014143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:01 Epoch 1 | Batch 629/2891 | Timestep 3520 | LR 0.0000100000 | Loss 0.021813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:02 Epoch 1 | Batch 639/2891 | Timestep 3530 | LR 0.0000100000 | Loss 0.085544 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:04 Epoch 1 | Batch 649/2891 | Timestep 3540 | LR 0.0000100000 | Loss 0.043028 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:06 Epoch 1 | Batch 659/2891 | Timestep 3550 | LR 0.0000100000 | Loss 0.029808 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:07 Epoch 1 | Batch 669/2891 | Timestep 3560 | LR 0.0000100000 | Loss 0.053997 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:09 Epoch 1 | Batch 679/2891 | Timestep 3570 | LR 0.0000100000 | Loss 0.018461 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:11 Epoch 1 | Batch 689/2891 | Timestep 3580 | LR 0.0000100000 | Loss 0.044684 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:12 Epoch 1 | Batch 699/2891 | Timestep 3590 | LR 0.0000100000 | Loss 0.091129 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:13 Epoch 1 | Batch 709/2891 | Timestep 3600 | LR 0.0000100000 | Loss 0.062903 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:15 Epoch 1 | Batch 719/2891 | Timestep 3610 | LR 0.0000100000 | Loss 0.052198 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:17 Epoch 1 | Batch 729/2891 | Timestep 3620 | LR 0.0000100000 | Loss 0.018338 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:19 Epoch 1 | Batch 739/2891 | Timestep 3630 | LR 0.0000100000 | Loss 0.129300 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:21 Epoch 1 | Batch 749/2891 | Timestep 3640 | LR 0.0000100000 | Loss 0.021366 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:23 Epoch 1 | Batch 759/2891 | Timestep 3650 | LR 0.0000100000 | Loss 0.019622 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:24 Epoch 1 | Batch 769/2891 | Timestep 3660 | LR 0.0000100000 | Loss 0.042027 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:26 Epoch 1 | Batch 779/2891 | Timestep 3670 | LR 0.0000100000 | Loss 0.054053 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:28 Epoch 1 | Batch 789/2891 | Timestep 3680 | LR 0.0000100000 | Loss 0.041986 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:30 Epoch 1 | Batch 799/2891 | Timestep 3690 | LR 0.0000100000 | Loss 0.038463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:32 Epoch 1 | Batch 809/2891 | Timestep 3700 | LR 0.0000100000 | Loss 0.061648 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:33 Epoch 1 | Batch 819/2891 | Timestep 3710 | LR 0.0000100000 | Loss 0.025274 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:36 Epoch 1 | Batch 829/2891 | Timestep 3720 | LR 0.0000100000 | Loss 0.149577 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:37 Epoch 1 | Batch 839/2891 | Timestep 3730 | LR 0.0000100000 | Loss 0.011839 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:38 Epoch 1 | Batch 849/2891 | Timestep 3740 | LR 0.0000100000 | Loss 0.021222 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:40 Epoch 1 | Batch 859/2891 | Timestep 3750 | LR 0.0000100000 | Loss 0.020202 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:42 Epoch 1 | Batch 869/2891 | Timestep 3760 | LR 0.0000100000 | Loss 0.035370 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:44 Epoch 1 | Batch 879/2891 | Timestep 3770 | LR 0.0000100000 | Loss 0.073219 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:46 Epoch 1 | Batch 889/2891 | Timestep 3780 | LR 0.0000100000 | Loss 0.030737 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:48 Epoch 1 | Batch 899/2891 | Timestep 3790 | LR 0.0000100000 | Loss 0.040769 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:50 Epoch 1 | Batch 909/2891 | Timestep 3800 | LR 0.0000100000 | Loss 0.069255 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:52 Epoch 1 | Batch 919/2891 | Timestep 3810 | LR 0.0000100000 | Loss 0.017657 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:53 Epoch 1 | Batch 929/2891 | Timestep 3820 | LR 0.0000100000 | Loss 0.049275 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:55 Epoch 1 | Batch 939/2891 | Timestep 3830 | LR 0.0000100000 | Loss 0.038141 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:56 Epoch 1 | Batch 949/2891 | Timestep 3840 | LR 0.0000100000 | Loss 0.009154 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:16:58 Epoch 1 | Batch 959/2891 | Timestep 3850 | LR 0.0000100000 | Loss 0.019775 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:00 Epoch 1 | Batch 969/2891 | Timestep 3860 | LR 0.0000100000 | Loss 0.037170 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:02 Epoch 1 | Batch 979/2891 | Timestep 3870 | LR 0.0000100000 | Loss 0.010173 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:03 Epoch 1 | Batch 989/2891 | Timestep 3880 | LR 0.0000100000 | Loss 0.054796 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:05 Epoch 1 | Batch 999/2891 | Timestep 3890 | LR 0.0000100000 | Loss 0.087111 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:07 Epoch 1 | Batch 1009/2891 | Timestep 3900 | LR 0.0000100000 | Loss 0.005140 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:08 Epoch 1 | Batch 1019/2891 | Timestep 3910 | LR 0.0000100000 | Loss 0.050905 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:10 Epoch 1 | Batch 1029/2891 | Timestep 3920 | LR 0.0000100000 | Loss 0.044252 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:11 Epoch 1 | Batch 1039/2891 | Timestep 3930 | LR 0.0000100000 | Loss 0.017641 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:13 Epoch 1 | Batch 1049/2891 | Timestep 3940 | LR 0.0000100000 | Loss 0.030723 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:15 Epoch 1 | Batch 1059/2891 | Timestep 3950 | LR 0.0000100000 | Loss 0.035192 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:16 Epoch 1 | Batch 1069/2891 | Timestep 3960 | LR 0.0000100000 | Loss 0.031581 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:18 Epoch 1 | Batch 1079/2891 | Timestep 3970 | LR 0.0000100000 | Loss 0.168259 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:20 Epoch 1 | Batch 1089/2891 | Timestep 3980 | LR 0.0000100000 | Loss 0.091665 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:21 Epoch 1 | Batch 1099/2891 | Timestep 3990 | LR 0.0000100000 | Loss 0.017646 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:23 Epoch 1 | Batch 1109/2891 | Timestep 4000 | LR 0.0000100000 | Loss 0.014258 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:24 Epoch 1 | Batch 1119/2891 | Timestep 4010 | LR 0.0000100000 | Loss 0.039363 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:26 Epoch 1 | Batch 1129/2891 | Timestep 4020 | LR 0.0000100000 | Loss 0.044748 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:27 Epoch 1 | Batch 1139/2891 | Timestep 4030 | LR 0.0000100000 | Loss 0.039223 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:28 Epoch 1 | Batch 1149/2891 | Timestep 4040 | LR 0.0000100000 | Loss 0.041987 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:30 Epoch 1 | Batch 1159/2891 | Timestep 4050 | LR 0.0000100000 | Loss 0.035276 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:32 Epoch 1 | Batch 1169/2891 | Timestep 4060 | LR 0.0000100000 | Loss 0.052884 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:34 Epoch 1 | Batch 1179/2891 | Timestep 4070 | LR 0.0000100000 | Loss 0.014562 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:35 Epoch 1 | Batch 1189/2891 | Timestep 4080 | LR 0.0000100000 | Loss 0.011690 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:37 Epoch 1 | Batch 1199/2891 | Timestep 4090 | LR 0.0000100000 | Loss 0.039345 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:39 Epoch 1 | Batch 1209/2891 | Timestep 4100 | LR 0.0000100000 | Loss 0.023941 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:41 Epoch 1 | Batch 1219/2891 | Timestep 4110 | LR 0.0000100000 | Loss 0.030782 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:43 Epoch 1 | Batch 1229/2891 | Timestep 4120 | LR 0.0000100000 | Loss 0.026264 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:44 Epoch 1 | Batch 1239/2891 | Timestep 4130 | LR 0.0000100000 | Loss 0.046999 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:46 Epoch 1 | Batch 1249/2891 | Timestep 4140 | LR 0.0000100000 | Loss 0.032607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:48 Epoch 1 | Batch 1259/2891 | Timestep 4150 | LR 0.0000100000 | Loss 0.076682 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:50 Epoch 1 | Batch 1269/2891 | Timestep 4160 | LR 0.0000100000 | Loss 0.025449 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:51 Epoch 1 | Batch 1279/2891 | Timestep 4170 | LR 0.0000100000 | Loss 0.111719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:53 Epoch 1 | Batch 1289/2891 | Timestep 4180 | LR 0.0000100000 | Loss 0.022218 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:54 Epoch 1 | Batch 1299/2891 | Timestep 4190 | LR 0.0000100000 | Loss 0.075241 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:56 Epoch 1 | Batch 1309/2891 | Timestep 4200 | LR 0.0000100000 | Loss 0.017833 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:58 Epoch 1 | Batch 1319/2891 | Timestep 4210 | LR 0.0000100000 | Loss 0.056434 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:17:59 Epoch 1 | Batch 1329/2891 | Timestep 4220 | LR 0.0000100000 | Loss 0.019114 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:01 Epoch 1 | Batch 1339/2891 | Timestep 4230 | LR 0.0000100000 | Loss 0.048177 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:03 Epoch 1 | Batch 1349/2891 | Timestep 4240 | LR 0.0000100000 | Loss 0.024247 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:05 Epoch 1 | Batch 1359/2891 | Timestep 4250 | LR 0.0000100000 | Loss 0.074641 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:06 Epoch 1 | Batch 1369/2891 | Timestep 4260 | LR 0.0000100000 | Loss 0.010493 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:08 Epoch 1 | Batch 1379/2891 | Timestep 4270 | LR 0.0000100000 | Loss 0.043765 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:10 Epoch 1 | Batch 1389/2891 | Timestep 4280 | LR 0.0000100000 | Loss 0.032666 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:12 Epoch 1 | Batch 1399/2891 | Timestep 4290 | LR 0.0000100000 | Loss 0.020858 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:13 Epoch 1 | Batch 1409/2891 | Timestep 4300 | LR 0.0000100000 | Loss 0.021372 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:15 Epoch 1 | Batch 1419/2891 | Timestep 4310 | LR 0.0000100000 | Loss 0.022038 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:17 Epoch 1 | Batch 1429/2891 | Timestep 4320 | LR 0.0000100000 | Loss 0.034047 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:19 Epoch 1 | Batch 1439/2891 | Timestep 4330 | LR 0.0000100000 | Loss 0.027379 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:20 Epoch 1 | Batch 1449/2891 | Timestep 4340 | LR 0.0000100000 | Loss 0.076425 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:22 Epoch 1 | Batch 1459/2891 | Timestep 4350 | LR 0.0000100000 | Loss 0.091185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:24 Epoch 1 | Batch 1469/2891 | Timestep 4360 | LR 0.0000100000 | Loss 0.012855 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:25 Epoch 1 | Batch 1479/2891 | Timestep 4370 | LR 0.0000100000 | Loss 0.036299 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:27 Epoch 1 | Batch 1489/2891 | Timestep 4380 | LR 0.0000100000 | Loss 0.034843 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:29 Epoch 1 | Batch 1499/2891 | Timestep 4390 | LR 0.0000100000 | Loss 0.021826 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:30 Epoch 1 | Batch 1509/2891 | Timestep 4400 | LR 0.0000100000 | Loss 0.003495 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:32 Epoch 1 | Batch 1519/2891 | Timestep 4410 | LR 0.0000100000 | Loss 0.151429 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:34 Epoch 1 | Batch 1529/2891 | Timestep 4420 | LR 0.0000100000 | Loss 0.014774 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:35 Epoch 1 | Batch 1539/2891 | Timestep 4430 | LR 0.0000100000 | Loss 0.127211 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:37 Epoch 1 | Batch 1549/2891 | Timestep 4440 | LR 0.0000100000 | Loss 0.018203 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:38 Epoch 1 | Batch 1559/2891 | Timestep 4450 | LR 0.0000100000 | Loss 0.030260 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:40 Epoch 1 | Batch 1569/2891 | Timestep 4460 | LR 0.0000100000 | Loss 0.029078 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:42 Epoch 1 | Batch 1579/2891 | Timestep 4470 | LR 0.0000100000 | Loss 0.018509 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:43 Epoch 1 | Batch 1589/2891 | Timestep 4480 | LR 0.0000100000 | Loss 0.023367 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:45 Epoch 1 | Batch 1599/2891 | Timestep 4490 | LR 0.0000100000 | Loss 0.028607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:46 Epoch 1 | Batch 1609/2891 | Timestep 4500 | LR 0.0000100000 | Loss 0.080528 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:48 Epoch 1 | Batch 1619/2891 | Timestep 4510 | LR 0.0000100000 | Loss 0.036201 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:49 Epoch 1 | Batch 1629/2891 | Timestep 4520 | LR 0.0000100000 | Loss 0.021607 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:52 Epoch 1 | Batch 1639/2891 | Timestep 4530 | LR 0.0000100000 | Loss 0.034993 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:54 Epoch 1 | Batch 1649/2891 | Timestep 4540 | LR 0.0000100000 | Loss 0.025393 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:55 Epoch 1 | Batch 1659/2891 | Timestep 4550 | LR 0.0000100000 | Loss 0.019237 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:18:57 Epoch 1 | Batch 1669/2891 | Timestep 4560 | LR 0.0000100000 | Loss 0.015571 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:00 Epoch 1 | Batch 1679/2891 | Timestep 4570 | LR 0.0000100000 | Loss 0.036700 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:01 Epoch 1 | Batch 1689/2891 | Timestep 4580 | LR 0.0000100000 | Loss 0.018382 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:03 Epoch 1 | Batch 1699/2891 | Timestep 4590 | LR 0.0000100000 | Loss 0.040524 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:04 Epoch 1 | Batch 1709/2891 | Timestep 4600 | LR 0.0000100000 | Loss 0.036615 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:06 Epoch 1 | Batch 1719/2891 | Timestep 4610 | LR 0.0000100000 | Loss 0.015813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:07 Epoch 1 | Batch 1729/2891 | Timestep 4620 | LR 0.0000100000 | Loss 0.005400 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:09 Epoch 1 | Batch 1739/2891 | Timestep 4630 | LR 0.0000100000 | Loss 0.028850 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:11 Epoch 1 | Batch 1749/2891 | Timestep 4640 | LR 0.0000100000 | Loss 0.022886 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:12 Epoch 1 | Batch 1759/2891 | Timestep 4650 | LR 0.0000100000 | Loss 0.043392 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:14 Epoch 1 | Batch 1769/2891 | Timestep 4660 | LR 0.0000100000 | Loss 0.036481 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:16 Epoch 1 | Batch 1779/2891 | Timestep 4670 | LR 0.0000100000 | Loss 0.027642 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:18 Epoch 1 | Batch 1789/2891 | Timestep 4680 | LR 0.0000100000 | Loss 0.012838 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:19 Epoch 1 | Batch 1799/2891 | Timestep 4690 | LR 0.0000100000 | Loss 0.022808 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:21 Epoch 1 | Batch 1809/2891 | Timestep 4700 | LR 0.0000100000 | Loss 0.006178 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:23 Epoch 1 | Batch 1819/2891 | Timestep 4710 | LR 0.0000100000 | Loss 0.042928 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:24 Epoch 1 | Batch 1829/2891 | Timestep 4720 | LR 0.0000100000 | Loss 0.012475 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:26 Epoch 1 | Batch 1839/2891 | Timestep 4730 | LR 0.0000100000 | Loss 0.035146 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:28 Epoch 1 | Batch 1849/2891 | Timestep 4740 | LR 0.0000100000 | Loss 0.070401 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:29 Epoch 1 | Batch 1859/2891 | Timestep 4750 | LR 0.0000100000 | Loss 0.029491 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:31 Epoch 1 | Batch 1869/2891 | Timestep 4760 | LR 0.0000100000 | Loss 0.010939 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:32 Epoch 1 | Batch 1879/2891 | Timestep 4770 | LR 0.0000100000 | Loss 0.031361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:34 Epoch 1 | Batch 1889/2891 | Timestep 4780 | LR 0.0000100000 | Loss 0.044763 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:35 Epoch 1 | Batch 1899/2891 | Timestep 4790 | LR 0.0000100000 | Loss 0.073494 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:37 Epoch 1 | Batch 1909/2891 | Timestep 4800 | LR 0.0000100000 | Loss 0.029712 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:38 Epoch 1 | Batch 1919/2891 | Timestep 4810 | LR 0.0000100000 | Loss 0.007421 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:40 Epoch 1 | Batch 1929/2891 | Timestep 4820 | LR 0.0000100000 | Loss 0.037597 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:42 Epoch 1 | Batch 1939/2891 | Timestep 4830 | LR 0.0000100000 | Loss 0.045057 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:43 Epoch 1 | Batch 1949/2891 | Timestep 4840 | LR 0.0000100000 | Loss 0.032426 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:45 Epoch 1 | Batch 1959/2891 | Timestep 4850 | LR 0.0000100000 | Loss 0.030504 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:46 Epoch 1 | Batch 1969/2891 | Timestep 4860 | LR 0.0000100000 | Loss 0.045024 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:48 Epoch 1 | Batch 1979/2891 | Timestep 4870 | LR 0.0000100000 | Loss 0.068116 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:50 Epoch 1 | Batch 1989/2891 | Timestep 4880 | LR 0.0000100000 | Loss 0.011537 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:51 Epoch 1 | Batch 1999/2891 | Timestep 4890 | LR 0.0000100000 | Loss 0.030675 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:53 Epoch 1 | Batch 2009/2891 | Timestep 4900 | LR 0.0000100000 | Loss 0.028545 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:54 Epoch 1 | Batch 2019/2891 | Timestep 4910 | LR 0.0000100000 | Loss 0.009644 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:56 Epoch 1 | Batch 2029/2891 | Timestep 4920 | LR 0.0000100000 | Loss 0.070988 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:57 Epoch 1 | Batch 2039/2891 | Timestep 4930 | LR 0.0000100000 | Loss 0.007668 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:19:59 Epoch 1 | Batch 2049/2891 | Timestep 4940 | LR 0.0000100000 | Loss 0.012718 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:01 Epoch 1 | Batch 2059/2891 | Timestep 4950 | LR 0.0000100000 | Loss 0.032546 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:03 Epoch 1 | Batch 2069/2891 | Timestep 4960 | LR 0.0000100000 | Loss 0.043241 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:04 Epoch 1 | Batch 2079/2891 | Timestep 4970 | LR 0.0000100000 | Loss 0.066216 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:06 Epoch 1 | Batch 2089/2891 | Timestep 4980 | LR 0.0000100000 | Loss 0.007685 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:08 Epoch 1 | Batch 2099/2891 | Timestep 4990 | LR 0.0000100000 | Loss 0.009732 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:09 Epoch 1 | Batch 2109/2891 | Timestep 5000 | LR 0.0000100000 | Loss 0.061151 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:11 Epoch 1 | Batch 2119/2891 | Timestep 5010 | LR 0.0000100000 | Loss 0.016845 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:13 Epoch 1 | Batch 2129/2891 | Timestep 5020 | LR 0.0000100000 | Loss 0.022166 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:16 Epoch 1 | Batch 2139/2891 | Timestep 5030 | LR 0.0000100000 | Loss 0.049750 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:17 Epoch 1 | Batch 2149/2891 | Timestep 5040 | LR 0.0000100000 | Loss 0.005883 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:19 Epoch 1 | Batch 2159/2891 | Timestep 5050 | LR 0.0000100000 | Loss 0.049131 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:20 Epoch 1 | Batch 2169/2891 | Timestep 5060 | LR 0.0000100000 | Loss 0.027144 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:22 Epoch 1 | Batch 2179/2891 | Timestep 5070 | LR 0.0000100000 | Loss 0.089298 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:24 Epoch 1 | Batch 2189/2891 | Timestep 5080 | LR 0.0000100000 | Loss 0.020661 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:26 Epoch 1 | Batch 2199/2891 | Timestep 5090 | LR 0.0000100000 | Loss 0.009714 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:27 Epoch 1 | Batch 2209/2891 | Timestep 5100 | LR 0.0000100000 | Loss 0.053550 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:29 Epoch 1 | Batch 2219/2891 | Timestep 5110 | LR 0.0000100000 | Loss 0.024286 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:31 Epoch 1 | Batch 2229/2891 | Timestep 5120 | LR 0.0000100000 | Loss 0.008441 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:33 Epoch 1 | Batch 2239/2891 | Timestep 5130 | LR 0.0000100000 | Loss 0.011281 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:34 Epoch 1 | Batch 2249/2891 | Timestep 5140 | LR 0.0000100000 | Loss 0.012536 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:36 Epoch 1 | Batch 2259/2891 | Timestep 5150 | LR 0.0000100000 | Loss 0.077472 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:38 Epoch 1 | Batch 2269/2891 | Timestep 5160 | LR 0.0000100000 | Loss 0.022599 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:39 Epoch 1 | Batch 2279/2891 | Timestep 5170 | LR 0.0000100000 | Loss 0.021462 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:42 Epoch 1 | Batch 2289/2891 | Timestep 5180 | LR 0.0000100000 | Loss 0.044454 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:43 Epoch 1 | Batch 2299/2891 | Timestep 5190 | LR 0.0000100000 | Loss 0.086869 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:45 Epoch 1 | Batch 2309/2891 | Timestep 5200 | LR 0.0000100000 | Loss 0.056931 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:46 Epoch 1 | Batch 2319/2891 | Timestep 5210 | LR 0.0000100000 | Loss 0.048191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:48 Epoch 1 | Batch 2329/2891 | Timestep 5220 | LR 0.0000100000 | Loss 0.018131 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:50 Epoch 1 | Batch 2339/2891 | Timestep 5230 | LR 0.0000100000 | Loss 0.032670 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:52 Epoch 1 | Batch 2349/2891 | Timestep 5240 | LR 0.0000100000 | Loss 0.051778 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:53 Epoch 1 | Batch 2359/2891 | Timestep 5250 | LR 0.0000100000 | Loss 0.028844 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:55 Epoch 1 | Batch 2369/2891 | Timestep 5260 | LR 0.0000100000 | Loss 0.018828 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:57 Epoch 1 | Batch 2379/2891 | Timestep 5270 | LR 0.0000100000 | Loss 0.056515 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:20:58 Epoch 1 | Batch 2389/2891 | Timestep 5280 | LR 0.0000100000 | Loss 0.050084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:00 Epoch 1 | Batch 2399/2891 | Timestep 5290 | LR 0.0000100000 | Loss 0.025543 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:02 Epoch 1 | Batch 2409/2891 | Timestep 5300 | LR 0.0000100000 | Loss 0.038440 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:04 Epoch 1 | Batch 2419/2891 | Timestep 5310 | LR 0.0000100000 | Loss 0.051145 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:05 Epoch 1 | Batch 2429/2891 | Timestep 5320 | LR 0.0000100000 | Loss 0.021570 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:07 Epoch 1 | Batch 2439/2891 | Timestep 5330 | LR 0.0000100000 | Loss 0.075696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:08 Epoch 1 | Batch 2449/2891 | Timestep 5340 | LR 0.0000100000 | Loss 0.037591 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:10 Epoch 1 | Batch 2459/2891 | Timestep 5350 | LR 0.0000100000 | Loss 0.059444 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:12 Epoch 1 | Batch 2469/2891 | Timestep 5360 | LR 0.0000100000 | Loss 0.084181 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:14 Epoch 1 | Batch 2479/2891 | Timestep 5370 | LR 0.0000100000 | Loss 0.022891 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:16 Epoch 1 | Batch 2489/2891 | Timestep 5380 | LR 0.0000100000 | Loss 0.011185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:17 Epoch 1 | Batch 2499/2891 | Timestep 5390 | LR 0.0000100000 | Loss 0.077082 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:19 Epoch 1 | Batch 2509/2891 | Timestep 5400 | LR 0.0000100000 | Loss 0.124046 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:21 Epoch 1 | Batch 2519/2891 | Timestep 5410 | LR 0.0000100000 | Loss 0.056802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:22 Epoch 1 | Batch 2529/2891 | Timestep 5420 | LR 0.0000100000 | Loss 0.074221 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:24 Epoch 1 | Batch 2539/2891 | Timestep 5430 | LR 0.0000100000 | Loss 0.008412 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:26 Epoch 1 | Batch 2549/2891 | Timestep 5440 | LR 0.0000100000 | Loss 0.014469 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:27 Epoch 1 | Batch 2559/2891 | Timestep 5450 | LR 0.0000100000 | Loss 0.015776 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:29 Epoch 1 | Batch 2569/2891 | Timestep 5460 | LR 0.0000100000 | Loss 0.057005 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:30 Epoch 1 | Batch 2579/2891 | Timestep 5470 | LR 0.0000100000 | Loss 0.024530 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:32 Epoch 1 | Batch 2589/2891 | Timestep 5480 | LR 0.0000100000 | Loss 0.030037 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:33 Epoch 1 | Batch 2599/2891 | Timestep 5490 | LR 0.0000100000 | Loss 0.057208 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:35 Epoch 1 | Batch 2609/2891 | Timestep 5500 | LR 0.0000100000 | Loss 0.031368 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:36 Epoch 1 | Batch 2619/2891 | Timestep 5510 | LR 0.0000100000 | Loss 0.026185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:38 Epoch 1 | Batch 2629/2891 | Timestep 5520 | LR 0.0000100000 | Loss 0.015361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:40 Epoch 1 | Batch 2639/2891 | Timestep 5530 | LR 0.0000100000 | Loss 0.029699 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:41 Epoch 1 | Batch 2649/2891 | Timestep 5540 | LR 0.0000100000 | Loss 0.036263 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:43 Epoch 1 | Batch 2659/2891 | Timestep 5550 | LR 0.0000100000 | Loss 0.057588 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:44 Epoch 1 | Batch 2669/2891 | Timestep 5560 | LR 0.0000100000 | Loss 0.071585 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:46 Epoch 1 | Batch 2679/2891 | Timestep 5570 | LR 0.0000100000 | Loss 0.017194 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:47 Epoch 1 | Batch 2689/2891 | Timestep 5580 | LR 0.0000100000 | Loss 0.073830 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:49 Epoch 1 | Batch 2699/2891 | Timestep 5590 | LR 0.0000100000 | Loss 0.006551 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:50 Epoch 1 | Batch 2709/2891 | Timestep 5600 | LR 0.0000100000 | Loss 0.004792 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:52 Epoch 1 | Batch 2719/2891 | Timestep 5610 | LR 0.0000100000 | Loss 0.013944 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:54 Epoch 1 | Batch 2729/2891 | Timestep 5620 | LR 0.0000100000 | Loss 0.008211 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:57 Epoch 1 | Batch 2739/2891 | Timestep 5630 | LR 0.0000100000 | Loss 0.019970 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:21:58 Epoch 1 | Batch 2749/2891 | Timestep 5640 | LR 0.0000100000 | Loss 0.018313 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:00 Epoch 1 | Batch 2759/2891 | Timestep 5650 | LR 0.0000100000 | Loss 0.035358 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:02 Epoch 1 | Batch 2769/2891 | Timestep 5660 | LR 0.0000100000 | Loss 0.025776 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:03 Epoch 1 | Batch 2779/2891 | Timestep 5670 | LR 0.0000100000 | Loss 0.005149 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:05 Epoch 1 | Batch 2789/2891 | Timestep 5680 | LR 0.0000100000 | Loss 0.039330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:07 Epoch 1 | Batch 2799/2891 | Timestep 5690 | LR 0.0000100000 | Loss 0.052815 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:08 Epoch 1 | Batch 2809/2891 | Timestep 5700 | LR 0.0000100000 | Loss 0.025324 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:09 Epoch 1 | Batch 2819/2891 | Timestep 5710 | LR 0.0000100000 | Loss 0.011378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:11 Epoch 1 | Batch 2829/2891 | Timestep 5720 | LR 0.0000100000 | Loss 0.007158 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:13 Epoch 1 | Batch 2839/2891 | Timestep 5730 | LR 0.0000100000 | Loss 0.014924 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:15 Epoch 1 | Batch 2849/2891 | Timestep 5740 | LR 0.0000100000 | Loss 0.033226 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:16 Epoch 1 | Batch 2859/2891 | Timestep 5750 | LR 0.0000100000 | Loss 0.069878 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:18 Epoch 1 | Batch 2869/2891 | Timestep 5760 | LR 0.0000100000 | Loss 0.033396 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:19 Epoch 1 | Batch 2879/2891 | Timestep 5770 | LR 0.0000100000 | Loss 0.050191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:21 Epoch 1 | Batch 2889/2891 | Timestep 5780 | LR 0.0000100000 | Loss 0.019295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:21 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:22:37 precision recall f1-score support CARDINAL 0.8600 0.7588 0.8063 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.9232 0.9359 0.9295 1592 EVENT 0.5702 0.7057 0.6307 282 FAC 0.4348 0.7609 0.5534 92 GPE 0.8467 0.9039 0.8744 1051 LANGUAGE 0.7500 0.7500 0.7500 16 LAW 0.5065 0.8298 0.6290 47 LOC 0.6515 0.5811 0.6143 74 MONEY 0.5806 0.8182 0.6792 22 NORP 0.6100 0.7205 0.6606 508 OCC 0.7960 0.8424 0.8185 514 ORDINAL 0.9426 0.8494 0.8936 445 ORG 0.8737 0.8897 0.8816 1578 PERCENT 0.7500 1.0000 0.8571 12 PERS 0.9402 0.9233 0.9317 613 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.0000 0.0000 0.0000 3 TIME 0.6000 0.4545 0.5172 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.4778 0.5375 0.5059 80 micro avg 0.8252 0.8634 0.8439 7143 macro avg 0.5768 0.6315 0.5968 7143 weighted avg 0.8349 0.8634 0.8471 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:38 Epoch 1 | Timestep 5782 | Train Loss 0.043601 | Val Loss 0.046721 | F1 0.843870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:22:38 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 14 May 2026 11:22:56 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, 14 May 2026 11:23:10 Predictions written to /content/Wojood/predictions.txt INFO root Thu, 14 May 2026 11:23:11 precision recall f1-score support CARDINAL 0.8057 0.8270 0.8162 341 CURR 0.0000 0.0000 0.0000 8 DATE 0.9334 0.9445 0.9389 3028 EVENT 0.6336 0.7545 0.6888 550 FAC 0.4248 0.6566 0.5159 198 GPE 0.8357 0.9006 0.8670 2254 LANGUAGE 0.8000 0.5455 0.6486 44 LAW 0.6179 0.8444 0.7136 90 LOC 0.7163 0.5739 0.6372 176 MONEY 0.6977 0.9091 0.7895 33 NORP 0.6362 0.7369 0.6829 1011 OCC 0.8321 0.8451 0.8386 1091 ORDINAL 0.9445 0.8616 0.9012 889 ORG 0.8718 0.8872 0.8794 3182 PERCENT 0.8065 0.7576 0.7812 33 PERS 0.9262 0.9256 0.9259 1411 PRODUCT 0.5000 0.1765 0.2609 17 QUANTITY 0.0000 0.0000 0.0000 9 TIME 0.7119 0.5000 0.5874 84 UNIT 0.0000 0.0000 0.0000 2 WEBSITE 0.5246 0.5517 0.5378 116 micro avg 0.8375 0.8680 0.8525 14567 macro avg 0.6295 0.6285 0.6196 14567 weighted avg 0.8433 0.8680 0.8540 14567 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:13 Epoch 1 | Timestep 5782 | Test Loss 0.047122 | F1 0.852452 INFO arabiner.trainers.BaseTrainer Thu, 14 May 2026 11:23:13 Saving checkpoint to /content/Wojood/checkpoints/checkpoint_1.pt INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:29 Epoch 2 | Batch 8/2891 | Timestep 5790 | LR 0.0000100000 | Loss 0.034005 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:30 Epoch 2 | Batch 18/2891 | Timestep 5800 | LR 0.0000100000 | Loss 0.040118 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:32 Epoch 2 | Batch 28/2891 | Timestep 5810 | LR 0.0000100000 | Loss 0.008435 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:33 Epoch 2 | Batch 38/2891 | Timestep 5820 | LR 0.0000100000 | Loss 0.012493 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:35 Epoch 2 | Batch 48/2891 | Timestep 5830 | LR 0.0000100000 | Loss 0.057385 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:36 Epoch 2 | Batch 58/2891 | Timestep 5840 | LR 0.0000100000 | Loss 0.010006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:38 Epoch 2 | Batch 68/2891 | Timestep 5850 | LR 0.0000100000 | Loss 0.028767 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:40 Epoch 2 | Batch 78/2891 | Timestep 5860 | LR 0.0000100000 | Loss 0.043423 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:42 Epoch 2 | Batch 88/2891 | Timestep 5870 | LR 0.0000100000 | Loss 0.033902 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:44 Epoch 2 | Batch 98/2891 | Timestep 5880 | LR 0.0000100000 | Loss 0.042203 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:46 Epoch 2 | Batch 108/2891 | Timestep 5890 | LR 0.0000100000 | Loss 0.030390 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:47 Epoch 2 | Batch 118/2891 | Timestep 5900 | LR 0.0000100000 | Loss 0.084277 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:49 Epoch 2 | Batch 128/2891 | Timestep 5910 | LR 0.0000100000 | Loss 0.035032 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:50 Epoch 2 | Batch 138/2891 | Timestep 5920 | LR 0.0000100000 | Loss 0.045966 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:52 Epoch 2 | Batch 148/2891 | Timestep 5930 | LR 0.0000100000 | Loss 0.015868 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:53 Epoch 2 | Batch 158/2891 | Timestep 5940 | LR 0.0000100000 | Loss 0.005856 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:55 Epoch 2 | Batch 168/2891 | Timestep 5950 | LR 0.0000100000 | Loss 0.019651 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:57 Epoch 2 | Batch 178/2891 | Timestep 5960 | LR 0.0000100000 | Loss 0.037935 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:23:59 Epoch 2 | Batch 188/2891 | Timestep 5970 | LR 0.0000100000 | Loss 0.005832 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:01 Epoch 2 | Batch 198/2891 | Timestep 5980 | LR 0.0000100000 | Loss 0.006922 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:02 Epoch 2 | Batch 208/2891 | Timestep 5990 | LR 0.0000100000 | Loss 0.019603 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:04 Epoch 2 | Batch 218/2891 | Timestep 6000 | LR 0.0000100000 | Loss 0.029308 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:06 Epoch 2 | Batch 228/2891 | Timestep 6010 | LR 0.0000100000 | Loss 0.023612 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:08 Epoch 2 | Batch 238/2891 | Timestep 6020 | LR 0.0000100000 | Loss 0.017419 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:10 Epoch 2 | Batch 248/2891 | Timestep 6030 | LR 0.0000100000 | Loss 0.011849 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:12 Epoch 2 | Batch 258/2891 | Timestep 6040 | LR 0.0000100000 | Loss 0.058259 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:13 Epoch 2 | Batch 268/2891 | Timestep 6050 | LR 0.0000100000 | Loss 0.051467 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:15 Epoch 2 | Batch 278/2891 | Timestep 6060 | LR 0.0000100000 | Loss 0.168285 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:17 Epoch 2 | Batch 288/2891 | Timestep 6070 | LR 0.0000100000 | Loss 0.006676 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:19 Epoch 2 | Batch 298/2891 | Timestep 6080 | LR 0.0000100000 | Loss 0.010295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:21 Epoch 2 | Batch 308/2891 | Timestep 6090 | LR 0.0000100000 | Loss 0.019825 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:23 Epoch 2 | Batch 318/2891 | Timestep 6100 | LR 0.0000100000 | Loss 0.024384 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:25 Epoch 2 | Batch 328/2891 | Timestep 6110 | LR 0.0000100000 | Loss 0.029713 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:27 Epoch 2 | Batch 338/2891 | Timestep 6120 | LR 0.0000100000 | Loss 0.015813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:28 Epoch 2 | Batch 348/2891 | Timestep 6130 | LR 0.0000100000 | Loss 0.030121 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:30 Epoch 2 | Batch 358/2891 | Timestep 6140 | LR 0.0000100000 | Loss 0.008473 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:32 Epoch 2 | Batch 368/2891 | Timestep 6150 | LR 0.0000100000 | Loss 0.028870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:33 Epoch 2 | Batch 378/2891 | Timestep 6160 | LR 0.0000100000 | Loss 0.024897 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:35 Epoch 2 | Batch 388/2891 | Timestep 6170 | LR 0.0000100000 | Loss 0.040301 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:37 Epoch 2 | Batch 398/2891 | Timestep 6180 | LR 0.0000100000 | Loss 0.016304 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:38 Epoch 2 | Batch 408/2891 | Timestep 6190 | LR 0.0000100000 | Loss 0.026505 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:40 Epoch 2 | Batch 418/2891 | Timestep 6200 | LR 0.0000100000 | Loss 0.016726 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:41 Epoch 2 | Batch 428/2891 | Timestep 6210 | LR 0.0000100000 | Loss 0.005727 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:42 Epoch 2 | Batch 438/2891 | Timestep 6220 | LR 0.0000100000 | Loss 0.051781 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:44 Epoch 2 | Batch 448/2891 | Timestep 6230 | LR 0.0000100000 | Loss 0.075569 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:46 Epoch 2 | Batch 458/2891 | Timestep 6240 | LR 0.0000100000 | Loss 0.020564 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:47 Epoch 2 | Batch 468/2891 | Timestep 6250 | LR 0.0000100000 | Loss 0.011860 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:49 Epoch 2 | Batch 478/2891 | Timestep 6260 | LR 0.0000100000 | Loss 0.032811 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:50 Epoch 2 | Batch 488/2891 | Timestep 6270 | LR 0.0000100000 | Loss 0.001837 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:52 Epoch 2 | Batch 498/2891 | Timestep 6280 | LR 0.0000100000 | Loss 0.023051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:53 Epoch 2 | Batch 508/2891 | Timestep 6290 | LR 0.0000100000 | Loss 0.059843 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:55 Epoch 2 | Batch 518/2891 | Timestep 6300 | LR 0.0000100000 | Loss 0.020214 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:57 Epoch 2 | Batch 528/2891 | Timestep 6310 | LR 0.0000100000 | Loss 0.128184 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:24:59 Epoch 2 | Batch 538/2891 | Timestep 6320 | LR 0.0000100000 | Loss 0.006664 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:00 Epoch 2 | Batch 548/2891 | Timestep 6330 | LR 0.0000100000 | Loss 0.041858 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:02 Epoch 2 | Batch 558/2891 | Timestep 6340 | LR 0.0000100000 | Loss 0.043750 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:04 Epoch 2 | Batch 568/2891 | Timestep 6350 | LR 0.0000100000 | Loss 0.018182 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:05 Epoch 2 | Batch 578/2891 | Timestep 6360 | LR 0.0000100000 | Loss 0.034044 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:07 Epoch 2 | Batch 588/2891 | Timestep 6370 | LR 0.0000100000 | Loss 0.052649 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:09 Epoch 2 | Batch 598/2891 | Timestep 6380 | LR 0.0000100000 | Loss 0.043748 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:10 Epoch 2 | Batch 608/2891 | Timestep 6390 | LR 0.0000100000 | Loss 0.024769 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:12 Epoch 2 | Batch 618/2891 | Timestep 6400 | LR 0.0000100000 | Loss 0.027218 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:13 Epoch 2 | Batch 628/2891 | Timestep 6410 | LR 0.0000100000 | Loss 0.034361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:15 Epoch 2 | Batch 638/2891 | Timestep 6420 | LR 0.0000100000 | Loss 0.025140 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:16 Epoch 2 | Batch 648/2891 | Timestep 6430 | LR 0.0000100000 | Loss 0.038535 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:18 Epoch 2 | Batch 658/2891 | Timestep 6440 | LR 0.0000100000 | Loss 0.010596 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:19 Epoch 2 | Batch 668/2891 | Timestep 6450 | LR 0.0000100000 | Loss 0.013504 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:21 Epoch 2 | Batch 678/2891 | Timestep 6460 | LR 0.0000100000 | Loss 0.034590 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:23 Epoch 2 | Batch 688/2891 | Timestep 6470 | LR 0.0000100000 | Loss 0.008102 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:25 Epoch 2 | Batch 698/2891 | Timestep 6480 | LR 0.0000100000 | Loss 0.013963 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:27 Epoch 2 | Batch 708/2891 | Timestep 6490 | LR 0.0000100000 | Loss 0.050690 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:28 Epoch 2 | Batch 718/2891 | Timestep 6500 | LR 0.0000100000 | Loss 0.025778 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:30 Epoch 2 | Batch 728/2891 | Timestep 6510 | LR 0.0000100000 | Loss 0.062427 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:32 Epoch 2 | Batch 738/2891 | Timestep 6520 | LR 0.0000100000 | Loss 0.023421 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:34 Epoch 2 | Batch 748/2891 | Timestep 6530 | LR 0.0000100000 | Loss 0.026338 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:35 Epoch 2 | Batch 758/2891 | Timestep 6540 | LR 0.0000100000 | Loss 0.037864 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:37 Epoch 2 | Batch 768/2891 | Timestep 6550 | LR 0.0000100000 | Loss 0.041029 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:39 Epoch 2 | Batch 778/2891 | Timestep 6560 | LR 0.0000100000 | Loss 0.007533 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:40 Epoch 2 | Batch 788/2891 | Timestep 6570 | LR 0.0000100000 | Loss 0.047116 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:42 Epoch 2 | Batch 798/2891 | Timestep 6580 | LR 0.0000100000 | Loss 0.023460 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:44 Epoch 2 | Batch 808/2891 | Timestep 6590 | LR 0.0000100000 | Loss 0.048299 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:46 Epoch 2 | Batch 818/2891 | Timestep 6600 | LR 0.0000100000 | Loss 0.049771 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:47 Epoch 2 | Batch 828/2891 | Timestep 6610 | LR 0.0000100000 | Loss 0.009294 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:49 Epoch 2 | Batch 838/2891 | Timestep 6620 | LR 0.0000100000 | Loss 0.014704 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:51 Epoch 2 | Batch 848/2891 | Timestep 6630 | LR 0.0000100000 | Loss 0.007926 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:53 Epoch 2 | Batch 858/2891 | Timestep 6640 | LR 0.0000100000 | Loss 0.023257 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:54 Epoch 2 | Batch 868/2891 | Timestep 6650 | LR 0.0000100000 | Loss 0.022051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:56 Epoch 2 | Batch 878/2891 | Timestep 6660 | LR 0.0000100000 | Loss 0.008627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:57 Epoch 2 | Batch 888/2891 | Timestep 6670 | LR 0.0000100000 | Loss 0.025561 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:25:59 Epoch 2 | Batch 898/2891 | Timestep 6680 | LR 0.0000100000 | Loss 0.050330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:01 Epoch 2 | Batch 908/2891 | Timestep 6690 | LR 0.0000100000 | Loss 0.039606 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:03 Epoch 2 | Batch 918/2891 | Timestep 6700 | LR 0.0000100000 | Loss 0.018412 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:04 Epoch 2 | Batch 928/2891 | Timestep 6710 | LR 0.0000100000 | Loss 0.021680 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:06 Epoch 2 | Batch 938/2891 | Timestep 6720 | LR 0.0000100000 | Loss 0.032298 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:08 Epoch 2 | Batch 948/2891 | Timestep 6730 | LR 0.0000100000 | Loss 0.049059 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:10 Epoch 2 | Batch 958/2891 | Timestep 6740 | LR 0.0000100000 | Loss 0.024660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:12 Epoch 2 | Batch 968/2891 | Timestep 6750 | LR 0.0000100000 | Loss 0.032230 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:14 Epoch 2 | Batch 978/2891 | Timestep 6760 | LR 0.0000100000 | Loss 0.053392 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:16 Epoch 2 | Batch 988/2891 | Timestep 6770 | LR 0.0000100000 | Loss 0.007711 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:18 Epoch 2 | Batch 998/2891 | Timestep 6780 | LR 0.0000100000 | Loss 0.102095 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:19 Epoch 2 | Batch 1008/2891 | Timestep 6790 | LR 0.0000100000 | Loss 0.028994 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:20 Epoch 2 | Batch 1018/2891 | Timestep 6800 | LR 0.0000100000 | Loss 0.026451 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:22 Epoch 2 | Batch 1028/2891 | Timestep 6810 | LR 0.0000100000 | Loss 0.019728 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:24 Epoch 2 | Batch 1038/2891 | Timestep 6820 | LR 0.0000100000 | Loss 0.013987 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:25 Epoch 2 | Batch 1048/2891 | Timestep 6830 | LR 0.0000100000 | Loss 0.030847 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:27 Epoch 2 | Batch 1058/2891 | Timestep 6840 | LR 0.0000100000 | Loss 0.007355 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:28 Epoch 2 | Batch 1068/2891 | Timestep 6850 | LR 0.0000100000 | Loss 0.007754 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:30 Epoch 2 | Batch 1078/2891 | Timestep 6860 | LR 0.0000100000 | Loss 0.012500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:32 Epoch 2 | Batch 1088/2891 | Timestep 6870 | LR 0.0000100000 | Loss 0.008307 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:33 Epoch 2 | Batch 1098/2891 | Timestep 6880 | LR 0.0000100000 | Loss 0.007472 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:35 Epoch 2 | Batch 1108/2891 | Timestep 6890 | LR 0.0000100000 | Loss 0.013252 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:38 Epoch 2 | Batch 1118/2891 | Timestep 6900 | LR 0.0000100000 | Loss 0.009314 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:39 Epoch 2 | Batch 1128/2891 | Timestep 6910 | LR 0.0000100000 | Loss 0.102724 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:41 Epoch 2 | Batch 1138/2891 | Timestep 6920 | LR 0.0000100000 | Loss 0.014044 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:43 Epoch 2 | Batch 1148/2891 | Timestep 6930 | LR 0.0000100000 | Loss 0.007457 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:45 Epoch 2 | Batch 1158/2891 | Timestep 6940 | LR 0.0000100000 | Loss 0.017627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:46 Epoch 2 | Batch 1168/2891 | Timestep 6950 | LR 0.0000100000 | Loss 0.019401 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:48 Epoch 2 | Batch 1178/2891 | Timestep 6960 | LR 0.0000100000 | Loss 0.009583 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:49 Epoch 2 | Batch 1188/2891 | Timestep 6970 | LR 0.0000100000 | Loss 0.053555 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:51 Epoch 2 | Batch 1198/2891 | Timestep 6980 | LR 0.0000100000 | Loss 0.018458 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:52 Epoch 2 | Batch 1208/2891 | Timestep 6990 | LR 0.0000100000 | Loss 0.026907 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:54 Epoch 2 | Batch 1218/2891 | Timestep 7000 | LR 0.0000100000 | Loss 0.042920 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:55 Epoch 2 | Batch 1228/2891 | Timestep 7010 | LR 0.0000100000 | Loss 0.004647 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:57 Epoch 2 | Batch 1238/2891 | Timestep 7020 | LR 0.0000100000 | Loss 0.070705 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:26:58 Epoch 2 | Batch 1248/2891 | Timestep 7030 | LR 0.0000100000 | Loss 0.006836 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:00 Epoch 2 | Batch 1258/2891 | Timestep 7040 | LR 0.0000100000 | Loss 0.009509 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:01 Epoch 2 | Batch 1268/2891 | Timestep 7050 | LR 0.0000100000 | Loss 0.115091 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:03 Epoch 2 | Batch 1278/2891 | Timestep 7060 | LR 0.0000100000 | Loss 0.009030 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:04 Epoch 2 | Batch 1288/2891 | Timestep 7070 | LR 0.0000100000 | Loss 0.011715 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:06 Epoch 2 | Batch 1298/2891 | Timestep 7080 | LR 0.0000100000 | Loss 0.019081 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:07 Epoch 2 | Batch 1308/2891 | Timestep 7090 | LR 0.0000100000 | Loss 0.015337 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:09 Epoch 2 | Batch 1318/2891 | Timestep 7100 | LR 0.0000100000 | Loss 0.060404 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:10 Epoch 2 | Batch 1328/2891 | Timestep 7110 | LR 0.0000100000 | Loss 0.047572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:13 Epoch 2 | Batch 1338/2891 | Timestep 7120 | LR 0.0000100000 | Loss 0.017841 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:15 Epoch 2 | Batch 1348/2891 | Timestep 7130 | LR 0.0000100000 | Loss 0.030140 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:17 Epoch 2 | Batch 1358/2891 | Timestep 7140 | LR 0.0000100000 | Loss 0.033907 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:18 Epoch 2 | Batch 1368/2891 | Timestep 7150 | LR 0.0000100000 | Loss 0.022031 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:20 Epoch 2 | Batch 1378/2891 | Timestep 7160 | LR 0.0000100000 | Loss 0.021044 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:22 Epoch 2 | Batch 1388/2891 | Timestep 7170 | LR 0.0000100000 | Loss 0.043450 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:23 Epoch 2 | Batch 1398/2891 | Timestep 7180 | LR 0.0000100000 | Loss 0.007762 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:25 Epoch 2 | Batch 1408/2891 | Timestep 7190 | LR 0.0000100000 | Loss 0.014771 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:26 Epoch 2 | Batch 1418/2891 | Timestep 7200 | LR 0.0000100000 | Loss 0.001968 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:27 Epoch 2 | Batch 1428/2891 | Timestep 7210 | LR 0.0000100000 | Loss 0.019089 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:29 Epoch 2 | Batch 1438/2891 | Timestep 7220 | LR 0.0000100000 | Loss 0.004242 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:31 Epoch 2 | Batch 1448/2891 | Timestep 7230 | LR 0.0000100000 | Loss 0.024635 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:33 Epoch 2 | Batch 1458/2891 | Timestep 7240 | LR 0.0000100000 | Loss 0.034549 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:34 Epoch 2 | Batch 1468/2891 | Timestep 7250 | LR 0.0000100000 | Loss 0.030650 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:36 Epoch 2 | Batch 1478/2891 | Timestep 7260 | LR 0.0000100000 | Loss 0.034692 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:37 Epoch 2 | Batch 1488/2891 | Timestep 7270 | LR 0.0000100000 | Loss 0.025679 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:39 Epoch 2 | Batch 1498/2891 | Timestep 7280 | LR 0.0000100000 | Loss 0.073056 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:40 Epoch 2 | Batch 1508/2891 | Timestep 7290 | LR 0.0000100000 | Loss 0.078098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:42 Epoch 2 | Batch 1518/2891 | Timestep 7300 | LR 0.0000100000 | Loss 0.009328 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:44 Epoch 2 | Batch 1528/2891 | Timestep 7310 | LR 0.0000100000 | Loss 0.026035 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:45 Epoch 2 | Batch 1538/2891 | Timestep 7320 | LR 0.0000100000 | Loss 0.029047 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:47 Epoch 2 | Batch 1548/2891 | Timestep 7330 | LR 0.0000100000 | Loss 0.012171 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:49 Epoch 2 | Batch 1558/2891 | Timestep 7340 | LR 0.0000100000 | Loss 0.035378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:50 Epoch 2 | Batch 1568/2891 | Timestep 7350 | LR 0.0000100000 | Loss 0.008740 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:52 Epoch 2 | Batch 1578/2891 | Timestep 7360 | LR 0.0000100000 | Loss 0.012143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:53 Epoch 2 | Batch 1588/2891 | Timestep 7370 | LR 0.0000100000 | Loss 0.069181 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:56 Epoch 2 | Batch 1598/2891 | Timestep 7380 | LR 0.0000100000 | Loss 0.009048 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:57 Epoch 2 | Batch 1608/2891 | Timestep 7390 | LR 0.0000100000 | Loss 0.026756 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:27:59 Epoch 2 | Batch 1618/2891 | Timestep 7400 | LR 0.0000100000 | Loss 0.062525 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:00 Epoch 2 | Batch 1628/2891 | Timestep 7410 | LR 0.0000100000 | Loss 0.029354 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:02 Epoch 2 | Batch 1638/2891 | Timestep 7420 | LR 0.0000100000 | Loss 0.014736 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:03 Epoch 2 | Batch 1648/2891 | Timestep 7430 | LR 0.0000100000 | Loss 0.034221 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:05 Epoch 2 | Batch 1658/2891 | Timestep 7440 | LR 0.0000100000 | Loss 0.036646 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:06 Epoch 2 | Batch 1668/2891 | Timestep 7450 | LR 0.0000100000 | Loss 0.034018 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:08 Epoch 2 | Batch 1678/2891 | Timestep 7460 | LR 0.0000100000 | Loss 0.008578 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:09 Epoch 2 | Batch 1688/2891 | Timestep 7470 | LR 0.0000100000 | Loss 0.014446 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:11 Epoch 2 | Batch 1698/2891 | Timestep 7480 | LR 0.0000100000 | Loss 0.007774 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:13 Epoch 2 | Batch 1708/2891 | Timestep 7490 | LR 0.0000100000 | Loss 0.035451 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:15 Epoch 2 | Batch 1718/2891 | Timestep 7500 | LR 0.0000100000 | Loss 0.028388 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:17 Epoch 2 | Batch 1728/2891 | Timestep 7510 | LR 0.0000100000 | Loss 0.011329 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:18 Epoch 2 | Batch 1738/2891 | Timestep 7520 | LR 0.0000100000 | Loss 0.050462 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:20 Epoch 2 | Batch 1748/2891 | Timestep 7530 | LR 0.0000100000 | Loss 0.023292 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:21 Epoch 2 | Batch 1758/2891 | Timestep 7540 | LR 0.0000100000 | Loss 0.027318 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:23 Epoch 2 | Batch 1768/2891 | Timestep 7550 | LR 0.0000100000 | Loss 0.054928 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:25 Epoch 2 | Batch 1778/2891 | Timestep 7560 | LR 0.0000100000 | Loss 0.027321 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:27 Epoch 2 | Batch 1788/2891 | Timestep 7570 | LR 0.0000100000 | Loss 0.028677 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:29 Epoch 2 | Batch 1798/2891 | Timestep 7580 | LR 0.0000100000 | Loss 0.012943 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:30 Epoch 2 | Batch 1808/2891 | Timestep 7590 | LR 0.0000100000 | Loss 0.054249 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:32 Epoch 2 | Batch 1818/2891 | Timestep 7600 | LR 0.0000100000 | Loss 0.009304 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:34 Epoch 2 | Batch 1828/2891 | Timestep 7610 | LR 0.0000100000 | Loss 0.039790 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:35 Epoch 2 | Batch 1838/2891 | Timestep 7620 | LR 0.0000100000 | Loss 0.019071 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:37 Epoch 2 | Batch 1848/2891 | Timestep 7630 | LR 0.0000100000 | Loss 0.031512 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:38 Epoch 2 | Batch 1858/2891 | Timestep 7640 | LR 0.0000100000 | Loss 0.009809 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:41 Epoch 2 | Batch 1868/2891 | Timestep 7650 | LR 0.0000100000 | Loss 0.060960 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:42 Epoch 2 | Batch 1878/2891 | Timestep 7660 | LR 0.0000100000 | Loss 0.005812 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:44 Epoch 2 | Batch 1888/2891 | Timestep 7670 | LR 0.0000100000 | Loss 0.035399 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:45 Epoch 2 | Batch 1898/2891 | Timestep 7680 | LR 0.0000100000 | Loss 0.051754 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:47 Epoch 2 | Batch 1908/2891 | Timestep 7690 | LR 0.0000100000 | Loss 0.033362 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:49 Epoch 2 | Batch 1918/2891 | Timestep 7700 | LR 0.0000100000 | Loss 0.011415 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:51 Epoch 2 | Batch 1928/2891 | Timestep 7710 | LR 0.0000100000 | Loss 0.005142 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:52 Epoch 2 | Batch 1938/2891 | Timestep 7720 | LR 0.0000100000 | Loss 0.038426 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:54 Epoch 2 | Batch 1948/2891 | Timestep 7730 | LR 0.0000100000 | Loss 0.008241 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:56 Epoch 2 | Batch 1958/2891 | Timestep 7740 | LR 0.0000100000 | Loss 0.227185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:58 Epoch 2 | Batch 1968/2891 | Timestep 7750 | LR 0.0000100000 | Loss 0.028009 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:28:59 Epoch 2 | Batch 1978/2891 | Timestep 7760 | LR 0.0000100000 | Loss 0.007489 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:01 Epoch 2 | Batch 1988/2891 | Timestep 7770 | LR 0.0000100000 | Loss 0.092032 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:03 Epoch 2 | Batch 1998/2891 | Timestep 7780 | LR 0.0000100000 | Loss 0.027802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:04 Epoch 2 | Batch 2008/2891 | Timestep 7790 | LR 0.0000100000 | Loss 0.022154 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:06 Epoch 2 | Batch 2018/2891 | Timestep 7800 | LR 0.0000100000 | Loss 0.007920 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:07 Epoch 2 | Batch 2028/2891 | Timestep 7810 | LR 0.0000100000 | Loss 0.018641 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:09 Epoch 2 | Batch 2038/2891 | Timestep 7820 | LR 0.0000100000 | Loss 0.051193 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:10 Epoch 2 | Batch 2048/2891 | Timestep 7830 | LR 0.0000100000 | Loss 0.043536 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:12 Epoch 2 | Batch 2058/2891 | Timestep 7840 | LR 0.0000100000 | Loss 0.058437 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:14 Epoch 2 | Batch 2068/2891 | Timestep 7850 | LR 0.0000100000 | Loss 0.034783 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:15 Epoch 2 | Batch 2078/2891 | Timestep 7860 | LR 0.0000100000 | Loss 0.002347 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:17 Epoch 2 | Batch 2088/2891 | Timestep 7870 | LR 0.0000100000 | Loss 0.004898 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:19 Epoch 2 | Batch 2098/2891 | Timestep 7880 | LR 0.0000100000 | Loss 0.081525 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:20 Epoch 2 | Batch 2108/2891 | Timestep 7890 | LR 0.0000100000 | Loss 0.021668 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:22 Epoch 2 | Batch 2118/2891 | Timestep 7900 | LR 0.0000100000 | Loss 0.025058 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:23 Epoch 2 | Batch 2128/2891 | Timestep 7910 | LR 0.0000100000 | Loss 0.012553 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:25 Epoch 2 | Batch 2138/2891 | Timestep 7920 | LR 0.0000100000 | Loss 0.026284 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:26 Epoch 2 | Batch 2148/2891 | Timestep 7930 | LR 0.0000100000 | Loss 0.021036 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:28 Epoch 2 | Batch 2158/2891 | Timestep 7940 | LR 0.0000100000 | Loss 0.013823 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:29 Epoch 2 | Batch 2168/2891 | Timestep 7950 | LR 0.0000100000 | Loss 0.035735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:32 Epoch 2 | Batch 2178/2891 | Timestep 7960 | LR 0.0000100000 | Loss 0.013331 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:34 Epoch 2 | Batch 2188/2891 | Timestep 7970 | LR 0.0000100000 | Loss 0.018447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:37 Epoch 2 | Batch 2198/2891 | Timestep 7980 | LR 0.0000100000 | Loss 0.013310 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:38 Epoch 2 | Batch 2208/2891 | Timestep 7990 | LR 0.0000100000 | Loss 0.023410 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:40 Epoch 2 | Batch 2218/2891 | Timestep 8000 | LR 0.0000100000 | Loss 0.025401 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:42 Epoch 2 | Batch 2228/2891 | Timestep 8010 | LR 0.0000100000 | Loss 0.020847 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:44 Epoch 2 | Batch 2238/2891 | Timestep 8020 | LR 0.0000100000 | Loss 0.025275 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:45 Epoch 2 | Batch 2248/2891 | Timestep 8030 | LR 0.0000100000 | Loss 0.036697 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:47 Epoch 2 | Batch 2258/2891 | Timestep 8040 | LR 0.0000100000 | Loss 0.016485 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:48 Epoch 2 | Batch 2268/2891 | Timestep 8050 | LR 0.0000100000 | Loss 0.028115 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:50 Epoch 2 | Batch 2278/2891 | Timestep 8060 | LR 0.0000100000 | Loss 0.022280 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:52 Epoch 2 | Batch 2288/2891 | Timestep 8070 | LR 0.0000100000 | Loss 0.033617 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:54 Epoch 2 | Batch 2298/2891 | Timestep 8080 | LR 0.0000100000 | Loss 0.043150 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:56 Epoch 2 | Batch 2308/2891 | Timestep 8090 | LR 0.0000100000 | Loss 0.029712 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:57 Epoch 2 | Batch 2318/2891 | Timestep 8100 | LR 0.0000100000 | Loss 0.100623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:29:59 Epoch 2 | Batch 2328/2891 | Timestep 8110 | LR 0.0000100000 | Loss 0.016221 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:01 Epoch 2 | Batch 2338/2891 | Timestep 8120 | LR 0.0000100000 | Loss 0.035687 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:03 Epoch 2 | Batch 2348/2891 | Timestep 8130 | LR 0.0000100000 | Loss 0.078905 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:04 Epoch 2 | Batch 2358/2891 | Timestep 8140 | LR 0.0000100000 | Loss 0.068624 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:06 Epoch 2 | Batch 2368/2891 | Timestep 8150 | LR 0.0000100000 | Loss 0.012207 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:08 Epoch 2 | Batch 2378/2891 | Timestep 8160 | LR 0.0000100000 | Loss 0.007274 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:09 Epoch 2 | Batch 2388/2891 | Timestep 8170 | LR 0.0000100000 | Loss 0.014748 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:11 Epoch 2 | Batch 2398/2891 | Timestep 8180 | LR 0.0000100000 | Loss 0.019564 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:13 Epoch 2 | Batch 2408/2891 | Timestep 8190 | LR 0.0000100000 | Loss 0.078394 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:14 Epoch 2 | Batch 2418/2891 | Timestep 8200 | LR 0.0000100000 | Loss 0.007293 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:16 Epoch 2 | Batch 2428/2891 | Timestep 8210 | LR 0.0000100000 | Loss 0.006897 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:19 Epoch 2 | Batch 2438/2891 | Timestep 8220 | LR 0.0000100000 | Loss 0.044380 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:20 Epoch 2 | Batch 2448/2891 | Timestep 8230 | LR 0.0000100000 | Loss 0.023268 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:21 Epoch 2 | Batch 2458/2891 | Timestep 8240 | LR 0.0000100000 | Loss 0.016643 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:23 Epoch 2 | Batch 2468/2891 | Timestep 8250 | LR 0.0000100000 | Loss 0.021494 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:25 Epoch 2 | Batch 2478/2891 | Timestep 8260 | LR 0.0000100000 | Loss 0.036517 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:27 Epoch 2 | Batch 2488/2891 | Timestep 8270 | LR 0.0000100000 | Loss 0.013743 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:28 Epoch 2 | Batch 2498/2891 | Timestep 8280 | LR 0.0000100000 | Loss 0.040818 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:30 Epoch 2 | Batch 2508/2891 | Timestep 8290 | LR 0.0000100000 | Loss 0.041903 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:31 Epoch 2 | Batch 2518/2891 | Timestep 8300 | LR 0.0000100000 | Loss 0.073922 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:33 Epoch 2 | Batch 2528/2891 | Timestep 8310 | LR 0.0000100000 | Loss 0.013172 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:35 Epoch 2 | Batch 2538/2891 | Timestep 8320 | LR 0.0000100000 | Loss 0.017330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:37 Epoch 2 | Batch 2548/2891 | Timestep 8330 | LR 0.0000100000 | Loss 0.011508 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:38 Epoch 2 | Batch 2558/2891 | Timestep 8340 | LR 0.0000100000 | Loss 0.002822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:40 Epoch 2 | Batch 2568/2891 | Timestep 8350 | LR 0.0000100000 | Loss 0.035788 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:42 Epoch 2 | Batch 2578/2891 | Timestep 8360 | LR 0.0000100000 | Loss 0.016909 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:43 Epoch 2 | Batch 2588/2891 | Timestep 8370 | LR 0.0000100000 | Loss 0.013715 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:45 Epoch 2 | Batch 2598/2891 | Timestep 8380 | LR 0.0000100000 | Loss 0.020384 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:47 Epoch 2 | Batch 2608/2891 | Timestep 8390 | LR 0.0000100000 | Loss 0.008428 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:49 Epoch 2 | Batch 2618/2891 | Timestep 8400 | LR 0.0000100000 | Loss 0.025960 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:50 Epoch 2 | Batch 2628/2891 | Timestep 8410 | LR 0.0000100000 | Loss 0.038837 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:52 Epoch 2 | Batch 2638/2891 | Timestep 8420 | LR 0.0000100000 | Loss 0.029870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:54 Epoch 2 | Batch 2648/2891 | Timestep 8430 | LR 0.0000100000 | Loss 0.013542 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:56 Epoch 2 | Batch 2658/2891 | Timestep 8440 | LR 0.0000100000 | Loss 0.008406 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:57 Epoch 2 | Batch 2668/2891 | Timestep 8450 | LR 0.0000100000 | Loss 0.033898 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:30:59 Epoch 2 | Batch 2678/2891 | Timestep 8460 | LR 0.0000100000 | Loss 0.014787 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:01 Epoch 2 | Batch 2688/2891 | Timestep 8470 | LR 0.0000100000 | Loss 0.017903 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:03 Epoch 2 | Batch 2698/2891 | Timestep 8480 | LR 0.0000100000 | Loss 0.025070 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:04 Epoch 2 | Batch 2708/2891 | Timestep 8490 | LR 0.0000100000 | Loss 0.042628 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:05 Epoch 2 | Batch 2718/2891 | Timestep 8500 | LR 0.0000100000 | Loss 0.055048 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:07 Epoch 2 | Batch 2728/2891 | Timestep 8510 | LR 0.0000100000 | Loss 0.017827 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:08 Epoch 2 | Batch 2738/2891 | Timestep 8520 | LR 0.0000100000 | Loss 0.069581 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:10 Epoch 2 | Batch 2748/2891 | Timestep 8530 | LR 0.0000100000 | Loss 0.004743 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:11 Epoch 2 | Batch 2758/2891 | Timestep 8540 | LR 0.0000100000 | Loss 0.017833 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:13 Epoch 2 | Batch 2768/2891 | Timestep 8550 | LR 0.0000100000 | Loss 0.037139 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:14 Epoch 2 | Batch 2778/2891 | Timestep 8560 | LR 0.0000100000 | Loss 0.018602 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:16 Epoch 2 | Batch 2788/2891 | Timestep 8570 | LR 0.0000100000 | Loss 0.025191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:18 Epoch 2 | Batch 2798/2891 | Timestep 8580 | LR 0.0000100000 | Loss 0.014626 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:19 Epoch 2 | Batch 2808/2891 | Timestep 8590 | LR 0.0000100000 | Loss 0.013574 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:21 Epoch 2 | Batch 2818/2891 | Timestep 8600 | LR 0.0000100000 | Loss 0.014305 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:23 Epoch 2 | Batch 2828/2891 | Timestep 8610 | LR 0.0000100000 | Loss 0.034562 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:24 Epoch 2 | Batch 2838/2891 | Timestep 8620 | LR 0.0000100000 | Loss 0.017872 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:26 Epoch 2 | Batch 2848/2891 | Timestep 8630 | LR 0.0000100000 | Loss 0.126378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:27 Epoch 2 | Batch 2858/2891 | Timestep 8640 | LR 0.0000100000 | Loss 0.022331 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:29 Epoch 2 | Batch 2868/2891 | Timestep 8650 | LR 0.0000100000 | Loss 0.077640 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:31 Epoch 2 | Batch 2878/2891 | Timestep 8660 | LR 0.0000100000 | Loss 0.040715 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:32 Epoch 2 | Batch 2888/2891 | Timestep 8670 | LR 0.0000100000 | Loss 0.005512 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:32 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:31:49 precision recall f1-score support CARDINAL 0.8036 0.7941 0.7988 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.9200 0.9384 0.9291 1592 EVENT 0.6552 0.7411 0.6955 282 FAC 0.5349 0.7500 0.6244 92 GPE 0.8797 0.9182 0.8985 1051 LANGUAGE 0.7500 0.7500 0.7500 16 LAW 0.6290 0.8298 0.7156 47 LOC 0.7500 0.7297 0.7397 74 MONEY 0.6207 0.8182 0.7059 22 NORP 0.6414 0.7323 0.6838 508 OCC 0.8519 0.8502 0.8510 514 ORDINAL 0.9129 0.9191 0.9160 445 ORG 0.8956 0.9132 0.9043 1578 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9349 0.9608 0.9477 613 PRODUCT 0.2500 0.1250 0.1667 8 QUANTITY 1.0000 0.6667 0.8000 3 TIME 0.7407 0.6061 0.6667 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.5833 0.5250 0.5526 80 micro avg 0.8524 0.8848 0.8683 7143 macro avg 0.6798 0.6937 0.6813 7143 weighted avg 0.8559 0.8848 0.8695 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:49 Epoch 2 | Timestep 8673 | Train Loss 0.029445 | Val Loss 0.040816 | F1 0.868311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:31:49 ** Validation improved, evaluating test data ** INFO arabiner.data.transforms Thu, 14 May 2026 11:32:09 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, 14 May 2026 11:32:22 Predictions written to /content/Wojood/predictions.txt INFO root Thu, 14 May 2026 11:32:24 precision recall f1-score support CARDINAL 0.7914 0.8680 0.8280 341 CURR 0.0000 0.0000 0.0000 8 DATE 0.9367 0.9524 0.9445 3028 EVENT 0.7010 0.7673 0.7326 550 FAC 0.5882 0.7071 0.6422 198 GPE 0.8561 0.9104 0.8824 2254 LANGUAGE 0.8529 0.6591 0.7436 44 LAW 0.6727 0.8222 0.7400 90 LOC 0.7056 0.7216 0.7135 176 MONEY 0.6667 0.9091 0.7692 33 NORP 0.6762 0.7517 0.7119 1011 OCC 0.8538 0.8295 0.8415 1091 ORDINAL 0.9093 0.9246 0.9169 889 ORG 0.8782 0.9111 0.8943 3182 PERCENT 0.8750 0.8485 0.8615 33 PERS 0.9202 0.9483 0.9340 1411 PRODUCT 0.3000 0.1765 0.2222 17 QUANTITY 0.3333 0.2222 0.2667 9 TIME 0.7123 0.6190 0.6624 84 UNIT 0.0000 0.0000 0.0000 2 WEBSITE 0.6383 0.5172 0.5714 116 micro avg 0.8549 0.8871 0.8707 14567 macro avg 0.6604 0.6698 0.6609 14567 weighted avg 0.8560 0.8871 0.8708 14567 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:25 Epoch 2 | Timestep 8673 | Test Loss 0.040407 | F1 0.870705 INFO arabiner.trainers.BaseTrainer Thu, 14 May 2026 11:32:25 Saving checkpoint to /content/Wojood/checkpoints/checkpoint_2.pt INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:37 Epoch 3 | Batch 7/2891 | Timestep 8680 | LR 0.0000100000 | Loss 0.020696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:38 Epoch 3 | Batch 17/2891 | Timestep 8690 | LR 0.0000100000 | Loss 0.003122 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:40 Epoch 3 | Batch 27/2891 | Timestep 8700 | LR 0.0000100000 | Loss 0.003996 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:42 Epoch 3 | Batch 37/2891 | Timestep 8710 | LR 0.0000100000 | Loss 0.052780 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:43 Epoch 3 | Batch 47/2891 | Timestep 8720 | LR 0.0000100000 | Loss 0.013225 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:45 Epoch 3 | Batch 57/2891 | Timestep 8730 | LR 0.0000100000 | Loss 0.018139 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:47 Epoch 3 | Batch 67/2891 | Timestep 8740 | LR 0.0000100000 | Loss 0.013682 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:49 Epoch 3 | Batch 77/2891 | Timestep 8750 | LR 0.0000100000 | Loss 0.017539 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:51 Epoch 3 | Batch 87/2891 | Timestep 8760 | LR 0.0000100000 | Loss 0.024406 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:52 Epoch 3 | Batch 97/2891 | Timestep 8770 | LR 0.0000100000 | Loss 0.026295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:54 Epoch 3 | Batch 107/2891 | Timestep 8780 | LR 0.0000100000 | Loss 0.021980 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:55 Epoch 3 | Batch 117/2891 | Timestep 8790 | LR 0.0000100000 | Loss 0.006695 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:57 Epoch 3 | Batch 127/2891 | Timestep 8800 | LR 0.0000100000 | Loss 0.046012 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:32:59 Epoch 3 | Batch 137/2891 | Timestep 8810 | LR 0.0000100000 | Loss 0.017222 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:00 Epoch 3 | Batch 147/2891 | Timestep 8820 | LR 0.0000100000 | Loss 0.016586 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:02 Epoch 3 | Batch 157/2891 | Timestep 8830 | LR 0.0000100000 | Loss 0.020628 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:04 Epoch 3 | Batch 167/2891 | Timestep 8840 | LR 0.0000100000 | Loss 0.021122 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:05 Epoch 3 | Batch 177/2891 | Timestep 8850 | LR 0.0000100000 | Loss 0.008976 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:07 Epoch 3 | Batch 187/2891 | Timestep 8860 | LR 0.0000100000 | Loss 0.022500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:09 Epoch 3 | Batch 197/2891 | Timestep 8870 | LR 0.0000100000 | Loss 0.044669 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:10 Epoch 3 | Batch 207/2891 | Timestep 8880 | LR 0.0000100000 | Loss 0.003809 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:13 Epoch 3 | Batch 217/2891 | Timestep 8890 | LR 0.0000100000 | Loss 0.006699 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:14 Epoch 3 | Batch 227/2891 | Timestep 8900 | LR 0.0000100000 | Loss 0.040575 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:16 Epoch 3 | Batch 237/2891 | Timestep 8910 | LR 0.0000100000 | Loss 0.050380 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:18 Epoch 3 | Batch 247/2891 | Timestep 8920 | LR 0.0000100000 | Loss 0.072339 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:19 Epoch 3 | Batch 257/2891 | Timestep 8930 | LR 0.0000100000 | Loss 0.021381 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:21 Epoch 3 | Batch 267/2891 | Timestep 8940 | LR 0.0000100000 | Loss 0.002756 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:22 Epoch 3 | Batch 277/2891 | Timestep 8950 | LR 0.0000100000 | Loss 0.042575 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:24 Epoch 3 | Batch 287/2891 | Timestep 8960 | LR 0.0000100000 | Loss 0.091870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:25 Epoch 3 | Batch 297/2891 | Timestep 8970 | LR 0.0000100000 | Loss 0.041057 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:27 Epoch 3 | Batch 307/2891 | Timestep 8980 | LR 0.0000100000 | Loss 0.014578 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:28 Epoch 3 | Batch 317/2891 | Timestep 8990 | LR 0.0000100000 | Loss 0.021831 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:30 Epoch 3 | Batch 327/2891 | Timestep 9000 | LR 0.0000100000 | Loss 0.022260 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:32 Epoch 3 | Batch 337/2891 | Timestep 9010 | LR 0.0000100000 | Loss 0.054617 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:33 Epoch 3 | Batch 347/2891 | Timestep 9020 | LR 0.0000100000 | Loss 0.011879 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:35 Epoch 3 | Batch 357/2891 | Timestep 9030 | LR 0.0000100000 | Loss 0.005383 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:37 Epoch 3 | Batch 367/2891 | Timestep 9040 | LR 0.0000100000 | Loss 0.015594 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:38 Epoch 3 | Batch 377/2891 | Timestep 9050 | LR 0.0000100000 | Loss 0.013736 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:40 Epoch 3 | Batch 387/2891 | Timestep 9060 | LR 0.0000100000 | Loss 0.027282 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:41 Epoch 3 | Batch 397/2891 | Timestep 9070 | LR 0.0000100000 | Loss 0.003157 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:43 Epoch 3 | Batch 407/2891 | Timestep 9080 | LR 0.0000100000 | Loss 0.010282 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:44 Epoch 3 | Batch 417/2891 | Timestep 9090 | LR 0.0000100000 | Loss 0.010279 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:46 Epoch 3 | Batch 427/2891 | Timestep 9100 | LR 0.0000100000 | Loss 0.016979 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:48 Epoch 3 | Batch 437/2891 | Timestep 9110 | LR 0.0000100000 | Loss 0.014686 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:49 Epoch 3 | Batch 447/2891 | Timestep 9120 | LR 0.0000100000 | Loss 0.017391 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:50 Epoch 3 | Batch 457/2891 | Timestep 9130 | LR 0.0000100000 | Loss 0.049148 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:52 Epoch 3 | Batch 467/2891 | Timestep 9140 | LR 0.0000100000 | Loss 0.008670 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:53 Epoch 3 | Batch 477/2891 | Timestep 9150 | LR 0.0000100000 | Loss 0.015447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:55 Epoch 3 | Batch 487/2891 | Timestep 9160 | LR 0.0000100000 | Loss 0.008938 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:56 Epoch 3 | Batch 497/2891 | Timestep 9170 | LR 0.0000100000 | Loss 0.002420 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:33:58 Epoch 3 | Batch 507/2891 | Timestep 9180 | LR 0.0000100000 | Loss 0.007374 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:00 Epoch 3 | Batch 517/2891 | Timestep 9190 | LR 0.0000100000 | Loss 0.043594 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:02 Epoch 3 | Batch 527/2891 | Timestep 9200 | LR 0.0000100000 | Loss 0.008336 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:03 Epoch 3 | Batch 537/2891 | Timestep 9210 | LR 0.0000100000 | Loss 0.036112 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:05 Epoch 3 | Batch 547/2891 | Timestep 9220 | LR 0.0000100000 | Loss 0.005889 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:06 Epoch 3 | Batch 557/2891 | Timestep 9230 | LR 0.0000100000 | Loss 0.045809 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:08 Epoch 3 | Batch 567/2891 | Timestep 9240 | LR 0.0000100000 | Loss 0.011379 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:09 Epoch 3 | Batch 577/2891 | Timestep 9250 | LR 0.0000100000 | Loss 0.008829 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:12 Epoch 3 | Batch 587/2891 | Timestep 9260 | LR 0.0000100000 | Loss 0.021487 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:13 Epoch 3 | Batch 597/2891 | Timestep 9270 | LR 0.0000100000 | Loss 0.096592 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:15 Epoch 3 | Batch 607/2891 | Timestep 9280 | LR 0.0000100000 | Loss 0.006642 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:16 Epoch 3 | Batch 617/2891 | Timestep 9290 | LR 0.0000100000 | Loss 0.049871 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:18 Epoch 3 | Batch 627/2891 | Timestep 9300 | LR 0.0000100000 | Loss 0.058249 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:20 Epoch 3 | Batch 637/2891 | Timestep 9310 | LR 0.0000100000 | Loss 0.005344 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:21 Epoch 3 | Batch 647/2891 | Timestep 9320 | LR 0.0000100000 | Loss 0.022832 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:23 Epoch 3 | Batch 657/2891 | Timestep 9330 | LR 0.0000100000 | Loss 0.044615 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:25 Epoch 3 | Batch 667/2891 | Timestep 9340 | LR 0.0000100000 | Loss 0.013193 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:26 Epoch 3 | Batch 677/2891 | Timestep 9350 | LR 0.0000100000 | Loss 0.017794 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:29 Epoch 3 | Batch 687/2891 | Timestep 9360 | LR 0.0000100000 | Loss 0.002907 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:31 Epoch 3 | Batch 697/2891 | Timestep 9370 | LR 0.0000100000 | Loss 0.050489 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:33 Epoch 3 | Batch 707/2891 | Timestep 9380 | LR 0.0000100000 | Loss 0.052901 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:34 Epoch 3 | Batch 717/2891 | Timestep 9390 | LR 0.0000100000 | Loss 0.038274 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:36 Epoch 3 | Batch 727/2891 | Timestep 9400 | LR 0.0000100000 | Loss 0.002091 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:38 Epoch 3 | Batch 737/2891 | Timestep 9410 | LR 0.0000100000 | Loss 0.033621 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:39 Epoch 3 | Batch 747/2891 | Timestep 9420 | LR 0.0000100000 | Loss 0.007532 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:41 Epoch 3 | Batch 757/2891 | Timestep 9430 | LR 0.0000100000 | Loss 0.010118 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:42 Epoch 3 | Batch 767/2891 | Timestep 9440 | LR 0.0000100000 | Loss 0.005430 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:43 Epoch 3 | Batch 777/2891 | Timestep 9450 | LR 0.0000100000 | Loss 0.024378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:45 Epoch 3 | Batch 787/2891 | Timestep 9460 | LR 0.0000100000 | Loss 0.008992 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:47 Epoch 3 | Batch 797/2891 | Timestep 9470 | LR 0.0000100000 | Loss 0.003629 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:49 Epoch 3 | Batch 807/2891 | Timestep 9480 | LR 0.0000100000 | Loss 0.002541 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:50 Epoch 3 | Batch 817/2891 | Timestep 9490 | LR 0.0000100000 | Loss 0.053270 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:52 Epoch 3 | Batch 827/2891 | Timestep 9500 | LR 0.0000100000 | Loss 0.026263 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:55 Epoch 3 | Batch 837/2891 | Timestep 9510 | LR 0.0000100000 | Loss 0.005831 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:56 Epoch 3 | Batch 847/2891 | Timestep 9520 | LR 0.0000100000 | Loss 0.033550 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:57 Epoch 3 | Batch 857/2891 | Timestep 9530 | LR 0.0000100000 | Loss 0.017094 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:34:59 Epoch 3 | Batch 867/2891 | Timestep 9540 | LR 0.0000100000 | Loss 0.006224 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:00 Epoch 3 | Batch 877/2891 | Timestep 9550 | LR 0.0000100000 | Loss 0.016185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:02 Epoch 3 | Batch 887/2891 | Timestep 9560 | LR 0.0000100000 | Loss 0.034186 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:04 Epoch 3 | Batch 897/2891 | Timestep 9570 | LR 0.0000100000 | Loss 0.040565 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:06 Epoch 3 | Batch 907/2891 | Timestep 9580 | LR 0.0000100000 | Loss 0.022771 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:08 Epoch 3 | Batch 917/2891 | Timestep 9590 | LR 0.0000100000 | Loss 0.042032 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:10 Epoch 3 | Batch 927/2891 | Timestep 9600 | LR 0.0000100000 | Loss 0.007835 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:12 Epoch 3 | Batch 937/2891 | Timestep 9610 | LR 0.0000100000 | Loss 0.009797 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:14 Epoch 3 | Batch 947/2891 | Timestep 9620 | LR 0.0000100000 | Loss 0.039172 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:15 Epoch 3 | Batch 957/2891 | Timestep 9630 | LR 0.0000100000 | Loss 0.011780 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:17 Epoch 3 | Batch 967/2891 | Timestep 9640 | LR 0.0000100000 | Loss 0.002874 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:18 Epoch 3 | Batch 977/2891 | Timestep 9650 | LR 0.0000100000 | Loss 0.004984 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:20 Epoch 3 | Batch 987/2891 | Timestep 9660 | LR 0.0000100000 | Loss 0.004078 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:22 Epoch 3 | Batch 997/2891 | Timestep 9670 | LR 0.0000100000 | Loss 0.029300 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:23 Epoch 3 | Batch 1007/2891 | Timestep 9680 | LR 0.0000100000 | Loss 0.017247 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:25 Epoch 3 | Batch 1017/2891 | Timestep 9690 | LR 0.0000100000 | Loss 0.006882 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:27 Epoch 3 | Batch 1027/2891 | Timestep 9700 | LR 0.0000100000 | Loss 0.044209 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:28 Epoch 3 | Batch 1037/2891 | Timestep 9710 | LR 0.0000100000 | Loss 0.030128 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:30 Epoch 3 | Batch 1047/2891 | Timestep 9720 | LR 0.0000100000 | Loss 0.003564 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:32 Epoch 3 | Batch 1057/2891 | Timestep 9730 | LR 0.0000100000 | Loss 0.001392 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:33 Epoch 3 | Batch 1067/2891 | Timestep 9740 | LR 0.0000100000 | Loss 0.002527 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:36 Epoch 3 | Batch 1077/2891 | Timestep 9750 | LR 0.0000100000 | Loss 0.017330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:37 Epoch 3 | Batch 1087/2891 | Timestep 9760 | LR 0.0000100000 | Loss 0.016695 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:39 Epoch 3 | Batch 1097/2891 | Timestep 9770 | LR 0.0000100000 | Loss 0.033685 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:41 Epoch 3 | Batch 1107/2891 | Timestep 9780 | LR 0.0000100000 | Loss 0.011253 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:42 Epoch 3 | Batch 1117/2891 | Timestep 9790 | LR 0.0000100000 | Loss 0.006165 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:43 Epoch 3 | Batch 1127/2891 | Timestep 9800 | LR 0.0000100000 | Loss 0.021684 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:45 Epoch 3 | Batch 1137/2891 | Timestep 9810 | LR 0.0000100000 | Loss 0.016191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:47 Epoch 3 | Batch 1147/2891 | Timestep 9820 | LR 0.0000100000 | Loss 0.010285 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:49 Epoch 3 | Batch 1157/2891 | Timestep 9830 | LR 0.0000100000 | Loss 0.044519 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:51 Epoch 3 | Batch 1167/2891 | Timestep 9840 | LR 0.0000100000 | Loss 0.010440 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:52 Epoch 3 | Batch 1177/2891 | Timestep 9850 | LR 0.0000100000 | Loss 0.005084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:54 Epoch 3 | Batch 1187/2891 | Timestep 9860 | LR 0.0000100000 | Loss 0.021634 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:55 Epoch 3 | Batch 1197/2891 | Timestep 9870 | LR 0.0000100000 | Loss 0.004891 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:57 Epoch 3 | Batch 1207/2891 | Timestep 9880 | LR 0.0000100000 | Loss 0.012703 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:35:59 Epoch 3 | Batch 1217/2891 | Timestep 9890 | LR 0.0000100000 | Loss 0.042270 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:01 Epoch 3 | Batch 1227/2891 | Timestep 9900 | LR 0.0000100000 | Loss 0.013588 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:03 Epoch 3 | Batch 1237/2891 | Timestep 9910 | LR 0.0000100000 | Loss 0.044025 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:04 Epoch 3 | Batch 1247/2891 | Timestep 9920 | LR 0.0000100000 | Loss 0.007581 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:06 Epoch 3 | Batch 1257/2891 | Timestep 9930 | LR 0.0000100000 | Loss 0.026772 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:07 Epoch 3 | Batch 1267/2891 | Timestep 9940 | LR 0.0000100000 | Loss 0.010784 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:09 Epoch 3 | Batch 1277/2891 | Timestep 9950 | LR 0.0000100000 | Loss 0.009481 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:11 Epoch 3 | Batch 1287/2891 | Timestep 9960 | LR 0.0000100000 | Loss 0.024913 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:13 Epoch 3 | Batch 1297/2891 | Timestep 9970 | LR 0.0000100000 | Loss 0.009975 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:15 Epoch 3 | Batch 1307/2891 | Timestep 9980 | LR 0.0000100000 | Loss 0.121627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:16 Epoch 3 | Batch 1317/2891 | Timestep 9990 | LR 0.0000100000 | Loss 0.027958 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:18 Epoch 3 | Batch 1327/2891 | Timestep 10000 | LR 0.0000100000 | Loss 0.054328 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:20 Epoch 3 | Batch 1337/2891 | Timestep 10010 | LR 0.0000100000 | Loss 0.014878 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:21 Epoch 3 | Batch 1347/2891 | Timestep 10020 | LR 0.0000100000 | Loss 0.034054 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:22 Epoch 3 | Batch 1357/2891 | Timestep 10030 | LR 0.0000100000 | Loss 0.018235 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:24 Epoch 3 | Batch 1367/2891 | Timestep 10040 | LR 0.0000100000 | Loss 0.064175 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:26 Epoch 3 | Batch 1377/2891 | Timestep 10050 | LR 0.0000100000 | Loss 0.014701 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:28 Epoch 3 | Batch 1387/2891 | Timestep 10060 | LR 0.0000100000 | Loss 0.071321 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:30 Epoch 3 | Batch 1397/2891 | Timestep 10070 | LR 0.0000100000 | Loss 0.036812 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:31 Epoch 3 | Batch 1407/2891 | Timestep 10080 | LR 0.0000100000 | Loss 0.021641 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:33 Epoch 3 | Batch 1417/2891 | Timestep 10090 | LR 0.0000100000 | Loss 0.030530 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:35 Epoch 3 | Batch 1427/2891 | Timestep 10100 | LR 0.0000100000 | Loss 0.040649 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:38 Epoch 3 | Batch 1437/2891 | Timestep 10110 | LR 0.0000100000 | Loss 0.008218 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:39 Epoch 3 | Batch 1447/2891 | Timestep 10120 | LR 0.0000100000 | Loss 0.006026 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:41 Epoch 3 | Batch 1457/2891 | Timestep 10130 | LR 0.0000100000 | Loss 0.021890 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:43 Epoch 3 | Batch 1467/2891 | Timestep 10140 | LR 0.0000100000 | Loss 0.035386 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:45 Epoch 3 | Batch 1477/2891 | Timestep 10150 | LR 0.0000100000 | Loss 0.005465 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:46 Epoch 3 | Batch 1487/2891 | Timestep 10160 | LR 0.0000100000 | Loss 0.005080 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:47 Epoch 3 | Batch 1497/2891 | Timestep 10170 | LR 0.0000100000 | Loss 0.012065 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:49 Epoch 3 | Batch 1507/2891 | Timestep 10180 | LR 0.0000100000 | Loss 0.025804 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:51 Epoch 3 | Batch 1517/2891 | Timestep 10190 | LR 0.0000100000 | Loss 0.047240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:53 Epoch 3 | Batch 1527/2891 | Timestep 10200 | LR 0.0000100000 | Loss 0.020443 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:55 Epoch 3 | Batch 1537/2891 | Timestep 10210 | LR 0.0000100000 | Loss 0.021501 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:56 Epoch 3 | Batch 1547/2891 | Timestep 10220 | LR 0.0000100000 | Loss 0.030375 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:36:58 Epoch 3 | Batch 1557/2891 | Timestep 10230 | LR 0.0000100000 | Loss 0.009997 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:00 Epoch 3 | Batch 1567/2891 | Timestep 10240 | LR 0.0000100000 | Loss 0.013563 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:02 Epoch 3 | Batch 1577/2891 | Timestep 10250 | LR 0.0000100000 | Loss 0.021563 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:03 Epoch 3 | Batch 1587/2891 | Timestep 10260 | LR 0.0000100000 | Loss 0.002390 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:05 Epoch 3 | Batch 1597/2891 | Timestep 10270 | LR 0.0000100000 | Loss 0.011961 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:07 Epoch 3 | Batch 1607/2891 | Timestep 10280 | LR 0.0000100000 | Loss 0.014726 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:08 Epoch 3 | Batch 1617/2891 | Timestep 10290 | LR 0.0000100000 | Loss 0.015383 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:10 Epoch 3 | Batch 1627/2891 | Timestep 10300 | LR 0.0000100000 | Loss 0.014928 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:12 Epoch 3 | Batch 1637/2891 | Timestep 10310 | LR 0.0000100000 | Loss 0.015567 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:14 Epoch 3 | Batch 1647/2891 | Timestep 10320 | LR 0.0000100000 | Loss 0.005720 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:15 Epoch 3 | Batch 1657/2891 | Timestep 10330 | LR 0.0000100000 | Loss 0.021668 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:18 Epoch 3 | Batch 1667/2891 | Timestep 10340 | LR 0.0000100000 | Loss 0.017942 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:20 Epoch 3 | Batch 1677/2891 | Timestep 10350 | LR 0.0000100000 | Loss 0.008908 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:22 Epoch 3 | Batch 1687/2891 | Timestep 10360 | LR 0.0000100000 | Loss 0.048844 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:24 Epoch 3 | Batch 1697/2891 | Timestep 10370 | LR 0.0000100000 | Loss 0.036033 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:25 Epoch 3 | Batch 1707/2891 | Timestep 10380 | LR 0.0000100000 | Loss 0.035424 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:27 Epoch 3 | Batch 1717/2891 | Timestep 10390 | LR 0.0000100000 | Loss 0.051022 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:29 Epoch 3 | Batch 1727/2891 | Timestep 10400 | LR 0.0000100000 | Loss 0.020595 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:31 Epoch 3 | Batch 1737/2891 | Timestep 10410 | LR 0.0000100000 | Loss 0.054025 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:32 Epoch 3 | Batch 1747/2891 | Timestep 10420 | LR 0.0000100000 | Loss 0.019864 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:34 Epoch 3 | Batch 1757/2891 | Timestep 10430 | LR 0.0000100000 | Loss 0.008564 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:36 Epoch 3 | Batch 1767/2891 | Timestep 10440 | LR 0.0000100000 | Loss 0.002665 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:38 Epoch 3 | Batch 1777/2891 | Timestep 10450 | LR 0.0000100000 | Loss 0.020276 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:39 Epoch 3 | Batch 1787/2891 | Timestep 10460 | LR 0.0000100000 | Loss 0.046198 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:41 Epoch 3 | Batch 1797/2891 | Timestep 10470 | LR 0.0000100000 | Loss 0.046653 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:42 Epoch 3 | Batch 1807/2891 | Timestep 10480 | LR 0.0000100000 | Loss 0.009490 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:45 Epoch 3 | Batch 1817/2891 | Timestep 10490 | LR 0.0000100000 | Loss 0.021125 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:46 Epoch 3 | Batch 1827/2891 | Timestep 10500 | LR 0.0000100000 | Loss 0.010812 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:48 Epoch 3 | Batch 1837/2891 | Timestep 10510 | LR 0.0000100000 | Loss 0.006123 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:49 Epoch 3 | Batch 1847/2891 | Timestep 10520 | LR 0.0000100000 | Loss 0.017137 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:51 Epoch 3 | Batch 1857/2891 | Timestep 10530 | LR 0.0000100000 | Loss 0.006117 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:53 Epoch 3 | Batch 1867/2891 | Timestep 10540 | LR 0.0000100000 | Loss 0.019458 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:55 Epoch 3 | Batch 1877/2891 | Timestep 10550 | LR 0.0000100000 | Loss 0.022792 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:56 Epoch 3 | Batch 1887/2891 | Timestep 10560 | LR 0.0000100000 | Loss 0.011487 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:58 Epoch 3 | Batch 1897/2891 | Timestep 10570 | LR 0.0000100000 | Loss 0.027696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:37:59 Epoch 3 | Batch 1907/2891 | Timestep 10580 | LR 0.0000100000 | Loss 0.030634 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:01 Epoch 3 | Batch 1917/2891 | Timestep 10590 | LR 0.0000100000 | Loss 0.023804 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:02 Epoch 3 | Batch 1927/2891 | Timestep 10600 | LR 0.0000100000 | Loss 0.031531 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:04 Epoch 3 | Batch 1937/2891 | Timestep 10610 | LR 0.0000100000 | Loss 0.035450 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:06 Epoch 3 | Batch 1947/2891 | Timestep 10620 | LR 0.0000100000 | Loss 0.019893 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:07 Epoch 3 | Batch 1957/2891 | Timestep 10630 | LR 0.0000100000 | Loss 0.003205 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:09 Epoch 3 | Batch 1967/2891 | Timestep 10640 | LR 0.0000100000 | Loss 0.007971 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:11 Epoch 3 | Batch 1977/2891 | Timestep 10650 | LR 0.0000100000 | Loss 0.089058 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:12 Epoch 3 | Batch 1987/2891 | Timestep 10660 | LR 0.0000100000 | Loss 0.044955 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:13 Epoch 3 | Batch 1997/2891 | Timestep 10670 | LR 0.0000100000 | Loss 0.011692 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:15 Epoch 3 | Batch 2007/2891 | Timestep 10680 | LR 0.0000100000 | Loss 0.014315 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:16 Epoch 3 | Batch 2017/2891 | Timestep 10690 | LR 0.0000100000 | Loss 0.014902 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:18 Epoch 3 | Batch 2027/2891 | Timestep 10700 | LR 0.0000100000 | Loss 0.003501 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:20 Epoch 3 | Batch 2037/2891 | Timestep 10710 | LR 0.0000100000 | Loss 0.046699 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:21 Epoch 3 | Batch 2047/2891 | Timestep 10720 | LR 0.0000100000 | Loss 0.007140 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:23 Epoch 3 | Batch 2057/2891 | Timestep 10730 | LR 0.0000100000 | Loss 0.013045 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:25 Epoch 3 | Batch 2067/2891 | Timestep 10740 | LR 0.0000100000 | Loss 0.015891 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:27 Epoch 3 | Batch 2077/2891 | Timestep 10750 | LR 0.0000100000 | Loss 0.052136 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:28 Epoch 3 | Batch 2087/2891 | Timestep 10760 | LR 0.0000100000 | Loss 0.012390 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:30 Epoch 3 | Batch 2097/2891 | Timestep 10770 | LR 0.0000100000 | Loss 0.003888 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:32 Epoch 3 | Batch 2107/2891 | Timestep 10780 | LR 0.0000100000 | Loss 0.004956 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:33 Epoch 3 | Batch 2117/2891 | Timestep 10790 | LR 0.0000100000 | Loss 0.069885 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:35 Epoch 3 | Batch 2127/2891 | Timestep 10800 | LR 0.0000100000 | Loss 0.030798 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:37 Epoch 3 | Batch 2137/2891 | Timestep 10810 | LR 0.0000100000 | Loss 0.011330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:39 Epoch 3 | Batch 2147/2891 | Timestep 10820 | LR 0.0000100000 | Loss 0.028086 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:40 Epoch 3 | Batch 2157/2891 | Timestep 10830 | LR 0.0000100000 | Loss 0.017589 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:42 Epoch 3 | Batch 2167/2891 | Timestep 10840 | LR 0.0000100000 | Loss 0.015777 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:44 Epoch 3 | Batch 2177/2891 | Timestep 10850 | LR 0.0000100000 | Loss 0.009436 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:46 Epoch 3 | Batch 2187/2891 | Timestep 10860 | LR 0.0000100000 | Loss 0.027051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:47 Epoch 3 | Batch 2197/2891 | Timestep 10870 | LR 0.0000100000 | Loss 0.004902 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:49 Epoch 3 | Batch 2207/2891 | Timestep 10880 | LR 0.0000100000 | Loss 0.013995 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:51 Epoch 3 | Batch 2217/2891 | Timestep 10890 | LR 0.0000100000 | Loss 0.011694 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:52 Epoch 3 | Batch 2227/2891 | Timestep 10900 | LR 0.0000100000 | Loss 0.012106 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:54 Epoch 3 | Batch 2237/2891 | Timestep 10910 | LR 0.0000100000 | Loss 0.032015 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:55 Epoch 3 | Batch 2247/2891 | Timestep 10920 | LR 0.0000100000 | Loss 0.033528 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:57 Epoch 3 | Batch 2257/2891 | Timestep 10930 | LR 0.0000100000 | Loss 0.003778 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:38:59 Epoch 3 | Batch 2267/2891 | Timestep 10940 | LR 0.0000100000 | Loss 0.010157 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:01 Epoch 3 | Batch 2277/2891 | Timestep 10950 | LR 0.0000100000 | Loss 0.010393 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:02 Epoch 3 | Batch 2287/2891 | Timestep 10960 | LR 0.0000100000 | Loss 0.010611 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:04 Epoch 3 | Batch 2297/2891 | Timestep 10970 | LR 0.0000100000 | Loss 0.007879 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:05 Epoch 3 | Batch 2307/2891 | Timestep 10980 | LR 0.0000100000 | Loss 0.004007 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:07 Epoch 3 | Batch 2317/2891 | Timestep 10990 | LR 0.0000100000 | Loss 0.011502 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:08 Epoch 3 | Batch 2327/2891 | Timestep 11000 | LR 0.0000100000 | Loss 0.015808 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:10 Epoch 3 | Batch 2337/2891 | Timestep 11010 | LR 0.0000100000 | Loss 0.033413 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:12 Epoch 3 | Batch 2347/2891 | Timestep 11020 | LR 0.0000100000 | Loss 0.001384 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:13 Epoch 3 | Batch 2357/2891 | Timestep 11030 | LR 0.0000100000 | Loss 0.012484 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:15 Epoch 3 | Batch 2367/2891 | Timestep 11040 | LR 0.0000100000 | Loss 0.031040 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:17 Epoch 3 | Batch 2377/2891 | Timestep 11050 | LR 0.0000100000 | Loss 0.016108 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:19 Epoch 3 | Batch 2387/2891 | Timestep 11060 | LR 0.0000100000 | Loss 0.010719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:21 Epoch 3 | Batch 2397/2891 | Timestep 11070 | LR 0.0000100000 | Loss 0.045447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:23 Epoch 3 | Batch 2407/2891 | Timestep 11080 | LR 0.0000100000 | Loss 0.010358 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:25 Epoch 3 | Batch 2417/2891 | Timestep 11090 | LR 0.0000100000 | Loss 0.007719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:26 Epoch 3 | Batch 2427/2891 | Timestep 11100 | LR 0.0000100000 | Loss 0.004447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:28 Epoch 3 | Batch 2437/2891 | Timestep 11110 | LR 0.0000100000 | Loss 0.026541 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:29 Epoch 3 | Batch 2447/2891 | Timestep 11120 | LR 0.0000100000 | Loss 0.021316 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:31 Epoch 3 | Batch 2457/2891 | Timestep 11130 | LR 0.0000100000 | Loss 0.012541 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:32 Epoch 3 | Batch 2467/2891 | Timestep 11140 | LR 0.0000100000 | Loss 0.017267 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:34 Epoch 3 | Batch 2477/2891 | Timestep 11150 | LR 0.0000100000 | Loss 0.071719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:36 Epoch 3 | Batch 2487/2891 | Timestep 11160 | LR 0.0000100000 | Loss 0.004259 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:37 Epoch 3 | Batch 2497/2891 | Timestep 11170 | LR 0.0000100000 | Loss 0.025390 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:39 Epoch 3 | Batch 2507/2891 | Timestep 11180 | LR 0.0000100000 | Loss 0.017195 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:41 Epoch 3 | Batch 2517/2891 | Timestep 11190 | LR 0.0000100000 | Loss 0.005388 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:43 Epoch 3 | Batch 2527/2891 | Timestep 11200 | LR 0.0000100000 | Loss 0.028774 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:45 Epoch 3 | Batch 2537/2891 | Timestep 11210 | LR 0.0000100000 | Loss 0.008240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:46 Epoch 3 | Batch 2547/2891 | Timestep 11220 | LR 0.0000100000 | Loss 0.006869 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:48 Epoch 3 | Batch 2557/2891 | Timestep 11230 | LR 0.0000100000 | Loss 0.009172 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:50 Epoch 3 | Batch 2567/2891 | Timestep 11240 | LR 0.0000100000 | Loss 0.029189 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:52 Epoch 3 | Batch 2577/2891 | Timestep 11250 | LR 0.0000100000 | Loss 0.011638 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:53 Epoch 3 | Batch 2587/2891 | Timestep 11260 | LR 0.0000100000 | Loss 0.002585 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:55 Epoch 3 | Batch 2597/2891 | Timestep 11270 | LR 0.0000100000 | Loss 0.013416 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:56 Epoch 3 | Batch 2607/2891 | Timestep 11280 | LR 0.0000100000 | Loss 0.022051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:58 Epoch 3 | Batch 2617/2891 | Timestep 11290 | LR 0.0000100000 | Loss 0.018270 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:39:59 Epoch 3 | Batch 2627/2891 | Timestep 11300 | LR 0.0000100000 | Loss 0.046151 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:01 Epoch 3 | Batch 2637/2891 | Timestep 11310 | LR 0.0000100000 | Loss 0.039566 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:03 Epoch 3 | Batch 2647/2891 | Timestep 11320 | LR 0.0000100000 | Loss 0.006012 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:04 Epoch 3 | Batch 2657/2891 | Timestep 11330 | LR 0.0000100000 | Loss 0.009444 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:06 Epoch 3 | Batch 2667/2891 | Timestep 11340 | LR 0.0000100000 | Loss 0.027619 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:09 Epoch 3 | Batch 2677/2891 | Timestep 11350 | LR 0.0000100000 | Loss 0.013103 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:11 Epoch 3 | Batch 2687/2891 | Timestep 11360 | LR 0.0000100000 | Loss 0.052596 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:12 Epoch 3 | Batch 2697/2891 | Timestep 11370 | LR 0.0000100000 | Loss 0.010388 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:14 Epoch 3 | Batch 2707/2891 | Timestep 11380 | LR 0.0000100000 | Loss 0.017264 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:15 Epoch 3 | Batch 2717/2891 | Timestep 11390 | LR 0.0000100000 | Loss 0.006006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:17 Epoch 3 | Batch 2727/2891 | Timestep 11400 | LR 0.0000100000 | Loss 0.018682 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:18 Epoch 3 | Batch 2737/2891 | Timestep 11410 | LR 0.0000100000 | Loss 0.014871 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:20 Epoch 3 | Batch 2747/2891 | Timestep 11420 | LR 0.0000100000 | Loss 0.005837 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:22 Epoch 3 | Batch 2757/2891 | Timestep 11430 | LR 0.0000100000 | Loss 0.036516 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:23 Epoch 3 | Batch 2767/2891 | Timestep 11440 | LR 0.0000100000 | Loss 0.035231 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:25 Epoch 3 | Batch 2777/2891 | Timestep 11450 | LR 0.0000100000 | Loss 0.009100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:27 Epoch 3 | Batch 2787/2891 | Timestep 11460 | LR 0.0000100000 | Loss 0.004200 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:28 Epoch 3 | Batch 2797/2891 | Timestep 11470 | LR 0.0000100000 | Loss 0.004669 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:30 Epoch 3 | Batch 2807/2891 | Timestep 11480 | LR 0.0000100000 | Loss 0.038134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:32 Epoch 3 | Batch 2817/2891 | Timestep 11490 | LR 0.0000100000 | Loss 0.002651 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:34 Epoch 3 | Batch 2827/2891 | Timestep 11500 | LR 0.0000100000 | Loss 0.022462 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:35 Epoch 3 | Batch 2837/2891 | Timestep 11510 | LR 0.0000100000 | Loss 0.032674 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:37 Epoch 3 | Batch 2847/2891 | Timestep 11520 | LR 0.0000100000 | Loss 0.003116 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:39 Epoch 3 | Batch 2857/2891 | Timestep 11530 | LR 0.0000100000 | Loss 0.009293 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:40 Epoch 3 | Batch 2867/2891 | Timestep 11540 | LR 0.0000100000 | Loss 0.021451 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:42 Epoch 3 | Batch 2877/2891 | Timestep 11550 | LR 0.0000100000 | Loss 0.006744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:44 Epoch 3 | Batch 2887/2891 | Timestep 11560 | LR 0.0000100000 | Loss 0.005346 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:40:44 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:41:03 precision recall f1-score support CARDINAL 0.8844 0.7647 0.8202 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.9116 0.9328 0.9221 1592 EVENT 0.5177 0.7766 0.6213 282 FAC 0.6098 0.8152 0.6977 92 GPE 0.8941 0.8915 0.8928 1051 LANGUAGE 0.5652 0.8125 0.6667 16 LAW 0.5263 0.8511 0.6504 47 LOC 0.7027 0.7027 0.7027 74 MONEY 0.6667 0.9091 0.7692 22 NORP 0.6789 0.7283 0.7028 508 OCC 0.8346 0.8638 0.8489 514 ORDINAL 0.9292 0.9146 0.9219 445 ORG 0.8942 0.9049 0.8995 1578 PERCENT 0.8000 1.0000 0.8889 12 PERS 0.9226 0.9527 0.9374 613 PRODUCT 0.2000 0.1250 0.1538 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.5476 0.6970 0.6133 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.4404 0.6000 0.5079 80 micro avg 0.8396 0.8806 0.8596 7143 macro avg 0.6282 0.7100 0.6612 7143 weighted avg 0.8504 0.8806 0.8635 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:04 Epoch 3 | Timestep 11564 | Train Loss 0.021544 | Val Loss 0.043958 | F1 0.859583 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:05 Epoch 4 | Batch 6/2891 | Timestep 11570 | LR 0.0000100000 | Loss 0.041324 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:07 Epoch 4 | Batch 16/2891 | Timestep 11580 | LR 0.0000100000 | Loss 0.028089 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:09 Epoch 4 | Batch 26/2891 | Timestep 11590 | LR 0.0000100000 | Loss 0.016312 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:11 Epoch 4 | Batch 36/2891 | Timestep 11600 | LR 0.0000100000 | Loss 0.062280 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:12 Epoch 4 | Batch 46/2891 | Timestep 11610 | LR 0.0000100000 | Loss 0.008341 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:14 Epoch 4 | Batch 56/2891 | Timestep 11620 | LR 0.0000100000 | Loss 0.054894 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:15 Epoch 4 | Batch 66/2891 | Timestep 11630 | LR 0.0000100000 | Loss 0.033993 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:17 Epoch 4 | Batch 76/2891 | Timestep 11640 | LR 0.0000100000 | Loss 0.006058 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:19 Epoch 4 | Batch 86/2891 | Timestep 11650 | LR 0.0000100000 | Loss 0.008798 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:20 Epoch 4 | Batch 96/2891 | Timestep 11660 | LR 0.0000100000 | Loss 0.007186 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:22 Epoch 4 | Batch 106/2891 | Timestep 11670 | LR 0.0000100000 | Loss 0.013259 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:24 Epoch 4 | Batch 116/2891 | Timestep 11680 | LR 0.0000100000 | Loss 0.005157 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:26 Epoch 4 | Batch 126/2891 | Timestep 11690 | LR 0.0000100000 | Loss 0.003665 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:27 Epoch 4 | Batch 136/2891 | Timestep 11700 | LR 0.0000100000 | Loss 0.027241 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:29 Epoch 4 | Batch 146/2891 | Timestep 11710 | LR 0.0000100000 | Loss 0.036758 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:30 Epoch 4 | Batch 156/2891 | Timestep 11720 | LR 0.0000100000 | Loss 0.015515 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:33 Epoch 4 | Batch 166/2891 | Timestep 11730 | LR 0.0000100000 | Loss 0.003065 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:34 Epoch 4 | Batch 176/2891 | Timestep 11740 | LR 0.0000100000 | Loss 0.011287 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:36 Epoch 4 | Batch 186/2891 | Timestep 11750 | LR 0.0000100000 | Loss 0.019839 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:37 Epoch 4 | Batch 196/2891 | Timestep 11760 | LR 0.0000100000 | Loss 0.039950 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:40 Epoch 4 | Batch 206/2891 | Timestep 11770 | LR 0.0000100000 | Loss 0.036500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:41 Epoch 4 | Batch 216/2891 | Timestep 11780 | LR 0.0000100000 | Loss 0.004343 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:43 Epoch 4 | Batch 226/2891 | Timestep 11790 | LR 0.0000100000 | Loss 0.012702 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:45 Epoch 4 | Batch 236/2891 | Timestep 11800 | LR 0.0000100000 | Loss 0.027552 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:46 Epoch 4 | Batch 246/2891 | Timestep 11810 | LR 0.0000100000 | Loss 0.006381 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:48 Epoch 4 | Batch 256/2891 | Timestep 11820 | LR 0.0000100000 | Loss 0.005651 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:50 Epoch 4 | Batch 266/2891 | Timestep 11830 | LR 0.0000100000 | Loss 0.006239 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:51 Epoch 4 | Batch 276/2891 | Timestep 11840 | LR 0.0000100000 | Loss 0.015710 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:53 Epoch 4 | Batch 286/2891 | Timestep 11850 | LR 0.0000100000 | Loss 0.043504 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:55 Epoch 4 | Batch 296/2891 | Timestep 11860 | LR 0.0000100000 | Loss 0.014319 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:56 Epoch 4 | Batch 306/2891 | Timestep 11870 | LR 0.0000100000 | Loss 0.015088 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:41:58 Epoch 4 | Batch 316/2891 | Timestep 11880 | LR 0.0000100000 | Loss 0.000498 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:00 Epoch 4 | Batch 326/2891 | Timestep 11890 | LR 0.0000100000 | Loss 0.018197 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:02 Epoch 4 | Batch 336/2891 | Timestep 11900 | LR 0.0000100000 | Loss 0.004393 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:03 Epoch 4 | Batch 346/2891 | Timestep 11910 | LR 0.0000100000 | Loss 0.003201 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:05 Epoch 4 | Batch 356/2891 | Timestep 11920 | LR 0.0000100000 | Loss 0.055527 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:07 Epoch 4 | Batch 366/2891 | Timestep 11930 | LR 0.0000100000 | Loss 0.027434 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:08 Epoch 4 | Batch 376/2891 | Timestep 11940 | LR 0.0000100000 | Loss 0.000851 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:10 Epoch 4 | Batch 386/2891 | Timestep 11950 | LR 0.0000100000 | Loss 0.014545 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:12 Epoch 4 | Batch 396/2891 | Timestep 11960 | LR 0.0000100000 | Loss 0.005437 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:14 Epoch 4 | Batch 406/2891 | Timestep 11970 | LR 0.0000100000 | Loss 0.001271 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:15 Epoch 4 | Batch 416/2891 | Timestep 11980 | LR 0.0000100000 | Loss 0.015185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:17 Epoch 4 | Batch 426/2891 | Timestep 11990 | LR 0.0000100000 | Loss 0.001817 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:19 Epoch 4 | Batch 436/2891 | Timestep 12000 | LR 0.0000100000 | Loss 0.038245 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:21 Epoch 4 | Batch 446/2891 | Timestep 12010 | LR 0.0000100000 | Loss 0.012591 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:23 Epoch 4 | Batch 456/2891 | Timestep 12020 | LR 0.0000100000 | Loss 0.025613 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:25 Epoch 4 | Batch 466/2891 | Timestep 12030 | LR 0.0000100000 | Loss 0.046984 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:26 Epoch 4 | Batch 476/2891 | Timestep 12040 | LR 0.0000100000 | Loss 0.011568 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:28 Epoch 4 | Batch 486/2891 | Timestep 12050 | LR 0.0000100000 | Loss 0.009010 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:30 Epoch 4 | Batch 496/2891 | Timestep 12060 | LR 0.0000100000 | Loss 0.008385 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:32 Epoch 4 | Batch 506/2891 | Timestep 12070 | LR 0.0000100000 | Loss 0.012915 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:33 Epoch 4 | Batch 516/2891 | Timestep 12080 | LR 0.0000100000 | Loss 0.009318 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:35 Epoch 4 | Batch 526/2891 | Timestep 12090 | LR 0.0000100000 | Loss 0.006152 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:37 Epoch 4 | Batch 536/2891 | Timestep 12100 | LR 0.0000100000 | Loss 0.009287 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:38 Epoch 4 | Batch 546/2891 | Timestep 12110 | LR 0.0000100000 | Loss 0.013012 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:40 Epoch 4 | Batch 556/2891 | Timestep 12120 | LR 0.0000100000 | Loss 0.005254 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:41 Epoch 4 | Batch 566/2891 | Timestep 12130 | LR 0.0000100000 | Loss 0.008447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:43 Epoch 4 | Batch 576/2891 | Timestep 12140 | LR 0.0000100000 | Loss 0.003684 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:44 Epoch 4 | Batch 586/2891 | Timestep 12150 | LR 0.0000100000 | Loss 0.029864 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:46 Epoch 4 | Batch 596/2891 | Timestep 12160 | LR 0.0000100000 | Loss 0.030100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:47 Epoch 4 | Batch 606/2891 | Timestep 12170 | LR 0.0000100000 | Loss 0.012663 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:49 Epoch 4 | Batch 616/2891 | Timestep 12180 | LR 0.0000100000 | Loss 0.015758 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:51 Epoch 4 | Batch 626/2891 | Timestep 12190 | LR 0.0000100000 | Loss 0.004229 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:52 Epoch 4 | Batch 636/2891 | Timestep 12200 | LR 0.0000100000 | Loss 0.011410 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:54 Epoch 4 | Batch 646/2891 | Timestep 12210 | LR 0.0000100000 | Loss 0.015230 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:56 Epoch 4 | Batch 656/2891 | Timestep 12220 | LR 0.0000100000 | Loss 0.055103 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:57 Epoch 4 | Batch 666/2891 | Timestep 12230 | LR 0.0000100000 | Loss 0.003677 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:42:59 Epoch 4 | Batch 676/2891 | Timestep 12240 | LR 0.0000100000 | Loss 0.012687 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:00 Epoch 4 | Batch 686/2891 | Timestep 12250 | LR 0.0000100000 | Loss 0.009309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:02 Epoch 4 | Batch 696/2891 | Timestep 12260 | LR 0.0000100000 | Loss 0.004509 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:04 Epoch 4 | Batch 706/2891 | Timestep 12270 | LR 0.0000100000 | Loss 0.003787 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:05 Epoch 4 | Batch 716/2891 | Timestep 12280 | LR 0.0000100000 | Loss 0.016697 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:07 Epoch 4 | Batch 726/2891 | Timestep 12290 | LR 0.0000100000 | Loss 0.016701 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:09 Epoch 4 | Batch 736/2891 | Timestep 12300 | LR 0.0000100000 | Loss 0.004295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:11 Epoch 4 | Batch 746/2891 | Timestep 12310 | LR 0.0000100000 | Loss 0.001290 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:12 Epoch 4 | Batch 756/2891 | Timestep 12320 | LR 0.0000100000 | Loss 0.026646 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:15 Epoch 4 | Batch 766/2891 | Timestep 12330 | LR 0.0000100000 | Loss 0.004078 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:16 Epoch 4 | Batch 776/2891 | Timestep 12340 | LR 0.0000100000 | Loss 0.004161 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:18 Epoch 4 | Batch 786/2891 | Timestep 12350 | LR 0.0000100000 | Loss 0.005008 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:20 Epoch 4 | Batch 796/2891 | Timestep 12360 | LR 0.0000100000 | Loss 0.019463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:22 Epoch 4 | Batch 806/2891 | Timestep 12370 | LR 0.0000100000 | Loss 0.016167 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:23 Epoch 4 | Batch 816/2891 | Timestep 12380 | LR 0.0000100000 | Loss 0.020671 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:25 Epoch 4 | Batch 826/2891 | Timestep 12390 | LR 0.0000100000 | Loss 0.004931 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:26 Epoch 4 | Batch 836/2891 | Timestep 12400 | LR 0.0000100000 | Loss 0.009086 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:28 Epoch 4 | Batch 846/2891 | Timestep 12410 | LR 0.0000100000 | Loss 0.067309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:29 Epoch 4 | Batch 856/2891 | Timestep 12420 | LR 0.0000100000 | Loss 0.023688 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:31 Epoch 4 | Batch 866/2891 | Timestep 12430 | LR 0.0000100000 | Loss 0.009811 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:33 Epoch 4 | Batch 876/2891 | Timestep 12440 | LR 0.0000100000 | Loss 0.020112 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:34 Epoch 4 | Batch 886/2891 | Timestep 12450 | LR 0.0000100000 | Loss 0.004954 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:36 Epoch 4 | Batch 896/2891 | Timestep 12460 | LR 0.0000100000 | Loss 0.000946 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:37 Epoch 4 | Batch 906/2891 | Timestep 12470 | LR 0.0000100000 | Loss 0.005387 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:39 Epoch 4 | Batch 916/2891 | Timestep 12480 | LR 0.0000100000 | Loss 0.006678 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:41 Epoch 4 | Batch 926/2891 | Timestep 12490 | LR 0.0000100000 | Loss 0.010463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:43 Epoch 4 | Batch 936/2891 | Timestep 12500 | LR 0.0000100000 | Loss 0.008122 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:45 Epoch 4 | Batch 946/2891 | Timestep 12510 | LR 0.0000100000 | Loss 0.001925 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:47 Epoch 4 | Batch 956/2891 | Timestep 12520 | LR 0.0000100000 | Loss 0.019485 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:48 Epoch 4 | Batch 966/2891 | Timestep 12530 | LR 0.0000100000 | Loss 0.007294 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:50 Epoch 4 | Batch 976/2891 | Timestep 12540 | LR 0.0000100000 | Loss 0.009188 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:52 Epoch 4 | Batch 986/2891 | Timestep 12550 | LR 0.0000100000 | Loss 0.012134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:54 Epoch 4 | Batch 996/2891 | Timestep 12560 | LR 0.0000100000 | Loss 0.001822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:55 Epoch 4 | Batch 1006/2891 | Timestep 12570 | LR 0.0000100000 | Loss 0.003840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:57 Epoch 4 | Batch 1016/2891 | Timestep 12580 | LR 0.0000100000 | Loss 0.029460 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:43:58 Epoch 4 | Batch 1026/2891 | Timestep 12590 | LR 0.0000100000 | Loss 0.013988 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:00 Epoch 4 | Batch 1036/2891 | Timestep 12600 | LR 0.0000100000 | Loss 0.004496 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:02 Epoch 4 | Batch 1046/2891 | Timestep 12610 | LR 0.0000100000 | Loss 0.001038 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:03 Epoch 4 | Batch 1056/2891 | Timestep 12620 | LR 0.0000100000 | Loss 0.010952 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:04 Epoch 4 | Batch 1066/2891 | Timestep 12630 | LR 0.0000100000 | Loss 0.016361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:06 Epoch 4 | Batch 1076/2891 | Timestep 12640 | LR 0.0000100000 | Loss 0.034550 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:07 Epoch 4 | Batch 1086/2891 | Timestep 12650 | LR 0.0000100000 | Loss 0.002997 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:10 Epoch 4 | Batch 1096/2891 | Timestep 12660 | LR 0.0000100000 | Loss 0.005267 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:11 Epoch 4 | Batch 1106/2891 | Timestep 12670 | LR 0.0000100000 | Loss 0.017806 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:12 Epoch 4 | Batch 1116/2891 | Timestep 12680 | LR 0.0000100000 | Loss 0.002134 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:14 Epoch 4 | Batch 1126/2891 | Timestep 12690 | LR 0.0000100000 | Loss 0.000828 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:16 Epoch 4 | Batch 1136/2891 | Timestep 12700 | LR 0.0000100000 | Loss 0.022016 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:17 Epoch 4 | Batch 1146/2891 | Timestep 12710 | LR 0.0000100000 | Loss 0.026975 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:19 Epoch 4 | Batch 1156/2891 | Timestep 12720 | LR 0.0000100000 | Loss 0.004589 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:21 Epoch 4 | Batch 1166/2891 | Timestep 12730 | LR 0.0000100000 | Loss 0.001072 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:22 Epoch 4 | Batch 1176/2891 | Timestep 12740 | LR 0.0000100000 | Loss 0.029417 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:24 Epoch 4 | Batch 1186/2891 | Timestep 12750 | LR 0.0000100000 | Loss 0.004405 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:26 Epoch 4 | Batch 1196/2891 | Timestep 12760 | LR 0.0000100000 | Loss 0.025665 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:27 Epoch 4 | Batch 1206/2891 | Timestep 12770 | LR 0.0000100000 | Loss 0.031724 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:29 Epoch 4 | Batch 1216/2891 | Timestep 12780 | LR 0.0000100000 | Loss 0.018648 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:31 Epoch 4 | Batch 1226/2891 | Timestep 12790 | LR 0.0000100000 | Loss 0.033773 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:32 Epoch 4 | Batch 1236/2891 | Timestep 12800 | LR 0.0000100000 | Loss 0.002050 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:35 Epoch 4 | Batch 1246/2891 | Timestep 12810 | LR 0.0000100000 | Loss 0.013789 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:37 Epoch 4 | Batch 1256/2891 | Timestep 12820 | LR 0.0000100000 | Loss 0.011554 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:39 Epoch 4 | Batch 1266/2891 | Timestep 12830 | LR 0.0000100000 | Loss 0.012618 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:40 Epoch 4 | Batch 1276/2891 | Timestep 12840 | LR 0.0000100000 | Loss 0.006062 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:42 Epoch 4 | Batch 1286/2891 | Timestep 12850 | LR 0.0000100000 | Loss 0.002747 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:43 Epoch 4 | Batch 1296/2891 | Timestep 12860 | LR 0.0000100000 | Loss 0.021861 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:45 Epoch 4 | Batch 1306/2891 | Timestep 12870 | LR 0.0000100000 | Loss 0.031155 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:46 Epoch 4 | Batch 1316/2891 | Timestep 12880 | LR 0.0000100000 | Loss 0.009466 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:48 Epoch 4 | Batch 1326/2891 | Timestep 12890 | LR 0.0000100000 | Loss 0.003449 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:50 Epoch 4 | Batch 1336/2891 | Timestep 12900 | LR 0.0000100000 | Loss 0.011660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:52 Epoch 4 | Batch 1346/2891 | Timestep 12910 | LR 0.0000100000 | Loss 0.012712 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:54 Epoch 4 | Batch 1356/2891 | Timestep 12920 | LR 0.0000100000 | Loss 0.020431 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:55 Epoch 4 | Batch 1366/2891 | Timestep 12930 | LR 0.0000100000 | Loss 0.007536 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:57 Epoch 4 | Batch 1376/2891 | Timestep 12940 | LR 0.0000100000 | Loss 0.018079 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:44:58 Epoch 4 | Batch 1386/2891 | Timestep 12950 | LR 0.0000100000 | Loss 0.007629 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:00 Epoch 4 | Batch 1396/2891 | Timestep 12960 | LR 0.0000100000 | Loss 0.014460 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:02 Epoch 4 | Batch 1406/2891 | Timestep 12970 | LR 0.0000100000 | Loss 0.069314 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:03 Epoch 4 | Batch 1416/2891 | Timestep 12980 | LR 0.0000100000 | Loss 0.002879 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:05 Epoch 4 | Batch 1426/2891 | Timestep 12990 | LR 0.0000100000 | Loss 0.002717 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:07 Epoch 4 | Batch 1436/2891 | Timestep 13000 | LR 0.0000100000 | Loss 0.005521 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:08 Epoch 4 | Batch 1446/2891 | Timestep 13010 | LR 0.0000100000 | Loss 0.013109 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:10 Epoch 4 | Batch 1456/2891 | Timestep 13020 | LR 0.0000100000 | Loss 0.016545 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:11 Epoch 4 | Batch 1466/2891 | Timestep 13030 | LR 0.0000100000 | Loss 0.010728 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:14 Epoch 4 | Batch 1476/2891 | Timestep 13040 | LR 0.0000100000 | Loss 0.001144 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:15 Epoch 4 | Batch 1486/2891 | Timestep 13050 | LR 0.0000100000 | Loss 0.010813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:17 Epoch 4 | Batch 1496/2891 | Timestep 13060 | LR 0.0000100000 | Loss 0.022039 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:18 Epoch 4 | Batch 1506/2891 | Timestep 13070 | LR 0.0000100000 | Loss 0.003788 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:20 Epoch 4 | Batch 1516/2891 | Timestep 13080 | LR 0.0000100000 | Loss 0.007041 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:22 Epoch 4 | Batch 1526/2891 | Timestep 13090 | LR 0.0000100000 | Loss 0.000835 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:23 Epoch 4 | Batch 1536/2891 | Timestep 13100 | LR 0.0000100000 | Loss 0.005132 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:26 Epoch 4 | Batch 1546/2891 | Timestep 13110 | LR 0.0000100000 | Loss 0.057630 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:27 Epoch 4 | Batch 1556/2891 | Timestep 13120 | LR 0.0000100000 | Loss 0.047654 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:29 Epoch 4 | Batch 1566/2891 | Timestep 13130 | LR 0.0000100000 | Loss 0.039904 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:30 Epoch 4 | Batch 1576/2891 | Timestep 13140 | LR 0.0000100000 | Loss 0.001018 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:32 Epoch 4 | Batch 1586/2891 | Timestep 13150 | LR 0.0000100000 | Loss 0.004444 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:33 Epoch 4 | Batch 1596/2891 | Timestep 13160 | LR 0.0000100000 | Loss 0.002591 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:36 Epoch 4 | Batch 1606/2891 | Timestep 13170 | LR 0.0000100000 | Loss 0.013935 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:37 Epoch 4 | Batch 1616/2891 | Timestep 13180 | LR 0.0000100000 | Loss 0.051174 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:39 Epoch 4 | Batch 1626/2891 | Timestep 13190 | LR 0.0000100000 | Loss 0.031622 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:40 Epoch 4 | Batch 1636/2891 | Timestep 13200 | LR 0.0000100000 | Loss 0.010777 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:43 Epoch 4 | Batch 1646/2891 | Timestep 13210 | LR 0.0000100000 | Loss 0.005404 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:44 Epoch 4 | Batch 1656/2891 | Timestep 13220 | LR 0.0000100000 | Loss 0.069143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:46 Epoch 4 | Batch 1666/2891 | Timestep 13230 | LR 0.0000100000 | Loss 0.002284 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:47 Epoch 4 | Batch 1676/2891 | Timestep 13240 | LR 0.0000100000 | Loss 0.038359 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:49 Epoch 4 | Batch 1686/2891 | Timestep 13250 | LR 0.0000100000 | Loss 0.010277 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:51 Epoch 4 | Batch 1696/2891 | Timestep 13260 | LR 0.0000100000 | Loss 0.009781 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:53 Epoch 4 | Batch 1706/2891 | Timestep 13270 | LR 0.0000100000 | Loss 0.009286 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:55 Epoch 4 | Batch 1716/2891 | Timestep 13280 | LR 0.0000100000 | Loss 0.012187 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:56 Epoch 4 | Batch 1726/2891 | Timestep 13290 | LR 0.0000100000 | Loss 0.010309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:45:58 Epoch 4 | Batch 1736/2891 | Timestep 13300 | LR 0.0000100000 | Loss 0.022669 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:00 Epoch 4 | Batch 1746/2891 | Timestep 13310 | LR 0.0000100000 | Loss 0.058459 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:01 Epoch 4 | Batch 1756/2891 | Timestep 13320 | LR 0.0000100000 | Loss 0.004024 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:03 Epoch 4 | Batch 1766/2891 | Timestep 13330 | LR 0.0000100000 | Loss 0.019740 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:04 Epoch 4 | Batch 1776/2891 | Timestep 13340 | LR 0.0000100000 | Loss 0.025833 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:06 Epoch 4 | Batch 1786/2891 | Timestep 13350 | LR 0.0000100000 | Loss 0.005965 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:08 Epoch 4 | Batch 1796/2891 | Timestep 13360 | LR 0.0000100000 | Loss 0.004318 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:09 Epoch 4 | Batch 1806/2891 | Timestep 13370 | LR 0.0000100000 | Loss 0.007730 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:11 Epoch 4 | Batch 1816/2891 | Timestep 13380 | LR 0.0000100000 | Loss 0.009642 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:12 Epoch 4 | Batch 1826/2891 | Timestep 13390 | LR 0.0000100000 | Loss 0.003440 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:14 Epoch 4 | Batch 1836/2891 | Timestep 13400 | LR 0.0000100000 | Loss 0.012454 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:16 Epoch 4 | Batch 1846/2891 | Timestep 13410 | LR 0.0000100000 | Loss 0.001536 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:18 Epoch 4 | Batch 1856/2891 | Timestep 13420 | LR 0.0000100000 | Loss 0.015032 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:19 Epoch 4 | Batch 1866/2891 | Timestep 13430 | LR 0.0000100000 | Loss 0.006744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:22 Epoch 4 | Batch 1876/2891 | Timestep 13440 | LR 0.0000100000 | Loss 0.012978 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:23 Epoch 4 | Batch 1886/2891 | Timestep 13450 | LR 0.0000100000 | Loss 0.014542 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:25 Epoch 4 | Batch 1896/2891 | Timestep 13460 | LR 0.0000100000 | Loss 0.018474 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:26 Epoch 4 | Batch 1906/2891 | Timestep 13470 | LR 0.0000100000 | Loss 0.039148 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:28 Epoch 4 | Batch 1916/2891 | Timestep 13480 | LR 0.0000100000 | Loss 0.030930 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:30 Epoch 4 | Batch 1926/2891 | Timestep 13490 | LR 0.0000100000 | Loss 0.007295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:32 Epoch 4 | Batch 1936/2891 | Timestep 13500 | LR 0.0000100000 | Loss 0.008754 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:33 Epoch 4 | Batch 1946/2891 | Timestep 13510 | LR 0.0000100000 | Loss 0.009384 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:35 Epoch 4 | Batch 1956/2891 | Timestep 13520 | LR 0.0000100000 | Loss 0.002317 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:37 Epoch 4 | Batch 1966/2891 | Timestep 13530 | LR 0.0000100000 | Loss 0.010147 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:39 Epoch 4 | Batch 1976/2891 | Timestep 13540 | LR 0.0000100000 | Loss 0.059628 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:40 Epoch 4 | Batch 1986/2891 | Timestep 13550 | LR 0.0000100000 | Loss 0.013847 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:42 Epoch 4 | Batch 1996/2891 | Timestep 13560 | LR 0.0000100000 | Loss 0.007722 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:43 Epoch 4 | Batch 2006/2891 | Timestep 13570 | LR 0.0000100000 | Loss 0.032021 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:45 Epoch 4 | Batch 2016/2891 | Timestep 13580 | LR 0.0000100000 | Loss 0.006922 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:46 Epoch 4 | Batch 2026/2891 | Timestep 13590 | LR 0.0000100000 | Loss 0.014443 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:48 Epoch 4 | Batch 2036/2891 | Timestep 13600 | LR 0.0000100000 | Loss 0.004188 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:50 Epoch 4 | Batch 2046/2891 | Timestep 13610 | LR 0.0000100000 | Loss 0.045214 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:51 Epoch 4 | Batch 2056/2891 | Timestep 13620 | LR 0.0000100000 | Loss 0.017084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:53 Epoch 4 | Batch 2066/2891 | Timestep 13630 | LR 0.0000100000 | Loss 0.013983 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:54 Epoch 4 | Batch 2076/2891 | Timestep 13640 | LR 0.0000100000 | Loss 0.005290 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:56 Epoch 4 | Batch 2086/2891 | Timestep 13650 | LR 0.0000100000 | Loss 0.013558 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:58 Epoch 4 | Batch 2096/2891 | Timestep 13660 | LR 0.0000100000 | Loss 0.070254 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:46:59 Epoch 4 | Batch 2106/2891 | Timestep 13670 | LR 0.0000100000 | Loss 0.020497 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:02 Epoch 4 | Batch 2116/2891 | Timestep 13680 | LR 0.0000100000 | Loss 0.015003 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:03 Epoch 4 | Batch 2126/2891 | Timestep 13690 | LR 0.0000100000 | Loss 0.151142 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:04 Epoch 4 | Batch 2136/2891 | Timestep 13700 | LR 0.0000100000 | Loss 0.004878 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:06 Epoch 4 | Batch 2146/2891 | Timestep 13710 | LR 0.0000100000 | Loss 0.062366 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:08 Epoch 4 | Batch 2156/2891 | Timestep 13720 | LR 0.0000100000 | Loss 0.007117 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:09 Epoch 4 | Batch 2166/2891 | Timestep 13730 | LR 0.0000100000 | Loss 0.006132 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:11 Epoch 4 | Batch 2176/2891 | Timestep 13740 | LR 0.0000100000 | Loss 0.002218 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:12 Epoch 4 | Batch 2186/2891 | Timestep 13750 | LR 0.0000100000 | Loss 0.001933 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:14 Epoch 4 | Batch 2196/2891 | Timestep 13760 | LR 0.0000100000 | Loss 0.005520 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:16 Epoch 4 | Batch 2206/2891 | Timestep 13770 | LR 0.0000100000 | Loss 0.003315 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:18 Epoch 4 | Batch 2216/2891 | Timestep 13780 | LR 0.0000100000 | Loss 0.001468 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:19 Epoch 4 | Batch 2226/2891 | Timestep 13790 | LR 0.0000100000 | Loss 0.006380 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:21 Epoch 4 | Batch 2236/2891 | Timestep 13800 | LR 0.0000100000 | Loss 0.015580 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:23 Epoch 4 | Batch 2246/2891 | Timestep 13810 | LR 0.0000100000 | Loss 0.003784 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:24 Epoch 4 | Batch 2256/2891 | Timestep 13820 | LR 0.0000100000 | Loss 0.019555 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:26 Epoch 4 | Batch 2266/2891 | Timestep 13830 | LR 0.0000100000 | Loss 0.004919 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:27 Epoch 4 | Batch 2276/2891 | Timestep 13840 | LR 0.0000100000 | Loss 0.007498 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:29 Epoch 4 | Batch 2286/2891 | Timestep 13850 | LR 0.0000100000 | Loss 0.001805 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:31 Epoch 4 | Batch 2296/2891 | Timestep 13860 | LR 0.0000100000 | Loss 0.019153 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:32 Epoch 4 | Batch 2306/2891 | Timestep 13870 | LR 0.0000100000 | Loss 0.018956 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:34 Epoch 4 | Batch 2316/2891 | Timestep 13880 | LR 0.0000100000 | Loss 0.005028 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:36 Epoch 4 | Batch 2326/2891 | Timestep 13890 | LR 0.0000100000 | Loss 0.002965 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:37 Epoch 4 | Batch 2336/2891 | Timestep 13900 | LR 0.0000100000 | Loss 0.006545 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:39 Epoch 4 | Batch 2346/2891 | Timestep 13910 | LR 0.0000100000 | Loss 0.020247 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:40 Epoch 4 | Batch 2356/2891 | Timestep 13920 | LR 0.0000100000 | Loss 0.015849 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:42 Epoch 4 | Batch 2366/2891 | Timestep 13930 | LR 0.0000100000 | Loss 0.001728 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:44 Epoch 4 | Batch 2376/2891 | Timestep 13940 | LR 0.0000100000 | Loss 0.016661 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:46 Epoch 4 | Batch 2386/2891 | Timestep 13950 | LR 0.0000100000 | Loss 0.024754 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:47 Epoch 4 | Batch 2396/2891 | Timestep 13960 | LR 0.0000100000 | Loss 0.065758 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:49 Epoch 4 | Batch 2406/2891 | Timestep 13970 | LR 0.0000100000 | Loss 0.013984 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:50 Epoch 4 | Batch 2416/2891 | Timestep 13980 | LR 0.0000100000 | Loss 0.047723 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:52 Epoch 4 | Batch 2426/2891 | Timestep 13990 | LR 0.0000100000 | Loss 0.050419 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:54 Epoch 4 | Batch 2436/2891 | Timestep 14000 | LR 0.0000100000 | Loss 0.007109 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:55 Epoch 4 | Batch 2446/2891 | Timestep 14010 | LR 0.0000100000 | Loss 0.018818 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:57 Epoch 4 | Batch 2456/2891 | Timestep 14020 | LR 0.0000100000 | Loss 0.003135 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:47:59 Epoch 4 | Batch 2466/2891 | Timestep 14030 | LR 0.0000100000 | Loss 0.043623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:01 Epoch 4 | Batch 2476/2891 | Timestep 14040 | LR 0.0000100000 | Loss 0.005528 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:03 Epoch 4 | Batch 2486/2891 | Timestep 14050 | LR 0.0000100000 | Loss 0.008525 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:04 Epoch 4 | Batch 2496/2891 | Timestep 14060 | LR 0.0000100000 | Loss 0.031069 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:05 Epoch 4 | Batch 2506/2891 | Timestep 14070 | LR 0.0000100000 | Loss 0.019558 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:07 Epoch 4 | Batch 2516/2891 | Timestep 14080 | LR 0.0000100000 | Loss 0.042284 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:09 Epoch 4 | Batch 2526/2891 | Timestep 14090 | LR 0.0000100000 | Loss 0.010723 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:11 Epoch 4 | Batch 2536/2891 | Timestep 14100 | LR 0.0000100000 | Loss 0.036994 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:12 Epoch 4 | Batch 2546/2891 | Timestep 14110 | LR 0.0000100000 | Loss 0.066273 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:14 Epoch 4 | Batch 2556/2891 | Timestep 14120 | LR 0.0000100000 | Loss 0.025527 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:15 Epoch 4 | Batch 2566/2891 | Timestep 14130 | LR 0.0000100000 | Loss 0.021357 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:17 Epoch 4 | Batch 2576/2891 | Timestep 14140 | LR 0.0000100000 | Loss 0.008044 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:19 Epoch 4 | Batch 2586/2891 | Timestep 14150 | LR 0.0000100000 | Loss 0.021531 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:20 Epoch 4 | Batch 2596/2891 | Timestep 14160 | LR 0.0000100000 | Loss 0.003660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:22 Epoch 4 | Batch 2606/2891 | Timestep 14170 | LR 0.0000100000 | Loss 0.009138 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:24 Epoch 4 | Batch 2616/2891 | Timestep 14180 | LR 0.0000100000 | Loss 0.011447 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:26 Epoch 4 | Batch 2626/2891 | Timestep 14190 | LR 0.0000100000 | Loss 0.006265 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:27 Epoch 4 | Batch 2636/2891 | Timestep 14200 | LR 0.0000100000 | Loss 0.028551 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:29 Epoch 4 | Batch 2646/2891 | Timestep 14210 | LR 0.0000100000 | Loss 0.002920 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:31 Epoch 4 | Batch 2656/2891 | Timestep 14220 | LR 0.0000100000 | Loss 0.006268 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:33 Epoch 4 | Batch 2666/2891 | Timestep 14230 | LR 0.0000100000 | Loss 0.073158 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:35 Epoch 4 | Batch 2676/2891 | Timestep 14240 | LR 0.0000100000 | Loss 0.011441 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:36 Epoch 4 | Batch 2686/2891 | Timestep 14250 | LR 0.0000100000 | Loss 0.046024 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:38 Epoch 4 | Batch 2696/2891 | Timestep 14260 | LR 0.0000100000 | Loss 0.017320 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:40 Epoch 4 | Batch 2706/2891 | Timestep 14270 | LR 0.0000100000 | Loss 0.023761 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:42 Epoch 4 | Batch 2716/2891 | Timestep 14280 | LR 0.0000100000 | Loss 0.030744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:43 Epoch 4 | Batch 2726/2891 | Timestep 14290 | LR 0.0000100000 | Loss 0.020189 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:45 Epoch 4 | Batch 2736/2891 | Timestep 14300 | LR 0.0000100000 | Loss 0.001752 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:46 Epoch 4 | Batch 2746/2891 | Timestep 14310 | LR 0.0000100000 | Loss 0.015821 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:48 Epoch 4 | Batch 2756/2891 | Timestep 14320 | LR 0.0000100000 | Loss 0.004790 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:50 Epoch 4 | Batch 2766/2891 | Timestep 14330 | LR 0.0000100000 | Loss 0.014779 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:52 Epoch 4 | Batch 2776/2891 | Timestep 14340 | LR 0.0000100000 | Loss 0.066840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:53 Epoch 4 | Batch 2786/2891 | Timestep 14350 | LR 0.0000100000 | Loss 0.018176 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:55 Epoch 4 | Batch 2796/2891 | Timestep 14360 | LR 0.0000100000 | Loss 0.051433 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:57 Epoch 4 | Batch 2806/2891 | Timestep 14370 | LR 0.0000100000 | Loss 0.007765 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:48:58 Epoch 4 | Batch 2816/2891 | Timestep 14380 | LR 0.0000100000 | Loss 0.034822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:00 Epoch 4 | Batch 2826/2891 | Timestep 14390 | LR 0.0000100000 | Loss 0.037075 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:01 Epoch 4 | Batch 2836/2891 | Timestep 14400 | LR 0.0000100000 | Loss 0.003281 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:03 Epoch 4 | Batch 2846/2891 | Timestep 14410 | LR 0.0000100000 | Loss 0.019643 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:05 Epoch 4 | Batch 2856/2891 | Timestep 14420 | LR 0.0000100000 | Loss 0.017428 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:07 Epoch 4 | Batch 2866/2891 | Timestep 14430 | LR 0.0000100000 | Loss 0.003399 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:08 Epoch 4 | Batch 2876/2891 | Timestep 14440 | LR 0.0000100000 | Loss 0.025696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:10 Epoch 4 | Batch 2886/2891 | Timestep 14450 | LR 0.0000100000 | Loss 0.004034 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:11 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:49:28 precision recall f1-score support CARDINAL 0.8481 0.7882 0.8171 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.8478 0.8712 0.8594 1592 EVENT 0.6731 0.7447 0.7071 282 FAC 0.6167 0.8043 0.6981 92 GPE 0.8845 0.9182 0.9010 1051 LANGUAGE 0.5417 0.8125 0.6500 16 LAW 0.5000 0.6809 0.5766 47 LOC 0.6471 0.7432 0.6918 74 MONEY 0.7778 0.9545 0.8571 22 NORP 0.6744 0.7461 0.7084 508 OCC 0.8528 0.8677 0.8602 514 ORDINAL 0.9257 0.9236 0.9246 445 ORG 0.8820 0.9138 0.8976 1578 PERCENT 0.8462 0.9167 0.8800 12 PERS 0.9468 0.9576 0.9521 613 PRODUCT 0.4000 0.2500 0.3077 8 QUANTITY 0.5000 0.6667 0.5714 3 TIME 0.6765 0.6970 0.6866 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.3600 0.5625 0.4390 80 micro avg 0.8339 0.8734 0.8532 7143 macro avg 0.6381 0.7057 0.6660 7143 weighted avg 0.8397 0.8734 0.8556 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:29 Epoch 4 | Timestep 14455 | Train Loss 0.017854 | Val Loss 0.048143 | F1 0.853197 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:30 Epoch 5 | Batch 5/2891 | Timestep 14460 | LR 0.0000100000 | Loss 0.001758 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:31 Epoch 5 | Batch 15/2891 | Timestep 14470 | LR 0.0000100000 | Loss 0.015774 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:33 Epoch 5 | Batch 25/2891 | Timestep 14480 | LR 0.0000100000 | Loss 0.008822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:35 Epoch 5 | Batch 35/2891 | Timestep 14490 | LR 0.0000100000 | Loss 0.135933 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:36 Epoch 5 | Batch 45/2891 | Timestep 14500 | LR 0.0000100000 | Loss 0.003508 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:38 Epoch 5 | Batch 55/2891 | Timestep 14510 | LR 0.0000100000 | Loss 0.026265 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:40 Epoch 5 | Batch 65/2891 | Timestep 14520 | LR 0.0000100000 | Loss 0.057555 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:41 Epoch 5 | Batch 75/2891 | Timestep 14530 | LR 0.0000100000 | Loss 0.012942 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:43 Epoch 5 | Batch 85/2891 | Timestep 14540 | LR 0.0000100000 | Loss 0.002059 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:44 Epoch 5 | Batch 95/2891 | Timestep 14550 | LR 0.0000100000 | Loss 0.057900 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:46 Epoch 5 | Batch 105/2891 | Timestep 14560 | LR 0.0000100000 | Loss 0.025313 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:48 Epoch 5 | Batch 115/2891 | Timestep 14570 | LR 0.0000100000 | Loss 0.008676 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:50 Epoch 5 | Batch 125/2891 | Timestep 14580 | LR 0.0000100000 | Loss 0.004278 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:52 Epoch 5 | Batch 135/2891 | Timestep 14590 | LR 0.0000100000 | Loss 0.015854 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:54 Epoch 5 | Batch 145/2891 | Timestep 14600 | LR 0.0000100000 | Loss 0.003702 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:55 Epoch 5 | Batch 155/2891 | Timestep 14610 | LR 0.0000100000 | Loss 0.011584 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:57 Epoch 5 | Batch 165/2891 | Timestep 14620 | LR 0.0000100000 | Loss 0.002474 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:49:58 Epoch 5 | Batch 175/2891 | Timestep 14630 | LR 0.0000100000 | Loss 0.017237 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:00 Epoch 5 | Batch 185/2891 | Timestep 14640 | LR 0.0000100000 | Loss 0.016344 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:01 Epoch 5 | Batch 195/2891 | Timestep 14650 | LR 0.0000100000 | Loss 0.006891 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:03 Epoch 5 | Batch 205/2891 | Timestep 14660 | LR 0.0000100000 | Loss 0.006006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:05 Epoch 5 | Batch 215/2891 | Timestep 14670 | LR 0.0000100000 | Loss 0.005432 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:07 Epoch 5 | Batch 225/2891 | Timestep 14680 | LR 0.0000100000 | Loss 0.016170 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:08 Epoch 5 | Batch 235/2891 | Timestep 14690 | LR 0.0000100000 | Loss 0.020845 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:10 Epoch 5 | Batch 245/2891 | Timestep 14700 | LR 0.0000100000 | Loss 0.029262 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:12 Epoch 5 | Batch 255/2891 | Timestep 14710 | LR 0.0000100000 | Loss 0.016021 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:14 Epoch 5 | Batch 265/2891 | Timestep 14720 | LR 0.0000100000 | Loss 0.048489 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:15 Epoch 5 | Batch 275/2891 | Timestep 14730 | LR 0.0000100000 | Loss 0.006653 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:17 Epoch 5 | Batch 285/2891 | Timestep 14740 | LR 0.0000100000 | Loss 0.026653 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:19 Epoch 5 | Batch 295/2891 | Timestep 14750 | LR 0.0000100000 | Loss 0.001185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:21 Epoch 5 | Batch 305/2891 | Timestep 14760 | LR 0.0000100000 | Loss 0.006790 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:22 Epoch 5 | Batch 315/2891 | Timestep 14770 | LR 0.0000100000 | Loss 0.010708 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:25 Epoch 5 | Batch 325/2891 | Timestep 14780 | LR 0.0000100000 | Loss 0.008575 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:26 Epoch 5 | Batch 335/2891 | Timestep 14790 | LR 0.0000100000 | Loss 0.041683 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:28 Epoch 5 | Batch 345/2891 | Timestep 14800 | LR 0.0000100000 | Loss 0.035930 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:30 Epoch 5 | Batch 355/2891 | Timestep 14810 | LR 0.0000100000 | Loss 0.009391 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:32 Epoch 5 | Batch 365/2891 | Timestep 14820 | LR 0.0000100000 | Loss 0.015665 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:33 Epoch 5 | Batch 375/2891 | Timestep 14830 | LR 0.0000100000 | Loss 0.020302 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:35 Epoch 5 | Batch 385/2891 | Timestep 14840 | LR 0.0000100000 | Loss 0.081035 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:37 Epoch 5 | Batch 395/2891 | Timestep 14850 | LR 0.0000100000 | Loss 0.008729 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:39 Epoch 5 | Batch 405/2891 | Timestep 14860 | LR 0.0000100000 | Loss 0.016572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:41 Epoch 5 | Batch 415/2891 | Timestep 14870 | LR 0.0000100000 | Loss 0.041277 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:42 Epoch 5 | Batch 425/2891 | Timestep 14880 | LR 0.0000100000 | Loss 0.033163 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:44 Epoch 5 | Batch 435/2891 | Timestep 14890 | LR 0.0000100000 | Loss 0.005677 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:45 Epoch 5 | Batch 445/2891 | Timestep 14900 | LR 0.0000100000 | Loss 0.015448 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:47 Epoch 5 | Batch 455/2891 | Timestep 14910 | LR 0.0000100000 | Loss 0.024562 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:49 Epoch 5 | Batch 465/2891 | Timestep 14920 | LR 0.0000100000 | Loss 0.013189 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:50 Epoch 5 | Batch 475/2891 | Timestep 14930 | LR 0.0000100000 | Loss 0.018454 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:52 Epoch 5 | Batch 485/2891 | Timestep 14940 | LR 0.0000100000 | Loss 0.013656 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:53 Epoch 5 | Batch 495/2891 | Timestep 14950 | LR 0.0000100000 | Loss 0.010815 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:55 Epoch 5 | Batch 505/2891 | Timestep 14960 | LR 0.0000100000 | Loss 0.009309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:57 Epoch 5 | Batch 515/2891 | Timestep 14970 | LR 0.0000100000 | Loss 0.004937 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:50:58 Epoch 5 | Batch 525/2891 | Timestep 14980 | LR 0.0000100000 | Loss 0.011694 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:00 Epoch 5 | Batch 535/2891 | Timestep 14990 | LR 0.0000100000 | Loss 0.028236 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:02 Epoch 5 | Batch 545/2891 | Timestep 15000 | LR 0.0000100000 | Loss 0.007476 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:03 Epoch 5 | Batch 555/2891 | Timestep 15010 | LR 0.0000100000 | Loss 0.011794 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:04 Epoch 5 | Batch 565/2891 | Timestep 15020 | LR 0.0000100000 | Loss 0.013498 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:06 Epoch 5 | Batch 575/2891 | Timestep 15030 | LR 0.0000100000 | Loss 0.026281 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:08 Epoch 5 | Batch 585/2891 | Timestep 15040 | LR 0.0000100000 | Loss 0.009560 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:09 Epoch 5 | Batch 595/2891 | Timestep 15050 | LR 0.0000100000 | Loss 0.007051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:11 Epoch 5 | Batch 605/2891 | Timestep 15060 | LR 0.0000100000 | Loss 0.029240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:12 Epoch 5 | Batch 615/2891 | Timestep 15070 | LR 0.0000100000 | Loss 0.001896 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:14 Epoch 5 | Batch 625/2891 | Timestep 15080 | LR 0.0000100000 | Loss 0.015363 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:16 Epoch 5 | Batch 635/2891 | Timestep 15090 | LR 0.0000100000 | Loss 0.028840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:18 Epoch 5 | Batch 645/2891 | Timestep 15100 | LR 0.0000100000 | Loss 0.009179 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:20 Epoch 5 | Batch 655/2891 | Timestep 15110 | LR 0.0000100000 | Loss 0.009308 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:22 Epoch 5 | Batch 665/2891 | Timestep 15120 | LR 0.0000100000 | Loss 0.002453 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:23 Epoch 5 | Batch 675/2891 | Timestep 15130 | LR 0.0000100000 | Loss 0.079228 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:25 Epoch 5 | Batch 685/2891 | Timestep 15140 | LR 0.0000100000 | Loss 0.026696 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:26 Epoch 5 | Batch 695/2891 | Timestep 15150 | LR 0.0000100000 | Loss 0.004735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:28 Epoch 5 | Batch 705/2891 | Timestep 15160 | LR 0.0000100000 | Loss 0.005343 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:29 Epoch 5 | Batch 715/2891 | Timestep 15170 | LR 0.0000100000 | Loss 0.037226 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:31 Epoch 5 | Batch 725/2891 | Timestep 15180 | LR 0.0000100000 | Loss 0.019578 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:33 Epoch 5 | Batch 735/2891 | Timestep 15190 | LR 0.0000100000 | Loss 0.011113 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:34 Epoch 5 | Batch 745/2891 | Timestep 15200 | LR 0.0000100000 | Loss 0.011193 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:36 Epoch 5 | Batch 755/2891 | Timestep 15210 | LR 0.0000100000 | Loss 0.024707 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:37 Epoch 5 | Batch 765/2891 | Timestep 15220 | LR 0.0000100000 | Loss 0.030566 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:39 Epoch 5 | Batch 775/2891 | Timestep 15230 | LR 0.0000100000 | Loss 0.003330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:41 Epoch 5 | Batch 785/2891 | Timestep 15240 | LR 0.0000100000 | Loss 0.010079 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:42 Epoch 5 | Batch 795/2891 | Timestep 15250 | LR 0.0000100000 | Loss 0.016474 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:44 Epoch 5 | Batch 805/2891 | Timestep 15260 | LR 0.0000100000 | Loss 0.024843 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:46 Epoch 5 | Batch 815/2891 | Timestep 15270 | LR 0.0000100000 | Loss 0.006307 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:48 Epoch 5 | Batch 825/2891 | Timestep 15280 | LR 0.0000100000 | Loss 0.027147 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:50 Epoch 5 | Batch 835/2891 | Timestep 15290 | LR 0.0000100000 | Loss 0.011577 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:52 Epoch 5 | Batch 845/2891 | Timestep 15300 | LR 0.0000100000 | Loss 0.029203 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:53 Epoch 5 | Batch 855/2891 | Timestep 15310 | LR 0.0000100000 | Loss 0.010508 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:55 Epoch 5 | Batch 865/2891 | Timestep 15320 | LR 0.0000100000 | Loss 0.005164 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:57 Epoch 5 | Batch 875/2891 | Timestep 15330 | LR 0.0000100000 | Loss 0.003619 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:51:58 Epoch 5 | Batch 885/2891 | Timestep 15340 | LR 0.0000100000 | Loss 0.081594 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:00 Epoch 5 | Batch 895/2891 | Timestep 15350 | LR 0.0000100000 | Loss 0.008204 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:02 Epoch 5 | Batch 905/2891 | Timestep 15360 | LR 0.0000100000 | Loss 0.005892 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:04 Epoch 5 | Batch 915/2891 | Timestep 15370 | LR 0.0000100000 | Loss 0.013451 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:05 Epoch 5 | Batch 925/2891 | Timestep 15380 | LR 0.0000100000 | Loss 0.025340 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:07 Epoch 5 | Batch 935/2891 | Timestep 15390 | LR 0.0000100000 | Loss 0.004967 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:08 Epoch 5 | Batch 945/2891 | Timestep 15400 | LR 0.0000100000 | Loss 0.015228 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:09 Epoch 5 | Batch 955/2891 | Timestep 15410 | LR 0.0000100000 | Loss 0.050660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:11 Epoch 5 | Batch 965/2891 | Timestep 15420 | LR 0.0000100000 | Loss 0.015341 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:13 Epoch 5 | Batch 975/2891 | Timestep 15430 | LR 0.0000100000 | Loss 0.012397 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:15 Epoch 5 | Batch 985/2891 | Timestep 15440 | LR 0.0000100000 | Loss 0.020360 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:16 Epoch 5 | Batch 995/2891 | Timestep 15450 | LR 0.0000100000 | Loss 0.009421 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:18 Epoch 5 | Batch 1005/2891 | Timestep 15460 | LR 0.0000100000 | Loss 0.004145 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:19 Epoch 5 | Batch 1015/2891 | Timestep 15470 | LR 0.0000100000 | Loss 0.023037 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:21 Epoch 5 | Batch 1025/2891 | Timestep 15480 | LR 0.0000100000 | Loss 0.005264 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:23 Epoch 5 | Batch 1035/2891 | Timestep 15490 | LR 0.0000100000 | Loss 0.085747 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:25 Epoch 5 | Batch 1045/2891 | Timestep 15500 | LR 0.0000100000 | Loss 0.018583 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:26 Epoch 5 | Batch 1055/2891 | Timestep 15510 | LR 0.0000100000 | Loss 0.015292 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:28 Epoch 5 | Batch 1065/2891 | Timestep 15520 | LR 0.0000100000 | Loss 0.019943 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:30 Epoch 5 | Batch 1075/2891 | Timestep 15530 | LR 0.0000100000 | Loss 0.027402 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:31 Epoch 5 | Batch 1085/2891 | Timestep 15540 | LR 0.0000100000 | Loss 0.056467 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:33 Epoch 5 | Batch 1095/2891 | Timestep 15550 | LR 0.0000100000 | Loss 0.015247 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:35 Epoch 5 | Batch 1105/2891 | Timestep 15560 | LR 0.0000100000 | Loss 0.028520 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:37 Epoch 5 | Batch 1115/2891 | Timestep 15570 | LR 0.0000100000 | Loss 0.033680 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:38 Epoch 5 | Batch 1125/2891 | Timestep 15580 | LR 0.0000100000 | Loss 0.023063 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:40 Epoch 5 | Batch 1135/2891 | Timestep 15590 | LR 0.0000100000 | Loss 0.005453 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:42 Epoch 5 | Batch 1145/2891 | Timestep 15600 | LR 0.0000100000 | Loss 0.015291 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:44 Epoch 5 | Batch 1155/2891 | Timestep 15610 | LR 0.0000100000 | Loss 0.024165 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:45 Epoch 5 | Batch 1165/2891 | Timestep 15620 | LR 0.0000100000 | Loss 0.046560 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:47 Epoch 5 | Batch 1175/2891 | Timestep 15630 | LR 0.0000100000 | Loss 0.018201 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:49 Epoch 5 | Batch 1185/2891 | Timestep 15640 | LR 0.0000100000 | Loss 0.080118 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:50 Epoch 5 | Batch 1195/2891 | Timestep 15650 | LR 0.0000100000 | Loss 0.016735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:52 Epoch 5 | Batch 1205/2891 | Timestep 15660 | LR 0.0000100000 | Loss 0.034009 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:55 Epoch 5 | Batch 1215/2891 | Timestep 15670 | LR 0.0000100000 | Loss 0.003313 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:56 Epoch 5 | Batch 1225/2891 | Timestep 15680 | LR 0.0000100000 | Loss 0.010783 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:52:58 Epoch 5 | Batch 1235/2891 | Timestep 15690 | LR 0.0000100000 | Loss 0.047931 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:00 Epoch 5 | Batch 1245/2891 | Timestep 15700 | LR 0.0000100000 | Loss 0.023173 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:01 Epoch 5 | Batch 1255/2891 | Timestep 15710 | LR 0.0000100000 | Loss 0.009373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:03 Epoch 5 | Batch 1265/2891 | Timestep 15720 | LR 0.0000100000 | Loss 0.010207 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:05 Epoch 5 | Batch 1275/2891 | Timestep 15730 | LR 0.0000100000 | Loss 0.016025 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:06 Epoch 5 | Batch 1285/2891 | Timestep 15740 | LR 0.0000100000 | Loss 0.044778 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:09 Epoch 5 | Batch 1295/2891 | Timestep 15750 | LR 0.0000100000 | Loss 0.004213 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:10 Epoch 5 | Batch 1305/2891 | Timestep 15760 | LR 0.0000100000 | Loss 0.079732 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:12 Epoch 5 | Batch 1315/2891 | Timestep 15770 | LR 0.0000100000 | Loss 0.020235 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:14 Epoch 5 | Batch 1325/2891 | Timestep 15780 | LR 0.0000100000 | Loss 0.024894 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:17 Epoch 5 | Batch 1335/2891 | Timestep 15790 | LR 0.0000100000 | Loss 0.001693 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:18 Epoch 5 | Batch 1345/2891 | Timestep 15800 | LR 0.0000100000 | Loss 0.010857 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:20 Epoch 5 | Batch 1355/2891 | Timestep 15810 | LR 0.0000100000 | Loss 0.054798 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:21 Epoch 5 | Batch 1365/2891 | Timestep 15820 | LR 0.0000100000 | Loss 0.021667 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:23 Epoch 5 | Batch 1375/2891 | Timestep 15830 | LR 0.0000100000 | Loss 0.010561 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:25 Epoch 5 | Batch 1385/2891 | Timestep 15840 | LR 0.0000100000 | Loss 0.010511 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:27 Epoch 5 | Batch 1395/2891 | Timestep 15850 | LR 0.0000100000 | Loss 0.017957 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:29 Epoch 5 | Batch 1405/2891 | Timestep 15860 | LR 0.0000100000 | Loss 0.010738 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:30 Epoch 5 | Batch 1415/2891 | Timestep 15870 | LR 0.0000100000 | Loss 0.010108 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:32 Epoch 5 | Batch 1425/2891 | Timestep 15880 | LR 0.0000100000 | Loss 0.024409 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:34 Epoch 5 | Batch 1435/2891 | Timestep 15890 | LR 0.0000100000 | Loss 0.021332 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:35 Epoch 5 | Batch 1445/2891 | Timestep 15900 | LR 0.0000100000 | Loss 0.001503 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:37 Epoch 5 | Batch 1455/2891 | Timestep 15910 | LR 0.0000100000 | Loss 0.002871 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:39 Epoch 5 | Batch 1465/2891 | Timestep 15920 | LR 0.0000100000 | Loss 0.006059 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:40 Epoch 5 | Batch 1475/2891 | Timestep 15930 | LR 0.0000100000 | Loss 0.036680 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:42 Epoch 5 | Batch 1485/2891 | Timestep 15940 | LR 0.0000100000 | Loss 0.012132 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:43 Epoch 5 | Batch 1495/2891 | Timestep 15950 | LR 0.0000100000 | Loss 0.012530 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:45 Epoch 5 | Batch 1505/2891 | Timestep 15960 | LR 0.0000100000 | Loss 0.006098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:46 Epoch 5 | Batch 1515/2891 | Timestep 15970 | LR 0.0000100000 | Loss 0.011202 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:48 Epoch 5 | Batch 1525/2891 | Timestep 15980 | LR 0.0000100000 | Loss 0.003980 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:50 Epoch 5 | Batch 1535/2891 | Timestep 15990 | LR 0.0000100000 | Loss 0.020002 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:52 Epoch 5 | Batch 1545/2891 | Timestep 16000 | LR 0.0000100000 | Loss 0.008129 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:53 Epoch 5 | Batch 1555/2891 | Timestep 16010 | LR 0.0000100000 | Loss 0.005639 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:55 Epoch 5 | Batch 1565/2891 | Timestep 16020 | LR 0.0000100000 | Loss 0.025010 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:57 Epoch 5 | Batch 1575/2891 | Timestep 16030 | LR 0.0000100000 | Loss 0.005458 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:53:58 Epoch 5 | Batch 1585/2891 | Timestep 16040 | LR 0.0000100000 | Loss 0.028660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:00 Epoch 5 | Batch 1595/2891 | Timestep 16050 | LR 0.0000100000 | Loss 0.011664 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:01 Epoch 5 | Batch 1605/2891 | Timestep 16060 | LR 0.0000100000 | Loss 0.027802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:03 Epoch 5 | Batch 1615/2891 | Timestep 16070 | LR 0.0000100000 | Loss 0.030030 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:05 Epoch 5 | Batch 1625/2891 | Timestep 16080 | LR 0.0000100000 | Loss 0.013482 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:06 Epoch 5 | Batch 1635/2891 | Timestep 16090 | LR 0.0000100000 | Loss 0.028242 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:08 Epoch 5 | Batch 1645/2891 | Timestep 16100 | LR 0.0000100000 | Loss 0.012425 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:10 Epoch 5 | Batch 1655/2891 | Timestep 16110 | LR 0.0000100000 | Loss 0.011911 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:11 Epoch 5 | Batch 1665/2891 | Timestep 16120 | LR 0.0000100000 | Loss 0.012772 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:13 Epoch 5 | Batch 1675/2891 | Timestep 16130 | LR 0.0000100000 | Loss 0.003155 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:14 Epoch 5 | Batch 1685/2891 | Timestep 16140 | LR 0.0000100000 | Loss 0.014087 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:16 Epoch 5 | Batch 1695/2891 | Timestep 16150 | LR 0.0000100000 | Loss 0.028496 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:18 Epoch 5 | Batch 1705/2891 | Timestep 16160 | LR 0.0000100000 | Loss 0.018832 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:20 Epoch 5 | Batch 1715/2891 | Timestep 16170 | LR 0.0000100000 | Loss 0.017120 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:22 Epoch 5 | Batch 1725/2891 | Timestep 16180 | LR 0.0000100000 | Loss 0.007036 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:24 Epoch 5 | Batch 1735/2891 | Timestep 16190 | LR 0.0000100000 | Loss 0.025463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:25 Epoch 5 | Batch 1745/2891 | Timestep 16200 | LR 0.0000100000 | Loss 0.034719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:28 Epoch 5 | Batch 1755/2891 | Timestep 16210 | LR 0.0000100000 | Loss 0.003623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:29 Epoch 5 | Batch 1765/2891 | Timestep 16220 | LR 0.0000100000 | Loss 0.000570 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:31 Epoch 5 | Batch 1775/2891 | Timestep 16230 | LR 0.0000100000 | Loss 0.004129 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:33 Epoch 5 | Batch 1785/2891 | Timestep 16240 | LR 0.0000100000 | Loss 0.003721 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:35 Epoch 5 | Batch 1795/2891 | Timestep 16250 | LR 0.0000100000 | Loss 0.022717 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:37 Epoch 5 | Batch 1805/2891 | Timestep 16260 | LR 0.0000100000 | Loss 0.023219 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:39 Epoch 5 | Batch 1815/2891 | Timestep 16270 | LR 0.0000100000 | Loss 0.010957 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:40 Epoch 5 | Batch 1825/2891 | Timestep 16280 | LR 0.0000100000 | Loss 0.007877 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:42 Epoch 5 | Batch 1835/2891 | Timestep 16290 | LR 0.0000100000 | Loss 0.010889 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:43 Epoch 5 | Batch 1845/2891 | Timestep 16300 | LR 0.0000100000 | Loss 0.006361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:45 Epoch 5 | Batch 1855/2891 | Timestep 16310 | LR 0.0000100000 | Loss 0.004885 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:46 Epoch 5 | Batch 1865/2891 | Timestep 16320 | LR 0.0000100000 | Loss 0.004111 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:48 Epoch 5 | Batch 1875/2891 | Timestep 16330 | LR 0.0000100000 | Loss 0.009132 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:50 Epoch 5 | Batch 1885/2891 | Timestep 16340 | LR 0.0000100000 | Loss 0.028926 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:51 Epoch 5 | Batch 1895/2891 | Timestep 16350 | LR 0.0000100000 | Loss 0.021934 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:53 Epoch 5 | Batch 1905/2891 | Timestep 16360 | LR 0.0000100000 | Loss 0.016126 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:55 Epoch 5 | Batch 1915/2891 | Timestep 16370 | LR 0.0000100000 | Loss 0.004523 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:57 Epoch 5 | Batch 1925/2891 | Timestep 16380 | LR 0.0000100000 | Loss 0.020094 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:54:58 Epoch 5 | Batch 1935/2891 | Timestep 16390 | LR 0.0000100000 | Loss 0.014084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:00 Epoch 5 | Batch 1945/2891 | Timestep 16400 | LR 0.0000100000 | Loss 0.010645 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:02 Epoch 5 | Batch 1955/2891 | Timestep 16410 | LR 0.0000100000 | Loss 0.050074 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:04 Epoch 5 | Batch 1965/2891 | Timestep 16420 | LR 0.0000100000 | Loss 0.017318 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:05 Epoch 5 | Batch 1975/2891 | Timestep 16430 | LR 0.0000100000 | Loss 0.007216 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:07 Epoch 5 | Batch 1985/2891 | Timestep 16440 | LR 0.0000100000 | Loss 0.052573 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:08 Epoch 5 | Batch 1995/2891 | Timestep 16450 | LR 0.0000100000 | Loss 0.016660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:10 Epoch 5 | Batch 2005/2891 | Timestep 16460 | LR 0.0000100000 | Loss 0.043272 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:11 Epoch 5 | Batch 2015/2891 | Timestep 16470 | LR 0.0000100000 | Loss 0.018089 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:13 Epoch 5 | Batch 2025/2891 | Timestep 16480 | LR 0.0000100000 | Loss 0.001576 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:15 Epoch 5 | Batch 2035/2891 | Timestep 16490 | LR 0.0000100000 | Loss 0.006606 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:16 Epoch 5 | Batch 2045/2891 | Timestep 16500 | LR 0.0000100000 | Loss 0.008128 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:18 Epoch 5 | Batch 2055/2891 | Timestep 16510 | LR 0.0000100000 | Loss 0.013358 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:19 Epoch 5 | Batch 2065/2891 | Timestep 16520 | LR 0.0000100000 | Loss 0.055487 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:20 Epoch 5 | Batch 2075/2891 | Timestep 16530 | LR 0.0000100000 | Loss 0.033102 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:22 Epoch 5 | Batch 2085/2891 | Timestep 16540 | LR 0.0000100000 | Loss 0.021268 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:23 Epoch 5 | Batch 2095/2891 | Timestep 16550 | LR 0.0000100000 | Loss 0.045878 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:26 Epoch 5 | Batch 2105/2891 | Timestep 16560 | LR 0.0000100000 | Loss 0.015797 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:27 Epoch 5 | Batch 2115/2891 | Timestep 16570 | LR 0.0000100000 | Loss 0.014978 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:28 Epoch 5 | Batch 2125/2891 | Timestep 16580 | LR 0.0000100000 | Loss 0.021432 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:30 Epoch 5 | Batch 2135/2891 | Timestep 16590 | LR 0.0000100000 | Loss 0.009571 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:32 Epoch 5 | Batch 2145/2891 | Timestep 16600 | LR 0.0000100000 | Loss 0.014279 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:34 Epoch 5 | Batch 2155/2891 | Timestep 16610 | LR 0.0000100000 | Loss 0.035257 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:36 Epoch 5 | Batch 2165/2891 | Timestep 16620 | LR 0.0000100000 | Loss 0.002691 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:37 Epoch 5 | Batch 2175/2891 | Timestep 16630 | LR 0.0000100000 | Loss 0.029740 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:39 Epoch 5 | Batch 2185/2891 | Timestep 16640 | LR 0.0000100000 | Loss 0.003704 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:40 Epoch 5 | Batch 2195/2891 | Timestep 16650 | LR 0.0000100000 | Loss 0.040386 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:42 Epoch 5 | Batch 2205/2891 | Timestep 16660 | LR 0.0000100000 | Loss 0.046896 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:43 Epoch 5 | Batch 2215/2891 | Timestep 16670 | LR 0.0000100000 | Loss 0.011576 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:46 Epoch 5 | Batch 2225/2891 | Timestep 16680 | LR 0.0000100000 | Loss 0.015465 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:47 Epoch 5 | Batch 2235/2891 | Timestep 16690 | LR 0.0000100000 | Loss 0.008020 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:49 Epoch 5 | Batch 2245/2891 | Timestep 16700 | LR 0.0000100000 | Loss 0.011146 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:51 Epoch 5 | Batch 2255/2891 | Timestep 16710 | LR 0.0000100000 | Loss 0.054411 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:53 Epoch 5 | Batch 2265/2891 | Timestep 16720 | LR 0.0000100000 | Loss 0.015176 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:54 Epoch 5 | Batch 2275/2891 | Timestep 16730 | LR 0.0000100000 | Loss 0.009998 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:56 Epoch 5 | Batch 2285/2891 | Timestep 16740 | LR 0.0000100000 | Loss 0.004724 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:57 Epoch 5 | Batch 2295/2891 | Timestep 16750 | LR 0.0000100000 | Loss 0.046383 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:55:59 Epoch 5 | Batch 2305/2891 | Timestep 16760 | LR 0.0000100000 | Loss 0.069759 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:01 Epoch 5 | Batch 2315/2891 | Timestep 16770 | LR 0.0000100000 | Loss 0.010468 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:03 Epoch 5 | Batch 2325/2891 | Timestep 16780 | LR 0.0000100000 | Loss 0.006560 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:04 Epoch 5 | Batch 2335/2891 | Timestep 16790 | LR 0.0000100000 | Loss 0.011608 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:06 Epoch 5 | Batch 2345/2891 | Timestep 16800 | LR 0.0000100000 | Loss 0.008183 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:08 Epoch 5 | Batch 2355/2891 | Timestep 16810 | LR 0.0000100000 | Loss 0.015714 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:09 Epoch 5 | Batch 2365/2891 | Timestep 16820 | LR 0.0000100000 | Loss 0.012970 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:11 Epoch 5 | Batch 2375/2891 | Timestep 16830 | LR 0.0000100000 | Loss 0.013356 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:13 Epoch 5 | Batch 2385/2891 | Timestep 16840 | LR 0.0000100000 | Loss 0.006522 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:14 Epoch 5 | Batch 2395/2891 | Timestep 16850 | LR 0.0000100000 | Loss 0.001153 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:16 Epoch 5 | Batch 2405/2891 | Timestep 16860 | LR 0.0000100000 | Loss 0.006748 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:18 Epoch 5 | Batch 2415/2891 | Timestep 16870 | LR 0.0000100000 | Loss 0.007158 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:19 Epoch 5 | Batch 2425/2891 | Timestep 16880 | LR 0.0000100000 | Loss 0.014962 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:21 Epoch 5 | Batch 2435/2891 | Timestep 16890 | LR 0.0000100000 | Loss 0.008176 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:22 Epoch 5 | Batch 2445/2891 | Timestep 16900 | LR 0.0000100000 | Loss 0.009119 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:24 Epoch 5 | Batch 2455/2891 | Timestep 16910 | LR 0.0000100000 | Loss 0.005029 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:25 Epoch 5 | Batch 2465/2891 | Timestep 16920 | LR 0.0000100000 | Loss 0.008951 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:27 Epoch 5 | Batch 2475/2891 | Timestep 16930 | LR 0.0000100000 | Loss 0.016024 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:29 Epoch 5 | Batch 2485/2891 | Timestep 16940 | LR 0.0000100000 | Loss 0.006707 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:30 Epoch 5 | Batch 2495/2891 | Timestep 16950 | LR 0.0000100000 | Loss 0.004627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:32 Epoch 5 | Batch 2505/2891 | Timestep 16960 | LR 0.0000100000 | Loss 0.025502 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:33 Epoch 5 | Batch 2515/2891 | Timestep 16970 | LR 0.0000100000 | Loss 0.010874 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:35 Epoch 5 | Batch 2525/2891 | Timestep 16980 | LR 0.0000100000 | Loss 0.040775 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:37 Epoch 5 | Batch 2535/2891 | Timestep 16990 | LR 0.0000100000 | Loss 0.009100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:38 Epoch 5 | Batch 2545/2891 | Timestep 17000 | LR 0.0000100000 | Loss 0.008042 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:40 Epoch 5 | Batch 2555/2891 | Timestep 17010 | LR 0.0000100000 | Loss 0.014766 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:42 Epoch 5 | Batch 2565/2891 | Timestep 17020 | LR 0.0000100000 | Loss 0.033252 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:43 Epoch 5 | Batch 2575/2891 | Timestep 17030 | LR 0.0000100000 | Loss 0.010991 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:45 Epoch 5 | Batch 2585/2891 | Timestep 17040 | LR 0.0000100000 | Loss 0.000730 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:47 Epoch 5 | Batch 2595/2891 | Timestep 17050 | LR 0.0000100000 | Loss 0.004522 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:48 Epoch 5 | Batch 2605/2891 | Timestep 17060 | LR 0.0000100000 | Loss 0.004286 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:50 Epoch 5 | Batch 2615/2891 | Timestep 17070 | LR 0.0000100000 | Loss 0.012297 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:52 Epoch 5 | Batch 2625/2891 | Timestep 17080 | LR 0.0000100000 | Loss 0.006491 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:53 Epoch 5 | Batch 2635/2891 | Timestep 17090 | LR 0.0000100000 | Loss 0.020945 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:55 Epoch 5 | Batch 2645/2891 | Timestep 17100 | LR 0.0000100000 | Loss 0.013627 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:56 Epoch 5 | Batch 2655/2891 | Timestep 17110 | LR 0.0000100000 | Loss 0.008921 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:58 Epoch 5 | Batch 2665/2891 | Timestep 17120 | LR 0.0000100000 | Loss 0.043020 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:56:59 Epoch 5 | Batch 2675/2891 | Timestep 17130 | LR 0.0000100000 | Loss 0.017206 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:01 Epoch 5 | Batch 2685/2891 | Timestep 17140 | LR 0.0000100000 | Loss 0.005358 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:03 Epoch 5 | Batch 2695/2891 | Timestep 17150 | LR 0.0000100000 | Loss 0.009484 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:04 Epoch 5 | Batch 2705/2891 | Timestep 17160 | LR 0.0000100000 | Loss 0.004229 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:06 Epoch 5 | Batch 2715/2891 | Timestep 17170 | LR 0.0000100000 | Loss 0.032455 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:08 Epoch 5 | Batch 2725/2891 | Timestep 17180 | LR 0.0000100000 | Loss 0.015340 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:09 Epoch 5 | Batch 2735/2891 | Timestep 17190 | LR 0.0000100000 | Loss 0.054055 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:11 Epoch 5 | Batch 2745/2891 | Timestep 17200 | LR 0.0000100000 | Loss 0.022205 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:12 Epoch 5 | Batch 2755/2891 | Timestep 17210 | LR 0.0000100000 | Loss 0.004816 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:14 Epoch 5 | Batch 2765/2891 | Timestep 17220 | LR 0.0000100000 | Loss 0.031740 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:16 Epoch 5 | Batch 2775/2891 | Timestep 17230 | LR 0.0000100000 | Loss 0.024208 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:17 Epoch 5 | Batch 2785/2891 | Timestep 17240 | LR 0.0000100000 | Loss 0.021325 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:19 Epoch 5 | Batch 2795/2891 | Timestep 17250 | LR 0.0000100000 | Loss 0.002082 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:20 Epoch 5 | Batch 2805/2891 | Timestep 17260 | LR 0.0000100000 | Loss 0.056873 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:22 Epoch 5 | Batch 2815/2891 | Timestep 17270 | LR 0.0000100000 | Loss 0.002175 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:24 Epoch 5 | Batch 2825/2891 | Timestep 17280 | LR 0.0000100000 | Loss 0.008758 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:26 Epoch 5 | Batch 2835/2891 | Timestep 17290 | LR 0.0000100000 | Loss 0.000817 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:28 Epoch 5 | Batch 2845/2891 | Timestep 17300 | LR 0.0000100000 | Loss 0.006993 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:29 Epoch 5 | Batch 2855/2891 | Timestep 17310 | LR 0.0000100000 | Loss 0.005456 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:31 Epoch 5 | Batch 2865/2891 | Timestep 17320 | LR 0.0000100000 | Loss 0.004871 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:33 Epoch 5 | Batch 2875/2891 | Timestep 17330 | LR 0.0000100000 | Loss 0.008717 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:35 Epoch 5 | Batch 2885/2891 | Timestep 17340 | LR 0.0000100000 | Loss 0.009018 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:36 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 11:57:52 precision recall f1-score support CARDINAL 0.8323 0.7882 0.8097 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.9206 0.9322 0.9263 1592 EVENT 0.6280 0.7482 0.6828 282 FAC 0.6396 0.7717 0.6995 92 GPE 0.8803 0.9163 0.8979 1051 LANGUAGE 0.5909 0.8125 0.6842 16 LAW 0.6667 0.8511 0.7477 47 LOC 0.7284 0.7973 0.7613 74 MONEY 0.6667 0.9091 0.7692 22 NORP 0.6835 0.7441 0.7125 508 OCC 0.8550 0.8716 0.8632 514 ORDINAL 0.9432 0.9326 0.9379 445 ORG 0.9003 0.9094 0.9048 1578 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9403 0.9511 0.9457 613 PRODUCT 0.3333 0.3750 0.3529 8 QUANTITY 0.5000 0.6667 0.5714 3 TIME 0.6304 0.8788 0.7342 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.6575 0.6000 0.6275 80 micro avg 0.8598 0.8887 0.8740 7143 macro avg 0.6629 0.7360 0.6947 7143 weighted avg 0.8637 0.8887 0.8754 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:54 Epoch 5 | Timestep 17346 | Train Loss 0.017976 | Val Loss 0.045366 | F1 0.874019 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:55 Epoch 6 | Batch 4/2891 | Timestep 17350 | LR 0.0000100000 | Loss 0.008799 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:56 Epoch 6 | Batch 14/2891 | Timestep 17360 | LR 0.0000100000 | Loss 0.012839 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:58 Epoch 6 | Batch 24/2891 | Timestep 17370 | LR 0.0000100000 | Loss 0.005231 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:57:59 Epoch 6 | Batch 34/2891 | Timestep 17380 | LR 0.0000100000 | Loss 0.010072 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:01 Epoch 6 | Batch 44/2891 | Timestep 17390 | LR 0.0000100000 | Loss 0.014882 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:03 Epoch 6 | Batch 54/2891 | Timestep 17400 | LR 0.0000100000 | Loss 0.003703 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:04 Epoch 6 | Batch 64/2891 | Timestep 17410 | LR 0.0000100000 | Loss 0.000603 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:06 Epoch 6 | Batch 74/2891 | Timestep 17420 | LR 0.0000100000 | Loss 0.000636 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:08 Epoch 6 | Batch 84/2891 | Timestep 17430 | LR 0.0000100000 | Loss 0.002299 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:09 Epoch 6 | Batch 94/2891 | Timestep 17440 | LR 0.0000100000 | Loss 0.009052 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:11 Epoch 6 | Batch 104/2891 | Timestep 17450 | LR 0.0000100000 | Loss 0.004439 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:14 Epoch 6 | Batch 114/2891 | Timestep 17460 | LR 0.0000100000 | Loss 0.002410 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:16 Epoch 6 | Batch 124/2891 | Timestep 17470 | LR 0.0000100000 | Loss 0.030945 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:18 Epoch 6 | Batch 134/2891 | Timestep 17480 | LR 0.0000100000 | Loss 0.003005 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:19 Epoch 6 | Batch 144/2891 | Timestep 17490 | LR 0.0000100000 | Loss 0.005210 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:22 Epoch 6 | Batch 154/2891 | Timestep 17500 | LR 0.0000100000 | Loss 0.003542 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:23 Epoch 6 | Batch 164/2891 | Timestep 17510 | LR 0.0000100000 | Loss 0.003566 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:25 Epoch 6 | Batch 174/2891 | Timestep 17520 | LR 0.0000100000 | Loss 0.025537 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:27 Epoch 6 | Batch 184/2891 | Timestep 17530 | LR 0.0000100000 | Loss 0.001164 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:29 Epoch 6 | Batch 194/2891 | Timestep 17540 | LR 0.0000100000 | Loss 0.001567 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:30 Epoch 6 | Batch 204/2891 | Timestep 17550 | LR 0.0000100000 | Loss 0.004342 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:32 Epoch 6 | Batch 214/2891 | Timestep 17560 | LR 0.0000100000 | Loss 0.006123 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:34 Epoch 6 | Batch 224/2891 | Timestep 17570 | LR 0.0000100000 | Loss 0.003486 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:35 Epoch 6 | Batch 234/2891 | Timestep 17580 | LR 0.0000100000 | Loss 0.000999 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:37 Epoch 6 | Batch 244/2891 | Timestep 17590 | LR 0.0000100000 | Loss 0.004238 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:38 Epoch 6 | Batch 254/2891 | Timestep 17600 | LR 0.0000100000 | Loss 0.001877 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:40 Epoch 6 | Batch 264/2891 | Timestep 17610 | LR 0.0000100000 | Loss 0.004342 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:41 Epoch 6 | Batch 274/2891 | Timestep 17620 | LR 0.0000100000 | Loss 0.001681 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:43 Epoch 6 | Batch 284/2891 | Timestep 17630 | LR 0.0000100000 | Loss 0.005310 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:45 Epoch 6 | Batch 294/2891 | Timestep 17640 | LR 0.0000100000 | Loss 0.009673 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:46 Epoch 6 | Batch 304/2891 | Timestep 17650 | LR 0.0000100000 | Loss 0.003040 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:48 Epoch 6 | Batch 314/2891 | Timestep 17660 | LR 0.0000100000 | Loss 0.005513 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:49 Epoch 6 | Batch 324/2891 | Timestep 17670 | LR 0.0000100000 | Loss 0.006601 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:51 Epoch 6 | Batch 334/2891 | Timestep 17680 | LR 0.0000100000 | Loss 0.020494 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:52 Epoch 6 | Batch 344/2891 | Timestep 17690 | LR 0.0000100000 | Loss 0.007340 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:54 Epoch 6 | Batch 354/2891 | Timestep 17700 | LR 0.0000100000 | Loss 0.023313 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:56 Epoch 6 | Batch 364/2891 | Timestep 17710 | LR 0.0000100000 | Loss 0.059817 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:57 Epoch 6 | Batch 374/2891 | Timestep 17720 | LR 0.0000100000 | Loss 0.002766 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:58:59 Epoch 6 | Batch 384/2891 | Timestep 17730 | LR 0.0000100000 | Loss 0.040956 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:01 Epoch 6 | Batch 394/2891 | Timestep 17740 | LR 0.0000100000 | Loss 0.029610 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:02 Epoch 6 | Batch 404/2891 | Timestep 17750 | LR 0.0000100000 | Loss 0.009955 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:04 Epoch 6 | Batch 414/2891 | Timestep 17760 | LR 0.0000100000 | Loss 0.010655 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:05 Epoch 6 | Batch 424/2891 | Timestep 17770 | LR 0.0000100000 | Loss 0.005007 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:07 Epoch 6 | Batch 434/2891 | Timestep 17780 | LR 0.0000100000 | Loss 0.007440 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:08 Epoch 6 | Batch 444/2891 | Timestep 17790 | LR 0.0000100000 | Loss 0.078147 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:10 Epoch 6 | Batch 454/2891 | Timestep 17800 | LR 0.0000100000 | Loss 0.005065 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:11 Epoch 6 | Batch 464/2891 | Timestep 17810 | LR 0.0000100000 | Loss 0.037327 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:13 Epoch 6 | Batch 474/2891 | Timestep 17820 | LR 0.0000100000 | Loss 0.027713 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:15 Epoch 6 | Batch 484/2891 | Timestep 17830 | LR 0.0000100000 | Loss 0.020046 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:17 Epoch 6 | Batch 494/2891 | Timestep 17840 | LR 0.0000100000 | Loss 0.007565 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:18 Epoch 6 | Batch 504/2891 | Timestep 17850 | LR 0.0000100000 | Loss 0.020089 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:20 Epoch 6 | Batch 514/2891 | Timestep 17860 | LR 0.0000100000 | Loss 0.007119 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:22 Epoch 6 | Batch 524/2891 | Timestep 17870 | LR 0.0000100000 | Loss 0.055639 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:24 Epoch 6 | Batch 534/2891 | Timestep 17880 | LR 0.0000100000 | Loss 0.029706 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:25 Epoch 6 | Batch 544/2891 | Timestep 17890 | LR 0.0000100000 | Loss 0.019623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:27 Epoch 6 | Batch 554/2891 | Timestep 17900 | LR 0.0000100000 | Loss 0.002494 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:29 Epoch 6 | Batch 564/2891 | Timestep 17910 | LR 0.0000100000 | Loss 0.005832 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:30 Epoch 6 | Batch 574/2891 | Timestep 17920 | LR 0.0000100000 | Loss 0.006350 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:32 Epoch 6 | Batch 584/2891 | Timestep 17930 | LR 0.0000100000 | Loss 0.015042 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:34 Epoch 6 | Batch 594/2891 | Timestep 17940 | LR 0.0000100000 | Loss 0.008548 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:35 Epoch 6 | Batch 604/2891 | Timestep 17950 | LR 0.0000100000 | Loss 0.010307 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:37 Epoch 6 | Batch 614/2891 | Timestep 17960 | LR 0.0000100000 | Loss 0.003058 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:39 Epoch 6 | Batch 624/2891 | Timestep 17970 | LR 0.0000100000 | Loss 0.039121 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:40 Epoch 6 | Batch 634/2891 | Timestep 17980 | LR 0.0000100000 | Loss 0.008472 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:42 Epoch 6 | Batch 644/2891 | Timestep 17990 | LR 0.0000100000 | Loss 0.001732 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:43 Epoch 6 | Batch 654/2891 | Timestep 18000 | LR 0.0000100000 | Loss 0.023343 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:45 Epoch 6 | Batch 664/2891 | Timestep 18010 | LR 0.0000100000 | Loss 0.047730 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:46 Epoch 6 | Batch 674/2891 | Timestep 18020 | LR 0.0000100000 | Loss 0.029773 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:48 Epoch 6 | Batch 684/2891 | Timestep 18030 | LR 0.0000100000 | Loss 0.013891 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:50 Epoch 6 | Batch 694/2891 | Timestep 18040 | LR 0.0000100000 | Loss 0.006137 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:51 Epoch 6 | Batch 704/2891 | Timestep 18050 | LR 0.0000100000 | Loss 0.005576 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:53 Epoch 6 | Batch 714/2891 | Timestep 18060 | LR 0.0000100000 | Loss 0.015972 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:56 Epoch 6 | Batch 724/2891 | Timestep 18070 | LR 0.0000100000 | Loss 0.003382 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:57 Epoch 6 | Batch 734/2891 | Timestep 18080 | LR 0.0000100000 | Loss 0.002320 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 11:59:59 Epoch 6 | Batch 744/2891 | Timestep 18090 | LR 0.0000100000 | Loss 0.003615 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:01 Epoch 6 | Batch 754/2891 | Timestep 18100 | LR 0.0000100000 | Loss 0.011402 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:02 Epoch 6 | Batch 764/2891 | Timestep 18110 | LR 0.0000100000 | Loss 0.013789 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:04 Epoch 6 | Batch 774/2891 | Timestep 18120 | LR 0.0000100000 | Loss 0.044223 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:06 Epoch 6 | Batch 784/2891 | Timestep 18130 | LR 0.0000100000 | Loss 0.006807 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:07 Epoch 6 | Batch 794/2891 | Timestep 18140 | LR 0.0000100000 | Loss 0.015154 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:09 Epoch 6 | Batch 804/2891 | Timestep 18150 | LR 0.0000100000 | Loss 0.002838 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:11 Epoch 6 | Batch 814/2891 | Timestep 18160 | LR 0.0000100000 | Loss 0.006187 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:12 Epoch 6 | Batch 824/2891 | Timestep 18170 | LR 0.0000100000 | Loss 0.012343 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:14 Epoch 6 | Batch 834/2891 | Timestep 18180 | LR 0.0000100000 | Loss 0.003228 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:16 Epoch 6 | Batch 844/2891 | Timestep 18190 | LR 0.0000100000 | Loss 0.042828 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:17 Epoch 6 | Batch 854/2891 | Timestep 18200 | LR 0.0000100000 | Loss 0.029058 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:19 Epoch 6 | Batch 864/2891 | Timestep 18210 | LR 0.0000100000 | Loss 0.015695 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:21 Epoch 6 | Batch 874/2891 | Timestep 18220 | LR 0.0000100000 | Loss 0.014535 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:22 Epoch 6 | Batch 884/2891 | Timestep 18230 | LR 0.0000100000 | Loss 0.000571 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:24 Epoch 6 | Batch 894/2891 | Timestep 18240 | LR 0.0000100000 | Loss 0.028050 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:25 Epoch 6 | Batch 904/2891 | Timestep 18250 | LR 0.0000100000 | Loss 0.011244 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:27 Epoch 6 | Batch 914/2891 | Timestep 18260 | LR 0.0000100000 | Loss 0.017251 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:28 Epoch 6 | Batch 924/2891 | Timestep 18270 | LR 0.0000100000 | Loss 0.008664 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:30 Epoch 6 | Batch 934/2891 | Timestep 18280 | LR 0.0000100000 | Loss 0.001522 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:31 Epoch 6 | Batch 944/2891 | Timestep 18290 | LR 0.0000100000 | Loss 0.026923 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:33 Epoch 6 | Batch 954/2891 | Timestep 18300 | LR 0.0000100000 | Loss 0.011570 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:34 Epoch 6 | Batch 964/2891 | Timestep 18310 | LR 0.0000100000 | Loss 0.012950 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:36 Epoch 6 | Batch 974/2891 | Timestep 18320 | LR 0.0000100000 | Loss 0.027389 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:38 Epoch 6 | Batch 984/2891 | Timestep 18330 | LR 0.0000100000 | Loss 0.038870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:39 Epoch 6 | Batch 994/2891 | Timestep 18340 | LR 0.0000100000 | Loss 0.007571 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:41 Epoch 6 | Batch 1004/2891 | Timestep 18350 | LR 0.0000100000 | Loss 0.008623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:42 Epoch 6 | Batch 1014/2891 | Timestep 18360 | LR 0.0000100000 | Loss 0.015814 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:44 Epoch 6 | Batch 1024/2891 | Timestep 18370 | LR 0.0000100000 | Loss 0.002288 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:46 Epoch 6 | Batch 1034/2891 | Timestep 18380 | LR 0.0000100000 | Loss 0.021006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:48 Epoch 6 | Batch 1044/2891 | Timestep 18390 | LR 0.0000100000 | Loss 0.011840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:50 Epoch 6 | Batch 1054/2891 | Timestep 18400 | LR 0.0000100000 | Loss 0.044809 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:53 Epoch 6 | Batch 1064/2891 | Timestep 18410 | LR 0.0000100000 | Loss 0.046361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:54 Epoch 6 | Batch 1074/2891 | Timestep 18420 | LR 0.0000100000 | Loss 0.025713 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:56 Epoch 6 | Batch 1084/2891 | Timestep 18430 | LR 0.0000100000 | Loss 0.008116 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:58 Epoch 6 | Batch 1094/2891 | Timestep 18440 | LR 0.0000100000 | Loss 0.006093 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:00:59 Epoch 6 | Batch 1104/2891 | Timestep 18450 | LR 0.0000100000 | Loss 0.015491 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:01 Epoch 6 | Batch 1114/2891 | Timestep 18460 | LR 0.0000100000 | Loss 0.003726 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:03 Epoch 6 | Batch 1124/2891 | Timestep 18470 | LR 0.0000100000 | Loss 0.005632 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:04 Epoch 6 | Batch 1134/2891 | Timestep 18480 | LR 0.0000100000 | Loss 0.020062 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:06 Epoch 6 | Batch 1144/2891 | Timestep 18490 | LR 0.0000100000 | Loss 0.020226 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:08 Epoch 6 | Batch 1154/2891 | Timestep 18500 | LR 0.0000100000 | Loss 0.031463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:10 Epoch 6 | Batch 1164/2891 | Timestep 18510 | LR 0.0000100000 | Loss 0.011779 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:12 Epoch 6 | Batch 1174/2891 | Timestep 18520 | LR 0.0000100000 | Loss 0.001398 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:14 Epoch 6 | Batch 1184/2891 | Timestep 18530 | LR 0.0000100000 | Loss 0.006092 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:16 Epoch 6 | Batch 1194/2891 | Timestep 18540 | LR 0.0000100000 | Loss 0.011438 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:17 Epoch 6 | Batch 1204/2891 | Timestep 18550 | LR 0.0000100000 | Loss 0.002468 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:19 Epoch 6 | Batch 1214/2891 | Timestep 18560 | LR 0.0000100000 | Loss 0.025068 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:21 Epoch 6 | Batch 1224/2891 | Timestep 18570 | LR 0.0000100000 | Loss 0.006140 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:22 Epoch 6 | Batch 1234/2891 | Timestep 18580 | LR 0.0000100000 | Loss 0.011279 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:24 Epoch 6 | Batch 1244/2891 | Timestep 18590 | LR 0.0000100000 | Loss 0.000994 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:26 Epoch 6 | Batch 1254/2891 | Timestep 18600 | LR 0.0000100000 | Loss 0.003883 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:28 Epoch 6 | Batch 1264/2891 | Timestep 18610 | LR 0.0000100000 | Loss 0.016027 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:29 Epoch 6 | Batch 1274/2891 | Timestep 18620 | LR 0.0000100000 | Loss 0.013150 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:31 Epoch 6 | Batch 1284/2891 | Timestep 18630 | LR 0.0000100000 | Loss 0.005304 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:33 Epoch 6 | Batch 1294/2891 | Timestep 18640 | LR 0.0000100000 | Loss 0.012884 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:35 Epoch 6 | Batch 1304/2891 | Timestep 18650 | LR 0.0000100000 | Loss 0.007726 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:37 Epoch 6 | Batch 1314/2891 | Timestep 18660 | LR 0.0000100000 | Loss 0.039136 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:38 Epoch 6 | Batch 1324/2891 | Timestep 18670 | LR 0.0000100000 | Loss 0.008805 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:40 Epoch 6 | Batch 1334/2891 | Timestep 18680 | LR 0.0000100000 | Loss 0.018469 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:42 Epoch 6 | Batch 1344/2891 | Timestep 18690 | LR 0.0000100000 | Loss 0.023915 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:44 Epoch 6 | Batch 1354/2891 | Timestep 18700 | LR 0.0000100000 | Loss 0.029232 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:45 Epoch 6 | Batch 1364/2891 | Timestep 18710 | LR 0.0000100000 | Loss 0.008602 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:46 Epoch 6 | Batch 1374/2891 | Timestep 18720 | LR 0.0000100000 | Loss 0.004964 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:48 Epoch 6 | Batch 1384/2891 | Timestep 18730 | LR 0.0000100000 | Loss 0.010800 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:50 Epoch 6 | Batch 1394/2891 | Timestep 18740 | LR 0.0000100000 | Loss 0.002473 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:51 Epoch 6 | Batch 1404/2891 | Timestep 18750 | LR 0.0000100000 | Loss 0.030824 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:53 Epoch 6 | Batch 1414/2891 | Timestep 18760 | LR 0.0000100000 | Loss 0.007579 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:54 Epoch 6 | Batch 1424/2891 | Timestep 18770 | LR 0.0000100000 | Loss 0.002320 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:56 Epoch 6 | Batch 1434/2891 | Timestep 18780 | LR 0.0000100000 | Loss 0.018661 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:57 Epoch 6 | Batch 1444/2891 | Timestep 18790 | LR 0.0000100000 | Loss 0.051693 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:01:59 Epoch 6 | Batch 1454/2891 | Timestep 18800 | LR 0.0000100000 | Loss 0.005983 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:01 Epoch 6 | Batch 1464/2891 | Timestep 18810 | LR 0.0000100000 | Loss 0.006822 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:02 Epoch 6 | Batch 1474/2891 | Timestep 18820 | LR 0.0000100000 | Loss 0.018363 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:04 Epoch 6 | Batch 1484/2891 | Timestep 18830 | LR 0.0000100000 | Loss 0.003295 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:05 Epoch 6 | Batch 1494/2891 | Timestep 18840 | LR 0.0000100000 | Loss 0.082617 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:07 Epoch 6 | Batch 1504/2891 | Timestep 18850 | LR 0.0000100000 | Loss 0.017283 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:08 Epoch 6 | Batch 1514/2891 | Timestep 18860 | LR 0.0000100000 | Loss 0.008628 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:10 Epoch 6 | Batch 1524/2891 | Timestep 18870 | LR 0.0000100000 | Loss 0.011691 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:11 Epoch 6 | Batch 1534/2891 | Timestep 18880 | LR 0.0000100000 | Loss 0.016434 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:13 Epoch 6 | Batch 1544/2891 | Timestep 18890 | LR 0.0000100000 | Loss 0.000614 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:14 Epoch 6 | Batch 1554/2891 | Timestep 18900 | LR 0.0000100000 | Loss 0.025225 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:16 Epoch 6 | Batch 1564/2891 | Timestep 18910 | LR 0.0000100000 | Loss 0.007637 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:18 Epoch 6 | Batch 1574/2891 | Timestep 18920 | LR 0.0000100000 | Loss 0.018180 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:20 Epoch 6 | Batch 1584/2891 | Timestep 18930 | LR 0.0000100000 | Loss 0.014846 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:21 Epoch 6 | Batch 1594/2891 | Timestep 18940 | LR 0.0000100000 | Loss 0.007349 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:23 Epoch 6 | Batch 1604/2891 | Timestep 18950 | LR 0.0000100000 | Loss 0.076413 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:25 Epoch 6 | Batch 1614/2891 | Timestep 18960 | LR 0.0000100000 | Loss 0.009797 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:27 Epoch 6 | Batch 1624/2891 | Timestep 18970 | LR 0.0000100000 | Loss 0.015735 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:29 Epoch 6 | Batch 1634/2891 | Timestep 18980 | LR 0.0000100000 | Loss 0.037022 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:30 Epoch 6 | Batch 1644/2891 | Timestep 18990 | LR 0.0000100000 | Loss 0.019274 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:32 Epoch 6 | Batch 1654/2891 | Timestep 19000 | LR 0.0000100000 | Loss 0.003486 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:34 Epoch 6 | Batch 1664/2891 | Timestep 19010 | LR 0.0000100000 | Loss 0.011920 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:35 Epoch 6 | Batch 1674/2891 | Timestep 19020 | LR 0.0000100000 | Loss 0.001145 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:37 Epoch 6 | Batch 1684/2891 | Timestep 19030 | LR 0.0000100000 | Loss 0.022454 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:38 Epoch 6 | Batch 1694/2891 | Timestep 19040 | LR 0.0000100000 | Loss 0.035840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:40 Epoch 6 | Batch 1704/2891 | Timestep 19050 | LR 0.0000100000 | Loss 0.065966 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:41 Epoch 6 | Batch 1714/2891 | Timestep 19060 | LR 0.0000100000 | Loss 0.014591 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:43 Epoch 6 | Batch 1724/2891 | Timestep 19070 | LR 0.0000100000 | Loss 0.014301 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:45 Epoch 6 | Batch 1734/2891 | Timestep 19080 | LR 0.0000100000 | Loss 0.002143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:46 Epoch 6 | Batch 1744/2891 | Timestep 19090 | LR 0.0000100000 | Loss 0.013398 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:48 Epoch 6 | Batch 1754/2891 | Timestep 19100 | LR 0.0000100000 | Loss 0.001442 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:49 Epoch 6 | Batch 1764/2891 | Timestep 19110 | LR 0.0000100000 | Loss 0.031119 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:51 Epoch 6 | Batch 1774/2891 | Timestep 19120 | LR 0.0000100000 | Loss 0.008932 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:54 Epoch 6 | Batch 1784/2891 | Timestep 19130 | LR 0.0000100000 | Loss 0.004452 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:56 Epoch 6 | Batch 1794/2891 | Timestep 19140 | LR 0.0000100000 | Loss 0.002293 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:02:58 Epoch 6 | Batch 1804/2891 | Timestep 19150 | LR 0.0000100000 | Loss 0.010999 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:00 Epoch 6 | Batch 1814/2891 | Timestep 19160 | LR 0.0000100000 | Loss 0.009074 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:01 Epoch 6 | Batch 1824/2891 | Timestep 19170 | LR 0.0000100000 | Loss 0.009454 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:03 Epoch 6 | Batch 1834/2891 | Timestep 19180 | LR 0.0000100000 | Loss 0.023830 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:05 Epoch 6 | Batch 1844/2891 | Timestep 19190 | LR 0.0000100000 | Loss 0.015683 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:06 Epoch 6 | Batch 1854/2891 | Timestep 19200 | LR 0.0000100000 | Loss 0.019631 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:08 Epoch 6 | Batch 1864/2891 | Timestep 19210 | LR 0.0000100000 | Loss 0.034183 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:09 Epoch 6 | Batch 1874/2891 | Timestep 19220 | LR 0.0000100000 | Loss 0.011161 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:11 Epoch 6 | Batch 1884/2891 | Timestep 19230 | LR 0.0000100000 | Loss 0.000514 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:13 Epoch 6 | Batch 1894/2891 | Timestep 19240 | LR 0.0000100000 | Loss 0.005160 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:14 Epoch 6 | Batch 1904/2891 | Timestep 19250 | LR 0.0000100000 | Loss 0.009978 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:16 Epoch 6 | Batch 1914/2891 | Timestep 19260 | LR 0.0000100000 | Loss 0.014105 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:18 Epoch 6 | Batch 1924/2891 | Timestep 19270 | LR 0.0000100000 | Loss 0.060786 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:20 Epoch 6 | Batch 1934/2891 | Timestep 19280 | LR 0.0000100000 | Loss 0.025967 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:21 Epoch 6 | Batch 1944/2891 | Timestep 19290 | LR 0.0000100000 | Loss 0.021626 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:23 Epoch 6 | Batch 1954/2891 | Timestep 19300 | LR 0.0000100000 | Loss 0.039561 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:25 Epoch 6 | Batch 1964/2891 | Timestep 19310 | LR 0.0000100000 | Loss 0.015077 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:26 Epoch 6 | Batch 1974/2891 | Timestep 19320 | LR 0.0000100000 | Loss 0.000799 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:28 Epoch 6 | Batch 1984/2891 | Timestep 19330 | LR 0.0000100000 | Loss 0.011747 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:30 Epoch 6 | Batch 1994/2891 | Timestep 19340 | LR 0.0000100000 | Loss 0.007416 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:31 Epoch 6 | Batch 2004/2891 | Timestep 19350 | LR 0.0000100000 | Loss 0.014423 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:33 Epoch 6 | Batch 2014/2891 | Timestep 19360 | LR 0.0000100000 | Loss 0.013802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:35 Epoch 6 | Batch 2024/2891 | Timestep 19370 | LR 0.0000100000 | Loss 0.002524 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:37 Epoch 6 | Batch 2034/2891 | Timestep 19380 | LR 0.0000100000 | Loss 0.006906 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:38 Epoch 6 | Batch 2044/2891 | Timestep 19390 | LR 0.0000100000 | Loss 0.012598 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:40 Epoch 6 | Batch 2054/2891 | Timestep 19400 | LR 0.0000100000 | Loss 0.009951 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:42 Epoch 6 | Batch 2064/2891 | Timestep 19410 | LR 0.0000100000 | Loss 0.006736 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:44 Epoch 6 | Batch 2074/2891 | Timestep 19420 | LR 0.0000100000 | Loss 0.033914 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:45 Epoch 6 | Batch 2084/2891 | Timestep 19430 | LR 0.0000100000 | Loss 0.036558 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:47 Epoch 6 | Batch 2094/2891 | Timestep 19440 | LR 0.0000100000 | Loss 0.007507 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:49 Epoch 6 | Batch 2104/2891 | Timestep 19450 | LR 0.0000100000 | Loss 0.015572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:50 Epoch 6 | Batch 2114/2891 | Timestep 19460 | LR 0.0000100000 | Loss 0.020852 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:52 Epoch 6 | Batch 2124/2891 | Timestep 19470 | LR 0.0000100000 | Loss 0.022663 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:53 Epoch 6 | Batch 2134/2891 | Timestep 19480 | LR 0.0000100000 | Loss 0.023351 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:55 Epoch 6 | Batch 2144/2891 | Timestep 19490 | LR 0.0000100000 | Loss 0.018184 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:57 Epoch 6 | Batch 2154/2891 | Timestep 19500 | LR 0.0000100000 | Loss 0.012924 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:03:58 Epoch 6 | Batch 2164/2891 | Timestep 19510 | LR 0.0000100000 | Loss 0.007040 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:00 Epoch 6 | Batch 2174/2891 | Timestep 19520 | LR 0.0000100000 | Loss 0.055819 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:01 Epoch 6 | Batch 2184/2891 | Timestep 19530 | LR 0.0000100000 | Loss 0.022651 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:03 Epoch 6 | Batch 2194/2891 | Timestep 19540 | LR 0.0000100000 | Loss 0.009123 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:04 Epoch 6 | Batch 2204/2891 | Timestep 19550 | LR 0.0000100000 | Loss 0.026576 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:06 Epoch 6 | Batch 2214/2891 | Timestep 19560 | LR 0.0000100000 | Loss 0.039253 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:08 Epoch 6 | Batch 2224/2891 | Timestep 19570 | LR 0.0000100000 | Loss 0.048250 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:10 Epoch 6 | Batch 2234/2891 | Timestep 19580 | LR 0.0000100000 | Loss 0.018421 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:11 Epoch 6 | Batch 2244/2891 | Timestep 19590 | LR 0.0000100000 | Loss 0.001930 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:13 Epoch 6 | Batch 2254/2891 | Timestep 19600 | LR 0.0000100000 | Loss 0.024625 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:15 Epoch 6 | Batch 2264/2891 | Timestep 19610 | LR 0.0000100000 | Loss 0.009719 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:16 Epoch 6 | Batch 2274/2891 | Timestep 19620 | LR 0.0000100000 | Loss 0.086809 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:18 Epoch 6 | Batch 2284/2891 | Timestep 19630 | LR 0.0000100000 | Loss 0.001775 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:20 Epoch 6 | Batch 2294/2891 | Timestep 19640 | LR 0.0000100000 | Loss 0.011480 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:22 Epoch 6 | Batch 2304/2891 | Timestep 19650 | LR 0.0000100000 | Loss 0.020331 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:24 Epoch 6 | Batch 2314/2891 | Timestep 19660 | LR 0.0000100000 | Loss 0.012039 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:26 Epoch 6 | Batch 2324/2891 | Timestep 19670 | LR 0.0000100000 | Loss 0.081502 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:28 Epoch 6 | Batch 2334/2891 | Timestep 19680 | LR 0.0000100000 | Loss 0.011820 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:30 Epoch 6 | Batch 2344/2891 | Timestep 19690 | LR 0.0000100000 | Loss 0.013269 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:31 Epoch 6 | Batch 2354/2891 | Timestep 19700 | LR 0.0000100000 | Loss 0.006892 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:34 Epoch 6 | Batch 2364/2891 | Timestep 19710 | LR 0.0000100000 | Loss 0.005391 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:36 Epoch 6 | Batch 2374/2891 | Timestep 19720 | LR 0.0000100000 | Loss 0.013335 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:37 Epoch 6 | Batch 2384/2891 | Timestep 19730 | LR 0.0000100000 | Loss 0.067092 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:39 Epoch 6 | Batch 2394/2891 | Timestep 19740 | LR 0.0000100000 | Loss 0.009303 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:41 Epoch 6 | Batch 2404/2891 | Timestep 19750 | LR 0.0000100000 | Loss 0.039903 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:42 Epoch 6 | Batch 2414/2891 | Timestep 19760 | LR 0.0000100000 | Loss 0.050632 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:44 Epoch 6 | Batch 2424/2891 | Timestep 19770 | LR 0.0000100000 | Loss 0.014803 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:45 Epoch 6 | Batch 2434/2891 | Timestep 19780 | LR 0.0000100000 | Loss 0.010615 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:47 Epoch 6 | Batch 2444/2891 | Timestep 19790 | LR 0.0000100000 | Loss 0.012222 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:49 Epoch 6 | Batch 2454/2891 | Timestep 19800 | LR 0.0000100000 | Loss 0.004772 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:51 Epoch 6 | Batch 2464/2891 | Timestep 19810 | LR 0.0000100000 | Loss 0.000709 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:52 Epoch 6 | Batch 2474/2891 | Timestep 19820 | LR 0.0000100000 | Loss 0.028692 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:54 Epoch 6 | Batch 2484/2891 | Timestep 19830 | LR 0.0000100000 | Loss 0.007854 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:56 Epoch 6 | Batch 2494/2891 | Timestep 19840 | LR 0.0000100000 | Loss 0.039639 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:57 Epoch 6 | Batch 2504/2891 | Timestep 19850 | LR 0.0000100000 | Loss 0.023879 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:04:59 Epoch 6 | Batch 2514/2891 | Timestep 19860 | LR 0.0000100000 | Loss 0.007395 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:01 Epoch 6 | Batch 2524/2891 | Timestep 19870 | LR 0.0000100000 | Loss 0.004642 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:02 Epoch 6 | Batch 2534/2891 | Timestep 19880 | LR 0.0000100000 | Loss 0.005623 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:04 Epoch 6 | Batch 2544/2891 | Timestep 19890 | LR 0.0000100000 | Loss 0.008240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:06 Epoch 6 | Batch 2554/2891 | Timestep 19900 | LR 0.0000100000 | Loss 0.023836 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:07 Epoch 6 | Batch 2564/2891 | Timestep 19910 | LR 0.0000100000 | Loss 0.008072 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:09 Epoch 6 | Batch 2574/2891 | Timestep 19920 | LR 0.0000100000 | Loss 0.036770 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:11 Epoch 6 | Batch 2584/2891 | Timestep 19930 | LR 0.0000100000 | Loss 0.030486 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:12 Epoch 6 | Batch 2594/2891 | Timestep 19940 | LR 0.0000100000 | Loss 0.008536 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:13 Epoch 6 | Batch 2604/2891 | Timestep 19950 | LR 0.0000100000 | Loss 0.031695 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:15 Epoch 6 | Batch 2614/2891 | Timestep 19960 | LR 0.0000100000 | Loss 0.006085 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:17 Epoch 6 | Batch 2624/2891 | Timestep 19970 | LR 0.0000100000 | Loss 0.009452 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:18 Epoch 6 | Batch 2634/2891 | Timestep 19980 | LR 0.0000100000 | Loss 0.015441 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:20 Epoch 6 | Batch 2644/2891 | Timestep 19990 | LR 0.0000100000 | Loss 0.038098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:21 Epoch 6 | Batch 2654/2891 | Timestep 20000 | LR 0.0000100000 | Loss 0.097509 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:23 Epoch 6 | Batch 2664/2891 | Timestep 20010 | LR 0.0000100000 | Loss 0.033142 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:25 Epoch 6 | Batch 2674/2891 | Timestep 20020 | LR 0.0000100000 | Loss 0.012631 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:27 Epoch 6 | Batch 2684/2891 | Timestep 20030 | LR 0.0000100000 | Loss 0.001006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:28 Epoch 6 | Batch 2694/2891 | Timestep 20040 | LR 0.0000100000 | Loss 0.016135 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:30 Epoch 6 | Batch 2704/2891 | Timestep 20050 | LR 0.0000100000 | Loss 0.026833 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:32 Epoch 6 | Batch 2714/2891 | Timestep 20060 | LR 0.0000100000 | Loss 0.002250 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:33 Epoch 6 | Batch 2724/2891 | Timestep 20070 | LR 0.0000100000 | Loss 0.015782 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:35 Epoch 6 | Batch 2734/2891 | Timestep 20080 | LR 0.0000100000 | Loss 0.018169 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:36 Epoch 6 | Batch 2744/2891 | Timestep 20090 | LR 0.0000100000 | Loss 0.025202 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:38 Epoch 6 | Batch 2754/2891 | Timestep 20100 | LR 0.0000100000 | Loss 0.003320 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:40 Epoch 6 | Batch 2764/2891 | Timestep 20110 | LR 0.0000100000 | Loss 0.006370 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:42 Epoch 6 | Batch 2774/2891 | Timestep 20120 | LR 0.0000100000 | Loss 0.007436 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:43 Epoch 6 | Batch 2784/2891 | Timestep 20130 | LR 0.0000100000 | Loss 0.032648 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:45 Epoch 6 | Batch 2794/2891 | Timestep 20140 | LR 0.0000100000 | Loss 0.033040 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:46 Epoch 6 | Batch 2804/2891 | Timestep 20150 | LR 0.0000100000 | Loss 0.006632 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:48 Epoch 6 | Batch 2814/2891 | Timestep 20160 | LR 0.0000100000 | Loss 0.156770 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:49 Epoch 6 | Batch 2824/2891 | Timestep 20170 | LR 0.0000100000 | Loss 0.030847 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:51 Epoch 6 | Batch 2834/2891 | Timestep 20180 | LR 0.0000100000 | Loss 0.010513 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:53 Epoch 6 | Batch 2844/2891 | Timestep 20190 | LR 0.0000100000 | Loss 0.003731 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:55 Epoch 6 | Batch 2854/2891 | Timestep 20200 | LR 0.0000100000 | Loss 0.024834 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:57 Epoch 6 | Batch 2864/2891 | Timestep 20210 | LR 0.0000100000 | Loss 0.004598 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:05:58 Epoch 6 | Batch 2874/2891 | Timestep 20220 | LR 0.0000100000 | Loss 0.024446 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:00 Epoch 6 | Batch 2884/2891 | Timestep 20230 | LR 0.0000100000 | Loss 0.001115 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:01 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 12:06:19 precision recall f1-score support CARDINAL 0.8452 0.7706 0.8062 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.5981 0.6087 0.6034 1592 EVENT 0.6564 0.7589 0.7039 282 FAC 0.7030 0.7717 0.7358 92 GPE 0.9107 0.9020 0.9063 1051 LANGUAGE 0.6842 0.8125 0.7429 16 LAW 0.7091 0.8298 0.7647 47 LOC 0.7746 0.7432 0.7586 74 MONEY 0.6552 0.8636 0.7451 22 NORP 0.6940 0.7677 0.7290 508 OCC 0.8447 0.8677 0.8560 514 ORDINAL 0.9424 0.9191 0.9306 445 ORG 0.8736 0.9328 0.9022 1578 PERCENT 1.0000 1.0000 1.0000 12 PERS 0.9464 0.9511 0.9487 613 PRODUCT 0.3333 0.3750 0.3529 8 QUANTITY 0.5000 0.6667 0.5714 3 TIME 0.7353 0.7576 0.7463 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.5366 0.5500 0.5432 80 micro avg 0.7917 0.8183 0.8048 7143 macro avg 0.6639 0.7071 0.6832 7143 weighted avg 0.7934 0.8183 0.8051 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:20 Epoch 6 | Timestep 20237 | Train Loss 0.016179 | Val Loss 0.058072 | F1 0.804764 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:21 Epoch 7 | Batch 3/2891 | Timestep 20240 | LR 0.0000100000 | Loss 0.009029 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:23 Epoch 7 | Batch 13/2891 | Timestep 20250 | LR 0.0000100000 | Loss 0.002374 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:25 Epoch 7 | Batch 23/2891 | Timestep 20260 | LR 0.0000100000 | Loss 0.029501 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:27 Epoch 7 | Batch 33/2891 | Timestep 20270 | LR 0.0000100000 | Loss 0.014378 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:29 Epoch 7 | Batch 43/2891 | Timestep 20280 | LR 0.0000100000 | Loss 0.001558 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:30 Epoch 7 | Batch 53/2891 | Timestep 20290 | LR 0.0000100000 | Loss 0.020720 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:31 Epoch 7 | Batch 63/2891 | Timestep 20300 | LR 0.0000100000 | Loss 0.015146 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:33 Epoch 7 | Batch 73/2891 | Timestep 20310 | LR 0.0000100000 | Loss 0.007407 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:35 Epoch 7 | Batch 83/2891 | Timestep 20320 | LR 0.0000100000 | Loss 0.024079 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:37 Epoch 7 | Batch 93/2891 | Timestep 20330 | LR 0.0000100000 | Loss 0.010217 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:38 Epoch 7 | Batch 103/2891 | Timestep 20340 | LR 0.0000100000 | Loss 0.009969 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:40 Epoch 7 | Batch 113/2891 | Timestep 20350 | LR 0.0000100000 | Loss 0.006005 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:41 Epoch 7 | Batch 123/2891 | Timestep 20360 | LR 0.0000100000 | Loss 0.031790 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:43 Epoch 7 | Batch 133/2891 | Timestep 20370 | LR 0.0000100000 | Loss 0.004853 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:45 Epoch 7 | Batch 143/2891 | Timestep 20380 | LR 0.0000100000 | Loss 0.012526 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:47 Epoch 7 | Batch 153/2891 | Timestep 20390 | LR 0.0000100000 | Loss 0.008652 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:48 Epoch 7 | Batch 163/2891 | Timestep 20400 | LR 0.0000100000 | Loss 0.016642 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:51 Epoch 7 | Batch 173/2891 | Timestep 20410 | LR 0.0000100000 | Loss 0.011683 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:53 Epoch 7 | Batch 183/2891 | Timestep 20420 | LR 0.0000100000 | Loss 0.011187 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:55 Epoch 7 | Batch 193/2891 | Timestep 20430 | LR 0.0000100000 | Loss 0.013582 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:56 Epoch 7 | Batch 203/2891 | Timestep 20440 | LR 0.0000100000 | Loss 0.006870 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:06:58 Epoch 7 | Batch 213/2891 | Timestep 20450 | LR 0.0000100000 | Loss 0.016305 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:00 Epoch 7 | Batch 223/2891 | Timestep 20460 | LR 0.0000100000 | Loss 0.027441 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:02 Epoch 7 | Batch 233/2891 | Timestep 20470 | LR 0.0000100000 | Loss 0.010456 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:03 Epoch 7 | Batch 243/2891 | Timestep 20480 | LR 0.0000100000 | Loss 0.009425 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:05 Epoch 7 | Batch 253/2891 | Timestep 20490 | LR 0.0000100000 | Loss 0.014559 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:07 Epoch 7 | Batch 263/2891 | Timestep 20500 | LR 0.0000100000 | Loss 0.007983 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:08 Epoch 7 | Batch 273/2891 | Timestep 20510 | LR 0.0000100000 | Loss 0.001744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:10 Epoch 7 | Batch 283/2891 | Timestep 20520 | LR 0.0000100000 | Loss 0.006663 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:12 Epoch 7 | Batch 293/2891 | Timestep 20530 | LR 0.0000100000 | Loss 0.000368 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:13 Epoch 7 | Batch 303/2891 | Timestep 20540 | LR 0.0000100000 | Loss 0.014354 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:15 Epoch 7 | Batch 313/2891 | Timestep 20550 | LR 0.0000100000 | Loss 0.022745 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:16 Epoch 7 | Batch 323/2891 | Timestep 20560 | LR 0.0000100000 | Loss 0.006394 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:18 Epoch 7 | Batch 333/2891 | Timestep 20570 | LR 0.0000100000 | Loss 0.025848 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:20 Epoch 7 | Batch 343/2891 | Timestep 20580 | LR 0.0000100000 | Loss 0.002516 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:21 Epoch 7 | Batch 353/2891 | Timestep 20590 | LR 0.0000100000 | Loss 0.024181 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:23 Epoch 7 | Batch 363/2891 | Timestep 20600 | LR 0.0000100000 | Loss 0.009961 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:25 Epoch 7 | Batch 373/2891 | Timestep 20610 | LR 0.0000100000 | Loss 0.005630 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:26 Epoch 7 | Batch 383/2891 | Timestep 20620 | LR 0.0000100000 | Loss 0.005828 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:28 Epoch 7 | Batch 393/2891 | Timestep 20630 | LR 0.0000100000 | Loss 0.053572 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:29 Epoch 7 | Batch 403/2891 | Timestep 20640 | LR 0.0000100000 | Loss 0.006185 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:32 Epoch 7 | Batch 413/2891 | Timestep 20650 | LR 0.0000100000 | Loss 0.014979 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:34 Epoch 7 | Batch 423/2891 | Timestep 20660 | LR 0.0000100000 | Loss 0.002501 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:36 Epoch 7 | Batch 433/2891 | Timestep 20670 | LR 0.0000100000 | Loss 0.021942 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:38 Epoch 7 | Batch 443/2891 | Timestep 20680 | LR 0.0000100000 | Loss 0.010006 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:39 Epoch 7 | Batch 453/2891 | Timestep 20690 | LR 0.0000100000 | Loss 0.000668 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:41 Epoch 7 | Batch 463/2891 | Timestep 20700 | LR 0.0000100000 | Loss 0.007191 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:43 Epoch 7 | Batch 473/2891 | Timestep 20710 | LR 0.0000100000 | Loss 0.010119 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:45 Epoch 7 | Batch 483/2891 | Timestep 20720 | LR 0.0000100000 | Loss 0.008527 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:46 Epoch 7 | Batch 493/2891 | Timestep 20730 | LR 0.0000100000 | Loss 0.050308 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:48 Epoch 7 | Batch 503/2891 | Timestep 20740 | LR 0.0000100000 | Loss 0.008259 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:50 Epoch 7 | Batch 513/2891 | Timestep 20750 | LR 0.0000100000 | Loss 0.016962 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:52 Epoch 7 | Batch 523/2891 | Timestep 20760 | LR 0.0000100000 | Loss 0.007687 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:53 Epoch 7 | Batch 533/2891 | Timestep 20770 | LR 0.0000100000 | Loss 0.012702 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:55 Epoch 7 | Batch 543/2891 | Timestep 20780 | LR 0.0000100000 | Loss 0.009709 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:58 Epoch 7 | Batch 553/2891 | Timestep 20790 | LR 0.0000100000 | Loss 0.006084 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:07:59 Epoch 7 | Batch 563/2891 | Timestep 20800 | LR 0.0000100000 | Loss 0.007225 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:01 Epoch 7 | Batch 573/2891 | Timestep 20810 | LR 0.0000100000 | Loss 0.010856 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:03 Epoch 7 | Batch 583/2891 | Timestep 20820 | LR 0.0000100000 | Loss 0.010901 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:04 Epoch 7 | Batch 593/2891 | Timestep 20830 | LR 0.0000100000 | Loss 0.008367 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:06 Epoch 7 | Batch 603/2891 | Timestep 20840 | LR 0.0000100000 | Loss 0.029132 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:07 Epoch 7 | Batch 613/2891 | Timestep 20850 | LR 0.0000100000 | Loss 0.003791 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:09 Epoch 7 | Batch 623/2891 | Timestep 20860 | LR 0.0000100000 | Loss 0.007497 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:10 Epoch 7 | Batch 633/2891 | Timestep 20870 | LR 0.0000100000 | Loss 0.005744 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:13 Epoch 7 | Batch 643/2891 | Timestep 20880 | LR 0.0000100000 | Loss 0.008824 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:14 Epoch 7 | Batch 653/2891 | Timestep 20890 | LR 0.0000100000 | Loss 0.007297 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:16 Epoch 7 | Batch 663/2891 | Timestep 20900 | LR 0.0000100000 | Loss 0.001599 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:18 Epoch 7 | Batch 673/2891 | Timestep 20910 | LR 0.0000100000 | Loss 0.017533 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:19 Epoch 7 | Batch 683/2891 | Timestep 20920 | LR 0.0000100000 | Loss 0.000515 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:21 Epoch 7 | Batch 693/2891 | Timestep 20930 | LR 0.0000100000 | Loss 0.002602 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:23 Epoch 7 | Batch 703/2891 | Timestep 20940 | LR 0.0000100000 | Loss 0.005525 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:24 Epoch 7 | Batch 713/2891 | Timestep 20950 | LR 0.0000100000 | Loss 0.008194 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:27 Epoch 7 | Batch 723/2891 | Timestep 20960 | LR 0.0000100000 | Loss 0.011366 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:28 Epoch 7 | Batch 733/2891 | Timestep 20970 | LR 0.0000100000 | Loss 0.015475 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:30 Epoch 7 | Batch 743/2891 | Timestep 20980 | LR 0.0000100000 | Loss 0.021263 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:31 Epoch 7 | Batch 753/2891 | Timestep 20990 | LR 0.0000100000 | Loss 0.017051 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:32 Epoch 7 | Batch 763/2891 | Timestep 21000 | LR 0.0000100000 | Loss 0.020373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:34 Epoch 7 | Batch 773/2891 | Timestep 21010 | LR 0.0000100000 | Loss 0.014296 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:35 Epoch 7 | Batch 783/2891 | Timestep 21020 | LR 0.0000100000 | Loss 0.009272 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:37 Epoch 7 | Batch 793/2891 | Timestep 21030 | LR 0.0000100000 | Loss 0.000898 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:38 Epoch 7 | Batch 803/2891 | Timestep 21040 | LR 0.0000100000 | Loss 0.012258 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:40 Epoch 7 | Batch 813/2891 | Timestep 21050 | LR 0.0000100000 | Loss 0.003977 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:42 Epoch 7 | Batch 823/2891 | Timestep 21060 | LR 0.0000100000 | Loss 0.016235 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:43 Epoch 7 | Batch 833/2891 | Timestep 21070 | LR 0.0000100000 | Loss 0.009819 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:45 Epoch 7 | Batch 843/2891 | Timestep 21080 | LR 0.0000100000 | Loss 0.004244 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:47 Epoch 7 | Batch 853/2891 | Timestep 21090 | LR 0.0000100000 | Loss 0.006011 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:48 Epoch 7 | Batch 863/2891 | Timestep 21100 | LR 0.0000100000 | Loss 0.022698 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:50 Epoch 7 | Batch 873/2891 | Timestep 21110 | LR 0.0000100000 | Loss 0.006875 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:51 Epoch 7 | Batch 883/2891 | Timestep 21120 | LR 0.0000100000 | Loss 0.001608 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:53 Epoch 7 | Batch 893/2891 | Timestep 21130 | LR 0.0000100000 | Loss 0.008204 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:56 Epoch 7 | Batch 903/2891 | Timestep 21140 | LR 0.0000100000 | Loss 0.000612 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:57 Epoch 7 | Batch 913/2891 | Timestep 21150 | LR 0.0000100000 | Loss 0.038599 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:08:59 Epoch 7 | Batch 923/2891 | Timestep 21160 | LR 0.0000100000 | Loss 0.005867 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:00 Epoch 7 | Batch 933/2891 | Timestep 21170 | LR 0.0000100000 | Loss 0.017618 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:02 Epoch 7 | Batch 943/2891 | Timestep 21180 | LR 0.0000100000 | Loss 0.011668 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:04 Epoch 7 | Batch 953/2891 | Timestep 21190 | LR 0.0000100000 | Loss 0.023463 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:05 Epoch 7 | Batch 963/2891 | Timestep 21200 | LR 0.0000100000 | Loss 0.001360 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:07 Epoch 7 | Batch 973/2891 | Timestep 21210 | LR 0.0000100000 | Loss 0.021746 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:09 Epoch 7 | Batch 983/2891 | Timestep 21220 | LR 0.0000100000 | Loss 0.009803 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:10 Epoch 7 | Batch 993/2891 | Timestep 21230 | LR 0.0000100000 | Loss 0.008660 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:12 Epoch 7 | Batch 1003/2891 | Timestep 21240 | LR 0.0000100000 | Loss 0.022240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:14 Epoch 7 | Batch 1013/2891 | Timestep 21250 | LR 0.0000100000 | Loss 0.006198 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:15 Epoch 7 | Batch 1023/2891 | Timestep 21260 | LR 0.0000100000 | Loss 0.002016 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:17 Epoch 7 | Batch 1033/2891 | Timestep 21270 | LR 0.0000100000 | Loss 0.018523 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:19 Epoch 7 | Batch 1043/2891 | Timestep 21280 | LR 0.0000100000 | Loss 0.001679 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:21 Epoch 7 | Batch 1053/2891 | Timestep 21290 | LR 0.0000100000 | Loss 0.009664 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:23 Epoch 7 | Batch 1063/2891 | Timestep 21300 | LR 0.0000100000 | Loss 0.010152 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:25 Epoch 7 | Batch 1073/2891 | Timestep 21310 | LR 0.0000100000 | Loss 0.008057 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:26 Epoch 7 | Batch 1083/2891 | Timestep 21320 | LR 0.0000100000 | Loss 0.022007 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:27 Epoch 7 | Batch 1093/2891 | Timestep 21330 | LR 0.0000100000 | Loss 0.010206 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:29 Epoch 7 | Batch 1103/2891 | Timestep 21340 | LR 0.0000100000 | Loss 0.030940 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:30 Epoch 7 | Batch 1113/2891 | Timestep 21350 | LR 0.0000100000 | Loss 0.011481 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:32 Epoch 7 | Batch 1123/2891 | Timestep 21360 | LR 0.0000100000 | Loss 0.007461 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:33 Epoch 7 | Batch 1133/2891 | Timestep 21370 | LR 0.0000100000 | Loss 0.012048 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:35 Epoch 7 | Batch 1143/2891 | Timestep 21380 | LR 0.0000100000 | Loss 0.007292 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:37 Epoch 7 | Batch 1153/2891 | Timestep 21390 | LR 0.0000100000 | Loss 0.004781 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:39 Epoch 7 | Batch 1163/2891 | Timestep 21400 | LR 0.0000100000 | Loss 0.005308 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:40 Epoch 7 | Batch 1173/2891 | Timestep 21410 | LR 0.0000100000 | Loss 0.016050 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:42 Epoch 7 | Batch 1183/2891 | Timestep 21420 | LR 0.0000100000 | Loss 0.030797 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:43 Epoch 7 | Batch 1193/2891 | Timestep 21430 | LR 0.0000100000 | Loss 0.004880 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:45 Epoch 7 | Batch 1203/2891 | Timestep 21440 | LR 0.0000100000 | Loss 0.015205 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:46 Epoch 7 | Batch 1213/2891 | Timestep 21450 | LR 0.0000100000 | Loss 0.031732 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:48 Epoch 7 | Batch 1223/2891 | Timestep 21460 | LR 0.0000100000 | Loss 0.013850 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:50 Epoch 7 | Batch 1233/2891 | Timestep 21470 | LR 0.0000100000 | Loss 0.032424 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:52 Epoch 7 | Batch 1243/2891 | Timestep 21480 | LR 0.0000100000 | Loss 0.018093 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:54 Epoch 7 | Batch 1253/2891 | Timestep 21490 | LR 0.0000100000 | Loss 0.038346 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:56 Epoch 7 | Batch 1263/2891 | Timestep 21500 | LR 0.0000100000 | Loss 0.008347 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:57 Epoch 7 | Batch 1273/2891 | Timestep 21510 | LR 0.0000100000 | Loss 0.010978 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:09:59 Epoch 7 | Batch 1283/2891 | Timestep 21520 | LR 0.0000100000 | Loss 0.005858 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:00 Epoch 7 | Batch 1293/2891 | Timestep 21530 | LR 0.0000100000 | Loss 0.020299 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:01 Epoch 7 | Batch 1303/2891 | Timestep 21540 | LR 0.0000100000 | Loss 0.011438 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:03 Epoch 7 | Batch 1313/2891 | Timestep 21550 | LR 0.0000100000 | Loss 0.013157 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:05 Epoch 7 | Batch 1323/2891 | Timestep 21560 | LR 0.0000100000 | Loss 0.007383 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:07 Epoch 7 | Batch 1333/2891 | Timestep 21570 | LR 0.0000100000 | Loss 0.006154 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:09 Epoch 7 | Batch 1343/2891 | Timestep 21580 | LR 0.0000100000 | Loss 0.001598 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:10 Epoch 7 | Batch 1353/2891 | Timestep 21590 | LR 0.0000100000 | Loss 0.012255 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:12 Epoch 7 | Batch 1363/2891 | Timestep 21600 | LR 0.0000100000 | Loss 0.037488 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:13 Epoch 7 | Batch 1373/2891 | Timestep 21610 | LR 0.0000100000 | Loss 0.004344 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:15 Epoch 7 | Batch 1383/2891 | Timestep 21620 | LR 0.0000100000 | Loss 0.041260 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:17 Epoch 7 | Batch 1393/2891 | Timestep 21630 | LR 0.0000100000 | Loss 0.008075 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:18 Epoch 7 | Batch 1403/2891 | Timestep 21640 | LR 0.0000100000 | Loss 0.010553 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:20 Epoch 7 | Batch 1413/2891 | Timestep 21650 | LR 0.0000100000 | Loss 0.005428 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:22 Epoch 7 | Batch 1423/2891 | Timestep 21660 | LR 0.0000100000 | Loss 0.000431 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:23 Epoch 7 | Batch 1433/2891 | Timestep 21670 | LR 0.0000100000 | Loss 0.012373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:25 Epoch 7 | Batch 1443/2891 | Timestep 21680 | LR 0.0000100000 | Loss 0.038075 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:27 Epoch 7 | Batch 1453/2891 | Timestep 21690 | LR 0.0000100000 | Loss 0.007236 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:28 Epoch 7 | Batch 1463/2891 | Timestep 21700 | LR 0.0000100000 | Loss 0.014309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:30 Epoch 7 | Batch 1473/2891 | Timestep 21710 | LR 0.0000100000 | Loss 0.006392 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:31 Epoch 7 | Batch 1483/2891 | Timestep 21720 | LR 0.0000100000 | Loss 0.015241 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:33 Epoch 7 | Batch 1493/2891 | Timestep 21730 | LR 0.0000100000 | Loss 0.003995 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:34 Epoch 7 | Batch 1503/2891 | Timestep 21740 | LR 0.0000100000 | Loss 0.008482 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:36 Epoch 7 | Batch 1513/2891 | Timestep 21750 | LR 0.0000100000 | Loss 0.016938 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:38 Epoch 7 | Batch 1523/2891 | Timestep 21760 | LR 0.0000100000 | Loss 0.020609 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:40 Epoch 7 | Batch 1533/2891 | Timestep 21770 | LR 0.0000100000 | Loss 0.009867 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:41 Epoch 7 | Batch 1543/2891 | Timestep 21780 | LR 0.0000100000 | Loss 0.023646 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:43 Epoch 7 | Batch 1553/2891 | Timestep 21790 | LR 0.0000100000 | Loss 0.020805 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:45 Epoch 7 | Batch 1563/2891 | Timestep 21800 | LR 0.0000100000 | Loss 0.018239 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:47 Epoch 7 | Batch 1573/2891 | Timestep 21810 | LR 0.0000100000 | Loss 0.019104 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:49 Epoch 7 | Batch 1583/2891 | Timestep 21820 | LR 0.0000100000 | Loss 0.041852 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:50 Epoch 7 | Batch 1593/2891 | Timestep 21830 | LR 0.0000100000 | Loss 0.007064 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:52 Epoch 7 | Batch 1603/2891 | Timestep 21840 | LR 0.0000100000 | Loss 0.023486 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:54 Epoch 7 | Batch 1613/2891 | Timestep 21850 | LR 0.0000100000 | Loss 0.010500 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:55 Epoch 7 | Batch 1623/2891 | Timestep 21860 | LR 0.0000100000 | Loss 0.011883 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:56 Epoch 7 | Batch 1633/2891 | Timestep 21870 | LR 0.0000100000 | Loss 0.050943 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:58 Epoch 7 | Batch 1643/2891 | Timestep 21880 | LR 0.0000100000 | Loss 0.016450 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:10:59 Epoch 7 | Batch 1653/2891 | Timestep 21890 | LR 0.0000100000 | Loss 0.020653 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:01 Epoch 7 | Batch 1663/2891 | Timestep 21900 | LR 0.0000100000 | Loss 0.005791 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:02 Epoch 7 | Batch 1673/2891 | Timestep 21910 | LR 0.0000100000 | Loss 0.013953 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:04 Epoch 7 | Batch 1683/2891 | Timestep 21920 | LR 0.0000100000 | Loss 0.008722 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:06 Epoch 7 | Batch 1693/2891 | Timestep 21930 | LR 0.0000100000 | Loss 0.012829 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:08 Epoch 7 | Batch 1703/2891 | Timestep 21940 | LR 0.0000100000 | Loss 0.061512 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:10 Epoch 7 | Batch 1713/2891 | Timestep 21950 | LR 0.0000100000 | Loss 0.013804 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:11 Epoch 7 | Batch 1723/2891 | Timestep 21960 | LR 0.0000100000 | Loss 0.014386 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:13 Epoch 7 | Batch 1733/2891 | Timestep 21970 | LR 0.0000100000 | Loss 0.031815 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:15 Epoch 7 | Batch 1743/2891 | Timestep 21980 | LR 0.0000100000 | Loss 0.026484 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:17 Epoch 7 | Batch 1753/2891 | Timestep 21990 | LR 0.0000100000 | Loss 0.002493 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:18 Epoch 7 | Batch 1763/2891 | Timestep 22000 | LR 0.0000100000 | Loss 0.004709 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:20 Epoch 7 | Batch 1773/2891 | Timestep 22010 | LR 0.0000100000 | Loss 0.012936 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:22 Epoch 7 | Batch 1783/2891 | Timestep 22020 | LR 0.0000100000 | Loss 0.010042 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:24 Epoch 7 | Batch 1793/2891 | Timestep 22030 | LR 0.0000100000 | Loss 0.002389 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:25 Epoch 7 | Batch 1803/2891 | Timestep 22040 | LR 0.0000100000 | Loss 0.013725 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:27 Epoch 7 | Batch 1813/2891 | Timestep 22050 | LR 0.0000100000 | Loss 0.002041 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:29 Epoch 7 | Batch 1823/2891 | Timestep 22060 | LR 0.0000100000 | Loss 0.004007 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:30 Epoch 7 | Batch 1833/2891 | Timestep 22070 | LR 0.0000100000 | Loss 0.014122 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:32 Epoch 7 | Batch 1843/2891 | Timestep 22080 | LR 0.0000100000 | Loss 0.035441 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:33 Epoch 7 | Batch 1853/2891 | Timestep 22090 | LR 0.0000100000 | Loss 0.030194 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:35 Epoch 7 | Batch 1863/2891 | Timestep 22100 | LR 0.0000100000 | Loss 0.033279 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:37 Epoch 7 | Batch 1873/2891 | Timestep 22110 | LR 0.0000100000 | Loss 0.005877 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:38 Epoch 7 | Batch 1883/2891 | Timestep 22120 | LR 0.0000100000 | Loss 0.012373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:40 Epoch 7 | Batch 1893/2891 | Timestep 22130 | LR 0.0000100000 | Loss 0.022433 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:42 Epoch 7 | Batch 1903/2891 | Timestep 22140 | LR 0.0000100000 | Loss 0.007880 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:44 Epoch 7 | Batch 1913/2891 | Timestep 22150 | LR 0.0000100000 | Loss 0.002838 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:45 Epoch 7 | Batch 1923/2891 | Timestep 22160 | LR 0.0000100000 | Loss 0.008022 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:47 Epoch 7 | Batch 1933/2891 | Timestep 22170 | LR 0.0000100000 | Loss 0.006347 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:49 Epoch 7 | Batch 1943/2891 | Timestep 22180 | LR 0.0000100000 | Loss 0.023254 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:51 Epoch 7 | Batch 1953/2891 | Timestep 22190 | LR 0.0000100000 | Loss 0.006548 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:53 Epoch 7 | Batch 1963/2891 | Timestep 22200 | LR 0.0000100000 | Loss 0.006148 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:54 Epoch 7 | Batch 1973/2891 | Timestep 22210 | LR 0.0000100000 | Loss 0.018435 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:56 Epoch 7 | Batch 1983/2891 | Timestep 22220 | LR 0.0000100000 | Loss 0.004330 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:58 Epoch 7 | Batch 1993/2891 | Timestep 22230 | LR 0.0000100000 | Loss 0.020105 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:11:59 Epoch 7 | Batch 2003/2891 | Timestep 22240 | LR 0.0000100000 | Loss 0.014173 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:01 Epoch 7 | Batch 2013/2891 | Timestep 22250 | LR 0.0000100000 | Loss 0.031943 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:03 Epoch 7 | Batch 2023/2891 | Timestep 22260 | LR 0.0000100000 | Loss 0.025777 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:04 Epoch 7 | Batch 2033/2891 | Timestep 22270 | LR 0.0000100000 | Loss 0.018691 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:06 Epoch 7 | Batch 2043/2891 | Timestep 22280 | LR 0.0000100000 | Loss 0.008014 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:08 Epoch 7 | Batch 2053/2891 | Timestep 22290 | LR 0.0000100000 | Loss 0.017100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:09 Epoch 7 | Batch 2063/2891 | Timestep 22300 | LR 0.0000100000 | Loss 0.002470 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:11 Epoch 7 | Batch 2073/2891 | Timestep 22310 | LR 0.0000100000 | Loss 0.018324 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:13 Epoch 7 | Batch 2083/2891 | Timestep 22320 | LR 0.0000100000 | Loss 0.014451 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:14 Epoch 7 | Batch 2093/2891 | Timestep 22330 | LR 0.0000100000 | Loss 0.005074 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:16 Epoch 7 | Batch 2103/2891 | Timestep 22340 | LR 0.0000100000 | Loss 0.005021 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:18 Epoch 7 | Batch 2113/2891 | Timestep 22350 | LR 0.0000100000 | Loss 0.007817 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:19 Epoch 7 | Batch 2123/2891 | Timestep 22360 | LR 0.0000100000 | Loss 0.058101 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:21 Epoch 7 | Batch 2133/2891 | Timestep 22370 | LR 0.0000100000 | Loss 0.008859 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:22 Epoch 7 | Batch 2143/2891 | Timestep 22380 | LR 0.0000100000 | Loss 0.010686 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:24 Epoch 7 | Batch 2153/2891 | Timestep 22390 | LR 0.0000100000 | Loss 0.013815 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:26 Epoch 7 | Batch 2163/2891 | Timestep 22400 | LR 0.0000100000 | Loss 0.011840 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:28 Epoch 7 | Batch 2173/2891 | Timestep 22410 | LR 0.0000100000 | Loss 0.017244 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:29 Epoch 7 | Batch 2183/2891 | Timestep 22420 | LR 0.0000100000 | Loss 0.080052 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:31 Epoch 7 | Batch 2193/2891 | Timestep 22430 | LR 0.0000100000 | Loss 0.040531 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:32 Epoch 7 | Batch 2203/2891 | Timestep 22440 | LR 0.0000100000 | Loss 0.002211 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:34 Epoch 7 | Batch 2213/2891 | Timestep 22450 | LR 0.0000100000 | Loss 0.006194 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:36 Epoch 7 | Batch 2223/2891 | Timestep 22460 | LR 0.0000100000 | Loss 0.010644 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:37 Epoch 7 | Batch 2233/2891 | Timestep 22470 | LR 0.0000100000 | Loss 0.011082 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:39 Epoch 7 | Batch 2243/2891 | Timestep 22480 | LR 0.0000100000 | Loss 0.012323 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:41 Epoch 7 | Batch 2253/2891 | Timestep 22490 | LR 0.0000100000 | Loss 0.001311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:42 Epoch 7 | Batch 2263/2891 | Timestep 22500 | LR 0.0000100000 | Loss 0.076394 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:44 Epoch 7 | Batch 2273/2891 | Timestep 22510 | LR 0.0000100000 | Loss 0.011435 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:45 Epoch 7 | Batch 2283/2891 | Timestep 22520 | LR 0.0000100000 | Loss 0.034723 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:47 Epoch 7 | Batch 2293/2891 | Timestep 22530 | LR 0.0000100000 | Loss 0.001260 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:48 Epoch 7 | Batch 2303/2891 | Timestep 22540 | LR 0.0000100000 | Loss 0.028127 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:50 Epoch 7 | Batch 2313/2891 | Timestep 22550 | LR 0.0000100000 | Loss 0.015843 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:51 Epoch 7 | Batch 2323/2891 | Timestep 22560 | LR 0.0000100000 | Loss 0.009648 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:53 Epoch 7 | Batch 2333/2891 | Timestep 22570 | LR 0.0000100000 | Loss 0.007802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:54 Epoch 7 | Batch 2343/2891 | Timestep 22580 | LR 0.0000100000 | Loss 0.016624 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:55 Epoch 7 | Batch 2353/2891 | Timestep 22590 | LR 0.0000100000 | Loss 0.014889 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:57 Epoch 7 | Batch 2363/2891 | Timestep 22600 | LR 0.0000100000 | Loss 0.009311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:12:58 Epoch 7 | Batch 2373/2891 | Timestep 22610 | LR 0.0000100000 | Loss 0.007252 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:01 Epoch 7 | Batch 2383/2891 | Timestep 22620 | LR 0.0000100000 | Loss 0.001373 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:02 Epoch 7 | Batch 2393/2891 | Timestep 22630 | LR 0.0000100000 | Loss 0.013111 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:03 Epoch 7 | Batch 2403/2891 | Timestep 22640 | LR 0.0000100000 | Loss 0.000682 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:05 Epoch 7 | Batch 2413/2891 | Timestep 22650 | LR 0.0000100000 | Loss 0.001309 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:07 Epoch 7 | Batch 2423/2891 | Timestep 22660 | LR 0.0000100000 | Loss 0.011993 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:09 Epoch 7 | Batch 2433/2891 | Timestep 22670 | LR 0.0000100000 | Loss 0.010554 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:11 Epoch 7 | Batch 2443/2891 | Timestep 22680 | LR 0.0000100000 | Loss 0.047471 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:12 Epoch 7 | Batch 2453/2891 | Timestep 22690 | LR 0.0000100000 | Loss 0.006000 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:14 Epoch 7 | Batch 2463/2891 | Timestep 22700 | LR 0.0000100000 | Loss 0.034098 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:15 Epoch 7 | Batch 2473/2891 | Timestep 22710 | LR 0.0000100000 | Loss 0.004506 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:17 Epoch 7 | Batch 2483/2891 | Timestep 22720 | LR 0.0000100000 | Loss 0.002100 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:18 Epoch 7 | Batch 2493/2891 | Timestep 22730 | LR 0.0000100000 | Loss 0.003027 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:20 Epoch 7 | Batch 2503/2891 | Timestep 22740 | LR 0.0000100000 | Loss 0.000813 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:22 Epoch 7 | Batch 2513/2891 | Timestep 22750 | LR 0.0000100000 | Loss 0.001355 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:23 Epoch 7 | Batch 2523/2891 | Timestep 22760 | LR 0.0000100000 | Loss 0.013490 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:25 Epoch 7 | Batch 2533/2891 | Timestep 22770 | LR 0.0000100000 | Loss 0.000578 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:27 Epoch 7 | Batch 2543/2891 | Timestep 22780 | LR 0.0000100000 | Loss 0.004802 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:29 Epoch 7 | Batch 2553/2891 | Timestep 22790 | LR 0.0000100000 | Loss 0.010731 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:30 Epoch 7 | Batch 2563/2891 | Timestep 22800 | LR 0.0000100000 | Loss 0.003930 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:32 Epoch 7 | Batch 2573/2891 | Timestep 22810 | LR 0.0000100000 | Loss 0.000516 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:34 Epoch 7 | Batch 2583/2891 | Timestep 22820 | LR 0.0000100000 | Loss 0.025112 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:35 Epoch 7 | Batch 2593/2891 | Timestep 22830 | LR 0.0000100000 | Loss 0.024633 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:37 Epoch 7 | Batch 2603/2891 | Timestep 22840 | LR 0.0000100000 | Loss 0.024249 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:39 Epoch 7 | Batch 2613/2891 | Timestep 22850 | LR 0.0000100000 | Loss 0.011317 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:41 Epoch 7 | Batch 2623/2891 | Timestep 22860 | LR 0.0000100000 | Loss 0.012192 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:43 Epoch 7 | Batch 2633/2891 | Timestep 22870 | LR 0.0000100000 | Loss 0.003857 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:44 Epoch 7 | Batch 2643/2891 | Timestep 22880 | LR 0.0000100000 | Loss 0.004158 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:45 Epoch 7 | Batch 2653/2891 | Timestep 22890 | LR 0.0000100000 | Loss 0.013925 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:47 Epoch 7 | Batch 2663/2891 | Timestep 22900 | LR 0.0000100000 | Loss 0.008361 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:49 Epoch 7 | Batch 2673/2891 | Timestep 22910 | LR 0.0000100000 | Loss 0.003652 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:50 Epoch 7 | Batch 2683/2891 | Timestep 22920 | LR 0.0000100000 | Loss 0.032101 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:52 Epoch 7 | Batch 2693/2891 | Timestep 22930 | LR 0.0000100000 | Loss 0.014875 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:54 Epoch 7 | Batch 2703/2891 | Timestep 22940 | LR 0.0000100000 | Loss 0.003799 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:56 Epoch 7 | Batch 2713/2891 | Timestep 22950 | LR 0.0000100000 | Loss 0.020417 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:58 Epoch 7 | Batch 2723/2891 | Timestep 22960 | LR 0.0000100000 | Loss 0.023589 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:13:59 Epoch 7 | Batch 2733/2891 | Timestep 22970 | LR 0.0000100000 | Loss 0.027661 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:00 Epoch 7 | Batch 2743/2891 | Timestep 22980 | LR 0.0000100000 | Loss 0.012240 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:02 Epoch 7 | Batch 2753/2891 | Timestep 22990 | LR 0.0000100000 | Loss 0.015438 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:04 Epoch 7 | Batch 2763/2891 | Timestep 23000 | LR 0.0000100000 | Loss 0.024264 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:05 Epoch 7 | Batch 2773/2891 | Timestep 23010 | LR 0.0000100000 | Loss 0.076569 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:07 Epoch 7 | Batch 2783/2891 | Timestep 23020 | LR 0.0000100000 | Loss 0.020123 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:09 Epoch 7 | Batch 2793/2891 | Timestep 23030 | LR 0.0000100000 | Loss 0.004578 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:11 Epoch 7 | Batch 2803/2891 | Timestep 23040 | LR 0.0000100000 | Loss 0.016619 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:13 Epoch 7 | Batch 2813/2891 | Timestep 23050 | LR 0.0000100000 | Loss 0.000311 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:15 Epoch 7 | Batch 2823/2891 | Timestep 23060 | LR 0.0000100000 | Loss 0.002335 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:16 Epoch 7 | Batch 2833/2891 | Timestep 23070 | LR 0.0000100000 | Loss 0.020947 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:18 Epoch 7 | Batch 2843/2891 | Timestep 23080 | LR 0.0000100000 | Loss 0.020071 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:20 Epoch 7 | Batch 2853/2891 | Timestep 23090 | LR 0.0000100000 | Loss 0.002667 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:21 Epoch 7 | Batch 2863/2891 | Timestep 23100 | LR 0.0000100000 | Loss 0.010821 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:23 Epoch 7 | Batch 2873/2891 | Timestep 23110 | LR 0.0000100000 | Loss 0.012622 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:24 Epoch 7 | Batch 2883/2891 | Timestep 23120 | LR 0.0000100000 | Loss 0.005738 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:26 ** Evaluating on validation dataset ** INFO root Thu, 14 May 2026 12:14:42 precision recall f1-score support CARDINAL 0.9014 0.7529 0.8205 170 CURR 0.0000 0.0000 0.0000 2 DATE 0.6656 0.6715 0.6685 1592 EVENT 0.6372 0.7411 0.6852 282 FAC 0.6491 0.8043 0.7184 92 GPE 0.9093 0.9058 0.9075 1051 LANGUAGE 0.6316 0.7500 0.6857 16 LAW 0.6667 0.8511 0.7477 47 LOC 0.6489 0.8243 0.7262 74 MONEY 0.6250 0.9091 0.7407 22 NORP 0.6730 0.7657 0.7164 508 OCC 0.8555 0.8755 0.8654 514 ORDINAL 0.9365 0.9281 0.9323 445 ORG 0.8732 0.9297 0.9006 1578 PERCENT 0.9231 1.0000 0.9600 12 PERS 0.9510 0.9494 0.9502 613 PRODUCT 0.3333 0.3750 0.3529 8 QUANTITY 0.5000 0.6667 0.5714 3 TIME 0.7812 0.7576 0.7692 33 UNIT 0.0000 0.0000 0.0000 1 WEBSITE 0.6027 0.5500 0.5752 80 micro avg 0.8032 0.8333 0.8180 7143 macro avg 0.6554 0.7147 0.6807 7143 weighted avg 0.8063 0.8333 0.8187 7143 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:42 Epoch 7 | Timestep 23128 | Train Loss 0.014832 | Val Loss 0.059634 | F1 0.817976 INFO arabiner.trainers.BertTrainer Thu, 14 May 2026 12:14:42 Early termination triggered