INFO __main__ Tue, 23 Dec 2025 09:43:26 Writing config to /rep/nhamad/ArabicNER/data/output/dir/args.json INFO Nested.utils.data Tue, 23 Dec 2025 09:43:27 2891 batches found INFO Nested.utils.data Tue, 23 Dec 2025 09:43:28 413 batches found INFO Nested.utils.data Tue, 23 Dec 2025 09:43:28 826 batches found INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:32 Epoch 0 | Batch 10/2891 | Timestep 10 | LR 0.0001000000 | Loss 6.939085 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:33 Epoch 0 | Batch 20/2891 | Timestep 20 | LR 0.0001000000 | Loss 3.731117 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:35 Epoch 0 | Batch 30/2891 | Timestep 30 | LR 0.0001000000 | Loss 1.904723 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:36 Epoch 0 | Batch 40/2891 | Timestep 40 | LR 0.0001000000 | Loss 1.420470 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:38 Epoch 0 | Batch 50/2891 | Timestep 50 | LR 0.0001000000 | Loss 0.806771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:41 Epoch 0 | Batch 60/2891 | Timestep 60 | LR 0.0001000000 | Loss 0.712674 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:42 Epoch 0 | Batch 70/2891 | Timestep 70 | LR 0.0001000000 | Loss 0.652736 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:44 Epoch 0 | Batch 80/2891 | Timestep 80 | LR 0.0001000000 | Loss 0.647976 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:46 Epoch 0 | Batch 90/2891 | Timestep 90 | LR 0.0001000000 | Loss 1.051719 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:47 Epoch 0 | Batch 100/2891 | Timestep 100 | LR 0.0001000000 | Loss 0.942496 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:50 Epoch 0 | Batch 110/2891 | Timestep 110 | LR 0.0001000000 | Loss 0.289565 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:51 Epoch 0 | Batch 120/2891 | Timestep 120 | LR 0.0001000000 | Loss 0.494516 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:53 Epoch 0 | Batch 130/2891 | Timestep 130 | LR 0.0001000000 | Loss 0.778104 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:55 Epoch 0 | Batch 140/2891 | Timestep 140 | LR 0.0001000000 | Loss 0.547687 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:56 Epoch 0 | Batch 150/2891 | Timestep 150 | LR 0.0001000000 | Loss 0.263183 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:58 Epoch 0 | Batch 160/2891 | Timestep 160 | LR 0.0001000000 | Loss 0.307228 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:43:59 Epoch 0 | Batch 170/2891 | Timestep 170 | LR 0.0001000000 | Loss 0.582884 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:01 Epoch 0 | Batch 180/2891 | Timestep 180 | LR 0.0001000000 | Loss 0.219766 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:03 Epoch 0 | Batch 190/2891 | Timestep 190 | LR 0.0001000000 | Loss 0.340832 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:04 Epoch 0 | Batch 200/2891 | Timestep 200 | LR 0.0001000000 | Loss 0.489281 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:06 Epoch 0 | Batch 210/2891 | Timestep 210 | LR 0.0001000000 | Loss 0.239207 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:08 Epoch 0 | Batch 220/2891 | Timestep 220 | LR 0.0001000000 | Loss 0.220449 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:10 Epoch 0 | Batch 230/2891 | Timestep 230 | LR 0.0001000000 | Loss 0.297084 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:11 Epoch 0 | Batch 240/2891 | Timestep 240 | LR 0.0001000000 | Loss 0.182801 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:13 Epoch 0 | Batch 250/2891 | Timestep 250 | LR 0.0001000000 | Loss 0.226114 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:15 Epoch 0 | Batch 260/2891 | Timestep 260 | LR 0.0001000000 | Loss 0.310990 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:17 Epoch 0 | Batch 270/2891 | Timestep 270 | LR 0.0001000000 | Loss 0.203016 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:18 Epoch 0 | Batch 280/2891 | Timestep 280 | LR 0.0001000000 | Loss 0.092367 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:20 Epoch 0 | Batch 290/2891 | Timestep 290 | LR 0.0001000000 | Loss 0.282901 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:22 Epoch 0 | Batch 300/2891 | Timestep 300 | LR 0.0001000000 | Loss 0.097438 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:23 Epoch 0 | Batch 310/2891 | Timestep 310 | LR 0.0001000000 | Loss 0.139536 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:25 Epoch 0 | Batch 320/2891 | Timestep 320 | LR 0.0001000000 | Loss 0.106218 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:27 Epoch 0 | Batch 330/2891 | Timestep 330 | LR 0.0001000000 | Loss 0.177978 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:28 Epoch 0 | Batch 340/2891 | Timestep 340 | LR 0.0001000000 | Loss 0.173189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:30 Epoch 0 | Batch 350/2891 | Timestep 350 | LR 0.0001000000 | Loss 0.167986 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:32 Epoch 0 | Batch 360/2891 | Timestep 360 | LR 0.0001000000 | Loss 0.209917 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:34 Epoch 0 | Batch 370/2891 | Timestep 370 | LR 0.0001000000 | Loss 0.085462 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:35 Epoch 0 | Batch 380/2891 | Timestep 380 | LR 0.0001000000 | Loss 0.251995 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:37 Epoch 0 | Batch 390/2891 | Timestep 390 | LR 0.0001000000 | Loss 0.142407 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:39 Epoch 0 | Batch 400/2891 | Timestep 400 | LR 0.0001000000 | Loss 0.119381 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:40 Epoch 0 | Batch 410/2891 | Timestep 410 | LR 0.0001000000 | Loss 0.132973 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:42 Epoch 0 | Batch 420/2891 | Timestep 420 | LR 0.0001000000 | Loss 0.072097 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:44 Epoch 0 | Batch 430/2891 | Timestep 430 | LR 0.0001000000 | Loss 0.113462 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:46 Epoch 0 | Batch 440/2891 | Timestep 440 | LR 0.0001000000 | Loss 0.149065 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:47 Epoch 0 | Batch 450/2891 | Timestep 450 | LR 0.0001000000 | Loss 0.064541 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:49 Epoch 0 | Batch 460/2891 | Timestep 460 | LR 0.0001000000 | Loss 0.093540 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:50 Epoch 0 | Batch 470/2891 | Timestep 470 | LR 0.0001000000 | Loss 0.139632 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:52 Epoch 0 | Batch 480/2891 | Timestep 480 | LR 0.0001000000 | Loss 0.193303 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:54 Epoch 0 | Batch 490/2891 | Timestep 490 | LR 0.0001000000 | Loss 0.083639 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:55 Epoch 0 | Batch 500/2891 | Timestep 500 | LR 0.0001000000 | Loss 0.197932 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:57 Epoch 0 | Batch 510/2891 | Timestep 510 | LR 0.0001000000 | Loss 0.115858 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:44:59 Epoch 0 | Batch 520/2891 | Timestep 520 | LR 0.0001000000 | Loss 0.165172 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:00 Epoch 0 | Batch 530/2891 | Timestep 530 | LR 0.0001000000 | Loss 0.279716 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:02 Epoch 0 | Batch 540/2891 | Timestep 540 | LR 0.0001000000 | Loss 0.079432 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:04 Epoch 0 | Batch 550/2891 | Timestep 550 | LR 0.0001000000 | Loss 0.084338 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:06 Epoch 0 | Batch 560/2891 | Timestep 560 | LR 0.0001000000 | Loss 0.134286 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:07 Epoch 0 | Batch 570/2891 | Timestep 570 | LR 0.0001000000 | Loss 0.167335 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:10 Epoch 0 | Batch 580/2891 | Timestep 580 | LR 0.0001000000 | Loss 0.071815 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:11 Epoch 0 | Batch 590/2891 | Timestep 590 | LR 0.0001000000 | Loss 0.063625 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:13 Epoch 0 | Batch 600/2891 | Timestep 600 | LR 0.0001000000 | Loss 0.062781 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:15 Epoch 0 | Batch 610/2891 | Timestep 610 | LR 0.0001000000 | Loss 0.116745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:16 Epoch 0 | Batch 620/2891 | Timestep 620 | LR 0.0001000000 | Loss 0.211086 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:18 Epoch 0 | Batch 630/2891 | Timestep 630 | LR 0.0001000000 | Loss 0.059800 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:20 Epoch 0 | Batch 640/2891 | Timestep 640 | LR 0.0001000000 | Loss 0.055765 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:21 Epoch 0 | Batch 650/2891 | Timestep 650 | LR 0.0001000000 | Loss 0.165931 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:23 Epoch 0 | Batch 660/2891 | Timestep 660 | LR 0.0001000000 | Loss 0.152339 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:25 Epoch 0 | Batch 670/2891 | Timestep 670 | LR 0.0001000000 | Loss 0.056822 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:27 Epoch 0 | Batch 680/2891 | Timestep 680 | LR 0.0001000000 | Loss 0.136750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:28 Epoch 0 | Batch 690/2891 | Timestep 690 | LR 0.0001000000 | Loss 0.127157 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:30 Epoch 0 | Batch 700/2891 | Timestep 700 | LR 0.0001000000 | Loss 0.106594 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:31 Epoch 0 | Batch 710/2891 | Timestep 710 | LR 0.0001000000 | Loss 0.044767 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:33 Epoch 0 | Batch 720/2891 | Timestep 720 | LR 0.0001000000 | Loss 0.294792 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:34 Epoch 0 | Batch 730/2891 | Timestep 730 | LR 0.0001000000 | Loss 0.124042 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:36 Epoch 0 | Batch 740/2891 | Timestep 740 | LR 0.0001000000 | Loss 0.056024 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:38 Epoch 0 | Batch 750/2891 | Timestep 750 | LR 0.0001000000 | Loss 0.154074 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:39 Epoch 0 | Batch 760/2891 | Timestep 760 | LR 0.0001000000 | Loss 0.071442 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:41 Epoch 0 | Batch 770/2891 | Timestep 770 | LR 0.0001000000 | Loss 0.026047 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:42 Epoch 0 | Batch 780/2891 | Timestep 780 | LR 0.0001000000 | Loss 0.112215 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:44 Epoch 0 | Batch 790/2891 | Timestep 790 | LR 0.0001000000 | Loss 0.140988 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:46 Epoch 0 | Batch 800/2891 | Timestep 800 | LR 0.0001000000 | Loss 0.204217 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:47 Epoch 0 | Batch 810/2891 | Timestep 810 | LR 0.0001000000 | Loss 0.153647 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:49 Epoch 0 | Batch 820/2891 | Timestep 820 | LR 0.0001000000 | Loss 0.113921 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:51 Epoch 0 | Batch 830/2891 | Timestep 830 | LR 0.0001000000 | Loss 0.056434 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:53 Epoch 0 | Batch 840/2891 | Timestep 840 | LR 0.0001000000 | Loss 0.071781 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:55 Epoch 0 | Batch 850/2891 | Timestep 850 | LR 0.0001000000 | Loss 0.113887 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:57 Epoch 0 | Batch 860/2891 | Timestep 860 | LR 0.0001000000 | Loss 0.049871 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:45:59 Epoch 0 | Batch 870/2891 | Timestep 870 | LR 0.0001000000 | Loss 0.064306 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:00 Epoch 0 | Batch 880/2891 | Timestep 880 | LR 0.0001000000 | Loss 0.069757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:02 Epoch 0 | Batch 890/2891 | Timestep 890 | LR 0.0001000000 | Loss 0.052002 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:04 Epoch 0 | Batch 900/2891 | Timestep 900 | LR 0.0001000000 | Loss 0.143188 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:06 Epoch 0 | Batch 910/2891 | Timestep 910 | LR 0.0001000000 | Loss 0.064515 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:07 Epoch 0 | Batch 920/2891 | Timestep 920 | LR 0.0001000000 | Loss 0.161029 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:09 Epoch 0 | Batch 930/2891 | Timestep 930 | LR 0.0001000000 | Loss 0.138872 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:11 Epoch 0 | Batch 940/2891 | Timestep 940 | LR 0.0001000000 | Loss 0.100031 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:13 Epoch 0 | Batch 950/2891 | Timestep 950 | LR 0.0001000000 | Loss 0.100934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:14 Epoch 0 | Batch 960/2891 | Timestep 960 | LR 0.0001000000 | Loss 0.060023 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:16 Epoch 0 | Batch 970/2891 | Timestep 970 | LR 0.0001000000 | Loss 0.081953 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:18 Epoch 0 | Batch 980/2891 | Timestep 980 | LR 0.0001000000 | Loss 0.162022 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:20 Epoch 0 | Batch 990/2891 | Timestep 990 | LR 0.0001000000 | Loss 0.023844 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:22 Epoch 0 | Batch 1000/2891 | Timestep 1000 | LR 0.0001000000 | Loss 0.078554 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:23 Epoch 0 | Batch 1010/2891 | Timestep 1010 | LR 0.0001000000 | Loss 0.090246 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:25 Epoch 0 | Batch 1020/2891 | Timestep 1020 | LR 0.0001000000 | Loss 0.070273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:26 Epoch 0 | Batch 1030/2891 | Timestep 1030 | LR 0.0001000000 | Loss 0.127764 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:28 Epoch 0 | Batch 1040/2891 | Timestep 1040 | LR 0.0001000000 | Loss 0.029789 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:30 Epoch 0 | Batch 1050/2891 | Timestep 1050 | LR 0.0001000000 | Loss 0.148893 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:32 Epoch 0 | Batch 1060/2891 | Timestep 1060 | LR 0.0001000000 | Loss 0.076614 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:34 Epoch 0 | Batch 1070/2891 | Timestep 1070 | LR 0.0001000000 | Loss 0.089607 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:35 Epoch 0 | Batch 1080/2891 | Timestep 1080 | LR 0.0001000000 | Loss 0.157943 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:36 Epoch 0 | Batch 1090/2891 | Timestep 1090 | LR 0.0001000000 | Loss 0.325307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:38 Epoch 0 | Batch 1100/2891 | Timestep 1100 | LR 0.0001000000 | Loss 0.048137 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:39 Epoch 0 | Batch 1110/2891 | Timestep 1110 | LR 0.0001000000 | Loss 0.027572 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:41 Epoch 0 | Batch 1120/2891 | Timestep 1120 | LR 0.0001000000 | Loss 0.120659 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:43 Epoch 0 | Batch 1130/2891 | Timestep 1130 | LR 0.0001000000 | Loss 0.077486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:45 Epoch 0 | Batch 1140/2891 | Timestep 1140 | LR 0.0001000000 | Loss 0.101891 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:46 Epoch 0 | Batch 1150/2891 | Timestep 1150 | LR 0.0001000000 | Loss 0.021666 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:48 Epoch 0 | Batch 1160/2891 | Timestep 1160 | LR 0.0001000000 | Loss 0.069615 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:49 Epoch 0 | Batch 1170/2891 | Timestep 1170 | LR 0.0001000000 | Loss 0.039655 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:51 Epoch 0 | Batch 1180/2891 | Timestep 1180 | LR 0.0001000000 | Loss 0.048126 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:53 Epoch 0 | Batch 1190/2891 | Timestep 1190 | LR 0.0001000000 | Loss 0.093643 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:54 Epoch 0 | Batch 1200/2891 | Timestep 1200 | LR 0.0001000000 | Loss 0.018792 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:56 Epoch 0 | Batch 1210/2891 | Timestep 1210 | LR 0.0001000000 | Loss 0.066973 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:46:58 Epoch 0 | Batch 1220/2891 | Timestep 1220 | LR 0.0001000000 | Loss 0.079094 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:00 Epoch 0 | Batch 1230/2891 | Timestep 1230 | LR 0.0001000000 | Loss 0.043607 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:01 Epoch 0 | Batch 1240/2891 | Timestep 1240 | LR 0.0001000000 | Loss 0.162373 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:03 Epoch 0 | Batch 1250/2891 | Timestep 1250 | LR 0.0001000000 | Loss 0.057931 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:05 Epoch 0 | Batch 1260/2891 | Timestep 1260 | LR 0.0001000000 | Loss 0.044323 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:06 Epoch 0 | Batch 1270/2891 | Timestep 1270 | LR 0.0001000000 | Loss 0.090407 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:08 Epoch 0 | Batch 1280/2891 | Timestep 1280 | LR 0.0001000000 | Loss 0.027798 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:09 Epoch 0 | Batch 1290/2891 | Timestep 1290 | LR 0.0001000000 | Loss 0.052124 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:11 Epoch 0 | Batch 1300/2891 | Timestep 1300 | LR 0.0001000000 | Loss 0.057364 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:13 Epoch 0 | Batch 1310/2891 | Timestep 1310 | LR 0.0001000000 | Loss 0.222210 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:15 Epoch 0 | Batch 1320/2891 | Timestep 1320 | LR 0.0001000000 | Loss 0.069990 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:16 Epoch 0 | Batch 1330/2891 | Timestep 1330 | LR 0.0001000000 | Loss 0.043431 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:19 Epoch 0 | Batch 1340/2891 | Timestep 1340 | LR 0.0001000000 | Loss 0.043095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:20 Epoch 0 | Batch 1350/2891 | Timestep 1350 | LR 0.0001000000 | Loss 0.080673 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:22 Epoch 0 | Batch 1360/2891 | Timestep 1360 | LR 0.0001000000 | Loss 0.106310 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:24 Epoch 0 | Batch 1370/2891 | Timestep 1370 | LR 0.0001000000 | Loss 0.030761 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:25 Epoch 0 | Batch 1380/2891 | Timestep 1380 | LR 0.0001000000 | Loss 0.053051 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:27 Epoch 0 | Batch 1390/2891 | Timestep 1390 | LR 0.0001000000 | Loss 0.015356 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:28 Epoch 0 | Batch 1400/2891 | Timestep 1400 | LR 0.0001000000 | Loss 0.049542 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:30 Epoch 0 | Batch 1410/2891 | Timestep 1410 | LR 0.0001000000 | Loss 0.081212 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:32 Epoch 0 | Batch 1420/2891 | Timestep 1420 | LR 0.0001000000 | Loss 0.046783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:34 Epoch 0 | Batch 1430/2891 | Timestep 1430 | LR 0.0001000000 | Loss 0.065819 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:35 Epoch 0 | Batch 1440/2891 | Timestep 1440 | LR 0.0001000000 | Loss 0.038971 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:37 Epoch 0 | Batch 1450/2891 | Timestep 1450 | LR 0.0001000000 | Loss 0.037208 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:38 Epoch 0 | Batch 1460/2891 | Timestep 1460 | LR 0.0001000000 | Loss 0.011286 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:40 Epoch 0 | Batch 1470/2891 | Timestep 1470 | LR 0.0001000000 | Loss 0.133052 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:42 Epoch 0 | Batch 1480/2891 | Timestep 1480 | LR 0.0001000000 | Loss 0.047082 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:43 Epoch 0 | Batch 1490/2891 | Timestep 1490 | LR 0.0001000000 | Loss 0.037236 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:45 Epoch 0 | Batch 1500/2891 | Timestep 1500 | LR 0.0001000000 | Loss 0.107130 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:46 Epoch 0 | Batch 1510/2891 | Timestep 1510 | LR 0.0001000000 | Loss 0.038035 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:48 Epoch 0 | Batch 1520/2891 | Timestep 1520 | LR 0.0001000000 | Loss 0.104783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:51 Epoch 0 | Batch 1530/2891 | Timestep 1530 | LR 0.0001000000 | Loss 0.029887 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:52 Epoch 0 | Batch 1540/2891 | Timestep 1540 | LR 0.0001000000 | Loss 0.126023 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:54 Epoch 0 | Batch 1550/2891 | Timestep 1550 | LR 0.0001000000 | Loss 0.050247 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:55 Epoch 0 | Batch 1560/2891 | Timestep 1560 | LR 0.0001000000 | Loss 0.016403 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:57 Epoch 0 | Batch 1570/2891 | Timestep 1570 | LR 0.0001000000 | Loss 0.036006 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:47:59 Epoch 0 | Batch 1580/2891 | Timestep 1580 | LR 0.0001000000 | Loss 0.111354 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:00 Epoch 0 | Batch 1590/2891 | Timestep 1590 | LR 0.0001000000 | Loss 0.034764 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:02 Epoch 0 | Batch 1600/2891 | Timestep 1600 | LR 0.0001000000 | Loss 0.091473 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:03 Epoch 0 | Batch 1610/2891 | Timestep 1610 | LR 0.0001000000 | Loss 0.104137 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:05 Epoch 0 | Batch 1620/2891 | Timestep 1620 | LR 0.0001000000 | Loss 0.077645 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:07 Epoch 0 | Batch 1630/2891 | Timestep 1630 | LR 0.0001000000 | Loss 0.102078 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:08 Epoch 0 | Batch 1640/2891 | Timestep 1640 | LR 0.0001000000 | Loss 0.038341 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:10 Epoch 0 | Batch 1650/2891 | Timestep 1650 | LR 0.0001000000 | Loss 0.092954 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:11 Epoch 0 | Batch 1660/2891 | Timestep 1660 | LR 0.0001000000 | Loss 0.034747 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:13 Epoch 0 | Batch 1670/2891 | Timestep 1670 | LR 0.0001000000 | Loss 0.044327 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:14 Epoch 0 | Batch 1680/2891 | Timestep 1680 | LR 0.0001000000 | Loss 0.026144 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:16 Epoch 0 | Batch 1690/2891 | Timestep 1690 | LR 0.0001000000 | Loss 0.023523 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:18 Epoch 0 | Batch 1700/2891 | Timestep 1700 | LR 0.0001000000 | Loss 0.008389 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:19 Epoch 0 | Batch 1710/2891 | Timestep 1710 | LR 0.0001000000 | Loss 0.058862 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:21 Epoch 0 | Batch 1720/2891 | Timestep 1720 | LR 0.0001000000 | Loss 0.100601 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:23 Epoch 0 | Batch 1730/2891 | Timestep 1730 | LR 0.0001000000 | Loss 0.030822 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:24 Epoch 0 | Batch 1740/2891 | Timestep 1740 | LR 0.0001000000 | Loss 0.097385 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:26 Epoch 0 | Batch 1750/2891 | Timestep 1750 | LR 0.0001000000 | Loss 0.017355 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:28 Epoch 0 | Batch 1760/2891 | Timestep 1760 | LR 0.0001000000 | Loss 0.021902 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:29 Epoch 0 | Batch 1770/2891 | Timestep 1770 | LR 0.0001000000 | Loss 0.063560 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:31 Epoch 0 | Batch 1780/2891 | Timestep 1780 | LR 0.0001000000 | Loss 0.179277 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:32 Epoch 0 | Batch 1790/2891 | Timestep 1790 | LR 0.0001000000 | Loss 0.082214 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:34 Epoch 0 | Batch 1800/2891 | Timestep 1800 | LR 0.0001000000 | Loss 0.013410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:36 Epoch 0 | Batch 1810/2891 | Timestep 1810 | LR 0.0001000000 | Loss 0.033452 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:38 Epoch 0 | Batch 1820/2891 | Timestep 1820 | LR 0.0001000000 | Loss 0.120648 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:39 Epoch 0 | Batch 1830/2891 | Timestep 1830 | LR 0.0001000000 | Loss 0.039758 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:41 Epoch 0 | Batch 1840/2891 | Timestep 1840 | LR 0.0001000000 | Loss 0.011330 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:43 Epoch 0 | Batch 1850/2891 | Timestep 1850 | LR 0.0001000000 | Loss 0.025853 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:44 Epoch 0 | Batch 1860/2891 | Timestep 1860 | LR 0.0001000000 | Loss 0.155653 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:46 Epoch 0 | Batch 1870/2891 | Timestep 1870 | LR 0.0001000000 | Loss 0.161299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:48 Epoch 0 | Batch 1880/2891 | Timestep 1880 | LR 0.0001000000 | Loss 0.113574 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:49 Epoch 0 | Batch 1890/2891 | Timestep 1890 | LR 0.0001000000 | Loss 0.027916 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:51 Epoch 0 | Batch 1900/2891 | Timestep 1900 | LR 0.0001000000 | Loss 0.102828 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:53 Epoch 0 | Batch 1910/2891 | Timestep 1910 | LR 0.0001000000 | Loss 0.033811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:54 Epoch 0 | Batch 1920/2891 | Timestep 1920 | LR 0.0001000000 | Loss 0.119787 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:56 Epoch 0 | Batch 1930/2891 | Timestep 1930 | LR 0.0001000000 | Loss 0.105287 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:48:58 Epoch 0 | Batch 1940/2891 | Timestep 1940 | LR 0.0001000000 | Loss 0.051442 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:00 Epoch 0 | Batch 1950/2891 | Timestep 1950 | LR 0.0001000000 | Loss 0.022454 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:01 Epoch 0 | Batch 1960/2891 | Timestep 1960 | LR 0.0001000000 | Loss 0.021548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:03 Epoch 0 | Batch 1970/2891 | Timestep 1970 | LR 0.0001000000 | Loss 0.056039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:05 Epoch 0 | Batch 1980/2891 | Timestep 1980 | LR 0.0001000000 | Loss 0.086076 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:07 Epoch 0 | Batch 1990/2891 | Timestep 1990 | LR 0.0001000000 | Loss 0.048253 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:08 Epoch 0 | Batch 2000/2891 | Timestep 2000 | LR 0.0001000000 | Loss 0.041601 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:10 Epoch 0 | Batch 2010/2891 | Timestep 2010 | LR 0.0001000000 | Loss 0.041410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:12 Epoch 0 | Batch 2020/2891 | Timestep 2020 | LR 0.0001000000 | Loss 0.192061 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:13 Epoch 0 | Batch 2030/2891 | Timestep 2030 | LR 0.0001000000 | Loss 0.059617 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:15 Epoch 0 | Batch 2040/2891 | Timestep 2040 | LR 0.0001000000 | Loss 0.077294 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:16 Epoch 0 | Batch 2050/2891 | Timestep 2050 | LR 0.0001000000 | Loss 0.044703 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:18 Epoch 0 | Batch 2060/2891 | Timestep 2060 | LR 0.0001000000 | Loss 0.056589 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:20 Epoch 0 | Batch 2070/2891 | Timestep 2070 | LR 0.0001000000 | Loss 0.034260 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:21 Epoch 0 | Batch 2080/2891 | Timestep 2080 | LR 0.0001000000 | Loss 0.062056 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:23 Epoch 0 | Batch 2090/2891 | Timestep 2090 | LR 0.0001000000 | Loss 0.032618 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:24 Epoch 0 | Batch 2100/2891 | Timestep 2100 | LR 0.0001000000 | Loss 0.046413 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:26 Epoch 0 | Batch 2110/2891 | Timestep 2110 | LR 0.0001000000 | Loss 0.130513 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:28 Epoch 0 | Batch 2120/2891 | Timestep 2120 | LR 0.0001000000 | Loss 0.062513 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:29 Epoch 0 | Batch 2130/2891 | Timestep 2130 | LR 0.0001000000 | Loss 0.059739 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:31 Epoch 0 | Batch 2140/2891 | Timestep 2140 | LR 0.0001000000 | Loss 0.028270 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:32 Epoch 0 | Batch 2150/2891 | Timestep 2150 | LR 0.0001000000 | Loss 0.065363 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:34 Epoch 0 | Batch 2160/2891 | Timestep 2160 | LR 0.0001000000 | Loss 0.045221 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:36 Epoch 0 | Batch 2170/2891 | Timestep 2170 | LR 0.0001000000 | Loss 0.150090 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:38 Epoch 0 | Batch 2180/2891 | Timestep 2180 | LR 0.0001000000 | Loss 0.026200 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:40 Epoch 0 | Batch 2190/2891 | Timestep 2190 | LR 0.0001000000 | Loss 0.073925 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:41 Epoch 0 | Batch 2200/2891 | Timestep 2200 | LR 0.0001000000 | Loss 0.102306 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:43 Epoch 0 | Batch 2210/2891 | Timestep 2210 | LR 0.0001000000 | Loss 0.021686 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:46 Epoch 0 | Batch 2220/2891 | Timestep 2220 | LR 0.0001000000 | Loss 0.070568 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:48 Epoch 0 | Batch 2230/2891 | Timestep 2230 | LR 0.0001000000 | Loss 0.055629 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:50 Epoch 0 | Batch 2240/2891 | Timestep 2240 | LR 0.0001000000 | Loss 0.073778 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:51 Epoch 0 | Batch 2250/2891 | Timestep 2250 | LR 0.0001000000 | Loss 0.042875 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:53 Epoch 0 | Batch 2260/2891 | Timestep 2260 | LR 0.0001000000 | Loss 0.070234 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:55 Epoch 0 | Batch 2270/2891 | Timestep 2270 | LR 0.0001000000 | Loss 0.026821 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:56 Epoch 0 | Batch 2280/2891 | Timestep 2280 | LR 0.0001000000 | Loss 0.057747 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:49:58 Epoch 0 | Batch 2290/2891 | Timestep 2290 | LR 0.0001000000 | Loss 0.121808 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:00 Epoch 0 | Batch 2300/2891 | Timestep 2300 | LR 0.0001000000 | Loss 0.073832 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:01 Epoch 0 | Batch 2310/2891 | Timestep 2310 | LR 0.0001000000 | Loss 0.028834 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:03 Epoch 0 | Batch 2320/2891 | Timestep 2320 | LR 0.0001000000 | Loss 0.068290 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:05 Epoch 0 | Batch 2330/2891 | Timestep 2330 | LR 0.0001000000 | Loss 0.060179 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:06 Epoch 0 | Batch 2340/2891 | Timestep 2340 | LR 0.0001000000 | Loss 0.011495 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:08 Epoch 0 | Batch 2350/2891 | Timestep 2350 | LR 0.0001000000 | Loss 0.155385 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:09 Epoch 0 | Batch 2360/2891 | Timestep 2360 | LR 0.0001000000 | Loss 0.022517 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:11 Epoch 0 | Batch 2370/2891 | Timestep 2370 | LR 0.0001000000 | Loss 0.044439 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:12 Epoch 0 | Batch 2380/2891 | Timestep 2380 | LR 0.0001000000 | Loss 0.018189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:14 Epoch 0 | Batch 2390/2891 | Timestep 2390 | LR 0.0001000000 | Loss 0.051695 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:16 Epoch 0 | Batch 2400/2891 | Timestep 2400 | LR 0.0001000000 | Loss 0.030302 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:17 Epoch 0 | Batch 2410/2891 | Timestep 2410 | LR 0.0001000000 | Loss 0.068410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:19 Epoch 0 | Batch 2420/2891 | Timestep 2420 | LR 0.0001000000 | Loss 0.165307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:21 Epoch 0 | Batch 2430/2891 | Timestep 2430 | LR 0.0001000000 | Loss 0.046429 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:23 Epoch 0 | Batch 2440/2891 | Timestep 2440 | LR 0.0001000000 | Loss 0.035548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:25 Epoch 0 | Batch 2450/2891 | Timestep 2450 | LR 0.0001000000 | Loss 0.124647 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:26 Epoch 0 | Batch 2460/2891 | Timestep 2460 | LR 0.0001000000 | Loss 0.031894 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:28 Epoch 0 | Batch 2470/2891 | Timestep 2470 | LR 0.0001000000 | Loss 0.013844 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:29 Epoch 0 | Batch 2480/2891 | Timestep 2480 | LR 0.0001000000 | Loss 0.012765 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:31 Epoch 0 | Batch 2490/2891 | Timestep 2490 | LR 0.0001000000 | Loss 0.035038 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:33 Epoch 0 | Batch 2500/2891 | Timestep 2500 | LR 0.0001000000 | Loss 0.031784 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:34 Epoch 0 | Batch 2510/2891 | Timestep 2510 | LR 0.0001000000 | Loss 0.039907 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:36 Epoch 0 | Batch 2520/2891 | Timestep 2520 | LR 0.0001000000 | Loss 0.163819 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:37 Epoch 0 | Batch 2530/2891 | Timestep 2530 | LR 0.0001000000 | Loss 0.076518 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:39 Epoch 0 | Batch 2540/2891 | Timestep 2540 | LR 0.0001000000 | Loss 0.081562 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:41 Epoch 0 | Batch 2550/2891 | Timestep 2550 | LR 0.0001000000 | Loss 0.175616 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:43 Epoch 0 | Batch 2560/2891 | Timestep 2560 | LR 0.0001000000 | Loss 0.135163 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:44 Epoch 0 | Batch 2570/2891 | Timestep 2570 | LR 0.0001000000 | Loss 0.097729 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:46 Epoch 0 | Batch 2580/2891 | Timestep 2580 | LR 0.0001000000 | Loss 0.019624 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:47 Epoch 0 | Batch 2590/2891 | Timestep 2590 | LR 0.0001000000 | Loss 0.089746 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:50 Epoch 0 | Batch 2600/2891 | Timestep 2600 | LR 0.0001000000 | Loss 0.056024 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:51 Epoch 0 | Batch 2610/2891 | Timestep 2610 | LR 0.0001000000 | Loss 0.031756 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:53 Epoch 0 | Batch 2620/2891 | Timestep 2620 | LR 0.0001000000 | Loss 0.205120 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:55 Epoch 0 | Batch 2630/2891 | Timestep 2630 | LR 0.0001000000 | Loss 0.039750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:57 Epoch 0 | Batch 2640/2891 | Timestep 2640 | LR 0.0001000000 | Loss 0.068238 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:50:58 Epoch 0 | Batch 2650/2891 | Timestep 2650 | LR 0.0001000000 | Loss 0.037984 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:00 Epoch 0 | Batch 2660/2891 | Timestep 2660 | LR 0.0001000000 | Loss 0.043745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:01 Epoch 0 | Batch 2670/2891 | Timestep 2670 | LR 0.0001000000 | Loss 0.033140 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:03 Epoch 0 | Batch 2680/2891 | Timestep 2680 | LR 0.0001000000 | Loss 0.066204 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:06 Epoch 0 | Batch 2690/2891 | Timestep 2690 | LR 0.0001000000 | Loss 0.079556 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:07 Epoch 0 | Batch 2700/2891 | Timestep 2700 | LR 0.0001000000 | Loss 0.125426 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:09 Epoch 0 | Batch 2710/2891 | Timestep 2710 | LR 0.0001000000 | Loss 0.092932 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:10 Epoch 0 | Batch 2720/2891 | Timestep 2720 | LR 0.0001000000 | Loss 0.122840 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:12 Epoch 0 | Batch 2730/2891 | Timestep 2730 | LR 0.0001000000 | Loss 0.267140 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:14 Epoch 0 | Batch 2740/2891 | Timestep 2740 | LR 0.0001000000 | Loss 0.178183 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:16 Epoch 0 | Batch 2750/2891 | Timestep 2750 | LR 0.0001000000 | Loss 0.039821 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:17 Epoch 0 | Batch 2760/2891 | Timestep 2760 | LR 0.0001000000 | Loss 0.306144 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:19 Epoch 0 | Batch 2770/2891 | Timestep 2770 | LR 0.0001000000 | Loss 0.073155 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:21 Epoch 0 | Batch 2780/2891 | Timestep 2780 | LR 0.0001000000 | Loss 0.138891 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:22 Epoch 0 | Batch 2790/2891 | Timestep 2790 | LR 0.0001000000 | Loss 0.186811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:24 Epoch 0 | Batch 2800/2891 | Timestep 2800 | LR 0.0001000000 | Loss 0.123630 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:26 Epoch 0 | Batch 2810/2891 | Timestep 2810 | LR 0.0001000000 | Loss 0.081678 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:27 Epoch 0 | Batch 2820/2891 | Timestep 2820 | LR 0.0001000000 | Loss 0.064584 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:29 Epoch 0 | Batch 2830/2891 | Timestep 2830 | LR 0.0001000000 | Loss 0.198621 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:31 Epoch 0 | Batch 2840/2891 | Timestep 2840 | LR 0.0001000000 | Loss 0.061863 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:32 Epoch 0 | Batch 2850/2891 | Timestep 2850 | LR 0.0001000000 | Loss 0.096578 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:34 Epoch 0 | Batch 2860/2891 | Timestep 2860 | LR 0.0001000000 | Loss 0.143616 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:36 Epoch 0 | Batch 2870/2891 | Timestep 2870 | LR 0.0001000000 | Loss 0.170677 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:37 Epoch 0 | Batch 2880/2891 | Timestep 2880 | LR 0.0001000000 | Loss 0.100524 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:39 Epoch 0 | Batch 2890/2891 | Timestep 2890 | LR 0.0001000000 | Loss 0.228362 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:51:39 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 09:52:14 precision recall f1-score support CARDINAL 0.8056 0.6824 0.7389 170 CURR 0.5714 0.5000 0.5333 24 DATE 0.8996 0.8421 0.8699 1691 EVENT 0.6310 0.5856 0.6075 292 FAC 0.6389 0.5847 0.6106 118 GPE 0.9495 0.8636 0.9045 2156 LANGUAGE 0.8182 0.5625 0.6667 16 LAW 0.4789 0.7234 0.5763 47 LOC 0.5660 0.3333 0.4196 90 MONEY 0.4000 0.4545 0.4255 22 NORP 0.6280 0.5299 0.5748 551 OCC 0.7785 0.7203 0.7483 522 ORDINAL 0.9244 0.8088 0.8627 544 ORG 0.8169 0.8677 0.8415 1882 PERCENT 0.6875 0.9167 0.7857 12 PERS 0.9027 0.7511 0.8199 679 PRODUCT 0.0000 0.0000 0.0000 8 QUANTITY 0.0000 0.0000 0.0000 3 TIME 0.7826 0.5455 0.6429 33 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.0222 0.0125 0.0160 80 micro avg 0.8433 0.7850 0.8131 8944 macro avg 0.6334 0.5731 0.5953 8944 weighted avg 0.8407 0.7850 0.8102 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:52:25 Epoch 0 | Timestep 2891 | Train Loss 0.192132 | Val Loss 0.125252 | F1 0.813086 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:52:25 ** Validation improved, evaluating test data ** INFO Nested.data.transforms Tue, 23 Dec 2025 09:52:47 Truncating the sequence لكن صوت جوالي مزعج ما دفعني للنهوض وبعصبية وارتباك من هذا الاتصال وخصوصا أن الساعة الواحدة والنصف يعنى عز دين النوم فأمسكت الجوال وقمت بالضغط على زر الرد . فقلت الو مين معي فقال معك الرئيس فقلت رئيس مين بالضبط فقال جورج بوش رئيس الولايات المتحدة الأمريكية فقلت اهلا أهلا يا سيادة الرئيس , بس أنا على حد علمي انه الرئيس جورج بوش بتكلم اللغة الانجليزية فكيف أنت بتحكي عربي بوش انأ بتكلم اللغة العربية جيدا حتى أنى ممكن أحكى باللهجة الغزواية . فقلت عليك اه خير شو مالك متصل فيا وكيف عرفت رقمي بوش ما في شي قلت أسال كيف أهل غزة بجو الحصار أما كيف عرفت رقمك فقلت لمديرة مكتبي أعطيني اتصال مباشر مع اى شخص من غزة فقلت غزة ااه بدك تعرف أخبار غزة صامدين صامدين ومش راح نتخلى عن الثوابت الفلسطينية لو شو ما تعملوا بوش يعنى بدك تقنعني انه ما فى نتيجة من الحصار فقلت لا ما في نتيجة لأنه إحنا بنخاف على بعض وبنحب بعض حتى رغيف الخبز مرات بنتقاسموا بوش اه واضح حتى التعذيب بتتقاسموه بالضفة وغزة فقلت يا عمى هيك عارف كل شى , شو بدك من الأخر لأني بدى أنام بوش شو رأيك تحضر مؤتمر انابولس فقلت احضر شو , شمعنا أنا يعني بوش هيك اجت فى بالى الفكرة فقلت لا لا مش فاضى , ميش مستعد اضيع وقتي في شي عارف نهايته بوش طيب تابعنا على التلفزيون منه بتعرف شو صار قلت صدقني وقتي فل , بكون بقرا بكتاب الجنة لا تبعد كثيرا بوش غريبة أول إنسان عربي ادعوه على المؤتمر ويكون وقته مشغول قلت شكلوا الكل مضيوف بالبيت الأبيض بوش اه مليان مش عارف أتحرك براحتي مخنوق فقلت اذا انت مخنوق شو نقول احنا بوش عارف بحاول معهم لكن لا حياة لمن تنادى من الطرفين وحابب اخذ رايك بالموضوع هل فى امل ? فقلت : رأي انك تستقيل قبل مؤتمر انابولس واكسب بياض الوجه وسيبك من الشرق الأوسط صدقني ما بتستاهلوا شي بوش : لا وحياتك راح يستقيل اولمرت وعباس اذا صار شي فقلت : اسمحي بدى أنام نعسان , بس دير بالك على العراق وأفغانستان اصلو بسمع انه في قتلي بشكل غريب بوش : وما تقلق راح أتوصي بإيران كويس وراح نعمل الوطن العربي كله سلطة قلت : طيب يالله سلام بوش : بس ما تنسانى قلت : له / هو فى حدا راح ينساك وانقطع حلمي برنه جوال حقيقة شرذمت ما تبقى من الحلم , فاعذروني فما هذه المكالمة إلا من عتمة أفكاري فأتمنى للرئيس عباس كل التوفيق وأرجو الا يكون هذا المؤتمر هو رحلة حب قصيرة الأمد . to 510 INFO root Tue, 23 Dec 2025 09:53:08 Predictions written to /rep/nhamad/ArabicNER/data/output/dir/predictions.txt INFO root Tue, 23 Dec 2025 09:53:34 precision recall f1-score support CARDINAL 0.7926 0.6930 0.7395 342 CURR 0.5385 0.5122 0.5250 41 DATE 0.9072 0.8537 0.8796 3206 EVENT 0.6808 0.6211 0.6495 570 FAC 0.6147 0.5537 0.5826 242 GPE 0.9496 0.8699 0.9080 4336 LANGUAGE 0.8710 0.6136 0.7200 44 LAW 0.5154 0.7444 0.6091 90 LOC 0.4962 0.2982 0.3725 218 MONEY 0.5128 0.6061 0.5556 33 NORP 0.6987 0.5581 0.6205 1093 OCC 0.7949 0.7135 0.7520 1103 ORDINAL 0.9290 0.8098 0.8653 1083 ORG 0.8038 0.8573 0.8297 3798 PERCENT 0.1913 0.6667 0.2973 33 PERS 0.9151 0.7634 0.8324 1568 PRODUCT 0.0000 0.0000 0.0000 19 QUANTITY 0.0000 0.0000 0.0000 9 TIME 0.7500 0.5000 0.6000 84 UNIT 0.8000 0.3636 0.5000 11 WEBSITE 0.0500 0.0259 0.0341 116 micro avg 0.8466 0.7890 0.8168 18039 macro avg 0.6101 0.5535 0.5654 18039 weighted avg 0.8473 0.7890 0.8149 18039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:53:56 Epoch 0 | Timestep 2891 | Test Loss 0.128140 | F1 0.816781 INFO Nested.trainers.BaseTrainer Tue, 23 Dec 2025 09:53:56 Saving checkpoint to /rep/nhamad/ArabicNER/data/output/dir/checkpoints/checkpoint_0.pt INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:01 Epoch 1 | Batch 9/2891 | Timestep 2900 | LR 0.0001000000 | Loss 0.049745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:03 Epoch 1 | Batch 19/2891 | Timestep 2910 | LR 0.0001000000 | Loss 0.046091 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:04 Epoch 1 | Batch 29/2891 | Timestep 2920 | LR 0.0001000000 | Loss 0.070343 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:06 Epoch 1 | Batch 39/2891 | Timestep 2930 | LR 0.0001000000 | Loss 0.025158 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:07 Epoch 1 | Batch 49/2891 | Timestep 2940 | LR 0.0001000000 | Loss 0.120654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:09 Epoch 1 | Batch 59/2891 | Timestep 2950 | LR 0.0001000000 | Loss 0.042260 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:11 Epoch 1 | Batch 69/2891 | Timestep 2960 | LR 0.0001000000 | Loss 0.040088 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:12 Epoch 1 | Batch 79/2891 | Timestep 2970 | LR 0.0001000000 | Loss 0.044654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:14 Epoch 1 | Batch 89/2891 | Timestep 2980 | LR 0.0001000000 | Loss 0.070068 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:15 Epoch 1 | Batch 99/2891 | Timestep 2990 | LR 0.0001000000 | Loss 0.044353 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:17 Epoch 1 | Batch 109/2891 | Timestep 3000 | LR 0.0001000000 | Loss 0.046923 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:19 Epoch 1 | Batch 119/2891 | Timestep 3010 | LR 0.0001000000 | Loss 0.029192 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:21 Epoch 1 | Batch 129/2891 | Timestep 3020 | LR 0.0001000000 | Loss 0.054290 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:22 Epoch 1 | Batch 139/2891 | Timestep 3030 | LR 0.0001000000 | Loss 0.056757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:24 Epoch 1 | Batch 149/2891 | Timestep 3040 | LR 0.0001000000 | Loss 0.021174 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:26 Epoch 1 | Batch 159/2891 | Timestep 3050 | LR 0.0001000000 | Loss 0.044396 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:27 Epoch 1 | Batch 169/2891 | Timestep 3060 | LR 0.0001000000 | Loss 0.031433 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:29 Epoch 1 | Batch 179/2891 | Timestep 3070 | LR 0.0001000000 | Loss 0.104813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:31 Epoch 1 | Batch 189/2891 | Timestep 3080 | LR 0.0001000000 | Loss 0.039950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:33 Epoch 1 | Batch 199/2891 | Timestep 3090 | LR 0.0001000000 | Loss 0.020898 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:34 Epoch 1 | Batch 209/2891 | Timestep 3100 | LR 0.0001000000 | Loss 0.052630 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:36 Epoch 1 | Batch 219/2891 | Timestep 3110 | LR 0.0001000000 | Loss 0.053937 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:38 Epoch 1 | Batch 229/2891 | Timestep 3120 | LR 0.0001000000 | Loss 0.051339 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:40 Epoch 1 | Batch 239/2891 | Timestep 3130 | LR 0.0001000000 | Loss 0.069560 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:41 Epoch 1 | Batch 249/2891 | Timestep 3140 | LR 0.0001000000 | Loss 0.042528 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:43 Epoch 1 | Batch 259/2891 | Timestep 3150 | LR 0.0001000000 | Loss 0.036308 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:45 Epoch 1 | Batch 269/2891 | Timestep 3160 | LR 0.0001000000 | Loss 0.086043 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:46 Epoch 1 | Batch 279/2891 | Timestep 3170 | LR 0.0001000000 | Loss 0.060598 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:48 Epoch 1 | Batch 289/2891 | Timestep 3180 | LR 0.0001000000 | Loss 0.019947 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:50 Epoch 1 | Batch 299/2891 | Timestep 3190 | LR 0.0001000000 | Loss 0.108124 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:51 Epoch 1 | Batch 309/2891 | Timestep 3200 | LR 0.0001000000 | Loss 0.070206 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:53 Epoch 1 | Batch 319/2891 | Timestep 3210 | LR 0.0001000000 | Loss 0.100347 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:55 Epoch 1 | Batch 329/2891 | Timestep 3220 | LR 0.0001000000 | Loss 0.051845 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:56 Epoch 1 | Batch 339/2891 | Timestep 3230 | LR 0.0001000000 | Loss 0.018672 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:58 Epoch 1 | Batch 349/2891 | Timestep 3240 | LR 0.0001000000 | Loss 0.063138 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:54:59 Epoch 1 | Batch 359/2891 | Timestep 3250 | LR 0.0001000000 | Loss 0.031675 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:01 Epoch 1 | Batch 369/2891 | Timestep 3260 | LR 0.0001000000 | Loss 0.042711 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:03 Epoch 1 | Batch 379/2891 | Timestep 3270 | LR 0.0001000000 | Loss 0.020701 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:05 Epoch 1 | Batch 389/2891 | Timestep 3280 | LR 0.0001000000 | Loss 0.018572 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:07 Epoch 1 | Batch 399/2891 | Timestep 3290 | LR 0.0001000000 | Loss 0.013724 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:08 Epoch 1 | Batch 409/2891 | Timestep 3300 | LR 0.0001000000 | Loss 0.036947 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:10 Epoch 1 | Batch 419/2891 | Timestep 3310 | LR 0.0001000000 | Loss 0.020865 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:12 Epoch 1 | Batch 429/2891 | Timestep 3320 | LR 0.0001000000 | Loss 0.158150 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:13 Epoch 1 | Batch 439/2891 | Timestep 3330 | LR 0.0001000000 | Loss 0.028654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:15 Epoch 1 | Batch 449/2891 | Timestep 3340 | LR 0.0001000000 | Loss 0.030807 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:17 Epoch 1 | Batch 459/2891 | Timestep 3350 | LR 0.0001000000 | Loss 0.051187 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:19 Epoch 1 | Batch 469/2891 | Timestep 3360 | LR 0.0001000000 | Loss 0.059799 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:21 Epoch 1 | Batch 479/2891 | Timestep 3370 | LR 0.0001000000 | Loss 0.072417 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:22 Epoch 1 | Batch 489/2891 | Timestep 3380 | LR 0.0001000000 | Loss 0.024751 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:24 Epoch 1 | Batch 499/2891 | Timestep 3390 | LR 0.0001000000 | Loss 0.036890 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:25 Epoch 1 | Batch 509/2891 | Timestep 3400 | LR 0.0001000000 | Loss 0.083039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:28 Epoch 1 | Batch 519/2891 | Timestep 3410 | LR 0.0001000000 | Loss 0.010468 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:29 Epoch 1 | Batch 529/2891 | Timestep 3420 | LR 0.0001000000 | Loss 0.017273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:31 Epoch 1 | Batch 539/2891 | Timestep 3430 | LR 0.0001000000 | Loss 0.041265 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:32 Epoch 1 | Batch 549/2891 | Timestep 3440 | LR 0.0001000000 | Loss 0.082240 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:34 Epoch 1 | Batch 559/2891 | Timestep 3450 | LR 0.0001000000 | Loss 0.016238 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:36 Epoch 1 | Batch 569/2891 | Timestep 3460 | LR 0.0001000000 | Loss 0.116066 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:37 Epoch 1 | Batch 579/2891 | Timestep 3470 | LR 0.0001000000 | Loss 0.015273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:39 Epoch 1 | Batch 589/2891 | Timestep 3480 | LR 0.0001000000 | Loss 0.104771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:40 Epoch 1 | Batch 599/2891 | Timestep 3490 | LR 0.0001000000 | Loss 0.233813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:42 Epoch 1 | Batch 609/2891 | Timestep 3500 | LR 0.0001000000 | Loss 0.084924 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:44 Epoch 1 | Batch 619/2891 | Timestep 3510 | LR 0.0001000000 | Loss 0.124994 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:46 Epoch 1 | Batch 629/2891 | Timestep 3520 | LR 0.0001000000 | Loss 0.076316 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:47 Epoch 1 | Batch 639/2891 | Timestep 3530 | LR 0.0001000000 | Loss 0.014564 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:49 Epoch 1 | Batch 649/2891 | Timestep 3540 | LR 0.0001000000 | Loss 0.133657 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:51 Epoch 1 | Batch 659/2891 | Timestep 3550 | LR 0.0001000000 | Loss 0.056608 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:53 Epoch 1 | Batch 669/2891 | Timestep 3560 | LR 0.0001000000 | Loss 0.076878 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:54 Epoch 1 | Batch 679/2891 | Timestep 3570 | LR 0.0001000000 | Loss 0.040208 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:56 Epoch 1 | Batch 689/2891 | Timestep 3580 | LR 0.0001000000 | Loss 0.016532 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:58 Epoch 1 | Batch 699/2891 | Timestep 3590 | LR 0.0001000000 | Loss 0.051232 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:55:59 Epoch 1 | Batch 709/2891 | Timestep 3600 | LR 0.0001000000 | Loss 0.043360 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:01 Epoch 1 | Batch 719/2891 | Timestep 3610 | LR 0.0001000000 | Loss 0.067160 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:03 Epoch 1 | Batch 729/2891 | Timestep 3620 | LR 0.0001000000 | Loss 0.035406 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:05 Epoch 1 | Batch 739/2891 | Timestep 3630 | LR 0.0001000000 | Loss 0.014270 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:07 Epoch 1 | Batch 749/2891 | Timestep 3640 | LR 0.0001000000 | Loss 0.023956 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:09 Epoch 1 | Batch 759/2891 | Timestep 3650 | LR 0.0001000000 | Loss 0.018381 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:11 Epoch 1 | Batch 769/2891 | Timestep 3660 | LR 0.0001000000 | Loss 0.031320 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:13 Epoch 1 | Batch 779/2891 | Timestep 3670 | LR 0.0001000000 | Loss 0.093076 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:14 Epoch 1 | Batch 789/2891 | Timestep 3680 | LR 0.0001000000 | Loss 0.035520 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:16 Epoch 1 | Batch 799/2891 | Timestep 3690 | LR 0.0001000000 | Loss 0.040995 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:18 Epoch 1 | Batch 809/2891 | Timestep 3700 | LR 0.0001000000 | Loss 0.085180 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:20 Epoch 1 | Batch 819/2891 | Timestep 3710 | LR 0.0001000000 | Loss 0.043811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:22 Epoch 1 | Batch 829/2891 | Timestep 3720 | LR 0.0001000000 | Loss 0.088960 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:23 Epoch 1 | Batch 839/2891 | Timestep 3730 | LR 0.0001000000 | Loss 0.040631 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:25 Epoch 1 | Batch 849/2891 | Timestep 3740 | LR 0.0001000000 | Loss 0.140596 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:27 Epoch 1 | Batch 859/2891 | Timestep 3750 | LR 0.0001000000 | Loss 0.031652 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:28 Epoch 1 | Batch 869/2891 | Timestep 3760 | LR 0.0001000000 | Loss 0.038913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:30 Epoch 1 | Batch 879/2891 | Timestep 3770 | LR 0.0001000000 | Loss 0.023909 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:32 Epoch 1 | Batch 889/2891 | Timestep 3780 | LR 0.0001000000 | Loss 0.083219 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:33 Epoch 1 | Batch 899/2891 | Timestep 3790 | LR 0.0001000000 | Loss 0.035950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:35 Epoch 1 | Batch 909/2891 | Timestep 3800 | LR 0.0001000000 | Loss 0.095395 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:37 Epoch 1 | Batch 919/2891 | Timestep 3810 | LR 0.0001000000 | Loss 0.025442 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:38 Epoch 1 | Batch 929/2891 | Timestep 3820 | LR 0.0001000000 | Loss 0.032920 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:40 Epoch 1 | Batch 939/2891 | Timestep 3830 | LR 0.0001000000 | Loss 0.035305 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:42 Epoch 1 | Batch 949/2891 | Timestep 3840 | LR 0.0001000000 | Loss 0.033212 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:44 Epoch 1 | Batch 959/2891 | Timestep 3850 | LR 0.0001000000 | Loss 0.038307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:46 Epoch 1 | Batch 969/2891 | Timestep 3860 | LR 0.0001000000 | Loss 0.035469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:47 Epoch 1 | Batch 979/2891 | Timestep 3870 | LR 0.0001000000 | Loss 0.055221 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:49 Epoch 1 | Batch 989/2891 | Timestep 3880 | LR 0.0001000000 | Loss 0.026759 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:51 Epoch 1 | Batch 999/2891 | Timestep 3890 | LR 0.0001000000 | Loss 0.068206 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:52 Epoch 1 | Batch 1009/2891 | Timestep 3900 | LR 0.0001000000 | Loss 0.087053 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:54 Epoch 1 | Batch 1019/2891 | Timestep 3910 | LR 0.0001000000 | Loss 0.008835 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:56 Epoch 1 | Batch 1029/2891 | Timestep 3920 | LR 0.0001000000 | Loss 0.045548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:57 Epoch 1 | Batch 1039/2891 | Timestep 3930 | LR 0.0001000000 | Loss 0.042018 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:56:59 Epoch 1 | Batch 1049/2891 | Timestep 3940 | LR 0.0001000000 | Loss 0.054228 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:00 Epoch 1 | Batch 1059/2891 | Timestep 3950 | LR 0.0001000000 | Loss 0.016643 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:02 Epoch 1 | Batch 1069/2891 | Timestep 3960 | LR 0.0001000000 | Loss 0.017641 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:03 Epoch 1 | Batch 1079/2891 | Timestep 3970 | LR 0.0001000000 | Loss 0.030976 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:05 Epoch 1 | Batch 1089/2891 | Timestep 3980 | LR 0.0001000000 | Loss 0.100214 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:06 Epoch 1 | Batch 1099/2891 | Timestep 3990 | LR 0.0001000000 | Loss 0.295970 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:08 Epoch 1 | Batch 1109/2891 | Timestep 4000 | LR 0.0001000000 | Loss 0.206632 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:10 Epoch 1 | Batch 1119/2891 | Timestep 4010 | LR 0.0001000000 | Loss 0.031112 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:11 Epoch 1 | Batch 1129/2891 | Timestep 4020 | LR 0.0001000000 | Loss 0.073688 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:13 Epoch 1 | Batch 1139/2891 | Timestep 4030 | LR 0.0001000000 | Loss 0.031877 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:15 Epoch 1 | Batch 1149/2891 | Timestep 4040 | LR 0.0001000000 | Loss 0.251213 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:16 Epoch 1 | Batch 1159/2891 | Timestep 4050 | LR 0.0001000000 | Loss 0.064189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:18 Epoch 1 | Batch 1169/2891 | Timestep 4060 | LR 0.0001000000 | Loss 0.210989 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:19 Epoch 1 | Batch 1179/2891 | Timestep 4070 | LR 0.0001000000 | Loss 0.049547 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:21 Epoch 1 | Batch 1189/2891 | Timestep 4080 | LR 0.0001000000 | Loss 0.090850 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:22 Epoch 1 | Batch 1199/2891 | Timestep 4090 | LR 0.0001000000 | Loss 0.081075 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:24 Epoch 1 | Batch 1209/2891 | Timestep 4100 | LR 0.0001000000 | Loss 0.008166 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:25 Epoch 1 | Batch 1219/2891 | Timestep 4110 | LR 0.0001000000 | Loss 0.049970 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:27 Epoch 1 | Batch 1229/2891 | Timestep 4120 | LR 0.0001000000 | Loss 0.105746 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:29 Epoch 1 | Batch 1239/2891 | Timestep 4130 | LR 0.0001000000 | Loss 0.072314 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:30 Epoch 1 | Batch 1249/2891 | Timestep 4140 | LR 0.0001000000 | Loss 0.063364 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:32 Epoch 1 | Batch 1259/2891 | Timestep 4150 | LR 0.0001000000 | Loss 0.042009 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:34 Epoch 1 | Batch 1269/2891 | Timestep 4160 | LR 0.0001000000 | Loss 0.035237 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:35 Epoch 1 | Batch 1279/2891 | Timestep 4170 | LR 0.0001000000 | Loss 0.052259 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:37 Epoch 1 | Batch 1289/2891 | Timestep 4180 | LR 0.0001000000 | Loss 0.040165 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:39 Epoch 1 | Batch 1299/2891 | Timestep 4190 | LR 0.0001000000 | Loss 0.014509 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:40 Epoch 1 | Batch 1309/2891 | Timestep 4200 | LR 0.0001000000 | Loss 0.033494 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:42 Epoch 1 | Batch 1319/2891 | Timestep 4210 | LR 0.0001000000 | Loss 0.049799 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:43 Epoch 1 | Batch 1329/2891 | Timestep 4220 | LR 0.0001000000 | Loss 0.091803 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:45 Epoch 1 | Batch 1339/2891 | Timestep 4230 | LR 0.0001000000 | Loss 0.103417 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:47 Epoch 1 | Batch 1349/2891 | Timestep 4240 | LR 0.0001000000 | Loss 0.010458 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:49 Epoch 1 | Batch 1359/2891 | Timestep 4250 | LR 0.0001000000 | Loss 0.041710 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:51 Epoch 1 | Batch 1369/2891 | Timestep 4260 | LR 0.0001000000 | Loss 0.031530 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:53 Epoch 1 | Batch 1379/2891 | Timestep 4270 | LR 0.0001000000 | Loss 0.132414 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:55 Epoch 1 | Batch 1389/2891 | Timestep 4280 | LR 0.0001000000 | Loss 0.041490 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:56 Epoch 1 | Batch 1399/2891 | Timestep 4290 | LR 0.0001000000 | Loss 0.025692 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:57:58 Epoch 1 | Batch 1409/2891 | Timestep 4300 | LR 0.0001000000 | Loss 0.020532 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:00 Epoch 1 | Batch 1419/2891 | Timestep 4310 | LR 0.0001000000 | Loss 0.052053 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:01 Epoch 1 | Batch 1429/2891 | Timestep 4320 | LR 0.0001000000 | Loss 0.025046 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:03 Epoch 1 | Batch 1439/2891 | Timestep 4330 | LR 0.0001000000 | Loss 0.015090 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:05 Epoch 1 | Batch 1449/2891 | Timestep 4340 | LR 0.0001000000 | Loss 0.080257 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:07 Epoch 1 | Batch 1459/2891 | Timestep 4350 | LR 0.0001000000 | Loss 0.019628 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:09 Epoch 1 | Batch 1469/2891 | Timestep 4360 | LR 0.0001000000 | Loss 0.050228 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:10 Epoch 1 | Batch 1479/2891 | Timestep 4370 | LR 0.0001000000 | Loss 0.018402 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:12 Epoch 1 | Batch 1489/2891 | Timestep 4380 | LR 0.0001000000 | Loss 0.030829 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:14 Epoch 1 | Batch 1499/2891 | Timestep 4390 | LR 0.0001000000 | Loss 0.048342 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:15 Epoch 1 | Batch 1509/2891 | Timestep 4400 | LR 0.0001000000 | Loss 0.062852 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:17 Epoch 1 | Batch 1519/2891 | Timestep 4410 | LR 0.0001000000 | Loss 0.061223 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:19 Epoch 1 | Batch 1529/2891 | Timestep 4420 | LR 0.0001000000 | Loss 0.029051 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:21 Epoch 1 | Batch 1539/2891 | Timestep 4430 | LR 0.0001000000 | Loss 0.120176 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:23 Epoch 1 | Batch 1549/2891 | Timestep 4440 | LR 0.0001000000 | Loss 0.064314 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:24 Epoch 1 | Batch 1559/2891 | Timestep 4450 | LR 0.0001000000 | Loss 0.038202 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:26 Epoch 1 | Batch 1569/2891 | Timestep 4460 | LR 0.0001000000 | Loss 0.007954 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:27 Epoch 1 | Batch 1579/2891 | Timestep 4470 | LR 0.0001000000 | Loss 0.025351 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:29 Epoch 1 | Batch 1589/2891 | Timestep 4480 | LR 0.0001000000 | Loss 0.026892 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:31 Epoch 1 | Batch 1599/2891 | Timestep 4490 | LR 0.0001000000 | Loss 0.079687 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:32 Epoch 1 | Batch 1609/2891 | Timestep 4500 | LR 0.0001000000 | Loss 0.039110 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:34 Epoch 1 | Batch 1619/2891 | Timestep 4510 | LR 0.0001000000 | Loss 0.018704 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:36 Epoch 1 | Batch 1629/2891 | Timestep 4520 | LR 0.0001000000 | Loss 0.050519 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:38 Epoch 1 | Batch 1639/2891 | Timestep 4530 | LR 0.0001000000 | Loss 0.033743 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:40 Epoch 1 | Batch 1649/2891 | Timestep 4540 | LR 0.0001000000 | Loss 0.057257 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:41 Epoch 1 | Batch 1659/2891 | Timestep 4550 | LR 0.0001000000 | Loss 0.075250 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:43 Epoch 1 | Batch 1669/2891 | Timestep 4560 | LR 0.0001000000 | Loss 0.069854 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:44 Epoch 1 | Batch 1679/2891 | Timestep 4570 | LR 0.0001000000 | Loss 0.078836 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:46 Epoch 1 | Batch 1689/2891 | Timestep 4580 | LR 0.0001000000 | Loss 0.057991 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:48 Epoch 1 | Batch 1699/2891 | Timestep 4590 | LR 0.0001000000 | Loss 0.124873 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:50 Epoch 1 | Batch 1709/2891 | Timestep 4600 | LR 0.0001000000 | Loss 0.074800 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:51 Epoch 1 | Batch 1719/2891 | Timestep 4610 | LR 0.0001000000 | Loss 0.056494 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:53 Epoch 1 | Batch 1729/2891 | Timestep 4620 | LR 0.0001000000 | Loss 0.081685 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:55 Epoch 1 | Batch 1739/2891 | Timestep 4630 | LR 0.0001000000 | Loss 0.021856 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:56 Epoch 1 | Batch 1749/2891 | Timestep 4640 | LR 0.0001000000 | Loss 0.030124 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:58:58 Epoch 1 | Batch 1759/2891 | Timestep 4650 | LR 0.0001000000 | Loss 0.086142 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:00 Epoch 1 | Batch 1769/2891 | Timestep 4660 | LR 0.0001000000 | Loss 0.012831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:01 Epoch 1 | Batch 1779/2891 | Timestep 4670 | LR 0.0001000000 | Loss 0.068972 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:03 Epoch 1 | Batch 1789/2891 | Timestep 4680 | LR 0.0001000000 | Loss 0.070014 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:04 Epoch 1 | Batch 1799/2891 | Timestep 4690 | LR 0.0001000000 | Loss 0.049482 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:06 Epoch 1 | Batch 1809/2891 | Timestep 4700 | LR 0.0001000000 | Loss 0.077882 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:08 Epoch 1 | Batch 1819/2891 | Timestep 4710 | LR 0.0001000000 | Loss 0.049254 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:10 Epoch 1 | Batch 1829/2891 | Timestep 4720 | LR 0.0001000000 | Loss 0.048547 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:12 Epoch 1 | Batch 1839/2891 | Timestep 4730 | LR 0.0001000000 | Loss 0.052050 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:13 Epoch 1 | Batch 1849/2891 | Timestep 4740 | LR 0.0001000000 | Loss 0.069386 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:15 Epoch 1 | Batch 1859/2891 | Timestep 4750 | LR 0.0001000000 | Loss 0.033106 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:17 Epoch 1 | Batch 1869/2891 | Timestep 4760 | LR 0.0001000000 | Loss 0.044042 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:18 Epoch 1 | Batch 1879/2891 | Timestep 4770 | LR 0.0001000000 | Loss 0.077774 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:20 Epoch 1 | Batch 1889/2891 | Timestep 4780 | LR 0.0001000000 | Loss 0.097151 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:21 Epoch 1 | Batch 1899/2891 | Timestep 4790 | LR 0.0001000000 | Loss 0.078225 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:23 Epoch 1 | Batch 1909/2891 | Timestep 4800 | LR 0.0001000000 | Loss 0.253556 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:25 Epoch 1 | Batch 1919/2891 | Timestep 4810 | LR 0.0001000000 | Loss 0.044437 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:26 Epoch 1 | Batch 1929/2891 | Timestep 4820 | LR 0.0001000000 | Loss 0.032906 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:28 Epoch 1 | Batch 1939/2891 | Timestep 4830 | LR 0.0001000000 | Loss 0.134491 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:29 Epoch 1 | Batch 1949/2891 | Timestep 4840 | LR 0.0001000000 | Loss 0.051771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:31 Epoch 1 | Batch 1959/2891 | Timestep 4850 | LR 0.0001000000 | Loss 0.019410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:33 Epoch 1 | Batch 1969/2891 | Timestep 4860 | LR 0.0001000000 | Loss 0.042623 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:34 Epoch 1 | Batch 1979/2891 | Timestep 4870 | LR 0.0001000000 | Loss 0.064606 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:36 Epoch 1 | Batch 1989/2891 | Timestep 4880 | LR 0.0001000000 | Loss 0.090352 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:38 Epoch 1 | Batch 1999/2891 | Timestep 4890 | LR 0.0001000000 | Loss 0.041608 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:40 Epoch 1 | Batch 2009/2891 | Timestep 4900 | LR 0.0001000000 | Loss 0.055830 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:41 Epoch 1 | Batch 2019/2891 | Timestep 4910 | LR 0.0001000000 | Loss 0.010586 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:43 Epoch 1 | Batch 2029/2891 | Timestep 4920 | LR 0.0001000000 | Loss 0.052763 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:44 Epoch 1 | Batch 2039/2891 | Timestep 4930 | LR 0.0001000000 | Loss 0.081620 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:46 Epoch 1 | Batch 2049/2891 | Timestep 4940 | LR 0.0001000000 | Loss 0.024945 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:48 Epoch 1 | Batch 2059/2891 | Timestep 4950 | LR 0.0001000000 | Loss 0.064292 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:50 Epoch 1 | Batch 2069/2891 | Timestep 4960 | LR 0.0001000000 | Loss 0.040934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:52 Epoch 1 | Batch 2079/2891 | Timestep 4970 | LR 0.0001000000 | Loss 0.054797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:54 Epoch 1 | Batch 2089/2891 | Timestep 4980 | LR 0.0001000000 | Loss 0.051810 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:56 Epoch 1 | Batch 2099/2891 | Timestep 4990 | LR 0.0001000000 | Loss 0.020783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 09:59:58 Epoch 1 | Batch 2109/2891 | Timestep 5000 | LR 0.0001000000 | Loss 0.023794 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:00 Epoch 1 | Batch 2119/2891 | Timestep 5010 | LR 0.0001000000 | Loss 0.020259 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:02 Epoch 1 | Batch 2129/2891 | Timestep 5020 | LR 0.0001000000 | Loss 0.006080 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:03 Epoch 1 | Batch 2139/2891 | Timestep 5030 | LR 0.0001000000 | Loss 0.057310 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:06 Epoch 1 | Batch 2149/2891 | Timestep 5040 | LR 0.0001000000 | Loss 0.116316 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:07 Epoch 1 | Batch 2159/2891 | Timestep 5050 | LR 0.0001000000 | Loss 0.089864 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:09 Epoch 1 | Batch 2169/2891 | Timestep 5060 | LR 0.0001000000 | Loss 0.100550 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:11 Epoch 1 | Batch 2179/2891 | Timestep 5070 | LR 0.0001000000 | Loss 0.020820 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:13 Epoch 1 | Batch 2189/2891 | Timestep 5080 | LR 0.0001000000 | Loss 0.033859 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:14 Epoch 1 | Batch 2199/2891 | Timestep 5090 | LR 0.0001000000 | Loss 0.139948 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:16 Epoch 1 | Batch 2209/2891 | Timestep 5100 | LR 0.0001000000 | Loss 0.045096 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:18 Epoch 1 | Batch 2219/2891 | Timestep 5110 | LR 0.0001000000 | Loss 0.085789 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:20 Epoch 1 | Batch 2229/2891 | Timestep 5120 | LR 0.0001000000 | Loss 0.215364 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:21 Epoch 1 | Batch 2239/2891 | Timestep 5130 | LR 0.0001000000 | Loss 0.086845 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:23 Epoch 1 | Batch 2249/2891 | Timestep 5140 | LR 0.0001000000 | Loss 0.041772 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:24 Epoch 1 | Batch 2259/2891 | Timestep 5150 | LR 0.0001000000 | Loss 0.061785 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:26 Epoch 1 | Batch 2269/2891 | Timestep 5160 | LR 0.0001000000 | Loss 0.041032 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:28 Epoch 1 | Batch 2279/2891 | Timestep 5170 | LR 0.0001000000 | Loss 0.025257 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:30 Epoch 1 | Batch 2289/2891 | Timestep 5180 | LR 0.0001000000 | Loss 0.034027 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:31 Epoch 1 | Batch 2299/2891 | Timestep 5190 | LR 0.0001000000 | Loss 0.099918 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:33 Epoch 1 | Batch 2309/2891 | Timestep 5200 | LR 0.0001000000 | Loss 0.029671 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:35 Epoch 1 | Batch 2319/2891 | Timestep 5210 | LR 0.0001000000 | Loss 0.028935 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:36 Epoch 1 | Batch 2329/2891 | Timestep 5220 | LR 0.0001000000 | Loss 0.017369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:39 Epoch 1 | Batch 2339/2891 | Timestep 5230 | LR 0.0001000000 | Loss 0.119113 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:40 Epoch 1 | Batch 2349/2891 | Timestep 5240 | LR 0.0001000000 | Loss 0.113967 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:41 Epoch 1 | Batch 2359/2891 | Timestep 5250 | LR 0.0001000000 | Loss 0.114869 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:43 Epoch 1 | Batch 2369/2891 | Timestep 5260 | LR 0.0001000000 | Loss 0.108542 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:45 Epoch 1 | Batch 2379/2891 | Timestep 5270 | LR 0.0001000000 | Loss 0.074968 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:46 Epoch 1 | Batch 2389/2891 | Timestep 5280 | LR 0.0001000000 | Loss 0.021758 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:48 Epoch 1 | Batch 2399/2891 | Timestep 5290 | LR 0.0001000000 | Loss 0.053388 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:50 Epoch 1 | Batch 2409/2891 | Timestep 5300 | LR 0.0001000000 | Loss 0.032637 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:51 Epoch 1 | Batch 2419/2891 | Timestep 5310 | LR 0.0001000000 | Loss 0.081757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:53 Epoch 1 | Batch 2429/2891 | Timestep 5320 | LR 0.0001000000 | Loss 0.026025 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:54 Epoch 1 | Batch 2439/2891 | Timestep 5330 | LR 0.0001000000 | Loss 0.030955 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:56 Epoch 1 | Batch 2449/2891 | Timestep 5340 | LR 0.0001000000 | Loss 0.059385 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:58 Epoch 1 | Batch 2459/2891 | Timestep 5350 | LR 0.0001000000 | Loss 0.074472 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:00:59 Epoch 1 | Batch 2469/2891 | Timestep 5360 | LR 0.0001000000 | Loss 0.079757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:01 Epoch 1 | Batch 2479/2891 | Timestep 5370 | LR 0.0001000000 | Loss 0.084857 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:02 Epoch 1 | Batch 2489/2891 | Timestep 5380 | LR 0.0001000000 | Loss 0.009877 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:04 Epoch 1 | Batch 2499/2891 | Timestep 5390 | LR 0.0001000000 | Loss 0.019013 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:06 Epoch 1 | Batch 2509/2891 | Timestep 5400 | LR 0.0001000000 | Loss 0.019044 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:07 Epoch 1 | Batch 2519/2891 | Timestep 5410 | LR 0.0001000000 | Loss 0.026742 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:10 Epoch 1 | Batch 2529/2891 | Timestep 5420 | LR 0.0001000000 | Loss 0.064677 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:11 Epoch 1 | Batch 2539/2891 | Timestep 5430 | LR 0.0001000000 | Loss 0.210630 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:13 Epoch 1 | Batch 2549/2891 | Timestep 5440 | LR 0.0001000000 | Loss 0.043714 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:15 Epoch 1 | Batch 2559/2891 | Timestep 5450 | LR 0.0001000000 | Loss 0.012471 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:16 Epoch 1 | Batch 2569/2891 | Timestep 5460 | LR 0.0001000000 | Loss 0.022986 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:18 Epoch 1 | Batch 2579/2891 | Timestep 5470 | LR 0.0001000000 | Loss 0.032479 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:20 Epoch 1 | Batch 2589/2891 | Timestep 5480 | LR 0.0001000000 | Loss 0.028387 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:21 Epoch 1 | Batch 2599/2891 | Timestep 5490 | LR 0.0001000000 | Loss 0.044149 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:23 Epoch 1 | Batch 2609/2891 | Timestep 5500 | LR 0.0001000000 | Loss 0.008667 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:24 Epoch 1 | Batch 2619/2891 | Timestep 5510 | LR 0.0001000000 | Loss 0.143913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:26 Epoch 1 | Batch 2629/2891 | Timestep 5520 | LR 0.0001000000 | Loss 0.044649 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:28 Epoch 1 | Batch 2639/2891 | Timestep 5530 | LR 0.0001000000 | Loss 0.008994 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:29 Epoch 1 | Batch 2649/2891 | Timestep 5540 | LR 0.0001000000 | Loss 0.027432 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:31 Epoch 1 | Batch 2659/2891 | Timestep 5550 | LR 0.0001000000 | Loss 0.013956 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:32 Epoch 1 | Batch 2669/2891 | Timestep 5560 | LR 0.0001000000 | Loss 0.035555 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:34 Epoch 1 | Batch 2679/2891 | Timestep 5570 | LR 0.0001000000 | Loss 0.045394 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:36 Epoch 1 | Batch 2689/2891 | Timestep 5580 | LR 0.0001000000 | Loss 0.027733 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:37 Epoch 1 | Batch 2699/2891 | Timestep 5590 | LR 0.0001000000 | Loss 0.043539 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:39 Epoch 1 | Batch 2709/2891 | Timestep 5600 | LR 0.0001000000 | Loss 0.036479 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:41 Epoch 1 | Batch 2719/2891 | Timestep 5610 | LR 0.0001000000 | Loss 0.029811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:43 Epoch 1 | Batch 2729/2891 | Timestep 5620 | LR 0.0001000000 | Loss 0.040123 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:45 Epoch 1 | Batch 2739/2891 | Timestep 5630 | LR 0.0001000000 | Loss 0.047054 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:47 Epoch 1 | Batch 2749/2891 | Timestep 5640 | LR 0.0001000000 | Loss 0.057734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:48 Epoch 1 | Batch 2759/2891 | Timestep 5650 | LR 0.0001000000 | Loss 0.025258 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:50 Epoch 1 | Batch 2769/2891 | Timestep 5660 | LR 0.0001000000 | Loss 0.038928 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:52 Epoch 1 | Batch 2779/2891 | Timestep 5670 | LR 0.0001000000 | Loss 0.012297 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:53 Epoch 1 | Batch 2789/2891 | Timestep 5680 | LR 0.0001000000 | Loss 0.006345 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:55 Epoch 1 | Batch 2799/2891 | Timestep 5690 | LR 0.0001000000 | Loss 0.034858 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:57 Epoch 1 | Batch 2809/2891 | Timestep 5700 | LR 0.0001000000 | Loss 0.014763 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:01:59 Epoch 1 | Batch 2819/2891 | Timestep 5710 | LR 0.0001000000 | Loss 0.010062 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:00 Epoch 1 | Batch 2829/2891 | Timestep 5720 | LR 0.0001000000 | Loss 0.035825 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:02 Epoch 1 | Batch 2839/2891 | Timestep 5730 | LR 0.0001000000 | Loss 0.020328 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:04 Epoch 1 | Batch 2849/2891 | Timestep 5740 | LR 0.0001000000 | Loss 0.024376 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:06 Epoch 1 | Batch 2859/2891 | Timestep 5750 | LR 0.0001000000 | Loss 0.079807 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:07 Epoch 1 | Batch 2869/2891 | Timestep 5760 | LR 0.0001000000 | Loss 0.010673 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:10 Epoch 1 | Batch 2879/2891 | Timestep 5770 | LR 0.0001000000 | Loss 0.004354 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:11 Epoch 1 | Batch 2889/2891 | Timestep 5780 | LR 0.0001000000 | Loss 0.009153 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:12 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:02:46 precision recall f1-score support CARDINAL 0.7933 0.8353 0.8138 170 CURR 0.9524 0.8333 0.8889 24 DATE 0.9298 0.9314 0.9306 1691 EVENT 0.5817 0.6952 0.6334 292 FAC 0.6637 0.6356 0.6494 118 GPE 0.9584 0.9392 0.9487 2156 LANGUAGE 1.0000 0.6875 0.8148 16 LAW 0.6452 0.8511 0.7339 47 LOC 0.6962 0.6111 0.6509 90 MONEY 0.7391 0.7727 0.7556 22 NORP 0.6051 0.6897 0.6446 551 OCC 0.8408 0.8295 0.8351 522 ORDINAL 0.9174 0.9191 0.9183 544 ORG 0.9005 0.8799 0.8901 1882 PERCENT 0.7059 1.0000 0.8276 12 PERS 0.9280 0.9116 0.9198 679 PRODUCT 0.3333 0.1250 0.1818 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.6842 0.7879 0.7324 33 UNIT 0.6000 0.7500 0.6667 4 WEBSITE 0.5342 0.4875 0.5098 80 micro avg 0.8727 0.8759 0.8743 8944 macro avg 0.7465 0.7543 0.7435 8944 weighted avg 0.8773 0.8759 0.8759 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:56 Epoch 1 | Timestep 5782 | Train Loss 0.057948 | Val Loss 0.053227 | F1 0.874282 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:02:56 ** Validation improved, evaluating test data ** INFO Nested.data.transforms Tue, 23 Dec 2025 10:03:20 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 Tue, 23 Dec 2025 10:03:38 Predictions written to /rep/nhamad/ArabicNER/data/output/dir/predictions.txt INFO root Tue, 23 Dec 2025 10:04:04 precision recall f1-score support CARDINAL 0.7869 0.8421 0.8136 342 CURR 0.9118 0.7561 0.8267 41 DATE 0.9312 0.9379 0.9346 3206 EVENT 0.5830 0.7333 0.6496 570 FAC 0.7310 0.5950 0.6560 242 GPE 0.9532 0.9357 0.9444 4336 LANGUAGE 1.0000 0.5455 0.7059 44 LAW 0.6667 0.8000 0.7273 90 LOC 0.6536 0.5367 0.5894 218 MONEY 0.6053 0.6970 0.6479 33 NORP 0.6368 0.7411 0.6850 1093 OCC 0.8247 0.7978 0.8111 1103 ORDINAL 0.9312 0.9123 0.9216 1083 ORG 0.8825 0.8662 0.8743 3798 PERCENT 0.7895 0.9091 0.8451 33 PERS 0.9211 0.9011 0.9110 1568 PRODUCT 0.3333 0.1579 0.2143 19 QUANTITY 0.4000 0.4444 0.4211 9 TIME 0.5729 0.6548 0.6111 84 UNIT 0.7500 0.5455 0.6316 11 WEBSITE 0.5378 0.5517 0.5447 116 micro avg 0.8692 0.8717 0.8704 18039 macro avg 0.7335 0.7077 0.7127 18039 weighted avg 0.8740 0.8717 0.8718 18039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:26 Epoch 1 | Timestep 5782 | Test Loss 0.057182 | F1 0.870436 INFO Nested.trainers.BaseTrainer Tue, 23 Dec 2025 10:04:26 Saving checkpoint to /rep/nhamad/ArabicNER/data/output/dir/checkpoints/checkpoint_1.pt INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:31 Epoch 2 | Batch 8/2891 | Timestep 5790 | LR 0.0001000000 | Loss 0.028274 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:32 Epoch 2 | Batch 18/2891 | Timestep 5800 | LR 0.0001000000 | Loss 0.019622 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:34 Epoch 2 | Batch 28/2891 | Timestep 5810 | LR 0.0001000000 | Loss 0.031286 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:36 Epoch 2 | Batch 38/2891 | Timestep 5820 | LR 0.0001000000 | Loss 0.055710 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:38 Epoch 2 | Batch 48/2891 | Timestep 5830 | LR 0.0001000000 | Loss 0.017954 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:40 Epoch 2 | Batch 58/2891 | Timestep 5840 | LR 0.0001000000 | Loss 0.054826 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:41 Epoch 2 | Batch 68/2891 | Timestep 5850 | LR 0.0001000000 | Loss 0.126082 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:43 Epoch 2 | Batch 78/2891 | Timestep 5860 | LR 0.0001000000 | Loss 0.031041 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:44 Epoch 2 | Batch 88/2891 | Timestep 5870 | LR 0.0001000000 | Loss 0.045368 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:46 Epoch 2 | Batch 98/2891 | Timestep 5880 | LR 0.0001000000 | Loss 0.015143 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:48 Epoch 2 | Batch 108/2891 | Timestep 5890 | LR 0.0001000000 | Loss 0.028051 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:50 Epoch 2 | Batch 118/2891 | Timestep 5900 | LR 0.0001000000 | Loss 0.014467 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:51 Epoch 2 | Batch 128/2891 | Timestep 5910 | LR 0.0001000000 | Loss 0.020675 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:53 Epoch 2 | Batch 138/2891 | Timestep 5920 | LR 0.0001000000 | Loss 0.021832 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:55 Epoch 2 | Batch 148/2891 | Timestep 5930 | LR 0.0001000000 | Loss 0.028108 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:57 Epoch 2 | Batch 158/2891 | Timestep 5940 | LR 0.0001000000 | Loss 0.023601 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:04:59 Epoch 2 | Batch 168/2891 | Timestep 5950 | LR 0.0001000000 | Loss 0.046576 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:01 Epoch 2 | Batch 178/2891 | Timestep 5960 | LR 0.0001000000 | Loss 0.066530 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:02 Epoch 2 | Batch 188/2891 | Timestep 5970 | LR 0.0001000000 | Loss 0.032448 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:04 Epoch 2 | Batch 198/2891 | Timestep 5980 | LR 0.0001000000 | Loss 0.023488 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:05 Epoch 2 | Batch 208/2891 | Timestep 5990 | LR 0.0001000000 | Loss 0.108223 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:07 Epoch 2 | Batch 218/2891 | Timestep 6000 | LR 0.0001000000 | Loss 0.003419 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:08 Epoch 2 | Batch 228/2891 | Timestep 6010 | LR 0.0001000000 | Loss 0.084522 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:10 Epoch 2 | Batch 238/2891 | Timestep 6020 | LR 0.0001000000 | Loss 0.007273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:12 Epoch 2 | Batch 248/2891 | Timestep 6030 | LR 0.0001000000 | Loss 0.033732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:14 Epoch 2 | Batch 258/2891 | Timestep 6040 | LR 0.0001000000 | Loss 0.029660 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:16 Epoch 2 | Batch 268/2891 | Timestep 6050 | LR 0.0001000000 | Loss 0.036681 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:17 Epoch 2 | Batch 278/2891 | Timestep 6060 | LR 0.0001000000 | Loss 0.045492 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:19 Epoch 2 | Batch 288/2891 | Timestep 6070 | LR 0.0001000000 | Loss 0.040778 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:20 Epoch 2 | Batch 298/2891 | Timestep 6080 | LR 0.0001000000 | Loss 0.050264 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:22 Epoch 2 | Batch 308/2891 | Timestep 6090 | LR 0.0001000000 | Loss 0.028383 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:24 Epoch 2 | Batch 318/2891 | Timestep 6100 | LR 0.0001000000 | Loss 0.004003 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:26 Epoch 2 | Batch 328/2891 | Timestep 6110 | LR 0.0001000000 | Loss 0.015569 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:28 Epoch 2 | Batch 338/2891 | Timestep 6120 | LR 0.0001000000 | Loss 0.033434 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:29 Epoch 2 | Batch 348/2891 | Timestep 6130 | LR 0.0001000000 | Loss 0.036013 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:32 Epoch 2 | Batch 358/2891 | Timestep 6140 | LR 0.0001000000 | Loss 0.019335 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:34 Epoch 2 | Batch 368/2891 | Timestep 6150 | LR 0.0001000000 | Loss 0.186280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:36 Epoch 2 | Batch 378/2891 | Timestep 6160 | LR 0.0001000000 | Loss 0.047825 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:38 Epoch 2 | Batch 388/2891 | Timestep 6170 | LR 0.0001000000 | Loss 0.022678 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:39 Epoch 2 | Batch 398/2891 | Timestep 6180 | LR 0.0001000000 | Loss 0.052490 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:41 Epoch 2 | Batch 408/2891 | Timestep 6190 | LR 0.0001000000 | Loss 0.055354 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:43 Epoch 2 | Batch 418/2891 | Timestep 6200 | LR 0.0001000000 | Loss 0.053469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:44 Epoch 2 | Batch 428/2891 | Timestep 6210 | LR 0.0001000000 | Loss 0.043286 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:47 Epoch 2 | Batch 438/2891 | Timestep 6220 | LR 0.0001000000 | Loss 0.062445 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:48 Epoch 2 | Batch 448/2891 | Timestep 6230 | LR 0.0001000000 | Loss 0.021960 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:50 Epoch 2 | Batch 458/2891 | Timestep 6240 | LR 0.0001000000 | Loss 0.068496 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:52 Epoch 2 | Batch 468/2891 | Timestep 6250 | LR 0.0001000000 | Loss 0.035253 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:53 Epoch 2 | Batch 478/2891 | Timestep 6260 | LR 0.0001000000 | Loss 0.098304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:56 Epoch 2 | Batch 488/2891 | Timestep 6270 | LR 0.0001000000 | Loss 0.014396 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:57 Epoch 2 | Batch 498/2891 | Timestep 6280 | LR 0.0001000000 | Loss 0.017186 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:05:59 Epoch 2 | Batch 508/2891 | Timestep 6290 | LR 0.0001000000 | Loss 0.026585 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:00 Epoch 2 | Batch 518/2891 | Timestep 6300 | LR 0.0001000000 | Loss 0.024699 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:02 Epoch 2 | Batch 528/2891 | Timestep 6310 | LR 0.0001000000 | Loss 0.063971 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:04 Epoch 2 | Batch 538/2891 | Timestep 6320 | LR 0.0001000000 | Loss 0.038771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:06 Epoch 2 | Batch 548/2891 | Timestep 6330 | LR 0.0001000000 | Loss 0.024369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:08 Epoch 2 | Batch 558/2891 | Timestep 6340 | LR 0.0001000000 | Loss 0.045893 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:10 Epoch 2 | Batch 568/2891 | Timestep 6350 | LR 0.0001000000 | Loss 0.006051 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:11 Epoch 2 | Batch 578/2891 | Timestep 6360 | LR 0.0001000000 | Loss 0.092150 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:13 Epoch 2 | Batch 588/2891 | Timestep 6370 | LR 0.0001000000 | Loss 0.024567 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:15 Epoch 2 | Batch 598/2891 | Timestep 6380 | LR 0.0001000000 | Loss 0.051191 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:17 Epoch 2 | Batch 608/2891 | Timestep 6390 | LR 0.0001000000 | Loss 0.030570 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:19 Epoch 2 | Batch 618/2891 | Timestep 6400 | LR 0.0001000000 | Loss 0.030010 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:20 Epoch 2 | Batch 628/2891 | Timestep 6410 | LR 0.0001000000 | Loss 0.025497 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:22 Epoch 2 | Batch 638/2891 | Timestep 6420 | LR 0.0001000000 | Loss 0.006433 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:24 Epoch 2 | Batch 648/2891 | Timestep 6430 | LR 0.0001000000 | Loss 0.009189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:25 Epoch 2 | Batch 658/2891 | Timestep 6440 | LR 0.0001000000 | Loss 0.004735 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:27 Epoch 2 | Batch 668/2891 | Timestep 6450 | LR 0.0001000000 | Loss 0.014344 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:29 Epoch 2 | Batch 678/2891 | Timestep 6460 | LR 0.0001000000 | Loss 0.078928 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:31 Epoch 2 | Batch 688/2891 | Timestep 6470 | LR 0.0001000000 | Loss 0.030469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:32 Epoch 2 | Batch 698/2891 | Timestep 6480 | LR 0.0001000000 | Loss 0.010127 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:34 Epoch 2 | Batch 708/2891 | Timestep 6490 | LR 0.0001000000 | Loss 0.015697 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:36 Epoch 2 | Batch 718/2891 | Timestep 6500 | LR 0.0001000000 | Loss 0.044673 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:37 Epoch 2 | Batch 728/2891 | Timestep 6510 | LR 0.0001000000 | Loss 0.032196 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:39 Epoch 2 | Batch 738/2891 | Timestep 6520 | LR 0.0001000000 | Loss 0.016953 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:40 Epoch 2 | Batch 748/2891 | Timestep 6530 | LR 0.0001000000 | Loss 0.031103 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:42 Epoch 2 | Batch 758/2891 | Timestep 6540 | LR 0.0001000000 | Loss 0.030347 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:43 Epoch 2 | Batch 768/2891 | Timestep 6550 | LR 0.0001000000 | Loss 0.044480 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:45 Epoch 2 | Batch 778/2891 | Timestep 6560 | LR 0.0001000000 | Loss 0.026661 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:47 Epoch 2 | Batch 788/2891 | Timestep 6570 | LR 0.0001000000 | Loss 0.037592 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:48 Epoch 2 | Batch 798/2891 | Timestep 6580 | LR 0.0001000000 | Loss 0.030578 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:50 Epoch 2 | Batch 808/2891 | Timestep 6590 | LR 0.0001000000 | Loss 0.080021 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:52 Epoch 2 | Batch 818/2891 | Timestep 6600 | LR 0.0001000000 | Loss 0.022239 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:54 Epoch 2 | Batch 828/2891 | Timestep 6610 | LR 0.0001000000 | Loss 0.018747 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:56 Epoch 2 | Batch 838/2891 | Timestep 6620 | LR 0.0001000000 | Loss 0.004431 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:57 Epoch 2 | Batch 848/2891 | Timestep 6630 | LR 0.0001000000 | Loss 0.061570 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:06:59 Epoch 2 | Batch 858/2891 | Timestep 6640 | LR 0.0001000000 | Loss 0.130044 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:01 Epoch 2 | Batch 868/2891 | Timestep 6650 | LR 0.0001000000 | Loss 0.034043 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:02 Epoch 2 | Batch 878/2891 | Timestep 6660 | LR 0.0001000000 | Loss 0.022194 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:04 Epoch 2 | Batch 888/2891 | Timestep 6670 | LR 0.0001000000 | Loss 0.027111 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:06 Epoch 2 | Batch 898/2891 | Timestep 6680 | LR 0.0001000000 | Loss 0.003750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:08 Epoch 2 | Batch 908/2891 | Timestep 6690 | LR 0.0001000000 | Loss 0.008859 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:09 Epoch 2 | Batch 918/2891 | Timestep 6700 | LR 0.0001000000 | Loss 0.055593 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:11 Epoch 2 | Batch 928/2891 | Timestep 6710 | LR 0.0001000000 | Loss 0.023118 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:13 Epoch 2 | Batch 938/2891 | Timestep 6720 | LR 0.0001000000 | Loss 0.016998 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:14 Epoch 2 | Batch 948/2891 | Timestep 6730 | LR 0.0001000000 | Loss 0.077621 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:16 Epoch 2 | Batch 958/2891 | Timestep 6740 | LR 0.0001000000 | Loss 0.072361 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:18 Epoch 2 | Batch 968/2891 | Timestep 6750 | LR 0.0001000000 | Loss 0.021418 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:19 Epoch 2 | Batch 978/2891 | Timestep 6760 | LR 0.0001000000 | Loss 0.013302 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:21 Epoch 2 | Batch 988/2891 | Timestep 6770 | LR 0.0001000000 | Loss 0.025698 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:23 Epoch 2 | Batch 998/2891 | Timestep 6780 | LR 0.0001000000 | Loss 0.006382 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:24 Epoch 2 | Batch 1008/2891 | Timestep 6790 | LR 0.0001000000 | Loss 0.064554 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:26 Epoch 2 | Batch 1018/2891 | Timestep 6800 | LR 0.0001000000 | Loss 0.077816 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:28 Epoch 2 | Batch 1028/2891 | Timestep 6810 | LR 0.0001000000 | Loss 0.198092 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:29 Epoch 2 | Batch 1038/2891 | Timestep 6820 | LR 0.0001000000 | Loss 0.120138 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:31 Epoch 2 | Batch 1048/2891 | Timestep 6830 | LR 0.0001000000 | Loss 0.031872 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:32 Epoch 2 | Batch 1058/2891 | Timestep 6840 | LR 0.0001000000 | Loss 0.043944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:34 Epoch 2 | Batch 1068/2891 | Timestep 6850 | LR 0.0001000000 | Loss 0.062891 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:36 Epoch 2 | Batch 1078/2891 | Timestep 6860 | LR 0.0001000000 | Loss 0.046436 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:38 Epoch 2 | Batch 1088/2891 | Timestep 6870 | LR 0.0001000000 | Loss 0.029334 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:39 Epoch 2 | Batch 1098/2891 | Timestep 6880 | LR 0.0001000000 | Loss 0.019409 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:41 Epoch 2 | Batch 1108/2891 | Timestep 6890 | LR 0.0001000000 | Loss 0.024625 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:43 Epoch 2 | Batch 1118/2891 | Timestep 6900 | LR 0.0001000000 | Loss 0.029218 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:44 Epoch 2 | Batch 1128/2891 | Timestep 6910 | LR 0.0001000000 | Loss 0.082181 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:46 Epoch 2 | Batch 1138/2891 | Timestep 6920 | LR 0.0001000000 | Loss 0.020293 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:47 Epoch 2 | Batch 1148/2891 | Timestep 6930 | LR 0.0001000000 | Loss 0.024066 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:49 Epoch 2 | Batch 1158/2891 | Timestep 6940 | LR 0.0001000000 | Loss 0.045152 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:51 Epoch 2 | Batch 1168/2891 | Timestep 6950 | LR 0.0001000000 | Loss 0.018981 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:53 Epoch 2 | Batch 1178/2891 | Timestep 6960 | LR 0.0001000000 | Loss 0.072458 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:54 Epoch 2 | Batch 1188/2891 | Timestep 6970 | LR 0.0001000000 | Loss 0.011395 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:56 Epoch 2 | Batch 1198/2891 | Timestep 6980 | LR 0.0001000000 | Loss 0.005348 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:57 Epoch 2 | Batch 1208/2891 | Timestep 6990 | LR 0.0001000000 | Loss 0.022341 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:07:59 Epoch 2 | Batch 1218/2891 | Timestep 7000 | LR 0.0001000000 | Loss 0.008482 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:01 Epoch 2 | Batch 1228/2891 | Timestep 7010 | LR 0.0001000000 | Loss 0.043280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:03 Epoch 2 | Batch 1238/2891 | Timestep 7020 | LR 0.0001000000 | Loss 0.013287 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:04 Epoch 2 | Batch 1248/2891 | Timestep 7030 | LR 0.0001000000 | Loss 0.018764 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:07 Epoch 2 | Batch 1258/2891 | Timestep 7040 | LR 0.0001000000 | Loss 0.031845 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:08 Epoch 2 | Batch 1268/2891 | Timestep 7050 | LR 0.0001000000 | Loss 0.173743 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:10 Epoch 2 | Batch 1278/2891 | Timestep 7060 | LR 0.0001000000 | Loss 0.032073 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:12 Epoch 2 | Batch 1288/2891 | Timestep 7070 | LR 0.0001000000 | Loss 0.038109 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:13 Epoch 2 | Batch 1298/2891 | Timestep 7080 | LR 0.0001000000 | Loss 0.097465 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:15 Epoch 2 | Batch 1308/2891 | Timestep 7090 | LR 0.0001000000 | Loss 0.019151 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:17 Epoch 2 | Batch 1318/2891 | Timestep 7100 | LR 0.0001000000 | Loss 0.003228 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:18 Epoch 2 | Batch 1328/2891 | Timestep 7110 | LR 0.0001000000 | Loss 0.012273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:20 Epoch 2 | Batch 1338/2891 | Timestep 7120 | LR 0.0001000000 | Loss 0.069307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:22 Epoch 2 | Batch 1348/2891 | Timestep 7130 | LR 0.0001000000 | Loss 0.067829 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:23 Epoch 2 | Batch 1358/2891 | Timestep 7140 | LR 0.0001000000 | Loss 0.018203 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:25 Epoch 2 | Batch 1368/2891 | Timestep 7150 | LR 0.0001000000 | Loss 0.008884 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:26 Epoch 2 | Batch 1378/2891 | Timestep 7160 | LR 0.0001000000 | Loss 0.052635 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:28 Epoch 2 | Batch 1388/2891 | Timestep 7170 | LR 0.0001000000 | Loss 0.004608 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:30 Epoch 2 | Batch 1398/2891 | Timestep 7180 | LR 0.0001000000 | Loss 0.022393 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:32 Epoch 2 | Batch 1408/2891 | Timestep 7190 | LR 0.0001000000 | Loss 0.035527 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:33 Epoch 2 | Batch 1418/2891 | Timestep 7200 | LR 0.0001000000 | Loss 0.009806 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:35 Epoch 2 | Batch 1428/2891 | Timestep 7210 | LR 0.0001000000 | Loss 0.016313 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:36 Epoch 2 | Batch 1438/2891 | Timestep 7220 | LR 0.0001000000 | Loss 0.021719 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:37 Epoch 2 | Batch 1448/2891 | Timestep 7230 | LR 0.0001000000 | Loss 0.042304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:39 Epoch 2 | Batch 1458/2891 | Timestep 7240 | LR 0.0001000000 | Loss 0.017874 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:41 Epoch 2 | Batch 1468/2891 | Timestep 7250 | LR 0.0001000000 | Loss 0.020105 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:43 Epoch 2 | Batch 1478/2891 | Timestep 7260 | LR 0.0001000000 | Loss 0.066226 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:44 Epoch 2 | Batch 1488/2891 | Timestep 7270 | LR 0.0001000000 | Loss 0.026038 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:46 Epoch 2 | Batch 1498/2891 | Timestep 7280 | LR 0.0001000000 | Loss 0.005749 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:48 Epoch 2 | Batch 1508/2891 | Timestep 7290 | LR 0.0001000000 | Loss 0.021440 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:49 Epoch 2 | Batch 1518/2891 | Timestep 7300 | LR 0.0001000000 | Loss 0.011798 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:51 Epoch 2 | Batch 1528/2891 | Timestep 7310 | LR 0.0001000000 | Loss 0.110854 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:53 Epoch 2 | Batch 1538/2891 | Timestep 7320 | LR 0.0001000000 | Loss 0.020011 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:54 Epoch 2 | Batch 1548/2891 | Timestep 7330 | LR 0.0001000000 | Loss 0.014235 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:56 Epoch 2 | Batch 1558/2891 | Timestep 7340 | LR 0.0001000000 | Loss 0.042174 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:08:58 Epoch 2 | Batch 1568/2891 | Timestep 7350 | LR 0.0001000000 | Loss 0.048980 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:00 Epoch 2 | Batch 1578/2891 | Timestep 7360 | LR 0.0001000000 | Loss 0.029984 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:02 Epoch 2 | Batch 1588/2891 | Timestep 7370 | LR 0.0001000000 | Loss 0.015737 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:04 Epoch 2 | Batch 1598/2891 | Timestep 7380 | LR 0.0001000000 | Loss 0.016636 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:05 Epoch 2 | Batch 1608/2891 | Timestep 7390 | LR 0.0001000000 | Loss 0.022475 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:07 Epoch 2 | Batch 1618/2891 | Timestep 7400 | LR 0.0001000000 | Loss 0.063551 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:09 Epoch 2 | Batch 1628/2891 | Timestep 7410 | LR 0.0001000000 | Loss 0.008772 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:10 Epoch 2 | Batch 1638/2891 | Timestep 7420 | LR 0.0001000000 | Loss 0.022500 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:12 Epoch 2 | Batch 1648/2891 | Timestep 7430 | LR 0.0001000000 | Loss 0.018873 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:14 Epoch 2 | Batch 1658/2891 | Timestep 7440 | LR 0.0001000000 | Loss 0.038088 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:16 Epoch 2 | Batch 1668/2891 | Timestep 7450 | LR 0.0001000000 | Loss 0.035322 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:17 Epoch 2 | Batch 1678/2891 | Timestep 7460 | LR 0.0001000000 | Loss 0.010019 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:19 Epoch 2 | Batch 1688/2891 | Timestep 7470 | LR 0.0001000000 | Loss 0.015401 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:20 Epoch 2 | Batch 1698/2891 | Timestep 7480 | LR 0.0001000000 | Loss 0.036093 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:22 Epoch 2 | Batch 1708/2891 | Timestep 7490 | LR 0.0001000000 | Loss 0.017100 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:24 Epoch 2 | Batch 1718/2891 | Timestep 7500 | LR 0.0001000000 | Loss 0.015913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:26 Epoch 2 | Batch 1728/2891 | Timestep 7510 | LR 0.0001000000 | Loss 0.029521 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:27 Epoch 2 | Batch 1738/2891 | Timestep 7520 | LR 0.0001000000 | Loss 0.046446 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:29 Epoch 2 | Batch 1748/2891 | Timestep 7530 | LR 0.0001000000 | Loss 0.007442 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:31 Epoch 2 | Batch 1758/2891 | Timestep 7540 | LR 0.0001000000 | Loss 0.013459 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:32 Epoch 2 | Batch 1768/2891 | Timestep 7550 | LR 0.0001000000 | Loss 0.054011 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:34 Epoch 2 | Batch 1778/2891 | Timestep 7560 | LR 0.0001000000 | Loss 0.010833 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:36 Epoch 2 | Batch 1788/2891 | Timestep 7570 | LR 0.0001000000 | Loss 0.012970 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:37 Epoch 2 | Batch 1798/2891 | Timestep 7580 | LR 0.0001000000 | Loss 0.018151 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:39 Epoch 2 | Batch 1808/2891 | Timestep 7590 | LR 0.0001000000 | Loss 0.037897 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:40 Epoch 2 | Batch 1818/2891 | Timestep 7600 | LR 0.0001000000 | Loss 0.066994 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:42 Epoch 2 | Batch 1828/2891 | Timestep 7610 | LR 0.0001000000 | Loss 0.036396 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:44 Epoch 2 | Batch 1838/2891 | Timestep 7620 | LR 0.0001000000 | Loss 0.211817 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:46 Epoch 2 | Batch 1848/2891 | Timestep 7630 | LR 0.0001000000 | Loss 0.009299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:48 Epoch 2 | Batch 1858/2891 | Timestep 7640 | LR 0.0001000000 | Loss 0.006716 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:50 Epoch 2 | Batch 1868/2891 | Timestep 7650 | LR 0.0001000000 | Loss 0.014479 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:51 Epoch 2 | Batch 1878/2891 | Timestep 7660 | LR 0.0001000000 | Loss 0.018273 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:53 Epoch 2 | Batch 1888/2891 | Timestep 7670 | LR 0.0001000000 | Loss 0.061302 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:55 Epoch 2 | Batch 1898/2891 | Timestep 7680 | LR 0.0001000000 | Loss 0.059422 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:57 Epoch 2 | Batch 1908/2891 | Timestep 7690 | LR 0.0001000000 | Loss 0.011469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:09:59 Epoch 2 | Batch 1918/2891 | Timestep 7700 | LR 0.0001000000 | Loss 0.029536 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:00 Epoch 2 | Batch 1928/2891 | Timestep 7710 | LR 0.0001000000 | Loss 0.034531 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:02 Epoch 2 | Batch 1938/2891 | Timestep 7720 | LR 0.0001000000 | Loss 0.012338 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:04 Epoch 2 | Batch 1948/2891 | Timestep 7730 | LR 0.0001000000 | Loss 0.027616 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:05 Epoch 2 | Batch 1958/2891 | Timestep 7740 | LR 0.0001000000 | Loss 0.161001 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:07 Epoch 2 | Batch 1968/2891 | Timestep 7750 | LR 0.0001000000 | Loss 0.046769 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:09 Epoch 2 | Batch 1978/2891 | Timestep 7760 | LR 0.0001000000 | Loss 0.013153 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:10 Epoch 2 | Batch 1988/2891 | Timestep 7770 | LR 0.0001000000 | Loss 0.024571 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:12 Epoch 2 | Batch 1998/2891 | Timestep 7780 | LR 0.0001000000 | Loss 0.037213 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:14 Epoch 2 | Batch 2008/2891 | Timestep 7790 | LR 0.0001000000 | Loss 0.012842 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:16 Epoch 2 | Batch 2018/2891 | Timestep 7800 | LR 0.0001000000 | Loss 0.004328 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:17 Epoch 2 | Batch 2028/2891 | Timestep 7810 | LR 0.0001000000 | Loss 0.040081 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:19 Epoch 2 | Batch 2038/2891 | Timestep 7820 | LR 0.0001000000 | Loss 0.011765 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:20 Epoch 2 | Batch 2048/2891 | Timestep 7830 | LR 0.0001000000 | Loss 0.106619 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:22 Epoch 2 | Batch 2058/2891 | Timestep 7840 | LR 0.0001000000 | Loss 0.012178 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:24 Epoch 2 | Batch 2068/2891 | Timestep 7850 | LR 0.0001000000 | Loss 0.065703 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:25 Epoch 2 | Batch 2078/2891 | Timestep 7860 | LR 0.0001000000 | Loss 0.033280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:27 Epoch 2 | Batch 2088/2891 | Timestep 7870 | LR 0.0001000000 | Loss 0.057095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:29 Epoch 2 | Batch 2098/2891 | Timestep 7880 | LR 0.0001000000 | Loss 0.074002 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:30 Epoch 2 | Batch 2108/2891 | Timestep 7890 | LR 0.0001000000 | Loss 0.059892 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:32 Epoch 2 | Batch 2118/2891 | Timestep 7900 | LR 0.0001000000 | Loss 0.016001 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:34 Epoch 2 | Batch 2128/2891 | Timestep 7910 | LR 0.0001000000 | Loss 0.067941 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:36 Epoch 2 | Batch 2138/2891 | Timestep 7920 | LR 0.0001000000 | Loss 0.083547 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:37 Epoch 2 | Batch 2148/2891 | Timestep 7930 | LR 0.0001000000 | Loss 0.069415 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:39 Epoch 2 | Batch 2158/2891 | Timestep 7940 | LR 0.0001000000 | Loss 0.049530 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:41 Epoch 2 | Batch 2168/2891 | Timestep 7950 | LR 0.0001000000 | Loss 0.017624 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:42 Epoch 2 | Batch 2178/2891 | Timestep 7960 | LR 0.0001000000 | Loss 0.012760 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:44 Epoch 2 | Batch 2188/2891 | Timestep 7970 | LR 0.0001000000 | Loss 0.033476 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:46 Epoch 2 | Batch 2198/2891 | Timestep 7980 | LR 0.0001000000 | Loss 0.013046 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:48 Epoch 2 | Batch 2208/2891 | Timestep 7990 | LR 0.0001000000 | Loss 0.082877 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:50 Epoch 2 | Batch 2218/2891 | Timestep 8000 | LR 0.0001000000 | Loss 0.019154 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:51 Epoch 2 | Batch 2228/2891 | Timestep 8010 | LR 0.0001000000 | Loss 0.076938 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:53 Epoch 2 | Batch 2238/2891 | Timestep 8020 | LR 0.0001000000 | Loss 0.093735 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:55 Epoch 2 | Batch 2248/2891 | Timestep 8030 | LR 0.0001000000 | Loss 0.020349 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:56 Epoch 2 | Batch 2258/2891 | Timestep 8040 | LR 0.0001000000 | Loss 0.021298 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:10:58 Epoch 2 | Batch 2268/2891 | Timestep 8050 | LR 0.0001000000 | Loss 0.018563 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:00 Epoch 2 | Batch 2278/2891 | Timestep 8060 | LR 0.0001000000 | Loss 0.022792 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:01 Epoch 2 | Batch 2288/2891 | Timestep 8070 | LR 0.0001000000 | Loss 0.041537 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:03 Epoch 2 | Batch 2298/2891 | Timestep 8080 | LR 0.0001000000 | Loss 0.075368 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:05 Epoch 2 | Batch 2308/2891 | Timestep 8090 | LR 0.0001000000 | Loss 0.013635 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:07 Epoch 2 | Batch 2318/2891 | Timestep 8100 | LR 0.0001000000 | Loss 0.007155 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:08 Epoch 2 | Batch 2328/2891 | Timestep 8110 | LR 0.0001000000 | Loss 0.007918 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:10 Epoch 2 | Batch 2338/2891 | Timestep 8120 | LR 0.0001000000 | Loss 0.049143 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:11 Epoch 2 | Batch 2348/2891 | Timestep 8130 | LR 0.0001000000 | Loss 0.019092 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:13 Epoch 2 | Batch 2358/2891 | Timestep 8140 | LR 0.0001000000 | Loss 0.049245 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:14 Epoch 2 | Batch 2368/2891 | Timestep 8150 | LR 0.0001000000 | Loss 0.027486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:16 Epoch 2 | Batch 2378/2891 | Timestep 8160 | LR 0.0001000000 | Loss 0.044379 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:18 Epoch 2 | Batch 2388/2891 | Timestep 8170 | LR 0.0001000000 | Loss 0.037417 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:20 Epoch 2 | Batch 2398/2891 | Timestep 8180 | LR 0.0001000000 | Loss 0.085612 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:21 Epoch 2 | Batch 2408/2891 | Timestep 8190 | LR 0.0001000000 | Loss 0.023509 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:23 Epoch 2 | Batch 2418/2891 | Timestep 8200 | LR 0.0001000000 | Loss 0.075006 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:24 Epoch 2 | Batch 2428/2891 | Timestep 8210 | LR 0.0001000000 | Loss 0.048992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:26 Epoch 2 | Batch 2438/2891 | Timestep 8220 | LR 0.0001000000 | Loss 0.020398 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:27 Epoch 2 | Batch 2448/2891 | Timestep 8230 | LR 0.0001000000 | Loss 0.217579 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:29 Epoch 2 | Batch 2458/2891 | Timestep 8240 | LR 0.0001000000 | Loss 0.060030 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:30 Epoch 2 | Batch 2468/2891 | Timestep 8250 | LR 0.0001000000 | Loss 0.052345 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:32 Epoch 2 | Batch 2478/2891 | Timestep 8260 | LR 0.0001000000 | Loss 0.028853 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:34 Epoch 2 | Batch 2488/2891 | Timestep 8270 | LR 0.0001000000 | Loss 0.113759 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:36 Epoch 2 | Batch 2498/2891 | Timestep 8280 | LR 0.0001000000 | Loss 0.036329 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:37 Epoch 2 | Batch 2508/2891 | Timestep 8290 | LR 0.0001000000 | Loss 0.043353 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:39 Epoch 2 | Batch 2518/2891 | Timestep 8300 | LR 0.0001000000 | Loss 0.095892 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:41 Epoch 2 | Batch 2528/2891 | Timestep 8310 | LR 0.0001000000 | Loss 0.018418 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:43 Epoch 2 | Batch 2538/2891 | Timestep 8320 | LR 0.0001000000 | Loss 0.002992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:44 Epoch 2 | Batch 2548/2891 | Timestep 8330 | LR 0.0001000000 | Loss 0.027280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:46 Epoch 2 | Batch 2558/2891 | Timestep 8340 | LR 0.0001000000 | Loss 0.069280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:48 Epoch 2 | Batch 2568/2891 | Timestep 8350 | LR 0.0001000000 | Loss 0.080831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:50 Epoch 2 | Batch 2578/2891 | Timestep 8360 | LR 0.0001000000 | Loss 0.042685 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:52 Epoch 2 | Batch 2588/2891 | Timestep 8370 | LR 0.0001000000 | Loss 0.018225 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:53 Epoch 2 | Batch 2598/2891 | Timestep 8380 | LR 0.0001000000 | Loss 0.019200 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:55 Epoch 2 | Batch 2608/2891 | Timestep 8390 | LR 0.0001000000 | Loss 0.055612 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:57 Epoch 2 | Batch 2618/2891 | Timestep 8400 | LR 0.0001000000 | Loss 0.006967 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:11:59 Epoch 2 | Batch 2628/2891 | Timestep 8410 | LR 0.0001000000 | Loss 0.012074 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:00 Epoch 2 | Batch 2638/2891 | Timestep 8420 | LR 0.0001000000 | Loss 0.016244 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:02 Epoch 2 | Batch 2648/2891 | Timestep 8430 | LR 0.0001000000 | Loss 0.024127 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:03 Epoch 2 | Batch 2658/2891 | Timestep 8440 | LR 0.0001000000 | Loss 0.012309 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:05 Epoch 2 | Batch 2668/2891 | Timestep 8450 | LR 0.0001000000 | Loss 0.008123 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:07 Epoch 2 | Batch 2678/2891 | Timestep 8460 | LR 0.0001000000 | Loss 0.070761 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:09 Epoch 2 | Batch 2688/2891 | Timestep 8470 | LR 0.0001000000 | Loss 0.027963 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:11 Epoch 2 | Batch 2698/2891 | Timestep 8480 | LR 0.0001000000 | Loss 0.021921 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:12 Epoch 2 | Batch 2708/2891 | Timestep 8490 | LR 0.0001000000 | Loss 0.047272 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:14 Epoch 2 | Batch 2718/2891 | Timestep 8500 | LR 0.0001000000 | Loss 0.038941 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:16 Epoch 2 | Batch 2728/2891 | Timestep 8510 | LR 0.0001000000 | Loss 0.047258 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:18 Epoch 2 | Batch 2738/2891 | Timestep 8520 | LR 0.0001000000 | Loss 0.029844 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:19 Epoch 2 | Batch 2748/2891 | Timestep 8530 | LR 0.0001000000 | Loss 0.012824 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:21 Epoch 2 | Batch 2758/2891 | Timestep 8540 | LR 0.0001000000 | Loss 0.072942 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:23 Epoch 2 | Batch 2768/2891 | Timestep 8550 | LR 0.0001000000 | Loss 0.039632 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:24 Epoch 2 | Batch 2778/2891 | Timestep 8560 | LR 0.0001000000 | Loss 0.028280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:26 Epoch 2 | Batch 2788/2891 | Timestep 8570 | LR 0.0001000000 | Loss 0.029046 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:28 Epoch 2 | Batch 2798/2891 | Timestep 8580 | LR 0.0001000000 | Loss 0.021980 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:30 Epoch 2 | Batch 2808/2891 | Timestep 8590 | LR 0.0001000000 | Loss 0.045408 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:31 Epoch 2 | Batch 2818/2891 | Timestep 8600 | LR 0.0001000000 | Loss 0.096486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:33 Epoch 2 | Batch 2828/2891 | Timestep 8610 | LR 0.0001000000 | Loss 0.008021 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:34 Epoch 2 | Batch 2838/2891 | Timestep 8620 | LR 0.0001000000 | Loss 0.017914 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:36 Epoch 2 | Batch 2848/2891 | Timestep 8630 | LR 0.0001000000 | Loss 0.049571 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:38 Epoch 2 | Batch 2858/2891 | Timestep 8640 | LR 0.0001000000 | Loss 0.053629 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:39 Epoch 2 | Batch 2868/2891 | Timestep 8650 | LR 0.0001000000 | Loss 0.019634 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:41 Epoch 2 | Batch 2878/2891 | Timestep 8660 | LR 0.0001000000 | Loss 0.095433 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:43 Epoch 2 | Batch 2888/2891 | Timestep 8670 | LR 0.0001000000 | Loss 0.051483 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:12:43 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:13:17 precision recall f1-score support CARDINAL 0.8210 0.7824 0.8012 170 CURR 0.9500 0.7917 0.8636 24 DATE 0.9146 0.9373 0.9258 1691 EVENT 0.6517 0.7432 0.6944 292 FAC 0.6741 0.7712 0.7194 118 GPE 0.9522 0.9620 0.9571 2156 LANGUAGE 0.7692 0.6250 0.6897 16 LAW 0.6458 0.6596 0.6526 47 LOC 0.7727 0.7556 0.7640 90 MONEY 0.7826 0.8182 0.8000 22 NORP 0.7051 0.5989 0.6477 551 OCC 0.8602 0.7663 0.8105 522 ORDINAL 0.9287 0.9099 0.9192 544 ORG 0.8800 0.9160 0.8977 1882 PERCENT 0.9091 0.8333 0.8696 12 PERS 0.9266 0.9116 0.9191 679 PRODUCT 0.5000 0.2500 0.3333 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.6757 0.7576 0.7143 33 UNIT 0.6000 0.7500 0.6667 4 WEBSITE 0.4000 0.4750 0.4343 80 micro avg 0.8790 0.8826 0.8808 8944 macro avg 0.7612 0.7467 0.7499 8944 weighted avg 0.8791 0.8826 0.8801 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:13:28 Epoch 2 | Timestep 8673 | Train Loss 0.037972 | Val Loss 0.051614 | F1 0.880781 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:13:28 ** Validation improved, evaluating test data ** INFO Nested.data.transforms Tue, 23 Dec 2025 10:13:51 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 Tue, 23 Dec 2025 10:14:09 Predictions written to /rep/nhamad/ArabicNER/data/output/dir/predictions.txt INFO root Tue, 23 Dec 2025 10:14:35 precision recall f1-score support CARDINAL 0.8270 0.8246 0.8258 342 CURR 0.9375 0.7317 0.8219 41 DATE 0.9235 0.9420 0.9327 3206 EVENT 0.6661 0.7421 0.7021 570 FAC 0.6798 0.7107 0.6949 242 GPE 0.9390 0.9589 0.9489 4336 LANGUAGE 0.9630 0.5909 0.7324 44 LAW 0.7294 0.6889 0.7086 90 LOC 0.7864 0.7431 0.7642 218 MONEY 0.6667 0.7879 0.7222 33 NORP 0.7346 0.6203 0.6726 1093 OCC 0.8644 0.7516 0.8041 1103 ORDINAL 0.9525 0.9252 0.9386 1083 ORG 0.8628 0.9126 0.8870 3798 PERCENT 0.9677 0.9091 0.9375 33 PERS 0.9042 0.9024 0.9033 1568 PRODUCT 0.7500 0.3158 0.4444 19 QUANTITY 0.6000 0.6667 0.6316 9 TIME 0.6190 0.6190 0.6190 84 UNIT 0.6154 0.7273 0.6667 11 WEBSITE 0.2015 0.4741 0.2828 116 micro avg 0.8716 0.8819 0.8767 18039 macro avg 0.7710 0.7402 0.7448 18039 weighted avg 0.8768 0.8819 0.8779 18039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:14:58 Epoch 2 | Timestep 8673 | Test Loss 0.055388 | F1 0.876715 INFO Nested.trainers.BaseTrainer Tue, 23 Dec 2025 10:14:58 Saving checkpoint to /rep/nhamad/ArabicNER/data/output/dir/checkpoints/checkpoint_2.pt INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:02 Epoch 3 | Batch 7/2891 | Timestep 8680 | LR 0.0001000000 | Loss 0.030889 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:03 Epoch 3 | Batch 17/2891 | Timestep 8690 | LR 0.0001000000 | Loss 0.004527 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:05 Epoch 3 | Batch 27/2891 | Timestep 8700 | LR 0.0001000000 | Loss 0.117239 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:07 Epoch 3 | Batch 37/2891 | Timestep 8710 | LR 0.0001000000 | Loss 0.019974 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:09 Epoch 3 | Batch 47/2891 | Timestep 8720 | LR 0.0001000000 | Loss 0.003714 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:10 Epoch 3 | Batch 57/2891 | Timestep 8730 | LR 0.0001000000 | Loss 0.020350 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:12 Epoch 3 | Batch 67/2891 | Timestep 8740 | LR 0.0001000000 | Loss 0.025352 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:14 Epoch 3 | Batch 77/2891 | Timestep 8750 | LR 0.0001000000 | Loss 0.028685 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:16 Epoch 3 | Batch 87/2891 | Timestep 8760 | LR 0.0001000000 | Loss 0.020103 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:17 Epoch 3 | Batch 97/2891 | Timestep 8770 | LR 0.0001000000 | Loss 0.033712 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:19 Epoch 3 | Batch 107/2891 | Timestep 8780 | LR 0.0001000000 | Loss 0.014365 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:21 Epoch 3 | Batch 117/2891 | Timestep 8790 | LR 0.0001000000 | Loss 0.009140 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:22 Epoch 3 | Batch 127/2891 | Timestep 8800 | LR 0.0001000000 | Loss 0.006147 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:24 Epoch 3 | Batch 137/2891 | Timestep 8810 | LR 0.0001000000 | Loss 0.033077 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:26 Epoch 3 | Batch 147/2891 | Timestep 8820 | LR 0.0001000000 | Loss 0.013767 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:27 Epoch 3 | Batch 157/2891 | Timestep 8830 | LR 0.0001000000 | Loss 0.153583 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:29 Epoch 3 | Batch 167/2891 | Timestep 8840 | LR 0.0001000000 | Loss 0.004528 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:31 Epoch 3 | Batch 177/2891 | Timestep 8850 | LR 0.0001000000 | Loss 0.004217 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:32 Epoch 3 | Batch 187/2891 | Timestep 8860 | LR 0.0001000000 | Loss 0.019581 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:34 Epoch 3 | Batch 197/2891 | Timestep 8870 | LR 0.0001000000 | Loss 0.053168 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:35 Epoch 3 | Batch 207/2891 | Timestep 8880 | LR 0.0001000000 | Loss 0.018437 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:37 Epoch 3 | Batch 217/2891 | Timestep 8890 | LR 0.0001000000 | Loss 0.039016 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:39 Epoch 3 | Batch 227/2891 | Timestep 8900 | LR 0.0001000000 | Loss 0.026112 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:41 Epoch 3 | Batch 237/2891 | Timestep 8910 | LR 0.0001000000 | Loss 0.006994 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:42 Epoch 3 | Batch 247/2891 | Timestep 8920 | LR 0.0001000000 | Loss 0.010313 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:45 Epoch 3 | Batch 257/2891 | Timestep 8930 | LR 0.0001000000 | Loss 0.023940 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:46 Epoch 3 | Batch 267/2891 | Timestep 8940 | LR 0.0001000000 | Loss 0.018745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:48 Epoch 3 | Batch 277/2891 | Timestep 8950 | LR 0.0001000000 | Loss 0.031695 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:50 Epoch 3 | Batch 287/2891 | Timestep 8960 | LR 0.0001000000 | Loss 0.027033 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:51 Epoch 3 | Batch 297/2891 | Timestep 8970 | LR 0.0001000000 | Loss 0.013393 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:53 Epoch 3 | Batch 307/2891 | Timestep 8980 | LR 0.0001000000 | Loss 0.002497 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:54 Epoch 3 | Batch 317/2891 | Timestep 8990 | LR 0.0001000000 | Loss 0.014184 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:57 Epoch 3 | Batch 327/2891 | Timestep 9000 | LR 0.0001000000 | Loss 0.015863 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:15:58 Epoch 3 | Batch 337/2891 | Timestep 9010 | LR 0.0001000000 | Loss 0.010237 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:00 Epoch 3 | Batch 347/2891 | Timestep 9020 | LR 0.0001000000 | Loss 0.010746 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:01 Epoch 3 | Batch 357/2891 | Timestep 9030 | LR 0.0001000000 | Loss 0.004000 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:04 Epoch 3 | Batch 367/2891 | Timestep 9040 | LR 0.0001000000 | Loss 0.023911 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:06 Epoch 3 | Batch 377/2891 | Timestep 9050 | LR 0.0001000000 | Loss 0.008081 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:07 Epoch 3 | Batch 387/2891 | Timestep 9060 | LR 0.0001000000 | Loss 0.047732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:09 Epoch 3 | Batch 397/2891 | Timestep 9070 | LR 0.0001000000 | Loss 0.023063 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:11 Epoch 3 | Batch 407/2891 | Timestep 9080 | LR 0.0001000000 | Loss 0.006470 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:13 Epoch 3 | Batch 417/2891 | Timestep 9090 | LR 0.0001000000 | Loss 0.088702 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:15 Epoch 3 | Batch 427/2891 | Timestep 9100 | LR 0.0001000000 | Loss 0.010337 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:17 Epoch 3 | Batch 437/2891 | Timestep 9110 | LR 0.0001000000 | Loss 0.031470 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:18 Epoch 3 | Batch 447/2891 | Timestep 9120 | LR 0.0001000000 | Loss 0.010633 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:20 Epoch 3 | Batch 457/2891 | Timestep 9130 | LR 0.0001000000 | Loss 0.126180 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:22 Epoch 3 | Batch 467/2891 | Timestep 9140 | LR 0.0001000000 | Loss 0.043533 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:24 Epoch 3 | Batch 477/2891 | Timestep 9150 | LR 0.0001000000 | Loss 0.020638 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:25 Epoch 3 | Batch 487/2891 | Timestep 9160 | LR 0.0001000000 | Loss 0.003019 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:27 Epoch 3 | Batch 497/2891 | Timestep 9170 | LR 0.0001000000 | Loss 0.003831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:29 Epoch 3 | Batch 507/2891 | Timestep 9180 | LR 0.0001000000 | Loss 0.053034 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:30 Epoch 3 | Batch 517/2891 | Timestep 9190 | LR 0.0001000000 | Loss 0.028534 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:32 Epoch 3 | Batch 527/2891 | Timestep 9200 | LR 0.0001000000 | Loss 0.043868 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:34 Epoch 3 | Batch 537/2891 | Timestep 9210 | LR 0.0001000000 | Loss 0.024387 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:36 Epoch 3 | Batch 547/2891 | Timestep 9220 | LR 0.0001000000 | Loss 0.030225 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:37 Epoch 3 | Batch 557/2891 | Timestep 9230 | LR 0.0001000000 | Loss 0.091096 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:40 Epoch 3 | Batch 567/2891 | Timestep 9240 | LR 0.0001000000 | Loss 0.054295 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:41 Epoch 3 | Batch 577/2891 | Timestep 9250 | LR 0.0001000000 | Loss 0.038173 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:43 Epoch 3 | Batch 587/2891 | Timestep 9260 | LR 0.0001000000 | Loss 0.114384 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:45 Epoch 3 | Batch 597/2891 | Timestep 9270 | LR 0.0001000000 | Loss 0.051680 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:47 Epoch 3 | Batch 607/2891 | Timestep 9280 | LR 0.0001000000 | Loss 0.039866 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:48 Epoch 3 | Batch 617/2891 | Timestep 9290 | LR 0.0001000000 | Loss 0.028584 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:50 Epoch 3 | Batch 627/2891 | Timestep 9300 | LR 0.0001000000 | Loss 0.021104 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:52 Epoch 3 | Batch 637/2891 | Timestep 9310 | LR 0.0001000000 | Loss 0.020992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:53 Epoch 3 | Batch 647/2891 | Timestep 9320 | LR 0.0001000000 | Loss 0.013000 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:55 Epoch 3 | Batch 657/2891 | Timestep 9330 | LR 0.0001000000 | Loss 0.013797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:57 Epoch 3 | Batch 667/2891 | Timestep 9340 | LR 0.0001000000 | Loss 0.128490 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:16:59 Epoch 3 | Batch 677/2891 | Timestep 9350 | LR 0.0001000000 | Loss 0.059845 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:01 Epoch 3 | Batch 687/2891 | Timestep 9360 | LR 0.0001000000 | Loss 0.035361 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:02 Epoch 3 | Batch 697/2891 | Timestep 9370 | LR 0.0001000000 | Loss 0.092009 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:04 Epoch 3 | Batch 707/2891 | Timestep 9380 | LR 0.0001000000 | Loss 0.015064 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:06 Epoch 3 | Batch 717/2891 | Timestep 9390 | LR 0.0001000000 | Loss 0.067018 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:07 Epoch 3 | Batch 727/2891 | Timestep 9400 | LR 0.0001000000 | Loss 0.009193 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:09 Epoch 3 | Batch 737/2891 | Timestep 9410 | LR 0.0001000000 | Loss 0.032999 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:11 Epoch 3 | Batch 747/2891 | Timestep 9420 | LR 0.0001000000 | Loss 0.006573 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:12 Epoch 3 | Batch 757/2891 | Timestep 9430 | LR 0.0001000000 | Loss 0.081655 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:14 Epoch 3 | Batch 767/2891 | Timestep 9440 | LR 0.0001000000 | Loss 0.026397 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:15 Epoch 3 | Batch 777/2891 | Timestep 9450 | LR 0.0001000000 | Loss 0.035395 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:17 Epoch 3 | Batch 787/2891 | Timestep 9460 | LR 0.0001000000 | Loss 0.038476 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:19 Epoch 3 | Batch 797/2891 | Timestep 9470 | LR 0.0001000000 | Loss 0.016761 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:20 Epoch 3 | Batch 807/2891 | Timestep 9480 | LR 0.0001000000 | Loss 0.006094 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:22 Epoch 3 | Batch 817/2891 | Timestep 9490 | LR 0.0001000000 | Loss 0.044107 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:24 Epoch 3 | Batch 827/2891 | Timestep 9500 | LR 0.0001000000 | Loss 0.041966 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:25 Epoch 3 | Batch 837/2891 | Timestep 9510 | LR 0.0001000000 | Loss 0.011059 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:27 Epoch 3 | Batch 847/2891 | Timestep 9520 | LR 0.0001000000 | Loss 0.056211 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:29 Epoch 3 | Batch 857/2891 | Timestep 9530 | LR 0.0001000000 | Loss 0.011677 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:30 Epoch 3 | Batch 867/2891 | Timestep 9540 | LR 0.0001000000 | Loss 0.006050 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:32 Epoch 3 | Batch 877/2891 | Timestep 9550 | LR 0.0001000000 | Loss 0.074285 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:34 Epoch 3 | Batch 887/2891 | Timestep 9560 | LR 0.0001000000 | Loss 0.037622 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:36 Epoch 3 | Batch 897/2891 | Timestep 9570 | LR 0.0001000000 | Loss 0.052590 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:37 Epoch 3 | Batch 907/2891 | Timestep 9580 | LR 0.0001000000 | Loss 0.067774 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:39 Epoch 3 | Batch 917/2891 | Timestep 9590 | LR 0.0001000000 | Loss 0.012945 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:41 Epoch 3 | Batch 927/2891 | Timestep 9600 | LR 0.0001000000 | Loss 0.015797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:43 Epoch 3 | Batch 937/2891 | Timestep 9610 | LR 0.0001000000 | Loss 0.004371 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:45 Epoch 3 | Batch 947/2891 | Timestep 9620 | LR 0.0001000000 | Loss 0.031730 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:46 Epoch 3 | Batch 957/2891 | Timestep 9630 | LR 0.0001000000 | Loss 0.031752 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:48 Epoch 3 | Batch 967/2891 | Timestep 9640 | LR 0.0001000000 | Loss 0.073692 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:49 Epoch 3 | Batch 977/2891 | Timestep 9650 | LR 0.0001000000 | Loss 0.011953 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:51 Epoch 3 | Batch 987/2891 | Timestep 9660 | LR 0.0001000000 | Loss 0.004152 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:53 Epoch 3 | Batch 997/2891 | Timestep 9670 | LR 0.0001000000 | Loss 0.005525 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:54 Epoch 3 | Batch 1007/2891 | Timestep 9680 | LR 0.0001000000 | Loss 0.013599 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:55 Epoch 3 | Batch 1017/2891 | Timestep 9690 | LR 0.0001000000 | Loss 0.038378 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:57 Epoch 3 | Batch 1027/2891 | Timestep 9700 | LR 0.0001000000 | Loss 0.001840 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:17:59 Epoch 3 | Batch 1037/2891 | Timestep 9710 | LR 0.0001000000 | Loss 0.059667 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:00 Epoch 3 | Batch 1047/2891 | Timestep 9720 | LR 0.0001000000 | Loss 0.049350 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:02 Epoch 3 | Batch 1057/2891 | Timestep 9730 | LR 0.0001000000 | Loss 0.036968 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:04 Epoch 3 | Batch 1067/2891 | Timestep 9740 | LR 0.0001000000 | Loss 0.025365 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:05 Epoch 3 | Batch 1077/2891 | Timestep 9750 | LR 0.0001000000 | Loss 0.010033 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:07 Epoch 3 | Batch 1087/2891 | Timestep 9760 | LR 0.0001000000 | Loss 0.011980 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:08 Epoch 3 | Batch 1097/2891 | Timestep 9770 | LR 0.0001000000 | Loss 0.015308 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:10 Epoch 3 | Batch 1107/2891 | Timestep 9780 | LR 0.0001000000 | Loss 0.010022 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:12 Epoch 3 | Batch 1117/2891 | Timestep 9790 | LR 0.0001000000 | Loss 0.020211 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:13 Epoch 3 | Batch 1127/2891 | Timestep 9800 | LR 0.0001000000 | Loss 0.005762 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:15 Epoch 3 | Batch 1137/2891 | Timestep 9810 | LR 0.0001000000 | Loss 0.036766 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:16 Epoch 3 | Batch 1147/2891 | Timestep 9820 | LR 0.0001000000 | Loss 0.012190 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:18 Epoch 3 | Batch 1157/2891 | Timestep 9830 | LR 0.0001000000 | Loss 0.022261 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:20 Epoch 3 | Batch 1167/2891 | Timestep 9840 | LR 0.0001000000 | Loss 0.006772 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:21 Epoch 3 | Batch 1177/2891 | Timestep 9850 | LR 0.0001000000 | Loss 0.023296 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:23 Epoch 3 | Batch 1187/2891 | Timestep 9860 | LR 0.0001000000 | Loss 0.008919 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:25 Epoch 3 | Batch 1197/2891 | Timestep 9870 | LR 0.0001000000 | Loss 0.002627 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:26 Epoch 3 | Batch 1207/2891 | Timestep 9880 | LR 0.0001000000 | Loss 0.050860 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:28 Epoch 3 | Batch 1217/2891 | Timestep 9890 | LR 0.0001000000 | Loss 0.006974 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:30 Epoch 3 | Batch 1227/2891 | Timestep 9900 | LR 0.0001000000 | Loss 0.013036 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:31 Epoch 3 | Batch 1237/2891 | Timestep 9910 | LR 0.0001000000 | Loss 0.004529 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:33 Epoch 3 | Batch 1247/2891 | Timestep 9920 | LR 0.0001000000 | Loss 0.010244 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:34 Epoch 3 | Batch 1257/2891 | Timestep 9930 | LR 0.0001000000 | Loss 0.017587 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:36 Epoch 3 | Batch 1267/2891 | Timestep 9940 | LR 0.0001000000 | Loss 0.023921 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:38 Epoch 3 | Batch 1277/2891 | Timestep 9950 | LR 0.0001000000 | Loss 0.101590 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:40 Epoch 3 | Batch 1287/2891 | Timestep 9960 | LR 0.0001000000 | Loss 0.006304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:41 Epoch 3 | Batch 1297/2891 | Timestep 9970 | LR 0.0001000000 | Loss 0.018007 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:43 Epoch 3 | Batch 1307/2891 | Timestep 9980 | LR 0.0001000000 | Loss 0.026482 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:44 Epoch 3 | Batch 1317/2891 | Timestep 9990 | LR 0.0001000000 | Loss 0.001745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:46 Epoch 3 | Batch 1327/2891 | Timestep 10000 | LR 0.0001000000 | Loss 0.056181 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:48 Epoch 3 | Batch 1337/2891 | Timestep 10010 | LR 0.0001000000 | Loss 0.007757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:50 Epoch 3 | Batch 1347/2891 | Timestep 10020 | LR 0.0001000000 | Loss 0.072172 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:51 Epoch 3 | Batch 1357/2891 | Timestep 10030 | LR 0.0001000000 | Loss 0.006135 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:53 Epoch 3 | Batch 1367/2891 | Timestep 10040 | LR 0.0001000000 | Loss 0.008316 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:54 Epoch 3 | Batch 1377/2891 | Timestep 10050 | LR 0.0001000000 | Loss 0.054439 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:56 Epoch 3 | Batch 1387/2891 | Timestep 10060 | LR 0.0001000000 | Loss 0.067765 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:58 Epoch 3 | Batch 1397/2891 | Timestep 10070 | LR 0.0001000000 | Loss 0.005740 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:18:59 Epoch 3 | Batch 1407/2891 | Timestep 10080 | LR 0.0001000000 | Loss 0.021619 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:01 Epoch 3 | Batch 1417/2891 | Timestep 10090 | LR 0.0001000000 | Loss 0.018663 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:02 Epoch 3 | Batch 1427/2891 | Timestep 10100 | LR 0.0001000000 | Loss 0.081636 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:05 Epoch 3 | Batch 1437/2891 | Timestep 10110 | LR 0.0001000000 | Loss 0.009268 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:06 Epoch 3 | Batch 1447/2891 | Timestep 10120 | LR 0.0001000000 | Loss 0.002731 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:08 Epoch 3 | Batch 1457/2891 | Timestep 10130 | LR 0.0001000000 | Loss 0.020771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:10 Epoch 3 | Batch 1467/2891 | Timestep 10140 | LR 0.0001000000 | Loss 0.002430 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:11 Epoch 3 | Batch 1477/2891 | Timestep 10150 | LR 0.0001000000 | Loss 0.000818 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:14 Epoch 3 | Batch 1487/2891 | Timestep 10160 | LR 0.0001000000 | Loss 0.027601 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:16 Epoch 3 | Batch 1497/2891 | Timestep 10170 | LR 0.0001000000 | Loss 0.020493 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:17 Epoch 3 | Batch 1507/2891 | Timestep 10180 | LR 0.0001000000 | Loss 0.021498 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:19 Epoch 3 | Batch 1517/2891 | Timestep 10190 | LR 0.0001000000 | Loss 0.018159 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:20 Epoch 3 | Batch 1527/2891 | Timestep 10200 | LR 0.0001000000 | Loss 0.025204 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:22 Epoch 3 | Batch 1537/2891 | Timestep 10210 | LR 0.0001000000 | Loss 0.013971 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:24 Epoch 3 | Batch 1547/2891 | Timestep 10220 | LR 0.0001000000 | Loss 0.037314 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:25 Epoch 3 | Batch 1557/2891 | Timestep 10230 | LR 0.0001000000 | Loss 0.030496 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:27 Epoch 3 | Batch 1567/2891 | Timestep 10240 | LR 0.0001000000 | Loss 0.039739 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:29 Epoch 3 | Batch 1577/2891 | Timestep 10250 | LR 0.0001000000 | Loss 0.007005 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:30 Epoch 3 | Batch 1587/2891 | Timestep 10260 | LR 0.0001000000 | Loss 0.090933 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:32 Epoch 3 | Batch 1597/2891 | Timestep 10270 | LR 0.0001000000 | Loss 0.036546 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:34 Epoch 3 | Batch 1607/2891 | Timestep 10280 | LR 0.0001000000 | Loss 0.101008 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:35 Epoch 3 | Batch 1617/2891 | Timestep 10290 | LR 0.0001000000 | Loss 0.015219 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:37 Epoch 3 | Batch 1627/2891 | Timestep 10300 | LR 0.0001000000 | Loss 0.081985 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:39 Epoch 3 | Batch 1637/2891 | Timestep 10310 | LR 0.0001000000 | Loss 0.015541 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:41 Epoch 3 | Batch 1647/2891 | Timestep 10320 | LR 0.0001000000 | Loss 0.005627 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:42 Epoch 3 | Batch 1657/2891 | Timestep 10330 | LR 0.0001000000 | Loss 0.010423 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:44 Epoch 3 | Batch 1667/2891 | Timestep 10340 | LR 0.0001000000 | Loss 0.018191 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:46 Epoch 3 | Batch 1677/2891 | Timestep 10350 | LR 0.0001000000 | Loss 0.045858 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:47 Epoch 3 | Batch 1687/2891 | Timestep 10360 | LR 0.0001000000 | Loss 0.008429 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:49 Epoch 3 | Batch 1697/2891 | Timestep 10370 | LR 0.0001000000 | Loss 0.023542 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:50 Epoch 3 | Batch 1707/2891 | Timestep 10380 | LR 0.0001000000 | Loss 0.029031 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:52 Epoch 3 | Batch 1717/2891 | Timestep 10390 | LR 0.0001000000 | Loss 0.010495 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:54 Epoch 3 | Batch 1727/2891 | Timestep 10400 | LR 0.0001000000 | Loss 0.025758 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:56 Epoch 3 | Batch 1737/2891 | Timestep 10410 | LR 0.0001000000 | Loss 0.006841 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:19:58 Epoch 3 | Batch 1747/2891 | Timestep 10420 | LR 0.0001000000 | Loss 0.152111 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:00 Epoch 3 | Batch 1757/2891 | Timestep 10430 | LR 0.0001000000 | Loss 0.004539 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:01 Epoch 3 | Batch 1767/2891 | Timestep 10440 | LR 0.0001000000 | Loss 0.050864 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:03 Epoch 3 | Batch 1777/2891 | Timestep 10450 | LR 0.0001000000 | Loss 0.021367 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:04 Epoch 3 | Batch 1787/2891 | Timestep 10460 | LR 0.0001000000 | Loss 0.038095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:06 Epoch 3 | Batch 1797/2891 | Timestep 10470 | LR 0.0001000000 | Loss 0.137823 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:08 Epoch 3 | Batch 1807/2891 | Timestep 10480 | LR 0.0001000000 | Loss 0.022245 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:09 Epoch 3 | Batch 1817/2891 | Timestep 10490 | LR 0.0001000000 | Loss 0.047074 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:12 Epoch 3 | Batch 1827/2891 | Timestep 10500 | LR 0.0001000000 | Loss 0.007554 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:14 Epoch 3 | Batch 1837/2891 | Timestep 10510 | LR 0.0001000000 | Loss 0.005210 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:15 Epoch 3 | Batch 1847/2891 | Timestep 10520 | LR 0.0001000000 | Loss 0.029426 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:17 Epoch 3 | Batch 1857/2891 | Timestep 10530 | LR 0.0001000000 | Loss 0.019950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:19 Epoch 3 | Batch 1867/2891 | Timestep 10540 | LR 0.0001000000 | Loss 0.004474 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:21 Epoch 3 | Batch 1877/2891 | Timestep 10550 | LR 0.0001000000 | Loss 0.036885 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:22 Epoch 3 | Batch 1887/2891 | Timestep 10560 | LR 0.0001000000 | Loss 0.033544 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:24 Epoch 3 | Batch 1897/2891 | Timestep 10570 | LR 0.0001000000 | Loss 0.001674 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:25 Epoch 3 | Batch 1907/2891 | Timestep 10580 | LR 0.0001000000 | Loss 0.031877 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:27 Epoch 3 | Batch 1917/2891 | Timestep 10590 | LR 0.0001000000 | Loss 0.018880 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:29 Epoch 3 | Batch 1927/2891 | Timestep 10600 | LR 0.0001000000 | Loss 0.005934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:31 Epoch 3 | Batch 1937/2891 | Timestep 10610 | LR 0.0001000000 | Loss 0.007669 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:33 Epoch 3 | Batch 1947/2891 | Timestep 10620 | LR 0.0001000000 | Loss 0.023900 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:34 Epoch 3 | Batch 1957/2891 | Timestep 10630 | LR 0.0001000000 | Loss 0.073449 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:36 Epoch 3 | Batch 1967/2891 | Timestep 10640 | LR 0.0001000000 | Loss 0.030037 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:38 Epoch 3 | Batch 1977/2891 | Timestep 10650 | LR 0.0001000000 | Loss 0.027834 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:39 Epoch 3 | Batch 1987/2891 | Timestep 10660 | LR 0.0001000000 | Loss 0.006028 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:41 Epoch 3 | Batch 1997/2891 | Timestep 10670 | LR 0.0001000000 | Loss 0.020212 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:43 Epoch 3 | Batch 2007/2891 | Timestep 10680 | LR 0.0001000000 | Loss 0.026155 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:44 Epoch 3 | Batch 2017/2891 | Timestep 10690 | LR 0.0001000000 | Loss 0.094144 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:46 Epoch 3 | Batch 2027/2891 | Timestep 10700 | LR 0.0001000000 | Loss 0.005124 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:48 Epoch 3 | Batch 2037/2891 | Timestep 10710 | LR 0.0001000000 | Loss 0.060748 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:49 Epoch 3 | Batch 2047/2891 | Timestep 10720 | LR 0.0001000000 | Loss 0.014414 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:51 Epoch 3 | Batch 2057/2891 | Timestep 10730 | LR 0.0001000000 | Loss 0.007958 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:53 Epoch 3 | Batch 2067/2891 | Timestep 10740 | LR 0.0001000000 | Loss 0.050271 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:54 Epoch 3 | Batch 2077/2891 | Timestep 10750 | LR 0.0001000000 | Loss 0.015397 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:57 Epoch 3 | Batch 2087/2891 | Timestep 10760 | LR 0.0001000000 | Loss 0.075014 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:20:58 Epoch 3 | Batch 2097/2891 | Timestep 10770 | LR 0.0001000000 | Loss 0.013456 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:00 Epoch 3 | Batch 2107/2891 | Timestep 10780 | LR 0.0001000000 | Loss 0.028997 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:01 Epoch 3 | Batch 2117/2891 | Timestep 10790 | LR 0.0001000000 | Loss 0.026241 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:03 Epoch 3 | Batch 2127/2891 | Timestep 10800 | LR 0.0001000000 | Loss 0.059650 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:05 Epoch 3 | Batch 2137/2891 | Timestep 10810 | LR 0.0001000000 | Loss 0.027444 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:07 Epoch 3 | Batch 2147/2891 | Timestep 10820 | LR 0.0001000000 | Loss 0.033917 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:08 Epoch 3 | Batch 2157/2891 | Timestep 10830 | LR 0.0001000000 | Loss 0.004322 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:10 Epoch 3 | Batch 2167/2891 | Timestep 10840 | LR 0.0001000000 | Loss 0.001673 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:12 Epoch 3 | Batch 2177/2891 | Timestep 10850 | LR 0.0001000000 | Loss 0.021939 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:14 Epoch 3 | Batch 2187/2891 | Timestep 10860 | LR 0.0001000000 | Loss 0.035647 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:16 Epoch 3 | Batch 2197/2891 | Timestep 10870 | LR 0.0001000000 | Loss 0.025456 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:18 Epoch 3 | Batch 2207/2891 | Timestep 10880 | LR 0.0001000000 | Loss 0.011005 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:19 Epoch 3 | Batch 2217/2891 | Timestep 10890 | LR 0.0001000000 | Loss 0.007260 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:21 Epoch 3 | Batch 2227/2891 | Timestep 10900 | LR 0.0001000000 | Loss 0.035723 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:22 Epoch 3 | Batch 2237/2891 | Timestep 10910 | LR 0.0001000000 | Loss 0.036971 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:24 Epoch 3 | Batch 2247/2891 | Timestep 10920 | LR 0.0001000000 | Loss 0.006944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:26 Epoch 3 | Batch 2257/2891 | Timestep 10930 | LR 0.0001000000 | Loss 0.013475 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:27 Epoch 3 | Batch 2267/2891 | Timestep 10940 | LR 0.0001000000 | Loss 0.005770 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:29 Epoch 3 | Batch 2277/2891 | Timestep 10950 | LR 0.0001000000 | Loss 0.049483 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:32 Epoch 3 | Batch 2287/2891 | Timestep 10960 | LR 0.0001000000 | Loss 0.006777 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:33 Epoch 3 | Batch 2297/2891 | Timestep 10970 | LR 0.0001000000 | Loss 0.088768 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:35 Epoch 3 | Batch 2307/2891 | Timestep 10980 | LR 0.0001000000 | Loss 0.070879 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:37 Epoch 3 | Batch 2317/2891 | Timestep 10990 | LR 0.0001000000 | Loss 0.001843 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:38 Epoch 3 | Batch 2327/2891 | Timestep 11000 | LR 0.0001000000 | Loss 0.135315 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:40 Epoch 3 | Batch 2337/2891 | Timestep 11010 | LR 0.0001000000 | Loss 0.002241 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:42 Epoch 3 | Batch 2347/2891 | Timestep 11020 | LR 0.0001000000 | Loss 0.021736 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:43 Epoch 3 | Batch 2357/2891 | Timestep 11030 | LR 0.0001000000 | Loss 0.003155 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:45 Epoch 3 | Batch 2367/2891 | Timestep 11040 | LR 0.0001000000 | Loss 0.014864 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:47 Epoch 3 | Batch 2377/2891 | Timestep 11050 | LR 0.0001000000 | Loss 0.001908 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:48 Epoch 3 | Batch 2387/2891 | Timestep 11060 | LR 0.0001000000 | Loss 0.034567 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:50 Epoch 3 | Batch 2397/2891 | Timestep 11070 | LR 0.0001000000 | Loss 0.065602 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:51 Epoch 3 | Batch 2407/2891 | Timestep 11080 | LR 0.0001000000 | Loss 0.016119 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:53 Epoch 3 | Batch 2417/2891 | Timestep 11090 | LR 0.0001000000 | Loss 0.052175 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:54 Epoch 3 | Batch 2427/2891 | Timestep 11100 | LR 0.0001000000 | Loss 0.011917 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:56 Epoch 3 | Batch 2437/2891 | Timestep 11110 | LR 0.0001000000 | Loss 0.001643 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:58 Epoch 3 | Batch 2447/2891 | Timestep 11120 | LR 0.0001000000 | Loss 0.018654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:21:59 Epoch 3 | Batch 2457/2891 | Timestep 11130 | LR 0.0001000000 | Loss 0.021673 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:01 Epoch 3 | Batch 2467/2891 | Timestep 11140 | LR 0.0001000000 | Loss 0.004740 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:02 Epoch 3 | Batch 2477/2891 | Timestep 11150 | LR 0.0001000000 | Loss 0.057104 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:04 Epoch 3 | Batch 2487/2891 | Timestep 11160 | LR 0.0001000000 | Loss 0.025366 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:06 Epoch 3 | Batch 2497/2891 | Timestep 11170 | LR 0.0001000000 | Loss 0.085671 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:07 Epoch 3 | Batch 2507/2891 | Timestep 11180 | LR 0.0001000000 | Loss 0.070307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:09 Epoch 3 | Batch 2517/2891 | Timestep 11190 | LR 0.0001000000 | Loss 0.025340 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:11 Epoch 3 | Batch 2527/2891 | Timestep 11200 | LR 0.0001000000 | Loss 0.010255 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:13 Epoch 3 | Batch 2537/2891 | Timestep 11210 | LR 0.0001000000 | Loss 0.019512 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:14 Epoch 3 | Batch 2547/2891 | Timestep 11220 | LR 0.0001000000 | Loss 0.014308 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:16 Epoch 3 | Batch 2557/2891 | Timestep 11230 | LR 0.0001000000 | Loss 0.098627 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:17 Epoch 3 | Batch 2567/2891 | Timestep 11240 | LR 0.0001000000 | Loss 0.326114 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:19 Epoch 3 | Batch 2577/2891 | Timestep 11250 | LR 0.0001000000 | Loss 0.237654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:21 Epoch 3 | Batch 2587/2891 | Timestep 11260 | LR 0.0001000000 | Loss 0.361883 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:22 Epoch 3 | Batch 2597/2891 | Timestep 11270 | LR 0.0001000000 | Loss 0.024844 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:24 Epoch 3 | Batch 2607/2891 | Timestep 11280 | LR 0.0001000000 | Loss 0.045864 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:26 Epoch 3 | Batch 2617/2891 | Timestep 11290 | LR 0.0001000000 | Loss 0.036753 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:27 Epoch 3 | Batch 2627/2891 | Timestep 11300 | LR 0.0001000000 | Loss 0.042734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:29 Epoch 3 | Batch 2637/2891 | Timestep 11310 | LR 0.0001000000 | Loss 0.025957 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:30 Epoch 3 | Batch 2647/2891 | Timestep 11320 | LR 0.0001000000 | Loss 0.032734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:32 Epoch 3 | Batch 2657/2891 | Timestep 11330 | LR 0.0001000000 | Loss 0.019460 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:34 Epoch 3 | Batch 2667/2891 | Timestep 11340 | LR 0.0001000000 | Loss 0.020130 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:36 Epoch 3 | Batch 2677/2891 | Timestep 11350 | LR 0.0001000000 | Loss 0.009689 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:37 Epoch 3 | Batch 2687/2891 | Timestep 11360 | LR 0.0001000000 | Loss 0.019136 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:40 Epoch 3 | Batch 2697/2891 | Timestep 11370 | LR 0.0001000000 | Loss 0.021569 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:41 Epoch 3 | Batch 2707/2891 | Timestep 11380 | LR 0.0001000000 | Loss 0.016498 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:43 Epoch 3 | Batch 2717/2891 | Timestep 11390 | LR 0.0001000000 | Loss 0.007526 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:45 Epoch 3 | Batch 2727/2891 | Timestep 11400 | LR 0.0001000000 | Loss 0.038358 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:46 Epoch 3 | Batch 2737/2891 | Timestep 11410 | LR 0.0001000000 | Loss 0.012257 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:48 Epoch 3 | Batch 2747/2891 | Timestep 11420 | LR 0.0001000000 | Loss 0.005055 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:50 Epoch 3 | Batch 2757/2891 | Timestep 11430 | LR 0.0001000000 | Loss 0.038154 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:52 Epoch 3 | Batch 2767/2891 | Timestep 11440 | LR 0.0001000000 | Loss 0.015783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:54 Epoch 3 | Batch 2777/2891 | Timestep 11450 | LR 0.0001000000 | Loss 0.050351 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:56 Epoch 3 | Batch 2787/2891 | Timestep 11460 | LR 0.0001000000 | Loss 0.012548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:57 Epoch 3 | Batch 2797/2891 | Timestep 11470 | LR 0.0001000000 | Loss 0.003622 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:22:59 Epoch 3 | Batch 2807/2891 | Timestep 11480 | LR 0.0001000000 | Loss 0.002830 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:01 Epoch 3 | Batch 2817/2891 | Timestep 11490 | LR 0.0001000000 | Loss 0.006706 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:03 Epoch 3 | Batch 2827/2891 | Timestep 11500 | LR 0.0001000000 | Loss 0.035493 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:04 Epoch 3 | Batch 2837/2891 | Timestep 11510 | LR 0.0001000000 | Loss 0.120568 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:06 Epoch 3 | Batch 2847/2891 | Timestep 11520 | LR 0.0001000000 | Loss 0.002280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:08 Epoch 3 | Batch 2857/2891 | Timestep 11530 | LR 0.0001000000 | Loss 0.012732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:09 Epoch 3 | Batch 2867/2891 | Timestep 11540 | LR 0.0001000000 | Loss 0.086596 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:11 Epoch 3 | Batch 2877/2891 | Timestep 11550 | LR 0.0001000000 | Loss 0.013768 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:12 Epoch 3 | Batch 2887/2891 | Timestep 11560 | LR 0.0001000000 | Loss 0.031956 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:13 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:23:47 precision recall f1-score support CARDINAL 0.7316 0.8176 0.7722 170 CURR 0.8696 0.8333 0.8511 24 DATE 0.9125 0.9249 0.9186 1691 EVENT 0.6142 0.7089 0.6582 292 FAC 0.7300 0.6186 0.6697 118 GPE 0.9401 0.9615 0.9507 2156 LANGUAGE 0.7857 0.6875 0.7333 16 LAW 0.7170 0.8085 0.7600 47 LOC 0.7791 0.7444 0.7614 90 MONEY 0.7200 0.8182 0.7660 22 NORP 0.5915 0.6570 0.6225 551 OCC 0.6692 0.8563 0.7513 522 ORDINAL 0.9439 0.8971 0.9199 544 ORG 0.8741 0.9187 0.8959 1882 PERCENT 0.7692 0.8333 0.8000 12 PERS 0.9364 0.8675 0.9006 679 PRODUCT 0.2500 0.1250 0.1667 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.6667 0.7879 0.7222 33 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.5200 0.4875 0.5032 80 micro avg 0.8512 0.8839 0.8673 8944 macro avg 0.7470 0.7510 0.7451 8944 weighted avg 0.8568 0.8839 0.8690 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:58 Epoch 3 | Timestep 11564 | Train Loss 0.032247 | Val Loss 0.062628 | F1 0.867266 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:23:59 Epoch 4 | Batch 6/2891 | Timestep 11570 | LR 0.0001000000 | Loss 0.001823 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:01 Epoch 4 | Batch 16/2891 | Timestep 11580 | LR 0.0001000000 | Loss 0.003091 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:02 Epoch 4 | Batch 26/2891 | Timestep 11590 | LR 0.0001000000 | Loss 0.031933 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:05 Epoch 4 | Batch 36/2891 | Timestep 11600 | LR 0.0001000000 | Loss 0.006715 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:07 Epoch 4 | Batch 46/2891 | Timestep 11610 | LR 0.0001000000 | Loss 0.007400 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:09 Epoch 4 | Batch 56/2891 | Timestep 11620 | LR 0.0001000000 | Loss 0.002238 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:11 Epoch 4 | Batch 66/2891 | Timestep 11630 | LR 0.0001000000 | Loss 0.004481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:12 Epoch 4 | Batch 76/2891 | Timestep 11640 | LR 0.0001000000 | Loss 0.035890 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:14 Epoch 4 | Batch 86/2891 | Timestep 11650 | LR 0.0001000000 | Loss 0.017621 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:15 Epoch 4 | Batch 96/2891 | Timestep 11660 | LR 0.0001000000 | Loss 0.028517 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:17 Epoch 4 | Batch 106/2891 | Timestep 11670 | LR 0.0001000000 | Loss 0.010175 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:19 Epoch 4 | Batch 116/2891 | Timestep 11680 | LR 0.0001000000 | Loss 0.023619 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:20 Epoch 4 | Batch 126/2891 | Timestep 11690 | LR 0.0001000000 | Loss 0.051156 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:22 Epoch 4 | Batch 136/2891 | Timestep 11700 | LR 0.0001000000 | Loss 0.023358 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:24 Epoch 4 | Batch 146/2891 | Timestep 11710 | LR 0.0001000000 | Loss 0.019734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:26 Epoch 4 | Batch 156/2891 | Timestep 11720 | LR 0.0001000000 | Loss 0.009452 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:27 Epoch 4 | Batch 166/2891 | Timestep 11730 | LR 0.0001000000 | Loss 0.028368 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:29 Epoch 4 | Batch 176/2891 | Timestep 11740 | LR 0.0001000000 | Loss 0.020014 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:30 Epoch 4 | Batch 186/2891 | Timestep 11750 | LR 0.0001000000 | Loss 0.013783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:32 Epoch 4 | Batch 196/2891 | Timestep 11760 | LR 0.0001000000 | Loss 0.032481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:34 Epoch 4 | Batch 206/2891 | Timestep 11770 | LR 0.0001000000 | Loss 0.085472 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:36 Epoch 4 | Batch 216/2891 | Timestep 11780 | LR 0.0001000000 | Loss 0.012689 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:37 Epoch 4 | Batch 226/2891 | Timestep 11790 | LR 0.0001000000 | Loss 0.005918 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:39 Epoch 4 | Batch 236/2891 | Timestep 11800 | LR 0.0001000000 | Loss 0.006867 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:41 Epoch 4 | Batch 246/2891 | Timestep 11810 | LR 0.0001000000 | Loss 0.024498 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:43 Epoch 4 | Batch 256/2891 | Timestep 11820 | LR 0.0001000000 | Loss 0.023641 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:44 Epoch 4 | Batch 266/2891 | Timestep 11830 | LR 0.0001000000 | Loss 0.020936 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:46 Epoch 4 | Batch 276/2891 | Timestep 11840 | LR 0.0001000000 | Loss 0.026406 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:48 Epoch 4 | Batch 286/2891 | Timestep 11850 | LR 0.0001000000 | Loss 0.002938 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:50 Epoch 4 | Batch 296/2891 | Timestep 11860 | LR 0.0001000000 | Loss 0.025278 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:51 Epoch 4 | Batch 306/2891 | Timestep 11870 | LR 0.0001000000 | Loss 0.018934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:53 Epoch 4 | Batch 316/2891 | Timestep 11880 | LR 0.0001000000 | Loss 0.003751 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:55 Epoch 4 | Batch 326/2891 | Timestep 11890 | LR 0.0001000000 | Loss 0.002704 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:56 Epoch 4 | Batch 336/2891 | Timestep 11900 | LR 0.0001000000 | Loss 0.004094 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:24:58 Epoch 4 | Batch 346/2891 | Timestep 11910 | LR 0.0001000000 | Loss 0.013428 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:00 Epoch 4 | Batch 356/2891 | Timestep 11920 | LR 0.0001000000 | Loss 0.007595 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:01 Epoch 4 | Batch 366/2891 | Timestep 11930 | LR 0.0001000000 | Loss 0.021784 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:02 Epoch 4 | Batch 376/2891 | Timestep 11940 | LR 0.0001000000 | Loss 0.018447 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:04 Epoch 4 | Batch 386/2891 | Timestep 11950 | LR 0.0001000000 | Loss 0.008981 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:06 Epoch 4 | Batch 396/2891 | Timestep 11960 | LR 0.0001000000 | Loss 0.008498 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:07 Epoch 4 | Batch 406/2891 | Timestep 11970 | LR 0.0001000000 | Loss 0.049554 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:09 Epoch 4 | Batch 416/2891 | Timestep 11980 | LR 0.0001000000 | Loss 0.002285 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:11 Epoch 4 | Batch 426/2891 | Timestep 11990 | LR 0.0001000000 | Loss 0.029828 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:12 Epoch 4 | Batch 436/2891 | Timestep 12000 | LR 0.0001000000 | Loss 0.015714 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:14 Epoch 4 | Batch 446/2891 | Timestep 12010 | LR 0.0001000000 | Loss 0.016610 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:15 Epoch 4 | Batch 456/2891 | Timestep 12020 | LR 0.0001000000 | Loss 0.016537 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:17 Epoch 4 | Batch 466/2891 | Timestep 12030 | LR 0.0001000000 | Loss 0.018073 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:19 Epoch 4 | Batch 476/2891 | Timestep 12040 | LR 0.0001000000 | Loss 0.000511 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:20 Epoch 4 | Batch 486/2891 | Timestep 12050 | LR 0.0001000000 | Loss 0.019798 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:22 Epoch 4 | Batch 496/2891 | Timestep 12060 | LR 0.0001000000 | Loss 0.042690 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:24 Epoch 4 | Batch 506/2891 | Timestep 12070 | LR 0.0001000000 | Loss 0.063223 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:26 Epoch 4 | Batch 516/2891 | Timestep 12080 | LR 0.0001000000 | Loss 0.005768 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:27 Epoch 4 | Batch 526/2891 | Timestep 12090 | LR 0.0001000000 | Loss 0.001534 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:29 Epoch 4 | Batch 536/2891 | Timestep 12100 | LR 0.0001000000 | Loss 0.030947 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:30 Epoch 4 | Batch 546/2891 | Timestep 12110 | LR 0.0001000000 | Loss 0.006483 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:32 Epoch 4 | Batch 556/2891 | Timestep 12120 | LR 0.0001000000 | Loss 0.021087 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:34 Epoch 4 | Batch 566/2891 | Timestep 12130 | LR 0.0001000000 | Loss 0.002480 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:36 Epoch 4 | Batch 576/2891 | Timestep 12140 | LR 0.0001000000 | Loss 0.028952 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:38 Epoch 4 | Batch 586/2891 | Timestep 12150 | LR 0.0001000000 | Loss 0.009628 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:39 Epoch 4 | Batch 596/2891 | Timestep 12160 | LR 0.0001000000 | Loss 0.007377 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:41 Epoch 4 | Batch 606/2891 | Timestep 12170 | LR 0.0001000000 | Loss 0.014257 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:43 Epoch 4 | Batch 616/2891 | Timestep 12180 | LR 0.0001000000 | Loss 0.031000 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:45 Epoch 4 | Batch 626/2891 | Timestep 12190 | LR 0.0001000000 | Loss 0.013597 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:46 Epoch 4 | Batch 636/2891 | Timestep 12200 | LR 0.0001000000 | Loss 0.001818 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:48 Epoch 4 | Batch 646/2891 | Timestep 12210 | LR 0.0001000000 | Loss 0.008209 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:50 Epoch 4 | Batch 656/2891 | Timestep 12220 | LR 0.0001000000 | Loss 0.002561 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:52 Epoch 4 | Batch 666/2891 | Timestep 12230 | LR 0.0001000000 | Loss 0.015334 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:54 Epoch 4 | Batch 676/2891 | Timestep 12240 | LR 0.0001000000 | Loss 0.036384 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:55 Epoch 4 | Batch 686/2891 | Timestep 12250 | LR 0.0001000000 | Loss 0.006783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:57 Epoch 4 | Batch 696/2891 | Timestep 12260 | LR 0.0001000000 | Loss 0.007604 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:25:59 Epoch 4 | Batch 706/2891 | Timestep 12270 | LR 0.0001000000 | Loss 0.021808 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:01 Epoch 4 | Batch 716/2891 | Timestep 12280 | LR 0.0001000000 | Loss 0.013155 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:02 Epoch 4 | Batch 726/2891 | Timestep 12290 | LR 0.0001000000 | Loss 0.020460 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:04 Epoch 4 | Batch 736/2891 | Timestep 12300 | LR 0.0001000000 | Loss 0.019750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:05 Epoch 4 | Batch 746/2891 | Timestep 12310 | LR 0.0001000000 | Loss 0.014617 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:07 Epoch 4 | Batch 756/2891 | Timestep 12320 | LR 0.0001000000 | Loss 0.024778 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:09 Epoch 4 | Batch 766/2891 | Timestep 12330 | LR 0.0001000000 | Loss 0.016440 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:11 Epoch 4 | Batch 776/2891 | Timestep 12340 | LR 0.0001000000 | Loss 0.004790 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:13 Epoch 4 | Batch 786/2891 | Timestep 12350 | LR 0.0001000000 | Loss 0.009073 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:14 Epoch 4 | Batch 796/2891 | Timestep 12360 | LR 0.0001000000 | Loss 0.057916 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:16 Epoch 4 | Batch 806/2891 | Timestep 12370 | LR 0.0001000000 | Loss 0.006185 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:17 Epoch 4 | Batch 816/2891 | Timestep 12380 | LR 0.0001000000 | Loss 0.002731 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:20 Epoch 4 | Batch 826/2891 | Timestep 12390 | LR 0.0001000000 | Loss 0.060683 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:22 Epoch 4 | Batch 836/2891 | Timestep 12400 | LR 0.0001000000 | Loss 0.031706 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:23 Epoch 4 | Batch 846/2891 | Timestep 12410 | LR 0.0001000000 | Loss 0.009605 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:25 Epoch 4 | Batch 856/2891 | Timestep 12420 | LR 0.0001000000 | Loss 0.006961 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:27 Epoch 4 | Batch 866/2891 | Timestep 12430 | LR 0.0001000000 | Loss 0.001226 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:29 Epoch 4 | Batch 876/2891 | Timestep 12440 | LR 0.0001000000 | Loss 0.010738 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:30 Epoch 4 | Batch 886/2891 | Timestep 12450 | LR 0.0001000000 | Loss 0.027095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:32 Epoch 4 | Batch 896/2891 | Timestep 12460 | LR 0.0001000000 | Loss 0.020300 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:34 Epoch 4 | Batch 906/2891 | Timestep 12470 | LR 0.0001000000 | Loss 0.022107 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:35 Epoch 4 | Batch 916/2891 | Timestep 12480 | LR 0.0001000000 | Loss 0.004277 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:37 Epoch 4 | Batch 926/2891 | Timestep 12490 | LR 0.0001000000 | Loss 0.006449 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:38 Epoch 4 | Batch 936/2891 | Timestep 12500 | LR 0.0001000000 | Loss 0.021165 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:40 Epoch 4 | Batch 946/2891 | Timestep 12510 | LR 0.0001000000 | Loss 0.037797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:42 Epoch 4 | Batch 956/2891 | Timestep 12520 | LR 0.0001000000 | Loss 0.008977 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:44 Epoch 4 | Batch 966/2891 | Timestep 12530 | LR 0.0001000000 | Loss 0.002936 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:45 Epoch 4 | Batch 976/2891 | Timestep 12540 | LR 0.0001000000 | Loss 0.014732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:47 Epoch 4 | Batch 986/2891 | Timestep 12550 | LR 0.0001000000 | Loss 0.043457 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:49 Epoch 4 | Batch 996/2891 | Timestep 12560 | LR 0.0001000000 | Loss 0.024112 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:51 Epoch 4 | Batch 1006/2891 | Timestep 12570 | LR 0.0001000000 | Loss 0.047001 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:53 Epoch 4 | Batch 1016/2891 | Timestep 12580 | LR 0.0001000000 | Loss 0.004779 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:54 Epoch 4 | Batch 1026/2891 | Timestep 12590 | LR 0.0001000000 | Loss 0.003798 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:56 Epoch 4 | Batch 1036/2891 | Timestep 12600 | LR 0.0001000000 | Loss 0.005198 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:57 Epoch 4 | Batch 1046/2891 | Timestep 12610 | LR 0.0001000000 | Loss 0.075126 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:26:59 Epoch 4 | Batch 1056/2891 | Timestep 12620 | LR 0.0001000000 | Loss 0.022419 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:01 Epoch 4 | Batch 1066/2891 | Timestep 12630 | LR 0.0001000000 | Loss 0.049960 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:03 Epoch 4 | Batch 1076/2891 | Timestep 12640 | LR 0.0001000000 | Loss 0.007728 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:04 Epoch 4 | Batch 1086/2891 | Timestep 12650 | LR 0.0001000000 | Loss 0.040312 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:06 Epoch 4 | Batch 1096/2891 | Timestep 12660 | LR 0.0001000000 | Loss 0.011584 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:07 Epoch 4 | Batch 1106/2891 | Timestep 12670 | LR 0.0001000000 | Loss 0.011683 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:09 Epoch 4 | Batch 1116/2891 | Timestep 12680 | LR 0.0001000000 | Loss 0.026260 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:11 Epoch 4 | Batch 1126/2891 | Timestep 12690 | LR 0.0001000000 | Loss 0.035486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:12 Epoch 4 | Batch 1136/2891 | Timestep 12700 | LR 0.0001000000 | Loss 0.016660 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:14 Epoch 4 | Batch 1146/2891 | Timestep 12710 | LR 0.0001000000 | Loss 0.009146 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:16 Epoch 4 | Batch 1156/2891 | Timestep 12720 | LR 0.0001000000 | Loss 0.024116 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:17 Epoch 4 | Batch 1166/2891 | Timestep 12730 | LR 0.0001000000 | Loss 0.022745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:18 Epoch 4 | Batch 1176/2891 | Timestep 12740 | LR 0.0001000000 | Loss 0.009532 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:20 Epoch 4 | Batch 1186/2891 | Timestep 12750 | LR 0.0001000000 | Loss 0.009259 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:21 Epoch 4 | Batch 1196/2891 | Timestep 12760 | LR 0.0001000000 | Loss 0.023926 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:23 Epoch 4 | Batch 1206/2891 | Timestep 12770 | LR 0.0001000000 | Loss 0.040008 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:25 Epoch 4 | Batch 1216/2891 | Timestep 12780 | LR 0.0001000000 | Loss 0.052116 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:26 Epoch 4 | Batch 1226/2891 | Timestep 12790 | LR 0.0001000000 | Loss 0.010176 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:28 Epoch 4 | Batch 1236/2891 | Timestep 12800 | LR 0.0001000000 | Loss 0.015191 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:30 Epoch 4 | Batch 1246/2891 | Timestep 12810 | LR 0.0001000000 | Loss 0.007669 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:32 Epoch 4 | Batch 1256/2891 | Timestep 12820 | LR 0.0001000000 | Loss 0.051439 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:34 Epoch 4 | Batch 1266/2891 | Timestep 12830 | LR 0.0001000000 | Loss 0.009774 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:35 Epoch 4 | Batch 1276/2891 | Timestep 12840 | LR 0.0001000000 | Loss 0.047130 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:38 Epoch 4 | Batch 1286/2891 | Timestep 12850 | LR 0.0001000000 | Loss 0.041913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:39 Epoch 4 | Batch 1296/2891 | Timestep 12860 | LR 0.0001000000 | Loss 0.031443 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:41 Epoch 4 | Batch 1306/2891 | Timestep 12870 | LR 0.0001000000 | Loss 0.004620 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:43 Epoch 4 | Batch 1316/2891 | Timestep 12880 | LR 0.0001000000 | Loss 0.041050 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:44 Epoch 4 | Batch 1326/2891 | Timestep 12890 | LR 0.0001000000 | Loss 0.011035 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:46 Epoch 4 | Batch 1336/2891 | Timestep 12900 | LR 0.0001000000 | Loss 0.067837 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:48 Epoch 4 | Batch 1346/2891 | Timestep 12910 | LR 0.0001000000 | Loss 0.054369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:49 Epoch 4 | Batch 1356/2891 | Timestep 12920 | LR 0.0001000000 | Loss 0.021496 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:51 Epoch 4 | Batch 1366/2891 | Timestep 12930 | LR 0.0001000000 | Loss 0.053330 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:52 Epoch 4 | Batch 1376/2891 | Timestep 12940 | LR 0.0001000000 | Loss 0.011154 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:54 Epoch 4 | Batch 1386/2891 | Timestep 12950 | LR 0.0001000000 | Loss 0.033016 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:55 Epoch 4 | Batch 1396/2891 | Timestep 12960 | LR 0.0001000000 | Loss 0.100071 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:57 Epoch 4 | Batch 1406/2891 | Timestep 12970 | LR 0.0001000000 | Loss 0.054828 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:27:59 Epoch 4 | Batch 1416/2891 | Timestep 12980 | LR 0.0001000000 | Loss 0.017783 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:01 Epoch 4 | Batch 1426/2891 | Timestep 12990 | LR 0.0001000000 | Loss 0.044832 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:03 Epoch 4 | Batch 1436/2891 | Timestep 13000 | LR 0.0001000000 | Loss 0.004817 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:05 Epoch 4 | Batch 1446/2891 | Timestep 13010 | LR 0.0001000000 | Loss 0.003841 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:06 Epoch 4 | Batch 1456/2891 | Timestep 13020 | LR 0.0001000000 | Loss 0.142737 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:08 Epoch 4 | Batch 1466/2891 | Timestep 13030 | LR 0.0001000000 | Loss 0.021416 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:10 Epoch 4 | Batch 1476/2891 | Timestep 13040 | LR 0.0001000000 | Loss 0.026408 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:12 Epoch 4 | Batch 1486/2891 | Timestep 13050 | LR 0.0001000000 | Loss 0.024033 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:14 Epoch 4 | Batch 1496/2891 | Timestep 13060 | LR 0.0001000000 | Loss 0.003021 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:15 Epoch 4 | Batch 1506/2891 | Timestep 13070 | LR 0.0001000000 | Loss 0.004863 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:17 Epoch 4 | Batch 1516/2891 | Timestep 13080 | LR 0.0001000000 | Loss 0.021727 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:19 Epoch 4 | Batch 1526/2891 | Timestep 13090 | LR 0.0001000000 | Loss 0.004532 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:21 Epoch 4 | Batch 1536/2891 | Timestep 13100 | LR 0.0001000000 | Loss 0.082212 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:22 Epoch 4 | Batch 1546/2891 | Timestep 13110 | LR 0.0001000000 | Loss 0.027863 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:25 Epoch 4 | Batch 1556/2891 | Timestep 13120 | LR 0.0001000000 | Loss 0.022607 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:26 Epoch 4 | Batch 1566/2891 | Timestep 13130 | LR 0.0001000000 | Loss 0.046122 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:27 Epoch 4 | Batch 1576/2891 | Timestep 13140 | LR 0.0001000000 | Loss 0.078909 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:29 Epoch 4 | Batch 1586/2891 | Timestep 13150 | LR 0.0001000000 | Loss 0.001854 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:31 Epoch 4 | Batch 1596/2891 | Timestep 13160 | LR 0.0001000000 | Loss 0.027438 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:33 Epoch 4 | Batch 1606/2891 | Timestep 13170 | LR 0.0001000000 | Loss 0.011515 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:35 Epoch 4 | Batch 1616/2891 | Timestep 13180 | LR 0.0001000000 | Loss 0.036011 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:37 Epoch 4 | Batch 1626/2891 | Timestep 13190 | LR 0.0001000000 | Loss 0.042075 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:39 Epoch 4 | Batch 1636/2891 | Timestep 13200 | LR 0.0001000000 | Loss 0.008409 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:40 Epoch 4 | Batch 1646/2891 | Timestep 13210 | LR 0.0001000000 | Loss 0.034956 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:42 Epoch 4 | Batch 1656/2891 | Timestep 13220 | LR 0.0001000000 | Loss 0.006551 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:44 Epoch 4 | Batch 1666/2891 | Timestep 13230 | LR 0.0001000000 | Loss 0.044848 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:45 Epoch 4 | Batch 1676/2891 | Timestep 13240 | LR 0.0001000000 | Loss 0.088401 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:47 Epoch 4 | Batch 1686/2891 | Timestep 13250 | LR 0.0001000000 | Loss 0.022435 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:48 Epoch 4 | Batch 1696/2891 | Timestep 13260 | LR 0.0001000000 | Loss 0.006550 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:50 Epoch 4 | Batch 1706/2891 | Timestep 13270 | LR 0.0001000000 | Loss 0.004810 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:52 Epoch 4 | Batch 1716/2891 | Timestep 13280 | LR 0.0001000000 | Loss 0.038500 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:54 Epoch 4 | Batch 1726/2891 | Timestep 13290 | LR 0.0001000000 | Loss 0.143333 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:55 Epoch 4 | Batch 1736/2891 | Timestep 13300 | LR 0.0001000000 | Loss 0.025169 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:57 Epoch 4 | Batch 1746/2891 | Timestep 13310 | LR 0.0001000000 | Loss 0.017855 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:28:58 Epoch 4 | Batch 1756/2891 | Timestep 13320 | LR 0.0001000000 | Loss 0.012600 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:00 Epoch 4 | Batch 1766/2891 | Timestep 13330 | LR 0.0001000000 | Loss 0.001782 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:02 Epoch 4 | Batch 1776/2891 | Timestep 13340 | LR 0.0001000000 | Loss 0.022642 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:04 Epoch 4 | Batch 1786/2891 | Timestep 13350 | LR 0.0001000000 | Loss 0.004182 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:05 Epoch 4 | Batch 1796/2891 | Timestep 13360 | LR 0.0001000000 | Loss 0.022937 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:07 Epoch 4 | Batch 1806/2891 | Timestep 13370 | LR 0.0001000000 | Loss 0.073913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:08 Epoch 4 | Batch 1816/2891 | Timestep 13380 | LR 0.0001000000 | Loss 0.027715 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:10 Epoch 4 | Batch 1826/2891 | Timestep 13390 | LR 0.0001000000 | Loss 0.043263 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:12 Epoch 4 | Batch 1836/2891 | Timestep 13400 | LR 0.0001000000 | Loss 0.004049 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:13 Epoch 4 | Batch 1846/2891 | Timestep 13410 | LR 0.0001000000 | Loss 0.009149 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:15 Epoch 4 | Batch 1856/2891 | Timestep 13420 | LR 0.0001000000 | Loss 0.004538 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:17 Epoch 4 | Batch 1866/2891 | Timestep 13430 | LR 0.0001000000 | Loss 0.078904 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:18 Epoch 4 | Batch 1876/2891 | Timestep 13440 | LR 0.0001000000 | Loss 0.017353 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:20 Epoch 4 | Batch 1886/2891 | Timestep 13450 | LR 0.0001000000 | Loss 0.035212 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:21 Epoch 4 | Batch 1896/2891 | Timestep 13460 | LR 0.0001000000 | Loss 0.037140 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:23 Epoch 4 | Batch 1906/2891 | Timestep 13470 | LR 0.0001000000 | Loss 0.003580 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:25 Epoch 4 | Batch 1916/2891 | Timestep 13480 | LR 0.0001000000 | Loss 0.020250 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:27 Epoch 4 | Batch 1926/2891 | Timestep 13490 | LR 0.0001000000 | Loss 0.072899 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:28 Epoch 4 | Batch 1936/2891 | Timestep 13500 | LR 0.0001000000 | Loss 0.009690 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:29 Epoch 4 | Batch 1946/2891 | Timestep 13510 | LR 0.0001000000 | Loss 0.006292 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:31 Epoch 4 | Batch 1956/2891 | Timestep 13520 | LR 0.0001000000 | Loss 0.049474 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:33 Epoch 4 | Batch 1966/2891 | Timestep 13530 | LR 0.0001000000 | Loss 0.011153 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:34 Epoch 4 | Batch 1976/2891 | Timestep 13540 | LR 0.0001000000 | Loss 0.054806 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:36 Epoch 4 | Batch 1986/2891 | Timestep 13550 | LR 0.0001000000 | Loss 0.014909 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:38 Epoch 4 | Batch 1996/2891 | Timestep 13560 | LR 0.0001000000 | Loss 0.018364 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:39 Epoch 4 | Batch 2006/2891 | Timestep 13570 | LR 0.0001000000 | Loss 0.035437 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:41 Epoch 4 | Batch 2016/2891 | Timestep 13580 | LR 0.0001000000 | Loss 0.006712 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:42 Epoch 4 | Batch 2026/2891 | Timestep 13590 | LR 0.0001000000 | Loss 0.006083 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:44 Epoch 4 | Batch 2036/2891 | Timestep 13600 | LR 0.0001000000 | Loss 0.082543 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:46 Epoch 4 | Batch 2046/2891 | Timestep 13610 | LR 0.0001000000 | Loss 0.047077 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:48 Epoch 4 | Batch 2056/2891 | Timestep 13620 | LR 0.0001000000 | Loss 0.034026 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:49 Epoch 4 | Batch 2066/2891 | Timestep 13630 | LR 0.0001000000 | Loss 0.027424 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:51 Epoch 4 | Batch 2076/2891 | Timestep 13640 | LR 0.0001000000 | Loss 0.110663 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:52 Epoch 4 | Batch 2086/2891 | Timestep 13650 | LR 0.0001000000 | Loss 0.033071 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:54 Epoch 4 | Batch 2096/2891 | Timestep 13660 | LR 0.0001000000 | Loss 0.064538 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:56 Epoch 4 | Batch 2106/2891 | Timestep 13670 | LR 0.0001000000 | Loss 0.065372 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:29:58 Epoch 4 | Batch 2116/2891 | Timestep 13680 | LR 0.0001000000 | Loss 0.032042 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:00 Epoch 4 | Batch 2126/2891 | Timestep 13690 | LR 0.0001000000 | Loss 0.046566 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:01 Epoch 4 | Batch 2136/2891 | Timestep 13700 | LR 0.0001000000 | Loss 0.047336 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:03 Epoch 4 | Batch 2146/2891 | Timestep 13710 | LR 0.0001000000 | Loss 0.088574 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:05 Epoch 4 | Batch 2156/2891 | Timestep 13720 | LR 0.0001000000 | Loss 0.009771 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:07 Epoch 4 | Batch 2166/2891 | Timestep 13730 | LR 0.0001000000 | Loss 0.095623 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:09 Epoch 4 | Batch 2176/2891 | Timestep 13740 | LR 0.0001000000 | Loss 0.029190 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:10 Epoch 4 | Batch 2186/2891 | Timestep 13750 | LR 0.0001000000 | Loss 0.006849 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:12 Epoch 4 | Batch 2196/2891 | Timestep 13760 | LR 0.0001000000 | Loss 0.014218 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:14 Epoch 4 | Batch 2206/2891 | Timestep 13770 | LR 0.0001000000 | Loss 0.031162 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:16 Epoch 4 | Batch 2216/2891 | Timestep 13780 | LR 0.0001000000 | Loss 0.058629 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:17 Epoch 4 | Batch 2226/2891 | Timestep 13790 | LR 0.0001000000 | Loss 0.001912 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:19 Epoch 4 | Batch 2236/2891 | Timestep 13800 | LR 0.0001000000 | Loss 0.026715 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:20 Epoch 4 | Batch 2246/2891 | Timestep 13810 | LR 0.0001000000 | Loss 0.005161 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:22 Epoch 4 | Batch 2256/2891 | Timestep 13820 | LR 0.0001000000 | Loss 0.004184 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:24 Epoch 4 | Batch 2266/2891 | Timestep 13830 | LR 0.0001000000 | Loss 0.013329 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:25 Epoch 4 | Batch 2276/2891 | Timestep 13840 | LR 0.0001000000 | Loss 0.017486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:27 Epoch 4 | Batch 2286/2891 | Timestep 13850 | LR 0.0001000000 | Loss 0.016637 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:29 Epoch 4 | Batch 2296/2891 | Timestep 13860 | LR 0.0001000000 | Loss 0.051481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:31 Epoch 4 | Batch 2306/2891 | Timestep 13870 | LR 0.0001000000 | Loss 0.104515 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:33 Epoch 4 | Batch 2316/2891 | Timestep 13880 | LR 0.0001000000 | Loss 0.011875 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:34 Epoch 4 | Batch 2326/2891 | Timestep 13890 | LR 0.0001000000 | Loss 0.001857 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:36 Epoch 4 | Batch 2336/2891 | Timestep 13900 | LR 0.0001000000 | Loss 0.009705 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:38 Epoch 4 | Batch 2346/2891 | Timestep 13910 | LR 0.0001000000 | Loss 0.018357 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:39 Epoch 4 | Batch 2356/2891 | Timestep 13920 | LR 0.0001000000 | Loss 0.020793 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:41 Epoch 4 | Batch 2366/2891 | Timestep 13930 | LR 0.0001000000 | Loss 0.006369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:43 Epoch 4 | Batch 2376/2891 | Timestep 13940 | LR 0.0001000000 | Loss 0.008558 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:45 Epoch 4 | Batch 2386/2891 | Timestep 13950 | LR 0.0001000000 | Loss 0.029938 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:47 Epoch 4 | Batch 2396/2891 | Timestep 13960 | LR 0.0001000000 | Loss 0.017090 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:48 Epoch 4 | Batch 2406/2891 | Timestep 13970 | LR 0.0001000000 | Loss 0.038844 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:50 Epoch 4 | Batch 2416/2891 | Timestep 13980 | LR 0.0001000000 | Loss 0.005355 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:52 Epoch 4 | Batch 2426/2891 | Timestep 13990 | LR 0.0001000000 | Loss 0.013114 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:53 Epoch 4 | Batch 2436/2891 | Timestep 14000 | LR 0.0001000000 | Loss 0.010913 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:55 Epoch 4 | Batch 2446/2891 | Timestep 14010 | LR 0.0001000000 | Loss 0.011560 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:57 Epoch 4 | Batch 2456/2891 | Timestep 14020 | LR 0.0001000000 | Loss 0.009798 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:30:59 Epoch 4 | Batch 2466/2891 | Timestep 14030 | LR 0.0001000000 | Loss 0.000791 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:01 Epoch 4 | Batch 2476/2891 | Timestep 14040 | LR 0.0001000000 | Loss 0.002554 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:02 Epoch 4 | Batch 2486/2891 | Timestep 14050 | LR 0.0001000000 | Loss 0.030340 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:04 Epoch 4 | Batch 2496/2891 | Timestep 14060 | LR 0.0001000000 | Loss 0.012766 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:06 Epoch 4 | Batch 2506/2891 | Timestep 14070 | LR 0.0001000000 | Loss 0.019969 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:07 Epoch 4 | Batch 2516/2891 | Timestep 14080 | LR 0.0001000000 | Loss 0.003277 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:10 Epoch 4 | Batch 2526/2891 | Timestep 14090 | LR 0.0001000000 | Loss 0.026403 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:11 Epoch 4 | Batch 2536/2891 | Timestep 14100 | LR 0.0001000000 | Loss 0.035333 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:13 Epoch 4 | Batch 2546/2891 | Timestep 14110 | LR 0.0001000000 | Loss 0.007053 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:15 Epoch 4 | Batch 2556/2891 | Timestep 14120 | LR 0.0001000000 | Loss 0.003489 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:16 Epoch 4 | Batch 2566/2891 | Timestep 14130 | LR 0.0001000000 | Loss 0.027397 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:18 Epoch 4 | Batch 2576/2891 | Timestep 14140 | LR 0.0001000000 | Loss 0.021750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:20 Epoch 4 | Batch 2586/2891 | Timestep 14150 | LR 0.0001000000 | Loss 0.014350 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:21 Epoch 4 | Batch 2596/2891 | Timestep 14160 | LR 0.0001000000 | Loss 0.002495 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:23 Epoch 4 | Batch 2606/2891 | Timestep 14170 | LR 0.0001000000 | Loss 0.049345 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:25 Epoch 4 | Batch 2616/2891 | Timestep 14180 | LR 0.0001000000 | Loss 0.004982 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:27 Epoch 4 | Batch 2626/2891 | Timestep 14190 | LR 0.0001000000 | Loss 0.033379 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:28 Epoch 4 | Batch 2636/2891 | Timestep 14200 | LR 0.0001000000 | Loss 0.032419 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:30 Epoch 4 | Batch 2646/2891 | Timestep 14210 | LR 0.0001000000 | Loss 0.022982 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:32 Epoch 4 | Batch 2656/2891 | Timestep 14220 | LR 0.0001000000 | Loss 0.027774 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:33 Epoch 4 | Batch 2666/2891 | Timestep 14230 | LR 0.0001000000 | Loss 0.098884 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:35 Epoch 4 | Batch 2676/2891 | Timestep 14240 | LR 0.0001000000 | Loss 0.014719 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:37 Epoch 4 | Batch 2686/2891 | Timestep 14250 | LR 0.0001000000 | Loss 0.008174 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:39 Epoch 4 | Batch 2696/2891 | Timestep 14260 | LR 0.0001000000 | Loss 0.023341 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:41 Epoch 4 | Batch 2706/2891 | Timestep 14270 | LR 0.0001000000 | Loss 0.015087 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:43 Epoch 4 | Batch 2716/2891 | Timestep 14280 | LR 0.0001000000 | Loss 0.003762 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:44 Epoch 4 | Batch 2726/2891 | Timestep 14290 | LR 0.0001000000 | Loss 0.022236 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:46 Epoch 4 | Batch 2736/2891 | Timestep 14300 | LR 0.0001000000 | Loss 0.017225 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:48 Epoch 4 | Batch 2746/2891 | Timestep 14310 | LR 0.0001000000 | Loss 0.028297 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:49 Epoch 4 | Batch 2756/2891 | Timestep 14320 | LR 0.0001000000 | Loss 0.028665 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:51 Epoch 4 | Batch 2766/2891 | Timestep 14330 | LR 0.0001000000 | Loss 0.049008 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:53 Epoch 4 | Batch 2776/2891 | Timestep 14340 | LR 0.0001000000 | Loss 0.018988 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:54 Epoch 4 | Batch 2786/2891 | Timestep 14350 | LR 0.0001000000 | Loss 0.003804 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:56 Epoch 4 | Batch 2796/2891 | Timestep 14360 | LR 0.0001000000 | Loss 0.015656 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:31:58 Epoch 4 | Batch 2806/2891 | Timestep 14370 | LR 0.0001000000 | Loss 0.011762 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:00 Epoch 4 | Batch 2816/2891 | Timestep 14380 | LR 0.0001000000 | Loss 0.025149 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:02 Epoch 4 | Batch 2826/2891 | Timestep 14390 | LR 0.0001000000 | Loss 0.049500 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:03 Epoch 4 | Batch 2836/2891 | Timestep 14400 | LR 0.0001000000 | Loss 0.055359 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:05 Epoch 4 | Batch 2846/2891 | Timestep 14410 | LR 0.0001000000 | Loss 0.082200 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:07 Epoch 4 | Batch 2856/2891 | Timestep 14420 | LR 0.0001000000 | Loss 0.100672 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:08 Epoch 4 | Batch 2866/2891 | Timestep 14430 | LR 0.0001000000 | Loss 0.056093 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:10 Epoch 4 | Batch 2876/2891 | Timestep 14440 | LR 0.0001000000 | Loss 0.211461 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:12 Epoch 4 | Batch 2886/2891 | Timestep 14450 | LR 0.0001000000 | Loss 0.008061 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:12 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:32:46 precision recall f1-score support CARDINAL 0.7684 0.8000 0.7839 170 CURR 0.7895 0.6250 0.6977 24 DATE 0.9281 0.9243 0.9262 1691 EVENT 0.6983 0.7055 0.7019 292 FAC 0.5843 0.8220 0.6831 118 GPE 0.9614 0.9481 0.9547 2156 LANGUAGE 0.7857 0.6875 0.7333 16 LAW 0.6349 0.8511 0.7273 47 LOC 0.8049 0.7333 0.7674 90 MONEY 0.6190 0.5909 0.6047 22 NORP 0.6246 0.7187 0.6684 551 OCC 0.8238 0.7969 0.8101 522 ORDINAL 0.9435 0.9210 0.9321 544 ORG 0.8892 0.9123 0.9006 1882 PERCENT 1.0000 1.0000 1.0000 12 PERS 0.9331 0.8218 0.8739 679 PRODUCT 0.6667 0.5000 0.5714 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.5714 0.4848 0.5246 33 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.4018 0.5625 0.4688 80 micro avg 0.8725 0.8789 0.8757 8944 macro avg 0.7664 0.7534 0.7549 8944 weighted avg 0.8790 0.8789 0.8779 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:57 Epoch 4 | Timestep 14455 | Train Loss 0.026053 | Val Loss 0.068247 | F1 0.875682 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:32:58 Epoch 5 | Batch 5/2891 | Timestep 14460 | LR 0.0001000000 | Loss 0.040627 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:00 Epoch 5 | Batch 15/2891 | Timestep 14470 | LR 0.0001000000 | Loss 0.013453 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:02 Epoch 5 | Batch 25/2891 | Timestep 14480 | LR 0.0001000000 | Loss 0.029474 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:03 Epoch 5 | Batch 35/2891 | Timestep 14490 | LR 0.0001000000 | Loss 0.036669 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:05 Epoch 5 | Batch 45/2891 | Timestep 14500 | LR 0.0001000000 | Loss 0.024035 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:07 Epoch 5 | Batch 55/2891 | Timestep 14510 | LR 0.0001000000 | Loss 0.406965 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:08 Epoch 5 | Batch 65/2891 | Timestep 14520 | LR 0.0001000000 | Loss 0.069298 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:10 Epoch 5 | Batch 75/2891 | Timestep 14530 | LR 0.0001000000 | Loss 0.001528 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:11 Epoch 5 | Batch 85/2891 | Timestep 14540 | LR 0.0001000000 | Loss 0.003244 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:13 Epoch 5 | Batch 95/2891 | Timestep 14550 | LR 0.0001000000 | Loss 0.010953 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:14 Epoch 5 | Batch 105/2891 | Timestep 14560 | LR 0.0001000000 | Loss 0.003346 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:16 Epoch 5 | Batch 115/2891 | Timestep 14570 | LR 0.0001000000 | Loss 0.061526 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:17 Epoch 5 | Batch 125/2891 | Timestep 14580 | LR 0.0001000000 | Loss 0.007725 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:19 Epoch 5 | Batch 135/2891 | Timestep 14590 | LR 0.0001000000 | Loss 0.014524 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:21 Epoch 5 | Batch 145/2891 | Timestep 14600 | LR 0.0001000000 | Loss 0.031294 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:23 Epoch 5 | Batch 155/2891 | Timestep 14610 | LR 0.0001000000 | Loss 0.000751 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:25 Epoch 5 | Batch 165/2891 | Timestep 14620 | LR 0.0001000000 | Loss 0.014564 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:27 Epoch 5 | Batch 175/2891 | Timestep 14630 | LR 0.0001000000 | Loss 0.007237 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:28 Epoch 5 | Batch 185/2891 | Timestep 14640 | LR 0.0001000000 | Loss 0.027416 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:30 Epoch 5 | Batch 195/2891 | Timestep 14650 | LR 0.0001000000 | Loss 0.004048 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:31 Epoch 5 | Batch 205/2891 | Timestep 14660 | LR 0.0001000000 | Loss 0.011831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:33 Epoch 5 | Batch 215/2891 | Timestep 14670 | LR 0.0001000000 | Loss 0.024519 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:35 Epoch 5 | Batch 225/2891 | Timestep 14680 | LR 0.0001000000 | Loss 0.059481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:36 Epoch 5 | Batch 235/2891 | Timestep 14690 | LR 0.0001000000 | Loss 0.228850 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:38 Epoch 5 | Batch 245/2891 | Timestep 14700 | LR 0.0001000000 | Loss 0.402784 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:40 Epoch 5 | Batch 255/2891 | Timestep 14710 | LR 0.0001000000 | Loss 0.082749 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:41 Epoch 5 | Batch 265/2891 | Timestep 14720 | LR 0.0001000000 | Loss 0.174038 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:43 Epoch 5 | Batch 275/2891 | Timestep 14730 | LR 0.0001000000 | Loss 0.012610 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:45 Epoch 5 | Batch 285/2891 | Timestep 14740 | LR 0.0001000000 | Loss 0.010280 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:47 Epoch 5 | Batch 295/2891 | Timestep 14750 | LR 0.0001000000 | Loss 0.067763 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:49 Epoch 5 | Batch 305/2891 | Timestep 14760 | LR 0.0001000000 | Loss 0.165569 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:50 Epoch 5 | Batch 315/2891 | Timestep 14770 | LR 0.0001000000 | Loss 0.126954 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:52 Epoch 5 | Batch 325/2891 | Timestep 14780 | LR 0.0001000000 | Loss 0.303873 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:53 Epoch 5 | Batch 335/2891 | Timestep 14790 | LR 0.0001000000 | Loss 0.209677 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:55 Epoch 5 | Batch 345/2891 | Timestep 14800 | LR 0.0001000000 | Loss 0.258667 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:57 Epoch 5 | Batch 355/2891 | Timestep 14810 | LR 0.0001000000 | Loss 0.076789 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:33:59 Epoch 5 | Batch 365/2891 | Timestep 14820 | LR 0.0001000000 | Loss 0.038611 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:00 Epoch 5 | Batch 375/2891 | Timestep 14830 | LR 0.0001000000 | Loss 0.164465 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:02 Epoch 5 | Batch 385/2891 | Timestep 14840 | LR 0.0001000000 | Loss 0.111004 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:04 Epoch 5 | Batch 395/2891 | Timestep 14850 | LR 0.0001000000 | Loss 0.089448 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:06 Epoch 5 | Batch 405/2891 | Timestep 14860 | LR 0.0001000000 | Loss 0.070086 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:07 Epoch 5 | Batch 415/2891 | Timestep 14870 | LR 0.0001000000 | Loss 0.147873 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:09 Epoch 5 | Batch 425/2891 | Timestep 14880 | LR 0.0001000000 | Loss 0.116713 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:11 Epoch 5 | Batch 435/2891 | Timestep 14890 | LR 0.0001000000 | Loss 0.107226 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:12 Epoch 5 | Batch 445/2891 | Timestep 14900 | LR 0.0001000000 | Loss 0.036747 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:14 Epoch 5 | Batch 455/2891 | Timestep 14910 | LR 0.0001000000 | Loss 0.011163 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:16 Epoch 5 | Batch 465/2891 | Timestep 14920 | LR 0.0001000000 | Loss 0.021413 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:18 Epoch 5 | Batch 475/2891 | Timestep 14930 | LR 0.0001000000 | Loss 0.006734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:20 Epoch 5 | Batch 485/2891 | Timestep 14940 | LR 0.0001000000 | Loss 0.004481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:22 Epoch 5 | Batch 495/2891 | Timestep 14950 | LR 0.0001000000 | Loss 0.017847 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:23 Epoch 5 | Batch 505/2891 | Timestep 14960 | LR 0.0001000000 | Loss 0.014318 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:25 Epoch 5 | Batch 515/2891 | Timestep 14970 | LR 0.0001000000 | Loss 0.015793 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:27 Epoch 5 | Batch 525/2891 | Timestep 14980 | LR 0.0001000000 | Loss 0.008097 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:28 Epoch 5 | Batch 535/2891 | Timestep 14990 | LR 0.0001000000 | Loss 0.026692 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:30 Epoch 5 | Batch 545/2891 | Timestep 15000 | LR 0.0001000000 | Loss 0.013937 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:32 Epoch 5 | Batch 555/2891 | Timestep 15010 | LR 0.0001000000 | Loss 0.006376 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:33 Epoch 5 | Batch 565/2891 | Timestep 15020 | LR 0.0001000000 | Loss 0.005364 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:36 Epoch 5 | Batch 575/2891 | Timestep 15030 | LR 0.0001000000 | Loss 0.007640 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:37 Epoch 5 | Batch 585/2891 | Timestep 15040 | LR 0.0001000000 | Loss 0.012950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:39 Epoch 5 | Batch 595/2891 | Timestep 15050 | LR 0.0001000000 | Loss 0.039304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:41 Epoch 5 | Batch 605/2891 | Timestep 15060 | LR 0.0001000000 | Loss 0.015059 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:42 Epoch 5 | Batch 615/2891 | Timestep 15070 | LR 0.0001000000 | Loss 0.030719 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:44 Epoch 5 | Batch 625/2891 | Timestep 15080 | LR 0.0001000000 | Loss 0.058714 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:45 Epoch 5 | Batch 635/2891 | Timestep 15090 | LR 0.0001000000 | Loss 0.001440 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:47 Epoch 5 | Batch 645/2891 | Timestep 15100 | LR 0.0001000000 | Loss 0.019463 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:49 Epoch 5 | Batch 655/2891 | Timestep 15110 | LR 0.0001000000 | Loss 0.014386 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:51 Epoch 5 | Batch 665/2891 | Timestep 15120 | LR 0.0001000000 | Loss 0.004915 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:53 Epoch 5 | Batch 675/2891 | Timestep 15130 | LR 0.0001000000 | Loss 0.003095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:54 Epoch 5 | Batch 685/2891 | Timestep 15140 | LR 0.0001000000 | Loss 0.002037 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:56 Epoch 5 | Batch 695/2891 | Timestep 15150 | LR 0.0001000000 | Loss 0.021383 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:34:58 Epoch 5 | Batch 705/2891 | Timestep 15160 | LR 0.0001000000 | Loss 0.052326 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:00 Epoch 5 | Batch 715/2891 | Timestep 15170 | LR 0.0001000000 | Loss 0.082952 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:01 Epoch 5 | Batch 725/2891 | Timestep 15180 | LR 0.0001000000 | Loss 0.041315 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:03 Epoch 5 | Batch 735/2891 | Timestep 15190 | LR 0.0001000000 | Loss 0.014299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:05 Epoch 5 | Batch 745/2891 | Timestep 15200 | LR 0.0001000000 | Loss 0.049219 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:06 Epoch 5 | Batch 755/2891 | Timestep 15210 | LR 0.0001000000 | Loss 0.011891 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:08 Epoch 5 | Batch 765/2891 | Timestep 15220 | LR 0.0001000000 | Loss 0.008144 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:09 Epoch 5 | Batch 775/2891 | Timestep 15230 | LR 0.0001000000 | Loss 0.003014 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:11 Epoch 5 | Batch 785/2891 | Timestep 15240 | LR 0.0001000000 | Loss 0.015594 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:13 Epoch 5 | Batch 795/2891 | Timestep 15250 | LR 0.0001000000 | Loss 0.046842 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:15 Epoch 5 | Batch 805/2891 | Timestep 15260 | LR 0.0001000000 | Loss 0.004306 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:17 Epoch 5 | Batch 815/2891 | Timestep 15270 | LR 0.0001000000 | Loss 0.039363 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:19 Epoch 5 | Batch 825/2891 | Timestep 15280 | LR 0.0001000000 | Loss 0.021363 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:21 Epoch 5 | Batch 835/2891 | Timestep 15290 | LR 0.0001000000 | Loss 0.016525 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:23 Epoch 5 | Batch 845/2891 | Timestep 15300 | LR 0.0001000000 | Loss 0.140694 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:24 Epoch 5 | Batch 855/2891 | Timestep 15310 | LR 0.0001000000 | Loss 0.019272 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:26 Epoch 5 | Batch 865/2891 | Timestep 15320 | LR 0.0001000000 | Loss 0.032547 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:28 Epoch 5 | Batch 875/2891 | Timestep 15330 | LR 0.0001000000 | Loss 0.018931 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:30 Epoch 5 | Batch 885/2891 | Timestep 15340 | LR 0.0001000000 | Loss 0.007977 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:32 Epoch 5 | Batch 895/2891 | Timestep 15350 | LR 0.0001000000 | Loss 0.025846 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:34 Epoch 5 | Batch 905/2891 | Timestep 15360 | LR 0.0001000000 | Loss 0.076978 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:35 Epoch 5 | Batch 915/2891 | Timestep 15370 | LR 0.0001000000 | Loss 0.080207 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:37 Epoch 5 | Batch 925/2891 | Timestep 15380 | LR 0.0001000000 | Loss 0.019590 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:39 Epoch 5 | Batch 935/2891 | Timestep 15390 | LR 0.0001000000 | Loss 0.002643 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:41 Epoch 5 | Batch 945/2891 | Timestep 15400 | LR 0.0001000000 | Loss 0.043004 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:43 Epoch 5 | Batch 955/2891 | Timestep 15410 | LR 0.0001000000 | Loss 0.005907 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:44 Epoch 5 | Batch 965/2891 | Timestep 15420 | LR 0.0001000000 | Loss 0.036173 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:46 Epoch 5 | Batch 975/2891 | Timestep 15430 | LR 0.0001000000 | Loss 0.013282 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:48 Epoch 5 | Batch 985/2891 | Timestep 15440 | LR 0.0001000000 | Loss 0.002672 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:49 Epoch 5 | Batch 995/2891 | Timestep 15450 | LR 0.0001000000 | Loss 0.008011 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:51 Epoch 5 | Batch 1005/2891 | Timestep 15460 | LR 0.0001000000 | Loss 0.006072 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:53 Epoch 5 | Batch 1015/2891 | Timestep 15470 | LR 0.0001000000 | Loss 0.043095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:55 Epoch 5 | Batch 1025/2891 | Timestep 15480 | LR 0.0001000000 | Loss 0.001493 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:56 Epoch 5 | Batch 1035/2891 | Timestep 15490 | LR 0.0001000000 | Loss 0.017446 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:35:58 Epoch 5 | Batch 1045/2891 | Timestep 15500 | LR 0.0001000000 | Loss 0.064398 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:00 Epoch 5 | Batch 1055/2891 | Timestep 15510 | LR 0.0001000000 | Loss 0.009867 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:01 Epoch 5 | Batch 1065/2891 | Timestep 15520 | LR 0.0001000000 | Loss 0.062838 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:03 Epoch 5 | Batch 1075/2891 | Timestep 15530 | LR 0.0001000000 | Loss 0.031833 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:05 Epoch 5 | Batch 1085/2891 | Timestep 15540 | LR 0.0001000000 | Loss 0.068223 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:07 Epoch 5 | Batch 1095/2891 | Timestep 15550 | LR 0.0001000000 | Loss 0.015031 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:08 Epoch 5 | Batch 1105/2891 | Timestep 15560 | LR 0.0001000000 | Loss 0.010354 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:10 Epoch 5 | Batch 1115/2891 | Timestep 15570 | LR 0.0001000000 | Loss 0.034020 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:11 Epoch 5 | Batch 1125/2891 | Timestep 15580 | LR 0.0001000000 | Loss 0.020278 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:13 Epoch 5 | Batch 1135/2891 | Timestep 15590 | LR 0.0001000000 | Loss 0.004732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:15 Epoch 5 | Batch 1145/2891 | Timestep 15600 | LR 0.0001000000 | Loss 0.032654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:17 Epoch 5 | Batch 1155/2891 | Timestep 15610 | LR 0.0001000000 | Loss 0.022669 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:18 Epoch 5 | Batch 1165/2891 | Timestep 15620 | LR 0.0001000000 | Loss 0.008501 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:20 Epoch 5 | Batch 1175/2891 | Timestep 15630 | LR 0.0001000000 | Loss 0.003934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:21 Epoch 5 | Batch 1185/2891 | Timestep 15640 | LR 0.0001000000 | Loss 0.010287 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:23 Epoch 5 | Batch 1195/2891 | Timestep 15650 | LR 0.0001000000 | Loss 0.003711 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:25 Epoch 5 | Batch 1205/2891 | Timestep 15660 | LR 0.0001000000 | Loss 0.042695 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:27 Epoch 5 | Batch 1215/2891 | Timestep 15670 | LR 0.0001000000 | Loss 0.005572 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:29 Epoch 5 | Batch 1225/2891 | Timestep 15680 | LR 0.0001000000 | Loss 0.016045 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:31 Epoch 5 | Batch 1235/2891 | Timestep 15690 | LR 0.0001000000 | Loss 0.021561 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:32 Epoch 5 | Batch 1245/2891 | Timestep 15700 | LR 0.0001000000 | Loss 0.031486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:34 Epoch 5 | Batch 1255/2891 | Timestep 15710 | LR 0.0001000000 | Loss 0.002632 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:37 Epoch 5 | Batch 1265/2891 | Timestep 15720 | LR 0.0001000000 | Loss 0.004431 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:38 Epoch 5 | Batch 1275/2891 | Timestep 15730 | LR 0.0001000000 | Loss 0.006357 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:40 Epoch 5 | Batch 1285/2891 | Timestep 15740 | LR 0.0001000000 | Loss 0.002935 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:41 Epoch 5 | Batch 1295/2891 | Timestep 15750 | LR 0.0001000000 | Loss 0.006181 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:43 Epoch 5 | Batch 1305/2891 | Timestep 15760 | LR 0.0001000000 | Loss 0.035286 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:45 Epoch 5 | Batch 1315/2891 | Timestep 15770 | LR 0.0001000000 | Loss 0.038514 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:47 Epoch 5 | Batch 1325/2891 | Timestep 15780 | LR 0.0001000000 | Loss 0.002583 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:48 Epoch 5 | Batch 1335/2891 | Timestep 15790 | LR 0.0001000000 | Loss 0.015992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:50 Epoch 5 | Batch 1345/2891 | Timestep 15800 | LR 0.0001000000 | Loss 0.041408 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:51 Epoch 5 | Batch 1355/2891 | Timestep 15810 | LR 0.0001000000 | Loss 0.008139 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:53 Epoch 5 | Batch 1365/2891 | Timestep 15820 | LR 0.0001000000 | Loss 0.002624 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:55 Epoch 5 | Batch 1375/2891 | Timestep 15830 | LR 0.0001000000 | Loss 0.046360 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:57 Epoch 5 | Batch 1385/2891 | Timestep 15840 | LR 0.0001000000 | Loss 0.033574 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:36:58 Epoch 5 | Batch 1395/2891 | Timestep 15850 | LR 0.0001000000 | Loss 0.024813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:00 Epoch 5 | Batch 1405/2891 | Timestep 15860 | LR 0.0001000000 | Loss 0.029220 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:01 Epoch 5 | Batch 1415/2891 | Timestep 15870 | LR 0.0001000000 | Loss 0.042721 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:03 Epoch 5 | Batch 1425/2891 | Timestep 15880 | LR 0.0001000000 | Loss 0.027003 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:05 Epoch 5 | Batch 1435/2891 | Timestep 15890 | LR 0.0001000000 | Loss 0.020702 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:06 Epoch 5 | Batch 1445/2891 | Timestep 15900 | LR 0.0001000000 | Loss 0.006211 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:08 Epoch 5 | Batch 1455/2891 | Timestep 15910 | LR 0.0001000000 | Loss 0.091202 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:10 Epoch 5 | Batch 1465/2891 | Timestep 15920 | LR 0.0001000000 | Loss 0.001244 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:12 Epoch 5 | Batch 1475/2891 | Timestep 15930 | LR 0.0001000000 | Loss 0.004566 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:13 Epoch 5 | Batch 1485/2891 | Timestep 15940 | LR 0.0001000000 | Loss 0.003875 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:15 Epoch 5 | Batch 1495/2891 | Timestep 15950 | LR 0.0001000000 | Loss 0.006252 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:16 Epoch 5 | Batch 1505/2891 | Timestep 15960 | LR 0.0001000000 | Loss 0.002979 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:18 Epoch 5 | Batch 1515/2891 | Timestep 15970 | LR 0.0001000000 | Loss 0.003871 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:19 Epoch 5 | Batch 1525/2891 | Timestep 15980 | LR 0.0001000000 | Loss 0.033201 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:21 Epoch 5 | Batch 1535/2891 | Timestep 15990 | LR 0.0001000000 | Loss 0.092081 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:23 Epoch 5 | Batch 1545/2891 | Timestep 16000 | LR 0.0001000000 | Loss 0.006748 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:25 Epoch 5 | Batch 1555/2891 | Timestep 16010 | LR 0.0001000000 | Loss 0.028865 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:26 Epoch 5 | Batch 1565/2891 | Timestep 16020 | LR 0.0001000000 | Loss 0.113968 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:28 Epoch 5 | Batch 1575/2891 | Timestep 16030 | LR 0.0001000000 | Loss 0.011371 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:30 Epoch 5 | Batch 1585/2891 | Timestep 16040 | LR 0.0001000000 | Loss 0.030681 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:31 Epoch 5 | Batch 1595/2891 | Timestep 16050 | LR 0.0001000000 | Loss 0.018217 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:33 Epoch 5 | Batch 1605/2891 | Timestep 16060 | LR 0.0001000000 | Loss 0.004352 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:35 Epoch 5 | Batch 1615/2891 | Timestep 16070 | LR 0.0001000000 | Loss 0.011742 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:37 Epoch 5 | Batch 1625/2891 | Timestep 16080 | LR 0.0001000000 | Loss 0.079272 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:39 Epoch 5 | Batch 1635/2891 | Timestep 16090 | LR 0.0001000000 | Loss 0.008429 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:40 Epoch 5 | Batch 1645/2891 | Timestep 16100 | LR 0.0001000000 | Loss 0.002023 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:42 Epoch 5 | Batch 1655/2891 | Timestep 16110 | LR 0.0001000000 | Loss 0.004389 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:44 Epoch 5 | Batch 1665/2891 | Timestep 16120 | LR 0.0001000000 | Loss 0.015513 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:45 Epoch 5 | Batch 1675/2891 | Timestep 16130 | LR 0.0001000000 | Loss 0.022050 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:47 Epoch 5 | Batch 1685/2891 | Timestep 16140 | LR 0.0001000000 | Loss 0.023804 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:49 Epoch 5 | Batch 1695/2891 | Timestep 16150 | LR 0.0001000000 | Loss 0.030458 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:50 Epoch 5 | Batch 1705/2891 | Timestep 16160 | LR 0.0001000000 | Loss 0.030123 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:52 Epoch 5 | Batch 1715/2891 | Timestep 16170 | LR 0.0001000000 | Loss 0.001879 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:54 Epoch 5 | Batch 1725/2891 | Timestep 16180 | LR 0.0001000000 | Loss 0.011229 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:56 Epoch 5 | Batch 1735/2891 | Timestep 16190 | LR 0.0001000000 | Loss 0.069122 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:57 Epoch 5 | Batch 1745/2891 | Timestep 16200 | LR 0.0001000000 | Loss 0.020967 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:37:59 Epoch 5 | Batch 1755/2891 | Timestep 16210 | LR 0.0001000000 | Loss 0.005807 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:00 Epoch 5 | Batch 1765/2891 | Timestep 16220 | LR 0.0001000000 | Loss 0.035891 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:02 Epoch 5 | Batch 1775/2891 | Timestep 16230 | LR 0.0001000000 | Loss 0.007209 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:04 Epoch 5 | Batch 1785/2891 | Timestep 16240 | LR 0.0001000000 | Loss 0.023106 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:06 Epoch 5 | Batch 1795/2891 | Timestep 16250 | LR 0.0001000000 | Loss 0.028316 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:08 Epoch 5 | Batch 1805/2891 | Timestep 16260 | LR 0.0001000000 | Loss 0.009143 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:09 Epoch 5 | Batch 1815/2891 | Timestep 16270 | LR 0.0001000000 | Loss 0.012450 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:11 Epoch 5 | Batch 1825/2891 | Timestep 16280 | LR 0.0001000000 | Loss 0.011071 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:13 Epoch 5 | Batch 1835/2891 | Timestep 16290 | LR 0.0001000000 | Loss 0.006751 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:14 Epoch 5 | Batch 1845/2891 | Timestep 16300 | LR 0.0001000000 | Loss 0.025374 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:16 Epoch 5 | Batch 1855/2891 | Timestep 16310 | LR 0.0001000000 | Loss 0.014165 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:18 Epoch 5 | Batch 1865/2891 | Timestep 16320 | LR 0.0001000000 | Loss 0.003330 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:20 Epoch 5 | Batch 1875/2891 | Timestep 16330 | LR 0.0001000000 | Loss 0.005796 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:21 Epoch 5 | Batch 1885/2891 | Timestep 16340 | LR 0.0001000000 | Loss 0.003437 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:23 Epoch 5 | Batch 1895/2891 | Timestep 16350 | LR 0.0001000000 | Loss 0.028591 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:25 Epoch 5 | Batch 1905/2891 | Timestep 16360 | LR 0.0001000000 | Loss 0.001626 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:26 Epoch 5 | Batch 1915/2891 | Timestep 16370 | LR 0.0001000000 | Loss 0.006567 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:28 Epoch 5 | Batch 1925/2891 | Timestep 16380 | LR 0.0001000000 | Loss 0.012156 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:30 Epoch 5 | Batch 1935/2891 | Timestep 16390 | LR 0.0001000000 | Loss 0.011018 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:32 Epoch 5 | Batch 1945/2891 | Timestep 16400 | LR 0.0001000000 | Loss 0.013427 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:33 Epoch 5 | Batch 1955/2891 | Timestep 16410 | LR 0.0001000000 | Loss 0.013815 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:35 Epoch 5 | Batch 1965/2891 | Timestep 16420 | LR 0.0001000000 | Loss 0.011184 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:38 Epoch 5 | Batch 1975/2891 | Timestep 16430 | LR 0.0001000000 | Loss 0.005850 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:39 Epoch 5 | Batch 1985/2891 | Timestep 16440 | LR 0.0001000000 | Loss 0.001492 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:41 Epoch 5 | Batch 1995/2891 | Timestep 16450 | LR 0.0001000000 | Loss 0.018048 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:43 Epoch 5 | Batch 2005/2891 | Timestep 16460 | LR 0.0001000000 | Loss 0.022439 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:45 Epoch 5 | Batch 2015/2891 | Timestep 16470 | LR 0.0001000000 | Loss 0.016575 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:46 Epoch 5 | Batch 2025/2891 | Timestep 16480 | LR 0.0001000000 | Loss 0.002261 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:48 Epoch 5 | Batch 2035/2891 | Timestep 16490 | LR 0.0001000000 | Loss 0.018193 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:50 Epoch 5 | Batch 2045/2891 | Timestep 16500 | LR 0.0001000000 | Loss 0.039925 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:52 Epoch 5 | Batch 2055/2891 | Timestep 16510 | LR 0.0001000000 | Loss 0.013984 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:53 Epoch 5 | Batch 2065/2891 | Timestep 16520 | LR 0.0001000000 | Loss 0.025949 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:55 Epoch 5 | Batch 2075/2891 | Timestep 16530 | LR 0.0001000000 | Loss 0.005366 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:56 Epoch 5 | Batch 2085/2891 | Timestep 16540 | LR 0.0001000000 | Loss 0.006799 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:38:58 Epoch 5 | Batch 2095/2891 | Timestep 16550 | LR 0.0001000000 | Loss 0.101299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:00 Epoch 5 | Batch 2105/2891 | Timestep 16560 | LR 0.0001000000 | Loss 0.009223 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:01 Epoch 5 | Batch 2115/2891 | Timestep 16570 | LR 0.0001000000 | Loss 0.028303 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:03 Epoch 5 | Batch 2125/2891 | Timestep 16580 | LR 0.0001000000 | Loss 0.004369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:05 Epoch 5 | Batch 2135/2891 | Timestep 16590 | LR 0.0001000000 | Loss 0.039421 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:07 Epoch 5 | Batch 2145/2891 | Timestep 16600 | LR 0.0001000000 | Loss 0.010243 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:08 Epoch 5 | Batch 2155/2891 | Timestep 16610 | LR 0.0001000000 | Loss 0.006997 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:10 Epoch 5 | Batch 2165/2891 | Timestep 16620 | LR 0.0001000000 | Loss 0.007813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:12 Epoch 5 | Batch 2175/2891 | Timestep 16630 | LR 0.0001000000 | Loss 0.043601 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:14 Epoch 5 | Batch 2185/2891 | Timestep 16640 | LR 0.0001000000 | Loss 0.039781 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:16 Epoch 5 | Batch 2195/2891 | Timestep 16650 | LR 0.0001000000 | Loss 0.042370 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:18 Epoch 5 | Batch 2205/2891 | Timestep 16660 | LR 0.0001000000 | Loss 0.015121 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:20 Epoch 5 | Batch 2215/2891 | Timestep 16670 | LR 0.0001000000 | Loss 0.009934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:21 Epoch 5 | Batch 2225/2891 | Timestep 16680 | LR 0.0001000000 | Loss 0.010431 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:23 Epoch 5 | Batch 2235/2891 | Timestep 16690 | LR 0.0001000000 | Loss 0.009255 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:25 Epoch 5 | Batch 2245/2891 | Timestep 16700 | LR 0.0001000000 | Loss 0.026558 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:27 Epoch 5 | Batch 2255/2891 | Timestep 16710 | LR 0.0001000000 | Loss 0.060197 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:28 Epoch 5 | Batch 2265/2891 | Timestep 16720 | LR 0.0001000000 | Loss 0.024443 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:30 Epoch 5 | Batch 2275/2891 | Timestep 16730 | LR 0.0001000000 | Loss 0.013365 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:32 Epoch 5 | Batch 2285/2891 | Timestep 16740 | LR 0.0001000000 | Loss 0.006915 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:34 Epoch 5 | Batch 2295/2891 | Timestep 16750 | LR 0.0001000000 | Loss 0.022478 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:35 Epoch 5 | Batch 2305/2891 | Timestep 16760 | LR 0.0001000000 | Loss 0.027744 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:37 Epoch 5 | Batch 2315/2891 | Timestep 16770 | LR 0.0001000000 | Loss 0.032147 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:39 Epoch 5 | Batch 2325/2891 | Timestep 16780 | LR 0.0001000000 | Loss 0.042151 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:41 Epoch 5 | Batch 2335/2891 | Timestep 16790 | LR 0.0001000000 | Loss 0.016177 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:43 Epoch 5 | Batch 2345/2891 | Timestep 16800 | LR 0.0001000000 | Loss 0.058826 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:45 Epoch 5 | Batch 2355/2891 | Timestep 16810 | LR 0.0001000000 | Loss 0.000774 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:46 Epoch 5 | Batch 2365/2891 | Timestep 16820 | LR 0.0001000000 | Loss 0.011293 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:48 Epoch 5 | Batch 2375/2891 | Timestep 16830 | LR 0.0001000000 | Loss 0.074953 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:49 Epoch 5 | Batch 2385/2891 | Timestep 16840 | LR 0.0001000000 | Loss 0.014247 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:51 Epoch 5 | Batch 2395/2891 | Timestep 16850 | LR 0.0001000000 | Loss 0.076826 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:53 Epoch 5 | Batch 2405/2891 | Timestep 16860 | LR 0.0001000000 | Loss 0.019178 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:55 Epoch 5 | Batch 2415/2891 | Timestep 16870 | LR 0.0001000000 | Loss 0.019544 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:56 Epoch 5 | Batch 2425/2891 | Timestep 16880 | LR 0.0001000000 | Loss 0.045028 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:39:58 Epoch 5 | Batch 2435/2891 | Timestep 16890 | LR 0.0001000000 | Loss 0.032231 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:00 Epoch 5 | Batch 2445/2891 | Timestep 16900 | LR 0.0001000000 | Loss 0.007049 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:02 Epoch 5 | Batch 2455/2891 | Timestep 16910 | LR 0.0001000000 | Loss 0.038389 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:04 Epoch 5 | Batch 2465/2891 | Timestep 16920 | LR 0.0001000000 | Loss 0.020725 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:05 Epoch 5 | Batch 2475/2891 | Timestep 16930 | LR 0.0001000000 | Loss 0.013941 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:07 Epoch 5 | Batch 2485/2891 | Timestep 16940 | LR 0.0001000000 | Loss 0.008261 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:09 Epoch 5 | Batch 2495/2891 | Timestep 16950 | LR 0.0001000000 | Loss 0.044507 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:10 Epoch 5 | Batch 2505/2891 | Timestep 16960 | LR 0.0001000000 | Loss 0.028855 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:12 Epoch 5 | Batch 2515/2891 | Timestep 16970 | LR 0.0001000000 | Loss 0.004134 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:14 Epoch 5 | Batch 2525/2891 | Timestep 16980 | LR 0.0001000000 | Loss 0.004989 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:15 Epoch 5 | Batch 2535/2891 | Timestep 16990 | LR 0.0001000000 | Loss 0.034175 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:17 Epoch 5 | Batch 2545/2891 | Timestep 17000 | LR 0.0001000000 | Loss 0.000893 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:19 Epoch 5 | Batch 2555/2891 | Timestep 17010 | LR 0.0001000000 | Loss 0.046683 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:20 Epoch 5 | Batch 2565/2891 | Timestep 17020 | LR 0.0001000000 | Loss 0.025548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:22 Epoch 5 | Batch 2575/2891 | Timestep 17030 | LR 0.0001000000 | Loss 0.022812 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:23 Epoch 5 | Batch 2585/2891 | Timestep 17040 | LR 0.0001000000 | Loss 0.024972 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:25 Epoch 5 | Batch 2595/2891 | Timestep 17050 | LR 0.0001000000 | Loss 0.014110 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:27 Epoch 5 | Batch 2605/2891 | Timestep 17060 | LR 0.0001000000 | Loss 0.031145 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:29 Epoch 5 | Batch 2615/2891 | Timestep 17070 | LR 0.0001000000 | Loss 0.011820 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:31 Epoch 5 | Batch 2625/2891 | Timestep 17080 | LR 0.0001000000 | Loss 0.009452 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:33 Epoch 5 | Batch 2635/2891 | Timestep 17090 | LR 0.0001000000 | Loss 0.015069 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:34 Epoch 5 | Batch 2645/2891 | Timestep 17100 | LR 0.0001000000 | Loss 0.009239 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:36 Epoch 5 | Batch 2655/2891 | Timestep 17110 | LR 0.0001000000 | Loss 0.017870 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:37 Epoch 5 | Batch 2665/2891 | Timestep 17120 | LR 0.0001000000 | Loss 0.010126 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:39 Epoch 5 | Batch 2675/2891 | Timestep 17130 | LR 0.0001000000 | Loss 0.007709 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:41 Epoch 5 | Batch 2685/2891 | Timestep 17140 | LR 0.0001000000 | Loss 0.027788 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:43 Epoch 5 | Batch 2695/2891 | Timestep 17150 | LR 0.0001000000 | Loss 0.009185 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:44 Epoch 5 | Batch 2705/2891 | Timestep 17160 | LR 0.0001000000 | Loss 0.010309 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:46 Epoch 5 | Batch 2715/2891 | Timestep 17170 | LR 0.0001000000 | Loss 0.013521 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:48 Epoch 5 | Batch 2725/2891 | Timestep 17180 | LR 0.0001000000 | Loss 0.002986 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:49 Epoch 5 | Batch 2735/2891 | Timestep 17190 | LR 0.0001000000 | Loss 0.004553 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:51 Epoch 5 | Batch 2745/2891 | Timestep 17200 | LR 0.0001000000 | Loss 0.001424 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:53 Epoch 5 | Batch 2755/2891 | Timestep 17210 | LR 0.0001000000 | Loss 0.072734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:55 Epoch 5 | Batch 2765/2891 | Timestep 17220 | LR 0.0001000000 | Loss 0.025252 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:56 Epoch 5 | Batch 2775/2891 | Timestep 17230 | LR 0.0001000000 | Loss 0.019305 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:58 Epoch 5 | Batch 2785/2891 | Timestep 17240 | LR 0.0001000000 | Loss 0.003712 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:40:59 Epoch 5 | Batch 2795/2891 | Timestep 17250 | LR 0.0001000000 | Loss 0.048796 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:01 Epoch 5 | Batch 2805/2891 | Timestep 17260 | LR 0.0001000000 | Loss 0.011836 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:03 Epoch 5 | Batch 2815/2891 | Timestep 17270 | LR 0.0001000000 | Loss 0.024013 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:05 Epoch 5 | Batch 2825/2891 | Timestep 17280 | LR 0.0001000000 | Loss 0.012538 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:06 Epoch 5 | Batch 2835/2891 | Timestep 17290 | LR 0.0001000000 | Loss 0.001548 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:08 Epoch 5 | Batch 2845/2891 | Timestep 17300 | LR 0.0001000000 | Loss 0.002129 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:10 Epoch 5 | Batch 2855/2891 | Timestep 17310 | LR 0.0001000000 | Loss 0.006843 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:11 Epoch 5 | Batch 2865/2891 | Timestep 17320 | LR 0.0001000000 | Loss 0.029394 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:13 Epoch 5 | Batch 2875/2891 | Timestep 17330 | LR 0.0001000000 | Loss 0.003635 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:14 Epoch 5 | Batch 2885/2891 | Timestep 17340 | LR 0.0001000000 | Loss 0.010612 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:41:16 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:41:51 precision recall f1-score support CARDINAL 0.7374 0.7765 0.7564 170 CURR 0.9545 0.8750 0.9130 24 DATE 0.8920 0.9137 0.9027 1691 EVENT 0.6239 0.7329 0.6740 292 FAC 0.6875 0.8390 0.7557 118 GPE 0.9553 0.9606 0.9579 2156 LANGUAGE 0.9091 0.6250 0.7407 16 LAW 0.5634 0.8511 0.6780 47 LOC 0.7391 0.7556 0.7473 90 MONEY 0.7200 0.8182 0.7660 22 NORP 0.6345 0.7405 0.6834 551 OCC 0.8485 0.8582 0.8533 522 ORDINAL 0.9475 0.9283 0.9378 544 ORG 0.8553 0.9261 0.8893 1882 PERCENT 0.7500 0.7500 0.7500 12 PERS 0.9173 0.9308 0.9240 679 PRODUCT 0.1667 0.3750 0.2308 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.6585 0.8182 0.7297 33 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.4756 0.4875 0.4815 80 micro avg 0.8571 0.8986 0.8774 8944 macro avg 0.7478 0.7799 0.7569 8944 weighted avg 0.8631 0.8986 0.8797 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:02 Epoch 5 | Timestep 17346 | Train Loss 0.033107 | Val Loss 0.062598 | F1 0.877354 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:03 Epoch 6 | Batch 4/2891 | Timestep 17350 | LR 0.0001000000 | Loss 0.001142 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:04 Epoch 6 | Batch 14/2891 | Timestep 17360 | LR 0.0001000000 | Loss 0.015678 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:06 Epoch 6 | Batch 24/2891 | Timestep 17370 | LR 0.0001000000 | Loss 0.016314 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:08 Epoch 6 | Batch 34/2891 | Timestep 17380 | LR 0.0001000000 | Loss 0.002410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:10 Epoch 6 | Batch 44/2891 | Timestep 17390 | LR 0.0001000000 | Loss 0.000813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:11 Epoch 6 | Batch 54/2891 | Timestep 17400 | LR 0.0001000000 | Loss 0.000454 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:14 Epoch 6 | Batch 64/2891 | Timestep 17410 | LR 0.0001000000 | Loss 0.032219 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:16 Epoch 6 | Batch 74/2891 | Timestep 17420 | LR 0.0001000000 | Loss 0.027052 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:17 Epoch 6 | Batch 84/2891 | Timestep 17430 | LR 0.0001000000 | Loss 0.014278 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:19 Epoch 6 | Batch 94/2891 | Timestep 17440 | LR 0.0001000000 | Loss 0.004272 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:20 Epoch 6 | Batch 104/2891 | Timestep 17450 | LR 0.0001000000 | Loss 0.006310 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:22 Epoch 6 | Batch 114/2891 | Timestep 17460 | LR 0.0001000000 | Loss 0.014190 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:24 Epoch 6 | Batch 124/2891 | Timestep 17470 | LR 0.0001000000 | Loss 0.002307 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:25 Epoch 6 | Batch 134/2891 | Timestep 17480 | LR 0.0001000000 | Loss 0.001726 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:27 Epoch 6 | Batch 144/2891 | Timestep 17490 | LR 0.0001000000 | Loss 0.002486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:29 Epoch 6 | Batch 154/2891 | Timestep 17500 | LR 0.0001000000 | Loss 0.005278 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:31 Epoch 6 | Batch 164/2891 | Timestep 17510 | LR 0.0001000000 | Loss 0.001642 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:32 Epoch 6 | Batch 174/2891 | Timestep 17520 | LR 0.0001000000 | Loss 0.012467 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:34 Epoch 6 | Batch 184/2891 | Timestep 17530 | LR 0.0001000000 | Loss 0.005231 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:36 Epoch 6 | Batch 194/2891 | Timestep 17540 | LR 0.0001000000 | Loss 0.005120 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:37 Epoch 6 | Batch 204/2891 | Timestep 17550 | LR 0.0001000000 | Loss 0.004919 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:39 Epoch 6 | Batch 214/2891 | Timestep 17560 | LR 0.0001000000 | Loss 0.031734 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:41 Epoch 6 | Batch 224/2891 | Timestep 17570 | LR 0.0001000000 | Loss 0.002836 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:43 Epoch 6 | Batch 234/2891 | Timestep 17580 | LR 0.0001000000 | Loss 0.007490 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:44 Epoch 6 | Batch 244/2891 | Timestep 17590 | LR 0.0001000000 | Loss 0.023603 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:46 Epoch 6 | Batch 254/2891 | Timestep 17600 | LR 0.0001000000 | Loss 0.032607 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:48 Epoch 6 | Batch 264/2891 | Timestep 17610 | LR 0.0001000000 | Loss 0.005882 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:49 Epoch 6 | Batch 274/2891 | Timestep 17620 | LR 0.0001000000 | Loss 0.043513 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:51 Epoch 6 | Batch 284/2891 | Timestep 17630 | LR 0.0001000000 | Loss 0.031631 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:52 Epoch 6 | Batch 294/2891 | Timestep 17640 | LR 0.0001000000 | Loss 0.091040 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:54 Epoch 6 | Batch 304/2891 | Timestep 17650 | LR 0.0001000000 | Loss 0.061976 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:56 Epoch 6 | Batch 314/2891 | Timestep 17660 | LR 0.0001000000 | Loss 0.018431 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:58 Epoch 6 | Batch 324/2891 | Timestep 17670 | LR 0.0001000000 | Loss 0.058466 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:42:59 Epoch 6 | Batch 334/2891 | Timestep 17680 | LR 0.0001000000 | Loss 0.001564 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:01 Epoch 6 | Batch 344/2891 | Timestep 17690 | LR 0.0001000000 | Loss 0.092360 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:03 Epoch 6 | Batch 354/2891 | Timestep 17700 | LR 0.0001000000 | Loss 0.020535 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:05 Epoch 6 | Batch 364/2891 | Timestep 17710 | LR 0.0001000000 | Loss 0.052234 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:06 Epoch 6 | Batch 374/2891 | Timestep 17720 | LR 0.0001000000 | Loss 0.119731 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:08 Epoch 6 | Batch 384/2891 | Timestep 17730 | LR 0.0001000000 | Loss 0.039712 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:10 Epoch 6 | Batch 394/2891 | Timestep 17740 | LR 0.0001000000 | Loss 0.057596 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:11 Epoch 6 | Batch 404/2891 | Timestep 17750 | LR 0.0001000000 | Loss 0.354989 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:13 Epoch 6 | Batch 414/2891 | Timestep 17760 | LR 0.0001000000 | Loss 0.672639 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:15 Epoch 6 | Batch 424/2891 | Timestep 17770 | LR 0.0001000000 | Loss 0.231824 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:16 Epoch 6 | Batch 434/2891 | Timestep 17780 | LR 0.0001000000 | Loss 0.034160 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:18 Epoch 6 | Batch 444/2891 | Timestep 17790 | LR 0.0001000000 | Loss 0.022249 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:20 Epoch 6 | Batch 454/2891 | Timestep 17800 | LR 0.0001000000 | Loss 0.063418 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:22 Epoch 6 | Batch 464/2891 | Timestep 17810 | LR 0.0001000000 | Loss 0.082853 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:23 Epoch 6 | Batch 474/2891 | Timestep 17820 | LR 0.0001000000 | Loss 0.078356 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:25 Epoch 6 | Batch 484/2891 | Timestep 17830 | LR 0.0001000000 | Loss 0.133985 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:27 Epoch 6 | Batch 494/2891 | Timestep 17840 | LR 0.0001000000 | Loss 0.034555 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:28 Epoch 6 | Batch 504/2891 | Timestep 17850 | LR 0.0001000000 | Loss 0.022217 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:30 Epoch 6 | Batch 514/2891 | Timestep 17860 | LR 0.0001000000 | Loss 0.010732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:32 Epoch 6 | Batch 524/2891 | Timestep 17870 | LR 0.0001000000 | Loss 0.063441 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:33 Epoch 6 | Batch 534/2891 | Timestep 17880 | LR 0.0001000000 | Loss 0.026949 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:35 Epoch 6 | Batch 544/2891 | Timestep 17890 | LR 0.0001000000 | Loss 0.003991 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:37 Epoch 6 | Batch 554/2891 | Timestep 17900 | LR 0.0001000000 | Loss 0.014412 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:38 Epoch 6 | Batch 564/2891 | Timestep 17910 | LR 0.0001000000 | Loss 0.005598 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:40 Epoch 6 | Batch 574/2891 | Timestep 17920 | LR 0.0001000000 | Loss 0.027026 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:41 Epoch 6 | Batch 584/2891 | Timestep 17930 | LR 0.0001000000 | Loss 0.017009 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:43 Epoch 6 | Batch 594/2891 | Timestep 17940 | LR 0.0001000000 | Loss 0.007020 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:45 Epoch 6 | Batch 604/2891 | Timestep 17950 | LR 0.0001000000 | Loss 0.001527 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:46 Epoch 6 | Batch 614/2891 | Timestep 17960 | LR 0.0001000000 | Loss 0.001814 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:48 Epoch 6 | Batch 624/2891 | Timestep 17970 | LR 0.0001000000 | Loss 0.036688 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:50 Epoch 6 | Batch 634/2891 | Timestep 17980 | LR 0.0001000000 | Loss 0.002982 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:51 Epoch 6 | Batch 644/2891 | Timestep 17990 | LR 0.0001000000 | Loss 0.054714 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:53 Epoch 6 | Batch 654/2891 | Timestep 18000 | LR 0.0001000000 | Loss 0.011883 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:55 Epoch 6 | Batch 664/2891 | Timestep 18010 | LR 0.0001000000 | Loss 0.010882 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:57 Epoch 6 | Batch 674/2891 | Timestep 18020 | LR 0.0001000000 | Loss 0.016454 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:43:58 Epoch 6 | Batch 684/2891 | Timestep 18030 | LR 0.0001000000 | Loss 0.006118 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:00 Epoch 6 | Batch 694/2891 | Timestep 18040 | LR 0.0001000000 | Loss 0.003358 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:02 Epoch 6 | Batch 704/2891 | Timestep 18050 | LR 0.0001000000 | Loss 0.011261 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:03 Epoch 6 | Batch 714/2891 | Timestep 18060 | LR 0.0001000000 | Loss 0.029906 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:05 Epoch 6 | Batch 724/2891 | Timestep 18070 | LR 0.0001000000 | Loss 0.004724 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:07 Epoch 6 | Batch 734/2891 | Timestep 18080 | LR 0.0001000000 | Loss 0.011306 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:08 Epoch 6 | Batch 744/2891 | Timestep 18090 | LR 0.0001000000 | Loss 0.022821 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:10 Epoch 6 | Batch 754/2891 | Timestep 18100 | LR 0.0001000000 | Loss 0.010813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:12 Epoch 6 | Batch 764/2891 | Timestep 18110 | LR 0.0001000000 | Loss 0.015947 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:14 Epoch 6 | Batch 774/2891 | Timestep 18120 | LR 0.0001000000 | Loss 0.119930 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:16 Epoch 6 | Batch 784/2891 | Timestep 18130 | LR 0.0001000000 | Loss 0.009143 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:17 Epoch 6 | Batch 794/2891 | Timestep 18140 | LR 0.0001000000 | Loss 0.002406 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:19 Epoch 6 | Batch 804/2891 | Timestep 18150 | LR 0.0001000000 | Loss 0.079496 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:21 Epoch 6 | Batch 814/2891 | Timestep 18160 | LR 0.0001000000 | Loss 0.001129 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:22 Epoch 6 | Batch 824/2891 | Timestep 18170 | LR 0.0001000000 | Loss 0.016501 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:24 Epoch 6 | Batch 834/2891 | Timestep 18180 | LR 0.0001000000 | Loss 0.008860 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:26 Epoch 6 | Batch 844/2891 | Timestep 18190 | LR 0.0001000000 | Loss 0.003340 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:28 Epoch 6 | Batch 854/2891 | Timestep 18200 | LR 0.0001000000 | Loss 0.005139 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:29 Epoch 6 | Batch 864/2891 | Timestep 18210 | LR 0.0001000000 | Loss 0.000629 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:31 Epoch 6 | Batch 874/2891 | Timestep 18220 | LR 0.0001000000 | Loss 0.068055 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:33 Epoch 6 | Batch 884/2891 | Timestep 18230 | LR 0.0001000000 | Loss 0.014829 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:34 Epoch 6 | Batch 894/2891 | Timestep 18240 | LR 0.0001000000 | Loss 0.013001 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:36 Epoch 6 | Batch 904/2891 | Timestep 18250 | LR 0.0001000000 | Loss 0.016982 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:38 Epoch 6 | Batch 914/2891 | Timestep 18260 | LR 0.0001000000 | Loss 0.002093 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:39 Epoch 6 | Batch 924/2891 | Timestep 18270 | LR 0.0001000000 | Loss 0.011750 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:41 Epoch 6 | Batch 934/2891 | Timestep 18280 | LR 0.0001000000 | Loss 0.033519 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:42 Epoch 6 | Batch 944/2891 | Timestep 18290 | LR 0.0001000000 | Loss 0.001037 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:44 Epoch 6 | Batch 954/2891 | Timestep 18300 | LR 0.0001000000 | Loss 0.009811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:46 Epoch 6 | Batch 964/2891 | Timestep 18310 | LR 0.0001000000 | Loss 0.005312 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:47 Epoch 6 | Batch 974/2891 | Timestep 18320 | LR 0.0001000000 | Loss 0.022486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:49 Epoch 6 | Batch 984/2891 | Timestep 18330 | LR 0.0001000000 | Loss 0.015997 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:51 Epoch 6 | Batch 994/2891 | Timestep 18340 | LR 0.0001000000 | Loss 0.000090 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:52 Epoch 6 | Batch 1004/2891 | Timestep 18350 | LR 0.0001000000 | Loss 0.178030 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:54 Epoch 6 | Batch 1014/2891 | Timestep 18360 | LR 0.0001000000 | Loss 0.015788 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:56 Epoch 6 | Batch 1024/2891 | Timestep 18370 | LR 0.0001000000 | Loss 0.017416 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:58 Epoch 6 | Batch 1034/2891 | Timestep 18380 | LR 0.0001000000 | Loss 0.037564 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:44:59 Epoch 6 | Batch 1044/2891 | Timestep 18390 | LR 0.0001000000 | Loss 0.001755 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:01 Epoch 6 | Batch 1054/2891 | Timestep 18400 | LR 0.0001000000 | Loss 0.036006 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:03 Epoch 6 | Batch 1064/2891 | Timestep 18410 | LR 0.0001000000 | Loss 0.003713 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:04 Epoch 6 | Batch 1074/2891 | Timestep 18420 | LR 0.0001000000 | Loss 0.001580 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:06 Epoch 6 | Batch 1084/2891 | Timestep 18430 | LR 0.0001000000 | Loss 0.009195 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:08 Epoch 6 | Batch 1094/2891 | Timestep 18440 | LR 0.0001000000 | Loss 0.052970 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:10 Epoch 6 | Batch 1104/2891 | Timestep 18450 | LR 0.0001000000 | Loss 0.005441 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:11 Epoch 6 | Batch 1114/2891 | Timestep 18460 | LR 0.0001000000 | Loss 0.018469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:13 Epoch 6 | Batch 1124/2891 | Timestep 18470 | LR 0.0001000000 | Loss 0.001947 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:15 Epoch 6 | Batch 1134/2891 | Timestep 18480 | LR 0.0001000000 | Loss 0.052441 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:17 Epoch 6 | Batch 1144/2891 | Timestep 18490 | LR 0.0001000000 | Loss 0.020457 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:18 Epoch 6 | Batch 1154/2891 | Timestep 18500 | LR 0.0001000000 | Loss 0.016589 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:20 Epoch 6 | Batch 1164/2891 | Timestep 18510 | LR 0.0001000000 | Loss 0.005036 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:22 Epoch 6 | Batch 1174/2891 | Timestep 18520 | LR 0.0001000000 | Loss 0.011893 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:24 Epoch 6 | Batch 1184/2891 | Timestep 18530 | LR 0.0001000000 | Loss 0.008996 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:26 Epoch 6 | Batch 1194/2891 | Timestep 18540 | LR 0.0001000000 | Loss 0.005264 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:28 Epoch 6 | Batch 1204/2891 | Timestep 18550 | LR 0.0001000000 | Loss 0.016921 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:29 Epoch 6 | Batch 1214/2891 | Timestep 18560 | LR 0.0001000000 | Loss 0.057079 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:31 Epoch 6 | Batch 1224/2891 | Timestep 18570 | LR 0.0001000000 | Loss 0.010544 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:33 Epoch 6 | Batch 1234/2891 | Timestep 18580 | LR 0.0001000000 | Loss 0.018877 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:35 Epoch 6 | Batch 1244/2891 | Timestep 18590 | LR 0.0001000000 | Loss 0.101645 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:36 Epoch 6 | Batch 1254/2891 | Timestep 18600 | LR 0.0001000000 | Loss 0.061500 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:38 Epoch 6 | Batch 1264/2891 | Timestep 18610 | LR 0.0001000000 | Loss 0.002941 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:40 Epoch 6 | Batch 1274/2891 | Timestep 18620 | LR 0.0001000000 | Loss 0.026473 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:42 Epoch 6 | Batch 1284/2891 | Timestep 18630 | LR 0.0001000000 | Loss 0.003481 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:43 Epoch 6 | Batch 1294/2891 | Timestep 18640 | LR 0.0001000000 | Loss 0.000510 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:45 Epoch 6 | Batch 1304/2891 | Timestep 18650 | LR 0.0001000000 | Loss 0.038679 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:47 Epoch 6 | Batch 1314/2891 | Timestep 18660 | LR 0.0001000000 | Loss 0.011522 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:49 Epoch 6 | Batch 1324/2891 | Timestep 18670 | LR 0.0001000000 | Loss 0.020407 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:50 Epoch 6 | Batch 1334/2891 | Timestep 18680 | LR 0.0001000000 | Loss 0.020899 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:52 Epoch 6 | Batch 1344/2891 | Timestep 18690 | LR 0.0001000000 | Loss 0.003325 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:54 Epoch 6 | Batch 1354/2891 | Timestep 18700 | LR 0.0001000000 | Loss 0.063930 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:56 Epoch 6 | Batch 1364/2891 | Timestep 18710 | LR 0.0001000000 | Loss 0.059746 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:57 Epoch 6 | Batch 1374/2891 | Timestep 18720 | LR 0.0001000000 | Loss 0.016472 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:45:59 Epoch 6 | Batch 1384/2891 | Timestep 18730 | LR 0.0001000000 | Loss 0.000880 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:01 Epoch 6 | Batch 1394/2891 | Timestep 18740 | LR 0.0001000000 | Loss 0.012674 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:02 Epoch 6 | Batch 1404/2891 | Timestep 18750 | LR 0.0001000000 | Loss 0.010537 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:04 Epoch 6 | Batch 1414/2891 | Timestep 18760 | LR 0.0001000000 | Loss 0.009163 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:06 Epoch 6 | Batch 1424/2891 | Timestep 18770 | LR 0.0001000000 | Loss 0.017963 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:08 Epoch 6 | Batch 1434/2891 | Timestep 18780 | LR 0.0001000000 | Loss 0.011173 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:10 Epoch 6 | Batch 1444/2891 | Timestep 18790 | LR 0.0001000000 | Loss 0.001167 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:11 Epoch 6 | Batch 1454/2891 | Timestep 18800 | LR 0.0001000000 | Loss 0.002828 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:14 Epoch 6 | Batch 1464/2891 | Timestep 18810 | LR 0.0001000000 | Loss 0.017530 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:16 Epoch 6 | Batch 1474/2891 | Timestep 18820 | LR 0.0001000000 | Loss 0.005797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:17 Epoch 6 | Batch 1484/2891 | Timestep 18830 | LR 0.0001000000 | Loss 0.040614 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:19 Epoch 6 | Batch 1494/2891 | Timestep 18840 | LR 0.0001000000 | Loss 0.030161 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:21 Epoch 6 | Batch 1504/2891 | Timestep 18850 | LR 0.0001000000 | Loss 0.016599 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:23 Epoch 6 | Batch 1514/2891 | Timestep 18860 | LR 0.0001000000 | Loss 0.021460 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:24 Epoch 6 | Batch 1524/2891 | Timestep 18870 | LR 0.0001000000 | Loss 0.024804 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:26 Epoch 6 | Batch 1534/2891 | Timestep 18880 | LR 0.0001000000 | Loss 0.194340 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:28 Epoch 6 | Batch 1544/2891 | Timestep 18890 | LR 0.0001000000 | Loss 0.019956 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:29 Epoch 6 | Batch 1554/2891 | Timestep 18900 | LR 0.0001000000 | Loss 0.004276 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:31 Epoch 6 | Batch 1564/2891 | Timestep 18910 | LR 0.0001000000 | Loss 0.047782 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:33 Epoch 6 | Batch 1574/2891 | Timestep 18920 | LR 0.0001000000 | Loss 0.105235 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:35 Epoch 6 | Batch 1584/2891 | Timestep 18930 | LR 0.0001000000 | Loss 0.018526 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:36 Epoch 6 | Batch 1594/2891 | Timestep 18940 | LR 0.0001000000 | Loss 0.007658 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:38 Epoch 6 | Batch 1604/2891 | Timestep 18950 | LR 0.0001000000 | Loss 0.021111 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:40 Epoch 6 | Batch 1614/2891 | Timestep 18960 | LR 0.0001000000 | Loss 0.015194 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:42 Epoch 6 | Batch 1624/2891 | Timestep 18970 | LR 0.0001000000 | Loss 0.013588 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:43 Epoch 6 | Batch 1634/2891 | Timestep 18980 | LR 0.0001000000 | Loss 0.039619 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:45 Epoch 6 | Batch 1644/2891 | Timestep 18990 | LR 0.0001000000 | Loss 0.008809 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:47 Epoch 6 | Batch 1654/2891 | Timestep 19000 | LR 0.0001000000 | Loss 0.019493 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:48 Epoch 6 | Batch 1664/2891 | Timestep 19010 | LR 0.0001000000 | Loss 0.002493 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:50 Epoch 6 | Batch 1674/2891 | Timestep 19020 | LR 0.0001000000 | Loss 0.009715 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:51 Epoch 6 | Batch 1684/2891 | Timestep 19030 | LR 0.0001000000 | Loss 0.030626 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:53 Epoch 6 | Batch 1694/2891 | Timestep 19040 | LR 0.0001000000 | Loss 0.002578 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:55 Epoch 6 | Batch 1704/2891 | Timestep 19050 | LR 0.0001000000 | Loss 0.002125 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:57 Epoch 6 | Batch 1714/2891 | Timestep 19060 | LR 0.0001000000 | Loss 0.028598 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:46:59 Epoch 6 | Batch 1724/2891 | Timestep 19070 | LR 0.0001000000 | Loss 0.004494 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:00 Epoch 6 | Batch 1734/2891 | Timestep 19080 | LR 0.0001000000 | Loss 0.004811 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:02 Epoch 6 | Batch 1744/2891 | Timestep 19090 | LR 0.0001000000 | Loss 0.006089 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:04 Epoch 6 | Batch 1754/2891 | Timestep 19100 | LR 0.0001000000 | Loss 0.004860 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:06 Epoch 6 | Batch 1764/2891 | Timestep 19110 | LR 0.0001000000 | Loss 0.079127 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:07 Epoch 6 | Batch 1774/2891 | Timestep 19120 | LR 0.0001000000 | Loss 0.012009 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:09 Epoch 6 | Batch 1784/2891 | Timestep 19130 | LR 0.0001000000 | Loss 0.050568 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:10 Epoch 6 | Batch 1794/2891 | Timestep 19140 | LR 0.0001000000 | Loss 0.051145 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:12 Epoch 6 | Batch 1804/2891 | Timestep 19150 | LR 0.0001000000 | Loss 0.026333 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:14 Epoch 6 | Batch 1814/2891 | Timestep 19160 | LR 0.0001000000 | Loss 0.050981 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:16 Epoch 6 | Batch 1824/2891 | Timestep 19170 | LR 0.0001000000 | Loss 0.023540 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:17 Epoch 6 | Batch 1834/2891 | Timestep 19180 | LR 0.0001000000 | Loss 0.034594 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:19 Epoch 6 | Batch 1844/2891 | Timestep 19190 | LR 0.0001000000 | Loss 0.004017 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:20 Epoch 6 | Batch 1854/2891 | Timestep 19200 | LR 0.0001000000 | Loss 0.018302 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:22 Epoch 6 | Batch 1864/2891 | Timestep 19210 | LR 0.0001000000 | Loss 0.047081 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:24 Epoch 6 | Batch 1874/2891 | Timestep 19220 | LR 0.0001000000 | Loss 0.033509 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:26 Epoch 6 | Batch 1884/2891 | Timestep 19230 | LR 0.0001000000 | Loss 0.016724 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:28 Epoch 6 | Batch 1894/2891 | Timestep 19240 | LR 0.0001000000 | Loss 0.012996 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:30 Epoch 6 | Batch 1904/2891 | Timestep 19250 | LR 0.0001000000 | Loss 0.006198 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:32 Epoch 6 | Batch 1914/2891 | Timestep 19260 | LR 0.0001000000 | Loss 0.010278 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:33 Epoch 6 | Batch 1924/2891 | Timestep 19270 | LR 0.0001000000 | Loss 0.033685 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:34 Epoch 6 | Batch 1934/2891 | Timestep 19280 | LR 0.0001000000 | Loss 0.050449 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:36 Epoch 6 | Batch 1944/2891 | Timestep 19290 | LR 0.0001000000 | Loss 0.041696 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:38 Epoch 6 | Batch 1954/2891 | Timestep 19300 | LR 0.0001000000 | Loss 0.062420 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:40 Epoch 6 | Batch 1964/2891 | Timestep 19310 | LR 0.0001000000 | Loss 0.010409 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:42 Epoch 6 | Batch 1974/2891 | Timestep 19320 | LR 0.0001000000 | Loss 0.002112 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:44 Epoch 6 | Batch 1984/2891 | Timestep 19330 | LR 0.0001000000 | Loss 0.031927 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:46 Epoch 6 | Batch 1994/2891 | Timestep 19340 | LR 0.0001000000 | Loss 0.009894 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:47 Epoch 6 | Batch 2004/2891 | Timestep 19350 | LR 0.0001000000 | Loss 0.013087 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:49 Epoch 6 | Batch 2014/2891 | Timestep 19360 | LR 0.0001000000 | Loss 0.009432 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:51 Epoch 6 | Batch 2024/2891 | Timestep 19370 | LR 0.0001000000 | Loss 0.002333 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:52 Epoch 6 | Batch 2034/2891 | Timestep 19380 | LR 0.0001000000 | Loss 0.005915 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:55 Epoch 6 | Batch 2044/2891 | Timestep 19390 | LR 0.0001000000 | Loss 0.013576 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:56 Epoch 6 | Batch 2054/2891 | Timestep 19400 | LR 0.0001000000 | Loss 0.018299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:47:58 Epoch 6 | Batch 2064/2891 | Timestep 19410 | LR 0.0001000000 | Loss 0.017511 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:00 Epoch 6 | Batch 2074/2891 | Timestep 19420 | LR 0.0001000000 | Loss 0.005791 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:02 Epoch 6 | Batch 2084/2891 | Timestep 19430 | LR 0.0001000000 | Loss 0.063418 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:03 Epoch 6 | Batch 2094/2891 | Timestep 19440 | LR 0.0001000000 | Loss 0.015789 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:05 Epoch 6 | Batch 2104/2891 | Timestep 19450 | LR 0.0001000000 | Loss 0.033400 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:07 Epoch 6 | Batch 2114/2891 | Timestep 19460 | LR 0.0001000000 | Loss 0.014362 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:09 Epoch 6 | Batch 2124/2891 | Timestep 19470 | LR 0.0001000000 | Loss 0.013386 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:10 Epoch 6 | Batch 2134/2891 | Timestep 19480 | LR 0.0001000000 | Loss 0.014609 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:12 Epoch 6 | Batch 2144/2891 | Timestep 19490 | LR 0.0001000000 | Loss 0.008996 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:13 Epoch 6 | Batch 2154/2891 | Timestep 19500 | LR 0.0001000000 | Loss 0.006575 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:15 Epoch 6 | Batch 2164/2891 | Timestep 19510 | LR 0.0001000000 | Loss 0.018261 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:17 Epoch 6 | Batch 2174/2891 | Timestep 19520 | LR 0.0001000000 | Loss 0.041102 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:18 Epoch 6 | Batch 2184/2891 | Timestep 19530 | LR 0.0001000000 | Loss 0.006052 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:20 Epoch 6 | Batch 2194/2891 | Timestep 19540 | LR 0.0001000000 | Loss 0.049847 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:21 Epoch 6 | Batch 2204/2891 | Timestep 19550 | LR 0.0001000000 | Loss 0.002452 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:23 Epoch 6 | Batch 2214/2891 | Timestep 19560 | LR 0.0001000000 | Loss 0.044418 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:25 Epoch 6 | Batch 2224/2891 | Timestep 19570 | LR 0.0001000000 | Loss 0.024131 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:27 Epoch 6 | Batch 2234/2891 | Timestep 19580 | LR 0.0001000000 | Loss 0.029304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:28 Epoch 6 | Batch 2244/2891 | Timestep 19590 | LR 0.0001000000 | Loss 0.005921 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:30 Epoch 6 | Batch 2254/2891 | Timestep 19600 | LR 0.0001000000 | Loss 0.032077 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:32 Epoch 6 | Batch 2264/2891 | Timestep 19610 | LR 0.0001000000 | Loss 0.021343 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:33 Epoch 6 | Batch 2274/2891 | Timestep 19620 | LR 0.0001000000 | Loss 0.021949 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:35 Epoch 6 | Batch 2284/2891 | Timestep 19630 | LR 0.0001000000 | Loss 0.012090 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:36 Epoch 6 | Batch 2294/2891 | Timestep 19640 | LR 0.0001000000 | Loss 0.007974 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:38 Epoch 6 | Batch 2304/2891 | Timestep 19650 | LR 0.0001000000 | Loss 0.018865 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:40 Epoch 6 | Batch 2314/2891 | Timestep 19660 | LR 0.0001000000 | Loss 0.002499 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:42 Epoch 6 | Batch 2324/2891 | Timestep 19670 | LR 0.0001000000 | Loss 0.000976 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:44 Epoch 6 | Batch 2334/2891 | Timestep 19680 | LR 0.0001000000 | Loss 0.012352 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:46 Epoch 6 | Batch 2344/2891 | Timestep 19690 | LR 0.0001000000 | Loss 0.001833 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:48 Epoch 6 | Batch 2354/2891 | Timestep 19700 | LR 0.0001000000 | Loss 0.042359 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:49 Epoch 6 | Batch 2364/2891 | Timestep 19710 | LR 0.0001000000 | Loss 0.144502 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:51 Epoch 6 | Batch 2374/2891 | Timestep 19720 | LR 0.0001000000 | Loss 0.009299 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:52 Epoch 6 | Batch 2384/2891 | Timestep 19730 | LR 0.0001000000 | Loss 0.010745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:54 Epoch 6 | Batch 2394/2891 | Timestep 19740 | LR 0.0001000000 | Loss 0.011189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:56 Epoch 6 | Batch 2404/2891 | Timestep 19750 | LR 0.0001000000 | Loss 0.006414 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:58 Epoch 6 | Batch 2414/2891 | Timestep 19760 | LR 0.0001000000 | Loss 0.044443 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:48:59 Epoch 6 | Batch 2424/2891 | Timestep 19770 | LR 0.0001000000 | Loss 0.048195 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:01 Epoch 6 | Batch 2434/2891 | Timestep 19780 | LR 0.0001000000 | Loss 0.002345 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:03 Epoch 6 | Batch 2444/2891 | Timestep 19790 | LR 0.0001000000 | Loss 0.021893 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:05 Epoch 6 | Batch 2454/2891 | Timestep 19800 | LR 0.0001000000 | Loss 0.005924 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:06 Epoch 6 | Batch 2464/2891 | Timestep 19810 | LR 0.0001000000 | Loss 0.030827 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:08 Epoch 6 | Batch 2474/2891 | Timestep 19820 | LR 0.0001000000 | Loss 0.014434 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:10 Epoch 6 | Batch 2484/2891 | Timestep 19830 | LR 0.0001000000 | Loss 0.032313 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:12 Epoch 6 | Batch 2494/2891 | Timestep 19840 | LR 0.0001000000 | Loss 0.009264 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:13 Epoch 6 | Batch 2504/2891 | Timestep 19850 | LR 0.0001000000 | Loss 0.001736 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:15 Epoch 6 | Batch 2514/2891 | Timestep 19860 | LR 0.0001000000 | Loss 0.005974 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:17 Epoch 6 | Batch 2524/2891 | Timestep 19870 | LR 0.0001000000 | Loss 0.018369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:18 Epoch 6 | Batch 2534/2891 | Timestep 19880 | LR 0.0001000000 | Loss 0.001241 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:20 Epoch 6 | Batch 2544/2891 | Timestep 19890 | LR 0.0001000000 | Loss 0.015055 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:21 Epoch 6 | Batch 2554/2891 | Timestep 19900 | LR 0.0001000000 | Loss 0.043281 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:23 Epoch 6 | Batch 2564/2891 | Timestep 19910 | LR 0.0001000000 | Loss 0.030535 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:25 Epoch 6 | Batch 2574/2891 | Timestep 19920 | LR 0.0001000000 | Loss 0.014616 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:27 Epoch 6 | Batch 2584/2891 | Timestep 19930 | LR 0.0001000000 | Loss 0.039743 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:29 Epoch 6 | Batch 2594/2891 | Timestep 19940 | LR 0.0001000000 | Loss 0.012603 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:30 Epoch 6 | Batch 2604/2891 | Timestep 19950 | LR 0.0001000000 | Loss 0.067184 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:32 Epoch 6 | Batch 2614/2891 | Timestep 19960 | LR 0.0001000000 | Loss 0.002095 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:33 Epoch 6 | Batch 2624/2891 | Timestep 19970 | LR 0.0001000000 | Loss 0.021881 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:35 Epoch 6 | Batch 2634/2891 | Timestep 19980 | LR 0.0001000000 | Loss 0.038392 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:37 Epoch 6 | Batch 2644/2891 | Timestep 19990 | LR 0.0001000000 | Loss 0.008537 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:38 Epoch 6 | Batch 2654/2891 | Timestep 20000 | LR 0.0001000000 | Loss 0.055990 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:40 Epoch 6 | Batch 2664/2891 | Timestep 20010 | LR 0.0001000000 | Loss 0.028410 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:42 Epoch 6 | Batch 2674/2891 | Timestep 20020 | LR 0.0001000000 | Loss 0.027576 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:43 Epoch 6 | Batch 2684/2891 | Timestep 20030 | LR 0.0001000000 | Loss 0.002573 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:46 Epoch 6 | Batch 2694/2891 | Timestep 20040 | LR 0.0001000000 | Loss 0.013269 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:47 Epoch 6 | Batch 2704/2891 | Timestep 20050 | LR 0.0001000000 | Loss 0.077234 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:49 Epoch 6 | Batch 2714/2891 | Timestep 20060 | LR 0.0001000000 | Loss 0.014046 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:50 Epoch 6 | Batch 2724/2891 | Timestep 20070 | LR 0.0001000000 | Loss 0.006007 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:52 Epoch 6 | Batch 2734/2891 | Timestep 20080 | LR 0.0001000000 | Loss 0.022172 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:54 Epoch 6 | Batch 2744/2891 | Timestep 20090 | LR 0.0001000000 | Loss 0.021787 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:56 Epoch 6 | Batch 2754/2891 | Timestep 20100 | LR 0.0001000000 | Loss 0.008741 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:49:58 Epoch 6 | Batch 2764/2891 | Timestep 20110 | LR 0.0001000000 | Loss 0.069096 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:00 Epoch 6 | Batch 2774/2891 | Timestep 20120 | LR 0.0001000000 | Loss 0.045904 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:02 Epoch 6 | Batch 2784/2891 | Timestep 20130 | LR 0.0001000000 | Loss 0.005528 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:03 Epoch 6 | Batch 2794/2891 | Timestep 20140 | LR 0.0001000000 | Loss 0.022080 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:05 Epoch 6 | Batch 2804/2891 | Timestep 20150 | LR 0.0001000000 | Loss 0.036349 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:07 Epoch 6 | Batch 2814/2891 | Timestep 20160 | LR 0.0001000000 | Loss 0.002179 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:08 Epoch 6 | Batch 2824/2891 | Timestep 20170 | LR 0.0001000000 | Loss 0.021639 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:10 Epoch 6 | Batch 2834/2891 | Timestep 20180 | LR 0.0001000000 | Loss 0.039729 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:12 Epoch 6 | Batch 2844/2891 | Timestep 20190 | LR 0.0001000000 | Loss 0.014020 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:15 Epoch 6 | Batch 2854/2891 | Timestep 20200 | LR 0.0001000000 | Loss 0.018198 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:17 Epoch 6 | Batch 2864/2891 | Timestep 20210 | LR 0.0001000000 | Loss 0.030574 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:18 Epoch 6 | Batch 2874/2891 | Timestep 20220 | LR 0.0001000000 | Loss 0.039950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:20 Epoch 6 | Batch 2884/2891 | Timestep 20230 | LR 0.0001000000 | Loss 0.022763 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:50:21 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 10:50:57 precision recall f1-score support CARDINAL 0.6862 0.7588 0.7207 170 CURR 0.9130 0.8750 0.8936 24 DATE 0.9428 0.9361 0.9395 1691 EVENT 0.7578 0.5788 0.6563 292 FAC 0.6984 0.7458 0.7213 118 GPE 0.9579 0.9601 0.9590 2156 LANGUAGE 1.0000 0.6250 0.7692 16 LAW 0.7069 0.8723 0.7810 47 LOC 0.6083 0.8111 0.6952 90 MONEY 0.7391 0.7727 0.7556 22 NORP 0.6784 0.7005 0.6893 551 OCC 0.8549 0.8467 0.8508 522 ORDINAL 0.9485 0.8805 0.9133 544 ORG 0.8844 0.9267 0.9050 1882 PERCENT 0.9167 0.9167 0.9167 12 PERS 0.9310 0.9146 0.9227 679 PRODUCT 0.5000 0.5000 0.5000 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.6222 0.8485 0.7179 33 UNIT 1.0000 0.2500 0.4000 4 WEBSITE 0.4048 0.6375 0.4951 80 micro avg 0.8820 0.8911 0.8865 8944 macro avg 0.7818 0.7631 0.7557 8944 weighted avg 0.8865 0.8911 0.8875 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:08 Epoch 6 | Timestep 20237 | Train Loss 0.027414 | Val Loss 0.067766 | F1 0.886541 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:08 Epoch 7 | Batch 3/2891 | Timestep 20240 | LR 0.0001000000 | Loss 0.005022 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:10 Epoch 7 | Batch 13/2891 | Timestep 20250 | LR 0.0001000000 | Loss 0.025357 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:12 Epoch 7 | Batch 23/2891 | Timestep 20260 | LR 0.0001000000 | Loss 0.002615 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:13 Epoch 7 | Batch 33/2891 | Timestep 20270 | LR 0.0001000000 | Loss 0.041234 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:15 Epoch 7 | Batch 43/2891 | Timestep 20280 | LR 0.0001000000 | Loss 0.000697 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:16 Epoch 7 | Batch 53/2891 | Timestep 20290 | LR 0.0001000000 | Loss 0.003831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:18 Epoch 7 | Batch 63/2891 | Timestep 20300 | LR 0.0001000000 | Loss 0.013660 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:20 Epoch 7 | Batch 73/2891 | Timestep 20310 | LR 0.0001000000 | Loss 0.056452 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:22 Epoch 7 | Batch 83/2891 | Timestep 20320 | LR 0.0001000000 | Loss 0.033181 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:24 Epoch 7 | Batch 93/2891 | Timestep 20330 | LR 0.0001000000 | Loss 0.019897 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:25 Epoch 7 | Batch 103/2891 | Timestep 20340 | LR 0.0001000000 | Loss 0.067540 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:27 Epoch 7 | Batch 113/2891 | Timestep 20350 | LR 0.0001000000 | Loss 0.003621 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:29 Epoch 7 | Batch 123/2891 | Timestep 20360 | LR 0.0001000000 | Loss 0.053575 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:31 Epoch 7 | Batch 133/2891 | Timestep 20370 | LR 0.0001000000 | Loss 0.031490 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:32 Epoch 7 | Batch 143/2891 | Timestep 20380 | LR 0.0001000000 | Loss 0.024674 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:34 Epoch 7 | Batch 153/2891 | Timestep 20390 | LR 0.0001000000 | Loss 0.080081 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:36 Epoch 7 | Batch 163/2891 | Timestep 20400 | LR 0.0001000000 | Loss 0.213099 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:37 Epoch 7 | Batch 173/2891 | Timestep 20410 | LR 0.0001000000 | Loss 0.140578 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:39 Epoch 7 | Batch 183/2891 | Timestep 20420 | LR 0.0001000000 | Loss 0.052144 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:40 Epoch 7 | Batch 193/2891 | Timestep 20430 | LR 0.0001000000 | Loss 0.032055 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:42 Epoch 7 | Batch 203/2891 | Timestep 20440 | LR 0.0001000000 | Loss 0.010394 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:43 Epoch 7 | Batch 213/2891 | Timestep 20450 | LR 0.0001000000 | Loss 0.044064 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:45 Epoch 7 | Batch 223/2891 | Timestep 20460 | LR 0.0001000000 | Loss 0.054136 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:47 Epoch 7 | Batch 233/2891 | Timestep 20470 | LR 0.0001000000 | Loss 0.032100 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:48 Epoch 7 | Batch 243/2891 | Timestep 20480 | LR 0.0001000000 | Loss 0.069885 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:50 Epoch 7 | Batch 253/2891 | Timestep 20490 | LR 0.0001000000 | Loss 0.018884 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:52 Epoch 7 | Batch 263/2891 | Timestep 20500 | LR 0.0001000000 | Loss 0.114820 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:54 Epoch 7 | Batch 273/2891 | Timestep 20510 | LR 0.0001000000 | Loss 0.057713 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:55 Epoch 7 | Batch 283/2891 | Timestep 20520 | LR 0.0001000000 | Loss 0.012748 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:57 Epoch 7 | Batch 293/2891 | Timestep 20530 | LR 0.0001000000 | Loss 0.040360 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:51:58 Epoch 7 | Batch 303/2891 | Timestep 20540 | LR 0.0001000000 | Loss 0.084345 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:00 Epoch 7 | Batch 313/2891 | Timestep 20550 | LR 0.0001000000 | Loss 0.047596 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:02 Epoch 7 | Batch 323/2891 | Timestep 20560 | LR 0.0001000000 | Loss 0.015813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:03 Epoch 7 | Batch 333/2891 | Timestep 20570 | LR 0.0001000000 | Loss 0.002686 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:05 Epoch 7 | Batch 343/2891 | Timestep 20580 | LR 0.0001000000 | Loss 0.019110 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:07 Epoch 7 | Batch 353/2891 | Timestep 20590 | LR 0.0001000000 | Loss 0.019757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:09 Epoch 7 | Batch 363/2891 | Timestep 20600 | LR 0.0001000000 | Loss 0.048034 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:10 Epoch 7 | Batch 373/2891 | Timestep 20610 | LR 0.0001000000 | Loss 0.036312 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:12 Epoch 7 | Batch 383/2891 | Timestep 20620 | LR 0.0001000000 | Loss 0.008368 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:13 Epoch 7 | Batch 393/2891 | Timestep 20630 | LR 0.0001000000 | Loss 0.013792 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:15 Epoch 7 | Batch 403/2891 | Timestep 20640 | LR 0.0001000000 | Loss 0.031169 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:16 Epoch 7 | Batch 413/2891 | Timestep 20650 | LR 0.0001000000 | Loss 0.038465 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:18 Epoch 7 | Batch 423/2891 | Timestep 20660 | LR 0.0001000000 | Loss 0.000896 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:20 Epoch 7 | Batch 433/2891 | Timestep 20670 | LR 0.0001000000 | Loss 0.017319 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:22 Epoch 7 | Batch 443/2891 | Timestep 20680 | LR 0.0001000000 | Loss 0.085412 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:23 Epoch 7 | Batch 453/2891 | Timestep 20690 | LR 0.0001000000 | Loss 0.015190 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:25 Epoch 7 | Batch 463/2891 | Timestep 20700 | LR 0.0001000000 | Loss 0.033906 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:27 Epoch 7 | Batch 473/2891 | Timestep 20710 | LR 0.0001000000 | Loss 0.019649 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:28 Epoch 7 | Batch 483/2891 | Timestep 20720 | LR 0.0001000000 | Loss 0.004459 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:30 Epoch 7 | Batch 493/2891 | Timestep 20730 | LR 0.0001000000 | Loss 0.030744 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:32 Epoch 7 | Batch 503/2891 | Timestep 20740 | LR 0.0001000000 | Loss 0.079237 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:33 Epoch 7 | Batch 513/2891 | Timestep 20750 | LR 0.0001000000 | Loss 0.013804 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:36 Epoch 7 | Batch 523/2891 | Timestep 20760 | LR 0.0001000000 | Loss 0.023671 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:38 Epoch 7 | Batch 533/2891 | Timestep 20770 | LR 0.0001000000 | Loss 0.044834 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:40 Epoch 7 | Batch 543/2891 | Timestep 20780 | LR 0.0001000000 | Loss 0.018004 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:41 Epoch 7 | Batch 553/2891 | Timestep 20790 | LR 0.0001000000 | Loss 0.009919 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:43 Epoch 7 | Batch 563/2891 | Timestep 20800 | LR 0.0001000000 | Loss 0.013609 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:45 Epoch 7 | Batch 573/2891 | Timestep 20810 | LR 0.0001000000 | Loss 0.065742 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:47 Epoch 7 | Batch 583/2891 | Timestep 20820 | LR 0.0001000000 | Loss 0.030523 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:49 Epoch 7 | Batch 593/2891 | Timestep 20830 | LR 0.0001000000 | Loss 0.005935 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:50 Epoch 7 | Batch 603/2891 | Timestep 20840 | LR 0.0001000000 | Loss 0.011240 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:52 Epoch 7 | Batch 613/2891 | Timestep 20850 | LR 0.0001000000 | Loss 0.057672 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:54 Epoch 7 | Batch 623/2891 | Timestep 20860 | LR 0.0001000000 | Loss 0.038020 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:56 Epoch 7 | Batch 633/2891 | Timestep 20870 | LR 0.0001000000 | Loss 0.018267 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:52:58 Epoch 7 | Batch 643/2891 | Timestep 20880 | LR 0.0001000000 | Loss 0.021610 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:00 Epoch 7 | Batch 653/2891 | Timestep 20890 | LR 0.0001000000 | Loss 0.015423 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:02 Epoch 7 | Batch 663/2891 | Timestep 20900 | LR 0.0001000000 | Loss 0.010126 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:03 Epoch 7 | Batch 673/2891 | Timestep 20910 | LR 0.0001000000 | Loss 0.030651 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:05 Epoch 7 | Batch 683/2891 | Timestep 20920 | LR 0.0001000000 | Loss 0.049623 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:06 Epoch 7 | Batch 693/2891 | Timestep 20930 | LR 0.0001000000 | Loss 0.065667 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:08 Epoch 7 | Batch 703/2891 | Timestep 20940 | LR 0.0001000000 | Loss 0.021277 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:10 Epoch 7 | Batch 713/2891 | Timestep 20950 | LR 0.0001000000 | Loss 0.076950 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:11 Epoch 7 | Batch 723/2891 | Timestep 20960 | LR 0.0001000000 | Loss 0.016133 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:13 Epoch 7 | Batch 733/2891 | Timestep 20970 | LR 0.0001000000 | Loss 0.058675 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:15 Epoch 7 | Batch 743/2891 | Timestep 20980 | LR 0.0001000000 | Loss 0.015146 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:17 Epoch 7 | Batch 753/2891 | Timestep 20990 | LR 0.0001000000 | Loss 0.036688 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:18 Epoch 7 | Batch 763/2891 | Timestep 21000 | LR 0.0001000000 | Loss 0.003274 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:20 Epoch 7 | Batch 773/2891 | Timestep 21010 | LR 0.0001000000 | Loss 0.001293 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:22 Epoch 7 | Batch 783/2891 | Timestep 21020 | LR 0.0001000000 | Loss 0.073293 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:24 Epoch 7 | Batch 793/2891 | Timestep 21030 | LR 0.0001000000 | Loss 0.024654 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:26 Epoch 7 | Batch 803/2891 | Timestep 21040 | LR 0.0001000000 | Loss 0.043293 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:28 Epoch 7 | Batch 813/2891 | Timestep 21050 | LR 0.0001000000 | Loss 0.008894 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:29 Epoch 7 | Batch 823/2891 | Timestep 21060 | LR 0.0001000000 | Loss 0.015358 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:31 Epoch 7 | Batch 833/2891 | Timestep 21070 | LR 0.0001000000 | Loss 0.025910 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:33 Epoch 7 | Batch 843/2891 | Timestep 21080 | LR 0.0001000000 | Loss 0.003209 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:34 Epoch 7 | Batch 853/2891 | Timestep 21090 | LR 0.0001000000 | Loss 0.055934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:36 Epoch 7 | Batch 863/2891 | Timestep 21100 | LR 0.0001000000 | Loss 0.055656 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:37 Epoch 7 | Batch 873/2891 | Timestep 21110 | LR 0.0001000000 | Loss 0.010708 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:39 Epoch 7 | Batch 883/2891 | Timestep 21120 | LR 0.0001000000 | Loss 0.040793 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:40 Epoch 7 | Batch 893/2891 | Timestep 21130 | LR 0.0001000000 | Loss 0.010766 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:42 Epoch 7 | Batch 903/2891 | Timestep 21140 | LR 0.0001000000 | Loss 0.004447 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:43 Epoch 7 | Batch 913/2891 | Timestep 21150 | LR 0.0001000000 | Loss 0.047522 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:45 Epoch 7 | Batch 923/2891 | Timestep 21160 | LR 0.0001000000 | Loss 0.001600 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:47 Epoch 7 | Batch 933/2891 | Timestep 21170 | LR 0.0001000000 | Loss 0.007584 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:49 Epoch 7 | Batch 943/2891 | Timestep 21180 | LR 0.0001000000 | Loss 0.004419 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:50 Epoch 7 | Batch 953/2891 | Timestep 21190 | LR 0.0001000000 | Loss 0.020561 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:52 Epoch 7 | Batch 963/2891 | Timestep 21200 | LR 0.0001000000 | Loss 0.061160 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:54 Epoch 7 | Batch 973/2891 | Timestep 21210 | LR 0.0001000000 | Loss 0.009283 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:56 Epoch 7 | Batch 983/2891 | Timestep 21220 | LR 0.0001000000 | Loss 0.013424 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:57 Epoch 7 | Batch 993/2891 | Timestep 21230 | LR 0.0001000000 | Loss 0.039757 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:53:59 Epoch 7 | Batch 1003/2891 | Timestep 21240 | LR 0.0001000000 | Loss 0.033836 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:01 Epoch 7 | Batch 1013/2891 | Timestep 21250 | LR 0.0001000000 | Loss 0.030785 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:02 Epoch 7 | Batch 1023/2891 | Timestep 21260 | LR 0.0001000000 | Loss 0.036006 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:04 Epoch 7 | Batch 1033/2891 | Timestep 21270 | LR 0.0001000000 | Loss 0.035256 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:06 Epoch 7 | Batch 1043/2891 | Timestep 21280 | LR 0.0001000000 | Loss 0.011722 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:07 Epoch 7 | Batch 1053/2891 | Timestep 21290 | LR 0.0001000000 | Loss 0.010674 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:09 Epoch 7 | Batch 1063/2891 | Timestep 21300 | LR 0.0001000000 | Loss 0.027312 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:11 Epoch 7 | Batch 1073/2891 | Timestep 21310 | LR 0.0001000000 | Loss 0.006436 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:12 Epoch 7 | Batch 1083/2891 | Timestep 21320 | LR 0.0001000000 | Loss 0.008365 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:14 Epoch 7 | Batch 1093/2891 | Timestep 21330 | LR 0.0001000000 | Loss 0.006949 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:16 Epoch 7 | Batch 1103/2891 | Timestep 21340 | LR 0.0001000000 | Loss 0.003716 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:18 Epoch 7 | Batch 1113/2891 | Timestep 21350 | LR 0.0001000000 | Loss 0.020140 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:19 Epoch 7 | Batch 1123/2891 | Timestep 21360 | LR 0.0001000000 | Loss 0.037759 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:21 Epoch 7 | Batch 1133/2891 | Timestep 21370 | LR 0.0001000000 | Loss 0.051189 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:23 Epoch 7 | Batch 1143/2891 | Timestep 21380 | LR 0.0001000000 | Loss 0.002288 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:24 Epoch 7 | Batch 1153/2891 | Timestep 21390 | LR 0.0001000000 | Loss 0.011656 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:26 Epoch 7 | Batch 1163/2891 | Timestep 21400 | LR 0.0001000000 | Loss 0.057862 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:28 Epoch 7 | Batch 1173/2891 | Timestep 21410 | LR 0.0001000000 | Loss 0.015605 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:30 Epoch 7 | Batch 1183/2891 | Timestep 21420 | LR 0.0001000000 | Loss 0.000781 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:32 Epoch 7 | Batch 1193/2891 | Timestep 21430 | LR 0.0001000000 | Loss 0.010313 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:34 Epoch 7 | Batch 1203/2891 | Timestep 21440 | LR 0.0001000000 | Loss 0.024992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:35 Epoch 7 | Batch 1213/2891 | Timestep 21450 | LR 0.0001000000 | Loss 0.004326 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:37 Epoch 7 | Batch 1223/2891 | Timestep 21460 | LR 0.0001000000 | Loss 0.003655 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:39 Epoch 7 | Batch 1233/2891 | Timestep 21470 | LR 0.0001000000 | Loss 0.015234 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:41 Epoch 7 | Batch 1243/2891 | Timestep 21480 | LR 0.0001000000 | Loss 0.029822 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:42 Epoch 7 | Batch 1253/2891 | Timestep 21490 | LR 0.0001000000 | Loss 0.001559 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:44 Epoch 7 | Batch 1263/2891 | Timestep 21500 | LR 0.0001000000 | Loss 0.013866 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:46 Epoch 7 | Batch 1273/2891 | Timestep 21510 | LR 0.0001000000 | Loss 0.013151 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:48 Epoch 7 | Batch 1283/2891 | Timestep 21520 | LR 0.0001000000 | Loss 0.008324 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:50 Epoch 7 | Batch 1293/2891 | Timestep 21530 | LR 0.0001000000 | Loss 0.002846 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:52 Epoch 7 | Batch 1303/2891 | Timestep 21540 | LR 0.0001000000 | Loss 0.013176 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:53 Epoch 7 | Batch 1313/2891 | Timestep 21550 | LR 0.0001000000 | Loss 0.003170 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:55 Epoch 7 | Batch 1323/2891 | Timestep 21560 | LR 0.0001000000 | Loss 0.008992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:56 Epoch 7 | Batch 1333/2891 | Timestep 21570 | LR 0.0001000000 | Loss 0.004188 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:58 Epoch 7 | Batch 1343/2891 | Timestep 21580 | LR 0.0001000000 | Loss 0.016309 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:54:59 Epoch 7 | Batch 1353/2891 | Timestep 21590 | LR 0.0001000000 | Loss 0.004942 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:01 Epoch 7 | Batch 1363/2891 | Timestep 21600 | LR 0.0001000000 | Loss 0.006794 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:03 Epoch 7 | Batch 1373/2891 | Timestep 21610 | LR 0.0001000000 | Loss 0.047331 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:04 Epoch 7 | Batch 1383/2891 | Timestep 21620 | LR 0.0001000000 | Loss 0.012768 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:06 Epoch 7 | Batch 1393/2891 | Timestep 21630 | LR 0.0001000000 | Loss 0.024916 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:08 Epoch 7 | Batch 1403/2891 | Timestep 21640 | LR 0.0001000000 | Loss 0.001874 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:10 Epoch 7 | Batch 1413/2891 | Timestep 21650 | LR 0.0001000000 | Loss 0.019407 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:11 Epoch 7 | Batch 1423/2891 | Timestep 21660 | LR 0.0001000000 | Loss 0.006497 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:14 Epoch 7 | Batch 1433/2891 | Timestep 21670 | LR 0.0001000000 | Loss 0.036435 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:15 Epoch 7 | Batch 1443/2891 | Timestep 21680 | LR 0.0001000000 | Loss 0.004981 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:17 Epoch 7 | Batch 1453/2891 | Timestep 21690 | LR 0.0001000000 | Loss 0.001072 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:19 Epoch 7 | Batch 1463/2891 | Timestep 21700 | LR 0.0001000000 | Loss 0.007232 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:21 Epoch 7 | Batch 1473/2891 | Timestep 21710 | LR 0.0001000000 | Loss 0.027742 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:22 Epoch 7 | Batch 1483/2891 | Timestep 21720 | LR 0.0001000000 | Loss 0.002719 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:24 Epoch 7 | Batch 1493/2891 | Timestep 21730 | LR 0.0001000000 | Loss 0.022214 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:25 Epoch 7 | Batch 1503/2891 | Timestep 21740 | LR 0.0001000000 | Loss 0.023885 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:27 Epoch 7 | Batch 1513/2891 | Timestep 21750 | LR 0.0001000000 | Loss 0.096532 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:29 Epoch 7 | Batch 1523/2891 | Timestep 21760 | LR 0.0001000000 | Loss 0.058176 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:31 Epoch 7 | Batch 1533/2891 | Timestep 21770 | LR 0.0001000000 | Loss 0.016830 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:32 Epoch 7 | Batch 1543/2891 | Timestep 21780 | LR 0.0001000000 | Loss 0.074775 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:34 Epoch 7 | Batch 1553/2891 | Timestep 21790 | LR 0.0001000000 | Loss 0.029370 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:36 Epoch 7 | Batch 1563/2891 | Timestep 21800 | LR 0.0001000000 | Loss 0.003413 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:37 Epoch 7 | Batch 1573/2891 | Timestep 21810 | LR 0.0001000000 | Loss 0.001835 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:39 Epoch 7 | Batch 1583/2891 | Timestep 21820 | LR 0.0001000000 | Loss 0.035413 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:40 Epoch 7 | Batch 1593/2891 | Timestep 21830 | LR 0.0001000000 | Loss 0.112087 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:42 Epoch 7 | Batch 1603/2891 | Timestep 21840 | LR 0.0001000000 | Loss 0.069255 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:44 Epoch 7 | Batch 1613/2891 | Timestep 21850 | LR 0.0001000000 | Loss 0.042553 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:45 Epoch 7 | Batch 1623/2891 | Timestep 21860 | LR 0.0001000000 | Loss 0.033337 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:47 Epoch 7 | Batch 1633/2891 | Timestep 21870 | LR 0.0001000000 | Loss 0.007689 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:49 Epoch 7 | Batch 1643/2891 | Timestep 21880 | LR 0.0001000000 | Loss 0.008828 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:51 Epoch 7 | Batch 1653/2891 | Timestep 21890 | LR 0.0001000000 | Loss 0.002399 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:52 Epoch 7 | Batch 1663/2891 | Timestep 21900 | LR 0.0001000000 | Loss 0.001999 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:54 Epoch 7 | Batch 1673/2891 | Timestep 21910 | LR 0.0001000000 | Loss 0.022616 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:55 Epoch 7 | Batch 1683/2891 | Timestep 21920 | LR 0.0001000000 | Loss 0.003237 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:57 Epoch 7 | Batch 1693/2891 | Timestep 21930 | LR 0.0001000000 | Loss 0.029597 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:55:58 Epoch 7 | Batch 1703/2891 | Timestep 21940 | LR 0.0001000000 | Loss 0.018847 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:00 Epoch 7 | Batch 1713/2891 | Timestep 21950 | LR 0.0001000000 | Loss 0.002753 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:02 Epoch 7 | Batch 1723/2891 | Timestep 21960 | LR 0.0001000000 | Loss 0.002395 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:03 Epoch 7 | Batch 1733/2891 | Timestep 21970 | LR 0.0001000000 | Loss 0.001262 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:05 Epoch 7 | Batch 1743/2891 | Timestep 21980 | LR 0.0001000000 | Loss 0.002602 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:07 Epoch 7 | Batch 1753/2891 | Timestep 21990 | LR 0.0001000000 | Loss 0.002845 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:08 Epoch 7 | Batch 1763/2891 | Timestep 22000 | LR 0.0001000000 | Loss 0.060170 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:10 Epoch 7 | Batch 1773/2891 | Timestep 22010 | LR 0.0001000000 | Loss 0.032120 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:12 Epoch 7 | Batch 1783/2891 | Timestep 22020 | LR 0.0001000000 | Loss 0.009835 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:14 Epoch 7 | Batch 1793/2891 | Timestep 22030 | LR 0.0001000000 | Loss 0.006745 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:15 Epoch 7 | Batch 1803/2891 | Timestep 22040 | LR 0.0001000000 | Loss 0.006423 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:17 Epoch 7 | Batch 1813/2891 | Timestep 22050 | LR 0.0001000000 | Loss 0.003482 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:19 Epoch 7 | Batch 1823/2891 | Timestep 22060 | LR 0.0001000000 | Loss 0.002304 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:21 Epoch 7 | Batch 1833/2891 | Timestep 22070 | LR 0.0001000000 | Loss 0.000622 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:23 Epoch 7 | Batch 1843/2891 | Timestep 22080 | LR 0.0001000000 | Loss 0.011113 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:25 Epoch 7 | Batch 1853/2891 | Timestep 22090 | LR 0.0001000000 | Loss 0.012199 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:27 Epoch 7 | Batch 1863/2891 | Timestep 22100 | LR 0.0001000000 | Loss 0.076879 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:28 Epoch 7 | Batch 1873/2891 | Timestep 22110 | LR 0.0001000000 | Loss 0.134887 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:30 Epoch 7 | Batch 1883/2891 | Timestep 22120 | LR 0.0001000000 | Loss 0.131439 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:32 Epoch 7 | Batch 1893/2891 | Timestep 22130 | LR 0.0001000000 | Loss 0.073114 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:33 Epoch 7 | Batch 1903/2891 | Timestep 22140 | LR 0.0001000000 | Loss 0.023677 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:35 Epoch 7 | Batch 1913/2891 | Timestep 22150 | LR 0.0001000000 | Loss 0.021885 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:36 Epoch 7 | Batch 1923/2891 | Timestep 22160 | LR 0.0001000000 | Loss 0.006590 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:38 Epoch 7 | Batch 1933/2891 | Timestep 22170 | LR 0.0001000000 | Loss 0.008054 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:40 Epoch 7 | Batch 1943/2891 | Timestep 22180 | LR 0.0001000000 | Loss 0.095892 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:42 Epoch 7 | Batch 1953/2891 | Timestep 22190 | LR 0.0001000000 | Loss 0.012683 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:44 Epoch 7 | Batch 1963/2891 | Timestep 22200 | LR 0.0001000000 | Loss 0.010208 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:45 Epoch 7 | Batch 1973/2891 | Timestep 22210 | LR 0.0001000000 | Loss 0.021901 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:47 Epoch 7 | Batch 1983/2891 | Timestep 22220 | LR 0.0001000000 | Loss 0.005934 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:49 Epoch 7 | Batch 1993/2891 | Timestep 22230 | LR 0.0001000000 | Loss 0.020999 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:51 Epoch 7 | Batch 2003/2891 | Timestep 22240 | LR 0.0001000000 | Loss 0.024190 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:52 Epoch 7 | Batch 2013/2891 | Timestep 22250 | LR 0.0001000000 | Loss 0.005023 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:54 Epoch 7 | Batch 2023/2891 | Timestep 22260 | LR 0.0001000000 | Loss 0.029168 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:56 Epoch 7 | Batch 2033/2891 | Timestep 22270 | LR 0.0001000000 | Loss 0.029154 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:57 Epoch 7 | Batch 2043/2891 | Timestep 22280 | LR 0.0001000000 | Loss 0.015590 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:56:59 Epoch 7 | Batch 2053/2891 | Timestep 22290 | LR 0.0001000000 | Loss 0.024550 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:00 Epoch 7 | Batch 2063/2891 | Timestep 22300 | LR 0.0001000000 | Loss 0.019908 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:02 Epoch 7 | Batch 2073/2891 | Timestep 22310 | LR 0.0001000000 | Loss 0.297039 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:04 Epoch 7 | Batch 2083/2891 | Timestep 22320 | LR 0.0001000000 | Loss 0.027085 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:06 Epoch 7 | Batch 2093/2891 | Timestep 22330 | LR 0.0001000000 | Loss 0.034429 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:08 Epoch 7 | Batch 2103/2891 | Timestep 22340 | LR 0.0001000000 | Loss 0.018203 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:10 Epoch 7 | Batch 2113/2891 | Timestep 22350 | LR 0.0001000000 | Loss 0.002788 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:11 Epoch 7 | Batch 2123/2891 | Timestep 22360 | LR 0.0001000000 | Loss 0.011773 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:13 Epoch 7 | Batch 2133/2891 | Timestep 22370 | LR 0.0001000000 | Loss 0.007112 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:15 Epoch 7 | Batch 2143/2891 | Timestep 22380 | LR 0.0001000000 | Loss 0.006813 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:17 Epoch 7 | Batch 2153/2891 | Timestep 22390 | LR 0.0001000000 | Loss 0.063389 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:19 Epoch 7 | Batch 2163/2891 | Timestep 22400 | LR 0.0001000000 | Loss 0.004451 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:20 Epoch 7 | Batch 2173/2891 | Timestep 22410 | LR 0.0001000000 | Loss 0.019878 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:22 Epoch 7 | Batch 2183/2891 | Timestep 22420 | LR 0.0001000000 | Loss 0.097737 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:24 Epoch 7 | Batch 2193/2891 | Timestep 22430 | LR 0.0001000000 | Loss 0.017350 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:26 Epoch 7 | Batch 2203/2891 | Timestep 22440 | LR 0.0001000000 | Loss 0.020486 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:27 Epoch 7 | Batch 2213/2891 | Timestep 22450 | LR 0.0001000000 | Loss 0.005662 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:29 Epoch 7 | Batch 2223/2891 | Timestep 22460 | LR 0.0001000000 | Loss 0.001658 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:31 Epoch 7 | Batch 2233/2891 | Timestep 22470 | LR 0.0001000000 | Loss 0.001797 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:33 Epoch 7 | Batch 2243/2891 | Timestep 22480 | LR 0.0001000000 | Loss 0.001686 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:34 Epoch 7 | Batch 2253/2891 | Timestep 22490 | LR 0.0001000000 | Loss 0.003026 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:36 Epoch 7 | Batch 2263/2891 | Timestep 22500 | LR 0.0001000000 | Loss 0.027284 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:38 Epoch 7 | Batch 2273/2891 | Timestep 22510 | LR 0.0001000000 | Loss 0.023160 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:39 Epoch 7 | Batch 2283/2891 | Timestep 22520 | LR 0.0001000000 | Loss 0.020034 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:41 Epoch 7 | Batch 2293/2891 | Timestep 22530 | LR 0.0001000000 | Loss 0.002997 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:43 Epoch 7 | Batch 2303/2891 | Timestep 22540 | LR 0.0001000000 | Loss 0.028187 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:45 Epoch 7 | Batch 2313/2891 | Timestep 22550 | LR 0.0001000000 | Loss 0.001638 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:46 Epoch 7 | Batch 2323/2891 | Timestep 22560 | LR 0.0001000000 | Loss 0.022802 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:48 Epoch 7 | Batch 2333/2891 | Timestep 22570 | LR 0.0001000000 | Loss 0.003110 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:49 Epoch 7 | Batch 2343/2891 | Timestep 22580 | LR 0.0001000000 | Loss 0.005768 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:51 Epoch 7 | Batch 2353/2891 | Timestep 22590 | LR 0.0001000000 | Loss 0.001488 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:53 Epoch 7 | Batch 2363/2891 | Timestep 22600 | LR 0.0001000000 | Loss 0.015534 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:54 Epoch 7 | Batch 2373/2891 | Timestep 22610 | LR 0.0001000000 | Loss 0.007983 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:56 Epoch 7 | Batch 2383/2891 | Timestep 22620 | LR 0.0001000000 | Loss 0.001365 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:57:58 Epoch 7 | Batch 2393/2891 | Timestep 22630 | LR 0.0001000000 | Loss 0.004080 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:00 Epoch 7 | Batch 2403/2891 | Timestep 22640 | LR 0.0001000000 | Loss 0.020755 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:01 Epoch 7 | Batch 2413/2891 | Timestep 22650 | LR 0.0001000000 | Loss 0.026149 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:03 Epoch 7 | Batch 2423/2891 | Timestep 22660 | LR 0.0001000000 | Loss 0.030327 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:05 Epoch 7 | Batch 2433/2891 | Timestep 22670 | LR 0.0001000000 | Loss 0.020831 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:07 Epoch 7 | Batch 2443/2891 | Timestep 22680 | LR 0.0001000000 | Loss 0.006659 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:09 Epoch 7 | Batch 2453/2891 | Timestep 22690 | LR 0.0001000000 | Loss 0.010399 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:11 Epoch 7 | Batch 2463/2891 | Timestep 22700 | LR 0.0001000000 | Loss 0.013737 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:12 Epoch 7 | Batch 2473/2891 | Timestep 22710 | LR 0.0001000000 | Loss 0.001506 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:14 Epoch 7 | Batch 2483/2891 | Timestep 22720 | LR 0.0001000000 | Loss 0.005854 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:16 Epoch 7 | Batch 2493/2891 | Timestep 22730 | LR 0.0001000000 | Loss 0.058620 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:18 Epoch 7 | Batch 2503/2891 | Timestep 22740 | LR 0.0001000000 | Loss 0.002936 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:19 Epoch 7 | Batch 2513/2891 | Timestep 22750 | LR 0.0001000000 | Loss 0.001199 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:21 Epoch 7 | Batch 2523/2891 | Timestep 22760 | LR 0.0001000000 | Loss 0.003434 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:23 Epoch 7 | Batch 2533/2891 | Timestep 22770 | LR 0.0001000000 | Loss 0.007643 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:24 Epoch 7 | Batch 2543/2891 | Timestep 22780 | LR 0.0001000000 | Loss 0.011028 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:27 Epoch 7 | Batch 2553/2891 | Timestep 22790 | LR 0.0001000000 | Loss 0.005394 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:29 Epoch 7 | Batch 2563/2891 | Timestep 22800 | LR 0.0001000000 | Loss 0.031675 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:30 Epoch 7 | Batch 2573/2891 | Timestep 22810 | LR 0.0001000000 | Loss 0.057180 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:32 Epoch 7 | Batch 2583/2891 | Timestep 22820 | LR 0.0001000000 | Loss 0.007544 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:34 Epoch 7 | Batch 2593/2891 | Timestep 22830 | LR 0.0001000000 | Loss 0.016011 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:36 Epoch 7 | Batch 2603/2891 | Timestep 22840 | LR 0.0001000000 | Loss 0.025698 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:37 Epoch 7 | Batch 2613/2891 | Timestep 22850 | LR 0.0001000000 | Loss 0.008386 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:39 Epoch 7 | Batch 2623/2891 | Timestep 22860 | LR 0.0001000000 | Loss 0.009116 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:40 Epoch 7 | Batch 2633/2891 | Timestep 22870 | LR 0.0001000000 | Loss 0.001235 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:42 Epoch 7 | Batch 2643/2891 | Timestep 22880 | LR 0.0001000000 | Loss 0.015541 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:43 Epoch 7 | Batch 2653/2891 | Timestep 22890 | LR 0.0001000000 | Loss 0.001118 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:45 Epoch 7 | Batch 2663/2891 | Timestep 22900 | LR 0.0001000000 | Loss 0.066832 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:47 Epoch 7 | Batch 2673/2891 | Timestep 22910 | LR 0.0001000000 | Loss 0.000808 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:48 Epoch 7 | Batch 2683/2891 | Timestep 22920 | LR 0.0001000000 | Loss 0.039064 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:50 Epoch 7 | Batch 2693/2891 | Timestep 22930 | LR 0.0001000000 | Loss 0.079219 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:52 Epoch 7 | Batch 2703/2891 | Timestep 22940 | LR 0.0001000000 | Loss 0.007104 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:53 Epoch 7 | Batch 2713/2891 | Timestep 22950 | LR 0.0001000000 | Loss 0.002565 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:55 Epoch 7 | Batch 2723/2891 | Timestep 22960 | LR 0.0001000000 | Loss 0.006732 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:56 Epoch 7 | Batch 2733/2891 | Timestep 22970 | LR 0.0001000000 | Loss 0.031469 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:58:58 Epoch 7 | Batch 2743/2891 | Timestep 22980 | LR 0.0001000000 | Loss 0.005168 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:00 Epoch 7 | Batch 2753/2891 | Timestep 22990 | LR 0.0001000000 | Loss 0.002448 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:02 Epoch 7 | Batch 2763/2891 | Timestep 23000 | LR 0.0001000000 | Loss 0.017146 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:04 Epoch 7 | Batch 2773/2891 | Timestep 23010 | LR 0.0001000000 | Loss 0.013236 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:05 Epoch 7 | Batch 2783/2891 | Timestep 23020 | LR 0.0001000000 | Loss 0.008731 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:07 Epoch 7 | Batch 2793/2891 | Timestep 23030 | LR 0.0001000000 | Loss 0.067905 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:09 Epoch 7 | Batch 2803/2891 | Timestep 23040 | LR 0.0001000000 | Loss 0.012834 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:11 Epoch 7 | Batch 2813/2891 | Timestep 23050 | LR 0.0001000000 | Loss 0.044369 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:12 Epoch 7 | Batch 2823/2891 | Timestep 23060 | LR 0.0001000000 | Loss 0.019992 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:14 Epoch 7 | Batch 2833/2891 | Timestep 23070 | LR 0.0001000000 | Loss 0.005540 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:16 Epoch 7 | Batch 2843/2891 | Timestep 23080 | LR 0.0001000000 | Loss 0.003255 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:18 Epoch 7 | Batch 2853/2891 | Timestep 23090 | LR 0.0001000000 | Loss 0.019687 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:20 Epoch 7 | Batch 2863/2891 | Timestep 23100 | LR 0.0001000000 | Loss 0.011184 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:21 Epoch 7 | Batch 2873/2891 | Timestep 23110 | LR 0.0001000000 | Loss 0.063980 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:23 Epoch 7 | Batch 2883/2891 | Timestep 23120 | LR 0.0001000000 | Loss 0.026753 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 10:59:24 ** Evaluating on validation dataset ** INFO root Tue, 23 Dec 2025 11:00:00 precision recall f1-score support CARDINAL 0.7771 0.7588 0.7679 170 CURR 0.9545 0.8750 0.9130 24 DATE 0.9194 0.9314 0.9254 1691 EVENT 0.6022 0.7363 0.6626 292 FAC 0.7405 0.8220 0.7791 118 GPE 0.9654 0.9439 0.9545 2156 LANGUAGE 0.8000 0.7500 0.7742 16 LAW 0.6029 0.8723 0.7130 47 LOC 0.7889 0.7889 0.7889 90 MONEY 0.7391 0.7727 0.7556 22 NORP 0.6260 0.7169 0.6684 551 OCC 0.8314 0.8314 0.8314 522 ORDINAL 0.9250 0.9301 0.9276 544 ORG 0.8893 0.9309 0.9097 1882 PERCENT 0.8571 1.0000 0.9231 12 PERS 0.9422 0.8881 0.9143 679 PRODUCT 0.2222 0.2500 0.2353 8 QUANTITY 0.6667 0.6667 0.6667 3 TIME 0.5686 0.8788 0.6905 33 UNIT 1.0000 0.7500 0.8571 4 WEBSITE 0.5479 0.5000 0.5229 80 micro avg 0.8728 0.8934 0.8830 8944 macro avg 0.7603 0.7902 0.7705 8944 weighted avg 0.8787 0.8934 0.8852 8944 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 11:00:11 Epoch 7 | Timestep 23128 | Train Loss 0.024001 | Val Loss 0.059225 | F1 0.882983 INFO Nested.trainers.BertNestedTrainer Tue, 23 Dec 2025 11:00:11 Early termination triggered