generated_from_trainer

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

dit-base-finetuned-rvlcdip-small_rvl_cdip-NK1000_hint

This model is a fine-tuned version of WinKawaks/vit-small-patch16-224 on the None dataset. It achieves the following results on the evaluation set:

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss Accuracy Brier Loss Nll F1 Micro F1 Macro Ece Aurc
2.8286 1.0 1000 2.6354 0.6627 0.4563 2.2971 0.6627 0.6604 0.0542 0.1330
2.3 2.0 2000 2.2674 0.73 0.3761 2.0481 0.7300 0.7314 0.0509 0.0916
2.0283 3.0 3000 2.0891 0.7602 0.3360 1.9964 0.7602 0.7626 0.0564 0.0728
1.8552 4.0 4000 2.1367 0.746 0.3686 2.0430 0.746 0.7485 0.0911 0.0815
1.7095 5.0 5000 2.0469 0.7725 0.3301 1.9740 0.7725 0.7715 0.0882 0.0683
1.6118 6.0 6000 1.9706 0.7788 0.3199 1.9470 0.7788 0.7773 0.0816 0.0617
1.4475 7.0 7000 2.0324 0.779 0.3364 2.0056 0.779 0.7789 0.1159 0.0640
1.3546 8.0 8000 2.0987 0.7955 0.3266 1.9823 0.7955 0.7965 0.1259 0.0597
1.2711 9.0 9000 2.1830 0.7863 0.3487 2.0545 0.7863 0.7879 0.1418 0.0621
1.1984 10.0 10000 2.2992 0.7923 0.3537 2.0028 0.7923 0.7925 0.1532 0.0612
1.1503 11.0 11000 2.3319 0.795 0.3449 2.0241 0.795 0.7946 0.1527 0.0594
1.0998 12.0 12000 2.4733 0.7973 0.3553 2.0856 0.7973 0.7964 0.1602 0.0589
1.0752 13.0 13000 2.4884 0.7887 0.3655 2.0351 0.7887 0.7902 0.1679 0.0644
1.0564 14.0 14000 2.4374 0.7963 0.3496 2.0512 0.7963 0.7985 0.1611 0.0570
1.0227 15.0 15000 2.5464 0.7973 0.3582 2.1184 0.7973 0.7936 0.1676 0.0568
1.0129 16.0 16000 2.5022 0.8027 0.3441 2.0449 0.8027 0.8036 0.1636 0.0560
0.9895 17.0 17000 2.4877 0.811 0.3358 2.0303 0.811 0.8099 0.1578 0.0562
0.9628 18.0 18000 2.4552 0.8107 0.3328 2.0399 0.8108 0.8114 0.1548 0.0527
0.9466 19.0 19000 2.5208 0.818 0.3251 2.0761 0.818 0.8189 0.1524 0.0520
0.9291 20.0 20000 2.5858 0.8137 0.3332 2.0634 0.8137 0.8141 0.1588 0.0538
0.9177 21.0 21000 2.5647 0.8107 0.3383 2.0875 0.8108 0.8124 0.1601 0.0539
0.9038 22.0 22000 2.6104 0.82 0.3301 2.1033 0.82 0.8198 0.1566 0.0559
0.8874 23.0 23000 2.5864 0.8237 0.3188 2.0000 0.8237 0.8244 0.1517 0.0519
0.8858 24.0 24000 2.5969 0.8185 0.3273 2.0714 0.8185 0.8191 0.1551 0.0527
0.8653 25.0 25000 2.5529 0.828 0.3109 2.0179 0.828 0.8287 0.1505 0.0509
0.8475 26.0 26000 2.5745 0.8265 0.3171 1.9994 0.8265 0.8272 0.1509 0.0526
0.8569 27.0 27000 2.5906 0.8265 0.3142 2.0156 0.8265 0.8272 0.1499 0.0565
0.8368 28.0 28000 2.7150 0.8225 0.3271 2.0439 0.8225 0.8215 0.1561 0.0580
0.8355 29.0 29000 2.6501 0.824 0.3211 1.9908 0.824 0.8260 0.1545 0.0541
0.832 30.0 30000 2.5656 0.8315 0.3076 2.0091 0.8315 0.8328 0.1474 0.0540
0.8191 31.0 31000 2.6891 0.827 0.3189 1.9819 0.827 0.8294 0.1529 0.0573
0.8118 32.0 32000 2.6791 0.827 0.3175 2.0233 0.827 0.8268 0.1523 0.0575
0.8098 33.0 33000 2.5437 0.8373 0.2992 1.9926 0.8373 0.8384 0.1435 0.0492
0.8006 34.0 34000 2.5751 0.8415 0.2932 2.0036 0.8415 0.8410 0.1403 0.0501
0.8033 35.0 35000 2.5944 0.8303 0.3113 2.0069 0.8303 0.8302 0.1492 0.0537
0.7916 36.0 36000 2.4955 0.839 0.2922 1.9523 0.839 0.8391 0.1407 0.0493
0.7919 37.0 37000 2.6199 0.8365 0.3003 1.9494 0.8365 0.8370 0.1458 0.0538
0.7844 38.0 38000 2.5823 0.8365 0.3011 1.9960 0.8365 0.8368 0.1462 0.0511
0.7795 39.0 39000 2.5626 0.8415 0.2928 1.9916 0.8415 0.8412 0.1406 0.0484
0.7757 40.0 40000 2.5528 0.8415 0.2891 1.9512 0.8415 0.8420 0.1406 0.0502
0.7788 41.0 41000 2.5829 0.8383 0.2983 1.9420 0.8383 0.8377 0.1438 0.0530
0.7743 42.0 42000 2.5285 0.838 0.2948 1.9636 0.838 0.8383 0.1449 0.0486
0.768 43.0 43000 2.5130 0.8405 0.2906 1.9448 0.8405 0.8404 0.1418 0.0479
0.7681 44.0 44000 2.5347 0.8383 0.2951 1.9588 0.8383 0.8390 0.1446 0.0508
0.7662 45.0 45000 2.5246 0.8413 0.2900 1.9314 0.8413 0.8416 0.1415 0.0508
0.7629 46.0 46000 2.5246 0.8397 0.2913 1.9648 0.8397 0.8403 0.1433 0.0498
0.7632 47.0 47000 2.5217 0.8425 0.2892 1.9648 0.8425 0.8429 0.1409 0.0503
0.7598 48.0 48000 2.5163 0.8435 0.2881 1.9776 0.8435 0.8439 0.1407 0.0500
0.7609 49.0 49000 2.5187 0.8438 0.2885 1.9677 0.8438 0.8442 0.1401 0.0500
0.759 50.0 50000 2.5149 0.8438 0.2886 1.9666 0.8438 0.8442 0.1400 0.0499

Framework versions