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-tiny_rvl_cdip-NK1000_simkd

This model is a fine-tuned version of WinKawaks/vit-tiny-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
0.149 1.0 1000 0.1482 0.1598 0.9334 6.4910 0.1598 0.1128 0.0991 0.7250
0.1278 2.0 2000 0.1248 0.5295 0.8391 3.1275 0.5295 0.4951 0.4011 0.2355
0.1156 3.0 3000 0.1146 0.6388 0.7532 2.4008 0.6388 0.6238 0.4480 0.1552
0.1094 4.0 4000 0.1089 0.7085 0.7069 2.1449 0.7085 0.7039 0.4850 0.1225
0.105 5.0 5000 0.1063 0.7252 0.6970 2.0868 0.7252 0.7291 0.4969 0.1087
0.1011 6.0 6000 0.1038 0.7472 0.6562 2.1759 0.7472 0.7478 0.4844 0.1095
0.097 7.0 7000 0.1043 0.7415 0.6509 2.5078 0.7415 0.7404 0.4668 0.1364
0.0946 8.0 8000 0.1022 0.7508 0.6416 2.1930 0.7508 0.7550 0.4714 0.1300
0.0916 9.0 9000 0.0995 0.7642 0.6271 1.9398 0.7642 0.7691 0.4791 0.1086
0.0901 10.0 10000 0.1013 0.747 0.6277 2.3724 0.747 0.7538 0.4538 0.1227
0.0881 11.0 11000 0.0991 0.7752 0.6037 1.9848 0.7752 0.7784 0.4696 0.1054
0.0868 12.0 12000 0.0983 0.7738 0.6074 2.0011 0.7738 0.7757 0.4741 0.0996
0.0855 13.0 13000 0.0977 0.7833 0.5864 1.9790 0.7833 0.7868 0.4633 0.1068
0.0845 14.0 14000 0.0986 0.782 0.5928 2.0415 0.782 0.7847 0.4645 0.1158
0.083 15.0 15000 0.0974 0.78 0.5793 2.0235 0.78 0.7857 0.4455 0.1243
0.0821 16.0 16000 0.0975 0.7823 0.5776 2.0363 0.7823 0.7859 0.4462 0.1238
0.0811 17.0 17000 0.0962 0.7883 0.5667 2.0085 0.7883 0.7907 0.4474 0.1108
0.0803 18.0 18000 0.0969 0.7833 0.5720 2.0028 0.7833 0.7840 0.4421 0.1276
0.0801 19.0 19000 0.0962 0.7823 0.5727 1.9412 0.7823 0.7847 0.4447 0.1182
0.0794 20.0 20000 0.0961 0.7847 0.5681 1.9442 0.7847 0.7851 0.4449 0.1121
0.0786 21.0 21000 0.0993 0.7612 0.5748 2.2878 0.7612 0.7627 0.4088 0.1494
0.0776 22.0 22000 0.0947 0.797 0.5491 1.8933 0.797 0.7986 0.4379 0.1211
0.0771 23.0 23000 0.0955 0.7893 0.5564 1.8974 0.7893 0.7918 0.4391 0.1124
0.0772 24.0 24000 0.0956 0.788 0.5524 1.9541 0.788 0.7898 0.4309 0.1166
0.0768 25.0 25000 0.0970 0.7748 0.5568 2.0627 0.7748 0.7776 0.4152 0.1264
0.0765 26.0 26000 0.0939 0.7975 0.5448 1.7874 0.7975 0.7996 0.4397 0.1086
0.0759 27.0 27000 0.0944 0.797 0.5425 1.8354 0.797 0.7982 0.4328 0.1185
0.0755 28.0 28000 0.0938 0.7993 0.5399 1.6911 0.7993 0.7993 0.4391 0.1025
0.0754 29.0 29000 0.0945 0.797 0.5387 1.8083 0.797 0.7980 0.4323 0.1117
0.075 30.0 30000 0.0941 0.8005 0.5353 1.7803 0.8005 0.8020 0.4318 0.1128
0.0745 31.0 31000 0.0928 0.805 0.5282 1.6621 0.805 0.8070 0.4338 0.1107
0.0747 32.0 32000 0.0935 0.806 0.5316 1.6745 0.806 0.8066 0.4368 0.1111
0.0743 33.0 33000 0.0928 0.8095 0.5288 1.7115 0.8095 0.8096 0.4401 0.1045
0.074 34.0 34000 0.0927 0.8063 0.5286 1.6801 0.8062 0.8064 0.4378 0.1001
0.0734 35.0 35000 0.0925 0.8083 0.5260 1.6524 0.8083 0.8102 0.4364 0.1066
0.0734 36.0 36000 0.0924 0.8087 0.5252 1.6727 0.8087 0.8106 0.4352 0.1077
0.0733 37.0 37000 0.0920 0.8133 0.5215 1.6062 0.8133 0.8147 0.4399 0.1000
0.0733 38.0 38000 0.0924 0.8083 0.5243 1.6319 0.8083 0.8100 0.4343 0.1063
0.0732 39.0 39000 0.0921 0.8105 0.5222 1.5823 0.8105 0.8106 0.4363 0.1034
0.073 40.0 40000 0.0917 0.8157 0.5203 1.5771 0.8157 0.8163 0.4414 0.1014
0.0728 41.0 41000 0.0916 0.8153 0.5192 1.5726 0.8153 0.8163 0.4395 0.1033
0.0729 42.0 42000 0.0916 0.8133 0.5188 1.5495 0.8133 0.8145 0.4392 0.1026
0.0726 43.0 43000 0.0917 0.816 0.5185 1.5969 0.816 0.8169 0.4395 0.1054
0.0728 44.0 44000 0.0914 0.8163 0.5164 1.5257 0.8163 0.8167 0.4388 0.1023
0.0725 45.0 45000 0.0914 0.8153 0.5165 1.5699 0.8153 0.8161 0.4386 0.1012
0.0723 46.0 46000 0.0915 0.816 0.5160 1.5653 0.816 0.8171 0.4386 0.1008
0.0723 47.0 47000 0.0914 0.8155 0.5159 1.5478 0.8155 0.8165 0.4380 0.0997
0.0721 48.0 48000 0.0914 0.816 0.5156 1.5579 0.816 0.8169 0.4379 0.1006
0.0725 49.0 49000 0.0914 0.8155 0.5153 1.5636 0.8155 0.8165 0.4369 0.1009
0.0721 50.0 50000 0.0914 0.8157 0.5152 1.5529 0.8157 0.8167 0.4370 0.1010

Framework versions