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. -->

vit-tiny_tobacco3482_simkd__tNone_gNone__logits

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
No log 1.0 100 0.0492 0.03 0.9002 15.7630 0.03 0.0130 0.1184 0.9407
No log 2.0 200 0.0479 0.045 0.8991 12.1839 0.045 0.0140 0.1350 0.9268
No log 3.0 300 0.0472 0.305 0.8968 12.2323 0.305 0.1551 0.2930 0.5596
No log 4.0 400 0.0463 0.305 0.8938 10.0711 0.305 0.1809 0.3077 0.5037
0.0541 5.0 500 0.0453 0.325 0.8898 9.3778 0.325 0.2046 0.3193 0.4698
0.0541 6.0 600 0.0442 0.4 0.8787 9.6363 0.4000 0.2403 0.3713 0.3759
0.0541 7.0 700 0.0433 0.4 0.8639 9.3483 0.4000 0.2510 0.3685 0.3742
0.0541 8.0 800 0.0428 0.475 0.8521 9.0007 0.4750 0.2666 0.4177 0.2978
0.0541 9.0 900 0.0422 0.515 0.8438 7.6934 0.515 0.3644 0.4480 0.2431
0.0451 10.0 1000 0.0417 0.515 0.8210 7.6243 0.515 0.3743 0.4387 0.2146
0.0451 11.0 1100 0.0411 0.68 0.8190 3.6435 0.68 0.5226 0.5677 0.1272
0.0451 12.0 1200 0.0403 0.655 0.7803 5.4537 0.655 0.5379 0.5202 0.1352
0.0451 13.0 1300 0.0398 0.75 0.7745 4.1150 0.75 0.6543 0.5945 0.0749
0.0451 14.0 1400 0.0390 0.77 0.7561 2.8538 0.7700 0.6703 0.6085 0.0753
0.0406 15.0 1500 0.0392 0.745 0.7637 3.7047 0.745 0.6673 0.5796 0.1060
0.0406 16.0 1600 0.0398 0.73 0.7603 4.3010 0.7300 0.6681 0.5693 0.0949
0.0406 17.0 1700 0.0399 0.705 0.7610 3.6375 0.705 0.6564 0.5590 0.0923
0.0406 18.0 1800 0.0397 0.705 0.7536 4.2628 0.705 0.6170 0.5472 0.1332
0.0406 19.0 1900 0.0390 0.745 0.7400 2.8861 0.745 0.6686 0.5644 0.1070
0.0379 20.0 2000 0.0394 0.785 0.7238 3.3111 0.785 0.7255 0.5995 0.0695
0.0379 21.0 2100 0.0396 0.76 0.7419 3.1935 0.76 0.7463 0.5885 0.0793
0.0379 22.0 2200 0.0396 0.785 0.7423 3.7954 0.785 0.7737 0.6043 0.0873
0.0379 23.0 2300 0.0395 0.78 0.7321 3.8067 0.78 0.7491 0.5885 0.0908
0.0379 24.0 2400 0.0387 0.8 0.7228 2.9339 0.8000 0.7758 0.6038 0.0609
0.037 25.0 2500 0.0387 0.795 0.7222 2.6252 0.795 0.7601 0.6094 0.0606
0.037 26.0 2600 0.0387 0.8 0.7241 2.6253 0.8000 0.7628 0.6110 0.0607
0.037 27.0 2700 0.0387 0.795 0.7235 2.4818 0.795 0.7616 0.6093 0.0629
0.037 28.0 2800 0.0387 0.795 0.7245 2.6226 0.795 0.7586 0.6032 0.0604
0.037 29.0 2900 0.0387 0.805 0.7253 2.7588 0.805 0.7725 0.6144 0.0609
0.0364 30.0 3000 0.0387 0.805 0.7233 2.4956 0.805 0.7701 0.6204 0.0594
0.0364 31.0 3100 0.0387 0.81 0.7241 2.7695 0.81 0.7797 0.6188 0.0602
0.0364 32.0 3200 0.0386 0.81 0.7239 2.6185 0.81 0.7797 0.6190 0.0580
0.0364 33.0 3300 0.0387 0.805 0.7238 2.9106 0.805 0.7717 0.6182 0.0586
0.0364 34.0 3400 0.0386 0.805 0.7231 2.9062 0.805 0.7725 0.6133 0.0590
0.0364 35.0 3500 0.0387 0.805 0.7247 2.7645 0.805 0.7717 0.6141 0.0590
0.0364 36.0 3600 0.0386 0.805 0.7238 2.9152 0.805 0.7717 0.6104 0.0578
0.0364 37.0 3700 0.0387 0.805 0.7229 2.9094 0.805 0.7717 0.6142 0.0588
0.0364 38.0 3800 0.0386 0.805 0.7237 2.9185 0.805 0.7717 0.6173 0.0565
0.0364 39.0 3900 0.0386 0.805 0.7230 2.9178 0.805 0.7717 0.6131 0.0578
0.0364 40.0 4000 0.0386 0.805 0.7233 2.9155 0.805 0.7717 0.6131 0.0561
0.0364 41.0 4100 0.0386 0.805 0.7235 2.9142 0.805 0.7717 0.6173 0.0574
0.0364 42.0 4200 0.0387 0.805 0.7225 2.9162 0.805 0.7717 0.6196 0.0572
0.0364 43.0 4300 0.0387 0.805 0.7231 3.0596 0.805 0.7717 0.6139 0.0560
0.0364 44.0 4400 0.0387 0.805 0.7229 3.0584 0.805 0.7717 0.6140 0.0558
0.0364 45.0 4500 0.0386 0.815 0.7231 2.9107 0.815 0.7856 0.6224 0.0551
0.0364 46.0 4600 0.0386 0.8 0.7228 3.0609 0.8000 0.7683 0.6154 0.0570
0.0364 47.0 4700 0.0386 0.8 0.7229 3.0539 0.8000 0.7683 0.6141 0.0564
0.0364 48.0 4800 0.0387 0.805 0.7228 2.9149 0.805 0.7753 0.6164 0.0559
0.0364 49.0 4900 0.0387 0.805 0.7239 3.0631 0.805 0.7729 0.6144 0.0569
0.0364 50.0 5000 0.0387 0.8 0.7231 3.0551 0.8000 0.7683 0.6094 0.0562
0.0364 51.0 5100 0.0387 0.815 0.7232 3.0662 0.815 0.7868 0.6212 0.0569
0.0364 52.0 5200 0.0386 0.805 0.7226 2.9067 0.805 0.7753 0.6241 0.0550
0.0364 53.0 5300 0.0387 0.81 0.7236 2.9086 0.81 0.7761 0.6209 0.0558
0.0364 54.0 5400 0.0387 0.805 0.7240 2.9108 0.805 0.7729 0.6072 0.0577
0.0364 55.0 5500 0.0387 0.815 0.7228 2.9235 0.815 0.7832 0.6202 0.0556
0.0364 56.0 5600 0.0387 0.82 0.7229 2.9335 0.82 0.7898 0.6273 0.0544
0.0364 57.0 5700 0.0387 0.82 0.7230 2.9210 0.82 0.7900 0.6292 0.0561
0.0364 58.0 5800 0.0387 0.82 0.7227 2.9211 0.82 0.7898 0.6325 0.0560
0.0364 59.0 5900 0.0386 0.82 0.7238 3.0664 0.82 0.7898 0.6249 0.0548
0.0364 60.0 6000 0.0387 0.82 0.7218 2.9137 0.82 0.7900 0.6397 0.0545
0.0364 61.0 6100 0.0387 0.82 0.7233 3.0756 0.82 0.7900 0.6225 0.0563
0.0364 62.0 6200 0.0387 0.815 0.7231 3.0725 0.815 0.7878 0.6190 0.0558
0.0364 63.0 6300 0.0387 0.82 0.7218 3.0589 0.82 0.7900 0.6223 0.0554
0.0364 64.0 6400 0.0387 0.82 0.7231 3.0632 0.82 0.7900 0.6289 0.0551
0.0363 65.0 6500 0.0387 0.82 0.7227 3.0595 0.82 0.7900 0.6339 0.0560
0.0363 66.0 6600 0.0387 0.82 0.7229 2.9000 0.82 0.7900 0.6320 0.0551
0.0363 67.0 6700 0.0387 0.82 0.7222 2.9092 0.82 0.7900 0.6292 0.0548
0.0363 68.0 6800 0.0387 0.82 0.7233 2.7662 0.82 0.7900 0.6299 0.0564
0.0363 69.0 6900 0.0387 0.82 0.7230 2.9095 0.82 0.7900 0.6239 0.0555
0.0363 70.0 7000 0.0387 0.82 0.7226 2.9175 0.82 0.7908 0.6274 0.0549
0.0363 71.0 7100 0.0387 0.82 0.7237 3.0548 0.82 0.7900 0.6337 0.0550
0.0363 72.0 7200 0.0387 0.815 0.7229 2.9144 0.815 0.7841 0.6207 0.0570
0.0363 73.0 7300 0.0387 0.82 0.7235 2.9041 0.82 0.7900 0.6310 0.0564
0.0363 74.0 7400 0.0387 0.82 0.7227 2.9094 0.82 0.7908 0.6291 0.0558
0.0363 75.0 7500 0.0387 0.825 0.7236 2.9105 0.825 0.7983 0.6319 0.0543
0.0363 76.0 7600 0.0387 0.82 0.7225 2.9172 0.82 0.7908 0.6260 0.0550
0.0363 77.0 7700 0.0387 0.815 0.7227 2.9050 0.815 0.7841 0.6325 0.0557
0.0363 78.0 7800 0.0387 0.825 0.7236 2.9242 0.825 0.7983 0.6264 0.0575
0.0363 79.0 7900 0.0387 0.82 0.7231 2.9167 0.82 0.7900 0.6263 0.0572
0.0363 80.0 8000 0.0387 0.825 0.7229 2.7707 0.825 0.8004 0.6311 0.0569
0.0363 81.0 8100 0.0387 0.81 0.7230 2.9083 0.81 0.7812 0.6295 0.0573
0.0363 82.0 8200 0.0387 0.82 0.7227 2.7600 0.82 0.7927 0.6263 0.0576
0.0363 83.0 8300 0.0387 0.815 0.7226 2.7902 0.815 0.7930 0.6169 0.0576
0.0363 84.0 8400 0.0387 0.815 0.7226 2.7666 0.815 0.7841 0.6254 0.0571
0.0363 85.0 8500 0.0387 0.82 0.7228 2.7730 0.82 0.7960 0.6226 0.0566
0.0363 86.0 8600 0.0387 0.815 0.7228 2.6311 0.815 0.7878 0.6186 0.0572
0.0363 87.0 8700 0.0388 0.82 0.7230 2.6272 0.82 0.7924 0.6321 0.0575
0.0363 88.0 8800 0.0387 0.82 0.7227 2.7579 0.82 0.7924 0.6318 0.0568
0.0363 89.0 8900 0.0388 0.82 0.7227 2.7688 0.82 0.7960 0.6238 0.0575
0.0363 90.0 9000 0.0387 0.82 0.7232 2.6100 0.82 0.7986 0.6290 0.0569
0.0363 91.0 9100 0.0387 0.82 0.7228 2.6088 0.82 0.7960 0.6258 0.0574
0.0363 92.0 9200 0.0387 0.825 0.7228 2.6134 0.825 0.8038 0.6239 0.0575
0.0363 93.0 9300 0.0387 0.825 0.7229 2.6136 0.825 0.7990 0.6283 0.0576
0.0363 94.0 9400 0.0387 0.82 0.7228 2.6112 0.82 0.7924 0.6235 0.0580
0.0363 95.0 9500 0.0388 0.82 0.7228 2.6077 0.82 0.7960 0.6185 0.0575
0.0363 96.0 9600 0.0388 0.825 0.7229 2.6073 0.825 0.8038 0.6206 0.0572
0.0363 97.0 9700 0.0388 0.82 0.7227 2.6077 0.82 0.7960 0.6213 0.0572
0.0363 98.0 9800 0.0388 0.815 0.7228 2.6094 0.815 0.7893 0.6161 0.0579
0.0363 99.0 9900 0.0388 0.815 0.7228 2.6086 0.815 0.7893 0.6160 0.0579
0.0363 100.0 10000 0.0388 0.82 0.7227 2.6079 0.82 0.7960 0.6182 0.0575

Framework versions