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. -->

test_crl_entropy_large

This model is a fine-tuned version of jordyvl/vit-base_rvl-cdip 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 0.96 12 2.5859 0.05 0.9010 18.0478 0.0500 0.0539 0.1568 0.9609
No log 2.0 25 2.5164 0.225 0.8825 11.6684 0.225 0.1480 0.2600 0.7882
No log 2.96 37 2.3841 0.435 0.8485 4.9677 0.435 0.2723 0.4030 0.2751
No log 4.0 50 2.1765 0.72 0.7878 3.1818 0.72 0.6092 0.5962 0.0863
No log 4.96 62 1.9498 0.8 0.7104 1.5065 0.8000 0.7202 0.6069 0.0453
No log 6.0 75 1.6936 0.85 0.6116 1.3333 0.85 0.8023 0.5897 0.0375
No log 6.96 87 1.4794 0.885 0.5207 1.1014 0.885 0.8689 0.5429 0.0360
No log 8.0 100 1.2753 0.905 0.4293 0.8992 0.905 0.8958 0.4920 0.0289
No log 8.96 112 1.1140 0.91 0.3546 1.0480 0.91 0.8979 0.4226 0.0229
No log 10.0 125 0.9650 0.91 0.2872 0.8855 0.91 0.9076 0.3683 0.0210
No log 10.96 137 0.8788 0.915 0.2493 1.0637 0.915 0.9156 0.3070 0.0202
No log 12.0 150 0.7997 0.9 0.2207 1.0602 0.9 0.9020 0.2929 0.0201
No log 12.96 162 0.7460 0.915 0.2033 0.8874 0.915 0.9106 0.2675 0.0175
No log 14.0 175 0.6631 0.925 0.1713 0.8091 0.925 0.9178 0.2271 0.0137
No log 14.96 187 0.6219 0.925 0.1593 0.9488 0.925 0.9169 0.2183 0.0177
No log 16.0 200 0.5861 0.93 0.1531 0.9181 0.93 0.9345 0.2110 0.0193
No log 16.96 212 0.5557 0.93 0.1407 0.9323 0.93 0.9247 0.1725 0.0186
No log 18.0 225 0.5394 0.92 0.1446 0.7790 0.92 0.9150 0.1847 0.0165
No log 18.96 237 0.5170 0.93 0.1345 0.7822 0.93 0.9269 0.1598 0.0157
No log 20.0 250 0.5079 0.91 0.1356 0.9286 0.91 0.9084 0.1598 0.0161
No log 20.96 262 0.4945 0.92 0.1342 0.7583 0.92 0.9150 0.1470 0.0153
No log 22.0 275 0.4850 0.91 0.1330 0.7760 0.91 0.9084 0.1398 0.0155
No log 22.96 287 0.4828 0.91 0.1334 0.9411 0.91 0.9084 0.1487 0.0154
No log 24.0 300 0.4758 0.91 0.1324 0.9241 0.91 0.9084 0.1294 0.0153
No log 24.96 312 0.4712 0.91 0.1327 1.0746 0.91 0.9084 0.1322 0.0156
No log 26.0 325 0.4672 0.91 0.1321 1.0726 0.91 0.9084 0.1248 0.0153
No log 26.96 337 0.4659 0.91 0.1331 1.0712 0.91 0.9084 0.1320 0.0153
No log 28.0 350 0.4618 0.91 0.1323 1.0693 0.91 0.9084 0.1276 0.0151
No log 28.96 362 0.4564 0.91 0.1315 1.0707 0.91 0.9084 0.1284 0.0156
No log 30.0 375 0.4587 0.91 0.1348 1.0736 0.91 0.9080 0.1334 0.0160
No log 30.96 387 0.4554 0.91 0.1334 1.0663 0.91 0.9080 0.1104 0.0155
No log 32.0 400 0.4512 0.91 0.1331 1.0691 0.91 0.9080 0.1079 0.0158
No log 32.96 412 0.4569 0.91 0.1385 1.2348 0.91 0.9080 0.1184 0.0166
No log 34.0 425 0.4516 0.91 0.1362 1.0761 0.91 0.9080 0.1178 0.0160
No log 34.96 437 0.4531 0.905 0.1376 1.0636 0.905 0.9051 0.1252 0.0156
No log 36.0 450 0.4526 0.91 0.1384 1.1004 0.91 0.9080 0.1128 0.0164
No log 36.96 462 0.4460 0.91 0.1345 1.0779 0.91 0.9080 0.1093 0.0173
No log 38.0 475 0.4422 0.905 0.1347 1.0680 0.905 0.9047 0.1237 0.0163
No log 38.96 487 0.4510 0.905 0.1410 1.2254 0.905 0.9065 0.1138 0.0176
0.6142 40.0 500 0.4426 0.91 0.1370 1.2232 0.91 0.9080 0.1067 0.0163
0.6142 40.96 512 0.4469 0.91 0.1407 1.2227 0.91 0.9080 0.1285 0.0159
0.6142 42.0 525 0.4456 0.91 0.1403 1.2315 0.91 0.9080 0.1099 0.0163
0.6142 42.96 537 0.4336 0.905 0.1319 1.2228 0.905 0.9028 0.1132 0.0180
0.6142 44.0 550 0.4435 0.915 0.1357 1.0493 0.915 0.9133 0.1055 0.0146
0.6142 44.96 562 0.5008 0.905 0.1585 1.4460 0.905 0.9070 0.1219 0.0234
0.6142 46.0 575 0.4496 0.915 0.1428 1.3785 0.915 0.9138 0.1162 0.0164
0.6142 46.96 587 0.4627 0.915 0.1476 1.3925 0.915 0.9138 0.1166 0.0178
0.6142 48.0 600 0.4545 0.915 0.1459 1.3840 0.915 0.9138 0.1145 0.0172
0.6142 48.96 612 0.4528 0.915 0.1457 1.3862 0.915 0.9138 0.1088 0.0175
0.6142 50.0 625 0.4578 0.915 0.1480 1.3905 0.915 0.9138 0.1079 0.0176
0.6142 50.96 637 0.4574 0.91 0.1473 1.3863 0.91 0.9105 0.1135 0.0178
0.6142 52.0 650 0.4497 0.915 0.1455 1.3807 0.915 0.9138 0.1072 0.0172
0.6142 52.96 662 0.4614 0.905 0.1503 1.3893 0.905 0.9076 0.1144 0.0174
0.6142 54.0 675 0.4560 0.915 0.1480 1.3884 0.915 0.9138 0.1134 0.0179
0.6142 54.96 687 0.4460 0.905 0.1457 1.2136 0.905 0.9076 0.1129 0.0163
0.6142 56.0 700 0.4499 0.91 0.1480 1.3847 0.91 0.9109 0.1075 0.0176
0.6142 56.96 712 0.4520 0.915 0.1477 1.3829 0.915 0.9138 0.1113 0.0175
0.6142 58.0 725 0.4519 0.915 0.1481 1.5477 0.915 0.9138 0.1059 0.0187
0.6142 58.96 737 0.4399 0.915 0.1440 1.0570 0.915 0.9138 0.1110 0.0167
0.6142 60.0 750 0.4451 0.91 0.1473 1.2166 0.91 0.9080 0.1071 0.0172
0.6142 60.96 762 0.4538 0.915 0.1502 1.2374 0.915 0.9138 0.1115 0.0183
0.6142 62.0 775 0.4489 0.91 0.1487 1.2152 0.91 0.9105 0.1049 0.0171
0.6142 62.96 787 0.4489 0.915 0.1488 1.2265 0.915 0.9138 0.1048 0.0183
0.6142 64.0 800 0.4480 0.915 0.1481 1.2384 0.915 0.9138 0.1092 0.0176
0.6142 64.96 812 0.4422 0.91 0.1465 1.0633 0.91 0.9080 0.1064 0.0164
0.6142 66.0 825 0.4410 0.91 0.1462 1.2394 0.91 0.9080 0.1060 0.0166
0.6142 66.96 837 0.4380 0.91 0.1460 1.2227 0.91 0.9080 0.1006 0.0165
0.6142 68.0 850 0.4434 0.91 0.1478 1.3838 0.91 0.9080 0.1025 0.0171
0.6142 68.96 862 0.4511 0.91 0.1504 1.3874 0.91 0.9080 0.1023 0.0177
0.6142 70.0 875 0.4405 0.91 0.1460 1.3857 0.91 0.9080 0.1076 0.0185
0.6142 70.96 887 0.4558 0.915 0.1518 1.3987 0.915 0.9138 0.1061 0.0191
0.6142 72.0 900 0.4434 0.91 0.1480 1.2224 0.91 0.9080 0.1021 0.0176
0.6142 72.96 912 0.4455 0.91 0.1491 1.2312 0.91 0.9080 0.1031 0.0177
0.6142 74.0 925 0.4549 0.915 0.1521 1.2332 0.915 0.9138 0.1066 0.0183
0.6142 74.96 937 0.4567 0.91 0.1516 1.2475 0.91 0.9109 0.0993 0.0194
0.6142 76.0 950 0.4465 0.905 0.1490 1.2255 0.905 0.9047 0.1050 0.0182
0.6142 76.96 962 0.4425 0.91 0.1476 1.2256 0.91 0.9080 0.1037 0.0180
0.6142 78.0 975 0.4535 0.91 0.1519 1.2320 0.91 0.9080 0.1070 0.0184
0.6142 78.96 987 0.4509 0.915 0.1507 1.2352 0.915 0.9138 0.1036 0.0185
0.0861 80.0 1000 0.4566 0.91 0.1527 1.2324 0.91 0.9109 0.1061 0.0185
0.0861 80.96 1012 0.4544 0.915 0.1513 1.3928 0.915 0.9138 0.1074 0.0183
0.0861 82.0 1025 0.4544 0.915 0.1512 1.2383 0.915 0.9138 0.1034 0.0186
0.0861 82.96 1037 0.4597 0.915 0.1532 1.3974 0.915 0.9138 0.1014 0.0188
0.0861 84.0 1050 0.4508 0.905 0.1515 1.2298 0.905 0.9047 0.1029 0.0180
0.0861 84.96 1062 0.4507 0.915 0.1508 1.2297 0.915 0.9138 0.1058 0.0178
0.0861 86.0 1075 0.4557 0.915 0.1524 1.3915 0.915 0.9138 0.1082 0.0183
0.0861 86.96 1087 0.4532 0.915 0.1516 1.2274 0.915 0.9138 0.1077 0.0184
0.0861 88.0 1100 0.4492 0.91 0.1506 1.2265 0.91 0.9080 0.1018 0.0181
0.0861 88.96 1112 0.4502 0.91 0.1511 1.2304 0.91 0.9080 0.1062 0.0184
0.0861 90.0 1125 0.4582 0.91 0.1536 1.2361 0.91 0.9080 0.1046 0.0186
0.0861 90.96 1137 0.4576 0.915 0.1531 1.2504 0.915 0.9138 0.1046 0.0187
0.0861 92.0 1150 0.4589 0.915 0.1533 1.3958 0.915 0.9138 0.1052 0.0188
0.0861 92.96 1162 0.4594 0.915 0.1536 1.2503 0.915 0.9138 0.1114 0.0188
0.0861 94.0 1175 0.4570 0.915 0.1529 1.2441 0.915 0.9138 0.1078 0.0185
0.0861 94.96 1187 0.4577 0.915 0.1531 1.2402 0.915 0.9138 0.1052 0.0186
0.0861 96.0 1200 0.4581 0.915 0.1532 1.2415 0.915 0.9138 0.1052 0.0187

Framework versions