| --- |
| library_name: transformers |
| license: apache-2.0 |
| base_model: google/vit-base-patch16-224 |
| tags: |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - precision |
| - recall |
| - f1 |
| model-index: |
| - name: ViT_B16 |
| results: [] |
| --- |
| |
| <!-- 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_B16 |
| |
| This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0999 |
| - Accuracy: 0.9729 |
| - Precision: 0.9874 |
| - Recall: 0.9536 |
| - F1: 0.9702 |
| - Tp: 1562 |
| - Tn: 1890 |
| - Fp: 20 |
| - Fn: 76 |
| |
| ## 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: |
| - learning_rate: 5e-06 |
| - train_batch_size: 64 |
| - eval_batch_size: 64 |
| - seed: 42 |
| - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
| - lr_scheduler_type: linear |
| - lr_scheduler_warmup_steps: 276 |
| - num_epochs: 5 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Tp | Tn | Fp | Fn | |
| |:-------------:|:------:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:----:|:----:|:---:|:---:| |
| | 0.6533 | 0.2477 | 55 | 0.5250 | 0.8470 | 0.8296 | 0.8413 | 0.8354 | 1378 | 1627 | 283 | 260 | |
| | 0.4246 | 0.4955 | 110 | 0.3119 | 0.9081 | 0.9379 | 0.8578 | 0.8960 | 1405 | 1817 | 93 | 233 | |
| | 0.2834 | 0.7432 | 165 | 0.2395 | 0.9194 | 0.9033 | 0.9243 | 0.9137 | 1514 | 1748 | 162 | 124 | |
| | 0.2425 | 0.9910 | 220 | 0.1882 | 0.9369 | 0.9348 | 0.9280 | 0.9314 | 1520 | 1804 | 106 | 118 | |
| | 0.2127 | 1.2387 | 275 | 0.1657 | 0.9501 | 0.9551 | 0.9359 | 0.9454 | 1533 | 1838 | 72 | 105 | |
| | 0.1973 | 1.4865 | 330 | 0.1446 | 0.9580 | 0.9709 | 0.9371 | 0.9537 | 1535 | 1864 | 46 | 103 | |
| | 0.1943 | 1.7342 | 385 | 0.1417 | 0.9628 | 0.9772 | 0.9414 | 0.9590 | 1542 | 1874 | 36 | 96 | |
| | 0.1934 | 1.9820 | 440 | 0.1173 | 0.9696 | 0.9904 | 0.9432 | 0.9662 | 1545 | 1895 | 15 | 93 | |
| | 0.1671 | 2.2297 | 495 | 0.1085 | 0.9707 | 0.9968 | 0.9396 | 0.9673 | 1539 | 1905 | 5 | 99 | |
| | 0.1755 | 2.4775 | 550 | 0.1140 | 0.9713 | 0.9898 | 0.9475 | 0.9682 | 1552 | 1894 | 16 | 86 | |
| | 0.1836 | 2.7252 | 605 | 0.1238 | 0.9659 | 0.9720 | 0.9536 | 0.9627 | 1562 | 1865 | 45 | 76 | |
| | 0.1664 | 2.9730 | 660 | 0.1199 | 0.9667 | 0.975 | 0.9524 | 0.9636 | 1560 | 1870 | 40 | 78 | |
| | 0.1693 | 3.2207 | 715 | 0.1189 | 0.9679 | 0.9745 | 0.9554 | 0.9649 | 1565 | 1869 | 41 | 73 | |
| | 0.1646 | 3.4685 | 770 | 0.1073 | 0.9701 | 0.9867 | 0.9481 | 0.9670 | 1553 | 1889 | 21 | 85 | |
| | 0.1585 | 3.7162 | 825 | 0.1076 | 0.9687 | 0.9805 | 0.9512 | 0.9656 | 1558 | 1879 | 31 | 80 | |
| | 0.1604 | 3.9640 | 880 | 0.1054 | 0.9729 | 0.9892 | 0.9518 | 0.9701 | 1559 | 1893 | 17 | 79 | |
| | 0.1701 | 4.2117 | 935 | 0.1046 | 0.9704 | 0.9806 | 0.9548 | 0.9675 | 1564 | 1879 | 31 | 74 | |
| | 0.1607 | 4.4595 | 990 | 0.1039 | 0.9713 | 0.9830 | 0.9542 | 0.9684 | 1563 | 1883 | 27 | 75 | |
| | 0.1631 | 4.7072 | 1045 | 0.1010 | 0.9727 | 0.9873 | 0.9530 | 0.9699 | 1561 | 1890 | 20 | 77 | |
| | 0.1483 | 4.9550 | 1100 | 0.0999 | 0.9729 | 0.9874 | 0.9536 | 0.9702 | 1562 | 1890 | 20 | 76 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 5.0.0 |
| - Pytorch 2.10.0+cu128 |
| - Datasets 4.0.0 |
| - Tokenizers 0.22.2 |
| |
