<!-- 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-base-patch16-224-Trial007-008-YEL_STEM2
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1014
- Accuracy: 1.0
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-05
- train_batch_size: 60
- eval_batch_size: 60
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 240
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7829 | 1.0 | 3 | 0.6908 | 0.5769 |
| 0.609 | 2.0 | 6 | 0.6573 | 0.6795 |
| 0.5343 | 3.0 | 9 | 0.4127 | 0.8205 |
| 0.4062 | 4.0 | 12 | 0.3091 | 0.8974 |
| 0.322 | 5.0 | 15 | 0.1731 | 0.9744 |
| 0.2056 | 6.0 | 18 | 0.1610 | 0.9615 |
| 0.265 | 7.0 | 21 | 0.1083 | 0.9744 |
| 0.2145 | 8.0 | 24 | 0.0809 | 0.9872 |
| 0.2869 | 9.0 | 27 | 0.1014 | 1.0 |
| 0.1803 | 10.0 | 30 | 0.0499 | 1.0 |
| 0.2353 | 11.0 | 33 | 0.0597 | 1.0 |
| 0.1768 | 12.0 | 36 | 0.0614 | 1.0 |
| 0.2124 | 13.0 | 39 | 0.0574 | 1.0 |
| 0.2366 | 14.0 | 42 | 0.0844 | 1.0 |
| 0.2283 | 15.0 | 45 | 0.0603 | 0.9872 |
| 0.246 | 16.0 | 48 | 0.0537 | 1.0 |
| 0.1636 | 17.0 | 51 | 0.0569 | 1.0 |
| 0.1983 | 18.0 | 54 | 0.0565 | 1.0 |
| 0.1817 | 19.0 | 57 | 0.0684 | 1.0 |
| 0.1835 | 20.0 | 60 | 0.0580 | 1.0 |
| 0.1293 | 21.0 | 63 | 0.0324 | 1.0 |
| 0.1985 | 22.0 | 66 | 0.0398 | 1.0 |
| 0.1827 | 23.0 | 69 | 0.0596 | 1.0 |
| 0.2516 | 24.0 | 72 | 0.0545 | 1.0 |
| 0.1871 | 25.0 | 75 | 0.0620 | 1.0 |
| 0.1853 | 26.0 | 78 | 0.0558 | 1.0 |
| 0.2257 | 27.0 | 81 | 0.0488 | 1.0 |
| 0.159 | 28.0 | 84 | 0.0500 | 1.0 |
| 0.1767 | 29.0 | 87 | 0.0508 | 1.0 |
| 0.1841 | 30.0 | 90 | 0.0599 | 1.0 |
| 0.1234 | 31.0 | 93 | 0.0602 | 1.0 |
| 0.1836 | 32.0 | 96 | 0.0504 | 1.0 |
| 0.1898 | 33.0 | 99 | 0.0477 | 1.0 |
| 0.187 | 34.0 | 102 | 0.0560 | 1.0 |
| 0.1405 | 35.0 | 105 | 0.0672 | 1.0 |
| 0.188 | 36.0 | 108 | 0.0783 | 1.0 |
| 0.1855 | 37.0 | 111 | 0.0727 | 1.0 |
| 0.1833 | 38.0 | 114 | 0.0611 | 1.0 |
| 0.1957 | 39.0 | 117 | 0.0552 | 1.0 |
| 0.1463 | 40.0 | 120 | 0.0529 | 1.0 |
| 0.1255 | 41.0 | 123 | 0.0541 | 1.0 |
| 0.1558 | 42.0 | 126 | 0.0526 | 1.0 |
| 0.148 | 43.0 | 129 | 0.0513 | 1.0 |
| 0.1703 | 44.0 | 132 | 0.0615 | 1.0 |
| 0.1951 | 45.0 | 135 | 0.0547 | 1.0 |
| 0.1637 | 46.0 | 138 | 0.0536 | 1.0 |
| 0.1754 | 47.0 | 141 | 0.0506 | 1.0 |
| 0.1444 | 48.0 | 144 | 0.0519 | 1.0 |
| 0.1726 | 49.0 | 147 | 0.0545 | 1.0 |
| 0.1439 | 50.0 | 150 | 0.0553 | 1.0 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 1.12.1
- Datasets 2.12.0
- Tokenizers 0.13.1
