vit_itri_82
This model is a fine-tuned version of google/vit-large-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0204
- Accuracy: 0.9947
- Precision: 0.9947
- Recall: 0.9947
- F1: 0.9946
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: 0.0001
- train_batch_size: 24
- eval_batch_size: 4
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.2231 | 1.0 | 1415 | 0.0780 | 0.9761 | 0.9769 | 0.9761 | 0.9759 |
| 0.0735 | 2.0 | 2830 | 0.0959 | 0.9730 | 0.9740 | 0.9730 | 0.9728 |
| 0.0359 | 3.0 | 4245 | 0.0550 | 0.9881 | 0.9884 | 0.9881 | 0.9879 |
| 0.0144 | 4.0 | 5660 | 0.0324 | 0.9923 | 0.9923 | 0.9923 | 0.9922 |
| 0.0042 | 5.0 | 7075 | 0.0204 | 0.9947 | 0.9947 | 0.9947 | 0.9946 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1