vit_itri_2class
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: 0.0109
- Accuracy: 0.9176
- Precision: 0.9113
- Recall: 0.9176
- F1: 0.9140
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| 0.0016 | 1.0 | 759 | 0.0011 | 0.9341 | 0.9261 | 0.9341 | 0.9255 |
| 0.0003 | 2.0 | 1518 | 0.0015 | 0.9496 | 0.9457 | 0.9496 | 0.9456 |
| 0.0003 | 3.0 | 2277 | 0.0021 | 0.9309 | 0.9217 | 0.9309 | 0.9209 |
| 0.0001 | 4.0 | 3036 | 0.0033 | 0.9204 | 0.9194 | 0.9204 | 0.9199 |
| 0.0001 | 5.0 | 3795 | 0.0048 | 0.9273 | 0.9180 | 0.9273 | 0.9201 |
| 0.0001 | 6.0 | 4554 | 0.0037 | 0.9168 | 0.9159 | 0.9168 | 0.9164 |
| 0.0001 | 7.0 | 5313 | 0.0090 | 0.9083 | 0.9158 | 0.9083 | 0.9116 |
| 0.0 | 8.0 | 6072 | 0.0054 | 0.9273 | 0.9185 | 0.9273 | 0.9209 |
| 0.0 | 9.0 | 6831 | 0.0089 | 0.9136 | 0.9118 | 0.9136 | 0.9126 |
| 0.0 | 10.0 | 7590 | 0.0109 | 0.9176 | 0.9113 | 0.9176 | 0.9140 |
Framework versions
- Transformers 4.53.0.dev0
- Pytorch 2.7.1+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1