<!-- 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-image-classification-yenthienviet
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the image-classification-yenthienviet dataset. It achieves the following results on the evaluation set:
- Loss: 0.2380
- Accuracy: 0.9344
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6118 | 0.56 | 100 | 0.4854 | 0.8616 |
| 0.329 | 1.11 | 200 | 0.4473 | 0.8616 |
| 0.3002 | 1.67 | 300 | 0.4167 | 0.8637 |
| 0.1549 | 2.22 | 400 | 0.2911 | 0.9178 |
| 0.1993 | 2.78 | 500 | 0.2934 | 0.9168 |
| 0.1071 | 3.33 | 600 | 0.2389 | 0.9324 |
| 0.1027 | 3.89 | 700 | 0.2380 | 0.9344 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1
