vit-base-patch16-224-finetuned-cassava-leaf-disease
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: 0.5363
- Accuracy: 0.8093
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: 200
- eval_batch_size: 200
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 800
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4458 | 0.99 | 24 | 1.0368 | 0.6687 |
| 0.6916 | 1.98 | 48 | 0.5888 | 0.7930 |
| 0.4886 | 2.97 | 72 | 0.5363 | 0.8093 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1
- Datasets 2.18.0
- Tokenizers 0.15.1