CGIAR
This model is a fine-tuned version of gianlab/swin-tiny-patch4-window7-224-finetuned-plantdisease on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7888
- Accuracy: 0.6571
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: 0.001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0123 | 1.0 | 652 | 0.8818 | 0.6178 |
| 0.8619 | 2.0 | 1304 | 0.8398 | 0.6346 |
| 0.8324 | 3.0 | 1956 | 0.8233 | 0.6366 |
| 0.7872 | 4.0 | 2608 | 0.7888 | 0.6571 |
Framework versions
- Transformers 4.37.1
- Pytorch 2.0.0
- Datasets 2.16.1
- Tokenizers 0.15.0