van-base-finetuned-eurosat-imgaug
This model is a fine-tuned version of Visual-Attention-Network/van-base on the image_folder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0379
- Accuracy: 0.9885
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 0.0887 | 1.0 | 190 | 0.0589 | 0.98 |
| 0.055 | 2.0 | 380 | 0.0390 | 0.9878 |
| 0.0223 | 3.0 | 570 | 0.0379 | 0.9885 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.11.6