swin-tiny-patch4-window7-224-finetuned-geo-industrials
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0742
- Accuracy: 0.9756
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 |
|---|---|---|---|---|
| 0.2648 | 1.0 | 190 | 0.1152 | 0.9634 |
| 0.1807 | 2.0 | 380 | 0.0897 | 0.9711 |
| 0.1267 | 3.0 | 570 | 0.0742 | 0.9756 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cpu
- Datasets 2.14.6
- Tokenizers 0.14.1