SWIN-AI-Image-Detector
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0461
- Accuracy: 0.9833
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2411 | 1.0 | 547 | 0.2430 | 0.9013 |
| 0.2011 | 2.0 | 1094 | 0.1053 | 0.9593 |
| 0.1722 | 3.0 | 1641 | 0.0825 | 0.9671 |
| 0.1424 | 4.0 | 2188 | 0.0851 | 0.9686 |
| 0.1244 | 5.0 | 2735 | 0.0714 | 0.9733 |
| 0.1089 | 6.0 | 3282 | 0.0712 | 0.9734 |
| 0.1047 | 7.0 | 3829 | 0.0461 | 0.9833 |
| 0.1079 | 8.0 | 4376 | 0.0454 | 0.9829 |
| 0.0805 | 9.0 | 4923 | 0.0577 | 0.9790 |
| 0.0778 | 10.0 | 5470 | 0.0539 | 0.9807 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3