deepfake-detection-swin
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: 0.0554
- Accuracy: 0.9881
- F1: 0.9881
- Precision: 0.9881
- Recall: 0.9881
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| 0.1329 | 1.0 | 4759 | 0.0650 | 0.9815 | 0.9815 | 0.9818 | 0.9815 |
| 0.0907 | 2.0 | 9518 | 0.0485 | 0.9865 | 0.9865 | 0.9865 | 0.9865 |
| 0.0434 | 3.0 | 14277 | 0.0554 | 0.9881 | 0.9881 | 0.9881 | 0.9881 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2