swin-tiny-patch4-window7-224-finetuned-FaceAIorNot200
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: 0.7310
- Accuracy: 0.65
- Precision: 1.0
- Recall: 0.3
- F1: 0.4615
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 | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 0.67 | 1 | 0.4061 | 0.85 | 0.8889 | 0.8 | 0.8421 |
| No log | 2.0 | 3 | 0.7310 | 0.65 | 1.0 | 0.3 | 0.4615 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.2