swin-tiny-patch4-window7-224-fraud_number_classification
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: 0.0107
- Accuracy: 0.9963
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0229 | 1.0 | 19 | 0.0516 | 0.9851 |
| 0.0193 | 2.0 | 38 | 0.0107 | 0.9963 |
| 0.0062 | 3.0 | 57 | 0.0275 | 0.9963 |
| 0.0172 | 4.0 | 76 | 0.0313 | 0.9963 |
| 0.028 | 5.0 | 95 | 0.0431 | 0.9926 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1