swin-transformer
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7366
- Accuracy: 0.39
- F1: 0.2753
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: 96
- eval_batch_size: 96
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 384
- 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 | F1 |
|---|---|---|---|---|---|
| No log | 0.7273 | 2 | 2.0766 | 0.3 | 0.2161 |
| No log | 1.8182 | 5 | 1.7687 | 0.37 | 0.2461 |
| No log | 2.1818 | 6 | 1.7366 | 0.39 | 0.2753 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.20.1