swin-base-patch4-window7-224-in22k-finetuned-batch8-22k
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224-in22k on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.0984
- Accuracy: 0.9886
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.3752 | 0.9697 | 24 | 0.1119 | 0.9659 |
| 0.2189 | 1.9798 | 49 | 0.1690 | 0.9375 |
| 0.0343 | 2.9899 | 74 | 0.0886 | 0.9830 |
| 0.009 | 4.0 | 99 | 0.0969 | 0.9830 |
| 0.0015 | 4.8485 | 120 | 0.0984 | 0.9886 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1