swin-tiny-patch4-window7-224-finetuned-car0001
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: 0.0029
- Accuracy: 1.0
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: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0328 | 0.99 | 126 | 0.0029 | 1.0 |
| 0.0107 | 2.0 | 253 | 0.0001 | 1.0 |
| 0.015 | 3.0 | 380 | 0.0002 | 1.0 |
| 0.0048 | 4.0 | 507 | 0.0000 | 1.0 |
| 0.0133 | 4.99 | 633 | 0.0000 | 1.0 |
| 0.0032 | 6.0 | 760 | 0.0000 | 1.0 |
| 0.0097 | 6.96 | 882 | 0.0000 | 1.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2