swin-tiny-patch4-window7-224-finetuned-herbify2
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: 0.0655
- 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.6649 | 0.97 | 18 | 0.5193 | 0.9242 |
| 0.4002 | 2.0 | 37 | 0.0655 | 1.0 |
| 0.1095 | 2.97 | 55 | 0.0249 | 1.0 |
| 0.0486 | 3.89 | 72 | 0.0154 | 1.0 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cpu
- Datasets 2.14.5
- Tokenizers 0.13.3