swin-tiny-patch4-window7-224-finetuned-HOMUS
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1539
- Accuracy: 0.9561
- Precision: 0.9565
- Recall: 0.9561
- F1 Score: 0.9561
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 1.2499 | 1.0 | 83 | 0.8461 | 0.7127 | 0.7385 | 0.7127 | 0.6973 |
| 0.3816 | 1.99 | 166 | 0.3134 | 0.8838 | 0.8923 | 0.8838 | 0.8802 |
| 0.2474 | 2.99 | 249 | 0.2274 | 0.9184 | 0.9247 | 0.9184 | 0.9176 |
| 0.1276 | 4.0 | 333 | 0.2281 | 0.9197 | 0.9255 | 0.9197 | 0.9194 |
| 0.0933 | 5.0 | 416 | 0.1916 | 0.9364 | 0.9407 | 0.9364 | 0.9361 |
| 0.0629 | 5.99 | 499 | 0.1796 | 0.9443 | 0.9466 | 0.9443 | 0.9441 |
| 0.054 | 6.99 | 582 | 0.1701 | 0.9465 | 0.9466 | 0.9465 | 0.9462 |
| 0.0228 | 8.0 | 666 | 0.1652 | 0.9482 | 0.9484 | 0.9482 | 0.9480 |
| 0.0297 | 9.0 | 749 | 0.1518 | 0.9548 | 0.9552 | 0.9548 | 0.9547 |
| 0.0221 | 9.97 | 830 | 0.1539 | 0.9561 | 0.9565 | 0.9561 | 0.9561 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3