swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_08
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: 0.1422
- Accuracy: 0.9537
- F1 Score: 0.9549
- Precision: 0.9564
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: 100
- eval_batch_size: 100
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 400
- 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 | F1 Score | Precision |
|---|---|---|---|---|---|---|
| 1.3618 | 0.99 | 19 | 0.6238 | 0.7541 | 0.7431 | 0.7821 |
| 0.3833 | 1.97 | 38 | 0.3097 | 0.8865 | 0.8884 | 0.8970 |
| 0.2011 | 2.96 | 57 | 0.2600 | 0.9053 | 0.9078 | 0.9171 |
| 0.1124 | 4.0 | 77 | 0.1793 | 0.9328 | 0.9342 | 0.9381 |
| 0.0711 | 4.99 | 96 | 0.1385 | 0.9497 | 0.9509 | 0.9522 |
| 0.0518 | 5.97 | 115 | 0.1506 | 0.9485 | 0.9501 | 0.9523 |
| 0.0393 | 6.96 | 134 | 0.1422 | 0.9537 | 0.9549 | 0.9564 |
| 0.0361 | 8.0 | 154 | 0.1545 | 0.9482 | 0.9497 | 0.9522 |
| 0.025 | 8.99 | 173 | 0.1482 | 0.9501 | 0.9516 | 0.9541 |
| 0.0204 | 9.87 | 190 | 0.1474 | 0.9513 | 0.9527 | 0.9550 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3