<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
swin-base-patch4-window7-224-in22k-finetuned-brain-tumor-final_04
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: 0.1011
- Accuracy: 0.9675
- F1 Score: 0.9673
- Precision: 0.9675
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
---|---|---|---|---|---|---|
0.8612 | 0.96 | 20 | 0.5617 | 0.8041 | 0.7839 | 0.8166 |
0.2544 | 1.98 | 41 | 0.3496 | 0.8759 | 0.8723 | 0.8858 |
0.1305 | 2.99 | 62 | 0.1768 | 0.9294 | 0.9285 | 0.9323 |
0.0766 | 4.0 | 83 | 0.1201 | 0.9510 | 0.9503 | 0.9507 |
0.0651 | 4.96 | 103 | 0.1046 | 0.9636 | 0.9633 | 0.9641 |
0.0532 | 5.98 | 124 | 0.1001 | 0.9664 | 0.9660 | 0.9663 |
0.0374 | 6.99 | 145 | 0.1416 | 0.9505 | 0.9498 | 0.9515 |
0.0263 | 8.0 | 166 | 0.1032 | 0.9630 | 0.9626 | 0.9628 |
0.0234 | 8.96 | 186 | 0.1011 | 0.9675 | 0.9673 | 0.9675 |
0.0207 | 9.64 | 200 | 0.1026 | 0.9647 | 0.9644 | 0.9647 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3