<!-- 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_07
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: 0.2904
- Accuracy: 0.9095
- F1 Score: 0.9095
- Precision: 0.9189
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 |
|---|---|---|---|---|---|---|
| 1.3335 | 0.98 | 13 | 0.9195 | 0.6281 | 0.6111 | 0.7245 |
| 0.6062 | 1.96 | 26 | 0.6114 | 0.7625 | 0.7673 | 0.8385 |
| 0.274 | 2.94 | 39 | 0.5468 | 0.7802 | 0.7772 | 0.8533 |
| 0.1211 | 4.0 | 53 | 0.3922 | 0.8417 | 0.8417 | 0.8749 |
| 0.0991 | 4.98 | 66 | 0.4734 | 0.8172 | 0.8209 | 0.8802 |
| 0.0682 | 5.96 | 79 | 0.3751 | 0.8599 | 0.8600 | 0.8882 |
| 0.0414 | 6.94 | 92 | 0.2951 | 0.8986 | 0.8995 | 0.9100 |
| 0.0264 | 8.0 | 106 | 0.3485 | 0.8844 | 0.8855 | 0.9069 |
| 0.021 | 8.98 | 119 | 0.3803 | 0.8764 | 0.8782 | 0.9031 |
| 0.0151 | 9.81 | 130 | 0.2904 | 0.9095 | 0.9095 | 0.9189 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
