<!-- 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_03
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: 1.3844
- Accuracy: 0.2739
- F1 Score: 0.2367
- Precision: 0.3487
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-08
- 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 |
---|---|---|---|---|---|---|
1.407 | 0.96 | 20 | 1.3971 | 0.2648 | 0.2170 | 0.3446 |
1.4124 | 1.98 | 41 | 1.3943 | 0.2665 | 0.2219 | 0.3467 |
1.4035 | 2.99 | 62 | 1.3918 | 0.2682 | 0.2255 | 0.3508 |
1.3978 | 4.0 | 83 | 1.3897 | 0.2705 | 0.2293 | 0.3512 |
1.3903 | 4.96 | 103 | 1.3880 | 0.2699 | 0.2295 | 0.3492 |
1.3978 | 5.98 | 124 | 1.3866 | 0.2733 | 0.2342 | 0.3537 |
1.3864 | 6.99 | 145 | 1.3855 | 0.2739 | 0.2362 | 0.3552 |
1.3913 | 8.0 | 166 | 1.3848 | 0.2733 | 0.2357 | 0.3507 |
1.3901 | 8.96 | 186 | 1.3844 | 0.2739 | 0.2367 | 0.3487 |
1.3921 | 9.64 | 200 | 1.3844 | 0.2739 | 0.2367 | 0.3487 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3