<!-- 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_06
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: 0.2384
- Accuracy: 0.9226
- F1 Score: 0.9210
- Precision: 0.9214
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 |
|---|---|---|---|---|---|---|
| 1.3082 | 0.98 | 13 | 0.7669 | 0.7819 | 0.7689 | 0.7723 |
| 0.5415 | 1.96 | 26 | 0.3100 | 0.8867 | 0.8812 | 0.8816 |
| 0.279 | 2.94 | 39 | 0.2901 | 0.8992 | 0.8967 | 0.8961 |
| 0.1563 | 4.0 | 53 | 0.2655 | 0.9089 | 0.9078 | 0.9084 |
| 0.1304 | 4.98 | 66 | 0.2971 | 0.8964 | 0.8935 | 0.8958 |
| 0.1058 | 5.96 | 79 | 0.2358 | 0.9243 | 0.9218 | 0.9224 |
| 0.0971 | 6.94 | 92 | 0.2298 | 0.9260 | 0.9245 | 0.9258 |
| 0.079 | 8.0 | 106 | 0.2468 | 0.9134 | 0.9123 | 0.9125 |
| 0.0638 | 8.98 | 119 | 0.2534 | 0.9112 | 0.9097 | 0.9101 |
| 0.0538 | 9.81 | 130 | 0.2384 | 0.9226 | 0.9210 | 0.9214 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
