vit-base-patch16-224-finetuned-brain-tumor-classification
This model is a fine-tuned version of google/vit-base-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.4348
- Accuracy: 0.8905
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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 |
|---|---|---|---|---|
| 3.1659 | 0.9897 | 48 | 2.4060 | 0.4086 |
| 1.8381 | 2.0 | 97 | 1.2904 | 0.6772 |
| 1.0781 | 2.9897 | 145 | 0.9211 | 0.7573 |
| 0.8049 | 4.0 | 194 | 0.7274 | 0.8036 |
| 0.6091 | 4.9897 | 242 | 0.6427 | 0.8330 |
| 0.4985 | 6.0 | 291 | 0.5519 | 0.8510 |
| 0.4077 | 6.9897 | 339 | 0.4921 | 0.8792 |
| 0.3583 | 8.0 | 388 | 0.4756 | 0.8826 |
| 0.3292 | 8.9897 | 436 | 0.4472 | 0.8883 |
| 0.338 | 9.8969 | 480 | 0.4348 | 0.8905 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1