metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- image-classification
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: vit-base-brain-mri
results: []
vit-base-brain-mri
This model is a fine-tuned version of google/vit-base-patch16-224 on the BrainMRI dataset. It achieves the following results on the evaluation set:
- Loss: 1.1297
- Accuracy: 0.5685
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 14
Training results
| Training Loss | Epoch | Step | Accuracy | Validation Loss |
|---|---|---|---|---|
| No log | 1.0 | 72 | 0.6289 | 0.9818 |
| 1.0744 | 2.0 | 144 | 0.6864 | 0.8287 |
| 0.7716 | 3.0 | 216 | 0.7160 | 0.7535 |
| 0.7716 | 4.0 | 288 | 0.7404 | 0.7140 |
| 0.6975 | 5.0 | 360 | 0.7491 | 0.7015 |
| 0.6651 | 6.0 | 432 | 0.7631 | 0.6839 |
| 0.6307 | 7.0 | 504 | 0.7700 | 0.6624 |
| 0.6307 | 8.0 | 576 | 0.7822 | 0.6363 |
| 0.5857 | 9.0 | 648 | 0.7822 | 0.6089 |
| 0.576 | 10.0 | 720 | 0.7770 | 0.6249 |
| 0.576 | 11.0 | 792 | 0.6184 | 0.7840 |
| 0.5733 | 12.0 | 864 | 0.6006 | 0.7944 |
| 0.5555 | 13.0 | 936 | 0.5898 | 0.8014 |
| 0.5481 | 14.0 | 1008 | 0.5857 | 0.8223 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Tokenizers 0.19.1