vit-base-patch16-224-drfx-CT-classifier
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: 0.6281
- Accuracy: 0.7059
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| No log | 1.0 | 4 | 0.7020 | 0.5294 |
| No log | 2.0 | 8 | 0.6686 | 0.6471 |
| 0.7085 | 3.0 | 12 | 0.6509 | 0.5882 |
| 0.7085 | 4.0 | 16 | 0.6336 | 0.6471 |
| 0.6847 | 5.0 | 20 | 0.6281 | 0.7059 |
| 0.6847 | 6.0 | 24 | 0.6256 | 0.7059 |
| 0.6847 | 7.0 | 28 | 0.6229 | 0.7059 |
| 0.6814 | 8.0 | 32 | 0.6218 | 0.7059 |
| 0.6814 | 9.0 | 36 | 0.6214 | 0.7059 |
| 0.6717 | 10.0 | 40 | 0.6213 | 0.7059 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3