vit-base-xray-pneumonia-lcbsi
This model is a fine-tuned version of nickmuchi/vit-base-xray-pneumonia on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3775
- Accuracy: 0.9773
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: 1e-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 |
|---|---|---|---|---|
| 1.5887 | 0.98 | 27 | 1.4949 | 0.4413 |
| 1.3065 | 1.98 | 54 | 1.1940 | 0.888 |
| 0.9621 | 2.98 | 81 | 0.9100 | 0.9493 |
| 0.792 | 3.98 | 108 | 0.7025 | 0.9653 |
| 0.5976 | 4.98 | 135 | 0.5612 | 0.972 |
| 0.4804 | 5.98 | 162 | 0.4705 | 0.9747 |
| 0.4194 | 6.98 | 189 | 0.4131 | 0.976 |
| 0.373 | 7.98 | 216 | 0.3775 | 0.9773 |
| 0.3402 | 8.98 | 243 | 0.3616 | 0.976 |
| 0.3308 | 9.98 | 270 | 0.3538 | 0.976 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.7.1
- Tokenizers 0.13.2