|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small |
|
tags: |
|
- image-classification |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: ViT-NIH-Chest-X-ray-dataset-small |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# ViT-NIH-Chest-X-ray-dataset-small |
|
|
|
This model is a fine-tuned version of [Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small](https://huggingface.co/Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small) on the Sohaibsoussi/NIH-Chest-X-ray-dataset-small dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2988 |
|
- Accuracy: 0.2299 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.2128 | 0.3690 | 100 | 0.2092 | 0.0 | |
|
| 0.1848 | 0.7380 | 200 | 0.1909 | 0.3821 | |
|
| 0.171 | 1.1070 | 300 | 0.1967 | 0.5387 | |
|
| 0.1772 | 1.4760 | 400 | 0.1932 | 0.5451 | |
|
| 0.1629 | 1.8450 | 500 | 0.1842 | 0.4486 | |
|
| 0.1942 | 2.2140 | 600 | 0.1770 | 0.4197 | |
|
| 0.1714 | 2.5830 | 700 | 0.1797 | 0.5023 | |
|
| 0.1832 | 2.9520 | 800 | 0.1730 | 0.3688 | |
|
| 0.1766 | 3.3210 | 900 | 0.1755 | 0.3428 | |
|
| 0.1697 | 3.6900 | 1000 | 0.1601 | 0.5168 | |
|
| 0.1568 | 4.0590 | 1100 | 0.1577 | 0.5353 | |
|
| 0.1484 | 4.4280 | 1200 | 0.1514 | 0.4919 | |
|
| 0.1483 | 4.7970 | 1300 | 0.1482 | 0.5699 | |
|
| 0.1301 | 5.1661 | 1400 | 0.1315 | 0.5434 | |
|
| 0.1149 | 5.5351 | 1500 | 0.1294 | 0.5584 | |
|
| 0.1448 | 5.9041 | 1600 | 0.1266 | 0.5416 | |
|
| 0.1035 | 6.2731 | 1700 | 0.1151 | 0.6017 | |
|
| 0.1048 | 6.6421 | 1800 | 0.1060 | 0.6046 | |
|
| 0.1168 | 7.0111 | 1900 | 0.1007 | 0.6173 | |
|
| 0.1104 | 7.3801 | 2000 | 0.0949 | 0.6445 | |
|
| 0.0873 | 7.7491 | 2100 | 0.0923 | 0.6526 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.5.1+cu121 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
