|
--- |
|
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: 0.6731 |
|
- Accuracy: 0.2189 |
|
|
|
## 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: 9 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.0271 | 0.3690 | 100 | 0.0347 | 0.8584 | |
|
| 0.0334 | 0.7380 | 200 | 0.0291 | 0.8624 | |
|
| 0.0438 | 1.1070 | 300 | 0.0352 | 0.8607 | |
|
| 0.0215 | 1.4760 | 400 | 0.0319 | 0.8746 | |
|
| 0.0267 | 1.8450 | 500 | 0.0277 | 0.8798 | |
|
| 0.0266 | 2.2140 | 600 | 0.0177 | 0.9116 | |
|
| 0.014 | 2.5830 | 700 | 0.0127 | 0.9497 | |
|
| 0.0207 | 2.9520 | 800 | 0.0144 | 0.9410 | |
|
| 0.0115 | 3.3210 | 900 | 0.0097 | 0.9653 | |
|
| 0.0113 | 3.6900 | 1000 | 0.0077 | 0.9711 | |
|
| 0.0054 | 4.0590 | 1100 | 0.0068 | 0.9844 | |
|
| 0.0047 | 4.4280 | 1200 | 0.0046 | 0.9850 | |
|
| 0.0056 | 4.7970 | 1300 | 0.0040 | 0.9902 | |
|
| 0.0026 | 5.1661 | 1400 | 0.0032 | 0.9925 | |
|
| 0.0037 | 5.5351 | 1500 | 0.0027 | 0.9936 | |
|
| 0.0039 | 5.9041 | 1600 | 0.0023 | 0.9977 | |
|
| 0.0019 | 6.2731 | 1700 | 0.0019 | 0.9971 | |
|
| 0.0019 | 6.6421 | 1800 | 0.0017 | 0.9988 | |
|
| 0.0016 | 7.0111 | 1900 | 0.0015 | 1.0 | |
|
| 0.002 | 7.3801 | 2000 | 0.0014 | 1.0 | |
|
| 0.0013 | 7.7491 | 2100 | 0.0014 | 1.0 | |
|
| 0.0015 | 8.1181 | 2200 | 0.0013 | 1.0 | |
|
| 0.0011 | 8.4871 | 2300 | 0.0013 | 1.0 | |
|
| 0.0013 | 8.8561 | 2400 | 0.0013 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.3 |
|
- Pytorch 2.4.0 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
