|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
base_model: google/vit-base-patch16-224-in21k |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: vit-xray-pneumonia-classification |
|
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-xray-pneumonia-classification |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1602 |
|
- Accuracy: 0.9313 |
|
|
|
## 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-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 15 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:------:|:----:|:---------------:|:--------:| |
|
| 0.4638 | 0.9882 | 63 | 0.2024 | 0.9236 | |
|
| 0.1987 | 1.9922 | 127 | 0.1342 | 0.9588 | |
|
| 0.1637 | 2.9961 | 191 | 0.1534 | 0.9442 | |
|
| 0.16 | 4.0 | 255 | 0.1365 | 0.9485 | |
|
| 0.1344 | 4.9882 | 318 | 0.1602 | 0.9313 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.40.1 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.0 |
|
- Tokenizers 0.19.1 |
|
|
