| --- |
| license: apache-2.0 |
| tags: |
| - image-classification |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| - recall |
| - f1 |
| - precision |
| model-index: |
| - name: vit-base-augmented-ph2-patch-32 |
| 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-base-augmented-ph2-patch-32 |
|
|
| This model is a fine-tuned version of [google/vit-base-patch32-224-in21k](https://huggingface.co/google/vit-base-patch32-224-in21k) on the ahishamm/Augmented_PH2_db_sharpened dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.3904 |
| - Accuracy: 0.8684 |
| - Recall: 0.8684 |
| - F1: 0.8684 |
| - Precision: 0.8684 |
| |
| ## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
| - lr_scheduler_type: linear |
| - num_epochs: 4 |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | Recall | F1 | Precision | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| |
| | 0.1087 | 0.36 | 50 | 0.3904 | 0.8684 | 0.8684 | 0.8684 | 0.8684 | |
| | 0.066 | 0.72 | 100 | 0.7073 | 0.8274 | 0.8274 | 0.8274 | 0.8274 | |
| | 0.0092 | 1.09 | 150 | 0.6635 | 0.8154 | 0.8154 | 0.8154 | 0.8154 | |
| | 0.0716 | 1.45 | 200 | 0.7824 | 0.8342 | 0.8342 | 0.8342 | 0.8342 | |
| | 0.0056 | 1.81 | 250 | 0.5071 | 0.8957 | 0.8957 | 0.8957 | 0.8957 | |
| | 0.0023 | 2.17 | 300 | 0.5978 | 0.8855 | 0.8855 | 0.8855 | 0.8855 | |
| | 0.0019 | 2.54 | 350 | 0.6143 | 0.8855 | 0.8855 | 0.8855 | 0.8855 | |
| | 0.0016 | 2.9 | 400 | 0.6227 | 0.8889 | 0.8889 | 0.8889 | 0.8889 | |
| | 0.0015 | 3.26 | 450 | 0.6294 | 0.8889 | 0.8889 | 0.8889 | 0.8889 | |
| | 0.0014 | 3.62 | 500 | 0.6338 | 0.8889 | 0.8889 | 0.8889 | 0.8889 | |
| | 0.0014 | 3.99 | 550 | 0.6351 | 0.8889 | 0.8889 | 0.8889 | 0.8889 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.30.2 |
| - Pytorch 2.0.1+cu118 |
| - Datasets 2.13.1 |
| - Tokenizers 0.13.3 |
| |
