--- license: apache-2.0 tags: - image-classification - generated_from_trainer metrics: - accuracy - recall - f1 - precision model-index: - name: vit-base-augmented-ph2-patch-16 results: [] --- # vit-base-augmented-ph2-patch-16 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the ahishamm/Augmented_PH2_db_sharpened dataset. It achieves the following results on the evaluation set: - Loss: 0.5420 - Accuracy: 0.8444 - Recall: 0.8444 - F1: 0.8444 - Precision: 0.8444 ## 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 | |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:------:|:---------:| | 0.0592 | 0.36 | 50 | 0.7161 | 0.8068 | 0.8068 | 0.8068 | 0.8068 | | 0.0703 | 0.72 | 100 | 0.5420 | 0.8444 | 0.8444 | 0.8444 | 0.8444 | | 0.0042 | 1.09 | 150 | 0.5557 | 0.8821 | 0.8821 | 0.8821 | 0.8821 | | 0.0034 | 1.45 | 200 | 0.6464 | 0.8701 | 0.8701 | 0.8701 | 0.8701 | | 0.0023 | 1.81 | 250 | 0.7943 | 0.8410 | 0.8410 | 0.8410 | 0.8410 | | 0.0018 | 2.17 | 300 | 0.7109 | 0.8598 | 0.8598 | 0.8598 | 0.8598 | | 0.0015 | 2.54 | 350 | 0.7254 | 0.8598 | 0.8598 | 0.8598 | 0.8598 | | 0.0013 | 2.9 | 400 | 0.7364 | 0.8598 | 0.8598 | 0.8598 | 0.8598 | | 0.0013 | 3.26 | 450 | 0.7438 | 0.8615 | 0.8615 | 0.8615 | 0.8615 | | 0.0012 | 3.62 | 500 | 0.7489 | 0.8615 | 0.8615 | 0.8615 | 0.8615 | | 0.0012 | 3.99 | 550 | 0.7506 | 0.8615 | 0.8615 | 0.8615 | 0.8615 | ### Framework versions - Transformers 4.30.2 - Pytorch 2.0.1+cu118 - Datasets 2.13.1 - Tokenizers 0.13.3