| --- |
| license: apache-2.0 |
| base_model: google/vit-base-patch16-224 |
| tags: |
| - image-classification |
| - beans |
| - mit-augmentation |
| - generated_from_trainer |
| datasets: |
| - beans |
| metrics: |
| - accuracy |
| model-index: |
| - name: beans_mit_aug_tens |
| results: |
| - task: |
| name: Image Classification |
| type: image-classification |
| dataset: |
| name: nateraw/beans |
| type: beans |
| config: default |
| split: validation |
| args: default |
| metrics: |
| - name: Accuracy |
| type: accuracy |
| value: 0.9924812030075187 |
| --- |
| |
| <!-- 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. --> |
|
|
| # beans_mit_aug_tens |
| |
| This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the nateraw/beans dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 0.0343 |
| - Accuracy: 0.9925 |
| |
| ## 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: 16 |
| - 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 | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 0.1483 | 1.0 | 259 | 0.0907 | 0.9774 | |
| | 0.0172 | 2.0 | 518 | 0.0064 | 0.9925 | |
| | 0.0008 | 3.0 | 777 | 0.0249 | 0.9925 | |
| | 0.0002 | 4.0 | 1036 | 0.0343 | 0.9925 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.38.2 |
| - Pytorch 2.7.0+cu126 |
| - Datasets 3.6.0 |
| - Tokenizers 0.15.2 |
| |
