| | --- |
| | license: apache-2.0 |
| | base_model: google/vit-base-patch16-224 |
| | tags: |
| | - generated_from_trainer |
| | datasets: |
| | - imagefolder |
| | metrics: |
| | - accuracy |
| | model-index: |
| | - name: vit-base-patch16-224-type |
| | results: |
| | - task: |
| | name: Image Classification |
| | type: image-classification |
| | dataset: |
| | name: imagefolder |
| | type: imagefolder |
| | config: default |
| | split: validation |
| | args: default |
| | metrics: |
| | - name: Accuracy |
| | type: accuracy |
| | value: 0.7583333333333333 |
| | --- |
| | |
| | <!-- 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-patch16-224-type |
| |
|
| | This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. |
| | It achieves the following results on the evaluation set: |
| | - Loss: 0.7249 |
| | - Accuracy: 0.7583 |
| |
|
| | ## 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 |
| |
|
| | ### Training results |
| |
|
| | | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| | |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | | 1.4991 | 0.99 | 78 | 1.2167 | 0.6019 | |
| | | 1.0157 | 1.99 | 157 | 0.8529 | 0.7083 | |
| | | 0.8163 | 3.0 | 236 | 0.7725 | 0.7287 | |
| | | 0.7916 | 4.0 | 315 | 0.7622 | 0.7343 | |
| | | 0.6525 | 4.99 | 393 | 0.7374 | 0.7361 | |
| | | 0.6159 | 5.99 | 472 | 0.7188 | 0.75 | |
| | | 0.5413 | 7.0 | 551 | 0.7029 | 0.7463 | |
| | | 0.4838 | 8.0 | 630 | 0.7254 | 0.7352 | |
| | | 0.4587 | 8.99 | 708 | 0.7219 | 0.7565 | |
| | | 0.4332 | 9.99 | 787 | 0.7077 | 0.7528 | |
| | | 0.379 | 11.0 | 866 | 0.7106 | 0.7583 | |
| | | 0.4181 | 12.0 | 945 | 0.7158 | 0.7556 | |
| | | 0.3798 | 12.99 | 1023 | 0.7234 | 0.7537 | |
| | | 0.3841 | 13.99 | 1102 | 0.7211 | 0.7556 | |
| | | 0.3464 | 14.86 | 1170 | 0.7249 | 0.7583 | |
| |
|
| |
|
| | ### Framework versions |
| |
|
| | - Transformers 4.35.2 |
| | - Pytorch 2.1.0+cu118 |
| | - Datasets 2.15.0 |
| | - Tokenizers 0.15.0 |
| |
|
