| license: apache-2.0 | |
| base_model: google/vit-base-patch16-224 | |
| tags: | |
| - image-classification | |
| - generated_from_trainer | |
| metrics: | |
| - accuracy | |
| model-index: | |
| - name: vit-base-pets | |
| 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-pets | |
| This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the pcuenq/oxford-pets dataset. | |
| It achieves the following results on the evaluation set: | |
| - Loss: 0.3168 | |
| - Accuracy: 0.9432 | |
| ## 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: 0.0003 | |
| - train_batch_size: 128 | |
| - eval_batch_size: 16 | |
| - seed: 42 | |
| - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 | |
| - lr_scheduler_type: linear | |
| - num_epochs: 5 | |
| - mixed_precision_training: Native AMP | |
| ### Training results | |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| | |
| | 1.5136 | 1.0 | 47 | 1.1031 | 0.8430 | | |
| | 0.5547 | 2.0 | 94 | 0.5232 | 0.9269 | | |
| | 0.4111 | 3.0 | 141 | 0.3988 | 0.9310 | | |
| | 0.3438 | 4.0 | 188 | 0.3553 | 0.9337 | | |
| | 0.298 | 5.0 | 235 | 0.3448 | 0.9296 | | |
| ### Framework versions | |
| - Transformers 4.39.2 | |
| - Pytorch 2.1.2 | |
| - Datasets 2.16.0 | |
| - Tokenizers 0.15.2 | |