| --- |
| license: apache-2.0 |
| tags: |
| - image-classification |
| - generated_from_trainer |
| metrics: |
| - accuracy |
| model-index: |
| - name: modelversion01 |
| 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. --> |
|
|
| # modelversion01 |
|
|
| 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 sudo-s/herbier_mesuem1 dataset. |
| It achieves the following results on the evaluation set: |
| - Loss: 1.3888 |
| - Accuracy: 0.7224 |
| |
| ## 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: 1 |
| - mixed_precision_training: Native AMP |
| |
| ### Training results |
| |
| | Training Loss | Epoch | Step | Validation Loss | Accuracy | |
| |:-------------:|:-----:|:----:|:---------------:|:--------:| |
| | 3.1304 | 0.16 | 100 | 3.1546 | 0.3254 | |
| | 2.6514 | 0.31 | 200 | 2.5058 | 0.4854 | |
| | 2.0636 | 0.47 | 300 | 2.0647 | 0.5771 | |
| | 1.7812 | 0.63 | 400 | 1.7536 | 0.6423 | |
| | 1.5857 | 0.78 | 500 | 1.5272 | 0.6974 | |
| | 1.3055 | 0.94 | 600 | 1.3888 | 0.7224 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.20.0 |
| - Pytorch 1.11.0+cu113 |
| - Datasets 2.3.2 |
| - Tokenizers 0.12.1 |
| |
