metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: finetune-apple-leaf
results: []
finetune-apple-leaf
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0682
- Accuracy: 0.9957
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: 2e-05
- train_batch_size: 64
- eval_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.1988 | 1.0 | 209 | 0.1881 | 0.9957 |
| 0.1012 | 2.0 | 418 | 0.1110 | 0.9953 |
| 0.1171 | 3.0 | 627 | 0.0925 | 0.9928 |
| 0.0766 | 4.0 | 836 | 0.0707 | 0.9966 |
| 0.0723 | 5.0 | 1045 | 0.0682 | 0.9957 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.1.2
- Datasets 2.19.1
- Tokenizers 0.19.1