vit-base-patch16-224-v23
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0692
- Accuracy: 0.9770
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1353 | 1.0 | 190 | 0.1414 | 0.9511 |
| 0.0729 | 2.0 | 380 | 0.0934 | 0.9685 |
| 0.0325 | 3.0 | 570 | 0.0692 | 0.9770 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3