vit-base-crack-classification-2
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0212
- Accuracy: 0.9917
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.222 | 1.0 | 203 | 0.2224 | 0.9097 |
| 0.0911 | 2.0 | 406 | 0.0806 | 0.9653 |
| 0.0163 | 3.0 | 609 | 0.0560 | 0.9681 |
| 0.0126 | 4.0 | 812 | 0.0554 | 0.9792 |
| 0.0233 | 5.0 | 1015 | 0.0347 | 0.9806 |
| 0.0096 | 6.0 | 1218 | 0.0949 | 0.9792 |
| 0.0013 | 7.0 | 1421 | 0.0440 | 0.9917 |
| 0.0011 | 8.0 | 1624 | 0.0222 | 0.9917 |
| 0.0009 | 9.0 | 1827 | 0.0213 | 0.9917 |
| 0.0009 | 10.0 | 2030 | 0.0212 | 0.9917 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0