vit-fine-tune-classification-cats-vs-dogs
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: 0.6934
- Accuracy: 0.0476
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.6972 | 1.0 | 1250 | 0.6933 | 0.4944 |
| 0.6955 | 2.0 | 2500 | 0.6958 | 0.4944 |
| 0.6944 | 3.0 | 3750 | 0.6939 | 0.4944 |
| 0.6943 | 4.0 | 5000 | 0.6993 | 0.5056 |
| 0.695 | 5.0 | 6250 | 0.6947 | 0.4944 |
| 0.6946 | 6.0 | 7500 | 0.6937 | 0.4944 |
| 0.6938 | 7.0 | 8750 | 0.6931 | 0.4944 |
| 0.6935 | 8.0 | 10000 | 0.6932 | 0.4944 |
| 0.6937 | 9.0 | 11250 | 0.6930 | 0.5056 |
| 0.6932 | 10.0 | 12500 | 0.6932 | 0.5052 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1