vit-base-fashion
This model is a fine-tuned version of google/vit-base-patch16-224 on the zalando-datasets/fashion_mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.2513
- Accuracy: 0.9102
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2888 | 1.0 | 3000 | 0.2934 | 0.8917 |
| 0.3066 | 2.0 | 6000 | 0.2694 | 0.9013 |
| 0.2722 | 3.0 | 9000 | 0.2589 | 0.9042 |
| 0.2593 | 4.0 | 12000 | 0.2576 | 0.9048 |
| 0.2422 | 5.0 | 15000 | 0.2540 | 0.9078 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.4.1
- Tokenizers 0.21.1