vit-base-patch16-224-cifar10
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: 0.0506
- Accuracy: 0.9906
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: 5e-05
- train_batch_size: 128
- eval_batch_size: 64
- 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: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0405 | 1.2788 | 500 | 0.0684 | 0.9801 |
| 0.0211 | 2.5575 | 1000 | 0.0913 | 0.9763 |
| 0.0107 | 3.8363 | 1500 | 0.0541 | 0.9864 |
| 0.0045 | 5.1151 | 2000 | 0.0534 | 0.9883 |
| 0.0022 | 6.3939 | 2500 | 0.0522 | 0.989 |
| 0.0009 | 7.6726 | 3000 | 0.0506 | 0.9906 |
| 0.0012 | 8.9514 | 3500 | 0.0487 | 0.9905 |
Framework versions
- Transformers 5.3.0
- Pytorch 2.6.0+cu124
- Datasets 4.8.3
- Tokenizers 0.22.2