vit-base-patch16-224-in21k-mnist-21
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the mnist dataset. It achieves the following results on the evaluation set:
- Loss: 0.0234
- Accuracy: 0.994
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: 32
- eval_batch_size: 256
- seed: 21
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.8042 | 1.0 | 1594 | 0.1245 | 0.9836 |
0.388 | 2.0 | 3188 | 0.0610 | 0.9906 |
0.3517 | 3.0 | 4782 | 0.0469 | 0.9903 |
0.3194 | 4.0 | 6376 | 0.0415 | 0.9908 |
0.3079 | 5.0 | 7970 | 0.0342 | 0.9923 |
0.2888 | 6.0 | 9564 | 0.0326 | 0.9921 |
0.2853 | 7.0 | 11158 | 0.0284 | 0.9926 |
0.2692 | 8.0 | 12752 | 0.0252 | 0.9931 |
0.2688 | 9.0 | 14346 | 0.0247 | 0.9934 |
0.2643 | 10.0 | 15940 | 0.0234 | 0.994 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.13.3
- Downloads last month
- 5