vit-fine-tune-CIFAR-10-100Epochs-v1
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the CIFAR 10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1420
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: 8
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0361 | 1.0 | 6250 | 0.1444 |
| 0.0075 | 2.0 | 12500 | 0.1456 |
| 0.0006 | 3.0 | 18750 | 0.1818 |
| 0.1435 | 4.0 | 25000 | 0.1572 |
| 0.0002 | 5.0 | 31250 | 0.1389 |
| 0.0004 | 6.0 | 37500 | 0.1366 |
| 0.0 | 7.0 | 43750 | 0.1531 |
| 0.0 | 8.0 | 50000 | 0.1327 |
| 0.0 | 9.0 | 56250 | 0.1483 |
| 0.0 | 10.0 | 62500 | 0.1420 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1