deit-tiny-patch16-224-finetuned-og-dataset-10e
This model is a fine-tuned version of facebook/deit-tiny-patch16-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.1402
- Accuracy: 0.9482
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: 48
- eval_batch_size: 48
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.5434 | 1.0 | 364 | 0.4649 | 0.8004 |
| 0.3968 | 2.0 | 728 | 0.3146 | 0.8713 |
| 0.3075 | 3.0 | 1092 | 0.2477 | 0.9012 |
| 0.2961 | 4.0 | 1456 | 0.1774 | 0.9335 |
| 0.2523 | 5.0 | 1820 | 0.1559 | 0.9422 |
| 0.2304 | 6.0 | 2184 | 0.1402 | 0.9482 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2