vit-base-patch16-224-dmae-va-U5-10-45-5e-05
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: 0.9129
- Accuracy: 0.75
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: 5.5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9 | 7 | 1.3457 | 0.5167 |
| 1.3687 | 1.94 | 15 | 1.2405 | 0.6 |
| 1.2688 | 2.97 | 23 | 1.1549 | 0.6167 |
| 1.1325 | 4.0 | 31 | 1.0675 | 0.5833 |
| 1.1325 | 4.9 | 38 | 1.0208 | 0.65 |
| 1.0211 | 5.94 | 46 | 0.9604 | 0.6 |
| 0.9458 | 6.97 | 54 | 0.9329 | 0.7 |
| 0.9048 | 8.0 | 62 | 0.9206 | 0.7167 |
| 0.9048 | 8.9 | 69 | 0.9129 | 0.75 |
| 0.8618 | 9.03 | 70 | 0.9127 | 0.75 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0