vit-tiny-lfw-faces
This model is a fine-tuned version of WinKawaks/vit-tiny-patch16-224 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6708
- Accuracy: 0.1759
- F1 Macro: 0.0048
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 3.7386 | 1.0 | 142 | 3.6954 | 0.1759 | 0.0048 |
| 3.7551 | 2.0 | 284 | 3.6838 | 0.1759 | 0.0048 |
| 3.6306 | 3.0 | 426 | 3.6823 | 0.1759 | 0.0048 |
| 3.6772 | 4.0 | 568 | 3.6761 | 0.1759 | 0.0048 |
| 3.6845 | 5.0 | 710 | 3.6715 | 0.1759 | 0.0048 |
| 3.6519 | 6.0 | 852 | 3.6700 | 0.1759 | 0.0048 |
| 3.8394 | 7.0 | 994 | 3.6684 | 0.1759 | 0.0048 |
| 3.5821 | 8.0 | 1136 | 3.6674 | 0.1759 | 0.0048 |
Framework versions
- Transformers 5.10.1
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2