<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
vit-base-lfw-face
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2539
- Accuracy: 0.9742
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 3.4943 | 0.41 | 100 | 2.8682 | 0.5572 |
| 2.6744 | 0.83 | 200 | 1.9178 | 0.7601 |
| 1.7785 | 1.24 | 300 | 1.2370 | 0.8819 |
| 1.4402 | 1.66 | 400 | 0.8530 | 0.9336 |
| 0.8081 | 2.07 | 500 | 0.6033 | 0.9446 |
| 0.6349 | 2.49 | 600 | 0.4308 | 0.9631 |
| 0.526 | 2.9 | 700 | 0.3396 | 0.9705 |
| 0.3106 | 3.32 | 800 | 0.2789 | 0.9742 |
| 0.2481 | 3.73 | 900 | 0.2539 | 0.9742 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3
