<!-- 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-mae-large-ai-or-not
This model is a fine-tuned version of facebook/vit-mae-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1883
- Accuracy: 0.9683
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 |
|---|---|---|---|---|
| 0.3623 | 0.19 | 200 | 0.2099 | 0.9243 |
| 0.2465 | 0.38 | 400 | 0.4055 | 0.8545 |
| 0.2164 | 0.57 | 600 | 0.1808 | 0.9259 |
| 0.1943 | 0.76 | 800 | 0.1765 | 0.9329 |
| 0.1723 | 0.95 | 1000 | 0.2083 | 0.9313 |
| 0.118 | 1.15 | 1200 | 0.2295 | 0.9168 |
| 0.0812 | 1.34 | 1400 | 0.1600 | 0.9511 |
| 0.082 | 1.53 | 1600 | 0.1331 | 0.9624 |
| 0.0863 | 1.72 | 1800 | 0.1352 | 0.9511 |
| 0.0858 | 1.91 | 2000 | 0.1643 | 0.9506 |
| 0.056 | 2.1 | 2200 | 0.1930 | 0.9586 |
| 0.0319 | 2.29 | 2400 | 0.1595 | 0.9624 |
| 0.0206 | 2.48 | 2600 | 0.2937 | 0.9447 |
| 0.0299 | 2.67 | 2800 | 0.1680 | 0.9603 |
| 0.0213 | 2.86 | 3000 | 0.1746 | 0.9586 |
| 0.0164 | 3.05 | 3200 | 0.1579 | 0.9624 |
| 0.0019 | 3.24 | 3400 | 0.1787 | 0.9646 |
| 0.0022 | 3.44 | 3600 | 0.1976 | 0.9640 |
| 0.0023 | 3.63 | 3800 | 0.2017 | 0.9651 |
| 0.0045 | 3.82 | 4000 | 0.1883 | 0.9683 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
