metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VIT_AI_image_detector
results: []
VIT_AI_image_detector
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0278
- Accuracy: 0.9931
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1943 | 1.0 | 1406 | 0.0682 | 0.9757 |
| 0.1288 | 2.0 | 2812 | 0.0423 | 0.9852 |
| 0.0952 | 3.0 | 4218 | 0.0393 | 0.9866 |
| 0.0743 | 4.0 | 5625 | 0.0410 | 0.9866 |
| 0.0587 | 5.0 | 7031 | 0.0332 | 0.9889 |
| 0.0493 | 6.0 | 8437 | 0.0253 | 0.9919 |
| 0.06 | 7.0 | 9843 | 0.0279 | 0.9922 |
| 0.0738 | 8.0 | 11250 | 0.0326 | 0.9907 |
| 0.065 | 9.0 | 12656 | 0.0278 | 0.9931 |
| 0.045 | 10.0 | 14060 | 0.0279 | 0.9928 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3