|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: VIT_AI_image_detector |
|
results: [] |
|
--- |
|
|
|
<!-- 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_AI_image_detector |
|
|
|
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/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 |
|
|
