metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ConvNeXT_AI_image_detector
results: []
ConvNeXT_AI_image_detector
This model is a fine-tuned version of facebook/convnext-tiny-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0518
- Accuracy: 0.9826
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 |
|---|---|---|---|---|
| 0.2164 | 1.0 | 1093 | 0.1476 | 0.9444 |
| 0.1647 | 2.0 | 2187 | 0.0872 | 0.9673 |
| 0.1784 | 3.0 | 3281 | 0.0761 | 0.9709 |
| 0.1247 | 4.0 | 4375 | 0.0869 | 0.9666 |
| 0.0994 | 5.0 | 5468 | 0.0808 | 0.9696 |
| 0.073 | 6.0 | 6562 | 0.0514 | 0.9820 |
| 0.0924 | 7.0 | 7656 | 0.0526 | 0.9809 |
| 0.0779 | 8.0 | 8750 | 0.0518 | 0.9819 |
| 0.0903 | 9.0 | 9843 | 0.0518 | 0.9826 |
| 0.0721 | 9.99 | 10930 | 0.0512 | 0.9817 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.13.3