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: 0.0466
- Accuracy: 0.9847
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 |
|---|---|---|---|---|
| 0.1893 | 1.0 | 1406 | 0.1578 | 0.9399 |
| 0.1777 | 2.0 | 2812 | 0.1009 | 0.9632 |
| 0.1255 | 3.0 | 4218 | 0.0752 | 0.9709 |
| 0.1296 | 4.0 | 5625 | 0.0808 | 0.9715 |
| 0.1154 | 5.0 | 7031 | 0.1031 | 0.963 |
| 0.089 | 6.0 | 8437 | 0.0569 | 0.9794 |
| 0.0949 | 7.0 | 9843 | 0.0468 | 0.9846 |
| 0.0808 | 8.0 | 11250 | 0.0466 | 0.9847 |
| 0.1091 | 9.0 | 12656 | 0.0507 | 0.9826 |
| 0.0765 | 10.0 | 14060 | 0.0521 | 0.9829 |
Framework versions
- Transformers 4.30.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3