finetuned-ai-real-cifake

This model is a fine-tuned version of ongtrandong2/ai_vs_real_image_detection on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.0622
• Accuracy: 0.9756

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: 32
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4286	0.3617	200	0.4256	0.8549
0.3499	0.7233	400	0.1693	0.9353
0.2664	1.0850	600	0.3467	0.8690
0.2303	1.4467	800	0.4582	0.8398
0.1553	1.8083	1000	0.2135	0.9186
0.1751	2.1700	1200	0.0793	0.9715
0.1383	2.5316	1400	0.0638	0.9753
0.1375	2.8933	1600	0.0622	0.9756

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0