swin-large-ai-or-not

This model is a fine-tuned version of itsLeen/swin-large-ai-or-not on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2806
• Accuracy: 0.9690

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: 1e-07
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 20
• num_epochs: 40
• mixed_precision_training: Native AMP
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2653	1.7699	50	0.2818	0.9558
0.2522	3.5398	100	0.2812	0.9646
0.2616	5.3097	150	0.2810	0.9690
0.2541	7.0796	200	0.2808	0.9690
0.2536	8.8496	250	0.2807	0.9690
0.2534	10.6195	300	0.2806	0.9690

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1