This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0662
Accuracy: 0.9743

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: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 512
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.2672	1.0	297	0.1128	0.9577
0.0958	2.0	595	0.0953	0.9634
0.0816	3.0	892	0.0776	0.9694
0.0712	4.0	1190	0.0746	0.9707
0.0647	5.0	1487	0.0680	0.9726
0.0616	6.0	1785	0.0656	0.9735
0.0565	7.0	2082	0.0676	0.9736
0.0533	7.99	2376	0.0662	0.9743

Framework versions

Transformers 4.38.1
Pytorch 2.1.2
Datasets 2.19.0
Tokenizers 0.15.2

Hemg/Deepfake-image

Deepfake-image

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Hemg/
Deepfake-image