Table 3. Network hyperparameters.

Outline of the network hyperparameters used for training the models. It includes key parameters like optimizer type (Adam), learning rate (3e–5), batch sizes for training and evaluation, the number of epochs (5), loss function (crossentropy), and activation function (ReLU).

Hyperparameter	Value
Optimizer	Adam
Learning rate	3e−5
Batch size	8 (training)/16 (evaluation)
Epochs	5
Loss function	Cross-entropy loss
Activation function	ReLU