# hyperparameters
batch_size = 32
lr = 1e-4
num_epochs = 5
temperature = 2.0
alpha = 0.5

# define optimizer
optimizer = optim.Adam(student_model.parameters(), lr=lr)

# create training data loader
dataloader = DataLoader(tokenized_data['train'], batch_size=batch_size)
# create testing data loader
test_dataloader = DataLoader(tokenized_data['test'], batch_size=batch_size)