# create testing data loader
validation_dataloader = DataLoader(tokenized_data['validation'], batch_size=8)

# Evaluate the teacher model
teacher_accuracy, teacher_precision, teacher_recall, teacher_f1 = 
                   evaluate_model(teacher_model, validation_dataloader, device)
print(f"Teacher (validation) - Accuracy: {teacher_accuracy:.4f}, 
                               Precision: {teacher_precision:.4f}, 
                               Recall: {teacher_recall:.4f}, 
                               F1 Score: {teacher_f1:.4f}")

# Evaluate the student model
student_accuracy, student_precision, student_recall, student_f1 = 
                   evaluate_model(student_model, validation_dataloader, device)
print(f"Student (validation) - Accuracy: {student_accuracy:.4f}, 
                               Precision: {student_precision:.4f}, 
                               Recall: {student_recall:.4f}, 
                               F1 Score: {student_f1:.4f}")