# hyperparameters
lr = 2e-4
batch_size = 8
num_epochs = 10

training_args = TrainingArguments(
    output_dir="bert-phishing-classifier_teacher",
    learning_rate=lr,
    per_device_train_batch_size=batch_size,
    per_device_eval_batch_size=batch_size,
    num_train_epochs=num_epochs,
    logging_strategy="epoch",
    eval_strategy="epoch",
    save_strategy="epoch",
    load_best_model_at_end=True,
)