ตั้งค่าโมเดลให้อยู่ในโหมดประเมินผล

metric = evaluate.load("glue", "mrpc")

# Set the model in evaluation mode
____.____()
for step, batch in enumerate(eval_dataloader):
    with torch.no_grad():
        outputs = model(**batch)
    predictions = outputs.logits.argmax(dim=-1)
    # Aggregate values across devices
    predictions, references = ____.____((predictions, batch["labels"]))
    metric.add_batch(predictions=predictions, references=references)
# Compute the evaluation metric
eval_metric = metric.____()
print(eval_metric)