트레이닝 에러 발생

for epoch in range(EPOCHS):
  start = time.time()

  train_loss.reset_states()
  train_accuracy.reset_states()

  # inp -> portuguese, tar -> english
  for (batch, (inp, tar)) in enumerate(train_batches):
    train_step(inp, tar)

    if batch % 50 == 0:
      print(f'Epoch {epoch + 1} Batch {batch} Loss {train_loss.result():.4f} Accuracy {train_accuracy.result():.4f}')

  if (epoch + 1) % 5 == 0:
    ckpt_save_path = ckpt_manager.save()
    print(f'Saving checkpoint for epoch {epoch+1} at {ckpt_save_path}')

  print(f'Epoch {epoch + 1} Loss {train_loss.result():.4f} Accuracy {train_accuracy.result():.4f}')

  print(f'Time taken for 1 epoch: {time.time() - start:.2f} secs\n')

위 코드에서 에러 발생합니다. GPT 에도 물어보고 해도 답이 안나와서 조치 방법 질문드립니다.

AttributeError                            Traceback (most recent call last)

<ipython-input-109-d5f75ec190c4> in <cell line: 1>()
      2   start = time.time()
      3 
----> 4   train_loss.reset_states()
      5   train_accuracy.reset_states()
      6 

AttributeError: 'Mean' object has no attribute 'reset_states'

train_loss = tf.keras.metrics.Mean(name='train_loss')
train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')

pip install --upgrade tensorflow