Validation_step_output is empty

I use google tft model from pytorch.

My question is : what does validation_step_output tft’s attribute contain ? When I debug my code I see that is still empty when calling on_validation_epoch_end, why??

def on_validation_epoch_end(self):

here I get self.validation_step_outputs empty list as mentioned before.

while this function is responsible of adding the val_loss into the list I think

def validation_step(self, batch, batch_idx):
        x, y = batch
        log, out = self.step(x, y, batch_idx)
        log.update(self.create_log(x, y, out, batch_idx))
        return log

Is this a double post from here?