test set and valid set are the same?

[zhuang-li]

Hi I am trying to run your code but am having difficulty replicating the result in IJCAI 2018. Why is the valid set the same with the test set in your code? I didn't see in anyplace that you use the valid set. Is this a mistake in your experiments or you just directly optimize your model on the test set? May you help me solve this problem?

trainset = utils.LabelDataset(datas['train'], char=config.char)
validset = utils.LabelDataset(datas['test'], char=config.char)

validloader = datas['validloader']
tgt_vocab = datas['tgt_vocab']