# batch_size = 32: In each batch contains 32 instaces. # batch
#       It has been proved that training in a batch gives better performance than learn a single data at a time
# device = torch.device("cuda"): Use GPU. If you do not have a GPU enviornment, use torch.device("cpu") instead
# repeat = False: Do not repeat the iterator for multiple epochs
# sort_key = lambda...: A key to use for sorting examples in order to batch together examples with similar lengths
#       and minimize padding. The sort_key provided to the Iterator constructor overrides the sort_key attribute of
#       the Dataset, or defers to it if None
train_iter, test_iter = data.BucketIterator.splits(
          (train, test), batch_size=32, device=torch.device("cuda"), repeat=False, sort_key=lambda x: len(x.Text))