Fix vqa loss

[henryj18]

VQA loss is not decreasing during training, we have tried several ways to reduce it, this is one of the tests. So far we have been following GATO paper to place all text (including VQA question and answer) to the left of separator. In this PR, we are doing a test to place the question to the left of the separator and place the answer to the right of the separator during training, and see whether that can reduce the VQA loss.

So far, the test has shown that it cannot reduce VQA loss.

This PR is created to track this issue and solicit code review and see whether we find a solution to reduce the VQA loss