This repo cannot reproduce the result of original paper

Thank you for your implementation, it is very helpful for me.
I run this code and can get the similar result when the number of heads equals to 1. But, I cannot get the result of original paper(73.6/82.7) when I use 8 heads, batch size 32, training step 150k, char dimension of 200 (the same setting as the original paper). I can only get around (71.27/80.58).
Same situation was ocurred when I ran the pytorch repo (https://github.com/andy840314/QANet-pytorch-).

Any suggestions?

Start by reproducing the reported run with 8 heads, batch size 32, 150k training steps, and character dimension 200, then compare its result with the original paper's 73.6/82.7 figures. The issue provides no file, test, or entry point; done would require identifying why both implementations reach only about 71.27/80.58 or documenting the confirmed cause.

Written by the indexing model from the issue text.