Performance discrepancy for torch 0.2.0 and 0.4.0

[tonytan48]

Hi Mr.Dai,

It seems the performance discrepancy has lead to slightly worse performance on the penn treebank in the readme page. I am able to reproduce the result for the Penn Treebank. However, for the WT2 benchmark. Before finetune I am able to get 65.66/62.94, and After finetune 64.41/61.77, for default dynamic evaluation setting I am getting 43.34/41.49. I also observed similar slight performance decrease(about 0.6) for pt0.4.0 and 0.2.0 in a following work of mos(https://github.com/ChengyueGongR/Frequency-Agnostic/issues/2). I am wondering is this result in-line with your benchmark in pytorch 0.4.0? Thank you for your time!