I have a fairly optimized cnn-blstm-crf tagger here with the crf defined here.
On pytorch 0.4.0
using cuda 9.0
and cudnn 7102
I can run a single epoch of the conll 2003 NER task in 21.41 +/- 0.28
When the only thing I change is the version of pytorch to 0.4.1
(the current conda install) a single epoch now takes 27.99 +/- 0.26
Has anyone else noticed anything like this?