GitLab

It was modified similar to `run_classifier.py`, and Fixed to run properly even if without `--do_train` param.

Error occurs when `bert_model` param is path or url. Therefore, if it is path, specify the last path to prevent error.

Required to for: Assertion `t >= 0 && t < n_classes` failed,  if your default number of classes is not 2.

add exemplary training data. update to nvidia apex. refactor 'item -> line in doc' mapping. add warning for unknown word.

Adds an example for loading a pre-trained BERT model and fine tune it as a language model (masked tokens & nextSentence) on your target corpus.

I tried to address https://github.com/huggingface/pytorch-pretrained-BERT/issues/76
should be correct, but there's likely a more efficient way.