Hard Negative generation

[rowedenny]

Hi Jingtao,

Thanks for open-source this interesting work and detailed implementation.

I have a question for the hard negative generation, is the mode should be train instead of dev?

python ./star/prepare_hardneg.py \
--data_type passage \
--max_query_length 32 \
--max_doc_length 256 \
--mode dev \
--topk 200