question about single model's results

duyvuleo / Transformer-DyNet

An Implementation of Transformer (Attention Is All You Need) in DyNet

MIT License

63 stars 19 forks source link

Closed tnq177 closed 6 years ago

tnq177 commented 6 years ago

Do the reported results of single model (not ensemble) come from single checkpoint or your average checkpoints before translating? Thanks.

duyvuleo commented 6 years ago

Hi @tnq177 , it came from a single checkpoint (actually a checkpoint with best pplx on dev data).

tnq177 commented 6 years ago

thanks!