Alec Segal comments

Repositories
Issues
Comments

Results 2 comments of


                                            Alec Segal

I trained a bert-large SQUAD v1.1 model as a test, but it works much worse than the denspi_sparc model from the project

Hi @jhyuklee, sorry for the confusion - the 55 EM score that I mentioned was just my ad-hock benchmark (not really the EM score) to compare model performances in the...

I trained a bert-large SQUAD v1.1 model as a test, but it works much worse than the denspi_sparc model from the project

Hi @jhyuklee, probably the value of filter_threshold is not the root cause. I had to set it to 0.3 to end up with the phrase dump file (encoding the second...