Nn

Results 3 issues of Nn

### Description ... ### Environment information ``` OS: $ pip freeze | grep tensor # your output here $ python -V # your output here ``` ### For bugs: reproduction...

### Description The checkpoint is always not found in T2T-decoder. After deleting checkpoint, can run T2T-decoder,Which model is used at this time?and why? ### Environment information OS: $ pip freeze...

this code is the fine tuning or use the bert do embedding?