In the imdb.ipynb notebook (in the create classifier section) the three lines displayed above are confusing to me. Why is wd set to 1e-7 then immediately set to 0? Is this a mistake?
@Esteban looks like it was probably that wd was tried first as one value, then the other value. The variable is overwritten by last time it is declared.
Did you finish running the file dl2/imdb.ipynb. can you share me the model output such as lm_last_ft, lm1, lm1_enc, clas_0, clas_1, clas_2 …
It took me more than 30 days to run all of the commands. Please help me if you have these model files, thanks.