NaN in input tensor
dikubab opened this issue · 2 comments
dikubab commented
The language model gives NaN or Inf found in input tensor.
train.txt
Can help why it is failing to train on non English character?
aaberdam commented
Hi,
Thank you for the interest in our work.
Please refer in this issue, to the changes that are required for training on non-English language.
In particular, make sure that you created AmharicText_train.csv
and AmharicText_eval.csv
with the right character set.
Let me know if it works for you.
Aviad
dikubab commented
Thank you for your prompt response. As per your suggestion, I have cleaned my train and valid text datasets and now it is working for me. I am closing the issue.