Cross entropy loss giving RuntimeError: CUDA error: device-side assert triggered
Deepayan137 opened this issue · 1 comments
Deepayan137 commented
Hi,
I tried to train a model from scratch on the data that I have downloaded from the link mentioned on your readme. However, when I am trying to train the model I am facing a runtime error. The issue I think is perhaps due to the format of data because when I tried to run the same code on a different dataset (eng-german), the code seems to run without any glitch.
Currently, I am using python 3.7 and pytorch version 1.3.
Any help would be deeply appreciated.
zhawe01 commented
If you want to run a translation dataset, I suggest you use the fairseq code. Different with fairseq, fairseq-gec contains copy mechanism and edit-weighted loss, and both of them are not so useful when you do the translation.