Runtime error when reload pretrain data in pytorch version

[kevinGit777]

hi, I got a runtime error when executing>python repr_code.py --reload_from 4000000 after replacing all file in data/github, here is the detail:RuntimeError: Expected tensor for argument #1 'indices' to have scalar type Long; but got torch.cuda.IntTensor instead (while checking arguments for embedding)

Could you help me figure it out? Thank you so much!
Environment:
Python 3.8
torch 1.4

[guxd]

You need to adapt your code to an older version of Python (3.6) and PyTorch (1.2).