I followed the steps in the README file to train the model, but I got an error. Here is the error message.

[Claude121381011]

I followed the steps in the README file to train the model, but I got an error. Here is the error message：
RuntimeError: Expected tensor for argument #1 'indices' to have one of the following scalar types: Long, Int; but got torch.cuda.HalfTensor instead (while checking arguments for embedding).
The dataset I used was the official Math-Step-DPO-10K dataset.
How to solve this problem？