the way of loading teacher's logits may be wrong

[HoJenson]

When you use global_step, after you have trained for several epochs, you may get an all-zero teacher logits because the start_idx and end_idx may be out of range. (you can print the length of loaded_data to verify this issue)

I think you can include the idx of the training data and use the idx to obtain the logits of the teachers.

[chywang]

@Andrewyan123 please check this issue