DwanZhang

> @Turlan my curve is similar to you. I think it is because discriminator is learning in the beginning. I meet the same problem, will you froze the discriminator for...

same question

Me too

I meet the same problem. Can we discuss more about this paper?

I also want to know the evaluation methods

Same

请问下解决了嘛？

BTW, I have muted the flash attention module.

So am I

Same problem, requires the validation code while fine-tuning