GFI-Fan

Do we have any randomness in the training since I did not see any code snippets that control randomness , such as `torch.seed`?

> 1 single epoch is too low. > First gen rank 8 loras were using 3 epochs. Thanks! I fine-tuned 2 modules with rank 8 and 10 epochs. I think...

Thanks for all your responses. They are all useful for training. However, the current performance is still poor. I believe we should explore more on performance improvement rather than other...

> 哈哈哈，那我感觉找到问题的原因了， 似乎旧版本的LlamaTokenizer 是实现了自己的eos_token_id和unk_token_id这两个property函数的，我的这个版本已经删除了，所以默认调用了基类SpecialTokensMixin的函数实现，直接返回的是 self.convert_tokens_to_ids(self.bos_token) > >  👍 这行代码的链接可以share一下吗？