Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

自己复现Seq2Edit效果没有那么好 #55

Open
Skywalker-Harrison opened this issue Sep 22, 2023 · 1 comment
Open

自己复现Seq2Edit效果没有那么好 #55

Skywalker-Harrison opened this issue Sep 22, 2023 · 1 comment

Comments

@Skywalker-Harrison
Copy link

您好，我自己用Transformer架构复现了一个Seq2Edit, 目前仅支持单轮纠正，但是我在训练的时候发现nonkeep标签正确率挺低的，我检查了输入，labels, d_tags都是和原文代码一致的。我觉得很有可能是训练过程中的问题，原文的代码训练过程在Allennlp的高度封装之下，我担心因为训练设置的不同导致性能没那么好。（在自己的数据集上训练，原文代码能达到80%多，但是我自己复现的只有30%多）
@Skywalker-Harrison Skywalker-Harrison changed the title 自己复现是Seq2Edit效果没有那么好 自己复现Seq2Edit效果没有那么好 Sep 22, 2023
@HillZhang1999
Copy link
Owner

可以参考这个仓库：https://github.com/cofe-ai/fast-gector
基于原生torch和deepspeed写的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@HillZhang1999 @Skywalker-Harrison