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.

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

llama2 结果复现 #23

Open
chengshuang18 opened this issue Jun 5, 2024 · 4 comments
Open

llama2 结果复现 #23

chengshuang18 opened this issue Jun 5, 2024 · 4 comments

Comments

@chengshuang18
Copy link

感谢作者的工作,提供了一个解决 cl 灾难性遗忘的思路。
我采用 codebase 提供的 llama2 的脚本,跑出来的结果直接坏掉了,这是什么原因呢,跑实验的过程中,有什么要点需要注意么,或者参数设置上需要做些什么调整呢?是 olora 的 lamda 参数设置太小导致过多的遗忘么?下面是我在 tune order2 时的逐 task 结果
***** predict metrics *****
epoch = 1.0
predict_exact_match = 97.6184
predict_exact_match_for_TC = 97.6184
predict_exact_match_for_dbpedia = 97.6184
***** predict metrics *****
epoch = 1.0
predict_exact_match = 43.2171
predict_exact_match_for_SC = 52.9868
predict_exact_match_for_TC = 33.4474
predict_exact_match_for_amazon = 52.9868
predict_exact_match_for_dbpedia = 33.4474
***** predict metrics *****
epoch = 1.0
predict_exact_match = 26.8114
predict_exact_match_for_SC = 3.3289
predict_exact_match_for_TC = 38.5526
predict_exact_match_for_amazon = 3.3289
predict_exact_match_for_dbpedia = 10.2105
predict_exact_match_for_yahoo = 66.8947
***** predict metrics *****
epoch = 0.99
predict_exact_match = 35.3191
predict_exact_match_for_SC = 25.5132
predict_exact_match_for_TC = 38.5877
predict_exact_match_for_agnews = 87.4868
predict_exact_match_for_amazon = 25.5132
predict_exact_match_for_dbpedia = 19.1447
predict_exact_match_for_yahoo = 9.1316

@cmnfriend
Copy link
Owner

cmnfriend commented Jun 5, 2024 via email

@chengshuang18
Copy link
Author

感谢及时的回复,不过我也是采用 8 卡跑的诶,上面的结果是采用 8 卡 A100 40G的显卡跑出的结果 @cmnfriend

@chengshuang18
Copy link
Author

还有一个问题,你们采用的是 llama2_chat 还是 llama2 啊

@BeyonderXX
Copy link
Collaborator

感谢及时的回复,不过我也是采用 8 卡跑的诶,上面的结果是采用 8 卡 A100 40G的显卡跑出的结果 @cmnfriend

llama2_chat

所有实验都是在对齐模型上面做的

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants