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

请问关于NER_IDCNN_CRF中关于训练次数的疑问 #125

Open
LittleSJL opened this issue Aug 26, 2020 · 0 comments
Open

请问关于NER_IDCNN_CRF中关于训练次数的疑问 #125

LittleSJL opened this issue Aug 26, 2020 · 0 comments

Comments

@LittleSJL
Copy link

您好作者,再次就代码中模型迭代次数(训练次数, max_eopoch)提出一些问题:

在您的原始代码中,max_eopch设置的是100,但我在实际跑模型的过程中发现大概10次左右(可能7,8次;可能12,13次),模型在训练集上的loss和在测试集上的F1值就会出现波动,所以再往后训练,即使loss会不断下降,大概率会overfit,所以我最终把训练次数设置在了10次左右。

我想问的是:
1、您设置100次的目的或者根据是什么呢?你在实际跑模型的时候具体用的是多少呢?(数据集我用的就是您给的)
2、为什么无论是用您给的ID_CNN或者LSTM,模型都收敛这么慢呢(我在别的github项目中用同样的数据集,大部分都是3、4次就收敛了),是否和loss的计算有关呢?请问这是10次左右才收敛是正常的吗?

希望能得到您的解答,谢谢!

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

1 participant