-
Notifications
You must be signed in to change notification settings - Fork 21
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
关于encoder用bert替换 #24
Comments
@VinnyHu 谢谢关注,我们最近在赶deadline,后续整理后以后会开源出来,如果着急可以参考https://github.com/hongwang600/DocRed/blob/master/models/bert.py |
好的,谢谢您的回复!!! |
您好,我又看到您代码里面 |
您好,这两天一直都在学习您的工作,对您代码里面StructInduction 模块 forward里面的代码对照着原文中的(3)-(8)的公式看,实在是看的不太懂。 |
谢谢关注!我们刚才开源了,您可以参考下,BERT Encoder比较耗GPU显卡,我们是在3 * 24GB的GPU上训练的
…On Thu, Oct 29, 2020 at 9:47 AM qiunlp ***@***.***> wrote:
是否能抽出宝贵时间把实验中BiLSTM换成Bert的代码开源?谢谢!
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub
<#24 (comment)>, or
unsubscribe
<https://github.com/notifications/unsubscribe-auth/ABBGN7SUMGVKPUZGOJAGJPLSNDCSDANCNFSM4QDCWNXQ>
.
--
Best Wishes
Guoshun Nan
|
用bert替换后,运行epoch 0 | step 1500 |错误,请问什么原因? |
Hi @qiunlp 抱歉,这个问题我一直来得及fix,你可以尝试用不同batch_size,或者换个random seed来临时解决这个问题 |
好的,谢谢!我试试 |
meet again! sad! |
您好,请问下您能不能将实验中把BiLSTM,换成Bert的代码也开源下?谢谢!
The text was updated successfully, but these errors were encountered: