-
Notifications
You must be signed in to change notification settings - Fork 128
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
train_dual_encoder 训练效果不好 #55
Comments
训练数据集的格式是: 测试时: |
我在做dual_encoder训练的时候 |
请问训练集有多大呢?是从头开始训练还是在现有的某个模型上开始训练的? |
从头开始和从现有模型上继续训练都不行。 |
训练集大概由5万条数据 |
我错了。忘记操作index了 |
我尝试用了一些训练集去训练dual_encoder ,但是效果不好
比如 可怜飞燕倚新妆\t\t《清平调》之二 李白\t\t"一枝秾艳露凝香,云雨巫山枉断肠。借问汉宫谁得似,可怜飞燕倚新妆。"\t0
但是我查询可怜飞燕倚新妆还是查不出来,
在dureader.para里存放了《清平调》之二 李白\t"一枝秾艳露凝香,云雨巫山枉断肠。借问汉宫谁得似,可怜飞燕倚新妆。"
并且使用了训练后的dual_encoder。
我想问下这个是我的训练集没写对吗还是有其他特别的要求
规格是: query \t\t title \t\t para \t 0,1 对吗?
The text was updated successfully, but these errors were encountered: