-
Notifications
You must be signed in to change notification settings - Fork 2.9k
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
[few-shot] Update README #3104
[few-shot] Update README #3104
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
| model_name | 训练方式 | Micro F1分数 | Macro F1分数 | | ||
| ---------- | ------- | ----------- | ----------- | | ||
| ernie-3.0-base-zh | 微调学习 | 0.7172 | 0.3821 | | ||
| ernie-3.0-base-zh | 提示学习 | 0.8855 | 0.8443 | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
微调学习 | 0.7172 | 0.3821
Macro F1分数 没错吧?有点低
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个是 5 次收敛结果取的均值,有一个Macro F1=0.34
,拉低了分数,未收敛的 5 次没有计入结果。
from paddlenlp.utils.log import logger | ||
from paddlenlp.transformers import AutoTokenizer, AutoModelForMaskedLM | ||
from paddlenlp.trainer import PdArgumentParser | ||
from paddlenlp.trainer import PdArgumentParser, EarlyStoppingCallback |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
我没有验证过EarlyStoppingCallback
,注意看效果是否符合预期。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
确认了日志,EarlyStoppingCallback
是符合预期的。
PR types
Others
PR changes
Others
Description