Comments (3)
@yanghb2020 你好,
根据我们的经验,
- prompt tuning系列方法对于learning rate比较敏感;不好的learning rate通常无法收敛。建议在1e-2到1e-3这个范围内做更细粒度的grid search寻找可以收敛的lr。
- prompt tuning系列方法收敛时间一般较长,从我们在一些类似于语义相似度的任务上的测试情况来看,可能需要等到20epoch以后才能逐渐收敛。建议将训练epoch数设置为100,如果到50epoch还没有收敛的迹象,说明这个lr不太合适。
from p-tuning-v2.
你好,请问有进展吗?我也遇到了同样的问题。
from p-tuning-v2.
from p-tuning-v2.
Related Issues (20)
- 请问,实现p-tuningv2,在每一层都添加可学习参数的代码在哪里?,nlp新手,感谢!! HOT 1
- ReCoRD dataset
- 微调结果不收敛是什么原因?
- 有没有大佬可以提供一些下游任务是“关键词提取”的数据集?
- 提问:MPT-2是否对每个任务训练一个独立的linear classifiers?
- 跟prefix tuning的区别是什么呢? HOT 1
- 使用微调后的模型报错 HOT 1
- AttributeError: 'ExponentialTrainer' object has no attribute 'deepspeed' HOT 1
- 如何加载本地模型
- Fine-tuning
- Is it possible to use p-tuning v2 during inference without causing any impact on the backbone model's performance?
- p tuning v2在NER任务 conll2003上复现F1值和文中写的差一个点啊 参数是跟着shell文件里面设置的 有朋友遇到相似的问题吗? HOT 1
- 还是丢了原有的很多能力 HOT 1
- 关于prompt depth
- Run scripts for GLUE tasks
- 请问在训练时模型中的dropout层还会工作吗?
- p-tuning v2适合分类任务吗?
- 怎么在chatglm3-6b中使用修改以后的p-tuning v2啊?
- GLUE、NER、SRL、QA 和 SuperGLUE任务集相关问题
- What are the main contributions of p tuning? HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from p-tuning-v2.