Code Monkey home page Code Monkey logo

Comments (6)

zhangfan-algo avatar zhangfan-algo commented on June 30, 2024

主要是想解决在进行simpo训练的过程中'rewards/chosen','rewards/rejected' 这俩都为负 而且都是在变小

from llama-factory.

exceedzhang avatar exceedzhang commented on June 30, 2024

同样的问题SimPO论文提到2个超参数：如何进行设置？对应参数是哪2个？Beta 参数和sim_gamma吗？
image

from llama-factory.

hiyouga avatar hiyouga commented on June 30, 2024

pref_beta

from llama-factory.

exceedzhang avatar exceedzhang commented on June 30, 2024

@hiyouga pref_beta 值设置可以超过1吗？ SimPO论文使用2 和2.5

from llama-factory.

hiyouga avatar hiyouga commented on June 30, 2024

可以

from llama-factory.

exceedzhang avatar exceedzhang commented on June 30, 2024

可以

感谢！

from llama-factory.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.