Coder Social home page Coder Social logo

Comments (3)

imlixinyang avatar imlixinyang commented on June 8, 2024

您好~回复迟了不好意思。

  1. 我猜测更多是因为对抗训练本身在后期崩了导致的,这里可能你得改变一下损失或者调大R1正则化权重。
  2. 一定会有影响,因为同时训练,网络会权衡任务的难易从而自动调整在每种任务上所用的自身资源。
  3. 并不一定,因为我也发现模型在后期reference-guided任务会越来越差(也是因为HiSD原本并没有引入reference-guided的路线),但足够稳定的训练一般最后的模型不会比训练过程中最好的模型差,特别是适用了EMA做模型平均后。
  4. 这个没太理解。

from hisd.

irine1210 avatar irine1210 commented on June 8, 2024

好的好的,感谢您的详细回复!让我看待HiSD有了全新的视角,我再继续研究一下

from hisd.

imlixinyang avatar imlixinyang commented on June 8, 2024

不客气~ 有任何问题都可再交流

from hisd.

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.