Giter Site home page Giter Site logo

Comments (5)

fengzuo97 avatar fengzuo97 commented on May 14, 2024

作者还提到了fp16不收敛，我试验了可以收敛，使用wiki的1.3G语料，在v100上混合精度训练5个epoch，loss讲到3.2，和单精度基本一致，不过我使用的是50257的bpe，并不是bert tokenizer。另外在1080TI上也收敛，不过在1080TI上混合精度训练比单精度训练稍慢一些。

from gpt2-chinese.

Morizeyao avatar Morizeyao commented on May 14, 2024

多gpu的话，问题可能是这个。
用BPE tokenizer做效果怎么样呀？

from gpt2-chinese.

fengzuo97 avatar fengzuo97 commented on May 14, 2024

谢谢，bpe tokenizer效果不错，最早之前是用bert tokenzier，效果并不是很好，loss有点难下降，不过我没有控制变量，中间还有一些其他的因素变动。

from gpt2-chinese.

Morizeyao avatar Morizeyao commented on May 14, 2024

介意分享一下设计中文bpe tokenizer的方案么？或者做个PR

from gpt2-chinese.

Morizeyao avatar Morizeyao commented on May 14, 2024

ok，谢谢分享 :)

from gpt2-chinese.

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.