Code Monkey home page Code Monkey logo

Comments (4)

sserdoubleh avatar sserdoubleh commented on June 7, 2024

大概率是因为，你的 data_format 为 raw 导致的

Knover/knover/utils/tokenization.py

Line 158 in 24636ef

if text in self.cached:

knover 对于这一格式，采用了缓存分词结果的方式，加速数据处理；这个数据格式主要是简单，方便，易于理解，但是性能较差

对于大规模的数据，就不建议采用该 data_format 格式，建议采用 numerical 格式
你可以更新到最新代码，参考 https://github.com/PaddlePaddle/Knover/blob/develop/knover/tools/pre_numericalize.sh ，将你的数据转为 numerical 格式

from knover.

yiyele avatar yiyele commented on June 7, 2024

使用numerical开始训练，但是会出现loss为nan的情况，这是怎么回事？
@sserdoubleh

from knover.

sserdoubleh avatar sserdoubleh commented on June 7, 2024

是训练一开始就出现nan 吗？

from knover.

yiyele avatar yiyele commented on June 7, 2024

应该是没问题了，我调整了warmup。
@sserdoubleh

from knover.

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.