Comments (6)
WThirteen
commented on June 11, 2024
1
我试着增加语料 但是没有解决。
但是为了让train跑起来 我在分母都加了一个很小的值。
代码确实是跑起来了
from gpt2-chitchat.
Delimeng
commented on June 11, 2024
问题解决了，是因为自己的语料太少了，可以增加一下语料的数量
from gpt2-chitchat.
Delimeng
commented on June 11, 2024
1，他这个报错的原因就是分母的值为零，你加上一个很小的值确实会避免这个错误，但是对于模型的训练来说准确度很重要。
2，另外增加语料没有解决这个问题的话，还是你增加的语料的数量太少了，我的建议是你不要手动去增加语料，你去作者的链接里面找一下，我记得有语料的压缩包，把它下载下来。
from gpt2-chitchat.
Delimeng
commented on June 11, 2024
1.他这个报错的原因就是分母的值为零，你在分母上加上一个很小的值确实会避免这个错误，但是对于模型的训练来说准确度很重要。2。另外增加语料还是没有解决这个问题的原因是你的语料增加的还是不够多，我的建议是你不要手动的去增加语料，你去作者的链接里面找找看，我记得有语料的压缩包，你把他下载下来就行，
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2024年4月16日(星期二) 下午4:26
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [yangjianxin1/GPT2-chitchat] ZeroDivisionError: division by zero (Issue #126)
我试着增加语料 但是没有解决。
但是为了让train跑起来 我在分母都加了一个很小的值。
image.png (view on web)
代码确实是跑起来了
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from gpt2-chitchat.
WThirteen
commented on June 11, 2024
我在分母增加最小值的方法确实不可取： 导致后面训练的模型使用出现乱码：
我再尝试去增加语料，谢谢你
from gpt2-chitchat.
Delimeng
commented on June 11, 2024
不客气，
…------------------ 原始邮件 ------------------
发件人: ***@***.***>;
发送时间: 2024年4月17日(星期三) 凌晨2:02
收件人: ***@***.***>;
抄送: ***@***.***>; ***@***.***>;
主题: Re: [yangjianxin1/GPT2-chitchat] ZeroDivisionError: division by zero (Issue #126)
我在分母增加最小值的方法确实不可取： 导致后面训练的模型使用出现乱码：
image.png (view on web)
我再尝试去增加语料，谢谢你
—
Reply to this email directly, view it on GitHub, or unsubscribe.
You are receiving this because you authored the thread.Message ID: ***@***.***>
from gpt2-chitchat.
Related Issues (20)
- train.py报错ZeroDivisionError: division by zero HOT 6
- Uuuu
- 为什么要删除mmi的方法啊？效果不好吗？
- fine-tuning HOT 1
- README中的小错误，但是可能造成不必要的麻烦 HOT 3
- 请问断点续训是否是不支持的？ HOT 1
- 有什么方法让已经训练好的模型去训练用户和bot的对话呢？
- 训练时的一些错误 HOT 1
- ignore_index 的设置 HOT 3
- 模型层数问题
- 训练代码逻辑问题 HOT 2
- 下载问题
- 网盘链接失效
- 想使用GPT2的微调来实现负样本的生成
- padding mask
- 有关对预训练模型微调的问题
- dataset HOT 1
- 新手求帮助啊，友友们 HOT 2
- 训练结果可视化 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 gpt2-chitchat.