-
Notifications
You must be signed in to change notification settings - Fork 296
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
增加chatGLM2+PT的预测代码 #99
base: master
Are you sure you want to change the base?
Conversation
补充一句,随着训练轮数增加,会出现灾难性遗忘现象 |
是真的,我感觉pt微调的遗忘问题非常严重,根本没有对话能力了 |
在我的实验里只做了一次微调训练,但是结果貌似lora好很多,遗忘效果也没那么明显,我再试试多次训练后什么情况 |
lora比pt好吗? |
我的实验结果是这样的,lora微调: |
很棒~ |
你好,我尝试lora微调,生成的文件中没有pytorch_model.bin,但predict.py和cli.py中都需要这个文件,请问这里是怎么处理的? |
现在用下面的方式可以加载成功, |
我也是这个问题,用了和你一样的代码加上 |
Description
在chatGLM2+PT场景下,可以复现三元组抽取任务, 不同epoch的模型f1在测试集上表现为:
基本和作者的实验相符