Skip to content
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

请问在训练过程中输出的日志中loss、learning_rate和epoch分别代表什么含义 #271

Open
juiceSea opened this issue Jan 30, 2024 · 0 comments

Comments

@juiceSea
Copy link

{'loss': 1.141, 'learning_rate': 8.366666666666668e-05, 'epoch': 50.0}
{'loss': 0.0003, 'learning_rate': 6.7e-05, 'epoch': 100.0}
{'loss': 0.0001, 'learning_rate': 5.0333333333333335e-05, 'epoch': 150.0}
{'loss': 0.0001, 'learning_rate': 3.366666666666667e-05, 'epoch': 200.0}
{'loss': 0.0001, 'learning_rate': 1.7000000000000003e-05, 'epoch': 250.0}
{'loss': 0.0001, 'learning_rate': 3.3333333333333335e-07, 'epoch': 300.0}
我在训练过程中发现loss在下降,是否表示这是模型回答的错误率?
在epoch达到150周loss没有变化了,是否表示训练轮次达到150之后再训练便没有意义了?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant