微调大模型的时候,训练集损失函数没有下降趋势,但是验证集损失函数一直下降,这种情况应该还不算是过拟合现象吧? #253
Labels
No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: HswOAuth/llm_course#253
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
这应该不算是过拟合。不过这个现象好奇怪,我认为这种情况已经算是收敛了,虽然这里面验证集损失在下降,但是真的下降的太少了,这都不能算下降了吧