You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Why is the label like this?
Is there something wrong with my data format?
Is it possible to get correct results with this kind of training, without distinguishing between question and answer
My loss has always been around 8.
Uh oh!
There was an error while loading. Please reload this page.
Thank you for your outstanding work!
My example data looks like this:
after apply_chat_template:
The final prompt:
input_ids.shape: (1,509)
I found that in the loss_fn function,
Why is the label like this?
Is there something wrong with my data format?
Is it possible to get correct results with this kind of training, without distinguishing between question and answer
My loss has always been around 8.
After fine-tuning, my output looks like this:
The text was updated successfully, but these errors were encountered: