Open rlgnswk opened 2 years ago
Hello, Thanks to your great work.
I just read your paper now. Actually, I am in trouble to understanding the meaning of "The fourth column (‘Refine’)" in Table.2 of your Paper
You wrote like that "The last row further fine-tunes the latter model using the original training data".
It means just you tried to do more training than 3rd column?
Hi @rlgnswk, thanks!
You can look at it as "pre-training", we used the 3rd row as an initialization for the "regular" supervised training.
The ± is std over a few separate training sessions
Hello, Thanks to your great work.
I just read your paper now. Actually, I am in trouble to understanding the meaning of "The fourth column (‘Refine’)" in Table.2 of your Paper
You wrote like that "The last row further fine-tunes the latter model using the original training data".
It means just you tried to do more training than 3rd column?