Closed Luoyang144 closed 1 month ago
The training loss of the counterfact model is NLL. The masked_log_probs is just an entry point, and the actual execution is at https://github.com/zjunlp/EasyEdit/blob/38c5c34d614646db14a45f59790434bc2f520c1b/easyeditor/trainer/losses.py#L55, where we calculate the NLL.
Hi, do you have any further questions?
@XeeKee Hi, thanks for reply, which function is the execution of scope classifier's loss?
Here, we referenced the source code from SERAC. The classifier and the small model are trained together.
Hi, do you have any further questions?
Hi, I'm tring to read the training code of SEARC, I wonder where is the loss and it seems not same with origin paper?
Here is loss I find in
editable_model.py
:It seems not same with follow loss which used in SERAC?