I am having a hard time to reproduce the baseline results (specifically LaBraM) to compare to CBraMod on almost all downstream tasks, for instance: FACED, MUMTAZ, BCIC. How did you get the baseline result numbers? Did you finetune use the LaBraM repo and do hyperparameter tuning? If so can you share the hyperparameters used so we can reproduce the results? Thanks.
I am having a hard time to reproduce the baseline results (specifically LaBraM) to compare to CBraMod on almost all downstream tasks, for instance: FACED, MUMTAZ, BCIC. How did you get the baseline result numbers? Did you finetune use the LaBraM repo and do hyperparameter tuning? If so can you share the hyperparameters used so we can reproduce the results? Thanks.