help me

[detroldandelion]

Hi,
Thank you so much for publishing your code. I download your code and run it step by step (run_all.sh, factorize.sh, run.sh, remove_mask.sh) on the sst-2 task. The last step, 'finetune again', is not provided and I follow the settings in run_all.sh. But the result is unsatisfying (dev acc =83%). And when I use your method on some smaller datasets (e.g., RTE, CoLA), the actual_compact_rate (after removing mask) is larger than 1. (RTE=1.36). Could your please provide more details of sst-2 task about the last step or tell me the most possible reasons, if it is convenient for you. I would really appreciate it.
Sincerely.

[Arexh]

Hi, there. I wrote this project a long time ago, and the original intention was to reproduce the Wang's paper. As you can see, the results of my experiment were terrible. At first, the results of my experiment were far inferior to the paper, then I added a fine-tuning step to improve the accuracy (which is not mentioned in this paper). According to my impression, this algorithm is more sensitive to parameters, and the training results fluctuate greatly. I think I can find a time to run my code, but I'm sorry I don't have time to do this recently.

Thanks for your attention. I will start ASAP!