search

wasiahmad / PLBART

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].
https://arxiv.org/abs/2103.06333
MIT License
186 stars 34 forks source link

The experiments of task classification #32

Closed vananh0905 closed 2 years ago

vananh0905 commented 2 years ago

Hi,

Thanks for sharing these interesting works.

When I loaded the best checkpoint to reproduce the results in the defect detection dataset, I got 61.75 ACC. File result.txt in google drive is also 61.78 ACC, while in the paper, the ACC is 63.18. Is it the best checkpoint?

Thank you so much

wasiahmad commented 2 years ago

Read the answer for Mismatch in performance reported in the paper and achieved using the released checkpoints from https://github.com/wasiahmad/PLBART#faqs.