Closed Dicer-Zz closed 2 years ago
Why does the effect of fine-tuning on the CB dataset using Bert-large in this paper exceed the SuperGLUE baseline by more than ten absolute points (83.6 -> 94.6)? And the results on other datasets are not much different.
@Dicer-Zz Hi,
We report the results on the development set of SuperGLUE (Page 16, Table 4).
Thank you for your quick reply! I get it.
Why does the effect of fine-tuning on the CB dataset using Bert-large in this paper exceed the SuperGLUE baseline by more than ten absolute points (83.6 -> 94.6)? And the results on other datasets are not much different.