3 comments

[ 9.4 ms ] story [ 29.2 ms ] thread
Hmm, the article's summary table showed "only the top task layer(s)" for BERT fine-tuning. Is that correct?

The original paper [1] wrote:

"All of the parameters of BERT and W are fine-tuned jointly to maximize the log-probability of the correct label."

[1]: https://arxiv.org/abs/1810.04805

thanks! my text should be correct but the table is wrong. just fixed.