Results
1
issues of
Shaoweihua Liu
https://github.com/google-research/albert/blob/a41cf11700c1ed2b7beab0a2649817fa52c8d6e1/modeling.py#L838-L860 There may be a problem with the shape description of `attention_mask` in L857~L860, which should be `[batch_size, from_seq_length]`.