SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge pull request #145 from wlhgtc/master

Browse Source 
Correct the  wrong note
This commit is contained in:
Thomas Wolf
2019-01-07 12:23:05 +01:00
committed by GitHub
parent 2e8c5c00ec e626eecc25
commit bcd607542c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch_pretrained_bert/modeling.py
View File

@@ -730,7 +730,7 @@ class BertForMaskedLM(PreTrainedBertModel):
is only computed for the labels set in [0, ..., vocab_size] is only computed for the labels set in [0, ..., vocab_size]
Outputs: Outputs:
if `masked_lm_labels` is `None`: if `masked_lm_labels` is not `None`:
Outputs the masked language modeling loss. Outputs the masked language modeling loss.
if `masked_lm_labels` is `None`: if `masked_lm_labels` is `None`:
Outputs the masked language modeling logits of shape [batch_size, sequence_length, vocab_size]. Outputs the masked language modeling logits of shape [batch_size, sequence_length, vocab_size].