double check cc @LysandreJik

This commit is contained in:
thomwolf
2019-12-14 09:56:27 +01:00
parent 3fd71c4431
commit dc667ce1a7
2 changed files with 3 additions and 3 deletions

View File

@@ -186,7 +186,7 @@ class Distiller:
-------
token_ids: `torch.tensor(bs, seq_length)` - The token ids after the modifications for MLM.
attn_mask: `torch.tensor(bs, seq_length)` - The attention mask for the self-attention.
mlm_labels: `torch.tensor(bs, seq_length)` - The masked languge modeling labels. There is a -1 where there is nothing to predict.
mlm_labels: `torch.tensor(bs, seq_length)` - The masked languge modeling labels. There is a -100 where there is nothing to predict.
"""
token_ids, lengths = batch
token_ids, lengths = self.round_batch(x=token_ids, lengths=lengths)
@@ -246,7 +246,7 @@ class Distiller:
-------
token_ids: `torch.tensor(bs, seq_length)` - The token ids after the modifications for MLM.
attn_mask: `torch.tensor(bs, seq_length)` - The attention mask for the self-attention.
clm_labels: `torch.tensor(bs, seq_length)` - The causal languge modeling labels. There is a -1 where there is nothing to predict.
clm_labels: `torch.tensor(bs, seq_length)` - The causal languge modeling labels. There is a -100 where there is nothing to predict.
"""
token_ids, lengths = batch
token_ids, lengths = self.round_batch(x=token_ids, lengths=lengths)