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

Switch return_dict to True by default. (#8530)

Browse Source 
* Use the CI to identify failing tests

* Remove from all examples and tests

* More default switch

* Fixes

* More test fixes

* More fixes

* Last fixes hopefully

* Use the CI to identify failing tests

* Remove from all examples and tests

* More default switch

* Fixes

* More test fixes

* More fixes

* Last fixes hopefully

* Run on the real suite

* Fix slow tests
This commit is contained in:
Sylvain Gugger
2020-11-16 11:43:00 -05:00
committed by GitHub
parent 0d0a0785fd
commit 1073a2bde5
106 changed files with 138 additions and 234 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/seq2seq/distillation.py
View File

@@ -153,7 +153,6 @@ class SummarizationDistiller(SummarizationModule):
output_hidden_states=self.do_calc_hidden_loss,
output_attentions=False,
use_cache=False,
return_dict=True,
)
lm_logits = student_outputs.logits
@@ -179,7 +178,6 @@ class SummarizationDistiller(SummarizationModule):
input_ids,
attention_mask=src_mask,
output_hidden_states=self.do_calc_hidden_loss,
return_dict=True,
)
if self.different_base_models:
teacher_enc_outputs = all_teacher_encoder_outputs.last_hidden_state
@@ -199,7 +197,6 @@ class SummarizationDistiller(SummarizationModule):
decoder_input_ids=decoder_input_ids,
output_hidden_states=self.do_calc_hidden_loss,
use_cache=False, # since we are not passing labels, never let this default to True
return_dict=True,
)
dec_mask = decoder_input_ids.ne(pad_token_id)
loss_ce = self.calc_ce_loss(dec_mask, lm_logits, teacher_outputs.logits)