New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
KeyError: 'eval_loss' when fine-tuning gpt-2 with run_clm.py
#8789
opened Nov 26, 2020 by
Potomac
1 of 1
What would be the license of the model files available in Hugging face repository?
#8786
opened Nov 25, 2020 by
jaingaurav3
Can't load tokenizer for 'facebook/rag-token-base/question_encoder_tokenizer'.
#8780
opened Nov 25, 2020 by
racoutinho
LXMERT - Visual features don't match original implementation
#8769
opened Nov 24, 2020 by
eladsegal
2 of 3
UnicodeDecodeError: 'utf-8' codec can't decode byte 0x80 in position 49: invalid start byte
#8757
opened Nov 24, 2020 by
singhsidhukuldeep
Continued training of the original BERT models (not to PyTorch)
#8756
opened Nov 24, 2020 by
singhsidhukuldeep
"AutoTokenizer.from_pretrained" does not work when loading a pretrained Albert model
#8748
opened Nov 24, 2020 by
iamfaith
1 of 4
Blank line indicates the end of a document for NER training ?
#8740
opened Nov 23, 2020 by
polodealvarado
It seem do not support convert multilabel classification model to onnx ?
#8726
opened Nov 23, 2020 by
MrRace
Longformer inference speed is slower than bert of the same length
Migration
#8725
opened Nov 23, 2020 by
chenlin038
@ehsan-soe I fixed the problem by truncating incomplete batches. So if there are 2001 examples and my batch size = 2, then I truncate the last example and train on the first 2000. This has fixed it for me both with and without distributed. My load_and_cache function now looks like this
#8724
opened Nov 23, 2020 by
ChaooMa
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.