search

stanfordnlp / stanza

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages
https://stanfordnlp.github.io/stanza/
Other
7.25k stars 888 forks source link

Fixes coref warmup rounding error #1342

Closed Jemoka closed 8 months ago

Jemoka commented 8 months ago

the original code only works in cases where n_docs is even for self.config.bert_finetune_begin_epoch=0.5 due to rounding error.