mrm8488/spanbert-large-finetuned-squadv1

Facebook Research created SpanBERT large fine-tuned on SQuAD v1.1 for Q&A downstream task (by them) Fine-tuning script can be downloaded here: python code/run_squad.py . The numbers marked as * are evaluated on the development sets because those models were not submitted to the official SQAD leaderboard. All the other numbers are test numbers.Note: Numbers marked as '*' are evaluated only on development sets. The number marked as "*" is not official. All of the numbers marked '*', 'x', 'y' and 'x' are not evaluated. The model was created by Facebook Research and,