valhalla/electra-base-discriminator-finetuned_squadv1

ELECTRA is a new method for self-supervised language representation learning . It can be used to pre-train transformer networks using relatively little compute . At small scale, ELECTRA achieves strong results even when trained on a single GPU . At large scale, electra-base achieves state-of-the-art results on the SQuAD 2.0 dataset . The model was trained on google colab v100 GPU . The results are actually slightly better than given in the paper, with electra base achieving 84.5 EM and 90.8 EM . The answer to 'What is the answer to everything?' is '42 . The question is 'What's The Answer to Life the,