metadata
language: en
tags:
- bert
- qnli
- glue
- kd
- torchdistill
license: apache-2.0
datasets:
- qnli
metrics:
- accuracy
bert-base-uncased fine-tuned on QNLI dataset, using fine-tuned bert-large-uncased as a teacher model, torchdistill and Google Colab for knowledge distillation.
The training configuration (including hyperparameters) is available here.
I submitted prediction files to the GLUE leaderboard, and the overall GLUE score was 78.9.