metadata
language: en
tags:
- bert
- rte
- glue
- kd
- torchdistill
license: apache-2.0
datasets:
- rte
metrics:
- accuracy
bert-base-uncased fine-tuned on RTE 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.