yoshitomo-matsubara commited on
Commit
4456ea6
1 Parent(s): 1d49bf3

tuned hyperparameters

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -14,4 +14,4 @@ metrics:
14
 
15
  `bert-large-uncased` fine-tuned on MRPC dataset, using [***torchdistill***](https://github.com/yoshitomo-matsubara/torchdistill) and [Google Colab](https://colab.research.google.com/github/yoshitomo-matsubara/torchdistill/blob/master/demo/glue_finetuning_and_submission.ipynb).
16
  The hyperparameters are the same as those in Hugging Face's example and/or the paper of BERT, and the training configuration (including hyperparameters) is available [here](https://github.com/yoshitomo-matsubara/torchdistill/blob/main/configs/sample/glue/mrpc/ce/bert_large_uncased.yaml).
17
- I submitted prediction files to [the GLUE leaderboard](https://gluebenchmark.com/leaderboard), and the overall GLUE score was **79.1**.
 
14
 
15
  `bert-large-uncased` fine-tuned on MRPC dataset, using [***torchdistill***](https://github.com/yoshitomo-matsubara/torchdistill) and [Google Colab](https://colab.research.google.com/github/yoshitomo-matsubara/torchdistill/blob/master/demo/glue_finetuning_and_submission.ipynb).
16
  The hyperparameters are the same as those in Hugging Face's example and/or the paper of BERT, and the training configuration (including hyperparameters) is available [here](https://github.com/yoshitomo-matsubara/torchdistill/blob/main/configs/sample/glue/mrpc/ce/bert_large_uncased.yaml).
17
+ I submitted prediction files to [the GLUE leaderboard](https://gluebenchmark.com/leaderboard), and the overall GLUE score was **80.2**.