olm
/

olm-roberta-base-dec-2022

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Tristan commited on Jan 15, 2023

Commit

78e0883

•

1 Parent(s): 50bde63

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -87,5 +87,6 @@ The model achieves the following results after tuning on GLUE tasks:
 |qnli  |acc       |0.9075           |**0.9192**                   |
 |rte   |acc       |0.6296           |**0.6390**                   |
 |wnli  |acc       |0.4000           |**0.4648**                   |
 For both the original BERT and our model, we used the Hugging Face run_glue.py script [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification).
 For both models, we used the default fine-tuning hyperparameters and we averaged the results over five training seeds. These are the results for the GLUE dev sets, which can be a bit different than the results for the test sets.

 |qnli  |acc       |0.9075           |**0.9192**                   |
 |rte   |acc       |0.6296           |**0.6390**                   |
 |wnli  |acc       |0.4000           |**0.4648**                   |
 For both the original BERT and our model, we used the Hugging Face run_glue.py script [here](https://github.com/huggingface/transformers/tree/main/examples/pytorch/text-classification).
 For both models, we used the default fine-tuning hyperparameters and we averaged the results over five training seeds. These are the results for the GLUE dev sets, which can be a bit different than the results for the test sets.