Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

• PyTorch
• Transformers
• datasets
• wandb
• tqdm
• scikit-learn

Most datasets used in paper are automatically downloaded by the datasets package. Instructions on downloading sst2 and multi30k are provided in readme.txt under the data folder.

Finetune the PLM with the following command:

>> python run.py --task_name task

The task_name parameter can take sst2, imdb, trec, or 20ng. The training loss and evaluation results on the test set are synced to the wandb dashboard.