From 35b9ea097e26784c16c638e5f839c754739ebca1 Mon Sep 17 00:00:00 2001 From: Yizhou Chi Date: Wed, 11 Sep 2024 11:59:52 +0800 Subject: [PATCH] update di instruction --- expo/data/dataset.py | 1 + 1 file changed, 1 insertion(+) diff --git a/expo/data/dataset.py b/expo/data/dataset.py index 510c39fce..c83f7b926 100644 --- a/expo/data/dataset.py +++ b/expo/data/dataset.py @@ -24,6 +24,7 @@ DI_INSTRUCTION = """\ 3. You should perform transformations on train, dev, and test sets at the same time (it's a good idea to define functions for this and avoid code repetition). 4. If labels are transformed during training, they should be transformed back to the original format before saving the predictions. 5. You could utilize dev set to improve model training. +6. Use techniques to avoid overfitting. ## Saving Dev and Test Predictions 1. Save the prediction results of BOTH the dev set and test set in `dev_predictions.csv` and `test_predictions.csv` respectively in the output directory.