XGB Regression: Is there a way to handle somewhat bimodal Y variable?

I am using XGBRegression to predict on continuous percentage data with 80% of the values around 100, 10% around 0 and 10% data distributed in the middle. Models are struggling with predictions around 0, due to the nature of the data. I tried oversampling, but it doesn't improve results much. Any suggestions of things to try?