You can't do it but there is a workaround:

You could use a fake time column and force it to be 80/10/10. 

If you specify this column (in the advanced section - "Time column for training/validation/testing split"), the dataset is split into training, validation, and test sets by time. The earliest points are used for training, the next earliest for validation, and the latest points are used as a test set. Try using all the earliest points as the same timestamp, then another for validation and another one for testing. 

Wouldn;t that just do a 60/20/20 split?

You'd need to put 80% of your data with the earliest timestamp, then 10% with another one and 10% with another.