May we use labelled data from other tasks (i.e. not for counterfactual detection) to fine-tune our model?
Yes ; )
We have scheduled a important maintenance operation for the Codalab public instance (http://competitions.codalab.org) for Saturday, September 8th.
The migration will start at approximately 9AM PST and should hopefully be completed by approximately 1PM PST that same day.
During that time the server will be down.
If you have a scheduling conflict with this move, please let us know before September
1st by posting an issue to GitHub here: