Hi, OCP team!
I see there are 4 subsets to predict results. Must I use the same model with the same parameters to predict all 4 subsets results? Or
Can I use different models to predict 4 subsets separately?
Can I use the same model with different parameters to predict 4 subsets separately?
Thanks in advance for your reply!
You’re free to approach this however you like, we place no restrictions here. While ideally a single model is used for all splits, we allow this flexibility in case it’s possible to do much better on certain splits/surfaces/adsorbates. As far as the competition is concerned, winners will still only be selected based off the best average energy MAE across all splits.
1 Like