Paper clarification for training CMLM

[anton164]

In the paper you say:

For training the CMLM, we use both XSUM and the CNN/Dailymail dataset.

Do you train the CMLM separately for each dataset depending on the downstream task, or do you train one CMLM using both datasets?

[mcao516]

Hi Anton, we train the CMLM separately for each dataset.

[anton164]

Thanks @mcao516 !