Question regarding training time

[jpan72]

Hello,

As a reference, how long did it take for you to train Stage 1 and 2, respectively (with the training data you described in the paper and set in the configuration file)?

Regarding training resource, from other posts I see that you are using 32 A100 for training.

Context - I found training Stage 1 and 2 with images is pretty fast but training with videos take much much longer time. So it would be helpful to know how long you took to understand if I missed something. (So if it's also possible to share how long it took you to train with images and videos respectively, then it would be even better)

Thank you!