Expected values of `ins_prob` and `ins_loss` in MoCo when training is working

[nlml]

Hi there

Thanks a lot for this great repo!

I am trying out MoCo on my own dataset (I also added additional augmentations). Training appears to have converged, but the max value I get for ins_prob is about 13.35, and the lowest value I get for loss is about 0.2422.

I am wondering what metrics you got when training on Imagenet? Am not sure what a "good" score should look like.

Here are screenshots from training progress in tensorboard (ignore the multiple lines at the start of training).

Thanks, Liam

[ajtejankar]

I think a simple solution would be to use the pre-trained MoCo model and get the loss for Imagenet. That will give you the final loss achieved by the model.