Different default parameter values than what is mentioned in the paper.

Hi

Thanks for the paper and code.

I noticed that a few argument values in search/src/args.py differ from what is mentioned in the paper like max_weight_decay, mul_factor.

Also if I understood it right, in the paper most plots seem to indicate that overfitting is reduced with drop_path_prob >= 0.5, yet the default value of it in code is given 0.2

The value of "factor" parameter (the threshold for eigenvalues) is also different in the paper than code.

Could you please clarify about the good/default value of all these 3 parameters as per your experiments?

Thank You!

Inspect search/src/args.py and compare max_weight_decay, mul_factor, drop_path_prob, and factor with the paper's experiments and plots. Confirm the intended defaults for these parameters and document or reconcile the paper/code discrepancy; done means the values and their rationale are clear.

Written by the indexing model from the issue text.