Not using entropy minimization loss in the final model?

[kkteru]

Hey @jiaaoc @diyiy,

A quick clarification question -- looks like the lambda-u-hinge parameter is always set to zero and also following the code, the hinge loss (entropy minimization loss, Sec 4.4 in the paper) is never added to the final loss in the MixText/TMix configuration of the code, i.e., line 353 is never executed.

Is that correct? Or am I missing something?