hello, in your code, I have seen several line codes like this:
if mbatch<=args.beta_freeze:
_beta = args.beta
else:
move = max(0, mbatch-args.beta_freeze)
_beta = max(args.beta_min, args.betamath.pow(1+args.gammamove, -1.0*args.power))
os.environ['BETA'] = str(_beta)
And I discover that the same parameter beta has also appear on Lsoftmax, but I don't know what their usage, Could you please help me solve this problem? thank you very much.
hello, in your code, I have seen several line codes like this: if mbatch<=args.beta_freeze: _beta = args.beta else: move = max(0, mbatch-args.beta_freeze) _beta = max(args.beta_min, args.betamath.pow(1+args.gammamove, -1.0*args.power)) os.environ['BETA'] = str(_beta) And I discover that the same parameter beta has also appear on Lsoftmax, but I don't know what their usage, Could you please help me solve this problem? thank you very much.