Gamma in the LR scheduler is too small

[grig-guz]

Gamma should be 0.999 and step_size=1, so that the learning rate is decayed by 0.1% as recommended in the paper. Otherwise the learning rate is just cut abruptly after 10k steps.

coreference-resolution/src/coref.py

Line 453 in f368f5a

gamma=0.001)