[cosmoflow] [logging] Weight decay and l2 regularization differs by a factor of 2

[m-ymzk]

Weight decay and l2 regularization differs by a factor of 2. (Refs)
I think the value of Weight Decay output in the following line should be "l2 * 2".

hpc/cosmoflow/models/cosmoflow.py

Line 52 in b796e7a

mllogger.event(key=mllog.constants.OPT_WEIGHT_DECAY, value=l2)

Refs

• Boris's blog, "weight decay vs L2 regularization"
  https://bbabenko.github.io/weight-decay/

• Keras/issues/2717 "Is it the same adding weight decay to all the layers (including input and output layer) than adding the weight decay term to the cost function? #2717"
  Is it the same adding weight decay to all the layers (including input and output layer) than adding the weight decay term to the cost function? keras-team/keras#2717 (comment)