‹ projects

cluster-rnn

a distributed Torch7 RNN cluster over MPI
Log | Files | Refs | README

commit 4b160086c9780103cea871284305e4ece7cc117c
parent 8fc62250622e585e26b20b45f9ae1d0feb17b5e7
Author: umhau <umhau@users.noreply.github.com>
Date:   Wed, 15 Feb 2017 01:37:02 -0500

p

Diffstat:
Mmlaunch.lua | 2+-
1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mlaunch.lua b/mlaunch.lua @@ -29,7 +29,7 @@ local learningRate = 1e-2 local momentum = 0.99 -- very advanced parameters -local learningRateDecay = 1e-4 +local learningRateDecay = 1e-2 local learningRateDecayPower = .5 -- see pg. 23, fig 9 of associated paper -- there's other EAMSGD variables that can be tuned below. I'll do that later.