summaryrefslogtreecommitdiff
path: root/docs
diff options
context:
space:
mode:
authorlivc <95livc@gmail.com>2019-03-13 08:06:56 -0700
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>2019-03-13 08:14:30 -0700
commitecc5e623a29a825937ab6e8e9c4b4156b5a48626 (patch)
treea82769acdc73abeb7e3ed8796d5ae3079047cb40 /docs
parent13bc0024225a5fba2d7f83fe189d1d766b0d8d45 (diff)
downloadpytorch-ecc5e623a29a825937ab6e8e9c4b4156b5a48626.tar.gz
pytorch-ecc5e623a29a825937ab6e8e9c4b4156b5a48626.tar.bz2
pytorch-ecc5e623a29a825937ab6e8e9c4b4156b5a48626.zip
fix punctuation
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/17973 Differential Revision: D14438725 Pulled By: zou3519 fbshipit-source-id: 30a5485b508b4ae028057e0b66a8abb2b163d66b
Diffstat (limited to 'docs')
-rw-r--r--docs/source/optim.rst2
1 files changed, 1 insertions, 1 deletions
diff --git a/docs/source/optim.rst b/docs/source/optim.rst
index f44f51a8b8..9ba6c395b9 100644
--- a/docs/source/optim.rst
+++ b/docs/source/optim.rst
@@ -57,7 +57,7 @@ For example, this is very useful when one wants to specify per-layer learning ra
This means that ``model.base``'s parameters will use the default learning rate of ``1e-2``,
``model.classifier``'s parameters will use a learning rate of ``1e-3``, and a momentum of
-``0.9`` will be used for all parameters
+``0.9`` will be used for all parameters.
Taking an optimization step
^^^^^^^^^^^^^^^^^^^^^^^^^^^