From 89bf26213098fef139e115db393ac455ae267bb8 Mon Sep 17 00:00:00 2001 From: Sumanth Ratna Date: Thu, 3 Sep 2020 16:37:39 -0400 Subject: [PATCH] [tune] Fix lr typo in FAQ (#10548) --- doc/source/tune/_tutorials/_faq.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/source/tune/_tutorials/_faq.rst b/doc/source/tune/_tutorials/_faq.rst index f489d4d5d..96ff28590 100644 --- a/doc/source/tune/_tutorials/_faq.rst +++ b/doc/source/tune/_tutorials/_faq.rst @@ -57,7 +57,7 @@ reports to use ``max_depth=6`` for the maximum decision tree depth. Here, anythi between 2 and 10 might make sense (though that naturally depends on your problem). For **learning rates**, we suggest using a **loguniform distribution** between -**1e-1** and **1e-5**: ``tune.loguniform(1e-1, 1e05)``. +**1e-1** and **1e-5**: ``tune.loguniform(1e-1, 1e-5)``. For **batch sizes**, we suggest trying **powers of 2**, for instance, 2, 4, 8, 16, 32, 64, 128, 256, etc. The magnitude depends on your problem. For easy