diff --git a/README b/README
index c139c39e3aee435654087c69386121c4766c5602..cb9e82a9be24d167aa85d560b73a641bcc73f869 100644
--- a/README
+++ b/README
@@ -20,7 +20,7 @@ inspired by http://www.ark.cs.cmu.edu/SEMAFOR/training/ and https://github.com/s
 01-parse-data.sh
 02-create-more-data-structures.sh
 03-train-frame-identification.sh
-04-train-argument-identification.sh
+04-train-argument-identification.sh (this step is 140h long, uses 30G of memory)
 
 4) Enjoy