From 93bb9a8d8dd6d74b41bc5dc745d423ff6fd38be8 Mon Sep 17 00:00:00 2001
From: cassieesvelt <73311224+cassieesvelt@users.noreply.github.com>
Date: Mon, 13 May 2024 13:28:16 -0700
Subject: [PATCH] fix when the job fails and doesn't kick the node (#3186)

* fix when the job fails and doesn't kick the node

* reformat
---
 .../largescale-deep-learning/Debugging/Compute/run_nhc.py        | 1 +
 1 file changed, 1 insertion(+)

diff --git a/best-practices/largescale-deep-learning/Debugging/Compute/run_nhc.py b/best-practices/largescale-deep-learning/Debugging/Compute/run_nhc.py
index 3b3bf15850..250b2660a6 100644
--- a/best-practices/largescale-deep-learning/Debugging/Compute/run_nhc.py
+++ b/best-practices/largescale-deep-learning/Debugging/Compute/run_nhc.py
@@ -100,6 +100,7 @@ def parse_output(output_file):
             output, error = process.communicate()
             print(output)
             print(error)
+        if full_errors:
             raise Exception(
                 "Failures were found while running the node health checks. Please see the std_log_process.txt files under the 'outputs and logs' tab of the job for more information."
                 + full_errors