bring all workers online

phueb · May 13, 2021 · 8228482 · 8228482
1 parent c0243ce
commit 8228482
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 4 deletions.
diff --git a/ludwig/__main__.py b/ludwig/__main__.py
@@ -55,7 +55,8 @@ def status():
         status_, output = subprocess.getstatusoutput(command)
 
         if status_ != 0:
-            return 'Something went wrong. Check your access to the shared drive. Try using --mnt flag.'
+            print(output)
+            return 'Something went wrong. Check your access to the shared drive. Try using -mnt PATH_TO_DRIVE.'
 
         lines = str(output).split('\n')
         lines_with_ludwig_status = [line for line in lines if 'Ludwig' in line]

diff --git a/ludwig/configs.py b/ludwig/configs.py
@@ -12,9 +12,7 @@ class WorkerDirs:
 class Remote:
     watched_pattern = 'run*.py'  # this is required for watcher to know which file to run
     path_to_ssh_config = Path.home() / '.ssh' / 'ludwig_config'
-    online_worker_names = ['norman', 'hebb', 'hinton', 'pitts', 'hawkins', 'lecun']
-    # TODO bengio is down - march 24 2020
-    # todo hoff - no NVIDIA driver found by torch.
+    online_worker_names = ['norman', 'hebb', 'hinton', 'pitts', 'hawkins', 'lecun', 'hoff', 'bengio']
     all_worker_names = ['hoff', 'norman', 'hebb', 'hinton', 'pitts', 'hawkins', 'bengio', 'lecun']
     group2workers = {'half1': ['hoff', 'norman', 'hebb', 'hinton'],
                      'half2': ['pitts', 'hawkins', 'bengio', 'lecun']}