diff --git a/deepspeed/runtime/zero/stage3.py b/deepspeed/runtime/zero/stage3.py
index 5d47edaa44ac..5350b06e654e 100755
--- a/deepspeed/runtime/zero/stage3.py
+++ b/deepspeed/runtime/zero/stage3.py
@@ -35,7 +35,7 @@
 from deepspeed.utils.debug import debug_module2name_id, debug_param2name_id_numel, debug_param2name_id_shape_device, debug_module2name_class, printflock, log_rank_file
 
 
-def print_rank_0(message, debug=False, force=True):
+def print_rank_0(message, debug=False, force=False):
     rank = torch.distributed.get_rank()
     if rank == 0 and (debug or force):
         print(message)
diff --git a/deepspeed/utils/debug.py b/deepspeed/utils/debug.py
index 06f966dfa7a5..bb2b5f7ef75b 100644
--- a/deepspeed/utils/debug.py
+++ b/deepspeed/utils/debug.py
@@ -68,7 +68,7 @@ def printflock(*msgs):
     1. Enable the force debug in say partitioning and zero3 files
     2. Override the usual versions with ::
 
-        def print_rank_0(message, debug=False, force=True):
+        def print_rank_0(message, debug=False, force=False):
             rank = torch.distributed.get_rank()
             printflock(f"[{rank}] {message}")
     3. run the program and you get both logs non-interleaved
@@ -99,7 +99,7 @@ def log_rank_file(rank, *msgs):
     1. Enable the force debug in say partitioning and zero3 files
     2. Override the usual versions of print_rank_0 in those files with ::
 
-        def print_rank_0(message, debug=False, force=True):
+        def print_rank_0(message, debug=False, force=False):
             rank = torch.distributed.get_rank()
             log_rank_file(rank, message)