Skip to content

Commit 19a0ce4

Browse files
authored
Fix lr-scaling store_true & default=True cli argument for textual_inversion training. (#1090)
Fix default lr-scaling cli argument
1 parent 856331c commit 19a0ce4

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

examples/textual_inversion/textual_inversion.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -164,7 +164,7 @@ def parse_args():
164164
parser.add_argument(
165165
"--scale_lr",
166166
action="store_true",
167-
default=True,
167+
default=False,
168168
help="Scale the learning rate by the number of GPUs, gradient accumulation steps, and batch size.",
169169
)
170170
parser.add_argument(

0 commit comments

Comments
 (0)