fix: 修正AdamW超参数默认值与文档示例

- 交换adamw_beta1/adamw_beta2默认值:beta1=0.95, beta2=0.99
- label_smoothing默认值改为0.05
- 文档示例统一更新:train_type=pt, weight_decay=0.01
- 移除文档中过时的strategy default标注
This commit is contained in:
2026-05-16 22:46:17 +08:00
parent f91bfee33e
commit e1638a7ade
5 changed files with 26 additions and 26 deletions
+3 -3
View File
@@ -69,13 +69,13 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--adamw_beta1",
type=float,
default=0.9,
default=0.95,
help="Beta values for AdamW optimizer.",
)
parser.add_argument(
"--adamw_beta2",
type=float,
default=0.95,
default=0.99,
help="Beta values for AdamW optimizer.",
)
parser.add_argument(
@@ -116,7 +116,7 @@ def parse_args() -> argparse.Namespace:
parser.add_argument(
"--label_smoothing",
type=float,
default=0.1,
default=0.05,
help="cross_entropy function label smoothing parameter",
)