Update train.py

train.py

@@ -278,7 +278,7 @@ def main():
     parser.add_argument("--max_grad_norm", default=1.0, type=float,
                         help="Max gradient norm.")
 
-    parser.add_argument("--local_rank", type=int, default=-1,
+    parser.add_argument("--local-rank", type=int, default=-1,
                         help="local_rank for distributed training on gpus")
     parser.add_argument('--seed', type=int, default=42,
                         help="random seed for initialization")