Fix typos . (#36551)

Signed-off-by: zhanluxianshen <[email protected]>

Author: zhanluxianshen

src/transformers/integrations/integration_utils.py

@@ -1218,7 +1218,7 @@ def setup(self, args, state, model):
             Whether to use MLflow nested runs. If set to `True` or *1*, will create a nested run inside the current
             run.
         - **MLFLOW_RUN_ID** (`str`, *optional*):
-            Allow to reattach to an existing run which can be usefull when resuming training from a checkpoint. When
+            Allow to reattach to an existing run which can be useful when resuming training from a checkpoint. When
             `MLFLOW_RUN_ID` environment variable is set, `start_run` attempts to resume a run with the specified run ID
             and other parameters are ignored.
         - **MLFLOW_FLATTEN_PARAMS** (`str`, *optional*, defaults to `False`):

src/transformers/models/nllb_moe/configuration_nllb_moe.py

@@ -100,7 +100,7 @@ class NllbMoeConfig(PretrainedConfig):
             experts.
         router_bias (`bool`, *optional*, defaults to `False`):
             Whether or not the classifier of the router should have a bias.
-        moe_token_dropout (`float`, *optional*, defualt ot 0.2):
+        moe_token_dropout (`float`, *optional*, default to 0.2):
             Masking rate for MoE expert output masking (EOM), which is implemented via a Dropout2d on the expert
             outputs.
         output_router_logits (`bool`, *optional*, defaults to `False`):