diff --git a/examples/flax/text-classification/run_flax_glue.py b/examples/flax/text-classification/run_flax_glue.py
index 4494243c9a5d2b..281881c51182ee 100755
--- a/examples/flax/text-classification/run_flax_glue.py
+++ b/examples/flax/text-classification/run_flax_glue.py
@@ -484,7 +484,7 @@ def main():
             label_to_id = {i: label_name_to_id[label_list[i]] for i in range(num_labels)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )
diff --git a/examples/pytorch/text-classification/run_glue.py b/examples/pytorch/text-classification/run_glue.py
index 967b6c7be5bf28..e3bb7ea94ca07f 100755
--- a/examples/pytorch/text-classification/run_glue.py
+++ b/examples/pytorch/text-classification/run_glue.py
@@ -428,7 +428,7 @@ def main():
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )
diff --git a/examples/pytorch/text-classification/run_glue_no_trainer.py b/examples/pytorch/text-classification/run_glue_no_trainer.py
index e66b6a35150f3d..5ec90faf87a57d 100644
--- a/examples/pytorch/text-classification/run_glue_no_trainer.py
+++ b/examples/pytorch/text-classification/run_glue_no_trainer.py
@@ -370,7 +370,7 @@ def main():
             label_to_id = {i: label_name_to_id[label_list[i]] for i in range(num_labels)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )
diff --git a/examples/pytorch/token-classification/run_ner.py b/examples/pytorch/token-classification/run_ner.py
index 9229b50063c842..937d09d74d6277 100755
--- a/examples/pytorch/token-classification/run_ner.py
+++ b/examples/pytorch/token-classification/run_ner.py
@@ -417,7 +417,7 @@ def get_label_list(labels):
                 label_to_id = {l: i for i, l in enumerate(label_list)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(model.config.label2id.keys())}, dataset labels:"
                 f" {sorted(label_list)}.\nIgnoring the model labels as a result.",
             )
diff --git a/examples/pytorch/token-classification/run_ner_no_trainer.py b/examples/pytorch/token-classification/run_ner_no_trainer.py
index a7d67942979dcc..61e14da6cb8b25 100755
--- a/examples/pytorch/token-classification/run_ner_no_trainer.py
+++ b/examples/pytorch/token-classification/run_ner_no_trainer.py
@@ -458,7 +458,7 @@ def get_label_list(labels):
                 label_to_id = {l: i for i, l in enumerate(label_list)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(model.config.label2id.keys())}, dataset labels:"
                 f" {sorted(label_list)}.\nIgnoring the model labels as a result.",
             )
diff --git a/examples/tensorflow/text-classification/run_glue.py b/examples/tensorflow/text-classification/run_glue.py
index e2eb2157fa9e65..ec3fbe8c61bad3 100644
--- a/examples/tensorflow/text-classification/run_glue.py
+++ b/examples/tensorflow/text-classification/run_glue.py
@@ -326,7 +326,7 @@ def main():
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )
diff --git a/examples/tensorflow/text-classification/run_text_classification.py b/examples/tensorflow/text-classification/run_text_classification.py
index 379f3674038ccf..1aaa632cd78803 100644
--- a/examples/tensorflow/text-classification/run_text_classification.py
+++ b/examples/tensorflow/text-classification/run_text_classification.py
@@ -374,7 +374,7 @@ def main():
                 label_to_id = label_name_to_id  # Use the model's labels
             else:
                 logger.warning(
-                    "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                    "Your model seems to have been trained with labels, but they don't match the dataset: "
                     f"model labels: {sorted(label_name_to_id.keys())}, dataset labels:"
                     f" {sorted(label_list)}.\nIgnoring the model labels as a result.",
                 )
diff --git a/src/transformers/models/beit/configuration_beit.py b/src/transformers/models/beit/configuration_beit.py
index 6ff00b2b8790f0..f0f3c2582c35cc 100644
--- a/src/transformers/models/beit/configuration_beit.py
+++ b/src/transformers/models/beit/configuration_beit.py
@@ -14,6 +14,7 @@
 # limitations under the License.
 """BEiT model configuration"""
 
+import warnings
 from collections import OrderedDict
 from typing import Mapping
 
@@ -21,13 +22,9 @@
 
 from ...configuration_utils import PretrainedConfig
 from ...onnx import OnnxConfig
-from ...utils import logging
 from ...utils.backbone_utils import BackboneConfigMixin, get_aligned_output_features_output_indices
 
 
-logger = logging.get_logger(__name__)
-
-
 class BeitConfig(BackboneConfigMixin, PretrainedConfig):
     r"""
     This is the configuration class to store the configuration of a [`BeitModel`]. It is used to instantiate an BEiT
@@ -197,7 +194,7 @@ def __init__(
 
         # handle backwards compatibility
         if "segmentation_indices" in kwargs:
-            logger.warning(
+            warnings.warn(
                 "The `segmentation_indices` argument is deprecated and will be removed in a future version, use `out_indices` instead.",
                 FutureWarning,
             )
diff --git a/src/transformers/models/maskformer/image_processing_maskformer.py b/src/transformers/models/maskformer/image_processing_maskformer.py
index 73b428e0bab26d..aeec214884155c 100644
--- a/src/transformers/models/maskformer/image_processing_maskformer.py
+++ b/src/transformers/models/maskformer/image_processing_maskformer.py
@@ -15,6 +15,7 @@
 """Image processor class for MaskFormer."""
 
 import math
+import warnings
 from typing import TYPE_CHECKING, Any, Dict, Iterable, List, Optional, Set, Tuple, Union
 
 import numpy as np
@@ -987,7 +988,7 @@ def post_process_segmentation(
             `torch.Tensor`:
                 A tensor of shape (`batch_size, num_class_labels, height, width`).
         """
-        logger.warning(
+        warnings.warn(
             "`post_process_segmentation` is deprecated and will be removed in v5 of Transformers, please use"
             " `post_process_instance_segmentation`",
             FutureWarning,
diff --git a/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py b/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py
index 4c1b1b991eae16..b050b1ca5a6c1b 100644
--- a/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py
+++ b/tests/sagemaker/scripts/pytorch/run_glue_model_parallelism.py
@@ -366,7 +366,7 @@ def main():
             label_to_id = {i: int(label_name_to_id[label_list[i]]) for i in range(num_labels)}
         else:
             logger.warning(
-                "Your model seems to have been trained with labels, but they don't match the dataset: ",
+                "Your model seems to have been trained with labels, but they don't match the dataset: "
                 f"model labels: {sorted(label_name_to_id.keys())}, dataset labels: {sorted(label_list)}."
                 "\nIgnoring the model labels as a result.",
             )