diff --git a/examples/flax/question-answering/run_qa.py b/examples/flax/question-answering/run_qa.py
index d08e7f01fd5..a8bf71e0a1a 100644
--- a/examples/flax/question-answering/run_qa.py
+++ b/examples/flax/question-answering/run_qa.py
@@ -62,7 +62,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset
diff --git a/examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py b/examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py
index ec7be4bc553..4e4f6818bf8 100644
--- a/examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py
+++ b/examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py
@@ -60,7 +60,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risk.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=2.14.0", "To fix: pip install -r examples/flax/speech-recogintion/requirements.txt")
 
diff --git a/examples/flax/text-classification/run_flax_glue.py b/examples/flax/text-classification/run_flax_glue.py
index 823eed2459a..39382e360fb 100755
--- a/examples/flax/text-classification/run_flax_glue.py
+++ b/examples/flax/text-classification/run_flax_glue.py
@@ -55,7 +55,7 @@
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 Array = Any
 Dataset = datasets.arrow_dataset.Dataset
diff --git a/examples/flax/token-classification/run_flax_ner.py b/examples/flax/token-classification/run_flax_ner.py
index d5ae59d9b1e..9c4d2c346c1 100644
--- a/examples/flax/token-classification/run_flax_ner.py
+++ b/examples/flax/token-classification/run_flax_ner.py
@@ -56,7 +56,7 @@
 
 logger = logging.getLogger(__name__)
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
 
diff --git a/examples/pytorch/audio-classification/run_audio_classification.py b/examples/pytorch/audio-classification/run_audio_classification.py
index 900bf4950c2..d95e04913b1 100644
--- a/examples/pytorch/audio-classification/run_audio_classification.py
+++ b/examples/pytorch/audio-classification/run_audio_classification.py
@@ -45,7 +45,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.14.0", "To fix: pip install -r examples/pytorch/audio-classification/requirements.txt")
 
diff --git a/examples/pytorch/contrastive-image-text/run_clip.py b/examples/pytorch/contrastive-image-text/run_clip.py
index d9ead22810d..dd272738e8b 100644
--- a/examples/pytorch/contrastive-image-text/run_clip.py
+++ b/examples/pytorch/contrastive-image-text/run_clip.py
@@ -55,7 +55,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/contrastive-image-text/requirements.txt")
 
diff --git a/examples/pytorch/image-classification/run_image_classification.py b/examples/pytorch/image-classification/run_image_classification.py
index 95ffdbf04ed..47c4dae6859 100755
--- a/examples/pytorch/image-classification/run_image_classification.py
+++ b/examples/pytorch/image-classification/run_image_classification.py
@@ -57,7 +57,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-classification/requirements.txt")
 
diff --git a/examples/pytorch/image-classification/run_image_classification_no_trainer.py b/examples/pytorch/image-classification/run_image_classification_no_trainer.py
index a9e0758ee7c..c8a3a409994 100644
--- a/examples/pytorch/image-classification/run_image_classification_no_trainer.py
+++ b/examples/pytorch/image-classification/run_image_classification_no_trainer.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 
diff --git a/examples/pytorch/image-pretraining/run_mae.py b/examples/pytorch/image-pretraining/run_mae.py
index 5e3ba45e6c0..ad53fe96561 100644
--- a/examples/pytorch/image-pretraining/run_mae.py
+++ b/examples/pytorch/image-pretraining/run_mae.py
@@ -44,7 +44,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 
diff --git a/examples/pytorch/image-pretraining/run_mim.py b/examples/pytorch/image-pretraining/run_mim.py
index e644cf48e47..6e2d661a305 100644
--- a/examples/pytorch/image-pretraining/run_mim.py
+++ b/examples/pytorch/image-pretraining/run_mim.py
@@ -49,7 +49,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 
diff --git a/examples/pytorch/image-pretraining/run_mim_no_trainer.py b/examples/pytorch/image-pretraining/run_mim_no_trainer.py
index ddce78940ae..a5894dfc0cb 100644
--- a/examples/pytorch/image-pretraining/run_mim_no_trainer.py
+++ b/examples/pytorch/image-pretraining/run_mim_no_trainer.py
@@ -54,7 +54,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-pretraining/requirements.txt")
 
diff --git a/examples/pytorch/language-modeling/run_clm.py b/examples/pytorch/language-modeling/run_clm.py
index 8521f2e8746..4715568838b 100755
--- a/examples/pytorch/language-modeling/run_clm.py
+++ b/examples/pytorch/language-modeling/run_clm.py
@@ -56,7 +56,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
diff --git a/examples/pytorch/language-modeling/run_clm_no_trainer.py b/examples/pytorch/language-modeling/run_clm_no_trainer.py
index 7a18814e650..5a9e0ac30ab 100755
--- a/examples/pytorch/language-modeling/run_clm_no_trainer.py
+++ b/examples/pytorch/language-modeling/run_clm_no_trainer.py
@@ -57,7 +57,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 
diff --git a/examples/pytorch/language-modeling/run_mlm.py b/examples/pytorch/language-modeling/run_mlm.py
index 98739ec62eb..ae991e54e39 100755
--- a/examples/pytorch/language-modeling/run_mlm.py
+++ b/examples/pytorch/language-modeling/run_mlm.py
@@ -54,7 +54,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
diff --git a/examples/pytorch/language-modeling/run_mlm_no_trainer.py b/examples/pytorch/language-modeling/run_mlm_no_trainer.py
index 8ef5eb3a2c0..18c3694db4d 100755
--- a/examples/pytorch/language-modeling/run_mlm_no_trainer.py
+++ b/examples/pytorch/language-modeling/run_mlm_no_trainer.py
@@ -57,7 +57,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
diff --git a/examples/pytorch/language-modeling/run_plm.py b/examples/pytorch/language-modeling/run_plm.py
index af0d5f06a0b..b8f6eee68e3 100755
--- a/examples/pytorch/language-modeling/run_plm.py
+++ b/examples/pytorch/language-modeling/run_plm.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/language-modeling/requirements.txt")
 
diff --git a/examples/pytorch/multiple-choice/run_swag.py b/examples/pytorch/multiple-choice/run_swag.py
index 5b7aaa0a705..9c7fa24a458 100755
--- a/examples/pytorch/multiple-choice/run_swag.py
+++ b/examples/pytorch/multiple-choice/run_swag.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = logging.getLogger(__name__)
 
diff --git a/examples/pytorch/multiple-choice/run_swag_no_trainer.py b/examples/pytorch/multiple-choice/run_swag_no_trainer.py
index e15cc9da9a3..55675584b14 100755
--- a/examples/pytorch/multiple-choice/run_swag_no_trainer.py
+++ b/examples/pytorch/multiple-choice/run_swag_no_trainer.py
@@ -56,7 +56,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 # You should update this to your particular problem to have better documentation of `model_type`
diff --git a/examples/pytorch/question-answering/run_qa.py b/examples/pytorch/question-answering/run_qa.py
index a7153287b00..4f01a2c8a5b 100755
--- a/examples/pytorch/question-answering/run_qa.py
+++ b/examples/pytorch/question-answering/run_qa.py
@@ -50,7 +50,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
diff --git a/examples/pytorch/question-answering/run_qa_beam_search.py b/examples/pytorch/question-answering/run_qa_beam_search.py
index 7eeca98a967..24a8807b6e4 100755
--- a/examples/pytorch/question-answering/run_qa_beam_search.py
+++ b/examples/pytorch/question-answering/run_qa_beam_search.py
@@ -49,7 +49,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
diff --git a/examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py b/examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py
index ed92bccbd20..2979f230f06 100644
--- a/examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py
+++ b/examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py
@@ -56,7 +56,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
diff --git a/examples/pytorch/question-answering/run_qa_no_trainer.py b/examples/pytorch/question-answering/run_qa_no_trainer.py
index 2ae3eb6c45c..a8c5ee35f93 100755
--- a/examples/pytorch/question-answering/run_qa_no_trainer.py
+++ b/examples/pytorch/question-answering/run_qa_no_trainer.py
@@ -57,7 +57,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
diff --git a/examples/pytorch/question-answering/run_seq2seq_qa.py b/examples/pytorch/question-answering/run_seq2seq_qa.py
index 42788b6886e..ef36a1c9640 100644
--- a/examples/pytorch/question-answering/run_seq2seq_qa.py
+++ b/examples/pytorch/question-answering/run_seq2seq_qa.py
@@ -47,7 +47,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/question-answering/requirements.txt")
 
diff --git a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py
index 4c9c16254fd..a820bd65959 100644
--- a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py
+++ b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py
@@ -52,7 +52,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=2.0.0", "To fix: pip install -r examples/pytorch/semantic-segmentation/requirements.txt")
 
diff --git a/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py b/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py
index a3c045b49f0..109dca1fde1 100644
--- a/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py
+++ b/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py
@@ -50,7 +50,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 
diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py b/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
index 47c08fc5f94..4f3ad63e13b 100755
--- a/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
+++ b/examples/pytorch/speech-recognition/run_speech_recognition_ctc.py
@@ -51,7 +51,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 
diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py b/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py
index a3d8a7b46ef..89a5a7cccd8 100755
--- a/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py
+++ b/examples/pytorch/speech-recognition/run_speech_recognition_ctc_adapter.py
@@ -53,7 +53,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 
diff --git a/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py b/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
index 555ecb39a01..5dee6016f68 100755
--- a/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
+++ b/examples/pytorch/speech-recognition/run_speech_recognition_seq2seq.py
@@ -49,7 +49,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.18.0", "To fix: pip install -r examples/pytorch/speech-recognition/requirements.txt")
 
diff --git a/examples/pytorch/summarization/run_summarization.py b/examples/pytorch/summarization/run_summarization.py
index f14783a78ff..3426b85b19e 100755
--- a/examples/pytorch/summarization/run_summarization.py
+++ b/examples/pytorch/summarization/run_summarization.py
@@ -53,7 +53,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 
diff --git a/examples/pytorch/summarization/run_summarization_no_trainer.py b/examples/pytorch/summarization/run_summarization_no_trainer.py
index 30c1b887e80..661721541e9 100644
--- a/examples/pytorch/summarization/run_summarization_no_trainer.py
+++ b/examples/pytorch/summarization/run_summarization_no_trainer.py
@@ -56,7 +56,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
diff --git a/examples/pytorch/test_accelerate_examples.py b/examples/pytorch/test_accelerate_examples.py
index 83f5b229bab..1fc8df3352c 100644
--- a/examples/pytorch/test_accelerate_examples.py
+++ b/examples/pytorch/test_accelerate_examples.py
@@ -77,12 +77,9 @@ def setUpClass(cls):
     def tearDownClass(cls):
         shutil.rmtree(cls.tmpdir)
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="rocm skip")
-    @mock.patch.dict(os.environ, {"WANDB_MODE": "offline"})
-=======
     @mock.patch.dict(os.environ, {"WANDB_MODE": "offline", "DVCLIVE_TEST": "true"})
->>>>>>> main
     def test_run_glue_no_trainer(self):
         tmp_dir = self.get_auto_remove_tmp_dir()
         testargs = f"""
@@ -155,12 +152,9 @@ def test_run_mlm_no_trainer(self):
         self.assertTrue(os.path.exists(os.path.join(tmp_dir, "epoch_0")))
         self.assertTrue(os.path.exists(os.path.join(tmp_dir, "mlm_no_trainer")))
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="rocm skip")
-    @mock.patch.dict(os.environ, {"WANDB_MODE": "offline"})
-=======
     @mock.patch.dict(os.environ, {"WANDB_MODE": "offline", "DVCLIVE_TEST": "true"})
->>>>>>> main
     def test_run_ner_no_trainer(self):
         # with so little data distributed training needs more epochs to get the score on par with 0/1 gpu
         epochs = 7 if backend_device_count(torch_device) > 1 else 2
@@ -216,12 +210,9 @@ def test_run_squad_no_trainer(self):
         self.assertTrue(os.path.exists(os.path.join(tmp_dir, "epoch_0")))
         self.assertTrue(os.path.exists(os.path.join(tmp_dir, "qa_no_trainer")))
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="rocm skip")
-    @mock.patch.dict(os.environ, {"WANDB_MODE": "offline"})
-=======
     @mock.patch.dict(os.environ, {"WANDB_MODE": "offline", "DVCLIVE_TEST": "true"})
->>>>>>> main
     def test_run_swag_no_trainer(self):
         tmp_dir = self.get_auto_remove_tmp_dir()
         testargs = f"""
@@ -326,12 +317,9 @@ def test_run_semantic_segmentation_no_trainer(self):
         result = get_results(tmp_dir)
         self.assertGreaterEqual(result["eval_overall_accuracy"], 0.10)
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="rocm skip")
-    @mock.patch.dict(os.environ, {"WANDB_MODE": "offline"})
-=======
     @mock.patch.dict(os.environ, {"WANDB_MODE": "offline", "DVCLIVE_TEST": "true"})
->>>>>>> main
     def test_run_image_classification_no_trainer(self):
         tmp_dir = self.get_auto_remove_tmp_dir()
         testargs = f"""
diff --git a/examples/pytorch/text-classification/run_classification.py b/examples/pytorch/text-classification/run_classification.py
index f278a5a7b46..35bf291f290 100755
--- a/examples/pytorch/text-classification/run_classification.py
+++ b/examples/pytorch/text-classification/run_classification.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 
diff --git a/examples/pytorch/text-classification/run_glue.py b/examples/pytorch/text-classification/run_glue.py
index 0fdeef7d18b..6dc042dfafb 100755
--- a/examples/pytorch/text-classification/run_glue.py
+++ b/examples/pytorch/text-classification/run_glue.py
@@ -49,7 +49,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 
diff --git a/examples/pytorch/text-classification/run_glue_no_trainer.py b/examples/pytorch/text-classification/run_glue_no_trainer.py
index 870eeb31e99..9eca1b6fc19 100644
--- a/examples/pytorch/text-classification/run_glue_no_trainer.py
+++ b/examples/pytorch/text-classification/run_glue_no_trainer.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 
diff --git a/examples/pytorch/text-classification/run_xnli.py b/examples/pytorch/text-classification/run_xnli.py
index d7c2c3fa816..98e423e88e7 100755
--- a/examples/pytorch/text-classification/run_xnli.py
+++ b/examples/pytorch/text-classification/run_xnli.py
@@ -49,7 +49,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 
diff --git a/examples/pytorch/token-classification/run_ner.py b/examples/pytorch/token-classification/run_ner.py
index 318d373483a..e52c6891f88 100755
--- a/examples/pytorch/token-classification/run_ner.py
+++ b/examples/pytorch/token-classification/run_ner.py
@@ -50,7 +50,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
 
diff --git a/examples/pytorch/token-classification/run_ner_no_trainer.py b/examples/pytorch/token-classification/run_ner_no_trainer.py
index 7d2939f81bf..c90ace1a7b9 100755
--- a/examples/pytorch/token-classification/run_ner_no_trainer.py
+++ b/examples/pytorch/token-classification/run_ner_no_trainer.py
@@ -56,7 +56,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/token-classification/requirements.txt")
diff --git a/examples/pytorch/translation/run_translation.py b/examples/pytorch/translation/run_translation.py
index c220519b3f2..0a9c5039449 100755
--- a/examples/pytorch/translation/run_translation.py
+++ b/examples/pytorch/translation/run_translation.py
@@ -53,7 +53,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/translation/requirements.txt")
 
diff --git a/examples/pytorch/translation/run_translation_no_trainer.py b/examples/pytorch/translation/run_translation_no_trainer.py
index 1e8009d42d8..3f91e67c855 100644
--- a/examples/pytorch/translation/run_translation_no_trainer.py
+++ b/examples/pytorch/translation/run_translation_no_trainer.py
@@ -57,7 +57,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = get_logger(__name__)
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/translation/requirements.txt")
diff --git a/examples/tensorflow/contrastive-image-text/run_clip.py b/examples/tensorflow/contrastive-image-text/run_clip.py
index d63712133ca..268618042cd 100644
--- a/examples/tensorflow/contrastive-image-text/run_clip.py
+++ b/examples/tensorflow/contrastive-image-text/run_clip.py
@@ -52,7 +52,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version(
     "datasets>=1.8.0", "To fix: pip install -r examples/tensorflow/contrastive-image-text/requirements.txt"
diff --git a/examples/tensorflow/image-classification/run_image_classification.py b/examples/tensorflow/image-classification/run_image_classification.py
index dfc8bd48441..be0afaa8b3a 100644
--- a/examples/tensorflow/image-classification/run_image_classification.py
+++ b/examples/tensorflow/image-classification/run_image_classification.py
@@ -55,7 +55,7 @@
 logger = logging.getLogger(__name__)
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/image-classification/requirements.txt")
 
diff --git a/examples/tensorflow/multiple-choice/run_swag.py b/examples/tensorflow/multiple-choice/run_swag.py
index e170daa9793..704ed2ccc3a 100644
--- a/examples/tensorflow/multiple-choice/run_swag.py
+++ b/examples/tensorflow/multiple-choice/run_swag.py
@@ -51,7 +51,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = logging.getLogger(__name__)
 
diff --git a/examples/tensorflow/question-answering/run_qa.py b/examples/tensorflow/question-answering/run_qa.py
index 70a65bed465..84e9668f189 100755
--- a/examples/tensorflow/question-answering/run_qa.py
+++ b/examples/tensorflow/question-answering/run_qa.py
@@ -49,7 +49,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 logger = logging.getLogger(__name__)
 
diff --git a/examples/tensorflow/summarization/run_summarization.py b/examples/tensorflow/summarization/run_summarization.py
index c4bf4e35d2f..cb4a6ff6590 100644
--- a/examples/tensorflow/summarization/run_summarization.py
+++ b/examples/tensorflow/summarization/run_summarization.py
@@ -54,7 +54,7 @@
 
 # region Checking dependencies
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 
diff --git a/examples/tensorflow/text-classification/run_glue.py b/examples/tensorflow/text-classification/run_glue.py
index 0bcaf56170a..36bd6574744 100644
--- a/examples/tensorflow/text-classification/run_glue.py
+++ b/examples/tensorflow/text-classification/run_glue.py
@@ -48,7 +48,7 @@
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 task_to_keys = {
     "cola": ("sentence", None),
diff --git a/examples/tensorflow/translation/run_translation.py b/examples/tensorflow/translation/run_translation.py
index 42b96c5515b..140307c1b82 100644
--- a/examples/tensorflow/translation/run_translation.py
+++ b/examples/tensorflow/translation/run_translation.py
@@ -57,7 +57,7 @@
 
 # region Dependencies and constants
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.37.0.dev0")
+check_min_version("4.36.0")
 
 require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 
diff --git a/setup.py b/setup.py
index aba442ff42b..2ac934841ef 100644
--- a/setup.py
+++ b/setup.py
@@ -428,7 +428,7 @@ def run(self):
 
 setup(
     name="transformers",
-    version="4.37.0.dev0",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
+    version="4.36.2",  # expected format is one of x.y.z.dev0, or x.y.z.rc1 or x.y.z (no to dashes, yes to dots)
     author="The Hugging Face team (past and future) with the help of all our contributors (https://github.com/huggingface/transformers/graphs/contributors)",
     author_email="transformers@huggingface.co",
     description="State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow",
diff --git a/src/transformers/__init__.py b/src/transformers/__init__.py
index e7d168154aa..eff5adb5597 100644
--- a/src/transformers/__init__.py
+++ b/src/transformers/__init__.py
@@ -18,7 +18,7 @@
 # to defer the actual importing for when the objects are requested. This way `import transformers` provides the names
 # in the namespace without actually importing anything (and especially none of the backends).
 
-__version__ = "4.37.0.dev0"
+__version__ = "4.36.2"
 
 from typing import TYPE_CHECKING
 
diff --git a/src/transformers/models/mixtral/modeling_mixtral.py b/src/transformers/models/mixtral/modeling_mixtral.py
index a32b9b1457a..3066eb86f7b 100644
--- a/src/transformers/models/mixtral/modeling_mixtral.py
+++ b/src/transformers/models/mixtral/modeling_mixtral.py
@@ -96,8 +96,9 @@ def load_balancing_loss_func(gate_logits: torch.Tensor, num_experts: torch.Tenso
         return 0
 
     if isinstance(gate_logits, tuple):
+        # cat along the layers?
         compute_device = gate_logits[0].device
-        concatenated_gate_logits = torch.cat([layer_gate.to(compute_device) for layer_gate in gate_logits], dim=0)
+        gate_logits = torch.cat([gate.to(compute_device) for gate in gate_logits], dim=0)
 
     routing_weights = torch.nn.functional.softmax(concatenated_gate_logits, dim=-1)
 
diff --git a/tests/models/blip_2/test_modeling_blip_2.py b/tests/models/blip_2/test_modeling_blip_2.py
index 546ca584177..7a9d23ea906 100644
--- a/tests/models/blip_2/test_modeling_blip_2.py
+++ b/tests/models/blip_2/test_modeling_blip_2.py
@@ -983,14 +983,10 @@ def test_inference_opt_multi_accelerator(self):
         )
         self.assertEqual(generated_text, "it's not a city, it's a beach")
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="UT compatability skip")
-    @require_torch_multi_gpu
-    def test_inference_t5_multi_gpu(self):
-=======
     @require_torch_multi_accelerator
     def test_inference_t5_multi_accelerator(self):
->>>>>>> main
         processor = Blip2Processor.from_pretrained("Salesforce/blip2-flan-t5-xl")
         device_map = device_map = {
             "query_tokens": 0,
diff --git a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py
index 9618b018890..ae464b182dd 100644
--- a/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py
+++ b/tests/models/mobilenet_v1/test_modeling_mobilenet_v1.py
@@ -14,12 +14,9 @@
 # limitations under the License.
 """ Testing suite for the PyTorch MobileNetV1 model. """
 
-<<<<<<< HEAD
+
 import pytest
 import inspect
-=======
-
->>>>>>> main
 import unittest
 
 from transformers import MobileNetV1Config
diff --git a/tests/pipelines/test_pipelines_automatic_speech_recognition.py b/tests/pipelines/test_pipelines_automatic_speech_recognition.py
index 8210ca18406..5fb759f63d0 100644
--- a/tests/pipelines/test_pipelines_automatic_speech_recognition.py
+++ b/tests/pipelines/test_pipelines_automatic_speech_recognition.py
@@ -1152,9 +1152,6 @@ def test_with_local_lm_fast(self):
 
     @require_torch
     @slow
-<<<<<<< HEAD
-    @pytest.mark.skip(reason="UT compatibility skip")
-=======
     def test_whisper_longform(self):
         # fmt: off
         EXPECTED_RESULT = """ Folks, if you watch the show, you know, I spent a lot of time right over there. Patiently and astutely scrutinizing the boxwood and mahogany chest set of the day's biggest stories developing the central headline pawns, definitely maneuvering an oso topical night to F6, fainting a classic Sicilian, nade door variation on the news, all the while seeing eight moves deep and patiently marshalling the latest press releases into a fisher's shows in Lip Nitsky attack that culminates in the elegant lethal slow-played, all-passant checkmate that is my nightly monologue. But sometimes, sometimes, folks, I. CHEERING AND APPLAUSE Sometimes I startle away, cubside down in the monkey bars of a condemned playground on a super fun site. Get all hept up on goofballs. Rummage that were discarded tag bag of defective toys. Yank out of fist bowl of disembodied doll limbs, toss them on a stained kid's place mat from a defunct denny's, set up a table inside a rusty cargo container down by the Wharf and challenged toothless drifters to the godless bughouse blitz of tournament that is my segment. Meanwhile!"""
@@ -1200,7 +1197,7 @@ def test_seamless_v2(self):
 
     @require_torch
     @slow
->>>>>>> main
+    @pytest.mark.skip(reason="UT compatibility skip")
     def test_chunking_and_timestamps(self):
         model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
         tokenizer = AutoTokenizer.from_pretrained("facebook/wav2vec2-base-960h")
diff --git a/tests/test_modeling_common.py b/tests/test_modeling_common.py
index 4bd21721283..34f4898ed3c 100755
--- a/tests/test_modeling_common.py
+++ b/tests/test_modeling_common.py
@@ -647,16 +647,12 @@ def check_training_gradient_checkpointing(self, gradient_checkpointing_kwargs=No
             loss.backward()
             optimizer.step()
 
-<<<<<<< HEAD
-    @mark.skip(reason="UT compatability skip")
-    def test_training_gradient_checkpointing(self):
-=======
             for k, v in model.named_parameters():
                 if v.requires_grad:
                     self.assertTrue(v.grad is not None, f"{k} in {model_class.__name__} has no gradient!")
 
+    @mark.skip(reason="UT compatability skip")
     def test_training(self):
->>>>>>> main
         if not self.model_tester.is_training:
             return
 
@@ -2916,9 +2912,6 @@ def test_load_with_mismatched_shapes(self):
                     else:
                         new_model_without_prefix(input_ids)
 
-<<<<<<< HEAD
-    @mark.skip(reason="UT compatability skip")
-=======
     def test_mismatched_shapes_have_properly_initialized_weights(self):
         if not self.test_mismatched_shapes:
             return
@@ -3023,7 +3016,7 @@ def _init_weights(self, module):
                         msg=f"the weight values for `{key}` in `new_model` and `target_model` are not identical",
                     )
 
->>>>>>> main
+    @mark.skip(reason="UT compatability skip")
     def test_model_is_small(self):
         # Just a consistency check to make sure we are not running tests on 80M parameter models.
         config, _ = self.model_tester.prepare_config_and_inputs_for_common()
diff --git a/tests/trainer/test_trainer.py b/tests/trainer/test_trainer.py
index 27d3c6a0271..7faef293a88 100644
--- a/tests/trainer/test_trainer.py
+++ b/tests/trainer/test_trainer.py
@@ -875,9 +875,8 @@ def test_number_of_steps_in_training_with_ipex(self):
             train_output = trainer.train()
             self.assertEqual(train_output.global_step, 10)
 
-<<<<<<< HEAD
+
     @pytest.mark.skip(reason="rocm skip")
-=======
     def test_neftune(self):
         config = GPT2Config(vocab_size=100, n_positions=128, n_embd=32, n_layer=3, n_head=4)
         tiny_gpt2 = GPT2LMHeadModel(config)
@@ -922,7 +921,7 @@ def test_neftune(self):
 
         self.assertTrue(torch.allclose(emb1, emb2), "Neftune noise is still applied!")
 
->>>>>>> main
+
     def test_logging_inf_nan_filter(self):
         config = GPT2Config(vocab_size=100, n_positions=128, n_embd=32, n_layer=3, n_head=4)
         tiny_gpt2 = GPT2LMHeadModel(config)