Fix .push_to_hub and cleanup get_full_repo_name usage (#25120)

* Fix .push_to_hub and cleanup get_full_repo_name usage

* Do not rely on Python bool conversion magic

* request changes

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -59,7 +59,7 @@ from transformers import (
     set_seed,
 )
 from transformers.models.bart.modeling_flax_bart import shift_tokens_right
-from transformers.utils import get_full_repo_name, send_example_telemetry
+from transformers.utils import send_example_telemetry
 
 
 MODEL_CONFIG_CLASSES = list(FLAX_MODEL_FOR_MASKED_LM_MAPPING.keys())
@@ -496,14 +496,14 @@ def main():
 
     # Handle the repository creation
     if training_args.push_to_hub:
-        if training_args.hub_model_id is None:
-            repo_name = get_full_repo_name(
-                Path(training_args.output_dir).absolute().name, token=training_args.hub_token
-            )
-        else:
-            repo_name = training_args.hub_model_id
-        create_repo(repo_name, exist_ok=True, token=training_args.hub_token)
-        repo = Repository(training_args.output_dir, clone_from=repo_name, token=training_args.hub_token)
+        # Retrieve of infer repo_name
+        repo_name = training_args.hub_model_id
+        if repo_name is None:
+            repo_name = Path(training_args.output_dir).absolute().name
+        # Create repo and retrieve repo_id
+        repo_id = create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
+        # Clone repo locally
+        repo = Repository(training_args.output_dir, clone_from=repo_id, token=training_args.hub_token)
 
     # Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/

examples/flax/language-modeling/run_clm_flax.py

@@ -58,7 +58,7 @@ from transformers import (
     set_seed,
 )
 from transformers.testing_utils import CaptureLogger
-from transformers.utils import get_full_repo_name, send_example_telemetry
+from transformers.utils import send_example_telemetry
 
 
 logger = logging.getLogger(__name__)
@@ -372,14 +372,14 @@ def main():
 
     # Handle the repository creation
     if training_args.push_to_hub:
-        if training_args.hub_model_id is None:
-            repo_name = get_full_repo_name(
-                Path(training_args.output_dir).absolute().name, token=training_args.hub_token
-            )
-        else:
-            repo_name = training_args.hub_model_id
-        create_repo(repo_name, exist_ok=True, token=training_args.hub_token)
-        repo = Repository(training_args.output_dir, clone_from=repo_name, token=training_args.hub_token)
+        # Retrieve of infer repo_name
+        repo_name = training_args.hub_model_id
+        if repo_name is None:
+            repo_name = Path(training_args.output_dir).absolute().name
+        # Create repo and retrieve repo_id
+        repo_id = create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
+        # Clone repo locally
+        repo = Repository(training_args.output_dir, clone_from=repo_id, token=training_args.hub_token)
 
     #  Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/

examples/flax/language-modeling/run_mlm_flax.py

@@ -59,7 +59,7 @@ from transformers import (
     is_tensorboard_available,
     set_seed,
 )
-from transformers.utils import get_full_repo_name, send_example_telemetry
+from transformers.utils import send_example_telemetry
 
 
 MODEL_CONFIG_CLASSES = list(FLAX_MODEL_FOR_MASKED_LM_MAPPING.keys())
@@ -410,14 +410,14 @@ def main():
 
     # Handle the repository creation
     if training_args.push_to_hub:
-        if training_args.hub_model_id is None:
-            repo_name = get_full_repo_name(
-                Path(training_args.output_dir).absolute().name, token=training_args.hub_token
-            )
-        else:
-            repo_name = training_args.hub_model_id
-        create_repo(repo_name, exist_ok=True, token=training_args.hub_token)
-        repo = Repository(training_args.output_dir, clone_from=repo_name, token=training_args.hub_token)
+        # Retrieve of infer repo_name
+        repo_name = training_args.hub_model_id
+        if repo_name is None:
+            repo_name = Path(training_args.output_dir).absolute().name
+        # Create repo and retrieve repo_id
+        repo_id = create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
+        # Clone repo locally
+        repo = Repository(training_args.output_dir, clone_from=repo_id, token=training_args.hub_token)
 
     # Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/

examples/flax/language-modeling/run_t5_mlm_flax.py

@@ -59,7 +59,7 @@ from transformers import (
     set_seed,
 )
 from transformers.models.t5.modeling_flax_t5 import shift_tokens_right
-from transformers.utils import get_full_repo_name, send_example_telemetry
+from transformers.utils import send_example_telemetry
 
 
 MODEL_CONFIG_CLASSES = list(FLAX_MODEL_FOR_MASKED_LM_MAPPING.keys())
@@ -537,14 +537,14 @@ def main():
 
     # Handle the repository creation
     if training_args.push_to_hub:
-        if training_args.hub_model_id is None:
-            repo_name = get_full_repo_name(
-                Path(training_args.output_dir).absolute().name, token=training_args.hub_token
-            )
-        else:
-            repo_name = training_args.hub_model_id
-        create_repo(repo_name, exist_ok=True, token=training_args.hub_token)
-        repo = Repository(training_args.output_dir, clone_from=repo_name, token=training_args.hub_token)
+        # Retrieve of infer repo_name
+        repo_name = training_args.hub_model_id
+        if repo_name is None:
+            repo_name = Path(training_args.output_dir).absolute().name
+        # Create repo and retrieve repo_id
+        repo_id = create_repo(repo_name, exist_ok=True, token=training_args.hub_token).repo_id
+        # Clone repo locally
+        repo = Repository(training_args.output_dir, clone_from=repo_id, token=training_args.hub_token)
 
     # Get the datasets: you can either provide your own CSV/JSON/TXT training and evaluation files (see below)
     # or just provide the name of one of the public datasets available on the hub at https://huggingface.co/datasets/