Add many missing spaces in adjacent strings (#26751)

Add missing spaces in adjacent strings

examples/research_projects/jax-projects/dataset-streaming/run_mlm_flax_stream.py

@@ -341,7 +341,7 @@ if __name__ == "__main__":
         and not training_args.overwrite_output_dir
     ):
         raise ValueError(
-            f"Output directory ({training_args.output_dir}) already exists and is not empty."
+            f"Output directory ({training_args.output_dir}) already exists and is not empty. "
             "Use --overwrite_output_dir to overcome."
         )
 
@@ -399,7 +399,7 @@ if __name__ == "__main__":
         )
     else:
         raise ValueError(
-            "You are instantiating a new tokenizer from scratch. This is not supported by this script."
+            "You are instantiating a new tokenizer from scratch. This is not supported by this script. "
             "You can do it from another script, save it, and load it from here, using --tokenizer_name."
         )
 

examples/research_projects/jax-projects/hybrid_clip/run_hybrid_clip.py

@@ -78,7 +78,7 @@ class ModelArguments:
     text_model_name_or_path: str = field(
         metadata={
             "help": (
-                "The text model checkpoint for weights initialization."
+                "The text model checkpoint for weights initialization. "
                 "Don't set if you want to train a model from scratch."
             )
         },
@@ -86,7 +86,7 @@ class ModelArguments:
     vision_model_name_or_path: str = field(
         metadata={
             "help": (
-                "The vision model checkpoint for weights initialization."
+                "The vision model checkpoint for weights initialization. "
                 "Don't set if you want to train a model from scratch."
             )
         },
@@ -311,7 +311,7 @@ def main():
         and not training_args.overwrite_output_dir
     ):
         raise ValueError(
-            f"Output directory ({training_args.output_dir}) already exists and is not empty."
+            f"Output directory ({training_args.output_dir}) already exists and is not empty. "
             "Use --overwrite_output_dir to overcome."
         )
 
@@ -341,7 +341,7 @@ def main():
         )
     else:
         raise ValueError(
-            "You are instantiating a new tokenizer from scratch. This is not supported by this script."
+            "You are instantiating a new tokenizer from scratch. This is not supported by this script. "
             "You can do it from another script, save it, and load it from here, using --tokenizer_name."
         )
 

examples/research_projects/jax-projects/model_parallel/run_clm_mp.py

@@ -246,7 +246,7 @@ def main():
         and not training_args.overwrite_output_dir
     ):
         raise ValueError(
-            f"Output directory ({training_args.output_dir}) already exists and is not empty."
+            f"Output directory ({training_args.output_dir}) already exists and is not empty. "
             "Use --overwrite_output_dir to overcome."
         )
 
@@ -325,7 +325,7 @@ def main():
         )
     else:
         raise ValueError(
-            "You are instantiating a new tokenizer from scratch. This is not supported by this script."
+            "You are instantiating a new tokenizer from scratch. This is not supported by this script. "
             "You can do it from another script, save it, and load it from here, using --tokenizer_name."
         )
 
@@ -368,7 +368,7 @@ def main():
     else:
         if data_args.block_size > tokenizer.model_max_length:
             logger.warning(
-                f"The block_size passed ({data_args.block_size}) is larger than the maximum length for the model"
+                f"The block_size passed ({data_args.block_size}) is larger than the maximum length for the model "
                 f"({tokenizer.model_max_length}). Using block_size={tokenizer.model_max_length}."
             )
         block_size = min(data_args.block_size, tokenizer.model_max_length)