Add many missing spaces in adjacent strings (huggingface#26751)

Add missing spaces in adjacent strings

examples/flax/image-captioning/create_model_from_encoder_decoder_models.py

@@ -37,15 +37,15 @@ class ModelArguments:
     encoder_model_name_or_path: str = field(
         metadata={
             "help": (
-                "The encoder model checkpoint for weights initialization."
+                "The encoder model checkpoint for weights initialization. "
                 "Don't set if you want to train an encoder model from scratch."
             )
         },
     )
     decoder_model_name_or_path: str = field(
         metadata={
             "help": (
-                "The decoder model checkpoint for weights initialization."
+                "The decoder model checkpoint for weights initialization. "
                 "Don't set if you want to train a decoder model from scratch."
             )
         },

examples/flax/image-captioning/run_image_captioning_flax.py

@@ -203,7 +203,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -256,7 +256,7 @@ class DataTrainingArguments:
         metadata={
             "help": (
                 "The maximum total sequence length for validation target text after tokenization. Sequences longer "
-                "than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`."
+                "than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`. "
                 "This argument is also used to override the `max_length` param of `model.generate`, which is used "
                 "during evaluation."
             )
@@ -423,7 +423,7 @@ 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."
         )
 
@@ -685,7 +685,7 @@ def preprocess_fn(examples, max_target_length, check_image=True):
     eval_batch_size = int(training_args.per_device_eval_batch_size) * jax.device_count()
     if training_args.block_size % train_batch_size > 0 or training_args.block_size % eval_batch_size > 0:
         raise ValueError(
-            "`training_args.block_size` needs to be a multiple of the global train/eval batch size."
+            "`training_args.block_size` needs to be a multiple of the global train/eval batch size. "
             f"Got {training_args.block_size}, {train_batch_size} and {eval_batch_size} respectively instead."
         )
 

examples/flax/language-modeling/run_bart_dlm_flax.py

@@ -487,7 +487,7 @@ 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."
         )
 
@@ -606,7 +606,7 @@ 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/flax/language-modeling/run_clm_flax.py

@@ -190,7 +190,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -368,7 +368,7 @@ 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."
         )
 
@@ -524,7 +524,7 @@ 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."
         )
 
@@ -586,7 +586,7 @@ def tokenize_function(examples):
     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)

examples/flax/language-modeling/run_mlm_flax.py

@@ -195,7 +195,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -411,7 +411,7 @@ 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."
         )
 
@@ -556,7 +556,7 @@ 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/flax/language-modeling/run_t5_mlm_flax.py

@@ -528,7 +528,7 @@ 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."
         )
 
@@ -647,7 +647,7 @@ 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/flax/question-answering/run_qa.py

@@ -176,7 +176,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -582,7 +582,7 @@ def main():
 
     if data_args.max_seq_length > tokenizer.model_max_length:
         logger.warning(
-            f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the"
+            f"The max_seq_length passed ({data_args.max_seq_length}) is larger than the maximum length for the "
             f"model ({tokenizer.model_max_length}). Using max_seq_length={tokenizer.model_max_length}."
         )
     max_seq_length = min(data_args.max_seq_length, tokenizer.model_max_length)

examples/flax/speech-recognition/run_flax_speech_recognition_seq2seq.py

@@ -415,7 +415,7 @@ 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."
         )
 

examples/flax/summarization/run_summarization_flax.py

@@ -209,7 +209,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -268,7 +268,7 @@ class DataTrainingArguments:
         metadata={
             "help": (
                 "The maximum total sequence length for validation target text after tokenization. Sequences longer "
-                "than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`."
+                "than this will be truncated, sequences shorter will be padded. Will default to `max_target_length`. "
                 "This argument is also used to override the `max_length` param of `model.generate`, which is used "
                 "during evaluation."
             )
@@ -451,7 +451,7 @@ 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."
         )
 
@@ -558,7 +558,7 @@ 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/flax/text-classification/run_flax_glue.py

@@ -122,7 +122,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },

examples/flax/token-classification/run_flax_ner.py

@@ -170,7 +170,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },

examples/flax/vision/run_image_classification.py

@@ -180,7 +180,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -291,7 +291,7 @@ 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."
         )
 

examples/legacy/multiple_choice/utils_multiple_choice.py

@@ -379,7 +379,7 @@ def get_test_examples(self, data_dir):
         """See base class."""
         logger.info("LOOKING AT {} dev".format(data_dir))
         raise ValueError(
-            "For swag testing, the input file does not contain a label column. It can not be tested in current code"
+            "For swag testing, the input file does not contain a label column. It can not be tested in current code "
             "setting!"
         )
         return self._create_examples(self._read_csv(os.path.join(data_dir, "test.csv")), "test")
@@ -541,7 +541,7 @@ def convert_examples_to_features(
             if "num_truncated_tokens" in inputs and inputs["num_truncated_tokens"] > 0:
                 logger.info(
                     "Attention! you are cropping tokens (swag task is ok). "
-                    "If you are training ARC and RACE and you are poping question + options,"
+                    "If you are training ARC and RACE and you are poping question + options, "
                     "you need to try to use a bigger max seq length!"
                 )
 

examples/legacy/pytorch-lightning/lightning_base.py

@@ -313,7 +313,7 @@ def add_generic_args(parser, root_dir) -> None:
         type=str,
         default="O2",
         help=(
-            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
+            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']. "
             "See details at https://nvidia.github.io/apex/amp.html"
         ),
     )

examples/legacy/question-answering/run_squad.py

@@ -663,7 +663,7 @@ def main():
         type=str,
         default="O1",
         help=(
-            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
+            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']. "
             "See details at https://nvidia.github.io/apex/amp.html"
         ),
     )

examples/legacy/run_language_modeling.py

@@ -149,7 +149,7 @@ class DataTrainingArguments:
         default=-1,
         metadata={
             "help": (
-                "Optional input sequence length after tokenization."
+                "Optional input sequence length after tokenization. "
                 "The training dataset will be truncated in block of this size for training."
                 "Default to the model max input length for single sentence inputs (take into account special tokens)."
             )
@@ -283,7 +283,7 @@ def main():
 
     if config.model_type in ["bert", "roberta", "distilbert", "camembert"] and not data_args.mlm:
         raise ValueError(
-            "BERT and RoBERTa-like models do not have LM heads but masked LM heads. They must be run using the"
+            "BERT and RoBERTa-like models do not have LM heads but masked LM heads. They must be run using the "
             "--mlm flag (masked language modeling)."
         )
 

examples/legacy/run_swag.py

@@ -579,7 +579,7 @@ def main():
         type=str,
         default="O1",
         help=(
-            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']."
+            "For fp16: Apex AMP optimization level selected in ['O0', 'O1', 'O2', and 'O3']. "
             "See details at https://nvidia.github.io/apex/amp.html"
         ),
     )

examples/pytorch/audio-classification/run_audio_classification.py

@@ -172,7 +172,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -189,14 +189,14 @@ def __post_init__(self):
         if not self.freeze_feature_extractor and self.freeze_feature_encoder:
             warnings.warn(
                 "The argument `--freeze_feature_extractor` is deprecated and "
-                "will be removed in a future version. Use `--freeze_feature_encoder`"
+                "will be removed in a future version. Use `--freeze_feature_encoder` "
                 "instead. Setting `freeze_feature_encoder==True`.",
                 FutureWarning,
             )
         if self.freeze_feature_extractor and not self.freeze_feature_encoder:
             raise ValueError(
                 "The argument `--freeze_feature_extractor` is deprecated and "
-                "should not be used in combination with `--freeze_feature_encoder`."
+                "should not be used in combination with `--freeze_feature_encoder`. "
                 "Only make use of `--freeze_feature_encoder`."
             )
 

examples/pytorch/contrastive-image-text/run_clip.py

@@ -107,7 +107,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },
@@ -358,7 +358,7 @@ 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/pytorch/image-classification/run_image_classification.py

@@ -163,7 +163,7 @@ class ModelArguments:
         metadata={
             "help": (
                 "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-                "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+                "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
                 "execute code present on the Hub on your local machine."
             )
         },

examples/pytorch/image-classification/run_image_classification_no_trainer.py

@@ -152,7 +152,7 @@ def parse_args():
         default=False,
         help=(
             "Whether or not to allow for custom models defined on the Hub in their own modeling files. This option"
-            "should only be set to `True` for repositories you trust and in which you have read the code, as it will"
+            "should only be set to `True` for repositories you trust and in which you have read the code, as it will "
             "execute code present on the Hub on your local machine."
         ),
     )
@@ -179,7 +179,7 @@ def parse_args():
         default="all",
         help=(
             'The integration to report the results and logs to. Supported platforms are `"tensorboard"`,'
-            ' `"wandb"`, `"comet_ml"` and `"clearml"`. Use `"all"` (default) to report to all integrations.'
+            ' `"wandb"`, `"comet_ml"` and `"clearml"`. Use `"all"` (default) to report to all integrations. '
             "Only applicable when `--with_tracking` is passed."
         ),
     )