update desc for map in all examples (#12226)

* update desc for map in all examples

* added plm

* suggestions

examples/pytorch/summarization/run_summarization.py

@@ -43,10 +43,12 @@ from transformers import (
 from transformers.file_utils import is_offline_mode
 from transformers.trainer_utils import get_last_checkpoint
 from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
 
 
 # Will error if the minimal version of Transformers is not installed. Remove at your own risks.
 check_min_version("4.8.0.dev0")
+require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -433,6 +435,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on train dataset",
         )
 
     if training_args.do_eval:
@@ -448,6 +451,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on validation dataset",
         )
 
     if training_args.do_predict:
@@ -463,6 +467,7 @@ def main():
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on prediction dataset",
         )
 
     # Data collator