add relevant description to tqdm in examples (#11927)

* add relevant `desc` in examples

* require_version datasets>=1.8.0

examples/pytorch/text-classification/requirements.txt

@@ -1,5 +1,5 @@
 accelerate
-datasets >= 1.1.3
+datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
 torch >= 1.3

examples/pytorch/text-classification/run_glue.py

@@ -42,10 +42,12 @@ from transformers import (
 )
 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("4.7.0.dev0")
+require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 
 task_to_keys = {
     "cola": ("sentence", None),
@@ -393,7 +395,12 @@ def main():
             result["label"] = [(label_to_id[l] if l != -1 else -1) for l in examples["label"]]
         return result
 
-    datasets = datasets.map(preprocess_function, batched=True, load_from_cache_file=not data_args.overwrite_cache)
+    datasets = datasets.map(
+        preprocess_function,
+        batched=True,
+        load_from_cache_file=not data_args.overwrite_cache,
+        desc="Running tokenizer on dataset",
+    )
     if training_args.do_train:
         if "train" not in datasets:
             raise ValueError("--do_train requires a train dataset")

examples/pytorch/text-classification/run_glue_no_trainer.py

@@ -38,10 +38,13 @@ from transformers import (
     get_scheduler,
     set_seed,
 )
+from transformers.utils.versions import require_version
 
 
 logger = logging.getLogger(__name__)
 
+require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
+
 task_to_keys = {
     "cola": ("sentence", None),
     "mnli": ("premise", "hypothesis"),
@@ -305,7 +308,10 @@ def main():
         return result
 
     processed_datasets = raw_datasets.map(
-        preprocess_function, batched=True, remove_columns=raw_datasets["train"].column_names
+        preprocess_function,
+        batched=True,
+        remove_columns=raw_datasets["train"].column_names,
+        desc="Running tokenizer on dataset",
     )
 
     train_dataset = processed_datasets["train"]

examples/pytorch/text-classification/run_xnli.py

@@ -42,10 +42,12 @@ from transformers import (
 )
 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("4.7.0.dev0")
+require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -280,6 +282,7 @@ def main():
             preprocess_function,
             batched=True,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on train dataset",
         )
         # Log a few random samples from the training set:
         for index in random.sample(range(len(train_dataset)), 3):
@@ -292,6 +295,7 @@ def main():
             preprocess_function,
             batched=True,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on validation dataset",
         )
 
     if training_args.do_predict:
@@ -301,6 +305,7 @@ def main():
             preprocess_function,
             batched=True,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on prediction dataset",
         )
 
     # Get the metric function