update desc for map in all examples (#12226)

* update desc for map in all examples

* added plm

* suggestions

Author: bhavitvyamalik

examples/pytorch/language-modeling/requirements.txt

@@ -1,4 +1,4 @@
 torch >= 1.3
-datasets >= 1.1.3
+datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf

examples/pytorch/language-modeling/run_clm.py

@@ -46,10 +46,12 @@
 from transformers.testing_utils import CaptureLogger
 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/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -355,6 +357,7 @@ def tokenize_function(examples):
         num_proc=data_args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not data_args.overwrite_cache,
+        desc="Running tokenizer on dataset",
     )
 
     if data_args.block_size is None:
@@ -401,6 +404,7 @@ def group_texts(examples):
         batched=True,
         num_proc=data_args.preprocessing_num_workers,
         load_from_cache_file=not data_args.overwrite_cache,
+        desc=f"Grouping texts in chunks of {block_size}",
     )
 
     if training_args.do_train:

examples/pytorch/language-modeling/run_clm_no_trainer.py

@@ -48,9 +48,13 @@
     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/language-modeling/requirements.txt")
+
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
 
@@ -300,6 +304,7 @@ def tokenize_function(examples):
         num_proc=args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on dataset",
     )
 
     if args.block_size is None:
@@ -346,6 +351,7 @@ def group_texts(examples):
         batched=True,
         num_proc=args.preprocessing_num_workers,
         load_from_cache_file=not args.overwrite_cache,
+        desc=f"Grouping texts in chunks of {block_size}",
     )
 
     train_dataset = lm_datasets["train"]

examples/pytorch/language-modeling/run_mlm.py

@@ -45,10 +45,12 @@
 )
 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/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 MODEL_CONFIG_CLASSES = list(MODEL_FOR_MASKED_LM_MAPPING.keys())
@@ -380,6 +382,7 @@ def tokenize_function(examples):
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=[text_column_name],
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on dataset line_by_line",
         )
     else:
         # Otherwise, we tokenize every text, then concatenate them together before splitting them in smaller parts.
@@ -394,6 +397,7 @@ def tokenize_function(examples):
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on every text in dataset",
         )
 
         # Main data processing function that will concatenate all texts from our dataset and generate chunks of
@@ -424,6 +428,7 @@ def group_texts(examples):
             batched=True,
             num_proc=data_args.preprocessing_num_workers,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc=f"Grouping texts in chunks of {max_seq_length}",
         )
 
     if training_args.do_train:

examples/pytorch/language-modeling/run_mlm_no_trainer.py

@@ -48,9 +48,11 @@
     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/language-modeling/requirements.txt")
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
 
@@ -346,6 +348,7 @@ def tokenize_function(examples):
             num_proc=args.preprocessing_num_workers,
             remove_columns=[text_column_name],
             load_from_cache_file=not args.overwrite_cache,
+            desc="Running tokenizer on dataset line_by_line",
         )
     else:
         # Otherwise, we tokenize every text, then concatenate them together before splitting them in smaller parts.
@@ -360,6 +363,7 @@ def tokenize_function(examples):
             num_proc=args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not args.overwrite_cache,
+            desc="Running tokenizer on every text in dataset",
         )
 
         # Main data processing function that will concatenate all texts from our dataset and generate chunks of
@@ -390,6 +394,7 @@ def group_texts(examples):
             batched=True,
             num_proc=args.preprocessing_num_workers,
             load_from_cache_file=not args.overwrite_cache,
+            desc=f"Grouping texts in chunks of {max_seq_length}",
         )
 
     train_dataset = tokenized_datasets["train"]

examples/pytorch/language-modeling/run_plm.py

@@ -41,10 +41,12 @@
 )
 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/language-modeling/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -358,6 +360,7 @@ def tokenize_function(examples):
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=[text_column_name],
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on dataset line_by_line",
         )
     else:
         # Otherwise, we tokenize every text, then concatenate them together before splitting them in smaller parts.
@@ -370,6 +373,7 @@ def tokenize_function(examples):
             num_proc=data_args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc="Running tokenizer on every text in dataset",
         )
 
         # Main data processing function that will concatenate all texts from our dataset and generate chunks of
@@ -400,6 +404,7 @@ def group_texts(examples):
             batched=True,
             num_proc=data_args.preprocessing_num_workers,
             load_from_cache_file=not data_args.overwrite_cache,
+            desc=f"Grouping texts in chunks of {max_seq_length}",
         )
 
     if training_args.do_train:

examples/pytorch/question-answering/requirements.txt

@@ -1,2 +1,2 @@
-datasets >= 1.4.0
+datasets >= 1.8.0
 torch >= 1.3.0

examples/pytorch/question-answering/run_qa.py

@@ -42,11 +42,13 @@
 )
 from transformers.trainer_utils import get_last_checkpoint
 from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
 from utils_qa import postprocess_qa_predictions
 
 
 # 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/question-answering/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -417,6 +419,7 @@ def prepare_train_features(examples):
             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 data_args.max_train_samples is not None:
             # Number of samples might increase during Feature Creation, We select only specified max samples
@@ -478,6 +481,7 @@ def prepare_validation_features(examples):
             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 data_args.max_eval_samples is not None:
             # During Feature creation dataset samples might increase, we will select required samples again
@@ -497,6 +501,7 @@ def prepare_validation_features(examples):
             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",
         )
         if data_args.max_predict_samples is not None:
             # During Feature creation dataset samples might increase, we will select required samples again

examples/pytorch/question-answering/run_qa_beam_search.py

@@ -41,11 +41,13 @@
 )
 from transformers.trainer_utils import get_last_checkpoint
 from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
 from utils_qa import postprocess_qa_predictions_with_beam_search
 
 
 # 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/question-answering/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -429,6 +431,7 @@ def prepare_train_features(examples):
             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 data_args.max_train_samples is not None:
             # Select samples from dataset again since Feature Creation might increase number of features
@@ -514,6 +517,7 @@ def prepare_validation_features(examples):
             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 data_args.max_eval_samples is not None:
             # Selecting Samples from Dataset again since Feature Creation might increase samples size
@@ -533,6 +537,7 @@ def prepare_validation_features(examples):
             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",
         )
         if data_args.max_predict_samples is not None:
             # During Feature creation dataset samples might increase, we will select required samples again

examples/pytorch/question-answering/run_qa_beam_search_no_trainer.py

@@ -46,11 +46,13 @@
     set_seed,
 )
 from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
 from utils_qa import postprocess_qa_predictions_with_beam_search
 
 
 # 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/question-answering/requirements.txt")
 
 logger = logging.getLogger(__name__)
 
@@ -419,6 +421,7 @@ def prepare_train_features(examples):
         num_proc=args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on train dataset",
     )
     if args.max_train_samples is not None:
         # Number of samples might increase during Feature Creation, We select only specified max samples
@@ -503,6 +506,7 @@ def prepare_validation_features(examples):
         num_proc=args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on validation dataset",
     )
 
     if args.max_eval_samples is not None:
@@ -523,6 +527,7 @@ def prepare_validation_features(examples):
             num_proc=args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not args.overwrite_cache,
+            desc="Running tokenizer on prediction dataset",
         )
         if args.max_predict_samples is not None:
             # During Feature creation dataset samples might increase, we will select required samples again

examples/pytorch/question-answering/run_qa_no_trainer.py

@@ -48,11 +48,13 @@
     set_seed,
 )
 from transformers.utils import check_min_version
+from transformers.utils.versions import require_version
 from utils_qa import postprocess_qa_predictions
 
 
 # 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/question-answering/requirements.txt")
 
 logger = logging.getLogger(__name__)
 # You should update this to your particular problem to have better documentation of `model_type`
@@ -448,6 +450,7 @@ def prepare_train_features(examples):
         num_proc=args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on train dataset",
     )
     if args.max_train_samples is not None:
         # Number of samples might increase during Feature Creation, We select only specified max samples
@@ -508,6 +511,7 @@ def prepare_validation_features(examples):
         num_proc=args.preprocessing_num_workers,
         remove_columns=column_names,
         load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on validation dataset",
     )
 
     if args.max_eval_samples is not None:
@@ -528,6 +532,7 @@ def prepare_validation_features(examples):
             num_proc=args.preprocessing_num_workers,
             remove_columns=column_names,
             load_from_cache_file=not args.overwrite_cache,
+            desc="Running tokenizer on prediction dataset",
         )
         if args.max_predict_samples is not None:
             # During Feature creation dataset samples might increase, we will select required samples again

examples/pytorch/summarization/requirements.txt

@@ -1,4 +1,4 @@
-datasets >= 1.1.3
+datasets >= 1.8.0
 sentencepiece != 0.1.92
 protobuf
 rouge-score

examples/pytorch/summarization/run_summarization.py

@@ -43,10 +43,12 @@
 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 preprocess_function(examples):
             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 preprocess_function(examples):
             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 preprocess_function(examples):
             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

examples/pytorch/summarization/run_summarization_no_trainer.py

@@ -48,9 +48,12 @@
     set_seed,
 )
 from transformers.file_utils import is_offline_mode
+from transformers.utils.versions import require_version
 
 
 logger = logging.getLogger(__name__)
+require_version("datasets>=1.8.0", "To fix: pip install -r examples/pytorch/summarization/requirements.txt")
+
 # You should update this to your particular problem to have better documentation of `model_type`
 MODEL_CONFIG_CLASSES = list(MODEL_MAPPING.keys())
 MODEL_TYPES = tuple(conf.model_type for conf in MODEL_CONFIG_CLASSES)
@@ -419,7 +422,11 @@ def preprocess_function(examples):
         return model_inputs
 
     processed_datasets = raw_datasets.map(
-        preprocess_function, batched=True, remove_columns=column_names, load_from_cache_file=not args.overwrite_cache
+        preprocess_function,
+        batched=True,
+        remove_columns=column_names,
+        load_from_cache_file=not args.overwrite_cache,
+        desc="Running tokenizer on dataset",
     )
 
     train_dataset = processed_datasets["train"]