Tokenizers: Start cleaning examples a little (#3455)

* Start cleaning examples

* Fixup

examples/glue/run_pl_glue.py

@@ -68,7 +68,7 @@ class GLUETransformer(BaseTransformer):
                     output_mode=args.glue_output_mode,
                     pad_on_left=bool(args.model_type in ["xlnet"]),  # pad on the left for xlnet
                     pad_token=self.tokenizer.convert_tokens_to_ids([self.tokenizer.pad_token])[0],
-                    pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+                    pad_token_segment_id=self.tokenizer.pad_token_type_id,
                 )
                 logger.info("Saving features into cached file %s", cached_features_file)
                 torch.save(features, cached_features_file)

examples/hans/test_hans.py

@@ -342,8 +342,8 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
             max_length=args.max_seq_length,
             output_mode=output_mode,
             pad_on_left=bool(args.model_type in ["xlnet"]),  # pad on the left for xlnet
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+            pad_token=tokenizer.pad_token_id,
-            pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
         )
         if args.local_rank in [-1, 0]:
             logger.info("Saving features into cached file %s", cached_features_file)

examples/ner/run_ner.py

@@ -348,8 +348,8 @@ def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, mode):
             # roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
             pad_on_left=bool(args.model_type in ["xlnet"]),
             # pad on the left for xlnet
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+            pad_token=tokenizer.pad_token_id,
-            pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
             pad_token_label_id=pad_token_label_id,
         )
         if args.local_rank in [-1, 0]:

examples/ner/run_pl_ner.py

@@ -64,8 +64,8 @@ class NERTransformer(BaseTransformer):
                     sep_token=self.tokenizer.sep_token,
                     sep_token_extra=bool(args.model_type in ["roberta"]),
                     pad_on_left=bool(args.model_type in ["xlnet"]),
-                    pad_token=self.tokenizer.convert_tokens_to_ids([self.tokenizer.pad_token])[0],
+                    pad_token=self.tokenizer.pad_token_id,
-                    pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+                    pad_token_segment_id=self.tokenizer.pad_token_type_id,
                     pad_token_label_id=self.pad_token_label_id,
                 )
                 logger.info("Saving features into cached file %s", cached_features_file)

examples/ner/run_tf_ner.py

@@ -434,8 +434,8 @@ def load_and_cache_examples(args, tokenizer, labels, pad_token_label_id, batch_s
             # roberta uses an extra separator b/w pairs of sentences, cf. github.com/pytorch/fairseq/commit/1684e166e3da03f5b600dbb7855cb98ddfcd0805
             pad_on_left=bool(args["model_type"] in ["xlnet"]),
             # pad on the left for xlnet
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+            pad_token=tokenizer.pad_token_id,
-            pad_token_segment_id=4 if args["model_type"] in ["xlnet"] else 0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
             pad_token_label_id=pad_token_label_id,
         )
         logging.info("Saving features into cached file %s", cached_features_file)

examples/run_glue.py

@@ -360,8 +360,8 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
             max_length=args.max_seq_length,
             output_mode=output_mode,
             pad_on_left=bool(args.model_type in ["xlnet"]),  # pad on the left for xlnet
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+            pad_token=tokenizer.pad_token_id,
-            pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
         )
         if args.local_rank in [-1, 0]:
             logger.info("Saving features into cached file %s", cached_features_file)

examples/run_multiple_choice.py

@@ -361,7 +361,7 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False, test=False):
             args.max_seq_length,
             tokenizer,
             pad_on_left=bool(args.model_type in ["xlnet"]),  # pad on the left for xlnet
-            pad_token_segment_id=4 if args.model_type in ["xlnet"] else 0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
         )
         if args.local_rank in [-1, 0]:
             logger.info("Saving features into cached file %s", cached_features_file)

examples/run_xnli.py

@@ -350,8 +350,8 @@ def load_and_cache_examples(args, task, tokenizer, evaluate=False):
             max_length=args.max_seq_length,
             output_mode=output_mode,
             pad_on_left=False,
-            pad_token=tokenizer.convert_tokens_to_ids([tokenizer.pad_token])[0],
+            pad_token=tokenizer.pad_token_id,
-            pad_token_segment_id=0,
+            pad_token_segment_id=tokenizer.pad_token_type_id,
         )
         if args.local_rank in [-1, 0]:
             logger.info("Saving features into cached file %s", cached_features_file)