Update comments mentioning Python 2.

examples/contrib/run_swag.py

@@ -341,7 +341,7 @@ def train(args, train_dataset, model, tokenizer):
     tr_loss, logging_loss = 0.0, 0.0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/distillation/run_squad_w_distillation.py

@@ -159,7 +159,7 @@ def train(args, train_dataset, model, tokenizer, teacher=None):
     tr_loss, logging_loss = 0.0, 0.0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/mm-imdb/run_mmimdb.py

@@ -164,7 +164,7 @@ def train(args, train_dataset, model, tokenizer, criterion):
     best_f1, n_no_improve = 0, 0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/run_glue.py

@@ -185,7 +185,7 @@ def train(args, train_dataset, model, tokenizer):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/run_lm_finetuning.py

@@ -281,7 +281,7 @@ def train(args, train_dataset, model, tokenizer):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    set_seed(args)  # Added here for reproducibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproducibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/run_multiple_choice.py

@@ -145,7 +145,7 @@ def train(args, train_dataset, model, tokenizer):
     best_steps = 0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/run_ner.py

@@ -169,7 +169,7 @@ def train(args, train_dataset, model, tokenizer, labels, pad_token_label_id):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

examples/run_squad.py

@@ -185,7 +185,7 @@ def train(args, train_dataset, model, tokenizer):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    # Added here for reproductibility (even between python 2 and 3)
+    # Added here for reproductibility
     set_seed(args)
 
     for _ in train_iterator:

examples/run_xnli.py

@@ -164,7 +164,7 @@ def train(args, train_dataset, model, tokenizer):
     train_iterator = trange(
         epochs_trained, int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0]
     )
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):

setup.py

@@ -14,7 +14,7 @@ To create the package for pypi.
    creating the wheel and the source distribution (obviously).
 
    For the wheel, run: "python setup.py bdist_wheel" in the top level directory.
-   (this will build a wheel for the python version you use to build it - make sure you use python 3.x).
+   (this will build a wheel for the python version you use to build it).
 
    For the sources, run: "python setup.py sdist"
    You should now have a /dist directory with both .whl and .tar.gz source versions.

templates/adding_a_new_example_script/run_xxx.py

@@ -155,7 +155,7 @@ def train(args, train_dataset, model, tokenizer):
     tr_loss, logging_loss = 0.0, 0.0
     model.zero_grad()
     train_iterator = trange(int(args.num_train_epochs), desc="Epoch", disable=args.local_rank not in [-1, 0])
-    set_seed(args)  # Added here for reproductibility (even between python 2 and 3)
+    set_seed(args)  # Added here for reproductibility
     for _ in train_iterator:
         epoch_iterator = tqdm(train_dataloader, desc="Iteration", disable=args.local_rank not in [-1, 0])
         for step, batch in enumerate(epoch_iterator):