[BIG] pytorch-transformers => transformers

examples/contrib/run_swag.py

@@ -35,10 +35,10 @@ from tqdm import tqdm, trange
 
 from tensorboardX import SummaryWriter
 
-from pytorch_transformers import (WEIGHTS_NAME, BertConfig,
+from transformers import (WEIGHTS_NAME, BertConfig,
                                   BertForMultipleChoice, BertTokenizer)
 
-from pytorch_transformers import AdamW, WarmupLinearSchedule
+from transformers import AdamW, WarmupLinearSchedule
 
 logger = logging.getLogger(__name__)
 
@@ -365,7 +365,7 @@ def train(args, train_dataset, model, tokenizer):
             #     inputs.update({'cls_index': batch[5],
             #                    'p_mask':       batch[6]})
             outputs = model(**inputs)
-            loss = outputs[0]  # model outputs are always tuple in pytorch-transformers (see doc)
+            loss = outputs[0]  # model outputs are always tuple in transformers (see doc)
 
             if args.n_gpu > 1:
                 loss = loss.mean() # mean() to average on multi-gpu parallel (not distributed) training
@@ -647,7 +647,7 @@ def main():
 
         if args.eval_all_checkpoints:
             checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("pytorch_transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
 
         logger.info("Evaluate the following checkpoints: %s", checkpoints)