[BIG] pytorch-transformers => transformers

examples/run_lm_finetuning.py

@@ -35,7 +35,7 @@ from torch.utils.data.distributed import DistributedSampler
 from tensorboardX import SummaryWriter
 from tqdm import tqdm, trange
 
-from pytorch_transformers import (WEIGHTS_NAME, AdamW, WarmupLinearSchedule,
+from transformers import (WEIGHTS_NAME, AdamW, WarmupLinearSchedule,
                                   BertConfig, BertForMaskedLM, BertTokenizer,
                                   GPT2Config, GPT2LMHeadModel, GPT2Tokenizer,
                                   OpenAIGPTConfig, OpenAIGPTLMHeadModel, OpenAIGPTTokenizer,
@@ -188,7 +188,7 @@ def train(args, train_dataset, model, tokenizer):
             labels = labels.to(args.device)
             model.train()
             outputs = model(inputs, masked_lm_labels=labels) if args.mlm else model(inputs, labels=labels)
-            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 training
@@ -481,7 +481,7 @@ def main():
         checkpoints = [args.output_dir]
         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 logging
+            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce logging
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
         for checkpoint in checkpoints:
             global_step = checkpoint.split('-')[-1] if len(checkpoints) > 1 else ""