clean up logger in examples for distributed case

examples/run_classifier.py

@@ -40,9 +40,6 @@ from pytorch_pretrained_bert.modeling import BertForSequenceClassification, Bert
 from pytorch_pretrained_bert.tokenization import BertTokenizer
 from pytorch_pretrained_bert.optimization import BertAdam, warmup_linear
 
-logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
-                    datefmt = '%m/%d/%Y %H:%M:%S',
-                    level = logging.INFO)
 logger = logging.getLogger(__name__)
 
 
@@ -697,6 +694,11 @@ def main():
         n_gpu = 1
         # Initializes the distributed backend which will take care of sychronizing nodes/GPUs
         torch.distributed.init_process_group(backend='nccl')
+
+    logging.basicConfig(format = '%(asctime)s - %(levelname)s - %(name)s -   %(message)s',
+                        datefmt = '%m/%d/%Y %H:%M:%S',
+                        level = logging.INFO if args.local_rank in [-1, 0] else logging.WARN)
+
     logger.info("device: {} n_gpu: {}, distributed training: {}, 16-bits training: {}".format(
         device, n_gpu, bool(args.local_rank != -1), args.fp16))