Update README.md

README.md

@@ -10,7 +10,8 @@ Model = distilbert-base-uncased
 
 Fine tuned the model from our own custom dataset
 
-`with training_args.strategy.scope():
+```python
+with training_args.strategy.scope():
     model = TFDistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")
 
 trainer = TFTrainer(
@@ -20,4 +21,4 @@ trainer = TFTrainer(
     eval_dataset=test_dataset             # evaluation dataset
 )
 
-trainer.train()`
+trainer.train()```