Update README.md

README.md

@@ -10,7 +10,8 @@ Please note that the label distribution in the dataset is imbalanced:
 * ARGUMENTS:
 
 **Model training**
-**RoBERTArg** was fine-tuned on a $RoBERTA_{base}$ pre-trained model using the HuggingFace trainer with the following hyperparameters. The hyperparameters were determined using a hyperparameter search on a 20% validation set.
+
+**RoBERTArg** was fine-tuned on a $$RoBERTA_{base}$$ pre-trained model using the HuggingFace trainer with the following hyperparameters. The hyperparameters were determined using a hyperparameter search on a 20% validation set.
 
 ```
 training_args = TrainingArguments(