Update README.md

README.md

@@ -9,7 +9,15 @@ pipeline_tag: text-classification
 # PropagandaDetection
 
 The model is a Transformer network based on a DistilBERT pre-trained model. 
-The pre-trained model is fine-tuned on the SemEval 2023 Task 3 training dataset for the propaganda detection task. To fine-tune the Transformer Distilbert-Base-Uncased, the following hyperparameters are used: the batch size of $16$; learning rate of $2e^{-5}$; AdamW optimizer; $4$ epochs. Tests provide an accuracy of around $90\%$.
+The pre-trained model is fine-tuned on the SemEval 2023 Task 3 training dataset for the propaganda detection task. 
+
+### Hyperparameters : 
+Batch size = 16; 
+Learning rate = 2e-5;
+AdamW optimizer;
+Epochs = 4. 
+
+Accuracy = 90 % on SemEval 2023 test set.
 
 
 ## References