Update README.md

README.md

@@ -45,6 +45,7 @@ and then finetuned the entire model on [nasa smd qa training split](https://hugg
 
 
 ## Finetune (1) Hyperparameters (NQ Dataset) zero-shot:
+```
 train_batch_size = 16   
 val_batch_size = 8   
 n_epochs = 2   
@@ -56,8 +57,10 @@ last_layer_learning_rate=5e-6
 qa_head_learning_rate=3e-5   
 release_model= "roberta-finetuned-nq"    
 gradient_checkpointing=True   
+```
 
 ## Finetune (2) Hyperparameters (Nasa train):
+```
 train_batch_size = 16   
 val_batch_size = 8   
 n_epochs = 5   
@@ -68,7 +71,8 @@ optimizer=adamW
 layer_learning_rate=1e-6    
 qa_head_learning_rate=1e-5     
 release_model= "roberta-finetuned-nq-nasa"     
-gradient_checkpointing=True   
+gradient_checkpointing=True
+```
 
 ## Motive of 2 finetunes
 Finetune 1 was already strong towards answering capability, however the model tried to answer more often than abstaining therefore finetune 2 was needed to teach the model when to abstain.