Update README.md

README.md

@@ -202,10 +202,6 @@ Each argument was constructed by selecting two random propositions (from a list
 
 <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
-#### Preprocessing
-
-[More Information Needed]
-We converted the data to the Alpaca chat format before feeding it to the model.
 
 #### Training
 
@@ -213,7 +209,7 @@ We used unsloth for memory reduced sped up training.
 
 We trained for one epoch.
 
-Less than 2.5 GB of VRAM were used for training, and it took 2.5 hours.
+Less than 3.5 GB of VRAM were used for training, and it took 3 hours.
 
 ## Evaluation