Update README.md

README.md

@@ -50,7 +50,7 @@ filtering_task_list = [
 ]
 ```
 
-Using the datasets mentioned above, we apply SFT and iterative DPO training, a proprietary alignment strategy, to maximize the performance of our resulting model.
+Using the datasets mentioned above, we applied SFT and iterative DPO training, a proprietary alignment strategy, to maximize the performance of our resulting model.
 
 [1] Rafailov, R., Sharma, A., Mitchell, E., Ermon, S., Manning, C.D. and Finn, C., 2023. Direct preference optimization: Your language model is secretly a reward model. NeurIPS.