Update README.md

README.md

@@ -37,7 +37,7 @@ The total number of the comparison pairs is 250K, where we perform the following
 
 ### Training
 
-We train the model for one epoch with a learning rate of 5e-6, batch size 256, cosine learning rate decay with a warmup ratio 0.03. You can see my training script here: https://github.com/WeiXiongUST/RAFT-Reward-Ranked-Finetuning/blob/main/reward_modeling.py 
+We train the model for one epoch with a learning rate of 5e-6, batch size 256, cosine learning rate decay with a warmup ratio 0.03. You can see my training script here: https://github.com/WeiXiongUST/RAFT-Reward-Ranked-Finetuning/blob/main/reward_modeling.py , which is modified from the TRL package.