Update README.md

README.md

@@ -111,7 +111,7 @@ bash reward_server/launch_reward.sh {MODEL_PATH} {ANSWER_PATH} {METRIC}
 ### Start training
 
 ```bash
-bash train.sh {METHOD} {PRETRAIN_PATH} {DATA_PATH} {REWARD_API}
+bash reward_server/RLVR_train.sh {METHOD} {PRETRAIN_PATH} {DATA_PATH} {REWARD_API}
 
 # METHOD:          advantage estimator, e.g., reinforce_baseline, reinforce, rloo
 # PRETRAIN_PATH:   path to the pretrained model, e.g., Qwen2.5-7B