diff --git a/docs/guides/grpo.md b/docs/guides/grpo.md
index a403b323df..37149ca7ae 100755
--- a/docs/guides/grpo.md
+++ b/docs/guides/grpo.md
@@ -249,7 +249,7 @@ This parameter specifies the number of prompts generated by each dataloader per
 
 - task_name (unique task identifier):
   - Determines which processor, env, prompts, and dataset to use for this task.
-  - Currently, we support a single dataset and a single environment. Therefore, task_name equals the dataset_name in the config (i.e., config.data.dataset_name).
+  - Currently, we support a single dataset and a single environment. Therefore, task_name equals the dataset_name in the config (i.e., config.data.train.dataset_name).
 - task_spec (TaskDataSpec):
   - Specifies per-task system prompt and prompt.
 - task_data_processors: