diff --git a/trinity/buffer/reader/file_reader.py b/trinity/buffer/reader/file_reader.py
index 1f8abbc9902..2fa5d955fd8 100644
--- a/trinity/buffer/reader/file_reader.py
+++ b/trinity/buffer/reader/file_reader.py
@@ -1,4 +1,4 @@
-"""Filed based buffer reader."""
+"""File-based buffer reader."""
 
 from typing import List, Optional, Tuple
 
diff --git a/trinity/common/workflows/math_ruler_workflow.py b/trinity/common/workflows/math_ruler_workflow.py
index b3889f61a5a..8e0fbf6d7c7 100644
--- a/trinity/common/workflows/math_ruler_workflow.py
+++ b/trinity/common/workflows/math_ruler_workflow.py
@@ -32,7 +32,7 @@ def __init__(
     def reset(self, task: Task):
         """
         Note that in this workflow, MathRewardFn is only used for calculating the 'golden reward',
-        whereasa the rewards used by RL training are calculated by RULER.
+        whereas the rewards used by RL training are calculated by RULER.
         """
 
         if task.reward_fn is None:
@@ -94,7 +94,7 @@ def get_ruler_scores(self, responses: List[Experience], judge: Any) -> Tuple[boo
 
         question_prompt = (
             f"Question: {self.task_desc}\n\n"
-            f"""Solution format requirement: first think about the reasoning process in the mind and then provides the final answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e.,
+            f"""Solution format requirement: first think about the reasoning process in the mind and then provide the final answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e.,
 <think> reasoning process here </think>
 <answer> answer here </answer>."""
         )
diff --git a/trinity/common/workflows/math_trainable_ruler_workflow.py b/trinity/common/workflows/math_trainable_ruler_workflow.py
index 1ab31d4c8ef..d53707c04aa 100644
--- a/trinity/common/workflows/math_trainable_ruler_workflow.py
+++ b/trinity/common/workflows/math_trainable_ruler_workflow.py
@@ -144,7 +144,7 @@ def get_ruler_responses(
 
         question_prompt = (
             f"Question: {self.task_desc}\n\n"
-            f"""Solution format requirement: first think about the reasoning process in the mind and then provides the final answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e.,
+            f"""Solution format requirement: first think about the reasoning process in the mind and then provide the final answer. The reasoning process and answer are enclosed within <think> </think> and <answer> </answer> tags, respectively, i.e.,
 <think> reasoning process here </think>
 <answer> answer here </answer>."""
         )