Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion trinity/buffer/reader/file_reader.py
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
"""Filed based buffer reader."""
"""File-based buffer reader."""

from typing import List, Optional, Tuple

Expand Down
4 changes: 2 additions & 2 deletions trinity/common/workflows/math_ruler_workflow.py
Original file line number Diff line number Diff line change
Expand Up @@ -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:
Expand Down Expand Up @@ -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>."""
)
Expand Down
2 changes: 1 addition & 1 deletion trinity/common/workflows/math_trainable_ruler_workflow.py
Original file line number Diff line number Diff line change
Expand Up @@ -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>."""
)
Expand Down