Spaces:
Paused
Paused
File size: 3,360 Bytes
2f5127c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 |
# Copyright 2020-2025 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import unittest
from trl.rewards import think_format_reward
class ThinkFormatRewardTester(unittest.TestCase):
def test_valid_format(self):
completions = [
"<think>This is my reasoning.</think>This is my answer.", # Simple, one-line reasoning
"<think>\nThis is my reasoning.\n</think>\nThis is my answer.", # Multiline reasoning
"<think>\nThis is\nmy reasoning.\n</think>\nThis is my answer.", # Multiline reasoning
"<think>\nThis is <some tag> my reasoning.</think>\nThis is my answer.", # Reasoning including other tags
"<think></think>\nThis is my answer.", # Empty reasoning
]
completions = [[{"content": completion}] for completion in completions]
expected_rewards = [1.0, 1.0, 1.0, 1.0, 1.0] # All should be valid
rewards = think_format_reward(completions)
self.assertEqual(rewards, expected_rewards)
def test_invalid_format(self):
completions = [
"<think>\nThis is my reasoning.\nThis is my answer.", # No closing </think>
"<think>This is my reasoning.\nThis is my answer.", # No closing </think>
"This is my reasoning. This is my answer.", # No <think> tags
"This is my reasoning.\nThis is my answer.", # No <think> tags
"This is my reasoning.</think>\nThis is my answer.", # No opening <think>
"This is my reasoning.</think>This is my answer.", # No opening <think>
"This<think>is my reasoning.</think>\nThis is my answer.", # <think> tag in the middle
"<think>This is<think>my reasoning.</think></think>This is my answer.", # Nested <think> tags
"<think>This is</think>\nmy\n<think>reasoning.</think>\nThis is my answer.", # Multiline <think>
]
completions = [[{"content": completion}] for completion in completions]
expected_rewards = [0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0] # All should be invalid
rewards = think_format_reward(completions)
self.assertEqual(rewards, expected_rewards)
def test_mixed_format(self):
completions = [
"<think>This is my reasoning.</think>This is my answer.", # Valid
"<think>\nThis is my reasoning.\n</think>\nThis is my answer.", # Valid
"<think>This is my reasoning.\nThis is my answer.", # Invalid
"This is my reasoning. This is my answer.", # Invalid
]
completions = [[{"content": completion}] for completion in completions]
expected_rewards = [1.0, 1.0, 0.0, 0.0]
rewards = think_format_reward(completions)
self.assertEqual(rewards, expected_rewards)
if __name__ == "__main__":
unittest.main()
|