add license

src/llamafactory/train/rm/trainer.py

@@ -1,3 +1,42 @@
+# Copyright 2024 the LlamaFactory team.
+#
+# This code is inspired by CarperAI's trlx library.
+# https://github.com/CarperAI/trlx/blob/v0.7.0/examples/summarize_rlhf/reward_model/reward_model.py
+#
+# 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.
+#
+# MIT License
+#
+# Copyright (c) 2022 CarperAI
+#
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+#
+# The above copyright notice and this permission notice shall be included in all
+# copies or substantial portions of the Software.
+#
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
 import json
 import os
 from types import MethodType
@@ -79,7 +118,6 @@ class PairwiseTrainer(Trainer):
         chosen_scores, rejected_scores = [], []
 
         # Compute pairwise loss. Only backprop on the different tokens before padding
-        # Inspired by: https://github.com/CarperAI/trlx/blob/main/examples/summarize_rlhf/reward_model/reward_model.py
         loss = 0
         for i in range(batch_size):
             chosen_length = (chosen_input_ids[i] != self.tokenizer.pad_token_id).nonzero()[-1] + 1