423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-18 12:50:38 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix API

Browse Source
This commit is contained in:
hiyouga
2023-07-19 00:01:14 +08:00
parent fe2887ca13
commit 29af67b015
5 changed files with 12 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/tuner/rm/trainer.py
View File

@@ -32,7 +32,7 @@ class PairwisePeftTrainer(PeftTrainer):
See: https://github.com/huggingface/transformers/blob/v4.30.2/src/transformers/trainer.py#L3509
"""
batch_size = inputs["input_ids"].size(0) // 2
_, _, values = model(**inputs)
_, _, values = model(**inputs, output_hidden_states=True, return_dict=True)
r_accept, r_reject = values[:, -1].split(batch_size, dim=0)
loss = -torch.log(torch.sigmoid(r_accept - r_reject)).mean()
return (loss, [loss, r_accept, r_reject]) if return_outputs else loss