423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-18 04:40:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

tiny fix

Browse Source 
Former-commit-id: d75e377b0f
This commit is contained in:
hiyouga
2023-08-18 13:07:35 +08:00
parent b88f0b396c
commit 9f1688924d
2 changed files with 9 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -42,7 +42,7 @@ class PairwisePeftTrainer(PeftTrainer):
"""
batch_size = inputs["input_ids"].size(0) // 2
_, _, values = model(**inputs, output_hidden_states=True, return_dict=True)
if values.size(0) != inputs["input_ids"].size(0): # adapt chatglm2
if values.size(0) != inputs["input_ids"].size(0): # adapt to chatglm2
values = torch.transpose(values, 0, 1)
r_accept, r_reject = values[:, -1].split(batch_size, dim=0)
loss = -torch.log(torch.sigmoid(r_accept - r_reject)).mean()