423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 06:12:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #5163 from liu-zichen/fix_ppo_optim

Browse Source 
fix lr not change

Former-commit-id: da335d42c30df2c2898516e290c0059250d57b63
This commit is contained in:
hoshi-hiyouga 2024-08-19 23:56:24 +08:00 committed by GitHub
commit 033dd1f1dc
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llamafactory/train/ppo/trainer.py
View File

@ -135,6 +135,7 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
dataset=train_dataset, dataset=train_dataset,
data_collator=data_collator, data_collator=data_collator,
lr_scheduler=scheduler, lr_scheduler=scheduler,
optimizer=optimizer,
) )
self.args = training_args self.args = training_args