423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-16 00:28:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix bug

Browse Source 
Former-commit-id: 2fd7a8fc3134af66193a5e8db8fea35025f82de9
This commit is contained in:
hiyouga 2023-12-03 21:40:40 +08:00
parent 60aea7521b
commit 09f165d442
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/train/ppo/trainer.py
View File

@ -66,7 +66,7 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
if self.args.max_steps > 0:
logger.info("max_steps is given, it will override any value given in num_train_epochs")
if reward_model is not None:
if finetuning_args.reward_model_type == "full":
if self.is_deepspeed_enabled:
if not (
getattr(reward_model.pretrained_model, "is_loaded_in_8bit", False)