ros/LlamaFactory
1
0
Fork 0
mirror of https://github.com/hiyouga/LlamaFactory.git synced 2026-03-18 23:13:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

tiny fix

Browse Source 
Former-commit-id: eae79707d31fd8be2cf4bee4d610557bbd49f6e7
This commit is contained in:
hiyouga
2023-05-29 09:42:29 +08:00
parent 83fc73c580
commit 35d04a2c05
5 changed files with 12 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/train_ppo.py
View File

@@ -69,7 +69,7 @@ def main():
ppo_trainer.ppo_train(max_target_length=data_args.max_target_length)
ppo_trainer.save_model()
ppo_trainer.save_state() # must be after save_model
if ppo_trainer.is_world_process_zero() and finetuning_args.plot_loss:
if ppo_trainer.is_world_process_zero() and model_args.plot_loss:
plot_loss(training_args, keys=["loss", "reward"])