423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 12:42:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update finetuning_args.py

Browse Source 
Former-commit-id: b24635d22b3084ad29217ef55c1dd1fa4f85a1fb
This commit is contained in:
Yuchen Han 2023-11-17 00:15:51 -08:00 committed by GitHub
parent 0d2262ffd0
commit ec910a87c0
1 changed files with 4 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/hparams/finetuning_args.py
View File

@ -74,6 +74,10 @@ class RLHFArguments:
default=None, default=None,
metadata={"help": "Log with either 'wandb' or 'tensorboard' in PPO training."} metadata={"help": "Log with either 'wandb' or 'tensorboard' in PPO training."}
) )
ppo_epochs: Optional[int] = field(
default=4,
metadata={"help": "Number of optimisation epochs per batch of samples"},
)
ppo_score_norm: Optional[bool] = field( ppo_score_norm: Optional[bool] = field(
default=False, default=False,
metadata={"help": "Use score normalization in PPO training."} metadata={"help": "Use score normalization in PPO training."}