ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix bug in PPO training

Browse Source 
Former-commit-id: 2e99f0e53ce6de0acbcab85dd50aef874e8c6336
This commit is contained in:
hiyouga
2023-11-16 02:32:54 +08:00
parent f81a8a5e5c
commit e017266b98
3 changed files with 7 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/model/parser.py
View File

@@ -95,9 +95,6 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
if not dataset_attr.ranking:
raise ValueError("Please use ranked datasets for reward modeling or DPO training.")
if finetuning_args.stage == "ppo" and model_args.reward_model is None:
raise ValueError("Reward model is necessary for PPO training.")
if finetuning_args.stage == "ppo" and model_args.shift_attn:
raise ValueError("PPO training is incompatible with S^2-Attn.")