423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-03 20:22:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix rm dataset

Browse Source 
Former-commit-id: 5edf7cce0eb4cd569438bb406fe6f148eb05ee46
This commit is contained in:
hiyouga 2024-01-18 14:45:37 +08:00
parent f266d473b8
commit 6af2f1f217
1 changed files with 0 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -120,9 +120,6 @@ def get_train_args(args: Optional[Dict[str, Any]] = None) -> _TRAIN_CLS:
if finetuning_args.stage == "ppo" and not training_args.do_train:
raise ValueError("PPO training does not support evaluation, use the SFT stage to evaluate models.")
if finetuning_args.stage in ["rm", "dpo"] and (not all([data_attr.ranking for data_attr in data_args.dataset_list])):
raise ValueError("Please use ranked datasets for reward modeling or DPO training.")
if finetuning_args.stage == "ppo" and model_args.shift_attn:
raise ValueError("PPO training is incompatible with S^2-Attn.")