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

fix ppo dataset bug #4012

Browse Source 
Former-commit-id: 7fc51b2e93698ae5e012566af8481f4d861c873d
This commit is contained in:
hiyouga
2024-06-06 19:03:20 +08:00
parent d5559461c1
commit ca95e98ca0
4 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/train/ppo/workflow.py
View File

@@ -29,7 +29,7 @@ def run_ppo(
):
tokenizer_module = load_tokenizer(model_args)
tokenizer = tokenizer_module["tokenizer"]
dataset = get_dataset(model_args, data_args, training_args, stage="pt", **tokenizer_module)
dataset = get_dataset(model_args, data_args, training_args, stage="ppo", **tokenizer_module)
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train, add_valuehead=True)
tokenizer.padding_side = "left" # use left-padding in generation while using right-padding in training