kyy/llm_trainer
1
0 Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix ppo dataset bug #4012

Browse Source
This commit is contained in:
hiyouga committed 2024-06-06 19:03:20 +08:00
1 parent fad2591e31
commit 149610c636
4 files changed
+4 -4
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

src/llamafactory/train/ppo/workflow.py
+1 -1
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