423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-16 20:00:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

update ppo trainer

Browse Source
This commit is contained in:
hiyouga
2023-08-02 18:46:41 +08:00
parent 286f7be346
commit b5ba87952a
2 changed files with 46 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/tuner/core/trainer.py
View File

@@ -47,7 +47,6 @@ class PeftTrainer(Seq2SeqTrainer):
logger.info(f"Saving model checkpoint to {output_dir}")
model = unwrap_model(self.model)
if isinstance(model, PreTrainedModelWrapper):
# Custom state dict: https://github.com/lvwerra/trl/blob/v0.4.7/trl/models/modeling_value_head.py#L200
model_state_dict = state_dict or model.state_dict()