p12475398
/
LLaMA-Factory-Mirror
forked from p04798526/LLaMA-Factory-Mirror
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix ppo trainer

This commit is contained in:
hiyouga 2023-12-28 18:09:28 +08:00
parent db6cb2d0e7
commit 5431be42f9
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
src/llmtuner/train/ppo/trainer.py
View File

@ -203,7 +203,7 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
r"""
Generates model's responses given queries.
"""
if self.finetuning_args.upcast_layernorm:
if self.model_args.upcast_layernorm:
layernorm_params = dump_layernorm(self.model)
if batch["input_ids"].size(0) == 1: # handle llama2 ppo with gradient accumulation > 1
@ -218,7 +218,7 @@ class CustomPPOTrainer(PPOTrainer, Trainer):
**batch
)
if self.finetuning_args.upcast_layernorm:
if self.model_args.upcast_layernorm:
restore_layernorm(self.model, layernorm_params)
query = batch["input_ids"].detach().cpu()