admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-26 11:16:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(train): raise ValueError for PEFT usage in reward model training

Browse Source
This commit is contained in:
Khalil Meftah
2026-04-23 13:59:58 +02:00
parent 173e3495dc
commit 9f739ac1ff
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/scripts/lerobot_train.py
+2
View File
@@ -275,6 +275,8 @@ def train(cfg: TrainPipelineConfig, accelerator: "Accelerator | None" = None):
) )
if cfg.peft is not None: if cfg.peft is not None:
if cfg.is_reward_model_training:
raise ValueError("PEFT is only supported for policy training. ")
logging.info("Using PEFT! Wrapping model.") logging.info("Using PEFT! Wrapping model.")
peft_cli_overrides = dataclasses.asdict(cfg.peft) peft_cli_overrides = dataclasses.asdict(cfg.peft)
policy = policy.wrap_with_peft(peft_cli_overrides=peft_cli_overrides) policy = policy.wrap_with_peft(peft_cli_overrides=peft_cli_overrides)