how to finetune this smolvla with my own dataset?

#3
by Xiaoyan97 - opened

Has your model worked? In my attempt, I recorded 40 action records at the same position and trained 20,000 steps using the official fine-tuning code. However, my model was unable to complete the actions.

python lerobot/scripts/train.py   --policy.path=lerobot/smolvla_base   --dataset.repo_id=Xiaoyan97/pick_up_scissors_v1   --dataset.root=Xiaoyan97/pick_up_scissors_v1   --batch_size=64   --steps=20000   --output_dir=outputs/smolvla_v1   --job_name=my_smolvla_training   --policy.device=cuda

Is it that my training steps are insufficient or for some other reason?

not yet, the task is too hard for smolVLA, I'm trying to adapt the iDP3 to it, but if you want to finetune with your own dataset, simply put the checkpoint in the argument like this:

python lerobot/scripts/train.py \
--policy.path=lerobot/smolvla_base\
 --dataset.repo_id=rancheng222/so101_tie_bag\
 --batch_size=32\
 --steps=200000\
 --dataset.video_backend=pyav\
 --output_dir=/home/ran/Codes/lerobot/outputs/smolvla_so101_tie_bag\
 --job_name=smol_vla_so101_tie_bag

Here's a vlog by smolvla. Hope it helps you.

Sign up or log in to comment