314a3f3c06
- Complete SLURM test scripts for all environment types - Gym fine-tuning: walker2d, halfcheetah validation tests - Robomimic fine-tuning: lift validation test with scheduler fix - D3IL validation: avoid_m1 pre-training and fine-tuning tests - Updated experiment plan with current validation status - All major environments now have automated testing pipeline
38 lines
1.3 KiB
Bash
38 lines
1.3 KiB
Bash
#!/bin/bash
|
|
#SBATCH --job-name=dppo_hc_ft
|
|
#SBATCH --account=hk-project-p0022232
|
|
#SBATCH --partition=dev_accelerated
|
|
#SBATCH --gres=gpu:1
|
|
#SBATCH --nodes=1
|
|
#SBATCH --ntasks-per-node=1
|
|
#SBATCH --cpus-per-task=8
|
|
#SBATCH --time=00:30:00
|
|
#SBATCH --mem=24G
|
|
#SBATCH --output=logs/dppo_hc_ft_%j.out
|
|
#SBATCH --error=logs/dppo_hc_ft_%j.err
|
|
|
|
module load devel/cuda/12.4
|
|
|
|
# MuJoCo environment for fine-tuning
|
|
export MUJOCO_PY_MUJOCO_PATH=/home/hk-project-robolear/ys1087/.mujoco/mujoco210
|
|
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/hk-project-robolear/ys1087/.mujoco/mujoco210/bin:/usr/lib/nvidia
|
|
export MUJOCO_GL=egl
|
|
|
|
# Environment variables
|
|
export WANDB_MODE=online
|
|
export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"dominik_roth"}
|
|
export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
|
|
export DPPO_LOG_DIR=${DPPO_LOG_DIR:-$SLURM_SUBMIT_DIR/log}
|
|
|
|
cd $SLURM_SUBMIT_DIR
|
|
source .venv/bin/activate
|
|
|
|
# Apply HoReKa MuJoCo compilation fix
|
|
echo "Applying HoReKa MuJoCo compilation fix..."
|
|
python -c "exec(open('fix_mujoco_compilation.py').read()); apply_mujoco_fix(); import mujoco_py; print('MuJoCo ready!')"
|
|
|
|
echo "Testing halfcheetah fine-tuning..."
|
|
python script/run.py --config-name=ft_ppo_diffusion_mlp \
|
|
--config-dir=cfg/gym/finetune/halfcheetah-v2 \
|
|
train.n_train_itr=10 \
|
|
train.save_model_freq=5 |