dppo/slurm/dev_tests/test_hopper_finetune_v2.sh
ys1087@partner.kit.edu 826b55a2d2 Integrate HoReKa Intel compiler fix for mujoco-py
- Add HoReKa-specific MuJoCo compilation fix to install script
- Pin compatible Cython version (0.29.37)
- Create fix_mujoco_compilation.py helper script
- Document Intel compiler override in README
- Update test script to use integrated fix
- Addresses Intel OneAPI compiler flag incompatibility with GCC
2025-08-27 16:09:13 +02:00

43 lines
1.4 KiB
Bash

#!/bin/bash
#SBATCH --job-name=dppo_hop_ft_v2
#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_hop_ft_v2_%j.out
#SBATCH --error=logs/dppo_hop_ft_v2_%j.err
module load devel/cuda/12.4
# MuJoCo environment for fine-tuning with compilation fixes
export MUJOCO_PY_MUJOCO_PATH=/home/hk-project-robolear/ys1087/.mujoco/mujoco210
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/hk-project-robolear/ys1087/.mujoco/mujoco210/bin:/usr/lib/nvidia
export MUJOCO_GL=egl
# Force GCC compilation environment
export CC=gcc
export CXX=g++
export CFLAGS="-w"
export CXXFLAGS="-w"
export WANDB_MODE=online
export DPPO_WANDB_ENTITY=${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 hopper finetune v2 with HoReKa MuJoCo fix..."
python script/run.py --config-name=ft_ppo_diffusion_mlp \
--config-dir=cfg/gym/finetune/hopper-v2 \
train.n_train_itr=10 \
train.save_model_freq=5