#!/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

echo "Testing hopper finetune v2 with stdio.h fix and cleared cache..."
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