#!/bin/bash
#SBATCH --job-name=dppo_d3il_test
#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_d3il_%j.out
#SBATCH --error=logs/dppo_d3il_%j.err

# Load modules and set environment
module load devel/cuda/12.4
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/lib/nvidia
export CC=gcc
export CXX=g++
export WANDB_MODE=online
export DPPO_WANDB_ENTITY=${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 D3IL avoid_m1 pretrain..."
echo "Job ID: $SLURM_JOB_ID"

python script/run.py --config-name=pre_diffusion_mlp \
    --config-dir=cfg/d3il/pretrain/avoid_m1 \
    train.n_epochs=2 \
    train.save_model_freq=1

echo "D3IL test completed!"