#!/bin/bash
#SBATCH --job-name=dppo_dev_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_dev_%j.out
#SBATCH --error=logs/dppo_dev_%j.err

# Load required modules
module load devel/cuda/12.4

# Set environment variables for WandB
export WANDB_MODE=online
export WANDB_PROJECT=dppo_dev_test
export DPPO_WANDB_ENTITY=${DPPO_WANDB_ENTITY:-"dominik_roth"}  # Use personal account, not shared

# Default paths (can be overridden by environment)
export DPPO_DATA_DIR=${DPPO_DATA_DIR:-$SLURM_SUBMIT_DIR/data}
export DPPO_LOG_DIR=${DPPO_LOG_DIR:-$SLURM_SUBMIT_DIR/log}

# Change to project directory
cd $SLURM_SUBMIT_DIR

# Activate virtual environment
source .venv/bin/activate

# Run quick test with Gym Hopper (faster than other environments)
echo "Starting DPPO dev test..."
echo "Job ID: $SLURM_JOB_ID"
echo "Node: $SLURM_NODELIST"
echo "GPU: $CUDA_VISIBLE_DEVICES"
echo ""
echo "Python version: $(python --version)"
echo "PyTorch version: $(python -c 'import torch; print(torch.__version__)')"
echo "CUDA available: $(python -c 'import torch; print(torch.cuda.is_available())')"
echo ""

# Run a quick pre-training test with reduced epochs
# Note: Will only log to WandB if WANDB_API_KEY and DPPO_WANDB_ENTITY are properly set
python script/run.py --config-name=pre_diffusion_mlp \
    --config-dir=cfg/gym/pretrain/hopper-medium-v2 \
    train.n_epochs=2 \
    train.save_model_freq=1

echo "Dev test completed!"