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
29 lines
875 B
Bash
29 lines
875 B
Bash
#!/bin/bash
|
|
#SBATCH --job-name=dppo_d3il_avoid_m1_pre
|
|
#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=16G
|
|
#SBATCH --output=logs/dppo_d3il_avoid_m1_pre_%j.out
|
|
#SBATCH --error=logs/dppo_d3il_avoid_m1_pre_%j.err
|
|
|
|
module load devel/cuda/12.4
|
|
|
|
# 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
|
|
|
|
echo "Testing D3IL avoid_m1 pre-training..."
|
|
python script/run.py --config-name=pre_diffusion_mlp \
|
|
--config-dir=cfg/d3il/pretrain/avoid_m1 \
|
|
train.n_epochs=50 \
|
|
train.save_model_freq=25 |