chore(hpc): finalize hpc settings and scripts
- Update train.pbs to default to smoke test for safety - Update .gitignore and ruff.toml - Sync uv.lock (removing python 3.11 remnants) - Refine smoke test config
This commit is contained in:
parent
92db8c2591
commit
92de38608f
13 changed files with 34 additions and 385 deletions
|
|
@ -11,8 +11,8 @@
|
|||
#PBS -l nodes=1:ppn=8:gpus=1
|
||||
#PBS -l walltime=24:00:00
|
||||
#PBS -l mem=32gb
|
||||
#PBS -o /dev/null
|
||||
#PBS -e /dev/null
|
||||
#PBS -o runs/brittlestar-ppo.o$PBS_JOBID
|
||||
#PBS -e runs/brittlestar-ppo.e$PBS_JOBID
|
||||
|
||||
set -euo pipefail
|
||||
|
||||
|
|
@ -27,9 +27,7 @@ export UV_CACHE_DIR="$VSC_SCRATCH/.cache/uv"
|
|||
RUN_ID="brittlestar_${PBS_JOBID}"
|
||||
SCRATCH_RUNDIR="$VSC_SCRATCH/runs/$RUN_ID"
|
||||
DATA_RUNDIR="$VSC_DATA/runs/$RUN_ID"
|
||||
mkdir -p "$PIP_CACHE_DIR" "$UV_CACHE_DIR" "$SCRATCH_RUNDIR" "$DATA_RUNDIR"
|
||||
|
||||
exec 1> "$DATA_RUNDIR/job.out" 2> "$DATA_RUNDIR/job.err"
|
||||
mkdir -p "$PIP_CACHE_DIR" "$UV_CACHE_DIR" "$SCRATCH_RUNDIR" "$DATA_RUNDIR" runs/
|
||||
|
||||
module load vsc-venv
|
||||
source vsc-venv --activate --modules env/hpc/modules.txt
|
||||
|
|
@ -38,7 +36,7 @@ export MUJOCO_GL=egl
|
|||
export WANDB_DIR="$SCRATCH_RUNDIR"
|
||||
|
||||
python src/train.py \
|
||||
--config configs/production_training.yaml \
|
||||
--run_dir "$SCRATCH_RUNDIR"
|
||||
--config configs/hpc/smoke_test.yaml
|
||||
# ^^^ Replace with your production config, e.g. configs/production_training.yaml
|
||||
|
||||
cp -r "$SCRATCH_RUNDIR/." "$DATA_RUNDIR/"
|
||||
|
|
|
|||
Reference in a new issue