diff options
Diffstat (limited to 'scripts/slurm_train.sh')
| -rw-r--r-- | scripts/slurm_train.sh | 30 |
1 files changed, 30 insertions, 0 deletions
diff --git a/scripts/slurm_train.sh b/scripts/slurm_train.sh new file mode 100644 index 0000000..6b283ea --- /dev/null +++ b/scripts/slurm_train.sh @@ -0,0 +1,30 @@ +#!/bin/bash +#SBATCH --partition=gpuA40x4 +#SBATCH --account=bfqt-delta-gpu +#SBATCH --nodes=1 +#SBATCH --gpus-per-node=1 +#SBATCH --time=02:00:00 +#SBATCH --mem=64g +#SBATCH --job-name=dagformer-sanity +#SBATCH --output=logs/sanity_%j.out +#SBATCH --error=logs/sanity_%j.err + +export HF_HOME=/projects/bfqt/users/yurenh2/hf_cache +export TRANSFORMERS_CACHE=/projects/bfqt/users/yurenh2/hf_cache/transformers +export HF_HUB_CACHE=/projects/bfqt/users/yurenh2/hf_cache/hub +export HF_DATASETS_CACHE=/projects/bfqt/users/yurenh2/hf_cache/datasets + +export PYTHONPATH=/projects/bfqt/users/yurenh2/ml-projects/DAGFormer:$PYTHONPATH +export PATH=$HOME/.local/bin:$PATH + +cd /projects/bfqt/users/yurenh2/ml-projects/DAGFormer +mkdir -p logs checkpoints + +echo "=== Job Info ===" +echo "Job ID: $SLURM_JOB_ID" +echo "Node: $SLURM_NODELIST" +echo "GPU: $(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader)" +echo "" + +echo "=== Starting training ===" +python3 scripts/train.py --config configs/sanity_check.yaml |
