diff options
Diffstat (limited to 'scripts/slurm_a14.sh')
| -rw-r--r-- | scripts/slurm_a14.sh | 22 |
1 files changed, 22 insertions, 0 deletions
diff --git a/scripts/slurm_a14.sh b/scripts/slurm_a14.sh new file mode 100644 index 0000000..a5daabe --- /dev/null +++ b/scripts/slurm_a14.sh @@ -0,0 +1,22 @@ +#!/bin/bash +#SBATCH --signal=SIGUSR1@120 +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 TOKENIZERS_PARALLELISM=false + +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/a14 + +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 A14: init_logit=1.0 ===" +python3 -u scripts/train.py --config configs/a14_init_logit_1.yaml |
