blob: 6b283ea5606af18f6e55810f196cd5b68897a42b (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
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
|
