| #SBATCH --job-name=run_edu_bert | |
| #SBATCH --partition hopper-prod | |
| #SBATCH --qos=normal | |
| #SBATCH --requeue | |
| #SBATCH --nodes=1 | |
| #SBATCH --ntasks-per-node=1 | |
| #SBATCH --cpus-per-task=12 | |
| #SBATCH --mem-per-cpu=20G | |
| #SBATCH --gpus=1 | |
| #SBATCH -o %x_%j.out | |
| #SBATCH -e %x_%j.err | |
| #SBATCH --time=7-00:00:00 | |
| #SBATCH --array=0,1,2,3,4,6,7,8,26,29,31%32 | |
| set -x -e | |
| source ~/.bashrc | |
| source "/admin/home/anton/miniforge3/etc/profile.d/conda.sh" | |
| source activate lighteval | |
| python run_edu_bert.py \ | |
| --model_name="HuggingFaceFW/fineweb-edu-classifier" \ | |
| --dataset_name="HuggingFaceFW/fineweb" \ | |
| --dataset_config="CC-MAIN-2019-04" \ | |
| --output_dataset_name="HuggingFaceFW/fineweb-edu-annotations" \ | |
| --output_dataset_config="CC-MAIN-2019-04" \ | |
| --text_column="text" \ | |
| --shard ${SLURM_ARRAY_TASK_ID} \ | |
| --num_shards 32 |