HCAI-Lab/w2-consensus-deepdive-unlearning-artifacts / social-data-attribution-w2 /scripts /slurm /dedup /extract_ids.sbatch
| #SBATCH --job-name=extract_ids | |
| #SBATCH --array=0-497%15 | |
| #SBATCH --cpus-per-task=4 | |
| #SBATCH --mem=16G | |
| #SBATCH --time=04:00:00 | |
| #SBATCH -C localNVMe | |
| #SBATCH --output=logs/dedup/%x_%A_%a.out | |
| #SBATCH --error=logs/dedup/%x_%A_%a.err | |
| set -euo pipefail | |
| REPO_DIR="${SLURM_SUBMIT_DIR:-$(cd "$(dirname "$0")/../../.." && pwd)}" | |
| cd "$REPO_DIR" | |
| mkdir -p logs/dedup | |
| if [ -f .venv/bin/activate ]; then | |
| source .venv/bin/activate | |
| fi | |
| export PYTHONPATH="${REPO_DIR}/src${PYTHONPATH:+:$PYTHONPATH}" | |
| export HF_TOKEN="${HF_TOKEN:-$(cat ~/.hf_token 2>/dev/null || true)}" | |
| python3 scripts/slurm/dedup/extract_ids.py \ | |
| --dataset "${DATASET_ID:-allenai/dolma3_mix-6T-1025-7B}" \ | |
| --manifest "${SHARD_MANIFEST:-scripts/slurm/shard_manifest_6t.txt}" \ | |
| --output-dir "${IDS_OUT_DIR:-/storage/ice-shared/cs7634/staff/TDA/soc-90/ids}" \ | |
| --task-id "${SLURM_ARRAY_TASK_ID}" \ | |
| --task-count "${TASK_COUNT:-498}" \ | |
| --shards-per-task "${SHARDS_PER_TASK:-132}" \ | |
| --startup-delay "${STARTUP_DELAY:-120}" | |
Xet Storage Details
- Size:
- 1.02 kB
- Xet hash:
- 57a00488a576f60e47ed3cece4f8e646b4d38353626a048777b2cb4aa5ff68e7
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.