| # LEARNABILITY GATE for SIGMORPHON, before any parallel-decoding claim. | |
| # Published transformer baselines reach roughly 90%+ exact match on medium data | |
| # for these languages. If our harness cannot get near that with sequential | |
| # decoding, nothing measured at one pass would mean anything. | |
| #SBATCH -J siggate | |
| #SBATCH -p gpu-h100 | |
| #SBATCH --gpus=h100:1 | |
| #SBATCH -c 8 | |
| #SBATCH --mem=32g | |
| #SBATCH -t 02:00:00 | |
| #SBATCH -o logs/siggate-%j.out | |
| source /etc/profile | |
| SCR=/scratch/zt1/project/msml612/user/$USER | |
| module load python/3.10.10 | |
| export PYTHONPATH= | |
| cd $SCR/pcmd/src | |
| for L in english german turkish; do | |
| echo "--- $L (mdlm baseline) ---" | |
| $SCR/hf_env/bin/python train_sig.py --lang $L --mode mdlm --size medium \ | |
| --steps 12000 --d 256 --layers 6 --lr 1e-4 --warmup 1000 \ | |
| --data_root $SCR/pcmd/data/sig --out $SCR/pcmd/runs/gate-$L 2>&1 | tail -2 | |
| done | |