| # The baselines that can overturn the paper's framing. | |
| # | |
| # 0,1 DIRECT + RECURRENT: predict every blank from the puzzle, no masking | |
| # schedule, recurrent with deep supervision. This is the Recurrent | |
| # Transformer setup reimplemented in our codebase - the control that asks | |
| # whether the DIFFUSION framing earns its place at all. If it matches | |
| # 99.70%, diffusion contributes nothing and the paper's framing collapses. | |
| # 2,3 DIRECT + FEED-FORWARD: same, without recurrence. Isolates recurrence | |
| # from the objective. | |
| # 4,5 AUTOREGRESSIVE: left-to-right cell filling at matched size. Asks whether | |
| # any iterative model would do, making the generative framing irrelevant. | |
| #SBATCH -J base | |
| #SBATCH -p gpu-h100 | |
| #SBATCH --gpus=h100:1 | |
| #SBATCH -c 8 | |
| #SBATCH --mem=48g | |
| #SBATCH -t 5:00:00 | |
| #SBATCH -o logs/base-%A_%a.out | |
| #SBATCH --array=0-5%6 | |
| source /etc/profile | |
| SCR=/scratch/zt1/project/msml612/user/$USER | |
| module load python/3.10.10 | |
| export PYTHONPATH= | |
| cd $SCR/pcmd/src | |
| I=$SLURM_ARRAY_TASK_ID | |
| S=$((I % 2)) | |
| COMMON="--seed $S --pe ape --hard $SCR/pcmd/data/sudoku_hard --augment \ | |
| --heads 4 --bs 256 --steps 120000 --lr 3e-4 --warmup 3000 \ | |
| --eval_bs 250 --ckpt_every 10000" | |
| case $((I / 2)) in | |
| 0) NAME="base-directrec-s$S" | |
| ARGS="--objective direct --recurrent --R 32 --R_infer 64 --d 128 --layers 1" ;; | |
| 1) NAME="base-directff-s$S" | |
| ARGS="--objective direct --d 128 --layers 12" ;; | |
| 2) NAME="base-ar-s$S" | |
| ARGS="--objective ar --d 128 --layers 12" ;; | |
| esac | |
| echo "=== $NAME ===" | |
| $SCR/hf_env/bin/python -u train_sudoku.py $ARGS $COMMON --out $SCR/pcmd/runs/$NAME | |