| # Properly specified baselines, replacing two broken ones. | |
| # | |
| # 0 DIRECT + all-cell supervision: the published recurrent classifier trains | |
| # on all 81 cells, not just the blanks. Our blanks-only version plateaued at | |
| # loss 0.34 against diffusion's 0.15, which is the likeliest cause. | |
| # 1 same, second seed - the first attempt had huge seed variance (40.9 / 6.6) | |
| # 2 AR PREFIX-LM: [puzzle][solution], causal, loss on the solution half. The | |
| # earlier in-place causal version was mis-specified: Sudoku clues are | |
| # scattered, so a causal model could not attend to clues on its right. | |
| #SBATCH -J fix | |
| #SBATCH -p gpu-h100 | |
| #SBATCH --gpus=h100:1 | |
| #SBATCH -c 8 | |
| #SBATCH --mem=48g | |
| #SBATCH -t 2:00:00 | |
| #SBATCH -o logs/fix-%A_%a.out | |
| #SBATCH --array=0-2%3 | |
| 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 | |
| COMMON="--pe ape --hard $SCR/pcmd/data/sudoku_hard --augment --heads 4 --bs 256 \ | |
| --steps 110000 --lr 3e-4 --warmup 3000 --eval_bs 250 --ckpt_every 10000" | |
| case $I in | |
| 0) NAME="fix-directall-s0"; ARGS="--objective direct --all_cells --recurrent --R 32 --R_infer 64 --d 128 --layers 1 --seed 0" ;; | |
| 1) NAME="fix-directall-s1"; ARGS="--objective direct --all_cells --recurrent --R 32 --R_infer 64 --d 128 --layers 1 --seed 1" ;; | |
| 2) NAME="fix-arprefix-s0"; ARGS="--objective ar --d 128 --layers 12 --seed 0" ;; | |
| esac | |
| echo "=== $NAME ===" | |
| $SCR/hf_env/bin/python -u train_sudoku.py $ARGS $COMMON --out $SCR/pcmd/runs/$NAME | |