| # Ablations that test the mechanism rather than decorate the result. | |
| # | |
| # 0,1 recurrent WITHOUT deep supervision -> is per-step supervision the | |
| # ingredient, or is recurrence alone enough? | |
| # 2,3 32 DISTINCT layers, d=128, no weight sharing -> is it the depth, or the | |
| # weight sharing? Same depth, ~32x the parameters. | |
| # 4,5 R=8 instead of 32 -> how much recurrence does the task actually need? | |
| # | |
| # All use the schedule-matched objective, which is the arm that reached 99.70%. | |
| #SBATCH -J abl | |
| #SBATCH -p gpu-h100 | |
| #SBATCH --gpus=h100:1 | |
| #SBATCH -c 8 | |
| #SBATCH --mem=48g | |
| #SBATCH -t 5:00:00 | |
| #SBATCH -o logs/abl-%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="--mode full --seed $S --pe ape --hard $SCR/pcmd/data/sudoku_hard --augment \ | |
| --heads 4 --bs 256 --steps 120000 --lr 3e-4 --warmup 3000 --K 8 --lam 1.0 \ | |
| --eval_bs 250 --ckpt_every 10000" | |
| case $((I / 2)) in | |
| 0) NAME="abl-nodeepsup-s$S" | |
| ARGS="--recurrent --R 32 --R_infer 64 --no_deep_sup --d 128 --layers 1" ;; | |
| 1) NAME="abl-deep32L-s$S" | |
| ARGS="--d 128 --layers 32" ;; | |
| 2) NAME="abl-R8-s$S" | |
| ARGS="--recurrent --R 8 --R_infer 16 --d 128 --layers 1" ;; | |
| esac | |
| echo "=== $NAME ===" | |
| $SCR/hf_env/bin/python -u train_sudoku.py $ARGS $COMMON --out $SCR/pcmd/runs/$NAME | |