| # Grid 8 - does the parallelism curriculum hold ACROSS difficulties? | |
| # | |
| # The previous method was excellent at 8 digits (3/3 seeds ~100%) but unstable | |
| # at 10-12 (1/3 seeds) because it demanded a full carry chain in one pass from | |
| # random initialisation. `prog` anneals the number of parallel commits 16->1 and | |
| # ramps the one-pass term in, so each stage is a small increment. Capacity is | |
| # also raised, since 14-16 digits previously failed even at sequential decoding | |
| # and that is a learnability failure, not a parallelism one. | |
| #SBATCH -J g8 | |
| #SBATCH -p gpu-h100 | |
| #SBATCH --gpus=h100:1 | |
| #SBATCH -c 8 | |
| #SBATCH --mem=64g | |
| #SBATCH -t 10:00:00 | |
| #SBATCH -o logs/g8-%A_%a.out | |
| #SBATCH --array=0-29%12 | |
| source /etc/profile | |
| SCR=/scratch/zt1/project/msml612/user/$USER | |
| module load python/3.10.10 | |
| export PYTHONPATH= | |
| PY=$SCR/hf_env/bin/python | |
| cd $SCR/pcmd/src | |
| I=$SLURM_ARRAY_TASK_ID | |
| DIG=(8 10 12 14 16); MODES=(mdlm prog); SEEDS=(0 1 2) | |
| D=${DIG[$((I / 6))]} | |
| M=${MODES[$(((I % 6) / 3))]} | |
| S=${SEEDS[$((I % 3))]} | |
| SL=$(( 3 * D + 4 )) | |
| NAME="g8-d$D-$M-s$S" | |
| echo "=== $NAME ===" | |
| $PY train_add.py --mode $M --digits $D --seq_len $SL --seed $S \ | |
| --n_train 500000 --n_eval 400 --eval_bs 100 \ | |
| --d 512 --layers 10 --heads 8 --bs 128 --steps 60000 --lr 3e-4 \ | |
| --K_max 16 --lam 1.0 --out $SCR/pcmd/runs/$NAME | |