blob: eff5342cc929cf64ce93b5ce93c578bd8bea1f6e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
|
#!/bin/bash
#SBATCH --job-name=scaled_d12
#SBATCH --account=bfqt-delta-gpu
#SBATCH --partition=gpuA40x4
#SBATCH --nodes=1
#SBATCH --ntasks=1
#SBATCH --cpus-per-task=8
#SBATCH --gpus-per-node=1
#SBATCH --mem=64G
#SBATCH --time=44:00:00
#SBATCH --output=runs/slurm_logs/%j_scaled_grid_d12.out
#SBATCH --error=runs/slurm_logs/%j_scaled_grid_d12.err
set -e
PROJECT_DIR="/projects/bfqt/users/yurenh2/ml-projects/snn-training"
cd "$PROJECT_DIR"
mkdir -p runs/slurm_logs runs/scaled_grid data
echo "============================================================"
echo "SCALED REGULARIZATION GRID SEARCH - DEPTH 12"
echo "Job ID: $SLURM_JOB_ID | Node: $SLURM_NODELIST"
echo "Start: $(date)"
echo "============================================================"
echo "Grid: λ_reg=[0.0005, 0.001, 0.002, 0.005] × reg_type=[mult_linear, mult_log]"
echo "Total: 8 experiments"
echo "============================================================"
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader
echo "============================================================"
python files/experiments/scaled_reg_grid_search.py \
--depth 12 \
--epochs 100 \
--batch_size 128 \
--lr 0.001 \
--data_dir ./data \
--out_dir ./runs/scaled_grid
echo "============================================================"
echo "Finished: $(date)"
echo "============================================================"
|
