blob: 2444d809139aad2db423ce79b718adccf94dce38 (
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
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
|
#!/bin/bash
#SBATCH --job-name=snn_weak_reg
#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=48:00:00
#SBATCH --output=runs/slurm_logs/%j_weak_reg.out
#SBATCH --error=runs/slurm_logs/%j_weak_reg.err
# ============================================================
# Experiment 1: Weaker Regularization (lambda_reg=0.01)
# ============================================================
# Hypothesis: The current lambda_reg=0.3 is too strong, causing
# the Lyapunov penalty to dominate the CE loss and prevent learning.
#
# With lambda_reg=0.01:
# - Penalty contribution: 0.01 * 4 = 0.04 (vs CE ~4.6)
# - Network can still learn while gently being regularized
# ============================================================
set -e
PROJECT_DIR="/projects/bfqt/users/yurenh2/ml-projects/snn-training"
cd "$PROJECT_DIR"
mkdir -p runs/slurm_logs data
echo "============================================================"
echo "WEAK REGULARIZATION Experiment (lambda_reg=0.01)"
echo "Job ID: $SLURM_JOB_ID | Node: $SLURM_NODELIST"
echo "Start: $(date)"
echo "============================================================"
nvidia-smi --query-gpu=name,memory.total --format=csv,noheader
echo "============================================================"
python files/experiments/depth_scaling_benchmark.py \
--dataset cifar100 \
--depths 4 8 12 16 \
--T 4 \
--epochs 150 \
--batch_size 128 \
--lr 0.001 \
--lambda_reg 0.01 \
--lambda_target -0.1 \
--reg_type squared \
--warmup_epochs 20 \
--data_dir ./data \
--out_dir runs/depth_scaling_weak_reg \
--device cuda
echo "============================================================"
echo "Finished: $(date)"
echo "============================================================"
|
