blob: 49e56c7570c70d5da0597e91ee41754f75ab6e16 (
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
58
|
#!/bin/bash
#SBATCH --job-name=snn_wkext
#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_extreme.out
#SBATCH --error=runs/slurm_logs/%j_weak_extreme.err
# ============================================================
# Experiment: Weak Reg + Extreme Threshold
# ============================================================
# Combine both approaches:
# - Very weak regularization (lambda_reg=0.01)
# - Only penalize extreme chaos (lambda > 3.0)
#
# This should give the network maximum freedom to learn while
# providing a safety net against explosive dynamics.
# ============================================================
set -e
PROJECT_DIR="/projects/bfqt/users/yurenh2/ml-projects/snn-training"
cd "$PROJECT_DIR"
mkdir -p runs/slurm_logs data
echo "============================================================"
echo "WEAK REG + EXTREME Experiment"
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 extreme \
--lyap_threshold 3.0 \
--warmup_epochs 20 \
--data_dir ./data \
--out_dir runs/depth_scaling_weak_extreme \
--device cuda
echo "============================================================"
echo "Finished: $(date)"
echo "============================================================"
|
