# Scaling experiment (paper figure)
# python run.py --config configs/scaling.yaml --N 16 --seed 0
# python run.py --config configs/scaling.yaml --N 16 --seed 0 --mode infonce
# python run.py --config configs/scaling.yaml --N 16 --seed 0 --mode whiten

experiment: scaling
out: results/scaling

# Data
source_dist: gaussian
num_eval: 10000

# Training (shared)
steps: 20000
lr: 3.0e-3
batch_size: 256
rho: 0.95
log_every: 500

# Encoder
encoder: matched
n_layers: 4
mode: lejepa     # default; override with --mode

# Mode-specific defaults (used based on --mode)
lamb: 1.0e-6     # for lejepa
lamb_whiten: 0.5  # used when mode=whiten
sigma: 1.0       # for infonce

# Mixing
mixing: coupling

# Sweep dimensions
dims: [2, 4, 8, 16, 32, 64, 128, 256, 512, 1024]
seeds: [0, 1, 2, 3, 4]
K: 3  # parallel encoder runs per (N, seed); pick lowest loss