gaojie
c66855adfc
Sync to site1 / sync (push) Has been cancelled
- 移除 JEPA/lejepa-identifiability 子模块 gitlink - 移除 research/multiply/MultiPLY 子模块 gitlink - 删除 .gitmodules（不再有外部 URL 依赖） - 两个目录内容作为普通文件纳入主仓库追踪 - 删除各自内部 .git 目录，消除嵌套 git 仓库
36 lines
846 B
YAML
36 lines
846 B
YAML
# 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 |