From b329856d15b91a6f31fb75f010f0a550cddd0ee8 Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Wed, 22 Jul 2026 05:31:43 -0500 Subject: baselines: audit native author runs --- BASELINES.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'BASELINES.md') diff --git a/BASELINES.md b/BASELINES.md index 34e9f58..cfdb3f5 100644 --- a/BASELINES.md +++ b/BASELINES.md @@ -57,7 +57,10 @@ model.Q.mode=sym_Y The inherited configuration supplies three convolutional layers plus a 1500-unit fully connected layer, batch size 32, 400 epochs, label smoothing 0.05, SGD momentum 0.9, weight decay `1e-4`, two warmup epochs and cosine -decay. Y and Q use learning rate `0.001`. The paper reports +decay. The resolved author config uses softmax outputs with MSE loss; Y and Q +use learning rate `0.001`. The current author loop interprets `n_epochs=400` +as an epoch-0 evaluation followed by 399 optimization epochs, and the audit +records both counts rather than silently relabelling them. The paper reports `17.03 ± 0.21%` top-1 error (`82.97 ± 0.21%` accuracy) for symmetric-plastic BurstCCN. -- cgit v1.2.3