From 73cb02f0aac517fa462fbd39e3c7491e388d9e25 Mon Sep 17 00:00:00 2001
From: ViperEkura <3081035982@qq.com>
Date: Sun, 28 Jun 2026 16:57:30 +0800
Subject: [PATCH] fix training hyperparams to match pretraining script: lr
 1.5e-4, wd 0.1, warmup 0.02

---
 main.tex | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/main.tex b/main.tex
index 69c1d3d..0e10a82 100644
--- a/main.tex
+++ b/main.tex
@@ -195,10 +195,10 @@ Table~\ref{tab:train_params} lists the key hyperparameters.
 \textbf{Hyperparameter} & \textbf{Value} \\
 \midrule
 Precision & BF16 (weights + AdamW states) \\
-Optimizer & AdamW, $\eta=7.5\times10^{-6}$ \\
-Betas & $(0.9, 0.95)$, weight decay $0.01$ \\
+Optimizer & AdamW, $\eta=1.5\times10^{-4}$ \\
+Betas & $(0.9, 0.95)$, weight decay $0.1$ \\
 Gradient clip & Global L2, max norm $1.0$ \\
-Scheduler & Cosine, warmup ratio $0.05$ \\
+Scheduler & Cosine, warmup ratio $0.02$ \\
 Batch size & 4 per device $\times$ 4 GPUs $\times$ 32 accumulation \\
 Sequence length & 2,048 tokens \\
 Total steps & 950,000 \\