diff --git a/main.tex b/main.tex
index 8488662..dc1be88 100644
--- a/main.tex
+++ b/main.tex
@@ -364,7 +364,7 @@ We use $\beta=0.1$, a batch of 64 preference pairs per step, and the
 same hybrid Muon/AdamW optimizer.  Unlike the pretraining and SFT
 phases, which both employ WSD (warmup--stable--decay) scheduling to
 maintain a long high-learning-rate plateau, DPO alignment uses a
-cosine schedule with short linear warmup.  The shorter ~1{,}500-step
+cosine schedule with short linear warmup.  The shorter ~3{,}000-step
 alignment run does not benefit from an extended stable phase; instead,
 cosine decay lowers the learning rate steadily, which discourages
 over-optimisation away from the reference distribution and matches the
@@ -373,7 +373,7 @@ observed convergence pattern in Figure~\ref{fig:dpo_metrics}.
 \begin{figure}[H]
 \centering
 \includegraphics[width=0.95\linewidth]{data/dpo_metrics.png}
-\caption{DPO training metrics over $\sim$1{,}500 alignment steps:
+\caption{DPO training metrics over $\sim$3{,}000 alignment steps:
 preference loss (raw and 100-step moving average), learning rate
 schedule, and gradient norm.}
 \label{fig:dpo_metrics}