Compare commits
2
Commits
a7bbc7b29f
...
0c2bc916f2
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
0c2bc916f2 | ||
|
|
4e70e827ff |
@@ -302,7 +302,7 @@ Sequence length & 2,048 tokens \\
|
||||
\centering
|
||||
\includegraphics[width=0.50\linewidth]{data/loss_compare.png}
|
||||
\caption{Training loss curves: GPT-2 residual scaling vs.~Kaiming
|
||||
initialization over $\sim$20B tokens.}
|
||||
initialization over $\sim$5B tokens.}
|
||||
\label{fig:loss}
|
||||
\end{figure}
|
||||
|
||||
@@ -547,17 +547,6 @@ spread.}
|
||||
\label{fig:ckpt_weight_density}
|
||||
\end{figure}
|
||||
|
||||
\begin{figure}[H]
|
||||
\centering
|
||||
\includegraphics[width=0.95\linewidth]{data/ckpt_weight_density_per_run.png}
|
||||
\caption{Per-checkpoint weight density breakdowns. The three checkpoints
|
||||
are \texttt{norm-15bt} (AdamW, Normal init, 15B tokens), \texttt{kami-15bt}
|
||||
(AdamW, GPT-2 residual scaling, 15B tokens), and \texttt{muon-25bt}
|
||||
(Muon, 25B tokens). Note: the iteration labels inside the figure reflect
|
||||
legacy script metadata and should be ignored in favour of the token
|
||||
budgets stated here.}
|
||||
\label{fig:ckpt_weight_density_per_run}
|
||||
\end{figure}
|
||||
|
||||
% ======================================================================
|
||||
\section{Conclusion}
|
||||
|
||||
Reference in New Issue
Block a user