From 82a5280f8fdf4350a7d40111b4987f1e7137a862 Mon Sep 17 00:00:00 2001
From: Daniel Zuegner <dzuegner@microsoft.com>
Date: Wed, 22 Jan 2025 10:55:25 +0000
Subject: [PATCH] readme

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index aaec835..eaeb162 100644
--- a/README.md
+++ b/README.md
@@ -176,6 +176,8 @@ You can train the MatterGen base model on `mp_20` using the following command.
 ```bash
 python scripts/run.py data_module=mp_20 ~trainer.logger
 ```
+> [!NOTE]
+> For Apple Silicon training, add `~trainer.strategy trainer.accelerator=mps` to the above command.
 
 The validation loss (`loss_val`) should reach 0.4 after 360 epochs (about 80k steps). The output checkpoints can be found at `outputs/singlerun/${now:%Y-%m-%d}/${now:%H-%M-%S}`. We call this folder `$MODEL_PATH` for future reference. 
 > [!NOTE]