From 01cb137bfd134307c19c093a40fc157999846050 Mon Sep 17 00:00:00 2001
From: Sebastian Raschka <mail@sebastianraschka.com>
Date: Mon, 19 Aug 2024 20:58:45 -0500
Subject: [PATCH] Note about MPS devices (#329)

---
 .../01_main-chapter-code/appendix-D.ipynb     | 27 ++++++++++++++++++-
 .../01_main-chapter-code/appendix-E.ipynb     | 15 +++++++++++
 ch05/01_main-chapter-code/ch05.ipynb          |  2 ++
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/appendix-D/01_main-chapter-code/appendix-D.ipynb b/appendix-D/01_main-chapter-code/appendix-D.ipynb
index 6b21133..a157b71 100644
--- a/appendix-D/01_main-chapter-code/appendix-D.ipynb
+++ b/appendix-D/01_main-chapter-code/appendix-D.ipynb
@@ -81,6 +81,20 @@
     "\n",
     "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
     "\n",
+    "# Note:\n",
+    "# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,\n",
+    "# which is approximately 2x faster than on an Apple CPU (as measured on an M3 MacBook Air).\n",
+    "# However, the resulting loss values may be slightly different.\n",
+    "\n",
+    "#if torch.cuda.is_available():\n",
+    "#    device = torch.device(\"cuda\")\n",
+    "#elif torch.backends.mps.is_available():\n",
+    "#    device = torch.device(\"mps\")\n",
+    "#else:\n",
+    "#    device = torch.device(\"cpu\")\n",
+    "#\n",
+    "# print(f\"Using {device} device.\")\n",
+    "\n",
     "torch.manual_seed(123)\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
     "model.eval();  # Disable dropout during inference"
@@ -660,6 +674,11 @@
    "source": [
     "import tiktoken\n",
     "\n",
+    "# Note:\n",
+    "# Uncomment the following code to calculate the execution time\n",
+    "# import time\n",
+    "# start_time = time.time()\n",
+    "\n",
     "torch.manual_seed(123)\n",
     "model = GPTModel(GPT_CONFIG_124M)\n",
     "model.to(device)\n",
@@ -674,7 +693,13 @@
     "    eval_freq=5, eval_iter=1, start_context=\"Every effort moves you\",\n",
     "    tokenizer=tokenizer, warmup_steps=warmup_steps, \n",
     "    initial_lr=1e-5, min_lr=1e-5\n",
-    ")"
+    ")\n",
+    "\n",
+    "# Note:\n",
+    "# Uncomment the following code to show the execution time\n",
+    "# end_time = time.time()\n",
+    "# execution_time_minutes = (end_time - start_time) / 60\n",
+    "# print(f\"Training completed in {execution_time_minutes:.2f} minutes.\")"
    ]
   },
   {
diff --git a/appendix-E/01_main-chapter-code/appendix-E.ipynb b/appendix-E/01_main-chapter-code/appendix-E.ipynb
index c73052c..c0ab95f 100644
--- a/appendix-E/01_main-chapter-code/appendix-E.ipynb
+++ b/appendix-E/01_main-chapter-code/appendix-E.ipynb
@@ -511,6 +511,21 @@
    "outputs": [],
    "source": [
     "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "\n",
+    "# Note:\n",
+    "# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,\n",
+    "# which is approximately 1.2x faster than on an Apple CPU (as measured on an M3 MacBook Air).\n",
+    "# However, the resulting loss values may be slightly different.\n",
+    "\n",
+    "#if torch.cuda.is_available():\n",
+    "#    device = torch.device(\"cuda\")\n",
+    "#elif torch.backends.mps.is_available():\n",
+    "#    device = torch.device(\"mps\")\n",
+    "#else:\n",
+    "#    device = torch.device(\"cpu\")\n",
+    "#\n",
+    "# print(f\"Using {device} device.\")\n",
+    "\n",
     "model.to(device);  # no assignment model = model.to(device) necessary for nn.Module classes"
    ]
   },
diff --git a/ch05/01_main-chapter-code/ch05.ipynb b/ch05/01_main-chapter-code/ch05.ipynb
index 5cec9eb..bb624e6 100644
--- a/ch05/01_main-chapter-code/ch05.ipynb
+++ b/ch05/01_main-chapter-code/ch05.ipynb
@@ -1154,6 +1154,8 @@
     "#    device = torch.device(\"mps\")\n",
     "#else:\n",
     "#    device = torch.device(\"cpu\")\n",
+    "#\n",
+    "# print(f\"Using {device} device.\")\n",
     "\n",
     "\n",
     "model.to(device) # no assignment model = model.to(device) necessary for nn.Module classes\n",