diff --git a/lab1/PT_Part2_Music_Generation.ipynb b/lab1/PT_Part2_Music_Generation.ipynb
index e4982c27..263e1d8e 100644
--- a/lab1/PT_Part2_Music_Generation.ipynb
+++ b/lab1/PT_Part2_Music_Generation.ipynb
@@ -451,7 +451,8 @@
         "        self.embedding = nn.Embedding(vocab_size, embedding_dim)\n",
         "\n",
         "        '''TODO: Layer 2: LSTM with hidden_size `hidden_size`. note: number of layers defaults to 1.\n",
-        "         Use the nn.LSTM() module from pytorch.'''\n",
+        "         Use the nn.LSTM() module from pytorch. Recall that get_batch returns\n",
+        "         tensors with shape (batch_size, sequence_length).'''\n",
         "        self.lstm = nn.LSTM('''TODO''') # TODO\n",
         "\n",
         "        '''TODO: Layer 3: Linear (fully-connected) layer that transforms the LSTM output\n",