Merge pull request #2218 from Sarvesh-Kesharwani:patch-1

copybara-github · copybara-github · commit 043c45aeab1f · 2023-05-22T17:25:45.000-07:00
PiperOrigin-RevId: 534235147
diff --git a/site/en/guide/basics.ipynb b/site/en/guide/basics.ipynb
@@ -784,7 +784,7 @@
         "id": "7EWyDu3zot2w"
       },
       "source": [
-        "Write a basic training loop for the model. The loop will make use of the MSE loss function and its gradients with respect to the input in order to iteratively update the model's parameters. Using mini-batches for training provides both memory efficienciy and faster convergence. The `tf.data.Dataset` API has useful functions for batching and shuffling."
+        "Write a basic training loop for the model. The loop will make use of the MSE loss function and its gradients with respect to the input in order to iteratively update the model's parameters. Using mini-batches for training provides both memory efficiency and faster convergence. The `tf.data.Dataset` API has useful functions for batching and shuffling."
       ]
     },
     {

Original file line number	Diff line number	Diff line change
`@@ -784,7 +784,7 @@`
`784`	`784`	`"id": "7EWyDu3zot2w"`
`785`	`785`	`},`
`786`	`786`	`"source": [`
`787`		- "Write a basic training loop for the model. The loop will make use of the MSE loss function and its gradients with respect to the input in order to iteratively update the model's parameters. Using mini-batches for training provides both memory efficienciy and faster convergence. The `tf.data.Dataset` API has useful functions for batching and shuffling."
	`787`	+ "Write a basic training loop for the model. The loop will make use of the MSE loss function and its gradients with respect to the input in order to iteratively update the model's parameters. Using mini-batches for training provides both memory efficiency and faster convergence. The `tf.data.Dataset` API has useful functions for batching and shuffling."
`788`	`788`	`]`
`789`	`789`	`},`
`790`	`790`	`{`