fixed typos

GoogleCloudPlatform · Sep 27, 2024 · df241a4 · df241a4
1 parent 421040e
commit df241a4
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 4 deletions.
diff --git a/notebooks/text_models/labs/rnn_encoder_decoder.ipynb b/notebooks/text_models/labs/rnn_encoder_decoder.ipynb
@@ -943,7 +943,7 @@
     "\n",
     "It still is imperfect, since it gives no credit to synonyms and so human evaluation is still best when feasible. However BLEU is commonly considered the best among bad options for an automated metric.\n",
     "\n",
-    "The Hugging Face evaluagte framework has an implementation that we will use.\n",
+    "The Hugging Face evaluate framework has an implementation that we will use.\n",
     "\n",
     "We can't run calculate BLEU during training, because at that time the correct decoder input is used. Instead we'll calculate it now.\n",
     "\n",
@@ -965,7 +965,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let's now average the `bleu_1` and `bleu_4` scores for all the sentence pairs in the eval set. The next cell takes around 1 minute (8 minutes for full dataset eval) to run, the bulk of which is decoding the sentences in the validation set. Please wait unitl completes."
+    "Let's now average the `bleu_1` and `bleu_4` scores for all the sentence pairs in the eval set. The next cell takes around 1 minute (8 minutes for full dataset eval) to run, the bulk of which is decoding the sentences in the validation set. Please wait until completes."
    ]
   },
   {

diff --git a/notebooks/text_models/solutions/rnn_encoder_decoder.ipynb b/notebooks/text_models/solutions/rnn_encoder_decoder.ipynb
@@ -951,7 +951,7 @@
     "\n",
     "It still is imperfect, since it gives no credit to synonyms and so human evaluation is still best when feasible. However BLEU is commonly considered the best among bad options for an automated metric.\n",
     "\n",
-    "The Hugging Face evaluagte framework has an implementation that we will use.\n",
+    "The Hugging Face evaluate framework has an implementation that we will use.\n",
     "\n",
     "We can't run calculate BLEU during training, because at that time the correct decoder input is used. Instead we'll calculate it now.\n",
     "\n",
@@ -975,7 +975,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Let's now average the `bleu_1` and `bleu_4` scores for all the sentence pairs in the eval set. The next cell takes around 1 minute (8 minutes for full dataset eval) to run, the bulk of which is decoding the sentences in the validation set. Please wait unitl completes."
+    "Let's now average the `bleu_1` and `bleu_4` scores for all the sentence pairs in the eval set. The next cell takes around 1 minute (8 minutes for full dataset eval) to run, the bulk of which is decoding the sentences in the validation set. Please wait until completes."
    ]
   },
   {