From bce3a708f9a714f74ec7bfb3bb2ce3a280d58bea Mon Sep 17 00:00:00 2001 From: TITC <35098797+TITC@users.noreply.github.com> Date: Tue, 23 Jul 2024 10:24:57 +0800 Subject: [PATCH] 47,678-->48,725 (#281) --- ch05/01_main-chapter-code/ch05.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ch05/01_main-chapter-code/ch05.ipynb b/ch05/01_main-chapter-code/ch05.ipynb index 4cfb388..4b470f6 100644 --- a/ch05/01_main-chapter-code/ch05.ipynb +++ b/ch05/01_main-chapter-code/ch05.ipynb @@ -743,7 +743,7 @@ "id": "71ae26dd-d77e-41fd-b924-6bd103dd4ee7", "metadata": {}, "source": [ - "- The perplexity is often considered more interpretable because it can be understood as the effective vocabulary size that the model is uncertain about at each step (in the example above, that'd be 47,678 words or tokens)\n", + "- The perplexity is often considered more interpretable because it can be understood as the effective vocabulary size that the model is uncertain about at each step (in the example above, that'd be 48,725 words or tokens)\n", "- In other words, perplexity provides a measure of how well the probability distribution predicted by the model matches the actual distribution of the words in the dataset\n", "- Similar to the loss, a lower perplexity indicates that the model predictions are closer to the actual distribution" ]