Differences

This shows you the differences between two versions of the page.

--- nlp:perplexity [2023/02/01 19:00] – [Conversion from log Probability to Perplexity] jmflanig
+++ nlp:perplexity [2023/06/15 07:36] (current) – external edit 127.0.0.1
@@ Line 3: / Line 3: @@
 ===== Conversion from log Probability to Perplexity =====
-To convert from loss (-log probability, aka cross entropy) to perplexity exponentiate the negative loss (perplexity = exp(loss)), and vice-versa (loss = ln(perplexity)).  When the loss is very low (< .1) then the perplexity is roughly 1 + loss.
+To convert from loss (-log probability, aka cross entropy) to perplexity exponentiate the loss (perplexity = exp(loss)), and vice-versa (loss = ln(perplexity)).  When the loss is very low (< .1) then the perplexity is roughly 1 + loss.
 ^ Loss (-log(prob)) ^ Perplexity ^