Perplexity
Evaluation & MetricsChapter 10: Report Card for BitTerm 176 of 253
How 'surprised' a language model is by text; lower = better prediction.
At Sunrise School
Gopal asksHow surprised is the model by school text?
Bit answersPerplexity: lower means the model predicts school language well. After adapting, it fell from 18 to 7.
In the real worldLow perplexity = fluent model.
Watch the short
Short coming soonSeason 5 · Day 35Follow @haigopala
Short coming soonSeason 5 · Day 35Follow @haigopala.telugu
Short coming soonSeason 5 · Day 35Follow @haigopala.hindi
Taught together with
Practise it
Try this term and all 253 others in the free Model Training Arena.
Open the Arena →Follow Bit daily: YouTube English · తెలుగు · हिंदी | Instagram English · తెలుగు · हिंदी