MDSection 36 of 38 · 10 subtopics
Evaluation
Measuring LLM quality. Perplexity, benchmarks, human eval, hallucination detection.
Learning path
Work through each subtopic in order. Click any file below to open its lesson. Track your progress with the checkbox at the bottom.
Subtopics
Each subtopic includes a concise explanation, code examples, and references.
01
Model Evaluation
Evaluation dashboard.
model-evaluation
02
Training Loss
Live loss curve.
training-loss
03
Validation Loss
Train vs validation graph.
validation-loss
04
Perplexity
Token prediction confidence visualization.
perplexity
05
Accuracy
Correct/incorrect result grid.
accuracy
06
Benchmarking
Model comparison table/chart.
benchmarking
07
Human Evaluation
Pairwise comparison UI.
human-evaluation
08
Hallucination Evaluation
Claim verification interface.
hallucination-evaluation
09
Latency Evaluation
Request latency distribution.
latency-evaluation
10
Throughput Evaluation
Tokens-per-second dashboard.
throughput-evaluation