📄 T5 Nli Mixture¶

metrics.perplexity_nli.t5_nli_mixture

Perplexity(
    model_name="google/t5_xxl_true_nli_mixture",
    source_template="premise: {reference} hypothesis: {prediction}",
    target_template="1",
    single_token_mode=True,
)
[source]

Explanation about Perplexity¶

Computes perplexity of generating target text given source context.

Range: [1, ∞) (lower is better) Measures how well a language model predicts the target sequence.

Reference: https://en.wikipedia.org/wiki/Perplexity