📁 Metrics¶
- 📁 Bert_score
- 📁 Perplexity
- 📁 Perplexity_a
- 📁 Perplexity_chat
- 📁 Perplexity_nli
- 📁 Perplexity_q
- 📁 Rag
- 📁 Reward
- 📁 Robustness
- 📁 Sentence_bert
- 📄 accuracy
- 📄 accuracy_binary
- 📄 bleu
- 📄 char_edit_dist_accuracy
- 📄 char_edit_distance
- 📄 f1_binary
- 📄 f1_macro
- 📄 f1_macro_multi_label
- 📄 f1_micro
- 📄 f1_micro_multi_label
- 📄 f1_weighted
- 📄 kendalltau_b
- 📄 kpa
- 📄 map
- 📄 matthews_correlation
- 📄 max_accuracy_binary
- 📄 max_f1_binary
- 📄 mrr
- 📄 ndcg
- 📄 ner
- 📄 normalized_sacrebleu
- 📄 precision_binary
- 📄 precision_macro_multi_label
- 📄 precision_micro_multi_label
- 📄 recall_binary
- 📄 recall_macro_multi_label
- 📄 recall_micro_multi_label
- 📄 regard
- 📄 rerank_recall
- 📄 retrieval_at_k
- 📄 roc_auc
- 📄 rouge
- 📄 rouge_with_confidence_intervals
- 📄 sacrebleu
- 📄 safety
- 📄 spearman
- 📄 squad
- 📄 string_containment
- 📄 token_overlap
- 📄 token_overlap_with_context
- 📄 unsorted_list_exact_match
- 📄 wer
Read more about catalog usage here.