flan-t5-small-squad-qag
/
eval
/metric.first.answer.paragraph.questions_answers.lmqg_qag_squad.default.json
{"validation": {"Bleu_1": 0.20405607221787056, "Bleu_2": 0.11651923206781724, "Bleu_3": 0.0674889034467983, "Bleu_4": 0.0442579024927662, "METEOR": 0.25221814883009747, "ROUGE_L": 0.24423036742390483, "BERTScore": 0.8666516939510628, "MoverScore": 0.5828986309013283, "QAAlignedF1Score (BERTScore)": 0.91873763482451, "QAAlignedRecall (BERTScore)": 0.9116887006516031, "QAAlignedPrecision (BERTScore)": 0.9261561570760444, "QAAlignedF1Score (MoverScore)": 0.6360174426233278, "QAAlignedRecall (MoverScore)": 0.6176346680055701, "QAAlignedPrecision (MoverScore)": 0.657378256046374}, "test": {"Bleu_1": 0.18825629891213996, "Bleu_2": 0.10563153189008037, "Bleu_3": 0.059361680910644955, "Bleu_4": 0.03795863394065141, "METEOR": 0.2443435239912263, "ROUGE_L": 0.22462210246221723, "BERTScore": 0.866851497550421, "MoverScore": 0.5813492651878985, "QAAlignedF1Score (BERTScore)": 0.9229931992254793, "QAAlignedRecall (BERTScore)": 0.9171223903676029, "QAAlignedPrecision (BERTScore)": 0.9291854900131855, "QAAlignedF1Score (MoverScore)": 0.6373537849135575, "QAAlignedRecall (MoverScore)": 0.6220281269909166, "QAAlignedPrecision (MoverScore)": 0.6549956214714001}} |