add eval

eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"test": {"QAAlignedF1Score (BERTScore)": 0.39689511725937515, "QAAlignedRecall (BERTScore)": 0.40032059062971453, "QAAlignedPrecision (BERTScore)": 0.39392174968140004, "QAAlignedF1Score (MoverScore)": 0.28887069114579245, "QAAlignedRecall (MoverScore)": 0.2901522643547535, "QAAlignedPrecision (MoverScore)": 0.287731094203997, "Bleu_1": 0.0025142038901180483, "Bleu_2": 7.50646036102876e-11, "Bleu_3": 2.3652041518774833e-13, "Bleu_4": 1.3409558416229979e-14, "METEOR": 0.10219515012393596, "ROUGE_L": 0.004617144531352161, "BERTScore": 0.3813734051613819, "MoverScore": 0.4792367382148584}, "validation": {"QAAlignedF1Score (BERTScore)": 0.4015211389991531, "QAAlignedRecall (BERTScore)": 0.39462290260389654, "QAAlignedPrecision (BERTScore)": 0.40935757347664736, "QAAlignedF1Score (MoverScore)": 0.29093749935852864, "QAAlignedRecall (MoverScore)": 0.28679876262363635, "QAAlignedPrecision (MoverScore)": 0.2954464423317324, "Bleu_1": 0.00745995994726418, "Bleu_2": 1.936113694858309e-10, "Bleu_3": 5.85879987122475e-13, "Bleu_4": 3.254001509925382e-14, "METEOR": 0.08855310757732072, "ROUGE_L": 0.011601127197842134, "BERTScore": 0.4000005471585977, "MoverScore": 0.47951064925800624}}

eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.9008794279608408, "Bleu_2": 0.8647027801857005, "Bleu_3": 0.8278918087516826, "Bleu_4": 0.7898122703010375, "METEOR": 0.6871054010501029, "ROUGE_L": 0.9414870823539028, "BERTScore": 0.9943921057423265, "MoverScore": 0.9777746318376621, "AnswerF1Score": 92.42067346608387, "AnswerExactMatch": 92.28994657600776}, "test": {"Bleu_1": 0.9212497325058454, "Bleu_2": 0.8895966484986538, "Bleu_3": 0.855682203106959, "Bleu_4": 0.8188349716403879, "METEOR": 0.7011500125797243, "ROUGE_L": 0.9526105070314671, "BERTScore": 0.9969201868435259, "MoverScore": 0.985024005271073, "AnswerF1Score": 94.22798283956614, "AnswerExactMatch": 94.13550267119962}}

eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_zhquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.34798489529693993, "Bleu_2": 0.2295511654606397, "Bleu_3": 0.16198317310426968, "Bleu_4": 0.11852449473138982, "METEOR": 0.22158216715913157, "ROUGE_L": 0.31437135391891685, "BERTScore": 0.7505470828969577, "MoverScore": 0.5623151088866599}, "test": {"Bleu_1": 0.3673742208373842, "Bleu_2": 0.2556515029936398, "Bleu_3": 0.18942175858726334, "Bleu_4": 0.14454369838151945, "METEOR": 0.2358352959896461, "ROUGE_L": 0.3391721152080222, "BERTScore": 0.7677152428262078, "MoverScore": 0.5719503341512616}}