add eval

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

@@ -0,0 +1 @@
+{"test": {"QAAlignedF1Score (BERTScore)": 0.8198366957498289, "QAAlignedRecall (BERTScore)": 0.8279058868254175, "QAAlignedPrecision (BERTScore)": 0.812428795704317, "QAAlignedF1Score (MoverScore)": 0.5636859717470377, "QAAlignedRecall (MoverScore)": 0.5675283274772175, "QAAlignedPrecision (MoverScore)": 0.5603653214977933, "Bleu_1": 0.23748793678767158, "Bleu_2": 0.1339444281195638, "Bleu_3": 0.06799155224098423, "Bleu_4": 0.03805345645538938, "METEOR": 0.2483492070438188, "ROUGE_L": 0.23486542602726787, "BERTScore": 0.7720076568589603, "MoverScore": 0.5482563498243764}, "validation": {"QAAlignedF1Score (BERTScore)": 0.8080408871561128, "QAAlignedRecall (BERTScore)": 0.8356645296436523, "QAAlignedPrecision (BERTScore)": 0.7829272132510307, "QAAlignedF1Score (MoverScore)": 0.5543721369292491, "QAAlignedRecall (MoverScore)": 0.5732630644308497, "QAAlignedPrecision (MoverScore)": 0.5377380495172662, "Bleu_1": 0.09911354440834208, "Bleu_2": 0.043182812002142724, "Bleu_3": 0.019528432392290455, "Bleu_4": 0.010096817436605506, "METEOR": 0.20119027569517173, "ROUGE_L": 0.14274656516481254, "BERTScore": 0.6919930745556856, "MoverScore": 0.5165135175183511}}

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.40225015942423237, "Bleu_2": 0.3438334597445478, "Bleu_3": 0.3067690765429287, "Bleu_4": 0.27328134400300574, "METEOR": 0.45259814978909135, "ROUGE_L": 0.4465529728266626, "BERTScore": 0.9264230873224722, "MoverScore": 0.8558230779616741, "AnswerF1Score": 78.59124292139775, "AnswerExactMatch": 67.69614929688527}, "test": {"Bleu_1": 0.4076807044722407, "Bleu_2": 0.35167826743460984, "Bleu_3": 0.3124872985676947, "Bleu_4": 0.2763930111037648, "METEOR": 0.44015880030304244, "ROUGE_L": 0.4600044520684709, "BERTScore": 0.9135333737173631, "MoverScore": 0.8315589100956681, "AnswerF1Score": 75.2473039422877, "AnswerExactMatch": 62.12380076225522}}

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.2344924707813063, "Bleu_2": 0.15711955040228198, "Bleu_3": 0.11078167495052886, "Bleu_4": 0.08061327379855072, "METEOR": 0.1927600303991632, "ROUGE_L": 0.23123569034547642, "BERTScore": 0.8182027558395766, "MoverScore": 0.5783277629069695}, "test": {"Bleu_1": 0.23505994864909152, "Bleu_2": 0.155218291749162, "Bleu_3": 0.1081978169786322, "Bleu_4": 0.07772811265502351, "METEOR": 0.18705560530121057, "ROUGE_L": 0.22982499101237244, "BERTScore": 0.812368726378055, "MoverScore": 0.5723485441800522}}