add eval

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.2512808570097713, "Bleu_2": 0.17200666979618856, "Bleu_3": 0.11601037389714632, "Bleu_4": 0.07833093186130648, "METEOR": 0.27241316698312057, "ROUGE_L": 0.2442186146594222, "BERTScore": 0.7912570112089063, "MoverScore": 0.6111877039173896, "AnswerF1Score": 47.97914329982987, "AnswerExactMatch": 13.203266787658801}, "test": {"Bleu_1": 0.19504937685970955, "Bleu_2": 0.13013436077051674, "Bleu_3": 0.08631932690075304, "Bleu_4": 0.056732079759815104, "METEOR": 0.2266378098231599, "ROUGE_L": 0.18189892033201369, "BERTScore": 0.7504787875336009, "MoverScore": 0.5779213304061341, "AnswerF1Score": 38.08332842395432, "AnswerExactMatch": 9.936479128856623}}

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

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.12215287779377382, "Bleu_2": 0.052578262597836246, "Bleu_3": 0.024112443205915976, "Bleu_4": 0.008702732064885895, "METEOR": 0.13773817064587052, "ROUGE_L": 0.11946680276213367, "BERTScore": 0.8194934565045169, "MoverScore": 0.5624235228037266}, "test": {"Bleu_1": 0.1043083900226701, "Bleu_2": 0.04316105757713112, "Bleu_3": 0.018803586872870995, "Bleu_4": 0.00756511319481653, "METEOR": 0.12323987544014788, "ROUGE_L": 0.10459936850793287, "BERTScore": 0.804436454869849, "MoverScore": 0.5509798112903916}}