AugTriever-Hybrid-TQGen-plus / eval_results.txt
memray's picture
Upload 161 files
d4f265a
eval/beir-arguana_ndcg@10 = 0.41208
eval/beir-arguana_recall@100 = 0.94808
eval/beir-avg_ndcg@10 = 0.39221599999999995
eval/beir-avg_recall@10 = 0.451112
eval/beir-avg_recall@100 = 0.66336
eval/beir-avg_recall@20 = 0.516078
eval/beir-climate-fever_ndcg@10 = 0.16356
eval/beir-climate-fever_recall@10 = 0.2108
eval/beir-climate-fever_recall@100 = 0.43891
eval/beir-climate-fever_recall@20 = 0.2629
eval/beir-cqadupstack_ndcg@10 = 0.29382749999999996
eval/beir-cqadupstack_recall@100 = 0.6354808333333334
eval/beir-dbpedia-entity_ndcg@10 = 0.32611
eval/beir-dbpedia-entity_recall@10 = 0.20661
eval/beir-dbpedia-entity_recall@100 = 0.4804
eval/beir-dbpedia-entity_recall@20 = 0.27924
eval/beir-fever_ndcg@10 = 0.65477
eval/beir-fever_recall@10 = 0.82563
eval/beir-fever_recall@100 = 0.92616
eval/beir-fever_recall@20 = 0.8717
eval/beir-fiqa_ndcg@10 = 0.26892
eval/beir-fiqa_recall@100 = 0.61544
eval/beir-hotpotqa_ndcg@10 = 0.57114
eval/beir-hotpotqa_recall@10 = 0.59467
eval/beir-hotpotqa_recall@100 = 0.73363
eval/beir-hotpotqa_recall@20 = 0.64382
eval/beir-msmarco_ndcg@10 = 0.2455
eval/beir-msmarco_recall@10 = 0.41785
eval/beir-msmarco_recall@100 = 0.7377
eval/beir-msmarco_recall@20 = 0.52273
eval/beir-nfcorpus_ndcg@10 = 0.32723
eval/beir-nfcorpus_recall@100 = 0.31693
eval/beir-nq_ndcg@10 = 0.32677
eval/beir-nq_recall@100 = 0.84849
eval/beir-quora_ndcg@10 = 0.79323
eval/beir-quora_recall@100 = 0.98182
eval/beir-scidocs_ndcg@10 = 0.16768
eval/beir-scidocs_recall@100 = 0.3918
eval/beir-scifact_ndcg@10 = 0.67807
eval/beir-scifact_recall@100 = 0.92989
eval/beir-trec-covid_ndcg@10 = 0.5952
eval/beir-trec-covid_recall@100 = 0.10661
eval/beir-webis-touche2020_ndcg@10 = 0.17834
eval/beir-webis-touche2020_recall@100 = 0.41812
eval/qa-curatedtrec-test-acc@100 = 0.9337175792507204
eval/qa-curatedtrec-test-acc@20 = 0.8688760806916427
eval/qa-curatedtrec-test-acc@5 = 0.6988472622478387
eval/qa-entityqs-macro-acc@100 = 0.7873324151667193
eval/qa-entityqs-macro-acc@20 = 0.6850549856454431
eval/qa-entityqs-macro-acc@5 = 0.5658741734385021
eval/qa-nq-test-acc@100 = 0.8274238227146814
eval/qa-nq-test-acc@20 = 0.6972299168975069
eval/qa-nq-test-acc@5 = 0.49473684210526314
eval/qa-squad1-test-acc@100 = 0.7799432355723747
eval/qa-squad1-test-acc@20 = 0.633774834437086
eval/qa-squad1-test-acc@5 = 0.438883632923368
eval/qa-trivia-test-acc@100 = 0.8433660390700963
eval/qa-trivia-test-acc@20 = 0.7657562096702908
eval/qa-trivia-test-acc@5 = 0.6412092283214001
eval/qa-webq-test-acc@100 = 0.8233267716535433
eval/qa-webq-test-acc@20 = 0.7071850393700787
eval/qa-webq-test-acc@5 = 0.5108267716535433
eval/senteval-CR = 88.38
eval/senteval-MPQA = 89.44
eval/senteval-MR = 82.2
eval/senteval-MRPC = 70.61
eval/senteval-SICKRelatedness = 0.6925290217821645
eval/senteval-SST2 = 84.29
eval/senteval-STS12 = 0.551472253212969
eval/senteval-STS13 = 0.7229160162899463
eval/senteval-STS14 = 0.6332541978552203
eval/senteval-STS15 = 0.7527302594998441
eval/senteval-STS16 = 0.7752096236911921
eval/senteval-STSBenchmark = 0.7134156978222834
eval/senteval-SUBJ = 95.78
eval/senteval-TREC = 80.47
eval/senteval-avg_sts_7 = 0.6916467243076598
eval/senteval-avg_transfer = 84.45285714285716
train/global_step = 200000
eval/beir-arguana_ndcg@10 = 0.41208
eval/beir-arguana_recall@100 = 0.94808
eval/beir-avg_ndcg@10 = 0.3352125
eval/beir-avg_recall@10 = 0.18044
eval/beir-avg_recall@100 = 0.4163675
eval/beir-avg_recall@20 = 0.2420775
eval/beir-bioasq_ndcg@10 = 0.29947
eval/beir-bioasq_recall@10 = 0.33049
eval/beir-bioasq_recall@100 = 0.54332
eval/beir-bioasq_recall@20 = 0.39463
eval/beir-climate-fever_ndcg@10 = 0.16356
eval/beir-climate-fever_recall@100 = 0.43891
eval/beir-cqadupstack_ndcg@10 = 0.29382749999999996
eval/beir-cqadupstack_recall@100 = 0.6354808333333334
eval/beir-dbpedia-entity_ndcg@10 = 0.32611
eval/beir-dbpedia-entity_recall@100 = 0.4804
eval/beir-fever_ndcg@10 = 0.65477
eval/beir-fever_recall@100 = 0.92616
eval/beir-fiqa_ndcg@10 = 0.26892
eval/beir-fiqa_recall@100 = 0.61544
eval/beir-hotpotqa_ndcg@10 = 0.57114
eval/beir-hotpotqa_recall@100 = 0.73363
eval/beir-msmarco_ndcg@10 = 0.2455
eval/beir-msmarco_recall@100 = 0.7377
eval/beir-nfcorpus_ndcg@10 = 0.32723
eval/beir-nfcorpus_recall@100 = 0.31693
eval/beir-nq_ndcg@10 = 0.32677
eval/beir-nq_recall@100 = 0.84849
eval/beir-quora_ndcg@10 = 0.79323
eval/beir-quora_recall@100 = 0.98182
eval/beir-robust04_ndcg@10 = 0.37855
eval/beir-robust04_recall@10 = 0.12422
eval/beir-robust04_recall@100 = 0.33149
eval/beir-robust04_recall@20 = 0.17174
eval/beir-scidocs_ndcg@10 = 0.16768
eval/beir-scidocs_recall@100 = 0.3918
eval/beir-scifact_ndcg@10 = 0.67807
eval/beir-scifact_recall@100 = 0.92989
eval/beir-signal1m_ndcg@10 = 0.27524
eval/beir-signal1m_recall@10 = 0.13187
eval/beir-signal1m_recall@100 = 0.3144
eval/beir-signal1m_recall@20 = 0.17823
eval/beir-trec-covid_ndcg@10 = 0.5952
eval/beir-trec-covid_recall@100 = 0.10661
eval/beir-trec-news_ndcg@10 = 0.38759
eval/beir-trec-news_recall@10 = 0.13518
eval/beir-trec-news_recall@100 = 0.47626
eval/beir-trec-news_recall@20 = 0.22371
eval/beir-webis-touche2020_ndcg@10 = 0.17834
eval/beir-webis-touche2020_recall@100 = 0.41812
train/global_step = 200000