AugTriever-TQGen-ExSum / eval_results.txt
memray's picture
Upload 130 files
e840ac8
eval/beir-arguana_ndcg@10 = 0.40399
eval/beir-arguana_recall@100 = 0.94666
eval/beir-avg_ndcg@10 = 0.365958
eval/beir-avg_recall@10 = 0.42534799999999995
eval/beir-avg_recall@100 = 0.6361640000000001
eval/beir-avg_recall@20 = 0.488368
eval/beir-climate-fever_ndcg@10 = 0.1608
eval/beir-climate-fever_recall@10 = 0.19355
eval/beir-climate-fever_recall@100 = 0.4308
eval/beir-climate-fever_recall@20 = 0.25216
eval/beir-cqadupstack_ndcg@10 = 0.27109750000000005
eval/beir-cqadupstack_recall@100 = 0.5988908333333334
eval/beir-dbpedia-entity_ndcg@10 = 0.30373
eval/beir-dbpedia-entity_recall@10 = 0.20251
eval/beir-dbpedia-entity_recall@100 = 0.43711
eval/beir-dbpedia-entity_recall@20 = 0.25943
eval/beir-fever_ndcg@10 = 0.60393
eval/beir-fever_recall@10 = 0.77489
eval/beir-fever_recall@100 = 0.90348
eval/beir-fever_recall@20 = 0.82755
eval/beir-fiqa_ndcg@10 = 0.25834
eval/beir-fiqa_recall@100 = 0.58671
eval/beir-hotpotqa_ndcg@10 = 0.53065
eval/beir-hotpotqa_recall@10 = 0.5607
eval/beir-hotpotqa_recall@100 = 0.70459
eval/beir-hotpotqa_recall@20 = 0.60614
eval/beir-msmarco_ndcg@10 = 0.23068
eval/beir-msmarco_recall@10 = 0.39509
eval/beir-msmarco_recall@100 = 0.70484
eval/beir-msmarco_recall@20 = 0.49656
eval/beir-nfcorpus_ndcg@10 = 0.29872
eval/beir-nfcorpus_recall@100 = 0.27142
eval/beir-nq_ndcg@10 = 0.27193
eval/beir-nq_recall@100 = 0.79637
eval/beir-quora_ndcg@10 = 0.78168
eval/beir-quora_recall@100 = 0.97651
eval/beir-scidocs_ndcg@10 = 0.15698
eval/beir-scidocs_recall@100 = 0.37647
eval/beir-scifact_ndcg@10 = 0.6428
eval/beir-scifact_recall@100 = 0.93156
eval/beir-trec-covid_ndcg@10 = 0.54138
eval/beir-trec-covid_recall@100 = 0.10381
eval/beir-webis-touche2020_ndcg@10 = 0.1662
eval/beir-webis-touche2020_recall@100 = 0.43201
eval/qa-curatedtrec-test-acc@100 = 0.930835734870317
eval/qa-curatedtrec-test-acc@20 = 0.8414985590778098
eval/qa-curatedtrec-test-acc@5 = 0.6858789625360231
eval/qa-entityqs-macro-acc@100 = 0.7691458456243941
eval/qa-entityqs-macro-acc@20 = 0.6556998771272563
eval/qa-entityqs-macro-acc@5 = 0.5259109395241858
eval/qa-nq-test-acc@100 = 0.7969529085872576
eval/qa-nq-test-acc@20 = 0.6529085872576177
eval/qa-nq-test-acc@5 = 0.45373961218836567
eval/qa-squad1-test-acc@100 = 0.7715231788079471
eval/qa-squad1-test-acc@20 = 0.6227057710501419
eval/qa-squad1-test-acc@5 = 0.4261116367076632
eval/qa-trivia-test-acc@100 = 0.8354105895872006
eval/qa-trivia-test-acc@20 = 0.7541766109785203
eval/qa-trivia-test-acc@5 = 0.6246795721736056
eval/qa-webq-test-acc@100 = 0.8159448818897638
eval/qa-webq-test-acc@20 = 0.6968503937007874
eval/qa-webq-test-acc@5 = 0.47687007874015747
eval/senteval-CR = 87.1
eval/senteval-MPQA = 88.87
eval/senteval-MR = 81.13
eval/senteval-MRPC = 71.32
eval/senteval-SICKRelatedness = 0.6909722716792152
eval/senteval-SST2 = 83.72
eval/senteval-STS12 = 0.606079829047924
eval/senteval-STS13 = 0.7564536182897523
eval/senteval-STS14 = 0.6704800621775756
eval/senteval-STS15 = 0.7993930145058169
eval/senteval-STS16 = 0.7931904794778135
eval/senteval-STSBenchmark = 0.7488342650348635
eval/senteval-SUBJ = 95.37
eval/senteval-TREC = 79.31
eval/senteval-avg_sts_7 = 0.7236290771732802
eval/senteval-avg_transfer = 83.83142857142856
train/global_step = 100000