Markgazol's picture
Upload folder using huggingface_hub
8c0e93b verified
{"arxivqa_subsampled": {"ndcg_at_1": 0.88, "ndcg_at_3": 0.91676, "ndcg_at_5": 0.92244, "ndcg_at_10": 0.92694, "ndcg_at_20": 0.92951, "ndcg_at_100": 0.93352, "ndcg_at_1000": 0.93352, "map_at_1": 0.88, "map_at_3": 0.908, "map_at_5": 0.9111, "map_at_10": 0.91295, "map_at_20": 0.91368, "map_at_100": 0.91434, "map_at_1000": 0.91434, "recall_at_1": 0.88, "recall_at_3": 0.942, "recall_at_5": 0.956, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88, "precision_at_3": 0.314, "precision_at_5": 0.1912, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9079999999999999, "mrr_at_5": 0.9107999999999998, "mrr_at_10": 0.9130079365079364, "mrr_at_20": 0.9138274518738912, "mrr_at_100": 0.9143900697712918, "mrr_at_1000": 0.9143900697712918, "naucs_at_1_max": 0.782341711740376, "naucs_at_1_std": -0.14517181037225524, "naucs_at_1_diff1": 0.9443207126948777, "naucs_at_3_max": 0.8482887407836682, "naucs_at_3_std": -0.08648056923919158, "naucs_at_3_diff1": 0.9459093982420557, "naucs_at_5_max": 0.9032340208810806, "naucs_at_5_std": 0.05192683133859547, "naucs_at_5_diff1": 0.9524658348187762, "naucs_at_10_max": 0.8853096794273262, "naucs_at_10_std": -0.17223778400249365, "naucs_at_10_diff1": 0.9564270152505474, "naucs_at_20_max": 0.8949579831932757, "naucs_at_20_std": 0.0233893557422963, "naucs_at_20_diff1": 0.9607843137254862, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.54989, "ndcg_at_3": 0.6272, "ndcg_at_5": 0.64447, "ndcg_at_10": 0.66722, "ndcg_at_20": 0.68113, "ndcg_at_100": 0.69422, "ndcg_at_1000": 0.70437, "map_at_1": 0.54989, "map_at_3": 0.60865, "map_at_5": 0.61818, "map_at_10": 0.62746, "map_at_20": 0.63122, "map_at_100": 0.63287, "map_at_1000": 0.63328, "recall_at_1": 0.54989, "recall_at_3": 0.68071, "recall_at_5": 0.72284, "recall_at_10": 0.79379, "recall_at_20": 0.84922, "recall_at_100": 0.92239, "recall_at_1000": 1.0, "precision_at_1": 0.54989, "precision_at_3": 0.2269, "precision_at_5": 0.14457, "precision_at_10": 0.07938, "precision_at_20": 0.04246, "precision_at_100": 0.00922, "precision_at_1000": 0.001, "mrr_at_1": 0.5587583148558758, "mrr_at_3": 0.6130820399113082, "mrr_at_5": 0.6231707317073171, "mrr_at_10": 0.6318692147960442, "mrr_at_20": 0.6354293062372974, "mrr_at_100": 0.6373227650448284, "mrr_at_1000": 0.637754578561162, "naucs_at_1_max": 0.6626446233829012, "naucs_at_1_std": 0.02058080661271672, "naucs_at_1_diff1": 0.8687412101807956, "naucs_at_3_max": 0.6794601721961877, "naucs_at_3_std": 0.06185764496543819, "naucs_at_3_diff1": 0.7728703329559015, "naucs_at_5_max": 0.6676424400555316, "naucs_at_5_std": 0.12888850524239007, "naucs_at_5_diff1": 0.7580804398339002, "naucs_at_10_max": 0.6389757378756173, "naucs_at_10_std": 0.32256488584252335, "naucs_at_10_diff1": 0.744102835781862, "naucs_at_20_max": 0.6224489347919718, "naucs_at_20_std": 0.5363125392531453, "naucs_at_20_diff1": 0.7175713575781184, "naucs_at_100_max": 0.6404116660832495, "naucs_at_100_std": 0.7094528544475855, "naucs_at_100_diff1": 0.7671064727074209, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "infovqa_subsampled": {"ndcg_at_1": 0.89676, "ndcg_at_3": 0.92965, "ndcg_at_5": 0.93471, "ndcg_at_10": 0.93678, "ndcg_at_20": 0.93888, "ndcg_at_100": 0.94181, "ndcg_at_1000": 0.94261, "map_at_1": 0.89676, "map_at_3": 0.92206, "map_at_5": 0.9249, "map_at_10": 0.92581, "map_at_20": 0.92642, "map_at_100": 0.92679, "map_at_1000": 0.92683, "recall_at_1": 0.89676, "recall_at_3": 0.95142, "recall_at_5": 0.96356, "recall_at_10": 0.96964, "recall_at_20": 0.97773, "recall_at_100": 0.99393, "recall_at_1000": 1.0, "precision_at_1": 0.89676, "precision_at_3": 0.31714, "precision_at_5": 0.19271, "precision_at_10": 0.09696, "precision_at_20": 0.04889, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.8967611336032388, "mrr_at_3": 0.9217273954116058, "mrr_at_5": 0.9245614035087718, "mrr_at_10": 0.9254771544245227, "mrr_at_20": 0.9260782045611765, "mrr_at_100": 0.9264483101466887, "mrr_at_1000": 0.9264798727472631, "naucs_at_1_max": 0.6109225337520844, "naucs_at_1_std": -0.28746226687710974, "naucs_at_1_diff1": 0.9377884442360623, "naucs_at_3_max": 0.7513425815887516, "naucs_at_3_std": -0.1831182034901586, "naucs_at_3_diff1": 0.9448939012384912, "naucs_at_5_max": 0.8499324771117274, "naucs_at_5_std": 0.1674786026708613, "naucs_at_5_diff1": 0.9410364743251854, "naucs_at_10_max": 0.8460392633470242, "naucs_at_10_std": 0.26520856149085326, "naucs_at_10_diff1": 0.9292437691902227, "naucs_at_20_max": 0.8964958869122784, "naucs_at_20_std": 0.4196427770061891, "naucs_at_20_diff1": 0.927259949634811, "naucs_at_100_max": 0.9564661819784259, "naucs_at_100_std": 0.39174816052979483, "naucs_at_100_diff1": 0.9564661819784259, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.88571, "ndcg_at_3": 0.92704, "ndcg_at_5": 0.93749, "ndcg_at_10": 0.942, "ndcg_at_20": 0.94297, "ndcg_at_100": 0.94297, "ndcg_at_1000": 0.94297, "map_at_1": 0.88571, "map_at_3": 0.91667, "map_at_5": 0.92256, "map_at_10": 0.92436, "map_at_20": 0.92465, "map_at_100": 0.92465, "map_at_1000": 0.92465, "recall_at_1": 0.88571, "recall_at_3": 0.95714, "recall_at_5": 0.98214, "recall_at_10": 0.99643, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.88571, "precision_at_3": 0.31905, "precision_at_5": 0.19643, "precision_at_10": 0.09964, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.8892857142857142, "mrr_at_3": 0.917261904761905, "mrr_at_5": 0.9240476190476191, "mrr_at_10": 0.9258432539682538, "mrr_at_20": 0.9261408730158731, "mrr_at_100": 0.9261408730158731, "mrr_at_1000": 0.9261408730158731, "naucs_at_1_max": 0.6158489558614146, "naucs_at_1_std": 0.3338573801613662, "naucs_at_1_diff1": 0.8969209776934031, "naucs_at_3_max": 0.8942187986305661, "naucs_at_3_std": 0.6969732337379421, "naucs_at_3_diff1": 0.8620837223778431, "naucs_at_5_max": 0.9738562091503306, "naucs_at_5_std": 0.7899159663865564, "naucs_at_5_diff1": 0.8585434173669502, "naucs_at_10_max": 1.0, "naucs_at_10_std": 0.35807656395890114, "naucs_at_10_diff1": 0.8692810457516478, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.68287, "ndcg_at_3": 0.78314, "ndcg_at_5": 0.80681, "ndcg_at_10": 0.82018, "ndcg_at_20": 0.82459, "ndcg_at_100": 0.82908, "ndcg_at_1000": 0.83033, "map_at_1": 0.68287, "map_at_3": 0.75932, "map_at_5": 0.77253, "map_at_10": 0.77817, "map_at_20": 0.77936, "map_at_100": 0.78001, "map_at_1000": 0.78007, "recall_at_1": 0.68287, "recall_at_3": 0.85176, "recall_at_5": 0.90887, "recall_at_10": 0.94957, "recall_at_20": 0.96719, "recall_at_100": 0.99089, "recall_at_1000": 1.0, "precision_at_1": 0.68287, "precision_at_3": 0.28392, "precision_at_5": 0.18177, "precision_at_10": 0.09496, "precision_at_20": 0.04836, "precision_at_100": 0.00991, "precision_at_1000": 0.001, "mrr_at_1": 0.6828675577156743, "mrr_at_3": 0.760024301336574, "mrr_at_5": 0.7729040097205355, "mrr_at_10": 0.7787074003355903, "mrr_at_20": 0.77981048225919, "mrr_at_100": 0.7804686644236308, "mrr_at_1000": 0.780530417746667, "naucs_at_1_max": 0.24316282742534667, "naucs_at_1_std": -0.2387486728504555, "naucs_at_1_diff1": 0.826824088265965, "naucs_at_3_max": 0.2785431946829428, "naucs_at_3_std": -0.21874668661261307, "naucs_at_3_diff1": 0.7258821333794314, "naucs_at_5_max": 0.37017261736106777, "naucs_at_5_std": -0.08964377104816615, "naucs_at_5_diff1": 0.6751762634115527, "naucs_at_10_max": 0.40798144776696565, "naucs_at_10_std": 0.0749134175280517, "naucs_at_10_diff1": 0.6195155652340053, "naucs_at_20_max": 0.3854116148741947, "naucs_at_20_std": 0.13880928341137488, "naucs_at_20_diff1": 0.6123683933054809, "naucs_at_100_max": 0.4016547830791494, "naucs_at_100_std": 0.3369662663486349, "naucs_at_100_diff1": 0.5452087419859556, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.78, "ndcg_at_3": 0.86309, "ndcg_at_5": 0.88375, "ndcg_at_10": 0.88708, "ndcg_at_20": 0.88979, "ndcg_at_100": 0.89155, "ndcg_at_1000": 0.89155, "map_at_1": 0.78, "map_at_3": 0.84333, "map_at_5": 0.85483, "map_at_10": 0.85626, "map_at_20": 0.8571, "map_at_100": 0.8573, "map_at_1000": 0.8573, "recall_at_1": 0.78, "recall_at_3": 0.92, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.78, "precision_at_3": 0.30667, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.79, "mrr_at_3": 0.8516666666666667, "mrr_at_5": 0.8636666666666667, "mrr_at_10": 0.8636666666666667, "mrr_at_20": 0.8643809523809525, "mrr_at_100": 0.8645850340136054, "mrr_at_1000": 0.8645850340136054, "naucs_at_1_max": -0.053646775165762495, "naucs_at_1_std": -0.4592664719246995, "naucs_at_1_diff1": 0.8246394955255713, "naucs_at_3_max": 0.3510154061624642, "naucs_at_3_std": 0.11437908496732017, "naucs_at_3_diff1": 0.7782446311858068, "naucs_at_5_max": 0.5169623404917556, "naucs_at_5_std": -0.22362278244631117, "naucs_at_5_diff1": 0.9074074074074108, "naucs_at_10_max": 0.27544351073763346, "naucs_at_10_std": -0.3968253968253954, "naucs_at_10_diff1": 0.861111111111116, "naucs_at_20_max": 0.7222222222222276, "naucs_at_20_std": 0.35807656395891135, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.98, "ndcg_at_3": 0.985, "ndcg_at_5": 0.98931, "ndcg_at_10": 0.98931, "ndcg_at_20": 0.98931, "ndcg_at_100": 0.98931, "ndcg_at_1000": 0.98931, "map_at_1": 0.98, "map_at_3": 0.98333, "map_at_5": 0.98583, "map_at_10": 0.98583, "map_at_20": 0.98583, "map_at_100": 0.98583, "map_at_1000": 0.98583, "recall_at_1": 0.98, "recall_at_3": 0.99, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.98, "precision_at_3": 0.33, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.98, "mrr_at_3": 0.9833333333333334, "mrr_at_5": 0.9858333333333335, "mrr_at_10": 0.9858333333333335, "mrr_at_20": 0.9858333333333335, "mrr_at_100": 0.9858333333333335, "mrr_at_1000": 0.9858333333333335, "naucs_at_1_max": 0.9346405228758133, "naucs_at_1_std": 0.41433239962652196, "naucs_at_1_diff1": 0.9346405228758133, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 0.8692810457516356, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_energy": {"ndcg_at_1": 0.93, "ndcg_at_3": 0.96024, "ndcg_at_5": 0.96454, "ndcg_at_10": 0.96454, "ndcg_at_20": 0.96454, "ndcg_at_100": 0.96658, "ndcg_at_1000": 0.96658, "map_at_1": 0.93, "map_at_3": 0.95333, "map_at_5": 0.95583, "map_at_10": 0.95583, "map_at_20": 0.95583, "map_at_100": 0.95618, "map_at_1000": 0.95618, "recall_at_1": 0.93, "recall_at_3": 0.98, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.93, "precision_at_3": 0.32667, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.95, "mrr_at_3": 0.9633333333333333, "mrr_at_5": 0.9658333333333333, "mrr_at_10": 0.9658333333333333, "mrr_at_20": 0.9658333333333333, "mrr_at_100": 0.9662333333333332, "mrr_at_1000": 0.9662333333333332, "naucs_at_1_max": 0.625917033480058, "naucs_at_1_std": -0.5382819794584509, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 0.8611111111111119, "naucs_at_3_std": -0.2987861811391324, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": -1.1517273576097316, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": -1.1517273576097316, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": -1.1517273576097316, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.91, "ndcg_at_3": 0.96417, "ndcg_at_5": 0.96417, "ndcg_at_10": 0.96417, "ndcg_at_20": 0.96417, "ndcg_at_100": 0.96417, "ndcg_at_1000": 0.96417, "map_at_1": 0.91, "map_at_3": 0.95167, "map_at_5": 0.95167, "map_at_10": 0.95167, "map_at_20": 0.95167, "map_at_100": 0.95167, "map_at_1000": 0.95167, "recall_at_1": 0.91, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.91, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.91, "mrr_at_3": 0.9533333333333335, "mrr_at_5": 0.9533333333333335, "mrr_at_10": 0.9533333333333335, "mrr_at_20": 0.9533333333333335, "mrr_at_100": 0.9533333333333335, "mrr_at_1000": 0.9533333333333335, "naucs_at_1_max": 0.8433447453055296, "naucs_at_1_std": 0.24981844589687535, "naucs_at_1_diff1": 0.9564270152505436, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.96, "ndcg_at_3": 0.98393, "ndcg_at_5": 0.98393, "ndcg_at_10": 0.98393, "ndcg_at_20": 0.98393, "ndcg_at_100": 0.98393, "ndcg_at_1000": 0.98393, "map_at_1": 0.96, "map_at_3": 0.97833, "map_at_5": 0.97833, "map_at_10": 0.97833, "map_at_20": 0.97833, "map_at_100": 0.97833, "map_at_1000": 0.97833, "recall_at_1": 0.96, "recall_at_3": 1.0, "recall_at_5": 1.0, "recall_at_10": 1.0, "recall_at_20": 1.0, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.96, "precision_at_3": 0.33333, "precision_at_5": 0.2, "precision_at_10": 0.1, "precision_at_20": 0.05, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.96, "mrr_at_3": 0.9783333333333334, "mrr_at_5": 0.9783333333333334, "mrr_at_10": 0.9783333333333334, "mrr_at_20": 0.9783333333333334, "mrr_at_100": 0.9783333333333334, "mrr_at_1000": 0.9783333333333334, "naucs_at_1_max": 0.7496498599439807, "naucs_at_1_std": -0.19304388422035748, "naucs_at_1_diff1": 1.0, "naucs_at_3_max": 1.0, "naucs_at_3_std": 1.0, "naucs_at_3_diff1": 1.0, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}