baseline-results / BAAI_bge-m3_ocr_metrics.json
HugSib's picture
Upload 7 files
9294e27 verified
{"vidore/arxivqa_test_subsampled_ocr_chunk": {"ndcg_at_1": 0.28056, "ndcg_at_3": 0.30702, "ndcg_at_5": 0.31357, "ndcg_at_10": 0.32002, "ndcg_at_20": 0.32605, "ndcg_at_100": 0.34549, "ndcg_at_1000": 0.40893, "map_at_1": 0.28056, "map_at_3": 0.30027, "map_at_5": 0.30387, "map_at_10": 0.30652, "map_at_20": 0.30815, "map_at_100": 0.3102, "map_at_1000": 0.31247, "recall_at_1": 0.28056, "recall_at_3": 0.32665, "recall_at_5": 0.34269, "recall_at_10": 0.36273, "recall_at_20": 0.38677, "recall_at_100": 0.501, "recall_at_1000": 1.0, "precision_at_1": 0.28056, "precision_at_3": 0.10888, "precision_at_5": 0.06854, "precision_at_10": 0.03627, "precision_at_20": 0.01934, "precision_at_100": 0.00501, "precision_at_1000": 0.001, "mrr_at_1": 0.2785571142284569, "mrr_at_3": 0.29926519706078825, "mrr_at_5": 0.30247160988643956, "mrr_at_10": 0.30479530489550527, "mrr_at_20": 0.3063476794924985, "mrr_at_100": 0.30861010919339893, "mrr_at_1000": 0.3108909560984022, "naucs_at_1_max": 0.6701941198685928, "naucs_at_1_std": 0.07854254090644529, "naucs_at_1_diff1": 0.8062461464261246, "naucs_at_3_max": 0.6285566101728887, "naucs_at_3_std": 0.03419297969513178, "naucs_at_3_diff1": 0.7458737426282002, "naucs_at_5_max": 0.6185634421795102, "naucs_at_5_std": 0.014538582674057355, "naucs_at_5_diff1": 0.7201402409078546, "naucs_at_10_max": 0.6305237157971464, "naucs_at_10_std": -0.01586330155399704, "naucs_at_10_diff1": 0.7166857368746579, "naucs_at_20_max": 0.6031464813028605, "naucs_at_20_std": 0.008045266551501822, "naucs_at_20_diff1": 0.6885970561890752, "naucs_at_100_max": 0.46502656149905125, "naucs_at_100_std": 0.013291127384033596, "naucs_at_100_diff1": 0.5527531281978629, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/docvqa_test_subsampled_ocr_chunk": {"ndcg_at_1": 0.22889, "ndcg_at_3": 0.25267, "ndcg_at_5": 0.25736, "ndcg_at_10": 0.26155, "ndcg_at_20": 0.26543, "ndcg_at_100": 0.28841, "ndcg_at_1000": 0.3631, "map_at_1": 0.22889, "map_at_3": 0.24704, "map_at_5": 0.2497, "map_at_10": 0.25136, "map_at_20": 0.2524, "map_at_100": 0.25482, "map_at_1000": 0.25824, "recall_at_1": 0.22889, "recall_at_3": 0.26889, "recall_at_5": 0.28, "recall_at_10": 0.29333, "recall_at_20": 0.30889, "recall_at_100": 0.44444, "recall_at_1000": 1.0, "precision_at_1": 0.22889, "precision_at_3": 0.08963, "precision_at_5": 0.056, "precision_at_10": 0.02933, "precision_at_20": 0.01544, "precision_at_100": 0.00444, "precision_at_1000": 0.001, "mrr_at_1": 0.22666666666666666, "mrr_at_3": 0.24555555555555553, "mrr_at_5": 0.2471111111111111, "mrr_at_10": 0.24873985890652553, "mrr_at_20": 0.24966410133076794, "mrr_at_100": 0.2523293519193986, "mrr_at_1000": 0.25576918896976125, "naucs_at_1_max": 0.2780949728450074, "naucs_at_1_std": 0.20071598153664302, "naucs_at_1_diff1": 0.5799246656997971, "naucs_at_3_max": 0.35936130977045494, "naucs_at_3_std": 0.1544914232935944, "naucs_at_3_diff1": 0.5846141193811738, "naucs_at_5_max": 0.34433643096138183, "naucs_at_5_std": 0.14037097044527622, "naucs_at_5_diff1": 0.5631196032056416, "naucs_at_10_max": 0.3380263733061344, "naucs_at_10_std": 0.12440198649764453, "naucs_at_10_diff1": 0.5548654621399775, "naucs_at_20_max": 0.32464209163769436, "naucs_at_20_std": 0.12130769207773692, "naucs_at_20_diff1": 0.5205029400950035, "naucs_at_100_max": 0.25585535869880977, "naucs_at_100_std": 0.11851873366250411, "naucs_at_100_diff1": 0.40237583502759233, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/infovqa_test_subsampled_ocr_chunk": {"ndcg_at_1": 0.53846, "ndcg_at_3": 0.59051, "ndcg_at_5": 0.60114, "ndcg_at_10": 0.60799, "ndcg_at_20": 0.61261, "ndcg_at_100": 0.61947, "ndcg_at_1000": 0.65326, "map_at_1": 0.53846, "map_at_3": 0.57895, "map_at_5": 0.58472, "map_at_10": 0.58773, "map_at_20": 0.589, "map_at_100": 0.58972, "map_at_1000": 0.59082, "recall_at_1": 0.53846, "recall_at_3": 0.62348, "recall_at_5": 0.6498, "recall_at_10": 0.67004, "recall_at_20": 0.68826, "recall_at_100": 0.72874, "recall_at_1000": 1.0, "precision_at_1": 0.53846, "precision_at_3": 0.20783, "precision_at_5": 0.12996, "precision_at_10": 0.067, "precision_at_20": 0.03441, "precision_at_100": 0.00729, "precision_at_1000": 0.001, "mrr_at_1": 0.5384615384615384, "mrr_at_3": 0.5796221322537113, "mrr_at_5": 0.5848852901484481, "mrr_at_10": 0.5876566416040101, "mrr_at_20": 0.5886210409817223, "mrr_at_100": 0.589597820218809, "mrr_at_1000": 0.5907229602144334, "naucs_at_1_max": 0.4978021774056528, "naucs_at_1_std": -0.07542917824583496, "naucs_at_1_diff1": 0.7399168050465158, "naucs_at_3_max": 0.570597973443351, "naucs_at_3_std": -0.15660038339464605, "naucs_at_3_diff1": 0.700280177148945, "naucs_at_5_max": 0.5829332498919231, "naucs_at_5_std": -0.21567450674021427, "naucs_at_5_diff1": 0.6972500134886034, "naucs_at_10_max": 0.5796166156572145, "naucs_at_10_std": -0.24012767901994408, "naucs_at_10_diff1": 0.6957322408739849, "naucs_at_20_max": 0.5765596430552485, "naucs_at_20_std": -0.2772336700449585, "naucs_at_20_diff1": 0.6820587708188958, "naucs_at_100_max": 0.5722998659227064, "naucs_at_100_std": -0.29836970923403416, "naucs_at_100_diff1": 0.6380591257832868, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "vidore/tabfquad_test_subsampled_ocr_chunk": {"ndcg_at_1": 0.55714, "ndcg_at_3": 0.66122, "ndcg_at_5": 0.70781, "ndcg_at_10": 0.72849, "ndcg_at_20": 0.73821, "ndcg_at_100": 0.7463, "ndcg_at_1000": 0.7463, "map_at_1": 0.55714, "map_at_3": 0.63333, "map_at_5": 0.65976, "map_at_10": 0.66824, "map_at_20": 0.67079, "map_at_100": 0.67196, "map_at_1000": 0.67196, "recall_at_1": 0.55714, "recall_at_3": 0.74286, "recall_at_5": 0.85357, "recall_at_10": 0.91786, "recall_at_20": 0.95714, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.55714, "precision_at_3": 0.24762, "precision_at_5": 0.17071, "precision_at_10": 0.09179, "precision_at_20": 0.04786, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.5535714285714286, "mrr_at_3": 0.6291666666666669, "mrr_at_5": 0.6566666666666668, "mrr_at_10": 0.665249433106576, "mrr_at_20": 0.6678019973938539, "mrr_at_100": 0.66896066730146, "mrr_at_1000": 0.66896066730146, "naucs_at_1_max": 0.5411840216710132, "naucs_at_1_std": 0.07136575899084238, "naucs_at_1_diff1": 0.7323518709442661, "naucs_at_3_max": 0.6245031564180499, "naucs_at_3_std": 0.2781447276128128, "naucs_at_3_diff1": 0.6712210661678748, "naucs_at_5_max": 0.5351381530493459, "naucs_at_5_std": 0.28173481266779, "naucs_at_5_diff1": 0.6158086051649996, "naucs_at_10_max": 0.5288434214265418, "naucs_at_10_std": 0.371676206714572, "naucs_at_10_diff1": 0.6439532334673006, "naucs_at_20_max": 0.6282679738562067, "naucs_at_20_std": 0.5775754746342978, "naucs_at_20_diff1": 0.7555244319950166, "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}, "vidore/tatdqa_test_ocr_chunk": {"ndcg_at_1": 0.38578, "ndcg_at_3": 0.47694, "ndcg_at_5": 0.50523, "ndcg_at_10": 0.53372, "ndcg_at_20": 0.55846, "ndcg_at_100": 0.58614, "ndcg_at_1000": 0.59367, "map_at_1": 0.38578, "map_at_3": 0.45504, "map_at_5": 0.47075, "map_at_10": 0.48273, "map_at_20": 0.48953, "map_at_100": 0.49317, "map_at_1000": 0.49354, "recall_at_1": 0.38578, "recall_at_3": 0.5401, "recall_at_5": 0.60875, "recall_at_10": 0.69563, "recall_at_20": 0.79344, "recall_at_100": 0.94532, "recall_at_1000": 1.0, "precision_at_1": 0.38578, "precision_at_3": 0.18003, "precision_at_5": 0.12175, "precision_at_10": 0.06956, "precision_at_20": 0.03967, "precision_at_100": 0.00945, "precision_at_1000": 0.001, "mrr_at_1": 0.3845686512758202, "mrr_at_3": 0.4548400162008913, "mrr_at_5": 0.4703624949372223, "mrr_at_10": 0.48243119442997984, "mrr_at_20": 0.48916878737157987, "mrr_at_100": 0.4928297342270563, "mrr_at_1000": 0.4931936357193615, "naucs_at_1_max": 0.19636682190619187, "naucs_at_1_std": -0.12016934920791428, "naucs_at_1_diff1": 0.636054782701776, "naucs_at_3_max": 0.23866558501463134, "naucs_at_3_std": -0.05621720922845977, "naucs_at_3_diff1": 0.5469023302617858, "naucs_at_5_max": 0.27577210800734087, "naucs_at_5_std": -0.013466567488641095, "naucs_at_5_diff1": 0.5174251534498898, "naucs_at_10_max": 0.3312730044210745, "naucs_at_10_std": 0.06275617207927053, "naucs_at_10_diff1": 0.4896897579908386, "naucs_at_20_max": 0.29736917644821625, "naucs_at_20_std": 0.15762621054222417, "naucs_at_20_diff1": 0.44963935988791637, "naucs_at_100_max": 0.3880630790183183, "naucs_at_100_std": 0.36142696422026793, "naucs_at_100_diff1": 0.4868848857263764, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/shiftproject_test_ocr_chunk": {"ndcg_at_1": 0.56, "ndcg_at_3": 0.71464, "ndcg_at_5": 0.73187, "ndcg_at_10": 0.74826, "ndcg_at_20": 0.75571, "ndcg_at_100": 0.76499, "ndcg_at_1000": 0.76499, "map_at_1": 0.56, "map_at_3": 0.675, "map_at_5": 0.685, "map_at_10": 0.69188, "map_at_20": 0.69385, "map_at_100": 0.6951, "map_at_1000": 0.6951, "recall_at_1": 0.56, "recall_at_3": 0.83, "recall_at_5": 0.87, "recall_at_10": 0.92, "recall_at_20": 0.95, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.56, "precision_at_3": 0.27667, "precision_at_5": 0.174, "precision_at_10": 0.092, "precision_at_20": 0.0475, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.56, "mrr_at_3": 0.675, "mrr_at_5": 0.685, "mrr_at_10": 0.6918849206349208, "mrr_at_20": 0.6938492063492063, "mrr_at_100": 0.6951016573295985, "mrr_at_1000": 0.6951016573295985, "naucs_at_1_max": 0.14671814671814648, "naucs_at_1_std": -0.2602344992050878, "naucs_at_1_diff1": 0.569043833749716, "naucs_at_3_max": 0.38410634469147203, "naucs_at_3_std": -0.07894584083125322, "naucs_at_3_diff1": 0.6384744877227599, "naucs_at_5_max": 0.5028141894393843, "naucs_at_5_std": 0.005369177219878741, "naucs_at_5_diff1": 0.6229726727393908, "naucs_at_10_max": 0.6828898225957046, "naucs_at_10_std": 0.18417366946778999, "naucs_at_10_diff1": 0.5221755368814213, "naucs_at_20_max": 0.6765639589169009, "naucs_at_20_std": 0.16321195144724954, "naucs_at_20_diff1": 0.6873015873015907, "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}, "vidore/syntheticDocQA_artificial_intelligence_test_ocr_chunk": {"ndcg_at_1": 0.82, "ndcg_at_3": 0.89809, "ndcg_at_5": 0.9024, "ndcg_at_10": 0.90573, "ndcg_at_20": 0.90573, "ndcg_at_100": 0.90789, "ndcg_at_1000": 0.91085, "map_at_1": 0.82, "map_at_3": 0.88, "map_at_5": 0.8825, "map_at_10": 0.88393, "map_at_20": 0.88393, "map_at_100": 0.88435, "map_at_1000": 0.88453, "recall_at_1": 0.82, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.97, "recall_at_20": 0.97, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.82, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.097, "precision_at_20": 0.0485, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.82, "mrr_at_3": 0.88, "mrr_at_5": 0.8825, "mrr_at_10": 0.8858333333333333, "mrr_at_20": 0.8858333333333333, "mrr_at_100": 0.8858333333333333, "mrr_at_1000": 0.886022911051213, "naucs_at_1_max": 0.5348882035466462, "naucs_at_1_std": 0.0736039211366895, "naucs_at_1_diff1": 0.8600066086573411, "naucs_at_3_max": 0.6056022408963601, "naucs_at_3_std": 0.06321195144724523, "naucs_at_3_diff1": 0.8921568627450972, "naucs_at_5_max": 0.5070028011204499, "naucs_at_5_std": 0.12184873949580138, "naucs_at_5_diff1": 0.9346405228758139, "naucs_at_10_max": 0.4352629940865253, "naucs_at_10_std": 0.043106131341428565, "naucs_at_10_diff1": 0.9564270152505424, "naucs_at_20_max": 0.4352629940865253, "naucs_at_20_std": 0.043106131341428565, "naucs_at_20_diff1": 0.9564270152505424, "naucs_at_100_max": 0.9346405228758174, "naucs_at_100_std": 0.9346405228758174, "naucs_at_100_diff1": 0.9346405228758174, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_energy_test_ocr_chunk": {"ndcg_at_1": 0.79, "ndcg_at_3": 0.83155, "ndcg_at_5": 0.83585, "ndcg_at_10": 0.84608, "ndcg_at_20": 0.85627, "ndcg_at_100": 0.85835, "ndcg_at_1000": 0.86512, "map_at_1": 0.79, "map_at_3": 0.82167, "map_at_5": 0.82417, "map_at_10": 0.82869, "map_at_20": 0.83154, "map_at_100": 0.83191, "map_at_1000": 0.83223, "recall_at_1": 0.79, "recall_at_3": 0.86, "recall_at_5": 0.87, "recall_at_10": 0.9, "recall_at_20": 0.94, "recall_at_100": 0.95, "recall_at_1000": 1.0, "precision_at_1": 0.79, "precision_at_3": 0.28667, "precision_at_5": 0.174, "precision_at_10": 0.09, "precision_at_20": 0.047, "precision_at_100": 0.0095, "precision_at_1000": 0.001, "mrr_at_1": 0.79, "mrr_at_3": 0.825, "mrr_at_5": 0.8275, "mrr_at_10": 0.8305952380952383, "mrr_at_20": 0.8334402264402265, "mrr_at_100": 0.833810596810597, "mrr_at_1000": 0.8341366395789735, "naucs_at_1_max": 0.4421574049582799, "naucs_at_1_std": -0.13735061437468474, "naucs_at_1_diff1": 0.8474523288527658, "naucs_at_3_max": 0.5847304974366062, "naucs_at_3_std": -0.11587224608563136, "naucs_at_3_diff1": 0.9381668283220167, "naucs_at_5_max": 0.5677627193956891, "naucs_at_5_std": -0.13359994075390383, "naucs_at_5_diff1": 0.9455676516329689, "naucs_at_10_max": 0.7481325863678815, "naucs_at_10_std": 0.19668534080298863, "naucs_at_10_diff1": 0.9052287581699361, "naucs_at_20_max": 0.7443977591036433, "naucs_at_20_std": -0.05648926237161577, "naucs_at_20_diff1": 0.91013071895425, "naucs_at_100_max": 0.7824463118580797, "naucs_at_100_std": 0.2802054154995361, "naucs_at_100_diff1": 0.9183006535947744, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_government_reports_test_ocr_chunk": {"ndcg_at_1": 0.76, "ndcg_at_3": 0.82417, "ndcg_at_5": 0.84913, "ndcg_at_10": 0.85228, "ndcg_at_20": 0.85228, "ndcg_at_100": 0.85557, "ndcg_at_1000": 0.8614, "map_at_1": 0.76, "map_at_3": 0.80833, "map_at_5": 0.82233, "map_at_10": 0.82358, "map_at_20": 0.82358, "map_at_100": 0.82389, "map_at_1000": 0.82425, "recall_at_1": 0.76, "recall_at_3": 0.87, "recall_at_5": 0.93, "recall_at_10": 0.94, "recall_at_20": 0.94, "recall_at_100": 0.96, "recall_at_1000": 1.0, "precision_at_1": 0.76, "precision_at_3": 0.29, "precision_at_5": 0.186, "precision_at_10": 0.094, "precision_at_20": 0.047, "precision_at_100": 0.0096, "precision_at_1000": 0.001, "mrr_at_1": 0.76, "mrr_at_3": 0.8083333333333335, "mrr_at_5": 0.8223333333333334, "mrr_at_10": 0.8235833333333333, "mrr_at_20": 0.8235833333333333, "mrr_at_100": 0.8240368698738264, "mrr_at_1000": 0.824290416165644, "naucs_at_1_max": 0.4211733148741023, "naucs_at_1_std": 0.3447261400017304, "naucs_at_1_diff1": 0.6573721554036518, "naucs_at_3_max": 0.7245426942160992, "naucs_at_3_std": 0.3127453158557342, "naucs_at_3_diff1": 0.46826631119010537, "naucs_at_5_max": 0.9176337201547295, "naucs_at_5_std": 0.18387354941976997, "naucs_at_5_diff1": 0.25203414699213317, "naucs_at_10_max": 0.9256924992219131, "naucs_at_10_std": 0.1221599751011489, "naucs_at_10_diff1": 0.14915966386554824, "naucs_at_20_max": 0.9256924992219131, "naucs_at_20_std": 0.1221599751011489, "naucs_at_20_diff1": 0.14915966386554824, "naucs_at_100_max": 1.0, "naucs_at_100_std": -0.1235994397759103, "naucs_at_100_diff1": 0.16234827264239116, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "vidore/syntheticDocQA_healthcare_industry_test_ocr_chunk": {"ndcg_at_1": 0.83, "ndcg_at_3": 0.89809, "ndcg_at_5": 0.91058, "ndcg_at_10": 0.91706, "ndcg_at_20": 0.91706, "ndcg_at_100": 0.91706, "ndcg_at_1000": 0.91837, "map_at_1": 0.83, "map_at_3": 0.88333, "map_at_5": 0.89033, "map_at_10": 0.89301, "map_at_20": 0.89301, "map_at_100": 0.89301, "map_at_1000": 0.89306, "recall_at_1": 0.83, "recall_at_3": 0.94, "recall_at_5": 0.97, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.83, "precision_at_3": 0.31333, "precision_at_5": 0.194, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.84, "mrr_at_3": 0.8883333333333333, "mrr_at_5": 0.8953333333333333, "mrr_at_10": 0.8980119047619048, "mrr_at_20": 0.8980119047619048, "mrr_at_100": 0.8980119047619048, "mrr_at_1000": 0.8980629251700681, "naucs_at_1_max": 0.7704765774656069, "naucs_at_1_std": 0.1858129680153242, "naucs_at_1_diff1": 0.9008823358681145, "naucs_at_3_max": 0.7176314970432593, "naucs_at_3_std": -0.25116713352007614, "naucs_at_3_diff1": 0.8856209150326754, "naucs_at_5_max": 0.6150015561780299, "naucs_at_5_std": -0.3020541549953327, "naucs_at_5_diff1": 1.0, "naucs_at_10_max": 1.0, "naucs_at_10_std": -0.1713352007469681, "naucs_at_10_diff1": 1.0, "naucs_at_20_max": 1.0, "naucs_at_20_std": -0.1713352007469681, "naucs_at_20_diff1": 1.0, "naucs_at_100_max": 1.0, "naucs_at_100_std": -0.17133520074697067, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}