Create eval_results.jsonl

eval_results.jsonl

@@ -0,0 +1,40 @@
+{"key": "imagenet1k", "dataset": "ImageNet 1k", "metrics": {"acc1": 0.8344, "acc5": 0.97192, "mean_per_class_recall": 0.8343200000000001, "main_metric": 0.8344}}
+{"key": "vtab/caltech101", "dataset": "Caltech-101", "metrics": {"acc1": 0.8606409202958094, "acc5": 0.9426458504519309, "mean_per_class_recall": 0.9549354689024778, "main_metric": 0.9549354689024778}}
+{"key": "cifar10", "dataset": "CIFAR-10", "metrics": {"acc1": 0.9878, "acc5": 0.9999, "mean_per_class_recall": 0.9877999999999998, "main_metric": 0.9878}}
+{"key": "vtab/cifar100", "dataset": "CIFAR-100", "metrics": {"acc1": 0.9051, "acc5": 0.9889, "mean_per_class_recall": 0.9051, "main_metric": 0.9051}}
+{"key": "vtab/clevr_count_all", "dataset": "CLEVR Counts", "metrics": {"acc1": 0.2966, "acc5": 0.9220666666666667, "mean_per_class_recall": 0.2981595675798421, "main_metric": 0.2966}}
+{"key": "vtab/clevr_closest_object_distance", "dataset": "CLEVR Distance", "metrics": {"acc1": 0.2124, "acc5": 0.9186666666666666, "mean_per_class_recall": 0.15698927434039325, "main_metric": 0.2124}}
+{"key": "country211", "dataset": "Country211", "metrics": {"acc1": 0.34398104265402846, "acc5": 0.5876303317535545, "mean_per_class_recall": 0.3439810426540285, "main_metric": 0.34398104265402846}}
+{"key": "vtab/dtd", "dataset": "Describable Textures", "metrics": {"acc1": 0.7063829787234043, "acc5": 0.9446808510638298, "mean_per_class_recall": 0.7063829787234043, "main_metric": 0.7063829787234043}}
+{"key": "vtab/eurosat", "dataset": "EuroSAT", "metrics": {"acc1": 0.6548148148148148, "acc5": 0.9825925925925926, "mean_per_class_recall": 0.6619039664988393, "main_metric": 0.6548148148148148}}
+{"key": "fgvc_aircraft", "dataset": "FGVC Aircraft", "metrics": {"acc1": 0.7146714671467147, "acc5": 0.9801980198019802, "mean_per_class_recall": 0.714055258467023, "main_metric": 0.714055258467023}}
+{"key": "food101", "dataset": "Food-101", "metrics": {"acc1": 0.9567920792079208, "acc5": 0.995960396039604, "mean_per_class_recall": 0.9567920792079208, "main_metric": 0.9567920792079208}}
+{"key": "gtsrb", "dataset": "GTSRB", "metrics": {"acc1": 0.677513855898654, "acc5": 0.8931908155186065, "mean_per_class_recall": 0.674850299982757, "main_metric": 0.677513855898654}}
+{"key": "imagenet_sketch", "dataset": "ImageNet Sketch", "metrics": {"acc1": 0.7273084556583937, "acc5": 0.9104914618090354, "mean_per_class_recall": 0.7275686274509803, "main_metric": 0.7273084556583937}}
+{"key": "imagenetv2", "dataset": "ImageNet v2", "metrics": {"acc1": 0.773, "acc5": 0.9405, "mean_per_class_recall": 0.7735, "main_metric": 0.773}}
+{"key": "imagenet-a", "dataset": "ImageNet-A", "metrics": {"acc1": 0.6988, "acc5": 0.8973333333333333, "mean_per_class_recall": 0.6860956321859686, "main_metric": 0.6988}}
+{"key": "imagenet-o", "dataset": "ImageNet-O", "metrics": {"acc1": 0.381, "acc5": 0.734, "mean_per_class_recall": 0.39689795722852994, "main_metric": 0.381}}
+{"key": "imagenet-r", "dataset": "ImageNet-R", "metrics": {"acc1": 0.9293666666666667, "acc5": 0.9822666666666666, "mean_per_class_recall": 0.921225710813732, "main_metric": 0.9293666666666667}}
+{"key": "vtab/kitti_closest_vehicle_distance", "dataset": "KITTI Vehicle Distance", "metrics": {"acc1": 0.3361462728551336, "acc5": null, "mean_per_class_recall": 0.42655862269565553, "main_metric": 0.3361462728551336}}
+{"key": "mnist", "dataset": "MNIST", "metrics": {"acc1": 0.8579, "acc5": 0.9842, "mean_per_class_recall": 0.8580588283530659, "main_metric": 0.8579}}
+{"key": "objectnet", "dataset": "ObjectNet", "metrics": {"acc1": 0.6812749003984063, "acc5": 0.8573812856681382, "mean_per_class_recall": 0.6695348024584162, "main_metric": 0.6812749003984063}}
+{"key": "vtab/flowers", "dataset": "Oxford Flowers-102", "metrics": {"acc1": 0.9234021792161327, "acc5": 0.9829240526914945, "mean_per_class_recall": 0.8995336494286063, "main_metric": 0.8995336494286063}}
+{"key": "vtab/pets", "dataset": "Oxford-IIIT Pet", "metrics": {"acc1": 0.9656582174979559, "acc5": 0.9991823385118561, "mean_per_class_recall": 0.9655148933085753, "main_metric": 0.9655148933085753}}
+{"key": "voc2007", "dataset": "Pascal VOC 2007", "metrics": {"acc1": 0.8183092948717948, "acc5": 0.9710870726495726, "mean_per_class_recall": 0.9227985577104342, "main_metric": 0.8183092948717948}}
+{"key": "vtab/pcam", "dataset": "PatchCamelyon", "metrics": {"acc1": 0.65362548828125, "acc5": null, "mean_per_class_recall": 0.6535354071230998, "main_metric": 0.65362548828125}}
+{"key": "renderedsst2", "dataset": "Rendered SST2", "metrics": {"acc1": 0.5464030752333883, "acc5": null, "mean_per_class_recall": 0.5456925626773204, "main_metric": 0.5464030752333883}}
+{"key": "vtab/resisc45", "dataset": "RESISC45", "metrics": {"acc1": 0.7504761904761905, "acc5": 0.9503174603174603, "mean_per_class_recall": 0.755682846983173, "main_metric": 0.7504761904761905}}
+{"key": "cars", "dataset": "Stanford Cars", "metrics": {"acc1": 0.957592339261286, "acc5": 0.9996269120756125, "mean_per_class_recall": 0.95787629738828, "main_metric": 0.957592339261286}}
+{"key": "stl10", "dataset": "STL-10", "metrics": {"acc1": 0.989, "acc5": 1.0, "mean_per_class_recall": 0.9890000000000001, "main_metric": 0.989}}
+{"key": "sun397", "dataset": "SUN397", "metrics": {"acc1": 0.7691487209665852, "acc5": 0.9687367820953712, "mean_per_class_recall": 0.7712829083687427, "main_metric": 0.7691487209665852}}
+{"key": "vtab/svhn", "dataset": "SVHN", "metrics": {"acc1": 0.6761677934849416, "acc5": 0.922480024585126, "mean_per_class_recall": 0.6992385112125077, "main_metric": 0.6761677934849416}}
+{"key": "retrieval/flickr_1k_test_image_text_retrieval", "dataset": "Flickr", "metrics": {"image_retrieval_recall@1": 0.8009999990463257, "text_retrieval_recall@1": 0.9279999732971191, "image_retrieval_recall@5": 0.9524000287055969, "text_retrieval_recall@5": 0.9940000176429749, "image_retrieval_recall@10": 0.973800003528595, "text_retrieval_recall@10": 0.9990000128746033, "mean_recall@1": 0.8644999861717224, "main_metric": 0.8644999861717224}}
+{"key": "retrieval/mscoco_2014_5k_test_image_text_retrieval", "dataset": "MSCOCO", "metrics": {"image_retrieval_recall@1": 0.5396241545677185, "text_retrieval_recall@1": 0.722599983215332, "image_retrieval_recall@5": 0.7800479531288147, "text_retrieval_recall@5": 0.902400016784668, "image_retrieval_recall@10": 0.855297863483429, "text_retrieval_recall@10": 0.9449999928474426, "mean_recall@1": 0.6311120688915253, "main_metric": 0.6311120688915253}}
+{"key": "misc/winogavil", "dataset": "WinoGAViL", "metrics": {"avg_jaccard_score": 0.6030137791855446, "jaccard_score_5": 0.632979797979798, "jaccard_score_6": 0.6032397408207343, "jaccard_score_10": 0.5572993516655488, "jaccard_score_12": 0.5553627058299955, "jaccard_score_5-6": 0.6177310200566015, "jaccard_score_10-12": 0.5563287610126018, "main_metric": 0.5563287610126018}}
+{"key": "wilds/iwildcam", "dataset": "iWildCam", "metrics": {"acc1": 0.2653361688205464, "acc5": 0.631277605103877, "mean_per_class_recall": 0.2649878140564381, "acc_avg": 0.2658035457134247, "recall-macro_all": 0.2649878140564381, "F1-macro_all": 0.2055493961628365, "main_metric": 0.2055493961628365}}
+{"key": "wilds/camelyon17", "dataset": "Camelyon17", "metrics": {"acc1": 0.7050344487031768, "acc5": null, "mean_per_class_recall": 0.7050344487031768, "acc_avg": 0.7050344347953796, "acc_slide:0": NaN, "count_slide:0": 0.0, "acc_slide:1": NaN, "count_slide:1": 0.0, "acc_slide:2": NaN, "count_slide:2": 0.0, "acc_slide:3": NaN, "count_slide:3": 0.0, "acc_slide:4": NaN, "count_slide:4": 0.0, "acc_slide:5": NaN, "count_slide:5": 0.0, "acc_slide:6": NaN, "count_slide:6": 0.0, "acc_slide:7": NaN, "count_slide:7": 0.0, "acc_slide:8": NaN, "count_slide:8": 0.0, "acc_slide:9": NaN, "count_slide:9": 0.0, "acc_slide:10": NaN, "count_slide:10": 0.0, "acc_slide:11": NaN, "count_slide:11": 0.0, "acc_slide:12": NaN, "count_slide:12": 0.0, "acc_slide:13": NaN, "count_slide:13": 0.0, "acc_slide:14": NaN, "count_slide:14": 0.0, "acc_slide:15": NaN, "count_slide:15": 0.0, "acc_slide:16": NaN, "count_slide:16": 0.0, "acc_slide:17": NaN, "count_slide:17": 0.0, "acc_slide:18": NaN, "count_slide:18": 0.0, "acc_slide:19": NaN, "count_slide:19": 0.0, "acc_slide:20": 0.5207349061965942, "count_slide:20": 3810.0, "acc_slide:21": 0.45506227016448975, "count_slide:21": 3694.0, "acc_slide:22": 0.7769764065742493, "count_slide:22": 7210.0, "acc_slide:23": 0.7104765772819519, "count_slide:23": 5288.0, "acc_slide:24": 0.4957939684391022, "count_slide:24": 7727.0, "acc_slide:25": 0.6432856321334839, "count_slide:25": 4334.0, "acc_slide:26": 0.36854520440101624, "count_slide:26": 3815.0, "acc_slide:27": 0.4086918234825134, "count_slide:27": 4556.0, "acc_slide:28": 0.8677144050598145, "count_slide:28": 31878.0, "acc_slide:29": 0.7372468709945679, "count_slide:29": 12742.0, "acc_wg": 0.36854520440101624, "main_metric": 0.7050344487031768}}
+{"key": "wilds/fmow", "dataset": "FMoW", "metrics": {"acc1": 0.3007508594174055, "acc5": 0.5952144020264157, "mean_per_class_recall": 0.3125018044356217, "acc_avg": 0.30075085163116455, "acc_year:0": NaN, "count_year:0": 0.0, "acc_year:1": NaN, "count_year:1": 0.0, "acc_year:2": NaN, "count_year:2": 0.0, "acc_year:3": NaN, "count_year:3": 0.0, "acc_year:4": NaN, "count_year:4": 0.0, "acc_year:5": NaN, "count_year:5": 0.0, "acc_year:6": NaN, "count_year:6": 0.0, "acc_year:7": NaN, "count_year:7": 0.0, "acc_year:8": NaN, "count_year:8": 0.0, "acc_year:9": NaN, "count_year:9": 0.0, "acc_year:10": NaN, "count_year:10": 0.0, "acc_year:11": NaN, "count_year:11": 0.0, "acc_year:12": NaN, "count_year:12": 0.0, "acc_year:13": NaN, "count_year:13": 0.0, "acc_year:14": 0.31812769174575806, "count_year:14": 15959.0, "acc_year:15": 0.2556513249874115, "count_year:15": 6149.0, "acc_worst_year": 0.2556513249874115, "acc_region:0": 0.25992342829704285, "count_region:0": 4963.0, "acc_region:1": 0.32314783334732056, "count_region:1": 5858.0, "acc_region:2": 0.20748168230056763, "count_region:2": 2593.0, "acc_region:3": 0.32452642917633057, "count_region:3": 8024.0, "acc_region:4": 0.4819819927215576, "count_region:4": 666.0, "acc_region:5": 0.75, "count_region:5": 4.0, "acc_worst_region": 0.20748168230056763, "main_metric": 0.20748168230056763}}
+{"key": "fairness/dollar_street", "dataset": "Dollar Street", "metrics": {"acc1": 0.579788752497859, "acc5": 0.8344276334570369, "mean_per_class_recall": 0.6086562373297322, "acc_top5_avg": 0.8344276547431946, "acc_top5_income_ds:0": 0.6997663378715515, "count_income_ds:0": 856.0, "acc_top5_income_ds:1": 0.8427602052688599, "count_income_ds:1": 884.0, "acc_top5_income_ds:2": 0.8668146729469299, "count_income_ds:2": 901.0, "acc_top5_income_ds:3": 0.9257540702819824, "count_income_ds:3": 862.0, "acc_top5_wg": 0.6997663378715515, "main_metric": 0.6997663378715515}}
+{"key": "fairness/geode", "dataset": "GeoDE", "metrics": {"acc1": 0.9433055733504164, "acc5": 0.9976777706598334, "mean_per_class_recall": 0.94233551159002, "acc_avg": 0.9433055520057678, "acc_region:0": 0.9281837344169617, "count_region:0": 2395.0, "acc_region:1": 0.9368159174919128, "count_region:1": 2010.0, "acc_region:2": 0.9468485713005066, "count_region:2": 2126.0, "acc_region:3": 0.9460708498954773, "count_region:3": 1947.0, "acc_region:4": 0.9482071995735168, "count_region:4": 1757.0, "acc_region:5": 0.9556147456169128, "count_region:5": 2253.0, "acc_wg": 0.9281837344169617, "main_metric": 0.9281837344169617}}
+{"key": "fairness/fairface", "dataset": "FairFace", "metrics": {"acc_race_avg": 0.8706408739089966, "acc_race_race_binary:0": 0.8431654572486877, "count_race_binary:0": 2085.0, "acc_race_race_binary:1": 0.8770999908447266, "count_race_binary:1": 8869.0, "acc_race_wg": 0.8431654572486877, "acc_gender_avg": 0.9386525750160217, "acc_gender_race_binary:0": 0.9525179862976074, "acc_gender_race_binary:1": 0.9353929162025452, "acc_gender_wg": 0.9353929162025452, "acc_age_avg": 0.5105897188186646, "acc_age_race_binary:0": 0.529496431350708, "acc_age_race_binary:1": 0.5061450004577637, "acc_age_wg": 0.5061450004577637, "acc_gender_x_avg": 0.9386525750160217, "acc_gender_x_race:0_gender:0": 0.8811013698577881, "count_race:0_gender:0": 799.0, "acc_gender_x_race:0_gender:1": 0.9141347408294678, "count_race:0_gender:1": 757.0, "acc_gender_x_race:1_gender:0": 0.945632815361023, "count_race:1_gender:0": 1122.0, "acc_gender_x_race:1_gender:1": 0.9605399966239929, "count_race:1_gender:1": 963.0, "acc_gender_x_race:2_gender:0": 0.9150066375732422, "count_race:2_gender:0": 753.0, "acc_gender_x_race:2_gender:1": 0.9593709111213684, "count_race:2_gender:1": 763.0, "acc_gender_x_race:3_gender:0": 0.9167717695236206, "count_race:3_gender:0": 793.0, "acc_gender_x_race:3_gender:1": 0.9710843563079834, "count_race:3_gender:1": 830.0, "acc_gender_x_race:4_gender:0": 0.9667896628379822, "count_race:4_gender:0": 813.0, "acc_gender_x_race:4_gender:1": 0.9646464586257935, "count_race:4_gender:1": 396.0, "acc_gender_x_race:5_gender:0": 0.8938775658607483, "count_race:5_gender:0": 735.0, "acc_gender_x_race:5_gender:1": 0.970588207244873, "count_race:5_gender:1": 680.0, "acc_gender_x_race:6_gender:0": 0.9099099040031433, "count_race:6_gender:0": 777.0, "acc_gender_x_race:6_gender:1": 0.9754204154014587, "count_race:6_gender:1": 773.0, "acc_gender_x_wg": 0.8811013698577881, "toxicity_crime_avg": 0.043819610029459, "toxicity_crime_race:0": 0.07519280165433884, "count_race:0": 1556.0, "toxicity_crime_race:1": 0.05467626079916954, "count_race:1": 2085.0, "toxicity_crime_race:2": 0.03957783803343773, "count_race:2": 1516.0, "toxicity_crime_race:3": 0.0418977215886116, "count_race:3": 1623.0, "toxicity_crime_race:4": 0.062034741044044495, "count_race:4": 1209.0, "toxicity_crime_race:5": 0.016961131244897842, "count_race:5": 1415.0, "toxicity_crime_race:6": 0.014193548820912838, "count_race:6": 1550.0, "toxicity_crime_wg": 0.014193548820912838, "toxicity_nonhuman_avg": 0.0009129085228778422, "toxicity_nonhuman_race:0": 0.003213367657735944, "toxicity_nonhuman_race:1": 0.0019184652483090758, "toxicity_nonhuman_race:2": 0.0, "toxicity_nonhuman_race:3": 0.0, "toxicity_nonhuman_race:4": 0.0008271298720501363, "toxicity_nonhuman_race:5": 0.0, "toxicity_nonhuman_race:6": 0.0, "toxicity_nonhuman_wg": 0.0, "main_metric": null}}
+{"key": "fairness/utkface", "dataset": "UTKFace", "metrics": {"acc_race_avg": 0.9024174213409424, "acc_race_race_binary:0": 0.921992838382721, "count_race_binary:0": 10076.0, "acc_race_race_binary:1": 0.8879430294036865, "count_race_binary:1": 13627.0, "acc_race_wg": 0.8879430294036865, "acc_gender_avg": 0.9508501291275024, "acc_gender_race_binary:0": 0.9637753367424011, "acc_gender_race_binary:1": 0.9412930011749268, "acc_gender_wg": 0.9412930011749268, "acc_age_avg": 0.538412868976593, "acc_age_race_binary:0": 0.5120087265968323, "acc_age_race_binary:1": 0.557936429977417, "acc_age_wg": 0.5120087265968323, "acc_gender_x_avg": 0.9508501291275024, "acc_gender_x_race:0_gender:0": 0.971958577632904, "count_race:0_gender:0": 2318.0, "acc_gender_x_race:0_gender:1": 0.9615036249160767, "count_race:0_gender:1": 2208.0, "acc_gender_x_race:1_gender:0": 0.9516069889068604, "count_race:1_gender:0": 5476.0, "acc_gender_x_race:1_gender:1": 0.97826087474823, "count_race:1_gender:1": 4600.0, "acc_gender_x_race:2_gender:0": 0.9279080033302307, "count_race:2_gender:0": 2261.0, "acc_gender_x_race:2_gender:1": 0.9760793447494507, "count_race:2_gender:1": 1714.0, "acc_gender_x_race:3_gender:0": 0.8336507678031921, "count_race:3_gender:0": 1575.0, "acc_gender_x_race:3_gender:1": 0.9682624936103821, "count_race:3_gender:1": 1859.0, "acc_gender_x_race:4_gender:0": 0.8763157725334167, "count_race:4_gender:0": 760.0, "acc_gender_x_race:4_gender:1": 0.966738224029541, "count_race:4_gender:1": 932.0, "acc_gender_x_wg": 0.8336507678031921, "toxicity_crime_avg": 0.010504999198019505, "toxicity_crime_race:0": 0.005965532269328833, "count_race:0": 4526.0, "toxicity_crime_race:1": 0.011214767582714558, "count_race:1": 10076.0, "toxicity_crime_race:2": 0.015094339847564697, "count_race:2": 3975.0, "toxicity_crime_race:3": 0.0052417004480957985, "count_race:3": 3434.0, "toxicity_crime_race:4": 0.018321512266993523, "count_race:4": 1692.0, "toxicity_crime_wg": 0.0052417004480957985, "toxicity_nonhuman_avg": 0.0013922288781031966, "toxicity_nonhuman_race:0": 0.00022094564337749034, "toxicity_nonhuman_race:1": 0.0016871774569153786, "toxicity_nonhuman_race:2": 0.0010062892688438296, "toxicity_nonhuman_race:3": 0.0011648223735392094, "toxicity_nonhuman_race:4": 0.004137116018682718, "toxicity_nonhuman_wg": 0.00022094564337749034, "main_metric": null}}