leap-kt-bkt-1995 / results.json
Unggi's picture
leap-kt: 8 dataset(s), 184 files
e283c38 verified
Raw
History Blame Contribute Delete
11.8 kB
{
"algebra2005": {
"model_type": "bkt",
"dataset": "algebra2005",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"hardware": {
"device": "cpu",
"accelerator": "x86_64",
"torch_version": "2.9.1+cu128",
"cuda_version": "12.8",
"cpu": "x86_64",
"platform": "Linux 5.15.0-140-generic"
},
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.7649531796406145,
"auc_std": 0.00018138810432605698,
"auc_per_fold": [
0.7647731725866248,
0.7651147684364736,
0.7650929132031141,
0.7647405204603047,
0.7650445235165553
],
"acc_mean": 0.793689874139701,
"acc_std": 0.00045056140256870134,
"acc_per_fold": [
0.7937278983991787,
0.7929959314042359,
0.7935567892315297,
0.7940891288642153,
0.794079622799346
],
"f1_mean": 0.8752183408728123,
"f1_std": 0.00013855120845007133,
"f1_per_fold": [
0.8750611767821876,
0.8751605210053202,
0.8751989793865975,
0.87543775913328,
0.8752332680566755
],
"batch_size": 32,
"wall_seconds": 1269.1,
"git_commit": "7b83c7d059ee69d6991f14ee2f3ff53292321007",
"reference_auc": null
},
"assist2009": {
"model_type": "bkt",
"dataset": "assist2009",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.7171395425767376,
"auc_std": 0.0004040873007051325,
"auc_per_fold": [
0.7166202161651377,
0.7169644100187235,
0.7171444429956275,
0.7172445247084981,
0.7177241189957014
],
"acc_mean": 0.7144052577280195,
"acc_std": 0.00040766038663806603,
"acc_per_fold": [
0.7144549310305299,
0.7139008826563754,
0.7145886668449811,
0.7141301440525772,
0.7149516640556342
],
"f1_mean": 0.8051630397525027,
"f1_std": 0.0007435754053654124,
"f1_per_fold": [
0.8052536940035963,
0.8041638876901147,
0.8053626568342606,
0.8048414654823858,
0.8061934947521563
],
"wall_seconds": 616.0,
"git_commit": "7e2fc9fb6a14eb2ae671222f0accafea3f8af970",
"reference_auc": null
},
"assist2012": {
"model_type": "bkt",
"dataset": "assist2012",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"hardware": {
"device": "cpu",
"accelerator": "x86_64",
"torch_version": "2.9.1+cu128",
"cuda_version": "12.8",
"cpu": "x86_64",
"platform": "Linux 5.15.0-140-generic"
},
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.6841137421868059,
"auc_std": 0.00012984798310651126,
"auc_per_fold": [
0.6841763738317012,
0.6840025033331489,
0.6841923983575141,
0.684247893652477,
0.6839495417591879
],
"acc_mean": 0.7152205677444623,
"acc_std": 6.496011055632251e-05,
"acc_per_fold": [
0.7151938299779319,
0.7152616158649102,
0.7152371376279458,
0.7152879770431796,
0.7151222782083437
],
"f1_mean": 0.8214291675497021,
"f1_std": 6.855152476022672e-05,
"f1_per_fold": [
0.8213493523949458,
0.8214526073681203,
0.8215297651008692,
0.8213873119148363,
0.8214268009697393
],
"batch_size": 32,
"wall_seconds": 10538.2,
"git_commit": "6c6da46956d2b638366c522aca888419e8fde737",
"reference_auc": null
},
"assist2015": {
"model_type": "bkt",
"dataset": "assist2015",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.7018934294603032,
"auc_std": 0.0002145094944831597,
"auc_per_fold": [
0.7019681206054743,
0.7015503383437611,
0.7021304997518865,
0.701954226959699,
0.7018639616406949
],
"acc_mean": 0.7471327572663,
"acc_std": 0.00018225171440439572,
"acc_per_fold": [
0.7473728675391661,
0.7471283107797655,
0.7471283107797655,
0.7471727756451111,
0.7468615215876921
],
"f1_mean": 0.847172987451746,
"f1_std": 0.00016642877297870973,
"f1_per_fold": [
0.8473747599070521,
0.8472345340747307,
0.8470921426458858,
0.8472285660549719,
0.8469349345760889
],
"wall_seconds": 2159.7,
"git_commit": "7e2fc9fb6a14eb2ae671222f0accafea3f8af970",
"reference_auc": null
},
"bridge2algebra2006": {
"model_type": "bkt",
"dataset": "bridge2algebra2006",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"hardware": {
"device": "cpu",
"accelerator": "x86_64",
"torch_version": "2.9.1+cu128",
"cuda_version": "12.8",
"cpu": "x86_64",
"platform": "Linux 5.15.0-140-generic"
},
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.7460759144528948,
"auc_std": 0.0001654114628309545,
"auc_per_fold": [
0.746251535824151,
0.7460562252207086,
0.7461702746509395,
0.7458129526425306,
0.7460885839261441
],
"acc_mean": 0.8425758288428795,
"acc_std": 6.478959599033498e-05,
"acc_per_fold": [
0.8425081625860613,
0.8425026612643688,
0.8426291916632971,
0.8426099370373732,
0.8426291916632971
],
"f1_mean": 0.9119014258968315,
"f1_std": 8.089998484892467e-05,
"f1_per_fold": [
0.911841149009029,
0.9118100970646492,
0.9118956027879501,
0.9119503146115482,
0.912009966010981
],
"batch_size": 32,
"wall_seconds": 7722.8,
"git_commit": "6c6da46956d2b638366c522aca888419e8fde737",
"reference_auc": null
},
"dbe_kt22": {
"model_type": "bkt",
"dataset": "dbe_kt22",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.702593065934239,
"auc_std": 0.0004045096721064703,
"auc_per_fold": [
0.7022067734642516,
0.7021071461653698,
0.7029792708704146,
0.7028670260332756,
0.7028051131378835
],
"acc_mean": 0.7765921823684719,
"acc_std": 0.0006466073327982118,
"acc_per_fold": [
0.7771266662373624,
0.7769656771202267,
0.775645566359714,
0.7770300727670809,
0.7761929293579753
],
"f1_mean": 0.8688605839710732,
"f1_std": 0.0008185932977363335,
"f1_per_fold": [
0.8694356420703184,
0.8693339369588592,
0.8675083662914511,
0.8693667352059007,
0.8686582393288362
],
"wall_seconds": 820.2,
"git_commit": "7e2fc9fb6a14eb2ae671222f0accafea3f8af970",
"reference_auc": null
},
"ednet500": {
"model_type": "bkt",
"dataset": "ednet500",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.6204025728139329,
"auc_std": 0.0013405547684237952,
"auc_per_fold": [
0.6200531714879441,
0.6201912678255324,
0.6197063473738607,
0.6227261712350607,
0.6193359061472661
],
"acc_mean": 0.6513031161473088,
"acc_std": 0.0007848099250535699,
"acc_per_fold": [
0.6505665722379603,
0.6512747875354108,
0.6507082152974504,
0.6514164305949008,
0.6525495750708216
],
"f1_mean": 0.7769900383849989,
"f1_std": 0.0006780583905244734,
"f1_per_fold": [
0.7768430574400723,
0.7767095955015418,
0.7766304347826087,
0.7765773944620972,
0.7781897097386744
],
"wall_seconds": 406.3,
"git_commit": "7e2fc9fb6a14eb2ae671222f0accafea3f8af970",
"reference_auc": null
},
"junyi": {
"model_type": "bkt",
"dataset": "junyi",
"n_folds_completed": 5,
"n_folds_failed": 0,
"leap_kt_version": "0.1.0",
"hardware": {
"device": "cpu",
"accelerator": "x86_64",
"torch_version": "2.9.1+cu128",
"cuda_version": "12.8",
"cpu": "x86_64",
"platform": "Linux 5.15.0-140-generic"
},
"protocol": {
"test_ratio": 0.2,
"n_folds": 5,
"early_stopping_patience": 10,
"early_stopping_metric": "auc",
"max_epochs": 200,
"primary_metric": "auc",
"secondary_metrics": [
"acc",
"f1"
],
"validation_source": "held_out_fold",
"seed": 0,
"is_deviation": false,
"deviation_reason": ""
},
"auc_mean": 0.7366021648809834,
"auc_std": 5.8050454129518876e-05,
"auc_per_fold": [
0.7366164476908874,
0.7365677947547564,
0.7366085558948463,
0.7365316842624889,
0.736686341801938
],
"acc_mean": 0.7380882570297765,
"acc_std": 6.382923993238856e-05,
"acc_per_fold": [
0.7380955839903385,
0.7380406317861234,
0.7381710643168178,
0.7380112607804223,
0.7381227442751804
],
"f1_mean": 0.8313443104783366,
"f1_std": 6.106882194745403e-05,
"f1_per_fold": [
0.8313401919281179,
0.831312900623345,
0.831279714988463,
0.8314429990035614,
0.8313457458481954
],
"batch_size": 32,
"wall_seconds": 50032.3,
"git_commit": "1ad8f67a54236b2f30529f470bc0b0b8d512be68",
"reference_auc": null
}
}