promotion's picture
Upload summaries/summary.json with huggingface_hub
65d6249 verified
Raw
History Blame Contribute Delete
11.7 kB
{
"seeds": [
1004,
1005,
1006,
1007,
1008
],
"split_hash": "2e38193a038079d66cfb5d17dc149af12a9f63a773a2e48ee21d04bb006250fc",
"data_sha256": "122dfd62dcf8d46ece390ed23335e69cac0d3db8e91479c162d5e4186acdbe0d",
"n_eval_tasks": 88,
"n_preference_decisions": 968,
"verifier_rmse": {
"Egc": {
"mean": 0.682365035610178,
"sd": 0.023200213429402764,
"ci95": 0.028802251598823818
},
"Egb": {
"mean": 0.7795461366589093,
"sd": 0.03702590414781171,
"ci95": 0.04596636191232919
}
},
"summary": {
"sft": {
"hypervolume": {
"mean": 0.3263172158958249,
"sd": 0.007077638860046684,
"ci95": 0.008786640510570721
},
"mip": {
"mean": 0.5542560282390163,
"sd": 0.00958850553545619,
"ci95": 0.01190379345988773
},
"preference_regret": {
"mean": 0.03366121577648368,
"sd": 0.00958850553545623,
"ci95": 0.01190379345988778
},
"near_optimal": {
"mean": 0.7822314049586777,
"sd": 0.07295465955600312,
"ci95": 0.09057065212923908
},
"unique": {
"mean": 2.090909090909091,
"sd": 0.1421590454908727,
"ci95": 0.17648547103827913
}
},
"random": {
"hypervolume": {
"mean": 0.32798411805224303,
"sd": 0.004243042593788916,
"ci95": 0.005267588623816396
},
"mip": {
"mean": 0.5,
"sd": 0.0,
"ci95": 0.0
},
"preference_regret": {
"mean": 0.08791724401549997,
"sd": 6.206335383118182e-18,
"ci95": 7.704947790898585e-18
},
"near_optimal": {
"mean": 0.4483471074380165,
"sd": 0.015059276587926896,
"ci95": 0.018695563922357987
},
"unique": {
"mean": 4.409090909090909,
"sd": 0.2249885212866286,
"ci95": 0.2793153613290541
}
},
"greedy_verifier": {
"hypervolume": {
"mean": 0.3374837855543042,
"sd": 0.0030145483976481056,
"ci95": 0.0037424561489530685
},
"mip": {
"mean": 0.5684625263089786,
"sd": 0.002066564745402613,
"ci95": 0.002565567679946882
},
"preference_regret": {
"mean": 0.019454717706521275,
"sd": 0.002066564745402651,
"ci95": 0.0025655676799469294
},
"near_optimal": {
"mean": 0.8334710743801652,
"sd": 0.01664794442821267,
"ci95": 0.020667839349138354
},
"unique": {
"mean": 2.0113636363636362,
"sd": 0.1041494476126327,
"ci95": 0.1292978878468356
}
},
"oracle_grid": {
"hypervolume": {
"mean": 0.3547658201014365,
"sd": 0.0,
"ci95": 0.0
},
"mip": {
"mean": 0.5879172440154999,
"sd": 0.0,
"ci95": 0.0
},
"preference_regret": {
"mean": 0.0,
"sd": 0.0,
"ci95": 0.0
},
"near_optimal": {
"mean": 1.0,
"sd": 0.0,
"ci95": 0.0
},
"unique": {
"mean": 1.9772727272727273,
"sd": 0.0,
"ci95": 0.0
}
}
},
"by_direction": {
"up_up": {
"sft": {
"hypervolume": {
"mean": 0.5547866157591552,
"sd": 0.004451111549643458,
"ci95": 0.005525898937842734
},
"mip": {
"mean": 0.7173941342744271,
"sd": 0.006962489498633501,
"ci95": 0.008643686615385294
}
},
"random": {
"hypervolume": {
"mean": 0.5300234743935974,
"sd": 0.008807646321860372,
"ci95": 0.010934384122267451
},
"mip": {
"mean": 0.62319888712802,
"sd": 0.00339621218061192,
"ci95": 0.0042162783547932525
}
},
"greedy_verifier": {
"hypervolume": {
"mean": 0.5415841777575114,
"sd": 0.008233289246674151,
"ci95": 0.010221339949746493
},
"mip": {
"mean": 0.7101234331357681,
"sd": 0.004102313866773968,
"ci95": 0.005092878843020596
}
},
"oracle_grid": {
"hypervolume": {
"mean": 0.5718122839434651,
"sd": 0.0,
"ci95": 0.0
},
"mip": {
"mean": 0.7311801380469454,
"sd": 0.0,
"ci95": 0.0
}
},
"sft_minus_greedy": {
"hypervolume": {
"mean": 0.013202438001643802,
"sd": 0.011560547874820054,
"ci95": 0.01435201488658834
},
"mip": {
"mean": 0.0072707011386590635,
"sd": 0.009143332516037751,
"ci95": 0.0113511267635526
}
}
},
"up_down": {
"sft": {
"hypervolume": {
"mean": 0.26637109162862416,
"sd": 0.008435619826089943,
"ci95": 0.010472526270605242
},
"mip": {
"mean": 0.5324022327044661,
"sd": 0.004339669649482129,
"ci95": 0.005387547725821998
}
},
"random": {
"hypervolume": {
"mean": 0.2768259355647035,
"sd": 0.0035200122661316934,
"ci95": 0.004369971820672209
},
"mip": {
"mean": 0.4991439280925797,
"sd": 0.0030486857043436617,
"ci95": 0.0037848364183994494
}
},
"greedy_verifier": {
"hypervolume": {
"mean": 0.2812522324658844,
"sd": 0.003391659625414806,
"ci95": 0.004210626517123577
},
"mip": {
"mean": 0.5487054102595932,
"sd": 0.0018000664676603043,
"ci95": 0.0022347194112641747
}
},
"oracle_grid": {
"hypervolume": {
"mean": 0.29986543339069294,
"sd": 0.0,
"ci95": 0.0
},
"mip": {
"mean": 0.5622086416925245,
"sd": 0.0,
"ci95": 0.0
}
},
"sft_minus_greedy": {
"hypervolume": {
"mean": -0.014881140837260253,
"sd": 0.0057456736527104965,
"ci95": 0.007133052402887352
},
"mip": {
"mean": -0.016303177555127068,
"sd": 0.0043833494770607615,
"ci95": 0.005441774700394509
}
}
},
"down_up": {
"sft": {
"hypervolume": {
"mean": 0.26823553613576073,
"sd": 0.0136372196937986,
"ci95": 0.01693013014403694
},
"mip": {
"mean": 0.5337835686465041,
"sd": 0.01378559041706564,
"ci95": 0.01711432719525979
}
},
"random": {
"hypervolume": {
"mean": 0.273847825696121,
"sd": 0.0032118959376035605,
"ci95": 0.003987456201021654
},
"mip": {
"mean": 0.5008560719074203,
"sd": 0.0030486857043436825,
"ci95": 0.003784836418399475
}
},
"greedy_verifier": {
"hypervolume": {
"mean": 0.28263117534455195,
"sd": 0.007162604591140678,
"ci95": 0.008892122486919516
},
"mip": {
"mean": 0.5490746269413723,
"sd": 0.0033286869480678356,
"ci95": 0.004132448145949615
}
},
"oracle_grid": {
"hypervolume": {
"mean": 0.2864046084806097,
"sd": 0.0,
"ci95": 0.0
},
"mip": {
"mean": 0.5687956961246301,
"sd": 0.0,
"ci95": 0.0
}
},
"sft_minus_greedy": {
"hypervolume": {
"mean": -0.014395639208791217,
"sd": 0.01697110797142767,
"ci95": 0.021069035558283978
},
"mip": {
"mean": -0.015291058294868076,
"sd": 0.014647717733847185,
"ci95": 0.01818462803381549
}
}
},
"down_down": {
"sft": {
"hypervolume": {
"mean": 0.21587562005975972,
"sd": 0.011945547963630178,
"ci95": 0.014829978999169532
},
"mip": {
"mean": 0.43344417733066765,
"sd": 0.015954219291847732,
"ci95": 0.019806603913576
}
},
"random": {
"hypervolume": {
"mean": 0.23123923655455006,
"sd": 0.00532492595981477,
"ci95": 0.0066107088931052806
},
"mip": {
"mean": 0.3768011128719801,
"sd": 0.003396212180611927,
"ci95": 0.004216278354793261
}
},
"greedy_verifier": {
"hypervolume": {
"mean": 0.24446755664926903,
"sd": 0.002140164385024888,
"ci95": 0.0026569390522161113
},
"mip": {
"mean": 0.46594663489918126,
"sd": 0.0020302006151077918,
"ci95": 0.0025204228870719827
}
},
"oracle_grid": {
"hypervolume": {
"mean": 0.2609809545909782,
"sd": 0.0,
"ci95": 0.0
},
"mip": {
"mean": 0.48948450019789985,
"sd": 0.0,
"ci95": 0.0
}
},
"sft_minus_greedy": {
"hypervolume": {
"mean": -0.028591936589509294,
"sd": 0.012851095799986063,
"ci95": 0.01595418489050146
},
"mip": {
"mean": -0.032502457568513596,
"sd": 0.016879600284616415,
"ci95": 0.020955431973265923
}
}
}
},
"sft_minus": {
"random": {
"hypervolume": {
"mean": -0.0016669021564180487,
"sd": 0.010411980805258838,
"ci95": 0.012926109137217073
},
"mip": {
"mean": 0.05425602823901628,
"sd": 0.00958850553545619,
"ci95": 0.01190379345988773
},
"preference_regret": {
"mean": -0.054256028239016284,
"sd": 0.00958850553545623,
"ci95": 0.01190379345988778
},
"near_optimal": {
"mean": 0.3338842975206612,
"sd": 0.07947633038235787,
"ci95": 0.09866707781760457
},
"unique": {
"mean": -2.3181818181818183,
"sd": 0.2821524776803439,
"ci95": 0.35028240908687147
}
},
"greedy_verifier": {
"hypervolume": {
"mean": -0.011166569658479253,
"sd": 0.008460070908431904,
"ci95": 0.010502881432104929
},
"mip": {
"mean": -0.014206498069962437,
"sd": 0.010572809308625373,
"ci95": 0.013125772085677476
},
"preference_regret": {
"mean": 0.014206498069962404,
"sd": 0.010572809308625449,
"ci95": 0.013125772085677572
},
"near_optimal": {
"mean": -0.05123966942148759,
"sd": 0.0774607415697123,
"ci95": 0.09616479497101585
},
"unique": {
"mean": 0.0795454545454544,
"sd": 0.11220691851211084,
"ci95": 0.1393009554825347
}
}
},
"sft_relative_percent": {
"random": {
"hypervolume": {
"mean": -0.4802110660459289,
"sd": 3.1398164434122986,
"ci95": 3.897972036010412
},
"mip": {
"mean": 10.851205647803255,
"sd": 1.9177011070912375,
"ci95": 2.3807586919775456
}
},
"greedy_verifier": {
"hypervolume": {
"mean": -3.298275440887257,
"sd": 2.4788612860440433,
"ci95": 3.0774193804932795
},
"mip": {
"mean": -2.496162558744969,
"sd": 1.8505323175982593,
"ci95": 2.2973709946853575
}
}
}
}