Buckets:

Pranav2748's picture
download
raw
12 kB
{
"table": {
"S1@1": {
"reasoning": 0.6406833333333333,
"lookup": 0.7396,
"other": 0.61495,
"core17": 0.6606941176470588,
"core14": 0.6405142857142856,
"ece_r": 0.16933333333333334,
"ece_l": 0.11779999999999999
},
"E1@1": {
"reasoning": 0.6498666666666667,
"lookup": 0.7410399999999999,
"other": 0.605,
"core17": 0.6608470588235293,
"core14": 0.641457142857143,
"ece_r": 0.16533333333333336,
"ece_l": 0.13491999999999998
},
"E2@1": {
"reasoning": 0.6467333333333333,
"lookup": 0.7444600000000001,
"other": 0.5982,
"core17": 0.6583470588235294,
"core14": 0.6393285714285714,
"ece_r": 0.1665333333333333,
"ece_l": 0.13146
},
"E2@2": {
"reasoning": 0.6464666666666667,
"lookup": 0.74448,
"other": 0.5975333333333334,
"core17": 0.6580235294117648,
"core14": 0.6384142857142857,
"ece_r": 0.16528333333333334,
"ece_l": 0.12835999999999997
},
"E2@4": {
"reasoning": 0.6481666666666667,
"lookup": 0.74434,
"other": 0.5982,
"core17": 0.6588176470588236,
"core14": 0.6396642857142857,
"ece_r": 0.16638333333333333,
"ece_l": 0.12762
},
"E2@8": {
"reasoning": 0.6476000000000001,
"lookup": 0.74354,
"other": 0.5994,
"core17": 0.6588058823529411,
"core14": 0.6396928571428572,
"ece_r": 0.16634999999999997,
"ece_l": 0.12882
},
"E3@1": {
"reasoning": 0.6450666666666667,
"lookup": 0.75312,
"other": 0.5956333333333333,
"core17": 0.6594000000000001,
"core14": 0.6401785714285715,
"ece_r": 0.16726666666666667,
"ece_l": 0.12766
},
"E3@2": {
"reasoning": 0.6408166666666667,
"lookup": 0.7527600000000001,
"other": 0.5948666666666667,
"core17": 0.6575235294117647,
"core14": 0.6376142857142858,
"ece_r": 0.16968333333333332,
"ece_l": 0.128
},
"E3@4": {
"reasoning": 0.64395,
"lookup": 0.7541399999999999,
"other": 0.59545,
"core17": 0.6592411764705881,
"core14": 0.6394142857142857,
"ece_r": 0.16671666666666665,
"ece_l": 0.12678
},
"E3@8": {
"reasoning": 0.6447,
"lookup": 0.75344,
"other": 0.5963166666666666,
"core17": 0.6596058823529412,
"core14": 0.6401428571428571,
"ece_r": 0.17145,
"ece_l": 0.1268
}
},
"tests": [
{
"diff": -0.02699730914900167,
"lo": -0.36332414447067657,
"hi": 0.29900863107664405,
"a": 64.6472722005679,
"b": 64.6742695097169,
"n_suites": 6,
"name": "H1 E2 K=2 vs K=1",
"group": "reasoning",
"arm_a": "E2@2",
"arm_b": "E2@1"
},
{
"diff": 0.004137931034475795,
"lo": -0.3291954022988497,
"hi": 0.33241379310344765,
"a": 74.44873563218391,
"b": 74.44459770114943,
"n_suites": 5,
"name": "H1 E2 K=2 vs K=1",
"group": "lookup",
"arm_a": "E2@2",
"arm_b": "E2@1"
},
{
"diff": 0.14219617683347563,
"lo": -0.17713875633987694,
"hi": 0.47481730443776826,
"a": 64.81646568655037,
"b": 64.6742695097169,
"n_suites": 6,
"name": "H1 E2 K=4 vs K=1",
"group": "reasoning",
"arm_a": "E2@4",
"arm_b": "E2@1",
"verdict": "not met"
},
{
"diff": -0.00919540229885607,
"lo": -0.34505747126437036,
"hi": 0.3241379310344806,
"a": 74.43540229885058,
"b": 74.44459770114943,
"n_suites": 5,
"name": "H1 E2 K=4 vs K=1",
"group": "lookup",
"arm_a": "E2@4",
"arm_b": "E2@1",
"verdict": "ok (>= -1.0)"
},
{
"diff": 0.08439235366695108,
"lo": -0.2688539974959878,
"hi": 0.43259550598698837,
"a": 64.75866186338385,
"b": 64.6742695097169,
"n_suites": 6,
"name": "H1 E2 K=8 vs K=1",
"group": "reasoning",
"arm_a": "E2@8",
"arm_b": "E2@1",
"verdict": "not met"
},
{
"diff": -0.08919540229884726,
"lo": -0.38574712643677955,
"hi": 0.1724137931034475,
"a": 74.35540229885058,
"b": 74.44459770114943,
"n_suites": 5,
"name": "H1 E2 K=8 vs K=1",
"group": "lookup",
"arm_a": "E2@8",
"arm_b": "E2@1",
"verdict": "ok (>= -1.0)"
},
{
"diff": -0.42427117061569763,
"lo": -1.037234941509671,
"hi": 0.06575557999000761,
"a": 64.0820390344333,
"b": 64.50631020504899,
"n_suites": 6,
"name": "H1 E3 K=2 vs K=1",
"group": "reasoning",
"arm_a": "E3@2",
"arm_b": "E3@1"
},
{
"diff": -0.03494252873561532,
"lo": -0.26482758620689717,
"hi": 0.18252873563218586,
"a": 75.27678160919541,
"b": 75.31172413793102,
"n_suites": 5,
"name": "H1 E3 K=2 vs K=1",
"group": "lookup",
"arm_a": "E3@2",
"arm_b": "E3@1"
},
{
"diff": -0.1122076921301951,
"lo": -0.4418432225787224,
"hi": 0.19463898096527454,
"a": 64.39410251291879,
"b": 64.50631020504899,
"n_suites": 6,
"name": "H1 E3 K=4 vs K=1",
"group": "reasoning",
"arm_a": "E3@4",
"arm_b": "E3@1",
"verdict": "not met"
},
{
"diff": 0.10252873563220133,
"lo": -0.1724137931034475,
"hi": 0.41241379310344767,
"a": 75.41425287356323,
"b": 75.31172413793102,
"n_suites": 5,
"name": "H1 E3 K=4 vs K=1",
"group": "lookup",
"arm_a": "E3@4",
"arm_b": "E3@1",
"verdict": "ok (>= -1.0)"
},
{
"diff": -0.036533705704044905,
"lo": -0.5793228220323845,
"hi": 0.590335763159028,
"a": 64.46977649934495,
"b": 64.50631020504899,
"n_suites": 6,
"name": "H1 E3 K=8 vs K=1",
"group": "reasoning",
"arm_a": "E3@8",
"arm_b": "E3@1",
"verdict": "not met"
},
{
"diff": 0.03172413793105511,
"lo": -0.26482758620689717,
"hi": 0.3416091954022993,
"a": 75.34344827586207,
"b": 75.31172413793102,
"n_suites": 5,
"name": "H1 E3 K=8 vs K=1",
"group": "lookup",
"arm_a": "E3@8",
"arm_b": "E3@1",
"verdict": "ok (>= -1.0)"
},
{
"diff": -0.3114396421644905,
"lo": -1.5090417705336712,
"hi": 0.9148080381266052,
"a": 64.6742695097169,
"b": 64.9857091518814,
"n_suites": 6,
"name": "H2 E2(best K) vs E1",
"group": "reasoning",
"arm_a": "E2@1",
"arm_b": "E1@1",
"verdict": "not supported"
},
{
"diff": -0.5922304752836061,
"lo": -1.8443107151265083,
"hi": 0.6046214022024817,
"a": 64.0820390344333,
"b": 64.6742695097169,
"n_suites": 6,
"name": "H3 E3(best K) vs E2(best K)",
"group": "reasoning",
"arm_a": "E3@2",
"arm_b": "E2@1",
"verdict": "not supported"
},
{
"diff": 0.9184877332396368,
"lo": -0.5860637261446555,
"hi": 2.4683407881110853,
"a": 64.9857091518814,
"b": 64.06722141864175,
"n_suites": 6,
"name": "E1 vs S1",
"group": "reasoning",
"arm_a": "E1@1",
"arm_b": "S1@1"
},
{
"diff": -0.3114396421644905,
"lo": -1.5090417705336712,
"hi": 0.9148080381266052,
"a": 64.6742695097169,
"b": 64.9857091518814,
"n_suites": 6,
"name": "slot cost: E2@1 vs E1",
"group": "reasoning",
"arm_a": "E2@1",
"arm_b": "E1@1"
},
{
"diff": -0.9036701174480966,
"lo": -2.2529662270835127,
"hi": 0.4068849333645518,
"a": 64.0820390344333,
"b": 64.9857091518814,
"n_suites": 6,
"name": "E3(best) vs E1",
"group": "reasoning",
"arm_a": "E3@2",
"arm_b": "E1@1"
},
{
"diff": 0.14528735632183265,
"lo": -1.380701149425287,
"hi": 1.6528850574712646,
"a": 74.1048275862069,
"b": 73.95954022988506,
"n_suites": 5,
"name": "E1 vs S1",
"group": "lookup",
"arm_a": "E1@1",
"arm_b": "S1@1"
},
{
"diff": 0.33977011494252807,
"lo": -0.5918045977011505,
"hi": 1.286896551724137,
"a": 74.44459770114943,
"b": 74.1048275862069,
"n_suites": 5,
"name": "slot cost: E2@1 vs E1",
"group": "lookup",
"arm_a": "E2@1",
"arm_b": "E1@1"
},
{
"diff": 1.1719540229885084,
"lo": 0.3121839080459776,
"hi": 2.044160919540233,
"a": 75.27678160919541,
"b": 74.1048275862069,
"n_suites": 5,
"name": "E3(best) vs E1",
"group": "lookup",
"arm_a": "E3@2",
"arm_b": "E1@1"
},
{
"diff": 0.015743646394750233,
"lo": -0.7780318058700959,
"hi": 0.8197626966598804,
"a": 66.08475224574127,
"b": 66.06900859934652,
"n_suites": 17,
"name": "E1 vs S1",
"group": "core17",
"arm_a": "E1@1",
"arm_b": "S1@1"
},
{
"diff": -0.24982574538372493,
"lo": -0.8424906248279496,
"hi": 0.3572883101773978,
"a": 65.83492650035755,
"b": 66.08475224574127,
"n_suites": 17,
"name": "slot cost: E2@1 vs E1",
"group": "core17",
"arm_a": "E2@1",
"arm_b": "E1@1"
},
{
"diff": -0.33218103382520736,
"lo": -0.9379607641375027,
"hi": 0.282567860615002,
"a": 65.75257121191606,
"b": 66.08475224574127,
"n_suites": 17,
"name": "E3(best) vs E1",
"group": "core17",
"arm_a": "E3@2",
"arm_b": "E1@1"
},
{
"diff": -0.032508439813705436,
"lo": -0.3646371725295938,
"hi": 0.2987397510798284,
"a": 61.79066179458904,
"b": 61.823170234402745,
"n_suites": 5,
"name": "sensitivity E2 K=8 vs K=1",
"group": "reasoning_no_mnli",
"arm_a": "E2@8",
"arm_b": "E2@1"
},
{
"diff": -0.4406172027044186,
"lo": -1.8293572393645052,
"hi": 0.9341674667497024,
"a": 61.823170234402745,
"b": 62.26378743710717,
"n_suites": 5,
"name": "sensitivity E2(best) vs E1",
"group": "reasoning_no_mnli",
"arm_a": "E2@1",
"arm_b": "E1@1"
},
{
"diff": -0.0438404468448339,
"lo": -0.6872245477978947,
"hi": 0.6998517803490172,
"a": 61.77844751827749,
"b": 61.82228796512233,
"n_suites": 5,
"name": "sensitivity E3 K=8 vs K=1",
"group": "reasoning_no_mnli",
"arm_a": "E3@8",
"arm_b": "E3@1"
},
{
"diff": 0.0356824787358323,
"lo": -0.15545721817280717,
"hi": 0.2244861926166043,
"a": 63.968824237292324,
"b": 63.93314175855649,
"n_suites": 14,
"name": "sensitivity E2 K=8 vs K=1",
"group": "core14",
"arm_a": "E2@8",
"arm_b": "E2@1"
},
{
"diff": -0.21296327371848056,
"lo": -0.9012121804347,
"hi": 0.47911302752026863,
"a": 63.93314175855649,
"b": 64.14610503227497,
"n_suites": 14,
"name": "sensitivity E2(best) vs E1",
"group": "core14",
"arm_a": "E2@1",
"arm_b": "E1@1"
},
{
"diff": -0.00506766297547756,
"lo": -0.2897248713392722,
"hi": 0.3125790056706852,
"a": 64.01324616246264,
"b": 64.01831382543811,
"n_suites": 14,
"name": "sensitivity E3 K=8 vs K=1",
"group": "core14",
"arm_a": "E3@8",
"arm_b": "E3@1"
}
],
"best_k": {
"S1": 1,
"E1": 1,
"E2": 1,
"E3": 2
},
"dev_acc": {
"S1": {},
"E1": {},
"E2": {
"1": 0.9147368421052632,
"2": 0.9136842105263158,
"3": 0.9136842105263158,
"4": 0.9136842105263158,
"5": 0.9136842105263158,
"6": 0.9147368421052632,
"7": 0.9136842105263158,
"8": 0.9136842105263158
},
"E3": {
"1": 0.9136842105263158,
"2": 0.9147368421052632,
"3": 0.9147368421052632,
"4": 0.9147368421052632,
"5": 0.9136842105263158,
"6": 0.9147368421052632,
"7": 0.9136842105263158,
"8": 0.9147368421052632
}
},
"adaptive": {
"E2": {
"0.001": [
4.515272835112693,
0.6294483985765125
],
"0.003": [
3.9443950177935942,
0.6294483985765125
],
"0.01": [
2.997479240806643,
0.6298932384341637
],
"0.03": [
2.07488137603796,
0.6297449584816133
],
"fixed": {
"1": 0.6295966785290629,
"2": 0.6291518386714117,
"3": 0.6295966785290629,
"4": 0.6298932384341637,
"5": 0.630338078291815,
"6": 0.6294483985765125,
"7": 0.6315243179122183,
"8": 0.6297449584816133
}
},
"E3": {
"0.001": [
4.460409252669039,
0.6356761565836299
],
"0.003": [
3.9304567022538555,
0.6358244365361803
],
"0.01": [
2.9529952550415186,
0.6361209964412812
],
"0.03": [
2.0440391459074734,
0.6353795966785291
],
"fixed": {
"1": 0.6352313167259787,
"2": 0.6356761565836299,
"3": 0.6367141162514828,
"4": 0.6361209964412812,
"5": 0.6359727164887308,
"6": 0.6343416370106761,
"7": 0.6361209964412812,
"8": 0.6343416370106761
}
}
}
}

Xet Storage Details

Size:
12 kB
·
Xet hash:
f5aad50c127290ca6b374f02492bd5ca1a5d66133bc96eb2ec6227b967276359

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.