Files
aituner/runs/opprof-oracle-gap/metrics.json

1027 lines
28 KiB
JSON

{
"equal_time_conservative": {
"best_static_config": "C00",
"gap": 0.0726072607260726,
"oracle_upper_rps": 16.25,
"p01_weight": 0.5,
"static_lower_rps": 15.15
},
"frontiers": {
"P01": {
"C00": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 28.0,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 26.0,
"pooled_cohort_n": 1560,
"pooled_pass_n": 1560,
"pooled_pass_rate": 1.0,
"rate_rps": 26.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 27.416666666666668,
"pooled_cohort_n": 5040,
"pooled_pass_n": 4905,
"pooled_pass_rate": 0.9732142857142857,
"rate_rps": 28.0,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 6.9,
"pooled_cohort_n": 5400,
"pooled_pass_n": 1200,
"pooled_pass_rate": 0.2222222222222222,
"rate_rps": 30.0,
"trial_feasible": [
false,
false,
false
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.45,
"pooled_cohort_n": 1920,
"pooled_pass_n": 87,
"pooled_pass_rate": 0.0453125,
"rate_rps": 32.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.4666666666666666,
"pooled_cohort_n": 2040,
"pooled_pass_n": 88,
"pooled_pass_rate": 0.043137254901960784,
"rate_rps": 34.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.35,
"pooled_cohort_n": 2160,
"pooled_pass_n": 81,
"pooled_pass_rate": 0.0375,
"rate_rps": 36.0,
"trial_feasible": [
false
],
"trials": 1
}
],
"upper_infeasible_rps": 30.0
},
"C01": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 28.0,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 26.0,
"pooled_cohort_n": 1560,
"pooled_pass_n": 1560,
"pooled_pass_rate": 1.0,
"rate_rps": 26.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 27.2,
"pooled_cohort_n": 5040,
"pooled_pass_n": 4889,
"pooled_pass_rate": 0.9700396825396825,
"rate_rps": 28.0,
"trial_feasible": [
true,
false,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 6.383333333333334,
"pooled_cohort_n": 5400,
"pooled_pass_n": 1153,
"pooled_pass_rate": 0.21351851851851852,
"rate_rps": 30.0,
"trial_feasible": [
false,
false,
false
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.4833333333333334,
"pooled_cohort_n": 1920,
"pooled_pass_n": 89,
"pooled_pass_rate": 0.04635416666666667,
"rate_rps": 32.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.5,
"pooled_cohort_n": 2040,
"pooled_pass_n": 90,
"pooled_pass_rate": 0.04411764705882353,
"rate_rps": 34.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.3666666666666667,
"pooled_cohort_n": 2160,
"pooled_pass_n": 82,
"pooled_pass_rate": 0.03796296296296296,
"rate_rps": 36.0,
"trial_feasible": [
false
],
"trials": 1
}
],
"upper_infeasible_rps": 30.0
},
"C10": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 24.0,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 24.0,
"pooled_cohort_n": 4320,
"pooled_pass_n": 4320,
"pooled_pass_rate": 1.0,
"rate_rps": 24.0,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 4680,
"pooled_pass_n": 1560,
"pooled_pass_rate": 0.3333333333333333,
"rate_rps": 26.0,
"trial_feasible": [
false,
true,
false
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1565,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 28.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1564,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 30.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1664,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 32.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1600,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 34.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1618,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 36.0,
"trial_feasible": [
false
],
"trials": 1
}
],
"upper_infeasible_rps": 26.0
},
"C11": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 24.0,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 24.0,
"pooled_cohort_n": 4320,
"pooled_pass_n": 4320,
"pooled_pass_rate": 1.0,
"rate_rps": 24.0,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 4667,
"pooled_pass_n": 1560,
"pooled_pass_rate": 0.3342618384401114,
"rate_rps": 26.0,
"trial_feasible": [
false,
true,
false
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1574,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 28.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1566,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 30.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1695,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 32.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1596,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 34.0,
"trial_feasible": [
false
],
"trials": 1
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.0,
"pooled_cohort_n": 1629,
"pooled_pass_n": 0,
"pooled_pass_rate": 0.0,
"rate_rps": 36.0,
"trial_feasible": [
false
],
"trials": 1
}
],
"upper_infeasible_rps": 26.0
}
},
"P06": {
"C00": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 2.3,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 1.4,
"pooled_cohort_n": 168,
"pooled_pass_n": 168,
"pooled_pass_rate": 1.0,
"rate_rps": 1.4,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.4666666666666666,
"pooled_cohort_n": 176,
"pooled_pass_n": 176,
"pooled_pass_rate": 1.0,
"rate_rps": 1.5,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.6,
"pooled_cohort_n": 192,
"pooled_pass_n": 192,
"pooled_pass_rate": 1.0,
"rate_rps": 1.6,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7333333333333334,
"pooled_cohort_n": 208,
"pooled_pass_n": 208,
"pooled_pass_rate": 1.0,
"rate_rps": 1.7,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7916666666666667,
"pooled_cohort_n": 216,
"pooled_pass_n": 215,
"pooled_pass_rate": 0.9953703703703703,
"rate_rps": 1.8,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.8583333333333334,
"pooled_cohort_n": 224,
"pooled_pass_n": 223,
"pooled_pass_rate": 0.9955357142857143,
"rate_rps": 1.9,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.975,
"pooled_cohort_n": 240,
"pooled_pass_n": 237,
"pooled_pass_rate": 0.9875,
"rate_rps": 2.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1083333333333334,
"pooled_cohort_n": 256,
"pooled_pass_n": 253,
"pooled_pass_rate": 0.98828125,
"rate_rps": 2.1,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1666666666666665,
"pooled_cohort_n": 264,
"pooled_pass_n": 260,
"pooled_pass_rate": 0.9848484848484849,
"rate_rps": 2.2,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.2333333333333334,
"pooled_cohort_n": 816,
"pooled_pass_n": 804,
"pooled_pass_rate": 0.9852941176470589,
"rate_rps": 2.3,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 2.275,
"pooled_cohort_n": 864,
"pooled_pass_n": 818,
"pooled_pass_rate": 0.9467592592592593,
"rate_rps": 2.4,
"trial_feasible": [
true,
false,
false
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.3583333333333334,
"pooled_cohort_n": 912,
"pooled_pass_n": 489,
"pooled_pass_rate": 0.5361842105263158,
"rate_rps": 2.5,
"trial_feasible": [
false,
false,
false
],
"trials": 3
}
],
"upper_infeasible_rps": 2.4
},
"C01": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 2.2,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 1.3833333333333333,
"pooled_cohort_n": 168,
"pooled_pass_n": 166,
"pooled_pass_rate": 0.9880952380952381,
"rate_rps": 1.4,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.45,
"pooled_cohort_n": 176,
"pooled_pass_n": 174,
"pooled_pass_rate": 0.9886363636363636,
"rate_rps": 1.5,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.5833333333333333,
"pooled_cohort_n": 192,
"pooled_pass_n": 190,
"pooled_pass_rate": 0.9895833333333334,
"rate_rps": 1.6,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7166666666666666,
"pooled_cohort_n": 208,
"pooled_pass_n": 206,
"pooled_pass_rate": 0.9903846153846154,
"rate_rps": 1.7,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7666666666666666,
"pooled_cohort_n": 216,
"pooled_pass_n": 212,
"pooled_pass_rate": 0.9814814814814815,
"rate_rps": 1.8,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.8333333333333333,
"pooled_cohort_n": 224,
"pooled_pass_n": 220,
"pooled_pass_rate": 0.9821428571428571,
"rate_rps": 1.9,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.9416666666666667,
"pooled_cohort_n": 240,
"pooled_pass_n": 233,
"pooled_pass_rate": 0.9708333333333333,
"rate_rps": 2.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.0416666666666665,
"pooled_cohort_n": 256,
"pooled_pass_n": 245,
"pooled_pass_rate": 0.95703125,
"rate_rps": 2.1,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1,
"pooled_cohort_n": 792,
"pooled_pass_n": 757,
"pooled_pass_rate": 0.9558080808080808,
"rate_rps": 2.2,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.85,
"pooled_cohort_n": 816,
"pooled_pass_n": 673,
"pooled_pass_rate": 0.8247549019607843,
"rate_rps": 2.3,
"trial_feasible": [
false,
false,
false
],
"trials": 3
}
],
"upper_infeasible_rps": 2.3
},
"C10": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 2.4,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 1.3916666666666666,
"pooled_cohort_n": 168,
"pooled_pass_n": 167,
"pooled_pass_rate": 0.9940476190476191,
"rate_rps": 1.4,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.4666666666666666,
"pooled_cohort_n": 176,
"pooled_pass_n": 176,
"pooled_pass_rate": 1.0,
"rate_rps": 1.5,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.6,
"pooled_cohort_n": 192,
"pooled_pass_n": 192,
"pooled_pass_rate": 1.0,
"rate_rps": 1.6,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7333333333333334,
"pooled_cohort_n": 208,
"pooled_pass_n": 208,
"pooled_pass_rate": 1.0,
"rate_rps": 1.7,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7916666666666667,
"pooled_cohort_n": 216,
"pooled_pass_n": 215,
"pooled_pass_rate": 0.9953703703703703,
"rate_rps": 1.8,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.8583333333333334,
"pooled_cohort_n": 224,
"pooled_pass_n": 223,
"pooled_pass_rate": 0.9955357142857143,
"rate_rps": 1.9,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.975,
"pooled_cohort_n": 240,
"pooled_pass_n": 237,
"pooled_pass_rate": 0.9875,
"rate_rps": 2.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1,
"pooled_cohort_n": 256,
"pooled_pass_n": 252,
"pooled_pass_rate": 0.984375,
"rate_rps": 2.1,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1666666666666665,
"pooled_cohort_n": 264,
"pooled_pass_n": 260,
"pooled_pass_rate": 0.9848484848484849,
"rate_rps": 2.2,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.2333333333333334,
"pooled_cohort_n": 272,
"pooled_pass_n": 268,
"pooled_pass_rate": 0.9852941176470589,
"rate_rps": 2.3,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.316666666666667,
"pooled_cohort_n": 864,
"pooled_pass_n": 831,
"pooled_pass_rate": 0.9618055555555556,
"rate_rps": 2.4,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 0.7916666666666666,
"pooled_cohort_n": 912,
"pooled_pass_n": 263,
"pooled_pass_rate": 0.2883771929824561,
"rate_rps": 2.5,
"trial_feasible": [
false,
false,
false
],
"trials": 3
}
],
"upper_infeasible_rps": 2.5
},
"C11": {
"boundary_repeated": true,
"bracketed": true,
"lower_feasible_rps": 2.2,
"monotone": true,
"rates": [
{
"accepted_feasible": true,
"median_goodput_rps": 1.3833333333333333,
"pooled_cohort_n": 168,
"pooled_pass_n": 166,
"pooled_pass_rate": 0.9880952380952381,
"rate_rps": 1.4,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.45,
"pooled_cohort_n": 176,
"pooled_pass_n": 174,
"pooled_pass_rate": 0.9886363636363636,
"rate_rps": 1.5,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.5833333333333333,
"pooled_cohort_n": 192,
"pooled_pass_n": 190,
"pooled_pass_rate": 0.9895833333333334,
"rate_rps": 1.6,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7166666666666666,
"pooled_cohort_n": 208,
"pooled_pass_n": 206,
"pooled_pass_rate": 0.9903846153846154,
"rate_rps": 1.7,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.7666666666666666,
"pooled_cohort_n": 216,
"pooled_pass_n": 212,
"pooled_pass_rate": 0.9814814814814815,
"rate_rps": 1.8,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.8333333333333333,
"pooled_cohort_n": 224,
"pooled_pass_n": 220,
"pooled_pass_rate": 0.9821428571428571,
"rate_rps": 1.9,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 1.9416666666666667,
"pooled_cohort_n": 240,
"pooled_pass_n": 233,
"pooled_pass_rate": 0.9708333333333333,
"rate_rps": 2.0,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.033333333333333,
"pooled_cohort_n": 256,
"pooled_pass_n": 244,
"pooled_pass_rate": 0.953125,
"rate_rps": 2.1,
"trial_feasible": [
true
],
"trials": 1
},
{
"accepted_feasible": true,
"median_goodput_rps": 2.1,
"pooled_cohort_n": 792,
"pooled_pass_n": 759,
"pooled_pass_rate": 0.9583333333333334,
"rate_rps": 2.2,
"trial_feasible": [
true,
true,
true
],
"trials": 3
},
{
"accepted_feasible": false,
"median_goodput_rps": 1.5,
"pooled_cohort_n": 816,
"pooled_pass_n": 560,
"pooled_pass_rate": 0.6862745098039216,
"rate_rps": 2.3,
"trial_feasible": [
false,
false,
false
],
"trials": 3
}
],
"upper_infeasible_rps": 2.3
}
}
},
"gpu_hours": 4.8877033844921325,
"sanity": {
"distinct_goodput_by_cell": {
"P01-C00": 10,
"P01-C01": 10,
"P01-C10": 3,
"P01-C11": 3,
"P06-C00": 16,
"P06-C01": 14,
"P06-C10": 16,
"P06-C11": 13
},
"goodput_rps": {
"distinct_n": 59,
"finite_n": 104,
"max": 27.816666666666666,
"min": 0.0,
"missing_n": 0,
"n": 104
},
"invariants": {
"all_cells_bracketed": true,
"all_counters_nonnegative": true,
"all_frontiers_monotone": true,
"all_ratios_in_0_1": true,
"all_trial_invariants": true,
"per_cell_results_not_all_identical": true,
"weight_scan_continuous": true
},
"pass_rates": {
"distinct_n": 57,
"finite_n": 104,
"max": 1.0,
"min": 0.0,
"missing_n": 0,
"n": 104
},
"target_rates": {
"distinct_n": 19,
"finite_n": 104,
"max": 36.0,
"min": 1.4,
"missing_n": 0,
"n": 104
},
"trial_count": {
"distinct_n": 30,
"finite_n": 104,
"max": 2160.0,
"min": 168.0,
"missing_n": 0,
"n": 104
}
},
"schema": 1,
"threshold": 0.1,
"trial_files": 104,
"verdict": "REFUTED",
"worst_mixture_conservative": {
"best_static_config": "C00",
"gap": 0.08333219454200091,
"oracle_upper_rps": 3.1710000000000003,
"p01_weight": 0.0244,
"static_lower_rps": 2.92708
}
}