improving-self-evolution-mbpp / eval64 /metrics_compact.json
humanlong's picture
Add final 64-sample MBPP evaluation
7acc25e verified
Raw History Blame Contribute Delete
21.2 kB
{
"base": {
"task_count": 500,
"sample_count": 32000,
"correct_count": 12142,
"correct_fraction": {
"mean": 0.3794375,
"all_task_mean": 0.3794375,
"ci95": [
0.34740546875,
0.41365703125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"pass_at_k": {
"1": {
"mean": 0.3794375,
"all_task_mean": 0.3794375,
"ci95": [
0.34740546875,
0.41365703125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 0.5507654491198912,
"all_task_mean": 0.5507654491198912,
"ci95": [
0.5132311306218681,
0.5890580618405479
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 0.6109743277142735,
"all_task_mean": 0.6109743277142735,
"ci95": [
0.5724928416444336,
0.6497163629340588
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 0.6569243830645763,
"all_task_mean": 0.6569243830645763,
"ci95": [
0.6184579345767386,
0.6952451294337093
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 0.72,
"all_task_mean": 0.72,
"ci95": [
0.6819500000000001,
0.758
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"implementation_coverage_at_k": {
"1": {
"mean": 0.3794375,
"all_task_mean": 0.3794375,
"ci95": [
0.34740546875,
0.41365703125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 1.2665641226612274,
"all_task_mean": 1.2665641226612274,
"ci95": [
1.159415250025182,
1.3736470797606455
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 2.2670132030155092,
"all_task_mean": 2.2670132030155092,
"ci95": [
2.0738004189885935,
2.4590917365037095
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 4.039637834881175,
"all_task_mean": 4.039637834881175,
"ci95": [
3.6929032849396326,
4.390863679872534
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 12.802,
"all_task_mean": 12.802,
"ci95": [
11.69585,
13.9681
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"correct_matched_coverage_at_budgets": {
"4": {
"mean": 3.3583723736089284,
"all_task_mean": null,
"ci95": [
3.282182510720265,
3.439956670735758
],
"eligible_tasks": 322,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_4_correct_samples",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 5.986525949447583,
"all_task_mean": null,
"ci95": [
5.779330460447849,
6.196882660452379
],
"eligible_tasks": 294,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_8_correct_samples",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 10.42331543495907,
"all_task_mean": null,
"ci95": [
9.959521542093748,
10.910493297809975
],
"eligible_tasks": 251,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_16_correct_samples",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 19.875,
"all_task_mean": null,
"ci95": [
15.0,
25.04092307692307
],
"eligible_tasks": 24,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_64_correct_samples",
"bootstrap_valid_replicates": 2000
}
}
},
"plain": {
"task_count": 500,
"sample_count": 32000,
"correct_count": 13263,
"correct_fraction": {
"mean": 0.41446875,
"all_task_mean": 0.41446875,
"ci95": [
0.38040546875,
0.45168984375
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"pass_at_k": {
"1": {
"mean": 0.41446875,
"all_task_mean": 0.41446875,
"ci95": [
0.38040546875,
0.45168984375
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 0.5654111549696559,
"all_task_mean": 0.5654111549696559,
"ci95": [
0.5268074897383598,
0.6045970197961521
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 0.6185723086964429,
"all_task_mean": 0.6185723086964429,
"ci95": [
0.5793926136329006,
0.65815805619536
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 0.6563636760539059,
"all_task_mean": 0.6563636760539059,
"ci95": [
0.6166121006457762,
0.6960772759859236
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 0.704,
"all_task_mean": 0.704,
"ci95": [
0.664,
0.744
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"implementation_coverage_at_k": {
"1": {
"mean": 0.41446875,
"all_task_mean": 0.41446875,
"ci95": [
0.38040546875,
0.45168984375
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 1.1661383023595477,
"all_task_mean": 1.1661383023595477,
"ci95": [
1.070903410028078,
1.2672731045868904
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 1.9228737911818574,
"all_task_mean": 1.9228737911818574,
"ci95": [
1.7571056197779187,
2.101574059760503
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 3.1592155356398983,
"all_task_mean": 3.1592155356398983,
"ci95": [
2.8673068380698647,
3.47591123889947
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 8.506,
"all_task_mean": 8.506,
"ci95": [
7.60195,
9.46405
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"correct_matched_coverage_at_budgets": {
"4": {
"mean": 2.856476213813779,
"all_task_mean": null,
"ci95": [
2.7541549099452163,
2.9606601396926697
],
"eligible_tasks": 321,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_4_correct_samples",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 4.690364473715527,
"all_task_mean": null,
"ci95": [
4.453332768614563,
4.9366147006484855
],
"eligible_tasks": 305,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_8_correct_samples",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 7.3244981368337205,
"all_task_mean": null,
"ci95": [
6.814141127178505,
7.842568973120032
],
"eligible_tasks": 263,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_16_correct_samples",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 8.686274509803921,
"all_task_mean": null,
"ci95": [
6.377226853883282,
11.162976249381494
],
"eligible_tasks": 51,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_64_correct_samples",
"bootstrap_valid_replicates": 2000
}
}
},
"spd_hard": {
"task_count": 500,
"sample_count": 32000,
"correct_count": 13365,
"correct_fraction": {
"mean": 0.41765625,
"all_task_mean": 0.41765625,
"ci95": [
0.384625,
0.4546578125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"pass_at_k": {
"1": {
"mean": 0.41765625,
"all_task_mean": 0.41765625,
"ci95": [
0.384625,
0.4546578125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 0.5659676600941804,
"all_task_mean": 0.5659676600941804,
"ci95": [
0.527518317657576,
0.604875113633502
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 0.6187692750882325,
"all_task_mean": 0.6187692750882325,
"ci95": [
0.5796125930854173,
0.6583837108361063
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 0.656461003056232,
"all_task_mean": 0.656461003056232,
"ci95": [
0.616541219686637,
0.6960544516270536
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 0.702,
"all_task_mean": 0.702,
"ci95": [
0.662,
0.7420499999999998
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"implementation_coverage_at_k": {
"1": {
"mean": 0.41765625,
"all_task_mean": 0.41765625,
"ci95": [
0.384625,
0.4546578125
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 1.1526910962957369,
"all_task_mean": 1.1526910962957369,
"ci95": [
1.059633787473874,
1.2513327874361007
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 1.8917267799240527,
"all_task_mean": 1.8917267799240527,
"ci95": [
1.7283757935135853,
2.062184461404335
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 3.103388895756195,
"all_task_mean": 3.103388895756195,
"ci95": [
2.817451519989818,
3.40744240345712
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 8.388,
"all_task_mean": 8.388,
"ci95": [
7.514,
9.322049999999999
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"correct_matched_coverage_at_budgets": {
"4": {
"mean": 2.8097969039470296,
"all_task_mean": null,
"ci95": [
2.702378107013863,
2.912624204119433
],
"eligible_tasks": 321,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_4_correct_samples",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 4.589740759204707,
"all_task_mean": null,
"ci95": [
4.341571130697039,
4.8420976777276685
],
"eligible_tasks": 303,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_8_correct_samples",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 7.136154971929802,
"all_task_mean": null,
"ci95": [
6.612424214688567,
7.64193275562665
],
"eligible_tasks": 264,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_16_correct_samples",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 7.981132075471698,
"all_task_mean": null,
"ci95": [
5.9298245614035086,
10.380074468085107
],
"eligible_tasks": 53,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_64_correct_samples",
"bootstrap_valid_replicates": 2000
}
}
},
"spectral_soft": {
"task_count": 500,
"sample_count": 32000,
"correct_count": 12906,
"correct_fraction": {
"mean": 0.4033125,
"all_task_mean": 0.4033125,
"ci95": [
0.37115312500000003,
0.43831796874999995
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"pass_at_k": {
"1": {
"mean": 0.4033125,
"all_task_mean": 0.4033125,
"ci95": [
0.37115312500000003,
0.43831796874999995
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 0.562148161088867,
"all_task_mean": 0.562148161088867,
"ci95": [
0.5239757778858503,
0.6009773591542646
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 0.6189282395695613,
"all_task_mean": 0.6189282395695613,
"ci95": [
0.5799531764909873,
0.6581920368265824
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 0.6622507815182023,
"all_task_mean": 0.6622507815182023,
"ci95": [
0.6233787417205545,
0.7018316378569717
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 0.726,
"all_task_mean": 0.726,
"ci95": [
0.688,
0.766
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"implementation_coverage_at_k": {
"1": {
"mean": 0.4033125,
"all_task_mean": 0.4033125,
"ci95": [
0.37115312500000003,
0.43831796874999995
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"4": {
"mean": 1.243749039938556,
"all_task_mean": 1.243749039938556,
"ci95": [
1.1431083542658207,
1.348755115711012
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 2.161080512531813,
"all_task_mean": 2.161080512531813,
"ci95": [
1.9763838957574165,
2.3468053037933396
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 3.758255772115641,
"all_task_mean": 3.758255772115641,
"ci95": [
3.4251782302115035,
4.103086515045223
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 11.51,
"all_task_mean": 11.51,
"ci95": [
10.424,
12.652399999999997
],
"eligible_tasks": 500,
"total_tasks": 500,
"population": "tasks_with_available_estimates",
"bootstrap_valid_replicates": 2000
}
},
"correct_matched_coverage_at_budgets": {
"4": {
"mean": 3.143291510215674,
"all_task_mean": null,
"ci95": [
3.052151432442491,
3.236868415837648
],
"eligible_tasks": 323,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_4_correct_samples",
"bootstrap_valid_replicates": 2000
},
"8": {
"mean": 5.451019508347272,
"all_task_mean": null,
"ci95": [
5.221458862962949,
5.691262607579812
],
"eligible_tasks": 302,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_8_correct_samples",
"bootstrap_valid_replicates": 2000
},
"16": {
"mean": 9.09058337320117,
"all_task_mean": null,
"ci95": [
8.580622492811118,
9.615960487699715
],
"eligible_tasks": 259,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_16_correct_samples",
"bootstrap_valid_replicates": 2000
},
"64": {
"mean": 12.176470588235293,
"all_task_mean": null,
"ci95": [
9.37483552631579,
15.0
],
"eligible_tasks": 34,
"total_tasks": 500,
"population": "tasks_with_complete_labels_and_at_least_64_correct_samples",
"bootstrap_valid_replicates": 2000
}
}
}
}