tinystories-diff-ar / poe_results.json
Asilarkness's picture
Super-squash branch 'main' using huggingface_hub
a6c51a2
Raw History Blame Contribute Delete
3.74 kB
[
{
"scheme": "AR",
"calls": 128,
"sec": 0.784,
"judge_nll": 2.7702,
"dup": 0.0172,
"distinct2": 0.5472
},
{
"scheme": "DIFF K=4",
"calls": 4,
"sec": 0.136,
"judge_nll": 5.9254,
"dup": 0.0541,
"distinct2": 0.4716
},
{
"scheme": "DIFF K=8",
"calls": 8,
"sec": 0.05,
"judge_nll": 4.4448,
"dup": 0.0495,
"distinct2": 0.4129
},
{
"scheme": "DIFF K=16",
"calls": 16,
"sec": 0.098,
"judge_nll": 3.7416,
"dup": 0.0459,
"distinct2": 0.4145
},
{
"scheme": "AR-ONLY K=4 p=0.10",
"calls": 5,
"sec": 0.03,
"judge_nll": 5.6685,
"dup": 0.0602,
"distinct2": 0.4295
},
{
"scheme": "POE K=4 p=0.10 a=0.00",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.5971,
"dup": 0.0569,
"distinct2": 0.4154
},
{
"scheme": "POE K=4 p=0.10 a=0.25",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.5133,
"dup": 0.0653,
"distinct2": 0.4072
},
{
"scheme": "POE K=4 p=0.10 a=0.50",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.3174,
"dup": 0.0561,
"distinct2": 0.3983
},
{
"scheme": "POE K=4 p=0.10 a=0.75",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.206,
"dup": 0.0591,
"distinct2": 0.3983
},
{
"scheme": "POE K=4 p=0.10 a=1.00",
"calls": 5,
"sec": 0.029,
"judge_nll": 5.2259,
"dup": 0.0564,
"distinct2": 0.408
},
{
"scheme": "AR-ONLY K=4 p=0.25",
"calls": 5,
"sec": 0.029,
"judge_nll": 5.9793,
"dup": 0.0576,
"distinct2": 0.4454
},
{
"scheme": "POE K=4 p=0.25 a=0.00",
"calls": 6,
"sec": 0.033,
"judge_nll": 5.9723,
"dup": 0.0535,
"distinct2": 0.4411
},
{
"scheme": "POE K=4 p=0.25 a=0.25",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.6715,
"dup": 0.0581,
"distinct2": 0.4227
},
{
"scheme": "POE K=4 p=0.25 a=0.50",
"calls": 6,
"sec": 0.033,
"judge_nll": 5.3627,
"dup": 0.0556,
"distinct2": 0.418
},
{
"scheme": "POE K=4 p=0.25 a=0.75",
"calls": 6,
"sec": 0.032,
"judge_nll": 5.1056,
"dup": 0.0525,
"distinct2": 0.3975
},
{
"scheme": "POE K=4 p=0.25 a=1.00",
"calls": 5,
"sec": 0.029,
"judge_nll": 5.0092,
"dup": 0.0504,
"distinct2": 0.4116
},
{
"scheme": "AR-ONLY K=8 p=0.10",
"calls": 9,
"sec": 0.054,
"judge_nll": 4.4933,
"dup": 0.0536,
"distinct2": 0.3981
},
{
"scheme": "POE K=8 p=0.10 a=0.00",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.4851,
"dup": 0.0554,
"distinct2": 0.3839
},
{
"scheme": "POE K=8 p=0.10 a=0.25",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.3206,
"dup": 0.0536,
"distinct2": 0.3789
},
{
"scheme": "POE K=8 p=0.10 a=0.50",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.1484,
"dup": 0.0441,
"distinct2": 0.383
},
{
"scheme": "POE K=8 p=0.10 a=0.75",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.075,
"dup": 0.0518,
"distinct2": 0.3832
},
{
"scheme": "POE K=8 p=0.10 a=1.00",
"calls": 9,
"sec": 0.054,
"judge_nll": 4.1021,
"dup": 0.0463,
"distinct2": 0.3993
},
{
"scheme": "AR-ONLY K=8 p=0.25",
"calls": 9,
"sec": 0.055,
"judge_nll": 5.0815,
"dup": 0.0418,
"distinct2": 0.4431
},
{
"scheme": "POE K=8 p=0.25 a=0.00",
"calls": 10,
"sec": 0.057,
"judge_nll": 5.1231,
"dup": 0.0494,
"distinct2": 0.4503
},
{
"scheme": "POE K=8 p=0.25 a=0.25",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.689,
"dup": 0.0468,
"distinct2": 0.4214
},
{
"scheme": "POE K=8 p=0.25 a=0.50",
"calls": 10,
"sec": 0.057,
"judge_nll": 4.3804,
"dup": 0.0497,
"distinct2": 0.4032
},
{
"scheme": "POE K=8 p=0.25 a=0.75",
"calls": 10,
"sec": 0.058,
"judge_nll": 4.1671,
"dup": 0.0481,
"distinct2": 0.3978
},
{
"scheme": "POE K=8 p=0.25 a=1.00",
"calls": 9,
"sec": 0.054,
"judge_nll": 4.0754,
"dup": 0.0446,
"distinct2": 0.4044
}
]