| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.342, |
| "acc_stderr": 0.01500870618212173 |
| }, |
| "anli_r2": { |
| "acc": 0.34, |
| "acc_stderr": 0.014987482264363937 |
| }, |
| "anli_r3": { |
| "acc": 0.335, |
| "acc_stderr": 0.013630871843821479 |
| }, |
| "cb": { |
| "acc": 0.48214285714285715, |
| "acc_stderr": 0.06737697508644648, |
| "f1": 0.31573655103066867 |
| }, |
| "copa": { |
| "acc": 0.83, |
| "acc_stderr": 0.03775251680686371 |
| }, |
| "hellaswag": { |
| "acc": 0.4805815574586736, |
| "acc_stderr": 0.00498601693867853, |
| "acc_norm": 0.6378211511651065, |
| "acc_norm_stderr": 0.004796478664403837 |
| }, |
| "rte": { |
| "acc": 0.5487364620938628, |
| "acc_stderr": 0.029953149241808946 |
| }, |
| "winogrande": { |
| "acc": 0.6503551696921863, |
| "acc_stderr": 0.013402073680850508 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7493319080705505, |
| "acc_stderr": 0.010022263975606228 |
| }, |
| "boolq": { |
| "acc": 0.6501529051987768, |
| "acc_stderr": 0.008341409251946758 |
| }, |
| "arc_easy": { |
| "acc": 0.680976430976431, |
| "acc_stderr": 0.009564133249441074, |
| "acc_norm": 0.6658249158249159, |
| "acc_norm_stderr": 0.009679106032919058 |
| }, |
| "arc_challenge": { |
| "acc": 0.34044368600682595, |
| "acc_stderr": 0.013847460518892981, |
| "acc_norm": 0.36945392491467577, |
| "acc_norm_stderr": 0.0141045783664919 |
| }, |
| "sciq": { |
| "acc": 0.927, |
| "acc_stderr": 0.00823035471524406, |
| "acc_norm": 0.921, |
| "acc_norm_stderr": 0.008534156773333442 |
| }, |
| "piqa": { |
| "acc": 0.7383025027203483, |
| "acc_stderr": 0.010255630772708229, |
| "acc_norm": 0.735038084874864, |
| "acc_norm_stderr": 0.010296557993316037 |
| } |
| }, |
| "versions": { |
| "anli_r1": 0, |
| "anli_r2": 0, |
| "anli_r3": 0, |
| "cb": 1, |
| "copa": 0, |
| "hellaswag": 0, |
| "rte": 0, |
| "winogrande": 0, |
| "storycloze_2016": 0, |
| "boolq": 1, |
| "arc_easy": 0, |
| "arc_challenge": 0, |
| "sciq": 0, |
| "piqa": 0 |
| } |
| } |