| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.324, |
| "acc_stderr": 0.014806864733738859 |
| }, |
| "anli_r2": { |
| "acc": 0.341, |
| "acc_stderr": 0.014998131348402702 |
| }, |
| "anli_r3": { |
| "acc": 0.3283333333333333, |
| "acc_stderr": 0.013562032919529026 |
| }, |
| "cb": { |
| "acc": 0.4642857142857143, |
| "acc_stderr": 0.0672477765493766, |
| "f1": 0.32666666666666666 |
| }, |
| "copa": { |
| "acc": 0.85, |
| "acc_stderr": 0.03588702812826373 |
| }, |
| "hellaswag": { |
| "acc": 0.4640509858593906, |
| "acc_stderr": 0.004976867796583557, |
| "acc_norm": 0.6164110734913364, |
| "acc_norm_stderr": 0.004852658876775374 |
| }, |
| "rte": { |
| "acc": 0.4981949458483754, |
| "acc_stderr": 0.030096267148976633 |
| }, |
| "winogrande": { |
| "acc": 0.5880031570639306, |
| "acc_stderr": 0.013833112857645935 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7204703367183325, |
| "acc_stderr": 0.01037770209970486 |
| }, |
| "boolq": { |
| "acc": 0.5691131498470948, |
| "acc_stderr": 0.008661108320775369 |
| }, |
| "arc_easy": { |
| "acc": 0.6342592592592593, |
| "acc_stderr": 0.009882988069418829, |
| "acc_norm": 0.6056397306397306, |
| "acc_norm_stderr": 0.01002817603839299 |
| }, |
| "arc_challenge": { |
| "acc": 0.30204778156996587, |
| "acc_stderr": 0.01341751914471642, |
| "acc_norm": 0.3242320819112628, |
| "acc_norm_stderr": 0.013678810399518819 |
| }, |
| "sciq": { |
| "acc": 0.891, |
| "acc_stderr": 0.009859828407037183, |
| "acc_norm": 0.882, |
| "acc_norm_stderr": 0.01020686926438179 |
| }, |
| "piqa": { |
| "acc": 0.7426550598476604, |
| "acc_stderr": 0.01019992106479251, |
| "acc_norm": 0.7464635473340587, |
| "acc_norm_stderr": 0.010150090834551786 |
| } |
| }, |
| "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 |
| } |
| } |