| { | |
| "results": { | |
| "anli_r1": { | |
| "acc": 0.385, | |
| "acc_stderr": 0.015395194445410808 | |
| }, | |
| "anli_r2": { | |
| "acc": 0.336, | |
| "acc_stderr": 0.014944140233795021 | |
| }, | |
| "anli_r3": { | |
| "acc": 0.36333333333333334, | |
| "acc_stderr": 0.013889898953170563 | |
| }, | |
| "cb": { | |
| "acc": 0.5535714285714286, | |
| "acc_stderr": 0.06703189227942394, | |
| "f1": 0.3077154912597951 | |
| }, | |
| "copa": { | |
| "acc": 0.75, | |
| "acc_stderr": 0.04351941398892446 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.4266082453694483, | |
| "acc_stderr": 0.0049357353003488666, | |
| "acc_norm": 0.566620195180243, | |
| "acc_norm_stderr": 0.004945291270072436 | |
| }, | |
| "rte": { | |
| "acc": 0.5523465703971119, | |
| "acc_stderr": 0.02993107036293953 | |
| }, | |
| "winogrande": { | |
| "acc": 0.5445935280189423, | |
| "acc_stderr": 0.013996485037729782 | |
| }, | |
| "storycloze_2016": { | |
| "acc": 0.6841261357562801, | |
| "acc_stderr": 0.010749892827011113 | |
| }, | |
| "boolq": { | |
| "acc": 0.5666666666666667, | |
| "acc_stderr": 0.008666972565214514 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.5904882154882155, | |
| "acc_stderr": 0.010090368160990059, | |
| "acc_norm": 0.5736531986531986, | |
| "acc_norm_stderr": 0.01014785860383514 | |
| }, | |
| "arc_challenge": { | |
| "acc": 0.257679180887372, | |
| "acc_stderr": 0.012780770562768402, | |
| "acc_norm": 0.27559726962457337, | |
| "acc_norm_stderr": 0.013057169655761838 | |
| }, | |
| "sciq": { | |
| "acc": 0.872, | |
| "acc_stderr": 0.010570133761108665, | |
| "acc_norm": 0.854, | |
| "acc_norm_stderr": 0.0111717862854965 | |
| }, | |
| "piqa": { | |
| "acc": 0.7285092491838956, | |
| "acc_stderr": 0.010376251176596135, | |
| "acc_norm": 0.7486398258977149, | |
| "acc_norm_stderr": 0.01012115601681925 | |
| } | |
| }, | |
| "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 | |
| } | |
| } |