| { | |
| "results": { | |
| "anli_r1": { | |
| "acc": 0.34, | |
| "acc_stderr": 0.014987482264363937 | |
| }, | |
| "anli_r2": { | |
| "acc": 0.326, | |
| "acc_stderr": 0.014830507204541028 | |
| }, | |
| "anli_r3": { | |
| "acc": 0.3541666666666667, | |
| "acc_stderr": 0.01381193349957096 | |
| }, | |
| "cb": { | |
| "acc": 0.42857142857142855, | |
| "acc_stderr": 0.06672848092813058, | |
| "f1": 0.36324786324786323 | |
| }, | |
| "copa": { | |
| "acc": 0.75, | |
| "acc_stderr": 0.04351941398892446 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.4411471818362876, | |
| "acc_stderr": 0.004955095096264714, | |
| "acc_norm": 0.5774746066520613, | |
| "acc_norm_stderr": 0.004929517011508216 | |
| }, | |
| "rte": { | |
| "acc": 0.5234657039711191, | |
| "acc_stderr": 0.030063300411902652 | |
| }, | |
| "winogrande": { | |
| "acc": 0.5595895816890292, | |
| "acc_stderr": 0.013952330311915603 | |
| }, | |
| "storycloze_2016": { | |
| "acc": 0.6830571886691609, | |
| "acc_stderr": 0.010759650951452121 | |
| }, | |
| "boolq": { | |
| "acc": 0.5562691131498471, | |
| "acc_stderr": 0.008689501105367413 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.5968013468013468, | |
| "acc_stderr": 0.010065668576794803, | |
| "acc_norm": 0.5913299663299664, | |
| "acc_norm_stderr": 0.01008717449876288 | |
| }, | |
| "arc_challenge": { | |
| "acc": 0.27474402730375425, | |
| "acc_stderr": 0.013044617212771227, | |
| "acc_norm": 0.3037542662116041, | |
| "acc_norm_stderr": 0.01343890918477876 | |
| }, | |
| "sciq": { | |
| "acc": 0.887, | |
| "acc_stderr": 0.010016552866696846, | |
| "acc_norm": 0.882, | |
| "acc_norm_stderr": 0.01020686926438179 | |
| }, | |
| "piqa": { | |
| "acc": 0.7295973884657236, | |
| "acc_stderr": 0.010363167031620784, | |
| "acc_norm": 0.7334058759521219, | |
| "acc_norm_stderr": 0.010316749863541365 | |
| } | |
| }, | |
| "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 | |
| } | |
| } |