| { | |
| "results": { | |
| "anli_r1": { | |
| "acc": 0.346, | |
| "acc_stderr": 0.01505026612756445 | |
| }, | |
| "anli_r2": { | |
| "acc": 0.345, | |
| "acc_stderr": 0.015039986742055242 | |
| }, | |
| "anli_r3": { | |
| "acc": 0.3541666666666667, | |
| "acc_stderr": 0.013811933499570963 | |
| }, | |
| "cb": { | |
| "acc": 0.4642857142857143, | |
| "acc_stderr": 0.06724777654937658, | |
| "f1": 0.255 | |
| }, | |
| "copa": { | |
| "acc": 0.79, | |
| "acc_stderr": 0.040936018074033256 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.42959569806811393, | |
| "acc_stderr": 0.004940067402031042, | |
| "acc_norm": 0.5713005377414858, | |
| "acc_norm_stderr": 0.004938787067611811 | |
| }, | |
| "rte": { | |
| "acc": 0.5234657039711191, | |
| "acc_stderr": 0.030063300411902652 | |
| }, | |
| "winogrande": { | |
| "acc": 0.5438042620363063, | |
| "acc_stderr": 0.013998453610924324 | |
| }, | |
| "storycloze_2016": { | |
| "acc": 0.6873329770176376, | |
| "acc_stderr": 0.010720223172953168 | |
| }, | |
| "boolq": { | |
| "acc": 0.5293577981651376, | |
| "acc_stderr": 0.008729967580199222 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.5951178451178452, | |
| "acc_stderr": 0.010072423960395703, | |
| "acc_norm": 0.5740740740740741, | |
| "acc_norm_stderr": 0.010146568651002255 | |
| }, | |
| "arc_challenge": { | |
| "acc": 0.25853242320819114, | |
| "acc_stderr": 0.01279455375428868, | |
| "acc_norm": 0.3037542662116041, | |
| "acc_norm_stderr": 0.01343890918477876 | |
| }, | |
| "sciq": { | |
| "acc": 0.895, | |
| "acc_stderr": 0.009698921026024954, | |
| "acc_norm": 0.891, | |
| "acc_norm_stderr": 0.009859828407037183 | |
| }, | |
| "piqa": { | |
| "acc": 0.7415669205658324, | |
| "acc_stderr": 0.01021397163677332, | |
| "acc_norm": 0.733949945593036, | |
| "acc_norm_stderr": 0.01031003926335282 | |
| } | |
| }, | |
| "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 | |
| } | |
| } |