| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.324, |
| "acc_stderr": 0.014806864733738859 |
| }, |
| "anli_r2": { |
| "acc": 0.322, |
| "acc_stderr": 0.014782913600996676 |
| }, |
| "anli_r3": { |
| "acc": 0.33166666666666667, |
| "acc_stderr": 0.013596836729485163 |
| }, |
| "cb": { |
| "acc": 0.5, |
| "acc_stderr": 0.06741998624632421, |
| "f1": 0.32868937048503616 |
| }, |
| "copa": { |
| "acc": 0.81, |
| "acc_stderr": 0.03942772444036623 |
| }, |
| "hellaswag": { |
| "acc": 0.4817765385381398, |
| "acc_stderr": 0.00498646615169878, |
| "acc_norm": 0.6341366261700856, |
| "acc_norm_stderr": 0.004806870285747301 |
| }, |
| "rte": { |
| "acc": 0.5451263537906137, |
| "acc_stderr": 0.029973636495415255 |
| }, |
| "winogrande": { |
| "acc": 0.6290449881610103, |
| "acc_stderr": 0.01357639990223157 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7439871726349546, |
| "acc_stderr": 0.010092361160364261 |
| }, |
| "boolq": { |
| "acc": 0.6474006116207951, |
| "acc_stderr": 0.008356412493562119 |
| }, |
| "arc_easy": { |
| "acc": 0.6712962962962963, |
| "acc_stderr": 0.009638903167022173, |
| "acc_norm": 0.6641414141414141, |
| "acc_norm_stderr": 0.009691180932083508 |
| }, |
| "arc_challenge": { |
| "acc": 0.318259385665529, |
| "acc_stderr": 0.013611993916971453, |
| "acc_norm": 0.35921501706484643, |
| "acc_norm_stderr": 0.01402022415583914 |
| }, |
| "sciq": { |
| "acc": 0.923, |
| "acc_stderr": 0.008434580140240646, |
| "acc_norm": 0.917, |
| "acc_norm_stderr": 0.00872852720607479 |
| }, |
| "piqa": { |
| "acc": 0.7431991294885746, |
| "acc_stderr": 0.010192864802278052, |
| "acc_norm": 0.7459194776931447, |
| "acc_norm_stderr": 0.010157271999135046 |
| } |
| }, |
| "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 |
| } |
| } |