| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.33, |
| "acc_stderr": 0.014876872027456732 |
| }, |
| "anli_r2": { |
| "acc": 0.33, |
| "acc_stderr": 0.014876872027456736 |
| }, |
| "anli_r3": { |
| "acc": 0.33166666666666667, |
| "acc_stderr": 0.01359683672948516 |
| }, |
| "cb": { |
| "acc": 0.5178571428571429, |
| "acc_stderr": 0.06737697508644648, |
| "f1": 0.35968427443837275 |
| }, |
| "copa": { |
| "acc": 0.79, |
| "acc_stderr": 0.040936018074033256 |
| }, |
| "hellaswag": { |
| "acc": 0.4790878311093408, |
| "acc_stderr": 0.004985415250690917, |
| "acc_norm": 0.6304521011750648, |
| "acc_norm_stderr": 0.004816958817726088 |
| }, |
| "rte": { |
| "acc": 0.5703971119133574, |
| "acc_stderr": 0.02979666882912467 |
| }, |
| "winogrande": { |
| "acc": 0.6235201262825573, |
| "acc_stderr": 0.013616931960667187 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7365045430251203, |
| "acc_stderr": 0.010187168219156485 |
| }, |
| "boolq": { |
| "acc": 0.6428134556574924, |
| "acc_stderr": 0.008380743796951404 |
| }, |
| "arc_easy": { |
| "acc": 0.6742424242424242, |
| "acc_stderr": 0.009616642976885964, |
| "acc_norm": 0.6523569023569024, |
| "acc_norm_stderr": 0.009771868846830909 |
| }, |
| "arc_challenge": { |
| "acc": 0.3378839590443686, |
| "acc_stderr": 0.013822047922283507, |
| "acc_norm": 0.3660409556313993, |
| "acc_norm_stderr": 0.014077223108470144 |
| }, |
| "sciq": { |
| "acc": 0.923, |
| "acc_stderr": 0.008434580140240644, |
| "acc_norm": 0.901, |
| "acc_norm_stderr": 0.009449248027662746 |
| }, |
| "piqa": { |
| "acc": 0.7404787812840044, |
| "acc_stderr": 0.010227939888173918, |
| "acc_norm": 0.7388465723612623, |
| "acc_norm_stderr": 0.010248738649935587 |
| } |
| }, |
| "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 |
| } |
| } |