| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.315, |
| "acc_stderr": 0.0146966319607925 |
| }, |
| "anli_r2": { |
| "acc": 0.335, |
| "acc_stderr": 0.014933117490932575 |
| }, |
| "anli_r3": { |
| "acc": 0.34, |
| "acc_stderr": 0.013680495725767789 |
| }, |
| "cb": { |
| "acc": 0.4107142857142857, |
| "acc_stderr": 0.0663363415035954, |
| "f1": 0.2854808590102708 |
| }, |
| "copa": { |
| "acc": 0.84, |
| "acc_stderr": 0.03684529491774709 |
| }, |
| "hellaswag": { |
| "acc": 0.4934276040629357, |
| "acc_stderr": 0.004989350311751647, |
| "acc_norm": 0.6552479585739892, |
| "acc_norm_stderr": 0.004743160034271143 |
| }, |
| "rte": { |
| "acc": 0.5018050541516246, |
| "acc_stderr": 0.030096267148976626 |
| }, |
| "winogrande": { |
| "acc": 0.6156274664561957, |
| "acc_stderr": 0.013671567600836192 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7413148049171566, |
| "acc_stderr": 0.010126662138021712 |
| }, |
| "boolq": { |
| "acc": 0.6217125382262997, |
| "acc_stderr": 0.008482001133930994 |
| }, |
| "arc_easy": { |
| "acc": 0.6523569023569024, |
| "acc_stderr": 0.00977186884683091, |
| "acc_norm": 0.6266835016835017, |
| "acc_norm_stderr": 0.009925009142802893 |
| }, |
| "arc_challenge": { |
| "acc": 0.3293515358361775, |
| "acc_stderr": 0.013734057652635473, |
| "acc_norm": 0.3387372013651877, |
| "acc_norm_stderr": 0.01383056892797433 |
| }, |
| "sciq": { |
| "acc": 0.916, |
| "acc_stderr": 0.008776162089491132, |
| "acc_norm": 0.892, |
| "acc_norm_stderr": 0.009820001651345682 |
| }, |
| "piqa": { |
| "acc": 0.7627856365614799, |
| "acc_stderr": 0.00992469493358637, |
| "acc_norm": 0.7709466811751904, |
| "acc_norm_stderr": 0.009804509865175505 |
| } |
| }, |
| "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 |
| } |
| } |