| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.338, |
| "acc_stderr": 0.014965960710224482 |
| }, |
| "anli_r2": { |
| "acc": 0.341, |
| "acc_stderr": 0.014998131348402699 |
| }, |
| "anli_r3": { |
| "acc": 0.3491666666666667, |
| "acc_stderr": 0.013767075395077249 |
| }, |
| "cb": { |
| "acc": 0.5, |
| "acc_stderr": 0.06741998624632421, |
| "f1": 0.33763440860215055 |
| }, |
| "copa": { |
| "acc": 0.76, |
| "acc_stderr": 0.04292346959909283 |
| }, |
| "hellaswag": { |
| "acc": 0.4814777932682733, |
| "acc_stderr": 0.004986356526063966, |
| "acc_norm": 0.6296554471220872, |
| "acc_norm_stderr": 0.004819100456867812 |
| }, |
| "rte": { |
| "acc": 0.5884476534296029, |
| "acc_stderr": 0.029621832222417196 |
| }, |
| "winogrande": { |
| "acc": 0.611681136543015, |
| "acc_stderr": 0.01369745665845723 |
| }, |
| "storycloze_2016": { |
| "acc": 0.740780331373597, |
| "acc_stderr": 0.010133463176449564 |
| }, |
| "boolq": { |
| "acc": 0.5972477064220183, |
| "acc_stderr": 0.008578054401368405 |
| }, |
| "arc_easy": { |
| "acc": 0.6430976430976431, |
| "acc_stderr": 0.009830630210347005, |
| "acc_norm": 0.5686026936026936, |
| "acc_norm_stderr": 0.010162752847747505 |
| }, |
| "arc_challenge": { |
| "acc": 0.3054607508532423, |
| "acc_stderr": 0.013460080478002501, |
| "acc_norm": 0.3267918088737201, |
| "acc_norm_stderr": 0.013706665975587336 |
| }, |
| "sciq": { |
| "acc": 0.869, |
| "acc_stderr": 0.010674874844837952, |
| "acc_norm": 0.773, |
| "acc_norm_stderr": 0.013253174964763921 |
| }, |
| "piqa": { |
| "acc": 0.7415669205658324, |
| "acc_stderr": 0.010213971636773319, |
| "acc_norm": 0.7421109902067464, |
| "acc_norm_stderr": 0.010206956662056252 |
| } |
| }, |
| "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 |
| } |
| } |