| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.335, |
| "acc_stderr": 0.014933117490932573 |
| }, |
| "anli_r2": { |
| "acc": 0.332, |
| "acc_stderr": 0.014899597242811476 |
| }, |
| "anli_r3": { |
| "acc": 0.33666666666666667, |
| "acc_stderr": 0.01364760294240639 |
| }, |
| "cb": { |
| "acc": 0.4107142857142857, |
| "acc_stderr": 0.0663363415035954, |
| "f1": 0.1940928270042194 |
| }, |
| "copa": { |
| "acc": 0.79, |
| "acc_stderr": 0.040936018074033256 |
| }, |
| "hellaswag": { |
| "acc": 0.4989046006771559, |
| "acc_stderr": 0.004989769436956927, |
| "acc_norm": 0.6554471220872337, |
| "acc_norm_stderr": 0.004742510354777903 |
| }, |
| "rte": { |
| "acc": 0.5342960288808665, |
| "acc_stderr": 0.030025579819366426 |
| }, |
| "winogrande": { |
| "acc": 0.5895816890292028, |
| "acc_stderr": 0.013825107120035865 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7349011223944415, |
| "acc_stderr": 0.01020698782076139 |
| }, |
| "boolq": { |
| "acc": 0.5923547400611621, |
| "acc_stderr": 0.008594580270731613 |
| }, |
| "arc_easy": { |
| "acc": 0.6031144781144782, |
| "acc_stderr": 0.010039236800583209, |
| "acc_norm": 0.5332491582491582, |
| "acc_norm_stderr": 0.010237073872130745 |
| }, |
| "arc_challenge": { |
| "acc": 0.28498293515358364, |
| "acc_stderr": 0.013191348179838793, |
| "acc_norm": 0.3037542662116041, |
| "acc_norm_stderr": 0.013438909184778757 |
| }, |
| "sciq": { |
| "acc": 0.862, |
| "acc_stderr": 0.010912152632504411, |
| "acc_norm": 0.782, |
| "acc_norm_stderr": 0.013063179040595296 |
| }, |
| "piqa": { |
| "acc": 0.7616974972796517, |
| "acc_stderr": 0.009940334245876207, |
| "acc_norm": 0.7693144722524483, |
| "acc_norm_stderr": 0.009828959550983103 |
| } |
| }, |
| "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 |
| } |
| } |