| { |
| "results": { |
| "anli_r1": { |
| "acc": 0.342, |
| "acc_stderr": 0.015008706182121733 |
| }, |
| "anli_r2": { |
| "acc": 0.331, |
| "acc_stderr": 0.014888272588203943 |
| }, |
| "anli_r3": { |
| "acc": 0.3233333333333333, |
| "acc_stderr": 0.013508372867300226 |
| }, |
| "cb": { |
| "acc": 0.48214285714285715, |
| "acc_stderr": 0.0673769750864465, |
| "f1": 0.32495309568480296 |
| }, |
| "copa": { |
| "acc": 0.79, |
| "acc_stderr": 0.040936018074033256 |
| }, |
| "hellaswag": { |
| "acc": 0.46106353316072496, |
| "acc_stderr": 0.004974628903829131, |
| "acc_norm": 0.6156144194383589, |
| "acc_norm_stderr": 0.004854555294017531 |
| }, |
| "rte": { |
| "acc": 0.51985559566787, |
| "acc_stderr": 0.030072723167317184 |
| }, |
| "winogrande": { |
| "acc": 0.5864246250986582, |
| "acc_stderr": 0.0138409717631953 |
| }, |
| "storycloze_2016": { |
| "acc": 0.7167290219134153, |
| "acc_stderr": 0.010419760409155363 |
| }, |
| "boolq": { |
| "acc": 0.5758409785932722, |
| "acc_stderr": 0.008643869023388125 |
| }, |
| "arc_easy": { |
| "acc": 0.6317340067340067, |
| "acc_stderr": 0.009897286209010892, |
| "acc_norm": 0.6127946127946128, |
| "acc_norm_stderr": 0.009995312065890341 |
| }, |
| "arc_challenge": { |
| "acc": 0.295221843003413, |
| "acc_stderr": 0.013329750293382318, |
| "acc_norm": 0.31313993174061433, |
| "acc_norm_stderr": 0.013552671543623503 |
| }, |
| "sciq": { |
| "acc": 0.89, |
| "acc_stderr": 0.009899393819724428, |
| "acc_norm": 0.872, |
| "acc_norm_stderr": 0.010570133761108665 |
| }, |
| "piqa": { |
| "acc": 0.7388465723612623, |
| "acc_stderr": 0.010248738649935576, |
| "acc_norm": 0.7431991294885746, |
| "acc_norm_stderr": 0.010192864802278039 |
| } |
| }, |
| "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 |
| } |
| } |