| { |
| "arc_easy": { |
| "alias": "arc_easy", |
| "acc,none": 0.45454545454545453, |
| "acc_stderr,none": 0.010217299762709388, |
| "acc_norm,none": 0.3867845117845118, |
| "acc_norm_stderr,none": 0.009993308355371001 |
| }, |
| "boolq": { |
| "alias": "boolq", |
| "acc,none": 0.5593272171253822, |
| "acc_stderr,none": 0.008683276495828953 |
| }, |
| "copa": { |
| "alias": "copa", |
| "acc,none": 0.59, |
| "acc_stderr,none": 0.04943110704237104 |
| }, |
| "hellaswag": { |
| "alias": "hellaswag", |
| "acc,none": 0.2773351921927903, |
| "acc_stderr,none": 0.0044676841327723595, |
| "acc_norm,none": 0.29655447122087236, |
| "acc_norm_stderr,none": 0.004558049018764774 |
| }, |
| "lambada_openai": { |
| "alias": "lambada_openai", |
| "perplexity,none": 83.33085129452657, |
| "perplexity_stderr,none": 3.7895421080707683, |
| "acc,none": 0.28138948185522994, |
| "acc_stderr,none": 0.006264880443501338 |
| }, |
| "piqa": { |
| "alias": "piqa", |
| "acc,none": 0.5767138193688792, |
| "acc_stderr,none": 0.011527699473614319, |
| "acc_norm,none": 0.5690968443960827, |
| "acc_norm_stderr,none": 0.011553893175901508 |
| }, |
| "sciq": { |
| "alias": "sciq", |
| "acc,none": 0.783, |
| "acc_stderr,none": 0.013041513757270706, |
| "acc_norm,none": 0.7, |
| "acc_norm_stderr,none": 0.014498627873361335 |
| }, |
| "wikitext": { |
| "alias": "wikitext", |
| "word_perplexity,none": 41.758996651525436, |
| "word_perplexity_stderr,none": "N/A", |
| "byte_perplexity,none": 2.0095016264299344, |
| "byte_perplexity_stderr,none": "N/A", |
| "bits_per_byte,none": 1.0068377450709307, |
| "bits_per_byte_stderr,none": "N/A" |
| }, |
| "winogrande": { |
| "alias": "winogrande", |
| "acc,none": 0.5082872928176796, |
| "acc_stderr,none": 0.01405055532282417 |
| } |
| } |