| { | |
| "hellaswag": { | |
| "name": "hellaswag", | |
| "alias": "hellaswag", | |
| "sample_len": 10042, | |
| "acc,none": 0.2808205536745668, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.29416450906193986, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "arc_easy": { | |
| "name": "arc_easy", | |
| "alias": "arc_easy", | |
| "sample_len": 2376, | |
| "acc,none": 0.45664983164983164, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.4086700336700337, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "arc_challenge": { | |
| "name": "arc_challenge", | |
| "alias": "arc_challenge", | |
| "sample_len": 1172, | |
| "acc,none": 0.189419795221843, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.22866894197952217, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "piqa": { | |
| "name": "piqa", | |
| "alias": "piqa", | |
| "sample_len": 1838, | |
| "acc,none": 0.6202393906420022, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.5984766050054406, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "winogrande": { | |
| "name": "winogrande", | |
| "alias": "winogrande", | |
| "sample_len": 1267, | |
| "acc,none": 0.5035516969218626, | |
| "acc_stderr,none": "N/A" | |
| }, | |
| "openbookqa": { | |
| "name": "openbookqa", | |
| "alias": "openbookqa", | |
| "sample_len": 500, | |
| "acc,none": 0.156, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.318, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "sciq": { | |
| "name": "sciq", | |
| "alias": "sciq", | |
| "sample_len": 1000, | |
| "acc,none": 0.719, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.59, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "lambada_openai": { | |
| "name": "lambada_openai", | |
| "alias": "lambada_openai", | |
| "sample_len": 5153, | |
| "perplexity,none": 176.07916349254722, | |
| "perplexity_stderr,none": "N/A", | |
| "acc,none": 0.18144770036871724, | |
| "acc_stderr,none": "N/A" | |
| } | |
| } |