| { | |
| "hellaswag": { | |
| "name": "hellaswag", | |
| "alias": "hellaswag", | |
| "sample_len": 10042, | |
| "acc,none": 0.28251344353714397, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.2954590718980283, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "arc_easy": { | |
| "name": "arc_easy", | |
| "alias": "arc_easy", | |
| "sample_len": 2376, | |
| "acc,none": 0.4524410774410774, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.4128787878787879, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "arc_challenge": { | |
| "name": "arc_challenge", | |
| "alias": "arc_challenge", | |
| "sample_len": 1172, | |
| "acc,none": 0.2030716723549488, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.2525597269624573, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "piqa": { | |
| "name": "piqa", | |
| "alias": "piqa", | |
| "sample_len": 1838, | |
| "acc,none": 0.6169749727965179, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.6011969532100109, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "winogrande": { | |
| "name": "winogrande", | |
| "alias": "winogrande", | |
| "sample_len": 1267, | |
| "acc,none": 0.5138121546961326, | |
| "acc_stderr,none": "N/A" | |
| }, | |
| "openbookqa": { | |
| "name": "openbookqa", | |
| "alias": "openbookqa", | |
| "sample_len": 500, | |
| "acc,none": 0.19, | |
| "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": 0.662, | |
| "acc_stderr,none": "N/A", | |
| "acc_norm,none": 0.576, | |
| "acc_norm_stderr,none": "N/A" | |
| }, | |
| "lambada_openai": { | |
| "name": "lambada_openai", | |
| "alias": "lambada_openai", | |
| "sample_len": 5153, | |
| "perplexity,none": 241.01776041846503, | |
| "perplexity_stderr,none": "N/A", | |
| "acc,none": 0.17581991073161266, | |
| "acc_stderr,none": "N/A" | |
| } | |
| } |