| { | |
| "PPL": 11.989105224609375, | |
| "arc_challenge": { | |
| "acc": 0.2431740614334471, | |
| "acc_stderr": 0.012536554144587092, | |
| "acc_norm": 0.28071672354948807, | |
| "acc_norm_stderr": 0.013131238126975583 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.4196127946127946, | |
| "acc_stderr": 0.010126315840891551, | |
| "acc_norm": 0.38846801346801346, | |
| "acc_norm_stderr": 0.010001276044485233 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.3899621589324836, | |
| "acc_stderr": 0.004867445945277156, | |
| "acc_norm": 0.49790878311093406, | |
| "acc_norm_stderr": 0.004989737768749952 | |
| }, | |
| "piqa": { | |
| "acc": 0.6621327529923831, | |
| "acc_stderr": 0.011035474307853836, | |
| "acc_norm": 0.6692056583242655, | |
| "acc_norm_stderr": 0.01097752058471443 | |
| }, | |
| "winogrande": { | |
| "acc": 0.5027624309392266, | |
| "acc_stderr": 0.014052271211616441 | |
| }, | |
| "QA Avg": 0.443528839782067 | |
| } |