| { | |
| "PPL": 16.7308349609375, | |
| "arc_challenge": { | |
| "acc": 0.2150170648464164, | |
| "acc_stderr": 0.012005717634133614, | |
| "acc_norm": 0.26109215017064846, | |
| "acc_norm_stderr": 0.012835523909473867 | |
| }, | |
| "arc_easy": { | |
| "acc": 0.37836700336700335, | |
| "acc_stderr": 0.00995157568333195, | |
| "acc_norm": 0.3611111111111111, | |
| "acc_norm_stderr": 0.009856013425811242 | |
| }, | |
| "hellaswag": { | |
| "acc": 0.33519219279028084, | |
| "acc_stderr": 0.00471092856998574, | |
| "acc_norm": 0.391256721768572, | |
| "acc_norm_stderr": 0.004870342592915051 | |
| }, | |
| "piqa": { | |
| "acc": 0.6142546245919478, | |
| "acc_stderr": 0.011357166777524042, | |
| "acc_norm": 0.6196953210010882, | |
| "acc_norm_stderr": 0.011326620892570317 | |
| }, | |
| "winogrande": { | |
| "acc": 0.4988161010260458, | |
| "acc_stderr": 0.014052446290529019 | |
| }, | |
| "QA Avg": 0.4083293973243388 | |
| } |