lm1-misc-oscar / 3b977b77b /evaluation /lm1-3b9-77b-oscar-results_lm-eval_global_step73814_2022-12-03-12-11-41.json
Muennighoff's picture
Add
8ec84fa
raw
history blame contribute delete
No virus
1.12 kB
{
"results": {
"boolq": {
"acc": 0.5431192660550459,
"acc_stderr": 0.008712475433089477
},
"hellaswag": {
"acc": 0.39543915554670384,
"acc_stderr": 0.00487945547466381,
"acc_norm": 0.5036845249950209,
"acc_norm_stderr": 0.004989645929811447
},
"arc_challenge": {
"acc": 0.23890784982935154,
"acc_stderr": 0.012461071376316612,
"acc_norm": 0.27986348122866894,
"acc_norm_stderr": 0.013119040897725923
},
"arc_easy": {
"acc": 0.561026936026936,
"acc_stderr": 0.010183076012972067,
"acc_norm": 0.5071548821548821,
"acc_norm_stderr": 0.01025873302244637
},
"sciq": {
"acc": 0.815,
"acc_stderr": 0.012285191326386693,
"acc_norm": 0.751,
"acc_norm_stderr": 0.013681600278702293
}
},
"versions": {
"boolq": 1,
"hellaswag": 0,
"arc_challenge": 0,
"arc_easy": 0,
"sciq": 0
}
}