Muennighoff's picture
add
f6c5fad
raw
history blame contribute delete
No virus
2.45 kB
{
"results": {
"anli_r1": {
"acc": 0.337,
"acc_stderr": 0.014955087918653607
},
"anli_r2": {
"acc": 0.337,
"acc_stderr": 0.014955087918653605
},
"anli_r3": {
"acc": 0.335,
"acc_stderr": 0.013630871843821474
},
"cb": {
"acc": 0.5892857142857143,
"acc_stderr": 0.06633634150359538,
"f1": 0.365874363327674
},
"copa": {
"acc": 0.71,
"acc_stderr": 0.04560480215720684
},
"hellaswag": {
"acc": 0.36217884883489343,
"acc_stderr": 0.004796478664403837,
"acc_norm": 0.4455287791276638,
"acc_norm_stderr": 0.0049600825288524325
},
"rte": {
"acc": 0.5667870036101083,
"acc_stderr": 0.029826764082138267
},
"winogrande": {
"acc": 0.510655090765588,
"acc_stderr": 0.0140492945362904
},
"storycloze_2016": {
"acc": 0.6419027258150721,
"acc_stderr": 0.011087006809925708
},
"boolq": {
"acc": 0.5657492354740061,
"acc_stderr": 0.008669116184243044
},
"arc_easy": {
"acc": 0.5454545454545454,
"acc_stderr": 0.010217299762709419,
"acc_norm": 0.5374579124579124,
"acc_norm_stderr": 0.010230952104570801
},
"arc_challenge": {
"acc": 0.23122866894197952,
"acc_stderr": 0.012320858834772273,
"acc_norm": 0.2636518771331058,
"acc_norm_stderr": 0.012875929151297065
},
"sciq": {
"acc": 0.9,
"acc_stderr": 0.009491579957525057,
"acc_norm": 0.892,
"acc_norm_stderr": 0.009820001651345694
},
"piqa": {
"acc": 0.705114254624592,
"acc_stderr": 0.010639030620156998,
"acc_norm": 0.6974972796517954,
"acc_norm_stderr": 0.010717199698083898
}
},
"versions": {
"anli_r1": 0,
"anli_r2": 0,
"anli_r3": 0,
"cb": 1,
"copa": 0,
"hellaswag": 0,
"rte": 0,
"winogrande": 0,
"storycloze_2016": 0,
"boolq": 1,
"arc_easy": 0,
"arc_challenge": 0,
"sciq": 0,
"piqa": 0
}
}