alephlm-adopt-0 / adopt0 /adopt0_bench.json
AbstractPhil's picture
adopt-0 standardized bench
f7a1e49 verified
Raw
History Blame Contribute Delete
2.86 kB
{
"stock": {
"arc_easy": {
"sample_len": 2376.0,
"acc,none": 0.6561,
"acc_stderr,none": 0.0097,
"acc_norm,none": 0.5888,
"acc_norm_stderr,none": 0.0101
},
"hellaswag": {
"sample_len": 10042.0,
"acc,none": 0.4055,
"acc_stderr,none": 0.0049,
"acc_norm,none": 0.5251,
"acc_norm_stderr,none": 0.005
},
"piqa": {
"sample_len": 1838.0,
"acc,none": 0.7057,
"acc_stderr,none": 0.0106,
"acc_norm,none": 0.7051,
"acc_norm_stderr,none": 0.0106
},
"winogrande": {
"sample_len": 1267.0,
"acc,none": 0.5564,
"acc_stderr,none": 0.014
},
"_mean": 0.5939
},
"aleph": {
"arc_easy": {
"sample_len": 2376.0,
"acc,none": 0.6393,
"acc_stderr,none": 0.0099,
"acc_norm,none": 0.596,
"acc_norm_stderr,none": 0.0101
},
"hellaswag": {
"sample_len": 10042.0,
"acc,none": 0.3754,
"acc_stderr,none": 0.0048,
"acc_norm,none": 0.4669,
"acc_norm_stderr,none": 0.005
},
"piqa": {
"sample_len": 1838.0,
"acc,none": 0.6806,
"acc_stderr,none": 0.0109,
"acc_norm,none": 0.6779,
"acc_norm_stderr,none": 0.0109
},
"winogrande": {
"sample_len": 1267.0,
"acc,none": 0.5675,
"acc_stderr,none": 0.0139
},
"_mean": 0.5771
},
"mlp": {
"arc_easy": {
"sample_len": 2376.0,
"acc,none": 0.6423,
"acc_stderr,none": 0.0098,
"acc_norm,none": 0.5968,
"acc_norm_stderr,none": 0.0101
},
"hellaswag": {
"sample_len": 10042.0,
"acc,none": 0.3789,
"acc_stderr,none": 0.0048,
"acc_norm,none": 0.4743,
"acc_norm_stderr,none": 0.005
},
"piqa": {
"sample_len": 1838.0,
"acc,none": 0.6915,
"acc_stderr,none": 0.0108,
"acc_norm,none": 0.6746,
"acc_norm_stderr,none": 0.0109
},
"winogrande": {
"sample_len": 1267.0,
"acc,none": 0.5462,
"acc_stderr,none": 0.014
},
"_mean": 0.573
},
"teacher": {
"arc_easy": {
"sample_len": 2376.0,
"acc,none": 0.7668,
"acc_stderr,none": 0.0087,
"acc_norm,none": 0.7584,
"acc_norm_stderr,none": 0.0088
},
"hellaswag": {
"sample_len": 10042.0,
"acc,none": 0.5086,
"acc_stderr,none": 0.005,
"acc_norm,none": 0.6822,
"acc_norm_stderr,none": 0.0046
},
"piqa": {
"sample_len": 1838.0,
"acc,none": 0.7612,
"acc_stderr,none": 0.0099,
"acc_norm,none": 0.7601,
"acc_norm_stderr,none": 0.01
},
"winogrande": {
"sample_len": 1267.0,
"acc,none": 0.629,
"acc_stderr,none": 0.0136
},
"_mean": 0.7074
}
}