26 lines
880 B
JSON
26 lines
880 B
JSON
{
|
|
"ckpt": "ConeML/coneml-810m-alpha-arithmetic",
|
|
"math_200": 138,
|
|
"everyday_20_auto": 6,
|
|
"by_category": {
|
|
"everyday::causal-evidence": "0/3",
|
|
"everyday::everyday-arithmetic": "2/2",
|
|
"everyday::money-change": "0/3",
|
|
"everyday::object-choice": "2/3",
|
|
"everyday::practical-judgment": "1/2",
|
|
"everyday::quantity-judgment": "0/2",
|
|
"everyday::temporal-order": "0/2",
|
|
"everyday::time-margin": "1/3",
|
|
"math::add-1d": "20/20",
|
|
"math::add-2d-carry": "30/30",
|
|
"math::missing-addend": "18/20",
|
|
"math::mul": "20/20",
|
|
"math::sub-2d-borrow": "29/30",
|
|
"math::transitive": "0/20",
|
|
"math::word-2step": "2/40",
|
|
"math::word-compare": "19/20"
|
|
},
|
|
"math_200_corrected": 154,
|
|
"correction": "transitive items scored by expected-name match on first line; original scorer extracted numbers only and zeroed all transitive rows"
|
|
}
|