refract-hsmall-blend2 / eval /eval_base_v5.json
Nikhil0097's picture
Initial upload: weights + model card
263e9a6 verified
Raw
History Blame Contribute Delete
345 Bytes
{
"label": "base",
"n_scored": 20,
"n_fail": 0,
"judge_means": {
"admits_multiplicity": 4.4,
"distinctness": 2.35,
"concreteness": 2.75,
"decisiveness": 2.7,
"foresight": 2.1,
"viability": 2.5
},
"judge_overall_mean": 2.8,
"viability_pass(>=3)": 50.0,
"distinct_pass(>=4)": 5.0,
"full_pd_diag": 0.3183
}