nonatofabio's picture
strands-decider-2B-hobson-v21: v21b seed 5
2b52a62 verified
Raw History Blame Contribute Delete
3.47 kB
{
"internal": {
"eval: [2] gen:all_conditions": {
"accuracy": 0.824,
"n": 34
},
"eval: [2] gen:dates": {
"accuracy": 0.871,
"n": 31
},
"eval: [2] gen:exception": {
"accuracy": 0.946,
"n": 37
},
"eval: [2] gen:lookup_chain": {
"accuracy": 0.8,
"n": 40
},
"eval: [2] gen:numbers": {
"accuracy": 0.848,
"n": 33
},
"eval: [2] gen:precedence": {
"accuracy": 0.917,
"n": 36
},
"eval: [2] gen:rubric": {
"accuracy": 0.794,
"n": 34
},
"eval: [2] gen:surface_trap": {
"accuracy": 0.958,
"n": 48
},
"eval: [2] gen:tradeoff": {
"accuracy": 0.7,
"n": 40
},
"eval: [2] gen:underdetermined": {
"accuracy": 0.765,
"n": 17
},
"eval: [3] gen:all_conditions": {
"accuracy": 0.889,
"n": 9
},
"eval: [3] gen:borderline_rubric": {
"accuracy": 0.538,
"n": 13
},
"eval: [3] gen:cross_artefact": {
"accuracy": 0.677,
"n": 31
},
"eval: [3] gen:dates": {
"accuracy": 0.8,
"n": 10
},
"eval: [3] gen:definition_scope": {
"accuracy": 0.667,
"n": 12
},
"eval: [3] gen:exception": {
"accuracy": 1.0,
"n": 15
},
"eval: [3] gen:judge_action": {
"accuracy": 0.714,
"n": 7
},
"eval: [3] gen:lookup_chain": {
"accuracy": 0.7,
"n": 10
},
"eval: [3] gen:missing_fact": {
"accuracy": 0.621,
"n": 29
},
"eval: [3] gen:nested_exception": {
"accuracy": 0.692,
"n": 13
},
"eval: [3] gen:numbers": {
"accuracy": 1.0,
"n": 1
},
"eval: [3] gen:precedence": {
"accuracy": 0.909,
"n": 11
},
"eval: [3] gen:rubric": {
"accuracy": 0.667,
"n": 3
},
"eval: [3] gen:running_total": {
"accuracy": 0.826,
"n": 23
},
"eval: [3] gen:surface_trap": {
"accuracy": 0.0,
"n": 1
},
"eval: [3] gen:tie_break": {
"accuracy": 0.826,
"n": 23
},
"eval: [3] gen:underdetermined": {
"accuracy": 1.0,
"n": 1
},
"eval: [3] gen:version_in_force": {
"accuracy": 0.704,
"n": 27
},
"eval: [3] gen:withdrawn_instruction": {
"accuracy": 0.75,
"n": 8
},
"eval: [4] adequacy_hs2": {
"accuracy": 0.739,
"n": 234
},
"eval: [5] gen:adequacy": {
"accuracy": 0.788,
"n": 302
},
"eval: boardgame": {
"accuracy": 0.821,
"n": 900
},
"eval: contractnli": {
"accuracy": 0.865,
"n": 1026
},
"eval: held-out short tasks": {
"accuracy": 0.65,
"ece": 0.06,
"n": 6000,
"nll": 0.851
},
"eval: hotpotqa (held out)": {
"accuracy": 0.746,
"n": 959
},
"eval: musique": {
"accuracy": 0.882,
"n": 1199
},
"eval: musique, answerable": {
"accuracy": 0.886,
"n": 599
},
"eval: musique, unanswerable": {
"accuracy": 0.877,
"n": 600
}
},
"jevbench": [
{
"accuracy": 0.7619047619047619,
"arm": "w4096",
"brier": 0.32261680428571426,
"ece": 0.06391125541125536,
"n": 231,
"n_correct": 176,
"schema_validity_strict": 1.0,
"served": "these files",
"window": 4096
}
],
"name": "hobson-2b-v21",
"role": "final",
"run_id": "v21b-s5"
}