modelops-research-lab / evaluation_results.json
Hugdrigo's picture
Upload 28 files
7c9e8d9 verified
Raw History Blame Contribute Delete
1.5 kB
{
"project": "ModelOps Research Lab",
"release": "2.0.0",
"dataset": "Academic Rhetorical Intent Mini v1.1",
"source_type": "synthetic_curated",
"train_count": 842,
"test_count": 130,
"challenge_count": 54,
"run_type": "recomputed Node baselines",
"methods": {
"nb": {
"iid": {
"n": 130,
"correct": 130,
"accuracy": 1,
"macroF1": 1
},
"challenge": {
"n": 54,
"correct": 40,
"accuracy": 0.7407407407407407,
"macroF1": 0.7362809928289805
}
},
"word": {
"iid": {
"n": 130,
"correct": 128,
"accuracy": 0.9846153846153847,
"macroF1": 0.9844877344877346
},
"challenge": {
"n": 54,
"correct": 39,
"accuracy": 0.7222222222222222,
"macroF1": 0.7061942959001782
}
},
"char": {
"iid": {
"n": 130,
"correct": 124,
"accuracy": 0.9538461538461539,
"macroF1": 0.9537925842273668
},
"challenge": {
"n": 54,
"correct": 38,
"accuracy": 0.7037037037037037,
"macroF1": 0.6836089069592907
}
},
"hybrid": {
"iid": {
"n": 130,
"correct": 127,
"accuracy": 0.9769230769230769,
"macroF1": 0.9767441860465116
},
"challenge": {
"n": 54,
"correct": 42,
"accuracy": 0.7777777777777778,
"macroF1": 0.7617571707045391
}
}
}
}