1-parameter-classifier / stage_2 /pruning_curve.json
phanerozoic's picture
Stage 2: attention-head pruning results + mask + apply_mask.py
a7e09b2 verified
{
"baseline_F1": 0.8939393758773804,
"curve": [
{
"heads_pruned": 1,
"F1": 0.9037178754806519,
"F1_drop": -0.009778499603271484,
"precision": 0.942345917224884,
"recall": 0.8681318759918213
},
{
"heads_pruned": 5,
"F1": 0.9085714221000671,
"F1_drop": -0.014632046222686768,
"precision": 0.9464285969734192,
"recall": 0.8736263513565063
},
{
"heads_pruned": 10,
"F1": 0.9158878326416016,
"F1_drop": -0.02194845676422119,
"precision": 0.9351145029067993,
"recall": 0.8974359035491943
},
{
"heads_pruned": 15,
"F1": 0.8949342966079712,
"F1_drop": -0.0009949207305908203,
"precision": 0.9173076748847961,
"recall": 0.8736263513565063
},
{
"heads_pruned": 20,
"F1": 0.8971269726753235,
"F1_drop": -0.0031875967979431152,
"precision": 0.908067524433136,
"recall": 0.8864468932151794
},
{
"heads_pruned": 30,
"F1": 0.3267175555229187,
"F1_drop": 0.5672218203544617,
"precision": 0.9816513657569885,
"recall": 0.19597069919109344
},
{
"heads_pruned": 40,
"F1": 0.21859706938266754,
"F1_drop": 0.6753423064947128,
"precision": 1.0,
"recall": 0.12271062284708023
},
{
"heads_pruned": 50,
"F1": 0.5074626803398132,
"F1_drop": 0.38647669553756714,
"precision": 0.9790576100349426,
"recall": 0.3424908518791199
},
{
"heads_pruned": 60,
"F1": 0.003656307002529502,
"F1_drop": 0.8902830688748509,
"precision": 1.0,
"recall": 0.0018315018387511373
},
{
"heads_pruned": 80,
"F1": 0.003656307002529502,
"F1_drop": 0.8902830688748509,
"precision": 1.0,
"recall": 0.0018315018387511373
},
{
"heads_pruned": 100,
"F1": 0.0,
"F1_drop": 0.8939393758773804,
"precision": 0.0,
"recall": 0.0
},
{
"heads_pruned": 120,
"F1": 0.0,
"F1_drop": 0.8939393758773804,
"precision": 0.0,
"recall": 0.0
},
{
"heads_pruned": 144,
"F1": 0.0,
"F1_drop": 0.8939393758773804,
"precision": 0.0,
"recall": 0.0
}
]
}