ann-sparseattention / checkpoints_packed_d256 /search_step_1000.compare_retrieval.json
datasysdev's picture
Upload clean block-causal and packed pilot checkpoints
57c6b5b verified
Raw
History Blame Contribute Delete
3.36 kB
{
"model": "Qwen/Qwen3-4B-Instruct-2507",
"ckpt": "/tmp/checkpoints_packed_d256/search_step_1000.pt",
"by_K": {
"16": {
"raw_qk": {
"per_layer": {
"4": 0.31979141881068546,
"8": 0.3186202198266983,
"12": 0.14174955089886984,
"16": 0.20945234596729279,
"20": 0.2801314915219943,
"24": 0.49455158909161884
},
"avg": 0.2940494360195266
},
"learned": {
"per_layer": {
"4": 0.2933313399553299,
"8": 0.29298429439465207,
"12": 0.39142733812332153,
"16": 0.2983766943216324,
"20": 0.3438563868403435,
"24": 0.525188535451889
},
"avg": 0.35752743151452804
}
},
"32": {
"raw_qk": {
"per_layer": {
"4": 0.341281255086263,
"8": 0.36785539239645004,
"12": 0.21019610886772475,
"16": 0.28323352212707203,
"20": 0.3406280030806859,
"24": 0.5262841482957205
},
"avg": 0.3449130716423194
},
"learned": {
"per_layer": {
"4": 0.3145047202706337,
"8": 0.3253612567981084,
"12": 0.4279355009396871,
"16": 0.344377006093661,
"20": 0.3977118283510208,
"24": 0.556083157658577
},
"avg": 0.39432891168528134
}
},
"64": {
"raw_qk": {
"per_layer": {
"4": 0.37279334167639416,
"8": 0.4341067870457967,
"12": 0.295872134466966,
"16": 0.37213313827912015,
"20": 0.4122797225912412,
"24": 0.5643380333979925
},
"avg": 0.40858719290958506
},
"learned": {
"per_layer": {
"4": 0.34352220843235654,
"8": 0.37063097457091015,
"12": 0.4752006282409032,
"16": 0.4067305897672971,
"20": 0.46815096338589984,
"24": 0.5977186262607574
},
"avg": 0.44365899844302076
}
},
"128": {
"raw_qk": {
"per_layer": {
"4": 0.4215788046518962,
"8": 0.5176494866609573,
"12": 0.4037476380666097,
"16": 0.47523776690165204,
"20": 0.49859579155842465,
"24": 0.6136594414710999
},
"avg": 0.48841148821844
},
"learned": {
"per_layer": {
"4": 0.3849342664082845,
"8": 0.43360541264216107,
"12": 0.5375104447205862,
"16": 0.488710917532444,
"20": 0.5576231330633163,
"24": 0.6525773753722509
},
"avg": 0.5091602582898406
}
},
"256": {
"raw_qk": {
"per_layer": {
"4": 0.4964489738146464,
"8": 0.6146760632594427,
"12": 0.5339744637409846,
"16": 0.5874835352102915,
"20": 0.602066790064176,
"24": 0.6779818137486776
},
"avg": 0.5854386066397032
},
"learned": {
"per_layer": {
"4": 0.44419410079717636,
"8": 0.5183951507012049,
"12": 0.6179872999588648,
"16": 0.5908408363660177,
"20": 0.6638876696427664,
"24": 0.7216567993164062
},
"avg": 0.592826976130406
}
}
},
"learned_over_raw_K128": 1.0424821499328059
}