ann-sparseattention / checkpoints_packed_d64 /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_d64/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": 0.29329264909029007,
"8": 0.28124504536390305,
"12": 0.37904051691293716,
"16": 0.2890646557013194,
"20": 0.3339161326487859,
"24": 0.5209685415029526
},
"avg": 0.34958792353669804
}
},
"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": 0.31185250480969745,
"8": 0.3099167247613271,
"12": 0.41439520567655563,
"16": 0.33257966736952466,
"20": 0.3849489390850067,
"24": 0.5501216500997543
},
"avg": 0.383969115300311
}
},
"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": 0.3371334026257197,
"8": 0.3503660187125206,
"12": 0.4602071891228358,
"16": 0.3917141556739807,
"20": 0.45263657718896866,
"24": 0.5895731498797735
},
"avg": 0.43027174886729985
}
},
"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": 0.37442514797051746,
"8": 0.40738723675409955,
"12": 0.5206492592891058,
"16": 0.4700211783250173,
"20": 0.5400509238243103,
"24": 0.6421113312244415
},
"avg": 0.4924408462312486
}
},
"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": 0.4301423355937004,
"8": 0.48568252722422284,
"12": 0.599395309885343,
"16": 0.5693490405877432,
"20": 0.6461250483989716,
"24": 0.709612175822258
},
"avg": 0.5733844062520398
}
}
},
"learned_over_raw_K128": 1.0082499247253711
}