ann-sparseattention / checkpoints /search_step_2000.compare_retrieval.json
datasysdev's picture
Upload clean block-causal and packed pilot checkpoints
57c6b5b verified
{
"model": "Qwen/Qwen3-4B-Instruct-2507",
"ckpt": "/tmp/checkpoints/search_step_2000.pt",
"by_K": {
"16": {
"raw_qk": {
"per_layer": {
"4": 0.4115331669648488,
"8": 0.2802686393260956,
"12": 0.1508728675544262,
"16": 0.07771651136378448,
"20": 0.053202067812283836,
"24": 0.10271163408954938
},
"avg": 0.1793841478518314
},
"learned": {
"per_layer": {
"4": 0.1072007929906249,
"8": 0.23697869976361594,
"12": 0.11224483884871006,
"16": 0.07637482260664304,
"20": 0.06903641019016504,
"24": 0.10397349204868078
},
"avg": 0.11763484274140662
}
},
"32": {
"raw_qk": {
"per_layer": {
"4": 0.4668281575043996,
"8": 0.3293568876882394,
"12": 0.19662011042237282,
"16": 0.11227216385304928,
"20": 0.07988839099804561,
"24": 0.144585732370615
},
"avg": 0.22159190713945362
},
"learned": {
"per_layer": {
"4": 0.13327929687996706,
"8": 0.2569987513124943,
"12": 0.1446449818710486,
"16": 0.10432848272224267,
"20": 0.09580977975080411,
"24": 0.13778831561406454
},
"avg": 0.14547493469177022
}
},
"64": {
"raw_qk": {
"per_layer": {
"4": 0.5168702056010565,
"8": 0.390024371445179,
"12": 0.25787363573908806,
"16": 0.15796820322672525,
"20": 0.11998403631150723,
"24": 0.2020296814541022
},
"avg": 0.2741250222962764
},
"learned": {
"per_layer": {
"4": 0.1732035626967748,
"8": 0.2893482334911823,
"12": 0.19321986908713976,
"16": 0.14695298795898756,
"20": 0.13634028658270836,
"24": 0.1862101349979639
},
"avg": 0.18754584580245945
}
},
"128": {
"raw_qk": {
"per_layer": {
"4": 0.571592112382253,
"8": 0.463805615901947,
"12": 0.33948806673288345,
"16": 0.22183777391910553,
"20": 0.18010229741533598,
"24": 0.27901028965910274
},
"avg": 0.34263935933510464
},
"learned": {
"per_layer": {
"4": 0.235384251922369,
"8": 0.3402557211617629,
"12": 0.2643987759947777,
"16": 0.21102494125564894,
"20": 0.19678996006647745,
"24": 0.25442706421017647
},
"avg": 0.25038011910186875
}
},
"256": {
"raw_qk": {
"per_layer": {
"4": 0.6327291478713354,
"8": 0.5521376008788744,
"12": 0.43828647087017697,
"16": 0.31400871525208157,
"20": 0.2687250425418218,
"24": 0.37980743249257404
},
"avg": 0.4309490683178107
},
"learned": {
"per_layer": {
"4": 0.3288092017173767,
"8": 0.41752680391073227,
"12": 0.36623430997133255,
"16": 0.30524607251087826,
"20": 0.2853706416984399,
"24": 0.34850213179985684
},
"avg": 0.3419481936014361
}
}
},
"learned_over_raw_K128": 0.7307395145371917
}