- 引入 MemoryRouterXL 与 v5/v6 流式多线程训练/编码管线 - 修复 prepare_memory_router_dataset 候选池重建缺陷(mega 家族 3568x 加速,输出逐字节相同) - 修复 v5 被破坏的拒答与多跳标签(train 未知样本 319 -> 16319,multi_hop 平均正例 1.00 -> 2.00) - 同存储预算下 V2-128 v6 逐轴 22/22 通过:Top-1 41.12% -> 94.62%,未知拒答 0.00% -> 100.00% - 记录三条被实测推翻的显然优化(logits_to_keep=1 反而慢 55%、XL 容量未带来收益) - 记忆手术跨架构可移植性 14/14,读写关闭时与原生模型逐位相同
436 lines
13 KiB
JSON
436 lines
13 KiB
JSON
{
|
|
"candidates": [
|
|
"XL-512 best",
|
|
"XL-512 final(step100k)"
|
|
],
|
|
"baselines": [
|
|
"V2-512 best(step1000)",
|
|
"V2-512 final(step100k)"
|
|
],
|
|
"passed_axes": 20,
|
|
"failed_axes": 22,
|
|
"skipped_axes": 0,
|
|
"dominates": false,
|
|
"rows": [
|
|
{
|
|
"axis": "Top-1 正确率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.6712104689203926,
|
|
"candidate_value": 0.608505997818975,
|
|
"delta": -0.06270447110141764,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "Top-1 正确率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.6712104689203926,
|
|
"candidate_value": 0.5436205016357688,
|
|
"delta": -0.1275899672846238,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "Recall@1",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.6712104689203926,
|
|
"candidate_value": 0.608505997818975,
|
|
"delta": -0.06270447110141764,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "Recall@1",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.6712104689203926,
|
|
"candidate_value": 0.5436205016357688,
|
|
"delta": -0.1275899672846238,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "Recall@3",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8876772082878953,
|
|
"candidate_value": 0.9296619411123228,
|
|
"delta": 0.041984732824427495,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "Recall@3",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8876772082878953,
|
|
"candidate_value": 0.8533260632497274,
|
|
"delta": -0.03435114503816794,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "Recall@5",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.9492911668484187,
|
|
"candidate_value": 0.9732824427480916,
|
|
"delta": 0.02399127589967287,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "Recall@5",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.9492911668484187,
|
|
"candidate_value": 0.9193020719738277,
|
|
"delta": -0.029989094874591005,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "MRR",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.7908385671852008,
|
|
"candidate_value": 0.759814160403073,
|
|
"delta": -0.03102440678212781,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "MRR",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.7908385671852008,
|
|
"candidate_value": 0.6950444145765433,
|
|
"delta": -0.09579415260865753,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "nDCG@3",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.7999554748364778,
|
|
"candidate_value": 0.792764395065411,
|
|
"delta": -0.007191079771066811,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "nDCG@3",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.7999554748364778,
|
|
"candidate_value": 0.7170573814087626,
|
|
"delta": -0.08289809342771515,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "多跳证据全中(Top-3)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8865866957470011,
|
|
"candidate_value": 0.9285714285714286,
|
|
"delta": 0.041984732824427495,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "多跳证据全中(Top-3)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8865866957470011,
|
|
"candidate_value": 0.8522355507088332,
|
|
"delta": -0.03435114503816794,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "多跳证据全中(仅多正例)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.5,
|
|
"candidate_value": 0.5,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "多跳证据全中(仅多正例)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.5,
|
|
"candidate_value": 0.5,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "hop 正确率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9969072164948454,
|
|
"candidate_value": 0.9938144329896907,
|
|
"delta": -0.003092783505154628,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "hop 正确率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9969072164948454,
|
|
"candidate_value": 0.9969072164948454,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "hop 欠预测率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.003271537622682661,
|
|
"candidate_value": 0.003271537622682661,
|
|
"delta": 0.0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "hop 欠预测率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.003271537622682661,
|
|
"candidate_value": 0.003271537622682661,
|
|
"delta": 0.0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "need F1 (门槛 0.50)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9989082969432315,
|
|
"candidate_value": 0.9961894393032119,
|
|
"delta": -0.0027188576400195563,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "need F1 (门槛 0.50)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9989082969432315,
|
|
"candidate_value": 0.9989082969432315,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "need 召回 (门槛 0.50)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.9978189749182116,
|
|
"candidate_value": 0.9978189749182116,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "need 召回 (门槛 0.50)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.9978189749182116,
|
|
"candidate_value": 0.9978189749182116,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "未知拒答率 (门槛 0.50)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 1.0,
|
|
"candidate_value": 0.9056603773584906,
|
|
"delta": -0.09433962264150941,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "未知拒答率 (门槛 0.50)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 1.0,
|
|
"candidate_value": 1.0,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "已知问题被误拒率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.0021810250817884407,
|
|
"candidate_value": 0.0021810250817884407,
|
|
"delta": 0.0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "已知问题被误拒率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.0021810250817884407,
|
|
"candidate_value": 0.0021810250817884407,
|
|
"delta": 0.0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "未知问题被误读率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.0,
|
|
"candidate_value": 0.09433962264150944,
|
|
"delta": 0.09433962264150944,
|
|
"direction": "min",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "未知问题被误读率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.0,
|
|
"candidate_value": 0.0,
|
|
"delta": 0.0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "仲裁准确率",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9979381443298969,
|
|
"candidate_value": 0.9927835051546392,
|
|
"delta": -0.005154639175257714,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "仲裁准确率",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 0.9979381443298969,
|
|
"candidate_value": 0.9979381443298969,
|
|
"delta": 0.0,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "平均分数余量",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 3.8836881184794065,
|
|
"candidate_value": 6.709678303645345,
|
|
"delta": 2.825990185165938,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "平均分数余量",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 final(step100k)",
|
|
"baseline_value": 3.8836881184794065,
|
|
"candidate_value": 25.375655539715694,
|
|
"delta": 21.49196742123629,
|
|
"direction": "max",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "单查询延迟 ms (GPU)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8951400030249109,
|
|
"candidate_value": 1.3101640006061643,
|
|
"delta": 0.4150239975812534,
|
|
"direction": "min",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "单查询延迟 ms (GPU)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 0.8951400030249109,
|
|
"candidate_value": 1.2458240000220637,
|
|
"delta": 0.3506839969971528,
|
|
"direction": "min",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "路由 QPS (GPU)",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 1117.1436832459055,
|
|
"candidate_value": 763.263224708767,
|
|
"delta": -353.88045853713857,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "路由 QPS (GPU)",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 1117.1436832459055,
|
|
"candidate_value": 802.6815986706708,
|
|
"delta": -314.4620845752347,
|
|
"direction": "max",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "地址字节/记录",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 2048,
|
|
"candidate_value": 2048,
|
|
"delta": 0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "地址字节/记录",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 2048,
|
|
"candidate_value": 2048,
|
|
"delta": 0,
|
|
"direction": "min",
|
|
"pass": true
|
|
},
|
|
{
|
|
"axis": "参数量",
|
|
"candidate": "XL-512 best",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 4741902,
|
|
"candidate_value": 7898127,
|
|
"delta": 3156225,
|
|
"direction": "min",
|
|
"pass": false
|
|
},
|
|
{
|
|
"axis": "参数量",
|
|
"candidate": "XL-512 final(step100k)",
|
|
"baseline": "V2-512 best(step1000)",
|
|
"baseline_value": 4741902,
|
|
"candidate_value": 7898127,
|
|
"delta": 3156225,
|
|
"direction": "min",
|
|
"pass": false
|
|
}
|
|
]
|
|
} |