- 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
63 lines
1.2 KiB
JSON
63 lines
1.2 KiB
JSON
{
|
|
"overall_auc": 0.6741,
|
|
"per_category": {
|
|
"alias_paraphrase": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.8255,
|
|
"mean_neg": null
|
|
},
|
|
"long_fact": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.7631,
|
|
"mean_neg": null
|
|
},
|
|
"multi_entity": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.7077,
|
|
"mean_neg": null
|
|
},
|
|
"multi_hop": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.7697,
|
|
"mean_neg": null
|
|
},
|
|
"near_miss": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.7452,
|
|
"mean_neg": null
|
|
},
|
|
"noise_context": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.6853,
|
|
"mean_neg": null
|
|
},
|
|
"unknown_attribute": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": null,
|
|
"mean_neg": 0.7149
|
|
},
|
|
"update_conflict": {
|
|
"n": 25,
|
|
"auc": null,
|
|
"mean_pos": 0.7203,
|
|
"mean_neg": null
|
|
}
|
|
},
|
|
"best_threshold": {
|
|
"margin": 0.02,
|
|
"refused_unknown_pct": 40.0,
|
|
"false_refusal_pct": 3.43
|
|
},
|
|
"auc": {
|
|
"max": 0.6741,
|
|
"margin": 0.9413,
|
|
"zscore": 0.1767
|
|
}
|
|
} |