@hmharness/evolution 0.14.11 → 0.14.12
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/reward-model.js +7 -1
- package/package.json +1 -1
package/dist/reward-model.js
CHANGED
|
@@ -146,7 +146,13 @@ export function exportDpoPairs(labels, insights, taskOf, answerOf, opts = {}) {
|
|
|
146
146
|
for (const b of rows) {
|
|
147
147
|
if (a.session >= b.session)
|
|
148
148
|
continue;
|
|
149
|
-
|
|
149
|
+
// round: 3/5 - 1/5 = 0.39999999999999997 in floats, and the epsilon
|
|
150
|
+
// silently ate every 2-step in-bucket pair (★1 vs ★3) - the judge's
|
|
151
|
+
// whole variance band
|
|
152
|
+
// abs: rows iterate in label-file order - the lower score can come first
|
|
153
|
+
// (judge labels do), which made a.y - b.y negative and silently dropped
|
|
154
|
+
// the pair; rounding kills the 3/5-1/5 float epsilon
|
|
155
|
+
const gap = Math.round(Math.abs(a.y - b.y) * 1000) / 1000;
|
|
150
156
|
if (gap < minGap)
|
|
151
157
|
continue;
|
|
152
158
|
const hi = gap > 0 ? a : b;
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@hmharness/evolution",
|
|
3
|
-
"version": "0.14.
|
|
3
|
+
"version": "0.14.12",
|
|
4
4
|
"description": "hmharness evolution subsystem: persistent memory, insight capture, skill library, and the bench that gives evolution its fitness signal. First-class kernel citizen, not a plugin.",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "dist/index.js",
|