forked from animatedread/Warrior_EA
afee4cc4c1
Reduce weight decay from 0.01 to 0.001 across all backends (Network.cl, Network.mqh, WarriorCPU.cpp) to fix a training collapse issue. The original 0.01 AdamW default caused discriminative weights to decay below the calibration-capped class-prior offsets, resulting in a monotonically shrinking per-bar logit spread and eventual constant Neutral predictions (argmax degenerated once evidence tilt dropped under the prior tilt). The new value 0.001 lifts the evidence ceiling 10× while still bounding long-run weight growth, restoring effective discrimination. Note: this change must remain in sync across all four backends. |
||
|---|---|---|
| .. | ||
| build.bat | ||
| build_cpu.bat | ||
| WarriorCPU.cpp | ||
| WarriorCPU.dll | ||
| WarriorCPU.exp | ||
| WarriorCPU.h | ||
| WarriorCPU.lib | ||
| WarriorCPU.obj | ||
| WarriorCPU.pdb | ||
| WarriorDML.cpp | ||
| WarriorDML.dll | ||
| WarriorDML.exp | ||
| WarriorDML.h | ||
| WarriorDML.lib | ||
| WarriorDML.obj | ||