docs: update model card — 5000-step run

README.md

@@ -131,7 +131,7 @@ Prepend `by <artist>, ` at the start of your prompt.
 | Base model | `Tongyi-MAI/Z-Image-Turbo` |
 | Fine-tuning method | LoRA rank=32, alpha=32 — merged into weights |
 | Target modules | `to_q`, `to_k`, `to_v`, `w1`, `w2`, `w3` |
-| Training steps | 3 000 (EMA decay=0.9999) |
+| Training steps | **5 000** (3 000 at lr=1e-4 + 2 000 continued at lr=5e-5, EMA decay=0.9999) |
 | Training resolution | 512 × 512 |
 | Inference steps | 8 |
 | CFG scale | 0.0 (CFG-free) |