docs: add Benchmark / Training metrics section

README.md

@@ -56,6 +56,39 @@ Derived from the internal **eu-kiki / mascarade** curation. All upstream samples
 are synthetic, permissively-licensed, or generated from Apache-2.0 base resources.
 See the [Ailiance-fr catalog](https://huggingface.co/Ailiance-fr) for related cards.
 
+## Training metrics
+
+Extracted from training log (`medium35-cpp-curriculum.log`):
+
+| Metric | Value |
+|---|---:|
+| Final train loss | 0.384 |
+| Final validation loss | 0.471 |
+| Val loss reduction | +1.817 (from 2.288) |
+| Iterations completed | 500 |
+| Trainable parameters | 0.224% (279.708M / 125025.989M) |
+
+> Validation loss is measured every 200 iterations on a held-out split of the
+> training corpus (`val_batches=5`, `mlx-lm` LoRA trainer).
+
+## Benchmark on production tasks
+
+This LoRA has **not yet been evaluated** through the
+[`electron-bench`](https://github.com/ailiance/ailiance-bench/blob/main) functional benchmark
+pipeline. The current pipeline targets the `gemma-4-E4B` base only; support for
+the **devstral** base is on the roadmap
+([open issues](https://github.com/ailiance/ailiance-bench/issues)).
+
+For a comparable reference matrix on a related domain (electronics, embedded,
+KiCad), see the Gemma champions:
+
+| Adapter | Highlights |
+|---|---|
+| [`Ailiance-fr/gemma-4-E4B-eukiki-lora`](https://huggingface.co/Ailiance-fr/gemma-4-E4B-eukiki-lora) | +55 P1-DSL, +42 P1-PCB, +25 SPICE, +38 P3 |
+| [`Ailiance-fr/gemma-4-E4B-mascarade-lora`](https://huggingface.co/Ailiance-fr/gemma-4-E4B-mascarade-lora) | +48 P3 extraction |
+
+Full base-vs-LoRA matrix: [`compare_base_vs_lora.md`](https://github.com/ailiance/ailiance-bench/blob/main/bench-results/compare_base_vs_lora.md).
+
 ## License chain
 
 | Component                         | License           |