Upload README.md with huggingface_hub

README.md

@@ -20,10 +20,14 @@ Trained with Unsloth, LoRA **r=32 / α=64**, lr 1e-4, **24,000 unique training c
 
 | Subfolder | MP-20 % | Best-of-10 match (full 8,096 MPTS-52 test) |
 |---|---:|---:|
-| `comp_mp20_00` | 0 (pure MPTS-52 baseline) | 30.1% |
-| `comp_mp20_50` | 50 : 50 | 29.5% |
-
-*(More ratios — 25 / 75 / 100 — to be added as training completes.)*
+| `comp_mp20_00`  | 0 (pure MPTS-52 baseline) | 30.1% |
+| `comp_mp20_25`  | 25 | 30.4% |
+| `comp_mp20_50`  | 50 | 29.5% |
+| `comp_mp20_75`  | 75 | 28.0% |
+| `comp_mp20_100` | 100 (pure MP-20) | 26.6% |
+
+**Finding:** at matched volume + steps, match declines monotonically as the MP-20 fraction rises —
+the gain reported for "combined" data was **volume, not symmetry composition**.
 
 Each subfolder contains: `model/` (LoRA adapter + `adapter_config.json`), `tokenizer/`,
 `config.json`, and `training_stats.json`.