README: add full_acc@0 row + cond_acc@0 note (complete per-position table)

README.md

@@ -37,17 +37,24 @@ replacement in the same vLLM serving path.
 
 Per-position draft accuracy on a fixed held-out val split, measured during
 training (teacher-forced argmax match; this is a *training-time* metric and is
-not directly comparable to runtime accept-length). Continual FT lifts the
-weaker later positions most:
+not directly comparable to runtime accept-length). `acc@i` is the accuracy at
+TTT position `i` (`i = 0, 1, 2`). `full_acc@i` requires positions `0..i` all
+correct; `cond_acc@i` is conditioned on `0..i-1` being correct. Continual FT
+lifts the weaker later positions most, while the already-strong position 0
+holds:
 
 | metric | init | final | rel. |
 | --- | --- | --- | --- |
 | val_loss | 7.69 | 5.62 | -27% |
+| full_acc@0 | 0.614 | 0.656 | +7% |
 | full_acc@1 | 0.253 | 0.367 | +45% |
 | full_acc@2 | 0.085 | 0.184 | +116% |
 | cond_acc@1 | 0.412 | 0.559 | +36% |
 | cond_acc@2 | 0.336 | 0.499 | +49% |
 
+(`cond_acc@0` equals `full_acc@0` by definition — position 0 has no prior to
+condition on — so it is the same 0.614 -> 0.656.)
+
 A runtime `accept_length` benchmark (vLLM 0.20, `num_speculative_tokens=3`) is
 pending and will be added once measured.