train: --eval-ckpt eval-only mode (v0-vs-v1 same-set val loss)

Expose eval_loss() and add a --eval-ckpt <path> branch to bin/train: load an
existing checkpoint into a model of the given arch and score it on the held-out
val split, then exit. Lets v0 and v1 be measured on the identical validation set
(the acceptance metric) without a separate eval binary.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

crates/xtrain-train/src/train_loop.rs

@@ -153,8 +153,8 @@ pub fn train(
 
 /// Mean cross-entropy over `batches` deterministic, non-overlapping windows of
 /// the validation corpus (no backward — eval only). Deterministic so val loss is
-/// comparable across steps and runs.
-fn eval_loss(
+/// comparable across steps and runs (and across models — the v0-vs-v1 metric).
+pub fn eval_loss(
     model: &TinyTransformer,
     device: Device,
     valid: &Corpus,