justfile/run_id: r override for low-rank antipasto sweeps

bench-variant gains an r_override arg (alpha tracks r for the antipasto family);
run_id appends __r<N> when an antipasto-family run uses r!=256, so the low-rank
corda-vs-antipasto sweep does not overwrite the r=256 results.

Co-Authored-By: Claudypoo <noreply@anthropic.com>

justfile

@@ -75,7 +75,7 @@ metamath-queue variant="lora" steps="5000" model="Qwen/Qwen3-0.6B-Base":
 
 # Run a single MetaMathQA->GSM8K benchmark for a given variant.
 # Per-variant lr / target-name defaults are baked in here.
-bench-variant model variant steps="5000" block="8":
+bench-variant model variant steps="5000" block="8" r_override="":
 	#!/usr/bin/env bash
 	set -euo pipefail
 	lr=1e-4
@@ -98,6 +98,8 @@ bench-variant model variant steps="5000" block="8":
 	# and destabilizes at that lr (block=128 got 45.7% vs block=8's 60.5%). Drop to
 	# LoRA's 1e-4 once the block dominates the param count.
 	if [ "{{variant}}" = "antipasto_arrow" ] && [ "{{block}}" -gt 8 ]; then lr=1e-4; fi
+	# r override (e.g. low-rank corda sweep); alpha tracks r for the antipasto family.
+	if [ -n "{{r_override}}" ]; then r="{{r_override}}"; alpha="{{r_override}}"; fi
 	exec uv run --extra benchmark python scripts/metamath_gsm8k_benchmark.py \
 		--model '{{model}}' \
 		--variant '{{variant}}' \

scripts/metamath_gsm8k_benchmark.py

@@ -536,6 +536,9 @@ def run(args: BenchmarkConfig) -> dict[str, Any]:
     # arrow's capacity is set by block, not r, so keep block-sweep runs from colliding.
     if args.variant == "antipasto_arrow" and args.antipasto_block != 8:
         run_id += f"__b{args.antipasto_block}"
+    # antipasto family defaults to r=256; low-rank sweeps get their own dirs.
+    if args.variant.startswith("antipasto") and args.r != 256:
+        run_id += f"__r{args.r}"
     out_dir = args.output_dir / run_id
     out_dir.mkdir(parents=True, exist_ok=True)