protocol: freeze convolutional HFA baseline funnel

1 files changed, 51 insertions, 0 deletions

diff --git a/experiments/oral_a_hfa_short_screen.py b/experiments/oral_a_hfa_short_screen.py
new file mode 100644
index 0000000..1a5b9ea
--- /dev/null
+++ b/experiments/oral_a_hfa_short_screen.py
@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+"""Run a deterministic shard of the frozen convolutional-HFA short screen."""
+import argparse
+import os
+import subprocess
+import sys
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--device", default="cuda")
+    parser.add_argument("--shard_index", type=int, default=0)
+    parser.add_argument("--num_shards", type=int, default=1)
+    parser.add_argument("--dry_run", action="store_true")
+    args = parser.parse_args()
+    if not 0 <= args.shard_index < args.num_shards:
+        raise ValueError("invalid shard index")
+
+    common = [
+        sys.executable, "experiments/conv_run.py", "--mode", "hfa",
+        "--device", args.device, "--depth", "20", "--width", "16",
+        "--seed", "0", "--loader_seed", "0", "--batch_size", "128",
+        "--epochs", "20", "--train_limit", "10000",
+        "--val_examples", "5000", "--split_seed", "2027",
+        "--eval_split", "validation", "--eval_every", "0",
+        "--augment_train", "1", "--lr_schedule", "cosine",
+        "--warmup_epochs", "0", "--momentum", "0.9",
+        "--weight_decay", "1e-4", "--normalization", "batchnorm",
+        "--output_lr", "0.1", "--a_scale", "1",
+        "--alignment_probe", "32",
+    ]
+    jobs = []
+    for rate in (0.01, 0.03, 0.1):
+        tag = f"hfa_lr{rate}"
+        jobs.append((tag, common + [
+            "--lr", str(rate),
+            "--out", f"results/oral_a_hfa_short/{tag}.json",
+        ]))
+
+    os.makedirs("results/oral_a_hfa_short", exist_ok=True)
+    selected = [job for index, job in enumerate(jobs)
+                if index % args.num_shards == args.shard_index]
+    for tag, command in selected:
+        print(tag, " ".join(command), flush=True)
+        if not args.dry_run:
+            subprocess.run(command, check=True)
+
+
+if __name__ == "__main__":
+    main()
+