protocol: freeze Oral-A v3 causal-capture funnel

1 files changed, 60 insertions, 0 deletions

diff --git a/experiments/oral_a_v3_calibration_screen.py b/experiments/oral_a_v3_calibration_screen.py
new file mode 100644
index 0000000..d353b3c
--- /dev/null
+++ b/experiments/oral_a_v3_calibration_screen.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+"""Run a shard of the frozen Oral-A-v3 causal-capture 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", "sdil", "--device", args.device,
+        "--depth", "20", "--width", "16", "--seed", "0",
+        "--loader_seed", "0", "--batch_size", "128", "--epochs", "0",
+        "--train_limit", "10000", "--val_examples", "5000",
+        "--split_seed", "2027", "--eval_split", "validation",
+        "--eval_every", "0", "--augment_train", "1",
+        "--lr", "0.03", "--output_lr", "0.1",
+        "--lr_schedule", "constant", "--warmup_epochs", "0",
+        "--momentum", "0.9", "--weight_decay", "1e-4",
+        "--normalization", "batchnorm", "--vectorizer_mode", "channel_gated",
+        "--a_scale", "0", "--a_warmup_steps", "400",
+        "--pert_sigma", "0.01", "--pert_directions", "1",
+        "--pert_every", "4", "--perturb_seed", "1000",
+        "--alignment_probe", "64",
+    ]
+    jobs = [
+        ("channel_subspace_etaA0.01", common + [
+            "--apical_calibration_mode", "channel_subspace",
+            "--eta_A", "0.01",
+            "--out", "results/oral_a_v3_calibration/channel_subspace_etaA0.01.json",
+        ])
+    ]
+    for rate in (0.01, 0.1, 1.0):
+        tag = f"vectorizer_subspace_etaA{rate}"
+        jobs.append((tag, common + [
+            "--apical_calibration_mode", "vectorizer_subspace",
+            "--eta_A", str(rate),
+            "--out", f"results/oral_a_v3_calibration/{tag}.json",
+        ]))
+    os.makedirs("results/oral_a_v3_calibration", exist_ok=True)
+    for index, (tag, command) in enumerate(jobs):
+        if index % args.num_shards != args.shard_index:
+            continue
+        print(tag, " ".join(command), flush=True)
+        if not args.dry_run:
+            subprocess.run(command, check=True)
+
+
+if __name__ == "__main__":
+    main()
+