summaryrefslogtreecommitdiff
path: root/experiments/residual_mirror_short_screen.py
diff options
context:
space:
mode:
Diffstat (limited to 'experiments/residual_mirror_short_screen.py')
-rwxr-xr-xexperiments/residual_mirror_short_screen.py64
1 files changed, 64 insertions, 0 deletions
diff --git a/experiments/residual_mirror_short_screen.py b/experiments/residual_mirror_short_screen.py
new file mode 100755
index 0000000..99e503a
--- /dev/null
+++ b/experiments/residual_mirror_short_screen.py
@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+"""Run the two frozen RRM-2 short ResNet-20 accuracy jobs."""
+import argparse
+import json
+import os
+import subprocess
+import sys
+
+
+def main():
+ parser = argparse.ArgumentParser()
+ parser.add_argument(
+ "--selection", default="results/residual_mirror_capture_gate.json")
+ 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")
+ with open(args.selection) as handle:
+ selection = json.load(handle)
+ if selection.get("protocol") != "residual_response_mirror_capture_v1":
+ raise ValueError("unexpected residual-mirror capture protocol")
+ if selection.get("status") != "passed":
+ raise ValueError("RRM-1 did not pass")
+ mirror_eta = float(selection["selected_rrm"]["mirror_eta"])
+ if mirror_eta != 0.1:
+ raise ValueError("RRM-1 selected an unexpected frozen rate")
+
+ common = [
+ sys.executable, "experiments/conv_run.py", "--mode", "rrm",
+ "--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", "--mirror_warmup_steps", "20",
+ "--mirror_every", "16", "--mirror_batch_size", "1",
+ "--mirror_eta", str(mirror_eta), "--mirror_noise_std", "1",
+ "--mirror_seed", "3000",
+ ]
+ jobs = []
+ for rate in (0.03, 0.1):
+ tag = f"rrm_lr{rate}"
+ jobs.append((tag, common + [
+ "--lr", str(rate),
+ "--out", f"results/residual_mirror_short/{tag}.json",
+ ]))
+ os.makedirs("results/residual_mirror_short", 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()