| |
| """Run the three Phase 2.1A v2 Robometer-Low-LoRA seeds serially with resume.""" |
|
|
| from __future__ import annotations |
|
|
| import argparse |
| import subprocess |
| import sys |
| from pathlib import Path |
|
|
|
|
| ROOT = Path(__file__).resolve().parents[1] |
| TRAINER = ROOT / "scripts" / "train_phase21a_robometer_low_lora.py" |
| def main() -> None: |
| parser = argparse.ArgumentParser() |
| parser.add_argument("--output-root", type=Path, required=True) |
| parser.add_argument("--snapshot", type=Path, required=True) |
| parser.add_argument( |
| "--manifest", |
| type=Path, |
| default=ROOT / "manifests" / "phase2_remediation_pairs_v1.jsonl", |
| ) |
| parser.add_argument( |
| "--processed-root", |
| type=Path, |
| default=ROOT / "artifacts" / "data_views" / "phase1_official" / "processed_datasets", |
| ) |
| parser.add_argument("--seeds", type=int, nargs="+", default=[7, 17, 27]) |
| parser.add_argument("--optimizer-steps", type=int, default=3000) |
| parser.add_argument("--micro-batch-pairs", type=int, default=32) |
| parser.add_argument("--gradient-accumulation", type=int, default=2) |
| parser.add_argument("--lora-lr", type=float, default=2.0e-6) |
| parser.add_argument("--head-lr", type=float, default=1.0e-4) |
| parser.add_argument("--checkpoint-every", type=int, default=250) |
| parser.add_argument("--eval-every", type=int, default=250) |
| parser.add_argument("--eval-micro-batch-pairs", type=int, default=32) |
| parser.add_argument("--early-stop-min-steps", type=int, default=1000) |
| parser.add_argument("--early-stop-patience-evals", type=int, default=4) |
| parser.add_argument("--early-stop-min-delta", type=float, default=5.0e-3) |
| args = parser.parse_args() |
| for seed in args.seeds: |
| output = args.output_root / f"seed_{seed}" |
| if (output / "summary.json").is_file(): |
| continue |
| command = [ |
| sys.executable, |
| str(TRAINER), |
| "--snapshot", str(args.snapshot), |
| "--manifest", str(args.manifest), |
| "--processed-root", str(args.processed_root), |
| "--seed", str(seed), |
| "--optimizer-steps", str(args.optimizer_steps), |
| "--micro-batch-pairs", str(args.micro_batch_pairs), |
| "--gradient-accumulation", str(args.gradient_accumulation), |
| "--lora-lr", str(args.lora_lr), |
| "--head-lr", str(args.head_lr), |
| "--checkpoint-every", str(args.checkpoint_every), |
| "--eval-every", str(args.eval_every), |
| "--eval-micro-batch-pairs", str(args.eval_micro_batch_pairs), |
| "--early-stop-min-steps", str(args.early_stop_min_steps), |
| "--early-stop-patience-evals", str(args.early_stop_patience_evals), |
| "--early-stop-min-delta", str(args.early_stop_min_delta), |
| "--output-dir", str(output), |
| ] |
| if (output / "latest_training_state.pt").is_file(): |
| command.append("--resume") |
| subprocess.run(command, check=True) |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
