From 9fecbe58cc0750e9e39b261a672b0c6e85e6ed4e Mon Sep 17 00:00:00 2001
From: Void Agent <void@jayrup.hermes>
Date: Fri, 14 Aug 2026 13:21:03 +0100
Subject: fix codex BLOCKERs: global fixed layout invariance, min_steps
 off-by-one, integers EOS alias, rerun guard, eval prereg-literal codes +
 dual-checkpoint honesty; +7 regression tests

---
 src/train.py | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

(limited to 'src/train.py')

diff --git a/src/train.py b/src/train.py
index 975598d..46bd8e7 100644
--- a/src/train.py
+++ b/src/train.py
@@ -1,8 +1,10 @@
 """Training loop. Usage: python -m src.train [model] [seed] [--flag ...]"""
 import csv
+import json
 import math
 import os
 import random
+import sys
 
 import numpy as np
 import torch
@@ -62,8 +64,21 @@ def main() -> None:
     cfg = parse_args()
     set_seed(cfg.seed)
     out_dir = os.path.join(cfg.out_dir, cfg.model, f"seed{cfg.seed}")
+    csv_path = os.path.join(out_dir, "metrics.csv")
+    if os.path.exists(csv_path):
+        raise SystemExit(f"REFUSING to rerun in place: {csv_path} exists. Use a fresh --out_dir "
+                         f"(reruns would corrupt the CSV and checkpoint provenance).")
     os.makedirs(out_dir, exist_ok=True)
     cfg.save(os.path.join(out_dir, "config.json"))
+    with open(os.path.join(out_dir, "run_meta.json"), "w") as fh:
+        json.dump({
+            "python": sys.version.split()[0],
+            "torch": torch.__version__,
+            "numpy": np.__version__,
+            "device": "cpu",
+            "torch_threads": torch.get_num_threads(),
+            "cmd": sys.argv,
+        }, fh, indent=2)
 
     train_in, val_in = get_splits(cfg)
     train_ex = build_examples(train_in, cfg)
@@ -75,9 +90,8 @@ def main() -> None:
     opt = torch.optim.AdamW(model.parameters(), lr=cfg.lr, weight_decay=cfg.weight_decay)
     ce = nn.CrossEntropyLoss(reduction="none")
 
-    log_examples = sorted(val_ex, key=lambda x: (len(str(x)), x))[: cfg.log_n_examples]
+    log_examples = sorted(val_ex, key=lambda ex: (len(ex[0]), ex[0]))[: cfg.log_n_examples]
 
-    csv_path = os.path.join(out_dir, "metrics.csv")
     fieldnames = ["step", "train_loss", "train_token_acc", "train_em", "val_token_acc",
                   "val_em", "mean_halt_steps", "log_examples", "param_count"]
     best_val_em = -1.0
@@ -152,6 +166,8 @@ def main() -> None:
                 _eval_pass(loss.detach(), halt.detach() if halt is not None else None)
                 if done:
                     break
+            if step >= cfg.max_train_steps:
+                break
 
     torch.save(model.state_dict(), os.path.join(out_dir, "last.pt"))
     print(f"DONE steps={step} best_val_em={best_val_em:.4f}")
-- 
cgit v1.2.3