BabyYarros: amend the decision rule to gate on voice and non-memorization (operator-authorised)

scripts/yarros-corpus/train_pairs_lora.py

@@ -135,6 +135,12 @@ def main() -> int:
     ap.add_argument("--seed", type=int, default=4919)
     ap.add_argument("--eval-steps", type=int, default=25)
     ap.add_argument("--save-steps", type=int, default=25)
+    # ⚠ Must exceed the number of saves the run will make. The pilot took 9 evals and the
+    # loss minimum was at the 6th; a full run at 1672 steps saving every 50 makes 33, and
+    # the hardcoded limit of 12 would have PRUNED an early minimum before it could be read.
+    # The 4B rung already proved the best checkpoint is not the last one -- a retention
+    # policy that silently deletes it turns that lesson into a trap rather than a guard.
+    ap.add_argument("--save-total-limit", type=int, default=12)
     a = ap.parse_args()
 
     torch.manual_seed(a.seed); random.seed(a.seed)
@@ -220,7 +226,7 @@ def main() -> int:
         lr_scheduler_type="cosine",
         warmup_steps=max(1, int(0.03 * steps_per_epoch * int(a.epochs))),
         bf16=True, logging_steps=10,
-        save_strategy="steps", save_steps=a.save_steps, save_total_limit=12,
+        save_strategy="steps", save_steps=a.save_steps, save_total_limit=a.save_total_limit,
         eval_strategy="steps", eval_steps=a.eval_steps,
         report_to=[], seed=a.seed,
         gradient_checkpointing=True, dataloader_num_workers=2,