From f1dd9fb33e74fbe6a827f18edc5d65755114ab3e Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Thu, 11 Jun 2026 00:35:29 +0000
Subject: [PATCH] chore: FastConfig save_ckpt_every 10->20 (disk pressure; ~6
 ckpts/run suffices)

Each lora2r ckpt is ~1.3G (A/B + redundant frozen A0/B0, 252 modules fp32). The
768G disk filled and runs crashed at the step-0 ckpt save. 20-step cadence halves
the per-run footprint while keeping enough points for the eval curve.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
---
 src/vgrout/train_config.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/src/vgrout/train_config.py b/src/vgrout/train_config.py
index 0c8437f..41dcfd0 100644
--- a/src/vgrout/train_config.py
+++ b/src/vgrout/train_config.py
@@ -128,3 +128,7 @@ class FastConfig(Config):
     adam_beta1: float = 0.5
     adam_beta2: float = 0.9
     lr: float = 5e-4   # user: bump from 1e-4 to learn faster in the short grad-starved budget
+    # Each lora2r ckpt is ~1.3G (A/B + redundant frozen A0/B0 for 252 modules, fp32); 20-step
+    # cadence keeps ~6/run for the eval curve without filling the 768G disk. (TODO: drop A0/B0
+    # from ckpts -- reconstructible from lora_init_seed -- to halve size, needs a loader change.)
+    save_ckpt_every: int = 20