From ada84e52472409dc23ea421a6db245c57950a7da Mon Sep 17 00:00:00 2001 From: Andrej Karpathy Date: Sat, 7 Mar 2026 16:29:59 +0000 Subject: [PATCH] soften the language just a bit --- program.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/program.md b/program.md index c591578..4619791 100644 --- a/program.md +++ b/program.md @@ -96,12 +96,12 @@ LOOP FOREVER (until I wake up and come back in the morning): 1. Look at the git state: the current branch/commit we're on 2. Tune `train.py` with an experimental idea by directly hacking the code. 3. git commit -4. run the experiment: `uv run train.py > run.log 2>&1` (redirect everything — do NOT use tee or let output flood your context) -5. read out the results: `grep "^val_bpb:\|^peak_vram_mb:" run.log` -6. If the grep output is empty, the run crashed. You MUST run `tail -n 50 run.log` to read the Python stack trace so you can actually diagnose and fix the bug. -7. record the results in the tsv -8. if val_bpb improved (lower), you "advance" the branch, keeping the git commit -9. if val_bpb is equal or worse, you git reset back to where you started +4. Run the experiment: `uv run train.py > run.log 2>&1` (redirect everything — do NOT use tee or let output flood your context) +5. Read out the results: `grep "^val_bpb:\|^peak_vram_mb:" run.log` +6. If the grep output is empty, the run crashed. Run `tail -n 50 run.log` to read the Python stack trace and attempt a fix. If you can't get things to work after more than a few attempts, give up. +7. Record the results in the tsv +8. If val_bpb improved (lower), you "advance" the branch, keeping the git commit +9. If val_bpb is equal or worse, you git reset back to where you started The idea is that you are a completely autonomous researcher trying things out. If they work, keep. If they don't, discard. And you're advancing the branch so that you can iterate. If you feel like you're getting stuck in some way, you can rewind but you should probably do this very very sparingly (if ever).