generated from mathias/template-go-web
mathiasandClaude Sonnet 4.6
69784f59cf
loop.py: Karpathy-style keep/revert loop. Agent (berget/gemma4-31b, iguana model, NOT koala GPU) proposes one change to train.py per iter → train.py runs on koala GPU (<2s) → read val_vol_r2 from metrics.json → keep if improved, else restore original content. STATUS.md tracks per-iter metric + delta + GPU snap. Iter 1 kept: improved EMBED_DIM/capacity, +9.3% on OOS R². Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
10 lines
153 B
JSON
10 lines
153 B
JSON
{
|
|
"val_vol_r2": 0.22343164905658508,
|
|
"n_test": 275,
|
|
"knobs": {
|
|
"WINDOW": 20,
|
|
"EMBED_DIM": 32,
|
|
"MASK_FRAC": 0.3,
|
|
"EPOCHS": 200
|
|
}
|
|
} |