Giorgio Gilestro
84124de143
Clarity pass over the main text (36-item audit), Discussion rewrite and cut, acknowledgements, Souly et al. as ref 62, lettered SI panels, model section moved under Results; plus the untracked curriculum/society/compose/smol configs, runners, figures, stats and tests that the SI already cites. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Y64o8FKP7rCuXzC48pxpMm
17 lines
812 B
YAML
17 lines
812 B
YAML
# Calibration stage A (prereg §4, gates C1a-c + C4): every candidate family's base / specialist
|
|
# accuracy, specialist confidence AUC, pairwise functional conflict, gen-0 behavioural distance.
|
|
# GG reviews the printed table and fixes the 12-family set in society_v2_calib_b.yaml + the campaign.
|
|
# ~1 h on a 16 GB GPU (17 specialists at 600 x 3 epochs, cached and reused by stage B).
|
|
experiment: llm_society_v2_calib_a
|
|
kind: llm_society_calib
|
|
stage: families
|
|
base_model: Qwen/Qwen2.5-0.5B-Instruct
|
|
seed: 1
|
|
families: [lists, strings, arith, roman, binary, sortletters, setops, numtheory, mixedtoken,
|
|
caesar, vectors, progression, charfreq, digits, liststats, alphabet, prime]
|
|
n_test: 100
|
|
n_probe: 10
|
|
spec_train: 600
|
|
spec_epochs: 3
|
|
lora: {r: 16, alpha: 32}
|
|
output: {dir: results/llm_society_v2_calib_a}
|