 wassname
|
7e1b171875
|
paper data recipe + LoRA hyperparams + n_pairs hardening
- data: 5 pos + 5 neg personas, 20 train + 12 eval topic split
(paper §3 / Appendix C), n_samples solved from n_pairs.
judge filter stub (off by default; paper uses GPT-4.1-mini).
- eval/sycophancy: read true held-out eval_topics() instead of
SYCOPHANCY_TOPICS[-16:].
- replicate: fix epochs threading; n_pairs reuse fails fast on mismatch;
smoke knobs (n_topics, n_personas) plumbed.
- train: paper hyperparams (rank 32 / alpha 16 / lr 1e-5 / warmup 5 /
wd 0.01); explicit alpha (no 2*r fallback); held-out 10% val + eval_loss
logging.
- run_demo: train_topics() for in_dist demo claims.
- README: scope block reflects paper-matching recipe.
|
2026-04-26 10:19:59 +08:00 |
|
|
wassnameandClaude Opus 4.7
|
363e2db14d
|
phase 0-2: HF+PEFT pipeline, smoke, subspace alignment
Rip Axolotl/vLLM, switch to HF+PEFT functional pipeline.
Add LoRA/DoRA/PiSSA/DeLoRA train, delta-W diff, weight_steer hook,
sycophancy logratio eval, and SVD top-k + weak-readout alignment.
Smoke runs end-to-end on tiny-random qwen3 with BEARTYPE=1.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
|
2026-04-25 20:14:07 +08:00 |
|