diff options
| author | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 20:56:01 -0500 |
|---|---|---|
| committer | Yuren Hao <yurenh2@illinois.edu> | 2026-07-10 20:56:01 -0500 |
| commit | 6d9fcd748df0836528b31f29717ac3bc8715d1dd (patch) | |
| tree | 288abf1e70f7d955f7d5d008d9648f3053986a00 /ep_run/casc_bp_train.py | |
| parent | 196ee7d8121fccaae630e408bf29f6664ff351f5 (diff) | |
RESULT 10: epoch endpoints (BP 1.2509/1.2750 vs EP 1.4802, +0.22 erosion cost); GENERATION GATE PASSED (casc_gen.py, coherent stories, no-backprop 42.75M); stage1b improved-recipe pair launched (Muon cosine via build_hybrid)
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014FAPDWQ49M5Ye3NpTndTpn
Diffstat (limited to 'ep_run/casc_bp_train.py')
| -rw-r--r-- | ep_run/casc_bp_train.py | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/ep_run/casc_bp_train.py b/ep_run/casc_bp_train.py index 987277f..d45327b 100644 --- a/ep_run/casc_bp_train.py +++ b/ep_run/casc_bp_train.py @@ -146,7 +146,8 @@ if args.resume: print(f'[resume] loaded {args.resume} at step {start_step}', flush=True) if args.opt == 'muon': from muon import build_hybrid - opt, sched = build_hybrid(blocks, params, args.lr, args.muon_lr, args.warmup) + opt, sched = build_hybrid(blocks, params, args.lr, args.muon_lr, args.warmup, + total_steps=(args.steps if args.cosine else 0), lr_min_ratio=args.lr_min_ratio) else: if args.wd >= 0: # OLMo2-style grouped decay nodecay = {id(p) for p in tok.parameters()} | {id(p) for p in pos.parameters()} | \ |
