summaryrefslogtreecommitdiff
path: root/ep_run/casc_bp_train.py
AgeCommit message (Expand)Author
2026-07-29RESULT 69: 饱和盲区被自己的治疗测试证伪(cap30/50关闭0.0000,...Yuren Hao
2026-07-22遥测扩展(用户规格): wandb新键 gn/clip_norm/clip_fired + watch_every...Yuren Hao
2026-07-17save final ckpt at last step (fixed-eval protocol); fw72m_ride crown-3 launch...Yuren Hao
2026-07-16Stage-0 BP mirror arms: qup/qcomp flags in casc_bp_train; bp_qctl + 6 quant a...Yuren Hao
2026-07-14wandb reorganized: per-regime team projects (ept-tinystories-42m / ept-finewe...Yuren Hao
2026-07-14wandb -> team entity eqprop-llm-training (trainers + full-history replay script)Yuren Hao
2026-07-13Fix swallowed --wandb_run arg (replace-comment bug); wandb default-on intactYuren Hao
2026-07-13wandb ON by default in both trainers (project ept-cascade); BP twin gains --a...Yuren Hao
2026-07-13Stage-2 data pipeline: FineWeb-Edu sample-10BT -> 32k BPE -> bins; --data fla...Yuren Hao
2026-07-10RESULT 10: epoch endpoints (BP 1.2509/1.2750 vs EP 1.4802, +0.22 erosion cost...Yuren Hao
2026-07-10OLMo2-standard architecture (user directive): norm-after-sublayer RMSNorm blo...Yuren Hao
2026-07-10AUDIT: retract confounded Muon verdict; tone down parity claims (n=3, best-of...Yuren Hao
2026-07-10Stage-1 epoch blowup @12100: sig story REFUTED (only +8%, cos fine till after...Yuren Hao
2026-07-10QK-norm: replace nn.MHA with explicit SDPA attn + --qk_norm (OLMo2-style, ana...Yuren Hao
2026-07-10Add --cosine (warmup->cosine decay to 0.1x lr) to both cascade trainers for f...Yuren Hao
2026-07-09A0.4 precision gate (TF32 harmless cos 0.9946==fp32; pure-bf16 cos 0.9427) + ...Yuren Hao
2026-07-09cascade root cause found: tied readout + default N(0,1) embedding init = path...Yuren Hao
2026-07-09cascade ablation program: plan doc (5 claims, tiers 0-4), probe v2 (jacobi/gs...Yuren Hao