Codeseys
/

composer-replication-framework

Reinforcement Learning

Model card Files Files and versions

composer-replication-framework / composer_replication /trainer /tests

Commit History

Wave 20: Tier-0 fidelity fixes — k1-in-reward KL + Composer-2 behavior rewards

41289bf

Baladithya Balamurugan Claude Opus 4.8 (1M context) commited on 10 days ago

Wave 3: close the HIGH review findings (kill-switch wiring, HeldoutSplit, EKS entrypoint bug)

bd0c358

Baladithya Balamurugan Claude Opus 4.8 (1M context) commited on 10 days ago

feat(trainer): policy-optimization objective MENU (ADR-014)

aae66fa

Codeseys commited on 21 days ago

feat(wave-a): close ADR-011 (SDPO alignment indices) + ADR-012 (review findings)

d02d724

Codeseys commited on 21 days ago

review+fix: cross-family adversarial ADR review (owed item) + remediation

185cce2

Codeseys commited on 21 days ago

feat(trainer): ADR-008 Dr.GRPO config + SDPO strict-alignment guard

bde5c5e

Codeseys commited on 21 days ago

Wave 21b: skip zero-signal SDPO on empty-recovery error turns + real-trace validation

d61036a

Codeseys commited on 22 days ago

Wave 21: close both Wave 20 debt items — chat-template alignment + structural is_error

6806cf7

Codeseys commited on 22 days ago