Commit History

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

    bde5c5e

  1. Wave 21c: verify PRIME-RL adapter parity against upstream source (byte-for-byte)⁠

    c98928e

  1. Wave 15: 4-angle multi-model self-critique caught 2 math BLOCKERs in primary loss kernels; fixed against upstream byte-for-byte + GSM8K example + ergonomics⁠

    e5add15
  2. Wave 14: close every Wave 13 review finding + 4 documentation files; Wave 14b: real PRIME-RL parity + multi-process DiLoCo convergence⁠

    d9dd3a5
  3. Wave 13: serverless DiLoCo + replaysim normalization + 3 distillation losses + PRIME-RL + Monarch⁠

    b266c31