Skip to content

Start Probe LoRA/Qwen/MLX training lane from clean GEPA traces #1094

Description

@AtlantisPleb

Objective

Start the Probe model-training lane only after GEPA produces clean traces and route scorecards.

GEPA is distributed rollout optimization over text artifacts. This issue is the separate later neural/model lane for LoRA, Qwen, and MLX/Apple-silicon adapter work.

Scope

  • Select training data from GEPA traces, route scorecards, and failure-family deltas.
  • Separate prompt/Blueprint optimization evidence from model fine-tuning evidence.
  • Define adapter evaluation against retained and validation Probe benchmark tasks before any wider claim.
  • Track Qwen and MLX/Apple FM paths as backend experiments, not benchmark authority.

Acceptance criteria

  • Training-data selection uses public-safe GEPA trace refs and failure-family deltas.
  • LoRA/Qwen/MLX runs are labeled as model-training experiments, not GEPA rollout optimization.
  • Adapter evaluation writes Benchmark Cloud-compatible evidence records.
  • Public summaries avoid model-training claims until external gates exist.

Related work

Metadata

Metadata

Assignees

No one assigned

    Labels

    area:gepaGEPA optimization workarea:psionicPsionic optimizer, training, and candidate frontier workenhancementNew feature or requesttype:evidenceReceipts, provenance, hashes, or evidence records

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions