| --- |
| library_name: peft |
| base_model: Qwen/Qwen3-14B |
| tags: [loracle, lora-interpreter, cispo, offline-rl] |
| --- |
| |
| # Loracle CISPO v9 (new best) |
|
|
| Interpreter LoRA. Trained via offline **CISPO** (MiniMax-M1, arXiv:2506.13585) with |
| **Dr. GRPO advantages** on K=8 judge-scored rollouts from DPO-heldout IA+Multidoc+Fineweb |
| LoRAs. Beats CISPO v7 on AB, OOD, and ties on heldout_ia_v2. |
|
|
| ## Eval results |
|
|
| | Set | pass@N | 95% CI | rollout-mean | |
| |---|---:|---|---:| |
| | AuditBench (56) | 76.8% | [64.2 - 85.9] | 49.4% [44.1 - 54.8] | |
| | heldout_ia_v2 (20) | 80.0% | [58.4 - 91.9] | 71.7% [60.3 - 83.1] | |
| | ood_models_v3 (23) | 56.5% | [36.8 - 74.4] | 20.9% [17.2 - 24.6] | |
|
|
| ## Hypers |
|
|
| - CISPO loss (paper Eq. 4 unbiased normalization, stop-grad clipped IS weight) |
| - Dr. GRPO advantage: A = score - mean(score) |
| - lr = 5e-6 |
| - eps_low = 1.0 (no lower clip — paper-faithful) |
| - eps_high = 1.0 (max ratio = 2.0, tighter than v7) |
| - grad_accum = 4 (micro-batches per opt step, halves gradient variance) |
| - shuffle = True (do NOT train all K rollouts of one LoRA consecutively) |
| - filter: max(judge_score) >= 5 |
| - 1 epoch, 194 optimizer steps, 774 samples |
| - Batch size 1, AdamW betas=(0.9, 0.95), grad_clip=1.0 |
| - Base: Qwen/Qwen3-14B, rank=256, alpha=32, all 7 mag7 modules |
| |
| ## Loading |
| |
| Feed direction tokens (shape [4480, 5120], svd_fixed_k16_mag7_rankfirst bf16) |
| through AOEncoder, inject at layer-1 output at placeholder positions, apply this |
| interpreter LoRA over frozen Qwen/Qwen3-14B, decode greedily. |
| |
