unconst/Affine-5czsc2fc98-r596-r252-odpo-hirank-midbeta-softctx-megaextra-merged

R596 — SoftCtx × HiRank × MidBeta MegaExtra (offline DPO)

Affine SN120 challenger trained to beat the live king on Reason v3 (teacher-anchored score: lpC(y_C|z_A) − lpC(y_C|∅)).

How this checkpoint was trained

• —Base / parent: unconst/Affine-5czsc2fc98-r252-merged@b42d6245d77fe30885ea8a90387771e1bc465e0f (our crowned r252, reign 33)
• —Method: offline DPO on Reason-ranked pairs (not SFT / not online GRPO)
• —What was optimized: preference for higher teacher-side Reason on mined pairs
• —Data: SoftCtx × HiRank pair set (soft context length band, high-rank filter); MidBeta β=0.1. See experiment plan.md / dpo_duel_reason.jsonl under mining/experiments/r596-r252-offline-dpo-hialpha-hirank-midbeta-softctx-megaextrasteps.
• —Key hyperparameters:
• —LoRA r=64, α=128
• —β=0.1 (MidBeta)
• —lr=5e-6
• —max_len=12288 (SoftCtx)
• —maxsteps target 3600 MegaExtra; **TRAINDONE@259** (adapter kept / merged)
• —Hardware: Lium mine-r226-marsplan-fullft-1 (brave) GPUs 6,7 for train; merge + n80 on mine-r252-vera-t4-nonking-grpo-1 GPUs 4,5 → /tmp/r596_merged
• —Local n80 vs live king reign34 (cryptoDev23/Affine-5Dku3dYp9j-hk8161@55b7ffe0…):
• —margin +0.006196, SE 0.002357, z=2.63, n=75
• —bar max(2·SE, δ=0.002) = 0.004713 (~1.31×)
• —thought median 199 (≥80), B pass 0.368 (≥0.30)
• —decision: Stage-5 licensed (r596_decision_reign34.json)
• —Prior n80 vs r252: margin +0.008490 (~1.19× bar), thought/B clear
• —Experiment path: mining/experiments/r596-r252-offline-dpo-hialpha-hirank-midbeta-softctx-megaextrasteps

Intended use

SN120 Affine miner submission / evalsrv Reason duel. Not a general chat model.

License

Follows base model + Affine mining artifacts policy.