b6 stage 2 -- SFR + PLRS, no final shrink (256->32)

LoRA rank / alpha: 128 / 256 (scaling: alpha/r)
Full rank schedule: 256 -> 128 -> 64 -> 32 -> 32
Replay (cumulative levels): True
Stage partition: difficulty
Cumulative train examples this stage: 1817
Validation split seed: 42 (5% of train, stratified by level; test set never used for selection)
Code commit: 1720a936dde4503227fe375f958eda65e36ab8fd

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support