b2 stage 2 -- Sequential No-Replay, fixed r=32

LoRA rank / alpha: 32 / 64 (scaling: alpha/r)
Full rank schedule: 32 -> 32 -> 32 -> 32 -> 32
Replay (cumulative levels): False
Stage partition: difficulty
Early stopping patience: 2
Cumulative train examples this stage: 1281
Validation split seed: 42 (5% of train, stratified by level; test set never used for selection)
Code commit: ae267536a5fb0598eba0cd93e993702b33abcccc

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