RL-Forgetting-Experiments-3/qwen2.5-3b-kk-sft-shuffled-lr1e5-all-checkpoints
0
Qwen2.5-3B kk SFT, shuffled: all checkpoints
Ten existing checkpoints: 318, 635, 952, 1270, 1588, 1905, 2222, 2540, 2858, 3175. Training and evaluation were already complete.
Per-checkpoint evaluation outputs: https://huggingface.co/datasets/RL-Forgetting-Experiments-3/qwen2.5-3b-math-kk-sft-artifacts/tree/main/runs/kk_shuffled/eval
Each checkpoints/step_N/ directory is a directly loadable Hugging Face model.
