RL-Forgetting-Experiments-3/qwen2.5-3b-kk-sft-shuffled-lr1e5-step3175
0374
kk_shuffled
Qwen2.5-3B one-epoch SFT checkpoint for the kk shuffled arm at optimizer step 3175. See delivery_manifest.json for exact source lineage and weight checksums.
Qwen2.5-3B one-epoch SFT checkpoint for the kk shuffled arm at optimizer step 3175. See delivery_manifest.json for exact source lineage and weight checksums.