Views
No views yet
jsanzolac/bpe_glove_300_lora_r300_qwen3 — same DriftingGloVeStudent rank=300 over a frozen
300-d cl100k BPE-GloVe — trained for an additional 150,000 steps with mined
hard negatives from jsanzolac/qwen3_emb_512_hard_negatives.cross_entropy(v @ [v_T ‖ v_hards]^T / τ) — MSE term disabled in this variant. with
τ = 0.05, H = 64 mined hard negatives per anchor.A.weight + B.weight from jsanzolac/bpe_glove_300_lora_r300_qwen3/rank_300/checkpoint_final.pt. Optimizer
state was not in the source checkpoint, so this run uses a fresh LR schedule
(5e-4 → 1e-5 cosine over 150,000 steps).E (300-d GloVe from jsanzolac/drifting-glove-distilled-r300), teacher (only used to produce the
cached v_T targets in jsanzolac/qwen3_emb_300_packed_cl100k — not loaded here).rank_300/:checkpoint_final.pt — A.weight + B.weight (E excluded; reinject from jsanzolac/drifting-glove-distilled-r300).config.jsonvectors_drifted.txt / .parquet — E + B(A(·)) per vocab row.train_log.jsonl