spadeMIA/pythia-1.4b-goodwiki-lora-r64

adapter

LoRA-fine-tuned checkpoint produced for membership inference research at the SPADE Lab, Koç University.

Base model

• —Model: EleutherAI/pythia-1.4b
• —PEFT method: LoRA

Training data

• —Dataset: `spadeMIA/GoodWiki_Corpus_1024_2040`
• —Split used: train (10,000 rows, all membership-positive)
• —Stored text token range: 1024-2039 tokens (Pythia tokenizer family), plus one appended EOS token
• —Max training sequence length: 2048 tokens
• —Observed token stats: min=1024, mean=1840.7, median=1926.0, max=2039

LoRA configuration

Training procedure

Notes

• —The corresponding held-out test split was not loaded or trained on.
• —Eval-loss logging (monitoring only, no checkpoint selection) used train[:50].

Generated automatically by `run_lora.py` on 2026-08-10.