Joint training did not fix the watermark merge: 8/8 alone, 0/8 at 0.75
Joint training: can one adapter carry both the task and the mark? The separately trained watermark is 8/8 alone and 0/8 at a 0.50/0.50 merge . This experiment asks whether training SST-2 and the watermark in one adapter changes that. If the joint adapter keeps the mark at a lower merge fraction, jo…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-11 15:32 · DEV Community — Machine Learning
Joint training did not fix the watermark merge: 8/8 alone, 0/8 at 0.75