wassname/ml_debug
1
0
Fork 0
mirror of https://github.com/wassname/ml_debug.git synced 2026-08-11 11:21:48 +08:00
Code Issues Packages Projects Releases Wiki Activity
87 Commits 2 Branches 0 Tags
996942c4dea332dc8552d4a672f0b3fc66fe0704
Commit Graph
3 Commits
Author SHA1 Message Date
wassnameandClaudypoo 4e45bd4140 DPO can barely move: tinker's own reference run reports 0.52 pair accuracy 
Contrast with the cookbook's RLHF pipeline (46% -> 94% win rate in 100 steps),
so a decreasing DPO loss is weak evidence of behaviour change.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
 2026-08-08 10:04:32 +08:00
wassname 160bd040cc docs: add sourced transformer report folklore 2026-06-12 07:02:58 +08:00
wassname 8b9a1d62ed docs: resolve ml-debug TODO references 2026-06-12 06:52:38 +08:00