diff options
| author | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-05 17:41:30 -0500 |
|---|---|---|
| committer | YurenHao0426 <Blackhao0426@gmail.com> | 2026-04-05 17:41:30 -0500 |
| commit | ab5fae5decb7d24aafd16d855885c1c99e51cf7f (patch) | |
| tree | fe17a62d77c151f7cd5ba174f76dd766ac6bf1e1 /scripts/shift_analysis.py | |
| parent | 6139a848c3b9d5d6c1322cf8acadf2baacee9e8a (diff) | |
Fix PromptTuning/PrefixTuning cleanup crash and tune learning rates
- peft_baseline.py: Fix cleanup() to handle PromptTuning/PrefixTuning
which don't support unload(). Falls back to base_model access.
- run_all_methods.py: Reduce lr from 0.3 to 0.01 for PromptTuning,
0.01 to 0.001 for PrefixTuning. Previous lr caused R-L=0.03 (broken).
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Diffstat (limited to 'scripts/shift_analysis.py')
0 files changed, 0 insertions, 0 deletions