Fix chosen-token regularization

This commit is contained in:
sam-paech
2026-07-23 15:42:54 -07:00
parent 6299030455
commit bc9e75fdec
10 changed files with 273 additions and 37 deletions

View File

@@ -258,7 +258,8 @@ finetune_shuffle_seed: 666
# 0 = off; 0.9 strongly downsamples overrepresented rule violations
# (this is useful because the raw generated dataset is typically very skewed)
ftpo_sample_rejected_regularisation_strength: 0.6
ftpo_sample_chosen_regularisation_strength: 0.2
# 0 = off; positive values trim globally overrepresented chosen-token slots
ftpo_sample_chosen_regularisation_strength: 0.0
ftpo_sample_min_chosen_tokens: 4 # filter out ftpo samples that have fewer than this number in the chosen tokens list