Jaromír
Jaromír
Confirmed.
When target_type == 'cost' then yes.
Train several models with lamda logarithmically spaced between [0, 1] (alterantively, use target cost), evaluate them and plot them in the cost vs accuracy plane. See section 4.1 Evaluation metric...
Hi @jackmpcollins, thanks for the answer and the proposed workarounds. Obviously, both of them have their drawbacks. My main motivation was to reduce costs by having one LLM call (especially...