from train_sft import _is_better_eval, _sibling def test_sibling_last_best(): assert _sibling("ckpts/k3_sft.pt", "_last") == "ckpts/k3_sft_last.pt" assert _sibling("ckpts/k3_sft.pt", "_best") == "ckpts/k3_sft_best.pt" def test_best_prefers_success_then_chrf(): assert _is_better_eval(1.0, 70.0, 0.95, 90.0) assert not _is_better_eval(0.95, 99.0, 1.0, 70.0) assert _is_better_eval(1.0, 91.0, 1.0, 81.0) assert not _is_better_eval(1.0, 70.0, 1.0, 81.0)