tofu_Llama-3.1-8B-Instruct_forget01_PDU
open-unlearning/tofu_Llama-3.1-8B-Instruct_full unlearned on the TOFU forget01 split with PDU, trained with the open-unlearning framework. Used as a weight-unlearning baseline / draft model in the Speculative-Decoding-Unlearning project.
Full training config: .hydra/config.yaml. TOFU evaluation outputs: evals/.
Method hyperparameters
gamma: 1.0
alpha: 100
retain_loss_type: NLL
retain_loss_eps: 0.3
primal_dual: True
dual_step_size: 5
dual_update_upon: step
dual_warmup_epochs: 5
loss_names: ['forget_loss', 'retain_loss']
TOFU summary metrics
| metric | value |
|---|---|
| exact_memorization | 0.0397 |
| extraction_strength | 0.0291 |
| forget_Q_A_PARA_Prob | 0.0000 |
| forget_Q_A_gibberish | 0.2053 |
| forget_quality | 0.0000 |
| forget_truth_ratio | 0.8044 |
| mia_loss | 0.0000 |
| mia_min_k | 0.0000 |
| mia_min_k_plus_plus | 0.0506 |
| mia_zlib | 0.0000 |
| model_utility | 0.6518 |
| privleak | 100.0000 |