shirasko/gemma-2-2b-it-crisp-gambling

Unlearned Checkpoint

Field	Value
Unlearning method	CRISP
Base model	google/gemma-2-2b-it
Target concept	Gambling
Checkpoint type	LoRA Adapter
Rank / seed	100 / 42
Train eval protocol	mc

---

Unlearning Configuration

Selected hyperparameters (from unlearned_checkpoints.json):

Parameter	Value
alpha	5
delta_embed	0
k_features	10
k_features_embed	0
layer_hi	15
layer_lo	5
layer_step	2
lora_rank	4
lr	0.0005
n_tokens_edited	0
num_epochs	2

---

Primary Unlearning Metrics (held-out test, MC protocol)

Headline scores used for checkpoint selection:

Metric	Train (after unlearning)	Test (after unlearning)
Efficacy	1	1
Specificity	0.955	0.885
Harmonic mean	0.977	0.939
Relearning QA (MC)	—	0.7

---

Full Evaluation (baseline → unlearned)

From evaluation/score_comparison.csv:

Metric	Baseline (train)	After unlearn (train)	Baseline (test)	After unlearn (test)
QA accuracy	0.76	0.12	0.82	0.18
QA fraction	1	0	1	0
SimDom accuracy	0.94	0.88	0.96	0.82
SimDom fraction	1	0.913	1	0.803
MMLU accuracy	0.52	0.56	0.551	0.547
MMLU fraction	1	1	1	0.987

---

Files in This Repository

File	Description
unlearned_checkpoints.json	Checkpoint metadata & hyperparameters
evaluation/evaluation_summary.json	Full evaluation payload (train/test/relearning)
evaluation/score_comparison.csv	Baseline vs. unlearned comparison table