119 lines
2.5 KiB
JSON
119 lines
2.5 KiB
JSON
|
{
|
||
|
|
"model": "Qwen/Qwen2.5-7B-Instruct",
|
||
|
|
"num_layers": 28,
|
||
|
|
"hidden_size": 3584,
|
||
|
|
"direction_layer": 20,
|
||
|
|
"refusal_subspace_rank": 1,
|
||
|
|
"initial_separation": 74.8803,
|
||
|
|
"baseline_refusal_rate": 0.9583,
|
||
|
|
"baseline_eval_n": 24,
|
||
|
|
"edited_refusal_rate": 0.2286,
|
||
|
|
"refusal_metric": "classifier + weak guard",
|
||
|
|
"harmless_kl_nats": 0.0903,
|
||
|
|
"kl_backoff_steps": 0,
|
||
|
|
"kl_layer_trim_steps": 0,
|
||
|
|
"repair_steps": 1,
|
||
|
|
"guard_history": [
|
||
|
|
{
|
||
|
|
"iter": 0,
|
||
|
|
"separation": 40.6304,
|
||
|
|
"ratio": 0.5426,
|
||
|
|
"rank": 1,
|
||
|
|
"refusal": 0.75,
|
||
|
|
"kl": 0.0128
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"iter": 1,
|
||
|
|
"separation": 40.7273,
|
||
|
|
"ratio": 0.5439,
|
||
|
|
"rank": 1,
|
||
|
|
"refusal": 0.4688,
|
||
|
|
"kl": 0.0278
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"layer_alphas": [
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
1.206,
|
||
|
|
1.222,
|
||
|
|
1.205,
|
||
|
|
1.202,
|
||
|
|
1.21,
|
||
|
|
0.0,
|
||
|
|
1.24,
|
||
|
|
1.333,
|
||
|
|
1.333,
|
||
|
|
1.333,
|
||
|
|
1.333,
|
||
|
|
1.202,
|
||
|
|
1.448,
|
||
|
|
1.333,
|
||
|
|
1.333,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667,
|
||
|
|
0.667
|
||
|
|
],
|
||
|
|
"embed_alpha": 0.059,
|
||
|
|
"head_alpha": 0.0,
|
||
|
|
"preserve_rank": 8,
|
||
|
|
"preserve_source": "harmless",
|
||
|
|
"pruned_layers": [],
|
||
|
|
"layers_after_prune": 28,
|
||
|
|
"elapsed_sec": 271.2,
|
||
|
|
"profile": "balanced",
|
||
|
|
"target_refusal": 0.03,
|
||
|
|
"max_kl": 0.16,
|
||
|
|
"kl_target": 0.06,
|
||
|
|
"kl_positions": 32,
|
||
|
|
"opt_capability": true,
|
||
|
|
"opt_capability_weight": 1.0,
|
||
|
|
"timings_sec": {
|
||
|
|
"load_model": 12.5,
|
||
|
|
"load_prompts": 16.0,
|
||
|
|
"baseline_refusal": 5.2,
|
||
|
|
"activation_fit": 13.7,
|
||
|
|
"causal_scores": 12.2,
|
||
|
|
"optimize_profile": 90.7,
|
||
|
|
"guard": 22.4,
|
||
|
|
"refine_refusal": 14.3,
|
||
|
|
"validation_metrics": 0.0,
|
||
|
|
"repair": 57.8,
|
||
|
|
"prune": 0.0,
|
||
|
|
"test_metrics": 13.6,
|
||
|
|
"bake": 13.0
|
||
|
|
},
|
||
|
|
"command": "apostate ablate --model Qwen/Qwen2.5-7B-Instruct --out qwen-apostate",
|
||
|
|
"optimized": true,
|
||
|
|
"best_params": {
|
||
|
|
"direction_source": "activations",
|
||
|
|
"direction_layer_frac": 0.7420306856024312,
|
||
|
|
"refusal_rank": 1,
|
||
|
|
"strength": 1.0860947545472213,
|
||
|
|
"band_center": 0.48999396234759546,
|
||
|
|
"band_width": 0.5636482354840956,
|
||
|
|
"causal_mix": 0.664168644393967,
|
||
|
|
"causal_power": 1.2972323636074856,
|
||
|
|
"direction_sign": 1.0,
|
||
|
|
"ablate_embed": true,
|
||
|
|
"embed_scale": 0.04047498432630894,
|
||
|
|
"ablate_head": false,
|
||
|
|
"head_scale": 0.010282217886773384,
|
||
|
|
"head_alpha": 0.6950566529600242
|
||
|
|
},
|
||
|
|
"best_trial": {
|
||
|
|
"refusal": 0.75,
|
||
|
|
"kl": 0.0128,
|
||
|
|
"capability_logprob": -7.9867,
|
||
|
|
"capability_drift": 0.0
|
||
|
|
},
|
||
|
|
"n_trials": 16,
|
||
|
|
"baked_to": "qwen-apostate"
|
||
|
|
}
|