| alg_name: "ROME" | |
| model_name: "./hugging_cache/gpt2-xl" | |
| stats_dir: "./data/stats" | |
| device: cpu | |
| layers: [5] | |
| fact_token: "subject_last" | |
| v_num_grad_steps: 20 | |
| v_lr: 5e-1 | |
| v_loss_layer: 11 | |
| v_weight_decay: 0.5 | |
| clamp_norm_factor: 4 | |
| kl_factor: 0.0625 | |
| mom2_adjustment: false | |
| context_template_length_params: [[5, 10], [10, 10]] | |
| rewrite_module_tmp: "transformer.h.{}.mlp.c_proj" | |
| layer_module_tmp: "transformer.h.{}" | |
| mlp_module_tmp: "transformer.h.{}.mlp" | |
| attn_module_tmp: "transformer.h.{}.attn" | |
| ln_f_module: "transformer.ln_f" | |
| lm_head_module: "transformer.wte" | |
| mom2_dataset: "wikipedia" | |
| mom2_n_samples: 100000 | |
| mom2_dtype: "float32" | |
| model_parallel: false | |
| fp16: false | |