experiment: name: controller_mini seed: 1 mode: prisme model: from_checkpoint checkpoint: experiments/runs/mini_editor_seed01_20261030005118/checkpoint labels: train: experiments/runs/labels_mini_seed01_20261030005150/labels_train.pt calib: experiments/runs/labels_mini_seed01_20261030005150/labels_calib.pt train: steps: 60 lr: 0.001 weight_decay: 0.01 alpha: 1.0 beta: 0.5 gamma: 0.1 huber_delta: 0.1 log_every: 20 eval_every: 30 seq_len: 320 lambda_grid: - 0.0 - 0.3 kappa_grid: - 0.0 sweep_batches: 2 max_budget: 4 selection_rule: max_loss_reduction_per_ops model: name: mini vocab_size: 128 d_model: 96 n_layers: 2 n_heads: 4 n_kv_heads: 2 ffn_width: 256 max_seq_len: 320 rope_theta: 10000.0 norm_eps: 1.0e-05 tie_embeddings: true init_std: 0.02 use_workspace: true w: 32 ffn_w: 96 n_slots: 16 n_editor_blocks: 2 n_editor_heads: 2 r_max: 8 eta_max: 0.25 clip_c: 1.0 clip_eps: 1.0e-06 readout_zero_init: false readout_init_std: 0.2 readout_scale: 0.11967716366052628 controller_hidden: 0 ctrl_input: h ctrl_use_entropy: true lambda_cost: 0.0 kappa_risk: 0.0 dense_writes: false