name: controller_v1rank seed: 1 mode: prisme model: from_checkpoint checkpoint: experiments/runs/p4_editor_v1_Ustd02_seed01_20261029235050/checkpoint labels: train: experiments/runs/labels_v1ctrl_seed01_20261030004018/labels_train.pt calib: experiments/runs/labels_v1ctrl_seed01_20261030004018/labels_calib.pt train: steps: 2000 lr: 0.001 weight_decay: 0.01 alpha: 1.0 beta: 0.5 gamma: 0.1 huber_delta: 0.1 log_every: 100 eval_every: 250 seq_len: 320 pairwise: 1.0 listwise: 1.0 rank_temp: 0.02 lambda_grid: - 0.0 - 0.01 - 0.03 - 0.1 - 0.3 kappa_grid: - 0.0 - 0.5 sweep_batches: 10 max_budget: 8 selection_rule: max_loss_reduction_per_ops model_overrides: ctrl_input: h ctrl_use_entropy: true