name: recursive_reasoning.hrm@HierarchicalReasoningModel_ACTV1
loss:
  name: losses@ACTLossHead
  loss_type: stablemax_cross_entropy

halt_exploration_prob: 0.1
halt_max_steps: 16

H_cycles: 2
L_cycles: 2

H_layers: 4
L_layers: 4

hidden_size: 512
num_heads: 8  # min(2, hidden_size // 64)
expansion: 4

puzzle_emb_ndim: ${.hidden_size}

pos_encodings: rope
forward_dtype: bfloat16

mlp_t: False # use mlp on L instead of transformer