arch:
  H_cycles: 2
  H_override: {}
  L_cycles: 3
  bp_max_steps: 5
  bp_warmup_ratio: 0.2
  expansion: 4
  half_layers: true
  head: lm_head@LMHead
  hidden_size: 1024
  init_type: lecun_normal
  n_layers: 12
  name: baselines.hrm_nocarry_bp_warmup@HierarchicalReasoningModel
  norm_eps: 1.0e-06
  norm_type: pre
  num_heads: 8
  pos_emb_type: rope
  rope_theta: 10000.0
beta1: 0.9
beta2: 0.95
checkpoint_interval: 1
checkpoint_path: /home/work/.data/hrm_text_checkpoints/koterm_b_swe_glm_pilot_v1
data:
  path: /home/work/.data/hrm_text_prepared/sft_swe_glm_mix_v1
  target_only: true
ema: 0.9999
epochs: 1
fwd_bwd_dtype: bfloat16
global_batch_size: 262144
log_interval: 5
lr: 0.00022
lr_min_ratio: 1.0
lr_warmup_steps: 100
project_name: HRM-Ko-Terminal
resume_epoch: null
resume_from: null
run_name: koterm_b_swe_glm_pilot_v1
seed: 0
weight_decay: 0.1
weights_only_resume_from_ema: false