name: pretrain_enlarged102m
seed: 1
model: configs/baselines/transformer_enlarged_102m.yaml
data:
  train_bin: data/processed/fineweb_edu_300m/train.bin
  val_bin: data/processed/fineweb_edu_300m/val.bin
train:
  batch_size: 32
  seq_len: 512
  steps: 6000          # 32*512*6000 = 98.3M tokens (actual pilot budget, see DECISIONS D13)
  lr: 6.0e-4
  warmup: 300
  weight_decay: 0.1
  grad_clip: 1.0
  log_every: 20
  eval_every: 500
  eval_batches: 20
  ckpt_every: 1000