SPB Git

spb/wp31_uqo

Public
916 B · 56 lines yaml
1name: p4_overfit64_b82seed: 13mode: prisme4model:5  name: tiny_p46  vocab_size: 1287  d_model: 1928  n_layers: 49  n_heads: 610  n_kv_heads: 211  ffn_width: 51212  max_seq_len: 32013  w: 6414  ffn_w: 19215  n_slots: 1616  n_editor_heads: 217  r_max: 818init:19  backbone_checkpoint: experiments/runs/p4_tiny_backbone_seed01_20261029232626/checkpoint20  freeze_backbone: true21  auto_readout_scale: true22data:23  kind: synthetic24  tokenizer: char25  splits_dir: data/splits/synthetic_v126  loss_span: answer27  eval_splits:28  - dev_iid29  max_train_items: 6430budgets:31- 832budget_probs:33- 1.034budget_per: position35train:36  batch_size: 3237  seq_len: 32038  steps: 60039  lr: 0.00140  warmup: 10041  weight_decay: 0.142  grad_clip: 1.043  log_every: 5044  eval_every: 10045  eval_batches: 446  ckpt_every: 150047em_budgets:48- 049- 250- 851em_max_items: 40052model_overrides:53  readout_zero_init: false54  readout_init_std: 0.555final_exact_match: false56
Files · a2c46f03643fdd75e8e87595931d35e18c590d57
Menu

Theme