| arch: |
| H_cycles: 3 |
| H_layers: 0 |
| L_cycles: 6 |
| L_layers: 2 |
| expansion: 4 |
| forward_dtype: bfloat16 |
| halt_exploration_prob: 0.1 |
| halt_max_steps: 16 |
| hidden_size: 512 |
| loss: |
| loss_type: stablemax_cross_entropy |
| name: losses@ACTLossHead |
| mlp_t: true |
| name: recursive_reasoning.trm@TinyRecursiveReasoningModel_ACTV1 |
| no_ACT_continue: true |
| num_heads: 8 |
| pos_encodings: none |
| puzzle_emb_len: 16 |
| puzzle_emb_ndim: 512 |
| beta1: 0.9 |
| beta2: 0.95 |
| checkpoint_every_eval: true |
| checkpoint_path: checkpoints/Sudoku-extreme-1k-aug-1000-ACT-torch/pretrain_mlp_t_sudoku |
| data_paths: |
| - data/sudoku-extreme-1k-aug-1000 |
| data_paths_test: [] |
| ema: true |
| ema_rate: 0.999 |
| epochs: 50000 |
| eval_interval: 5000 |
| eval_save_outputs: [] |
| evaluators: [] |
| freeze_weights: false |
| global_batch_size: 768 |
| load_checkpoint: null |
| lr: 0.0001 |
| lr_min_ratio: 1.0 |
| lr_warmup_steps: 2000 |
| min_eval_interval: 0 |
| project_name: Sudoku-extreme-1k-aug-1000-ACT-torch |
| puzzle_emb_lr: 0.0001 |
| puzzle_emb_weight_decay: 1.0 |
| run_name: pretrain_mlp_t_sudoku |
| seed: 0 |
| weight_decay: 1.0 |
|
|
