arch:
  H_cycles: 3
  H_layers: 0
  L_cycles: 4
  L_layers: 2
  expansion: 4
  forward_dtype: bfloat16
  grid_noise_fraction: 0.02
  grid_noise_prob: 0.05
  grid_token_dropout: 0.05
  halt_exploration_prob: 0.1
  halt_max_steps: 16
  halt_max_steps_eval: null
  hidden_size: 512
  loss:
    loss_type: stablemax_cross_entropy
    name: losses@ACTLossHead
  mlp_t: false
  name: recursive_reasoning.trm@TinyRecursiveReasoningModel_ACTV1
  no_ACT_continue: true
  num_heads: 8
  pos_encodings: rope
  puzzle_emb_dropout: 0.1
  puzzle_emb_len: 1
  puzzle_emb_ndim: 512
beta1: 0.9
beta2: 0.95
checkpoint_every_eval: true
checkpoint_every_n_steps: null
checkpoint_path: checkpoints/Arc2concept-aug-1000-ACT-torch/ctd_train_AAII_50k
data_paths:
- data/arc2concept-aug-1000
data_paths_test: []
dataloader_num_workers: 1
dataloader_persistent_workers: true
dataloader_pin_memory: true
dataloader_prefetch_factor: 8
ema: true
ema_rate: 0.999
entity: trelis
epochs: 50000
eval_global_batch_size: null
eval_interval: 5000
eval_max_augmentations: null
eval_save_outputs: []
evaluators:
- name: arc@ARC
freeze_weights: true
freeze_weights_epochs: 3125
global_batch_size: 768
grid_noise_fraction: null
grid_noise_prob: null
halt_max_steps_eval: null
load_checkpoint: /workspace/TinyRecursiveModels-private/pretrained/step_723914
lr: 0.0001
lr_min_ratio: 1.0
lr_warmup_steps: 2000
min_eval_interval: 0
project_name: Arc2concept-aug-1000-ACT-torch
puzzle_emb_lr: 0.01
puzzle_emb_reinit_strategy: mean
puzzle_emb_weight_decay: 0.1
run_name: ctd_train_AAII_50k
seed: 0
weight_decay: 0.1