blob: cf16aa5d5706a54edc9720050bf5ebc40523b04e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
|
name: recursive_reasoning.trm_singlez@TinyRecursiveReasoningModel_ACTV1
loss:
name: losses@ACTLossHead
loss_type: stablemax_cross_entropy
halt_exploration_prob: 0.1
halt_max_steps: 16
H_cycles: 3
L_cycles: 6
H_layers: 0
L_layers: 2
hidden_size: 512
num_heads: 8 # min(2, hidden_size // 64)
expansion: 4
puzzle_emb_ndim: ${.hidden_size}
pos_encodings: rope
forward_dtype: bfloat16
mlp_t: False # use mlp on L instead of transformer
puzzle_emb_len: 16 # if non-zero, its specified to this value
no_ACT_continue: True # No continue ACT loss, only use the sigmoid of the halt which makes much more sense
|
