Bendtorch.adam_m: def of bendtorch@1.3.0.0
Import: import bendtorch@1.3.0.0/main.bend as Bendtorch
Lines 273-277 of bendtorch@1.3.0.0/main.bend: https://jend.leeeet.dev/read.txt?path=bendtorch@1.3.0.0/main.bend&start_line=273&end_line=277

import Base

# c1 = 1 - b1 and c2 = 1 - b2 are given as their own constants (0.1, 0.001), as PyTorch computes 1 - beta in float64
# before rounding: 1 - b2 taken in F32 from b2 = 0.999 (0.99900001287 in F32) is 1.3e-5 too small, and over 100 steps
# that alone put the tiny Llama 21x further from float64 than PyTorch's float32 (NOTES, 2026-10-18)
def adam_m(+c1: F32, +m: F32, +g: F32) -> F32:
  (m + (c1 * (g - m : F32) : F32) : F32)

Uses (4):
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.add
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.mul
  https://jend.leeeet.dev/definition.txt?path=Base/base.bend&name=F32.sub