The stochastic differential equations example in the Bayesian DiffEq tutorial doesn't work.

[jerlich]

This section is broken (again?) https://turinglang.org/v0.31/tutorials/10-bayesian-differential-equations/#inference-of-a-stochastic-differential-equation

The plot in the tutorials shows no sampling (the chains are just flat lines).

Running the section gives this warning (over and over):

┌ Warning: Incorrect ϵ = NaN; ϵ_previous = 0.07500000000000001 is used instead.
└ @ AdvancedHMC.Adaptation ~/.julia/packages/AdvancedHMC/AlvV4/src/adaptation/stepsize.jl:131

The summary is just the initial parameters:

Summary Statistics
  parameters      mean       std      mcse   ess_bulk   ess_tail      rhat   ess_per_sec 
      Symbol   Float64   Float64   Float64    Float64    Float64   Float64       Float64 

           σ    1.5000    0.0000       NaN        NaN        NaN       NaN           NaN
           α    1.3000    0.0000    0.0000        NaN        NaN       NaN           NaN
           β    1.2000    0.0000    0.0000        NaN        NaN       NaN           NaN
           γ    2.7000    0.0000    0.0000        NaN        NaN       NaN           NaN
           δ    1.2000    0.0000    0.0000        NaN        NaN       NaN           NaN
          ϕ1    0.1200    0.0000    0.0000        NaN        NaN       NaN           NaN
          ϕ2    0.1200    0.0000    0.0000        NaN        NaN       NaN           NaN

(turing_sde) pkg> st
Project turing_sde v0.1.0
Status `~/repos/scratch/julia/turing_sde/Project.toml`
  [0c46a032] DifferentialEquations v7.13.0
  [f3b207a7] StatsPlots v0.15.7
  [fce5fe82] Turing v0.31.3
  [37e2e46d] LinearAlgebra

julia> versioninfo()
Julia Version 1.10.3
Commit 0b4590a5507 (2024-04-30 10:59 UTC)
Build Info:
  Official https://julialang.org/ release
Platform Info:
  OS: macOS (arm64-apple-darwin22.4.0)
  CPU: 10 × Apple M1 Max
  WORD_SIZE: 64
  LIBM: libopenlibm
  LLVM: libLLVM-15.0.7 (ORCJIT, apple-m1)
Threads: 8 default, 0 interactive, 4 GC (on 8 virtual cores)