Allow continuation of MCMC chains when using latest_sample

[jan-matthis]

While latest_sample was implemented, it was transferred from the proposal distribution to the posterior object returned by inference which made it impossible to be used. This is addressed in this PR.

[codecov-commenter]

Codecov Report

Merging #348 into main will decrease coverage by 0.14%.
The diff coverage is 50.00%.

@@            Coverage Diff             @@
##             main     #348      +/-   ##
==========================================
- Coverage   74.23%   74.09%   -0.15%     
==========================================
  Files          49       49              
  Lines        2826     2841      +15     
==========================================
+ Hits         2098     2105       +7     
- Misses        728      736       +8     

Flag	Coverage Δ
#unittests	74.09% <50.00%> (-0.15%)	⬇️

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files	Coverage Δ
sbi/inference/posteriors/base_posterior.py	64.59% <33.33%> (-0.32%)	⬇️
sbi/inference/snle/snle_base.py	95.18% <50.00%> (-1.12%)	⬇️
sbi/inference/snpe/snpe_base.py	93.26% <50.00%> (-0.85%)	⬇️
sbi/inference/snre/snre_base.py	94.84% <50.00%> (-0.95%)	⬇️
sbi/mcmc/init_strategy.py	37.50% <50.00%> (+4.16%)	⬆️
sbi/mcmc/__init__.py	100.00% <100.00%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 924ca57...76908b6. Read the comment docs.