jpata/particleflow: v1.9.0

What's Changed

• fix CMS instructions by @jpata in https://github.com/jpata/particleflow/pull/334
• MLPF datasets v2.0.0: track pythia-level genjets, genmet in datasets; add per-particle ispu flag by @jpata in https://github.com/jpata/particleflow/pull/332
• CMS training instructions by @jpata in https://github.com/jpata/particleflow/pull/336
• Retraining with CMS samples v2.0.0 by @jpata in https://github.com/jpata/particleflow/pull/337
• Fix use of deprecated Ray Tune environment variable by @erwulff in https://github.com/jpata/particleflow/pull/338
• CMS dataset relabel, generate v2.1.0 with more stats, separate binary classifier by @jpata in https://github.com/jpata/particleflow/pull/340
• Pre-layernorm by @erwulff in https://github.com/jpata/particleflow/pull/339
• Switch to datasets v2.2.0 by @jpata in https://github.com/jpata/particleflow/pull/341
• try to improve val loss stability by @jpata in https://github.com/jpata/particleflow/pull/342
• Regression of log-transformed energy and pt, training checkpoints by @jpata in https://github.com/jpata/particleflow/pull/343
• CLIC dataset v2.2.0, CMS dataset 2.4.0 by @jpata in https://github.com/jpata/particleflow/pull/345
• Update dataset validation plot notebooks by @jpata in https://github.com/jpata/particleflow/pull/347

Full Changelog: https://github.com/jpata/particleflow/compare/v1.8.0...v1.9.0