Patch release 1 - SFTTrainer enhancements and fixes

This patch release adds multiple fixes for the SFTTrainer and enhancements. Another patch release is coming for fixing an issue with PPOTrainer and Google Colab combined with wandb logging

What's Changed

• Add slurm utility by @vwxyzjn in https://github.com/lvwerra/trl/pull/412
• Enable autotag feature w/ wandb by @vwxyzjn in https://github.com/lvwerra/trl/pull/411
• [doc build] Use secrets by @mishig25 in https://github.com/lvwerra/trl/pull/420
• Update test_reward_trainer.py by @younesbelkada in https://github.com/lvwerra/trl/pull/421
• best-of-n sampler class by @metric-space in https://github.com/lvwerra/trl/pull/375
• handle the offline case by @younesbelkada in https://github.com/lvwerra/trl/pull/431
• Fix correct gradient accumulation by @younesbelkada in https://github.com/lvwerra/trl/pull/407
• Drop support for Python 3.7 by @younesbelkada in https://github.com/lvwerra/trl/pull/441
• [SFTTrainer] Relax dataset constraints by @younesbelkada in https://github.com/lvwerra/trl/pull/442
• [SFTTrainer] Fix non packed dataset by @younesbelkada in https://github.com/lvwerra/trl/pull/444
• [core] Add stale bot by @younesbelkada in https://github.com/lvwerra/trl/pull/447
• [SFTTrainer] Introducing DataCollatorForCompletionOnlyLM by @younesbelkada in https://github.com/lvwerra/trl/pull/445
• [ConstantLengthDataset] Fix packed dataset issue by @younesbelkada in https://github.com/lvwerra/trl/pull/452
• Update accelerate arg passthrourgh for tensorboard logging to reflect logging_dir deprecation. by @jganitkevitch in https://github.com/lvwerra/trl/pull/437
• Multi adapter RL (MARL) - a single model for RM & Value Head by @younesbelkada in https://github.com/lvwerra/trl/pull/373

New Contributors

• @jganitkevitch made their first contribution in https://github.com/lvwerra/trl/pull/437

Full Changelog: https://github.com/lvwerra/trl/compare/v0.4.4...v0.4.5