Logging docs appear to be out of date

[ezyang]

Reproduction

https://huggingface.co/docs/trl/main/en/logging mentions many metrics that do not seem to exist anymore. https://huggingface.co/docs/trl/main/en/ppo_trainer is substantially more up to date.

System Info

- Platform: Linux-6.4.3-0_fbk20_zion_2830_g3e5ab162667d-x86_64-with-glibc2.34
- Python version: 3.10.17
- PyTorch version: 2.6.0+cu124
- CUDA device(s): NVIDIA H100, NVIDIA H100, NVIDIA H100, NVIDIA H100, NVIDIA H100, NVIDIA H100, NVIDIA H100, NVIDIA H100
- Transformers version: 4.51.3
- Accelerate version: 1.6.0
- Accelerate config: 
  - compute_environment: LOCAL_MACHINE
  - distributed_type: MULTI_GPU
  - mixed_precision: no
  - use_cpu: False
  - debug: False
  - num_processes: 8
  - machine_rank: 0
  - num_machines: 1
  - gpu_ids: all
  - rdzv_backend: static
  - same_network: True
  - main_training_function: main
  - enable_cpu_affinity: False
  - downcast_bf16: no
  - tpu_use_cluster: False
  - tpu_use_sudo: False
  - tpu_env: []
- Datasets version: 3.6.0
- HF Hub version: 0.31.1
- TRL version: 0.15.2
- bitsandbytes version: 0.45.5
- DeepSpeed version: 0.16.7
- Diffusers version: 0.33.1
- Liger-Kernel version: not installed
- LLM-Blender version: not installed
- OpenAI version: 1.78.0
- PEFT version: 0.15.2

Checklist

• I have checked that my issue isn't already filed (see open issues)
• I have included my system information
• Any code provided is minimal, complete, and reproducible (more on MREs)
• Any code provided is properly formatted in code blocks, (no screenshot, more on code blocks)
• Any traceback provided is complete