Cases Skills About

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Meta

© 2026 ClawIndex All Rights Reserved.

Skills with output: training metrics

Browse skills that produce this output.

verl-rl-training - RL Training Library for LLMs
Reinforcement Learning RLHF GRPO PPO
★ 650 · Updated 2026-06-30
Provides guidance for training LLMs with RL using verl library
⚙ train models with RLHF ⚙ train models with GRPO ⚙ train models with PPO
verl-rl-training - LLM Reinforcement Learning Training with Verl
Reinforcement Learning RLHF Post-Training Distributed Training
★ 0 · Updated 2026-06-30
Train LLMs at scale using verl with PPO, GRPO, and other RL algorithms
⚙ train models with PPO ⚙ train models with GRPO ⚙ configure RL algorithms
verl-rl-training - Train LLMs with verl RL library
Reinforcement Learning RLHF Model Training Distributed Computing
★ 1 · Updated 2026-06-30
Flexible RL training library for large language models supporting multiple algorithms and backends
⚙ train LLM with GRPO algorithm ⚙ train LLM with PPO algorithm ⚙ train LLM with RLOO algorithm
pytorch-lightning - PyTorch Lightning Training Framework
PyTorch Lightning training framework distributed training ddp
★ 2 · Updated 2026-05-28
High-level PyTorch framework for distributed training with automatic DDP/FSDP/DeepSpeed support
⚙ train model ⚙ validate model ⚙ test model
PyTorch ML - PyTorch Deep Learning Environment
deep learning machine learning GPU acceleration computer vision
★ 15 · Updated 2026-03-21
Complete machine learning environment with PyTorch for model training and GPU acceleration
⚙ define neural network ⚙ load pretrained model ⚙ train model
distributed-training - Distributed Training Parallelism Strategies
machine learning distributed training GPU parallel deep learning
★ 2 · Updated 2026-03-10
Provides guidance for scaling ML training across multiple GPUs and nodes with parallelism strategies
⚙ train across multiple GPUs ⚙ select parallelism strategy ⚙ synchronize gradients