Supplemental practical concepts · MLD-0166
Checkpoint
A saved snapshot of model parameters and optionally optimizer, scheduler, and random-state information.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Resume interrupted training.
Original caveat
A weights-only checkpoint may not support identical training continuation.
Context and aliases
Level: Intermediate. Stages: Training · Inference · Evaluation.
Tags: ML · DL · LLM · SLM.
Aliases: Model checkpoint.
Related concepts
Concepts linking here
Original references
- Deep Learning: online textbook ↗ · Consulted
- Transformers glossary ↗ · Consulted
- OpenAI Spinning Up: reinforcement learning ↗ · Consulted
- PyTorch documentation ↗ · Reference link
- Original reference URL ↗