Lightning-AI/lit-llama

Resume in the pretraining code

Open

#359 aberto em 2 de jun. de 2023

Ver no GitHub
 (2 comments) (1 reaction) (0 assignees)Python (473 forks)batch import
help wanted

Métricas do repositório

Stars
 (5.533 stars)
Métricas de merge de PR
 (Nenhuma PRs mesclada em 30d)

Description

I would like to request a new feature in the code: the ability to resume training from a checkpoint.

Currently, the code can save a checkpoint of the model's state at any point during training. However, there is no way to resume training from a checkpoint.

The code can save two things along with the model state_dict: 1)the optimizer, 2)the id of the last example it has seen (assuming the data is fed sequentially to the model not randomly)

Guia do colaborador