Skip to content

Conversation

@Nicolas1203
Copy link
Contributor

Add last epoch argument. last_epoch is removed of the optimizer as a value different from -1 gives an error. Ideally, the model should be saved using a checkpoint containing the optimizer state_dict, like suggested here: https://pytorch.org/tutorials/beginner/saving_loading_models.html#saving-loading-a-general-checkpoint-for-inference-and-or-resuming-training

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant