Skip to content

Fix early stop conditions #89

Description

@SarahAlidoost

Currently in train.py module, The early stopping happens as:

        current_lr = optimizer.param_groups[0]["lr"]
        if counter >= training_config.patience and current_lr <= scheduler.min_lrs[0]:
            break

The scheduler.min_lrs[0] is hard coded as 1e-7 and reduction factor is 0.5. Therefore, as can be seen from the results of training, training reaches a plateau, but the epoch loop doesnot break. We should expose these argument to be bale to adjust them based on optimizer_lr.

Metadata

Metadata

Assignees

Labels

No labels
No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions