Open AdrianKs opened 1 year ago
Currently, logs for the training job are not written to kge.log if we resume from checkpoint. By default on model.create_from() we use a tmp file for logging.
This small change should fix the issue.
Currently, logs for the training job are not written to kge.log if we resume from checkpoint. By default on model.create_from() we use a tmp file for logging.
This small change should fix the issue.