Skip to content

Bug: encoder.pt and config not loaded correct during resume #72

@retoriax

Description

@retoriax

There seems to be a mismatch in how the model is loaded during resume.

See the original code:

KBLaM/experiments/train.py

Lines 906 to 908 in 029e2fb

if model_dir_to_resume:
encoder.load_state_dict(torch.load(os.path.join(model_dir_to_resume, "encoder.pt")))
kb_config = KBLaMConfig.from_pretrained(os.path.join(model_dir_to_resume, "kb_config.json"))

This needs to be changed to

 if model_dir_to_resume:
        encoder.load_state_dict(torch.load(os.path.join(model_dir_to_resume, "_encoder/encoder.pt")))
        kb_config = KBLaMConfig.from_pretrained(os.path.join(model_dir_to_resume, "config.json"))
        # or kb_config = KBLaMConfig.from_pretrained(model_dir_to_resume)

Why this change is neede:
• encoder.pt is saved inside an other folder _encoder/
• the config is saved as config.json, not kb_config.json

Metadata

Metadata

Assignees

No one assigned

    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