Skip to content

[Bug] Repetitive meaningless text on IFEval with Llama 3 (not seen on Llama 2) #4

@s30km0

Description

@s30km0

Description
Llama 3 models fine-tuned with QuanTA produce meaningless phrases when evaluated on IFEval. This repetition degrades IFEval scores. The same issue does not occur with Llama 2 models under the same QuanTA configuration.

Other fine-tuning methods (LoRA, FFT) on the same Llama 3 model also do not exhibit this behavior — the issue appears to be QuanTA.

Reproduction

  1. Fine-tune a Llama 3 model with QuanTA.
  2. Evaluate on IFEval (lm-evaluation-harness).
  3. Observe sentence-level repetition in generated outputs.

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