Fix evaluation split config in lsat_qa

## Describe the bug
The `lsat_qa` tasks were configured with `evaluation_splits = ["validation", "test"]`, but [`lighteval/lsat_qa`](https://huggingface.co/datasets/lighteval/lsat_qa) only has test split

## To Reproduce
```python
task = "lsat_qa|5"

pipeline = Pipeline(
tasks=task,
pipeline_parameters=pipeline_params,
evaluation_tracker=evaluation_tracker,
model_config=model_config,
)

pipeline.evaluate()
pipeline.save_and_push_results()
pipeline.show_results()```

## Expected behavior
The configuration should only reference the `test` split to ensure successful loading and evaluation.

## Version info
- OS: mac
- Lighteval version: main (local development)