← Back to API reference

neuralbench.main.BenchmarkAggregator

pydantic model neuralbench.main.BenchmarkAggregator

Orchestrate multiple Experiment runs and visualise results.

Experiments are submitted (possibly via Slurm) with prepare(), collected with _collect_results(), and plotted/tabled via the functions in neuralbench.plots.benchmark.

Fields:

• collect_max_workers (int)

• debug (bool)

• experiments (list['Experiment'])

• loss_to_metric_mapping (dict[str, str])

• max_workers (int)

• output_dir (str)

field experiments: list['Experiment'] [Required]

field max_workers: int = 256

field collect_max_workers: int = 32

field debug: bool = False

field output_dir: str [Optional]

field loss_to_metric_mapping: dict[str, str] = {'BCEWithLogitsLoss': 'test/f1_score_macro', 'ClipLoss': 'test/full_retrieval/top5_acc_subject-agg', 'CrossEntropyLoss': 'test/bal_acc', 'MSELoss': 'test/pearsonr'}

prepare() → None

run(cached_only: bool = False) → list[dict[str, Any]]

← Back to API reference