downstream_evaluators = [
    "pubmedqa_mc",
    "scifact_rc",
]

trainer_config = (
    TrainerConfig(
        ...
    ).with_callback(
        "evaluator",
        LMEvaluatorCallbackConfig(
            eval_dataset=NumpyDatasetConfig(
                paths=["/net/nfs/allennlp/llm-data/c4/en/c4-validation.00000-00008.npy"],
                metadata=[{"label": "c4-validation"}],
                name=NumpyDatasetType.padded_fsl,
                sequence_length=1024,
                tokenizer=tokenizer_config,
                work_dir="/tmp/dataset-cache",
            ),
            eval_interval=250,
            eval_duration=Duration.steps(10),
        ),
    ).with_callback(
        "downstream",
        DownstreamEvaluatorCallbackConfig(
            labels=downstream_evaluators,
            eval_batch_size=4,
            tokenizer="meta-llama/Llama-2-7b-hf",  # tokenizer implementation from OMLo
            eval_interval=10,
            # eval_duration=Duration.steps(10),
        ),
    )
)