MeasuredFit.Config(
        study_name='convextok',
        experiment_name='exp000',
        doc='',
        base_dir='/opt/scratch',
        working_dir=PosixPath('/opt/scratch/runs/convextok/exp000'),
        preparation=ConvexTokPreparation.Config(
            raw_dir=PosixPath('/opt/scratch/datasets/nanochat/raw'),
            shard_indices=[0, 1, 2, 3, 4, 5, 6],
            working_dir=PosixPath('/opt/scratch/runs/convextok/exp000'),
            vocab_size=16_384,
            reserved_count=10,
            split_pattern="'(?i:[sdmt]|ll|ve|re)|[^\\r\\n\\p{L}\\p{N}]?+\\p{L}+|\\p{N}{1,2}| "
            '?[^\\s\\p{L}\\p{N}]++[\\r\\n]*|\\s*[\\r\\n]|\\s+(?!\\S)|\\s+',
            num_workers=16,
            presolve=priml.baselines.convextok.presolver.presolve.presolve,
            solver=Pdlp.Config(
                tolerance=0.0001,
                iteration_limit=100_000,
                ruiz_iterations=10,
                restart_period=200,
                sufficient_reduction=0.2,
                necessary_reduction=0.8,
                artificial_restart=0.36,
                pid_proportional=0.99,
                pid_integral=0.01,
                pid_derivative=0.0,
                pid_integral_smoothing=0.3
            ),
            rounding=priml.baselines.convextok.rounding.deterministic_rounding,
            device='cuda'
        ),
        reference=None
    )
