def get_train_reward_experiments()

in launch.py [0:0]

• 47 lines of code
• 1 McCabe index (conditional complexity)

def get_train_reward_experiments():
    _shared = combos(
        bind('labels.type', 'best_of_4'),
        bind('normalize_after', True),
        bind('normalize_before', True),
        bind('normalize_samples', 256),
    )


    _books_task = combos(
        bind_nested('task', books_task),
        _shared,
        bind('batch_size', 32),
        bind('lr', 5e-5),
        bind('rollout_batch_size', 512),
    )

    sentiment = combos(
        _books_task,

        bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/sentiment/offline_5k.json'),
        bind('labels.num_train', 4_992),
        bind('run.seed', 1)
    )


    descriptiveness = combos(
        _books_task,

        bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/descriptiveness/offline_5k.json'),
        bind('labels.num_train', 4_992),
        bind('run.seed', 1)
    )

    cnndm = combos(
        bind_nested('task', summarize_cnndm_task),
        _shared,

        # bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/cnndm/offline_60k.json'),
        # bind('labels.num_train', 60_000),
        bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/cnndm/online_45k.json'),
        bind('labels.num_train', 46_000),

        bind('batch_size', 2 * 8),
        bind('lr', 2.5e-5),
        bind('rollout_batch_size', 128),
        bind('run.seed', 1)
    )

    tldr = combos(
        bind_nested('task', summarize_tldr_task),
        _shared,

        # bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/tldr/offline_60k.json'),
        # bind('labels.num_train', 60_000),
        bind('labels.source', 'https://openaipublic.blob.core.windows.net/lm-human-preferences/labels/tldr/online_45k.json'),
        bind('labels.num_train', 46_000),

        bind('batch_size', 2 * 8),
        bind('lr', 2.5e-5),
        bind('rollout_batch_size', 128),
        bind('run.seed', 1)
    )

    return locals()