from collections import Counter from psi.data.sampler import TaskMixtureSampler def _dataset_sequence(sampler): sequence = [] for batch in sampler: dataset_ids = {dataset_id for dataset_id, _ in batch} assert len(dataset_ids) == 1 sequence.append(next(iter(dataset_ids))) return sequence def test_task_mixture_sampler_batches_are_homogeneous(monkeypatch): monkeypatch.setenv("RANK", "0") monkeypatch.setenv("WORLD_SIZE", "1") sampler = TaskMixtureSampler( dataset_lens=[100, 50, 30], mixture_ratios=[3, 1, 0], num_samples_per_epoch=64, batch_size=4, seed=7, ) batches = list(sampler) assert len(batches) == 16 for batch in batches: assert len(batch) == 4 assert len({dataset_id for dataset_id, _ in batch}) == 1 def test_task_mixture_sampler_respects_batch_ratios(monkeypatch): monkeypatch.setenv("RANK", "0") monkeypatch.setenv("WORLD_SIZE", "1") sampler = TaskMixtureSampler( dataset_lens=[100, 50], mixture_ratios=[3, 1], num_samples_per_epoch=64, batch_size=4, seed=11, ) counts = Counter(_dataset_sequence(sampler)) assert counts == Counter({0: 12, 1: 4}) def test_task_mixture_sampler_distributed_schedule_matches_global(monkeypatch): common_kwargs = dict( dataset_lens=[100, 50, 30], mixture_ratios=[5, 3, 2], num_samples_per_epoch=64, batch_size=4, seed=19, ) monkeypatch.setenv("RANK", "0") monkeypatch.setenv("WORLD_SIZE", "1") global_sequence = _dataset_sequence(TaskMixtureSampler(**common_kwargs)) monkeypatch.setenv("RANK", "0") monkeypatch.setenv("WORLD_SIZE", "2") rank0_sequence = _dataset_sequence(TaskMixtureSampler(**common_kwargs)) monkeypatch.setenv("RANK", "1") monkeypatch.setenv("WORLD_SIZE", "2") rank1_sequence = _dataset_sequence(TaskMixtureSampler(**common_kwargs)) merged_sequence = [] for batch_idx in range(len(global_sequence)): local_idx = batch_idx // 2 merged_sequence.append(rank0_sequence[local_idx] if batch_idx % 2 == 0 else rank1_sequence[local_idx]) assert merged_sequence == global_sequence