ntized_states)
        >>> cosine_sim = torch.cosine_similarity(outputs.projected_states, outputs.projected_quantized_states, dim=-1)

        >>> # show that cosine similarity is much higher than random
        >>> cosine_sim[mask_time_indices.to(torch.bool)].mean() > 0.5
        tensor(True)

        >>> # for contrastive loss training model should be put into train mode
        >>> model = model.train()
        >>> loss = model(
        ...     input_values, mask_time_indices=mask_time_indices, sampled_negative_indices=sampled_negative_indices
        ... ).loss
        ```N)