preprocess/fewshot_gym_dataset.py [120:147]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def generate_k_shot_data(self, k, seed, path=None):
        """
        generate a k-shot (k) dataset using random seed (seed)
        return train, dev, test
        """

        if self.hf_identifier not in config_dict:
            return None, None, None

        if use_instruct and self.hf_identifier not in prompt_names_per_task:
            return None, None, None

        if do_train:
            if seed<100:
                return None, None, None
            k = 16384
        elif do_test:
            k = 16

        # load dataset
        dataset = self.load_dataset()

        # formulate into list (for consistency in np.random)
        train_lines, test_lines = self.get_train_test_lines(dataset)

        # shuffle the data
        np.random.seed(seed)
        np.random.shuffle(train_lines)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



preprocess/fewshot_gym_dataset.py [177:204]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def generate_k_shot_data(self, k, seed, path=None):
        """
        generate a k-shot (k) dataset using random seed (seed)
        return train, dev, test
        """

        if self.hf_identifier not in config_dict:
            return None, None, None

        if use_instruct and self.hf_identifier not in prompt_names_per_task:
            return None, None, None

        if do_train:
            if seed<100:
                return None, None, None
            k = 16384
        elif do_test:
            k = 16

        # load dataset
        dataset = self.load_dataset()

        # formulate into list (for consistency in np.random)
        train_lines, test_lines = self.get_train_test_lines(dataset)

        # shuffle the data
        np.random.seed(seed)
        np.random.shuffle(train_lines)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -