loss_metric.py

# Copyright 2020 The HuggingFace Datasets Authors and the current dataset script contributor.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
"""Calculation of the cross-entropy loss function using the huggingface evaluate module."""

import evaluate
import datasets
import numpy as np
import torch

from torch import nn, Tensor, tensor

_CITATION = """\
@InProceedings{huggingface:module,
title = {Loss Metric},
authors={YU YE},
year={2024}
}
"""

_DESCRIPTION = """\
Calculation of the cross-entropy loss function using the huggingface evaluate module.
"""

_KWARGS_DESCRIPTION = """
Calculates how good are predictions given some references, using certain scores
Args:
    predictions: list of predictions to score. Each predictions
        should be a string with tokens separated by spaces.
    references: list of reference for each prediction. Each
        reference should be a string with tokens separated by spaces.
Returns:
    loss: description of the first score,
Examples:
    Examples should be written in doctest format, and should illustrate how
    to use the function.

    >>> my_new_module = evaluate.load("Aye10032/loss_metric")
    >>> results = my_new_module.compute(references=[0, 1], predictions=[0, 1])
    >>> print(results)
    {'loss': 1.0}
"""


@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
class LossMetric(evaluate.Metric):
    """Calculation of the cross-entropy loss function using the huggingface evaluate module."""

    def _info(self):
        return evaluate.MetricInfo(
            # This is the description that will appear on the modules page.
            module_type="metric",
            description=_DESCRIPTION,
            citation=_CITATION,
            inputs_description=_KWARGS_DESCRIPTION,
            # This defines the format of each prediction and reference
            features=datasets.Features({
                'predictions': datasets.Value('int64'),
                'references': datasets.Value('int64'),
            }),
            # Homepage of the module for documentation
            homepage="http://module.homepage",
            # Additional links to the codebase or references
            codebase_urls=["http://github.com/path/to/codebase/of/new_module"],
            reference_urls=["http://path.to.reference.url/new_module"]
        )

    def _compute(self, predictions, references):
        """Returns the scores"""
        pred = tensor(np.array(predictions), dtype=torch.float16)
        label = tensor(np.array(references), dtype=torch.float16)
        loss_func = nn.CrossEntropyLoss()
        loss = loss_func(pred, label)

        mean_loss = loss.item() / label.shape[0]
        return {
            "loss": mean_loss,
        }