File size: 3,465 Bytes
13362e2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
# Copyright 2024 Llamole Team
#
# 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.
from dataclasses import dataclass
from typing import TYPE_CHECKING, Dict
import numpy as np
import torch
from transformers.utils import is_jieba_available, is_nltk_available
from ...extras.constants import IGNORE_INDEX
from ...extras.packages import is_rouge_available
if TYPE_CHECKING:
from transformers import EvalPrediction, PreTrainedTokenizer
if is_jieba_available():
import jieba # type: ignore
if is_nltk_available():
from nltk.translate.bleu_score import SmoothingFunction, sentence_bleu
if is_rouge_available():
from rouge_chinese import Rouge
def compute_accuracy(eval_preds: "EvalPrediction") -> Dict[str, float]:
preds, labels = eval_preds.predictions, eval_preds.label_ids
accuracies = []
for i in range(len(preds)):
pred, label = preds[i, :-1], labels[i, 1:]
label_mask = label != IGNORE_INDEX
accuracies.append(np.mean(pred[label_mask] == label[label_mask]))
return {"accuracy": float(np.mean(accuracies))}
def eval_logit_processor(logits: "torch.Tensor", labels: "torch.Tensor") -> "torch.Tensor":
logits = logits[0] if isinstance(logits, (list, tuple)) else logits
return torch.argmax(logits, dim=-1)
@dataclass
class ComputeMetrics:
r"""
Wraps the tokenizer into metric functions, used in Seq2SeqPeftTrainer.
"""
tokenizer: "PreTrainedTokenizer"
def __call__(self, eval_preds: "EvalPrediction") -> Dict[str, float]:
r"""
Uses the model predictions to compute metrics.
"""
preds, labels = eval_preds.predictions, eval_preds.label_ids
score_dict = {"rouge-1": [], "rouge-2": [], "rouge-l": [], "bleu-4": []}
preds = np.where(preds != IGNORE_INDEX, preds, self.tokenizer.pad_token_id)
labels = np.where(labels != IGNORE_INDEX, labels, self.tokenizer.pad_token_id)
decoded_preds = self.tokenizer.batch_decode(preds, skip_special_tokens=True)
decoded_labels = self.tokenizer.batch_decode(labels, skip_special_tokens=True)
for pred, label in zip(decoded_preds, decoded_labels):
hypothesis = list(jieba.cut(pred))
reference = list(jieba.cut(label))
if len(" ".join(hypothesis).split()) == 0 or len(" ".join(reference).split()) == 0:
result = {"rouge-1": {"f": 0.0}, "rouge-2": {"f": 0.0}, "rouge-l": {"f": 0.0}}
else:
rouge = Rouge()
scores = rouge.get_scores(" ".join(hypothesis), " ".join(reference))
result = scores[0]
for k, v in result.items():
score_dict[k].append(round(v["f"] * 100, 4))
bleu_score = sentence_bleu([list(label)], list(pred), smoothing_function=SmoothingFunction().method3)
score_dict["bleu-4"].append(round(bleu_score * 100, 4))
return {k: float(np.mean(v)) for k, v in score_dict.items()}
|