引言

今天我们来实现ESIM文本匹配，这是一个典型的交互型文本匹配方式，也是近期第一个测试集准确率超过80%的模型。

我们来看下是如何实现的。

模型架构

我们主要实现左边的ESIM网络。

从下往上看，分别是

• 输入编码层(Input Ecoding)
  对前提和假设进行编码
  把语句中的单词转换为词向量，得到一个向量序列
  把两句话的向量序列分别送入各自的Bi-LSTM网络进行语义特征抽取
• 局部推理建模层(Local Inference Modeling)
  就是注意力层
  通过注意力层捕获LSTM输出向量间的局部特征
  然后通过元素级方法构造了一些特征
• 推理组合层(Inference Composition)
  和输入编码层一样，也是Bi-LSTM
  在捕获了文本间的注意力特征后，进一步做的融合/提取语义特征工作
• 预测层(Prediction)
  拼接平均池化和最大池化后得到的向量
  接Softmax进行分类

模型实现

class ESIM(nn.Module):
    def __init__(
        self,
        vocab_size: int,
        embedding_size: int,
        hidden_size: int,
        num_classes: int,
        lstm_dropout: float = 0.1,
        dropout: float = 0.5,
    ) -> None:
        """_summary_

        Args:
            vocab_size (int): the size of the Vocabulary
            embedding_size (int): the size of each embedding vector
            hidden_size (int): the size of the hidden layer
            num_classes (int): the output size
            lstm_dropout (float, optional): dropout ratio in lstm layer. Defaults to 0.1.
            dropout (float, optional): dropout ratio in linear layer. Defaults to 0.5.
        """
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, embedding_size)
        # lstm for input embedding
        self.lstm_a = nn.LSTM(
            hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )
        self.lstm_b = nn.LSTM(
            hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )

首先有一个嵌入层，然后对于输入的两个句子分别有一个Bi-LSTM。

然后定义推理组合层：

        # lstm for augment inference vector
        self.lstm_v_a = nn.LSTM(
            8 * hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )
        self.lstm_v_b = nn.LSTM(
            8 * hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )

完了就是最后的预测层，这里是一个多层前馈网络：

   self.predict = nn.Sequential(
            nn.Linear(8 * hidden_size, 2 * hidden_size),
            nn.ReLU(),
            nn.Dropout(dropout),
            nn.Linear(2 * hidden_size, hidden_size),
            nn.ReLU(),
            nn.Dropout(dropout),
            nn.Linear(hidden_size, num_classes),
        )

初始化函数的完整实现为：

class ESIM(nn.Module):
    def __init__(
        self,
        vocab_size: int,
        embedding_size: int,
        hidden_size: int,
        num_classes: int,
        lstm_dropout: float = 0.1,
        dropout: float = 0.5,
    ) -> None:
        """_summary_

        Args:
            vocab_size (int): the size of the Vocabulary
            embedding_size (int): the size of each embedding vector
            hidden_size (int): the size of the hidden layer
            num_classes (int): the output size
            lstm_dropout (float, optional): dropout ratio in lstm layer. Defaults to 0.1.
            dropout (float, optional): dropout ratio in linear layer. Defaults to 0.5.
        """
        super().__init__()
        self.embedding = nn.Embedding(vocab_size, embedding_size)
        # lstm for input embedding
        self.lstm_a = nn.LSTM(
            hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )
        self.lstm_b = nn.LSTM(
            hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )
        # lstm for augment inference vector
        self.lstm_v_a = nn.LSTM(
            8 * hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )
        self.lstm_v_b = nn.LSTM(
            8 * hidden_size,
            hidden_size,
            batch_first=True,
            bidirectional=True,
            dropout=lstm_dropout,
        )

        self.predict = nn.Sequential(
            nn.Linear(8 * hidden_size, 2 * hidden_size),
            nn.ReLU(),
            nn.Dropout(dropout),
            nn.Linear(2 * hidden_size, hidden_size),
            nn.ReLU(),
            nn.Dropout(dropout),
            nn.Linear(hidden_size, num_classes),
        )

使用ReLU激活函数，在激活函数后都有一个Dropout。

重点是forward方法：

  def forward(self, a: torch.Tensor, b: torch.Tensor) -> torch.Tensor:
        """

        Args:
            a (torch.Tensor): input sequence a with shape (batch_size, a_seq_len)
            b (torch.Tensor): input sequence b with shape (batch_size, b_seq_len)

        Returns:
            torch.Tensor:
        """
        # a (batch_size, a_seq_len, embedding_size)
        a_embed = self.embedding(a)
        # b (batch_size, b_seq_len, embedding_size)
        b_embed = self.embedding(b)

        # a_bar (batch_size, a_seq_len, 2 * hidden_size)
        a_bar, _ = self.lstm_a(a_embed)
        # b_bar (batch_size, b_seq_len, 2 * hidden_size)
        b_bar, _ = self.lstm_b(b_embed)

        # score (batch_size, a_seq_len, b_seq_len)
        score = torch.matmul(a_bar, b_bar.permute(0, 2, 1))

        # softmax (batch_size, a_seq_len, b_seq_len) x (batch_size, b_seq_len, 2 * hidden_size)
        # a_tilde (batch_size, a_seq_len, 2 * hidden_size)
        a_tilde = torch.matmul(torch.softmax(score, dim=2), b_bar)
        # permute (batch_size, b_seq_len, a_seq_len) x (batch_size, a_seq_len, 2 * hidden_size)
        # b_tilde (batch_size, b_seq_len, 2 * hidden_size)
        b_tilde = torch.matmul(torch.softmax(score, dim=1).permute(0, 2, 1), a_bar)

        # m_a (batch_size, a_seq_len, 8 * hidden_size)
        m_a = torch.cat([a_bar, a_tilde, a_bar - a_tilde, a_bar * a_tilde], dim=-1)
        # m_b (batch_size, b_seq_len, 8 * hidden_size)
        m_b = torch.cat([b_bar, b_tilde, b_bar - b_tilde, b_bar * b_tilde], dim=-1)

        # v_a (batch_size, a_seq_len, 2 * hidden_size)
        v_a, _ = self.lstm_v_a(m_a)
        # v_b (batch_size, b_seq_len, 2 * hidden_size)
        v_b, _ = self.lstm_v_b(m_b)

        # (batch_size, 2 * hidden_size)
        avg_a = torch.mean(v_a, dim=1)
        avg_b = torch.mean(v_b, dim=1)

        max_a, _ = torch.max(v_a, dim=1)
        max_b, _ = torch.max(v_b, dim=1)
        # (batch_size, 8 * hidden_size)
        v = torch.cat([avg_a, max_a, avg_b, max_b], dim=-1)

        return self.predict(v)

标注出每个向量的维度就挺好理解的。

首先分别为两个输入得到嵌入向量；

其次喂给各自的LSTM层，得到每个时间步的输出，注意由于是双向LSTM，因此最后的维度是2 * hidden_size；

接着对它两计算注意力分数score (batch_size, a_seq_len, b_seq_len)；

然后分别计算a对b和b对a的注意力，这里要注意softmax中dim的维度。在计算a的注意力输出时，是利用b每个输入的加权和，所以softmax(score, dim=2)在b_seq_len维度上间求和；

然后是增强的局部推理，差、乘各种拼接，得到一个8 * hidden_size的维度，所以lstm_v_a的输入维度是8 * hidden_size；

接下来就是对得到的a和b进行平均池化和最大池化，然后把它们拼接起来，也得到了8 * hidden_size的一个维度；

最后经过我们的预测层，多层前馈网络，进行了一些非线性变换后变成了输出维度大小，比较最后一个维度的值哪个大当成对哪个类的一个预测；

数据准备

和前面几篇几乎一样，这里直接贴代码：

from collections import defaultdict
from tqdm import tqdm
import numpy as np
import json
from torch.utils.data import Dataset
import pandas as pd
from typing import Tuple

UNK_TOKEN = "<UNK>"
PAD_TOKEN = "<PAD>"


class Vocabulary:
    """Class to process text and extract vocabulary for mapping"""

    def __init__(self, token_to_idx: dict = None, tokens: list[str] = None) -> None:
        """
        Args:
            token_to_idx (dict, optional): a pre-existing map of tokens to indices. Defaults to None.
            tokens (list[str], optional): a list of unique tokens with no duplicates. Defaults to None.
        """

        assert any(
            [tokens, token_to_idx]
        ), "At least one of these parameters should be set as not None."
        if token_to_idx:
            self._token_to_idx = token_to_idx
        else:
            self._token_to_idx = {}
            if PAD_TOKEN not in tokens:
                tokens = [PAD_TOKEN] + tokens

            for idx, token in enumerate(tokens):
                self._token_to_idx[token] = idx

        self._idx_to_token = {idx: token for token, idx in self._token_to_idx.items()}

        self.unk_index = self._token_to_idx[UNK_TOKEN]
        self.pad_index = self._token_to_idx[PAD_TOKEN]

    @classmethod
    def build(
        cls,
        sentences: list[list[str]],
        min_freq: int = 2,
        reserved_tokens: list[str] = None,
    ) -> "Vocabulary":
        """Construct the Vocabulary from sentences

        Args:
            sentences (list[list[str]]): a list of tokenized sequences
            min_freq (int, optional): the minimum word frequency to be saved. Defaults to 2.
            reserved_tokens (list[str], optional): the reserved tokens to add into the Vocabulary. Defaults to None.

        Returns:
            Vocabulary: a Vocubulary instane
        """

        token_freqs = defaultdict(int)
        for sentence in tqdm(sentences):
            for token in sentence:
                token_freqs[token] += 1

        unique_tokens = (reserved_tokens if reserved_tokens else []) + [UNK_TOKEN]
        unique_tokens += [
            token
            for token, freq in token_freqs.items()
            if freq >= min_freq and token != UNK_TOKEN
        ]
        return cls(tokens=unique_tokens)

    def __len__(self) -> int:
        return len(self._idx_to_token)

    def __getitem__(self, tokens: list[str] | str) -> list[int] | int:
        """Retrieve the indices associated with the tokens or the index with the single token

        Args:
            tokens (list[str] | str): a list of tokens or single token

        Returns:
            list[int] | int: the indices or the single index
        """
        if not isinstance(tokens, (list, tuple)):
            return self._token_to_idx.get(tokens, self.unk_index)
        return [self.__getitem__(token) for token in tokens]

    def lookup_token(self, indices: list[int] | int) -> list[str] | str:
        """Retrive the tokens associated with the indices or the token with the single index

        Args:
            indices (list[int] | int): a list of index or single index

        Returns:
            list[str] | str: the corresponding tokens (or token)
        """

        if not isinstance(indices, (list, tuple)):
            return self._idx_to_token[indices]

        return [self._idx_to_token[index] for index in indices]

    def to_serializable(self) -> dict:
        """Returns a dictionary that can be serialized"""
        return {"token_to_idx": self._token_to_idx}

    @classmethod
    def from_serializable(cls, contents: dict) -> "Vocabulary":
        """Instantiates the Vocabulary from a serialized dictionary


        Args:
            contents (dict): a dictionary generated by `to_serializable`

        Returns:
            Vocabulary: the Vocabulary instance
        """
        return cls(**contents)

    def __repr__(self):
        return f"<Vocabulary(size={len(self)})>"


class TMVectorizer:
    """The Vectorizer which vectorizes the Vocabulary"""

    def __init__(self, vocab: Vocabulary, max_len: int) -> None:
        """
        Args:
            vocab (Vocabulary): maps characters to integers
            max_len (int): the max length of the sequence in the dataset
        """
        self.vocab = vocab
        self.max_len = max_len

    def _vectorize(
        self, indices: list[int], vector_length: int = -1, padding_index: int = 0
    ) -> np.ndarray:
        """Vectorize the provided indices

        Args:
            indices (list[int]): a list of integers that represent a sequence
            vector_length (int, optional): an arugment for forcing the length of index vector. Defaults to -1.
            padding_index (int, optional): the padding index to use. Defaults to 0.

        Returns:
            np.ndarray: the vectorized index array
        """

        if vector_length <= 0:
            vector_length = len(indices)

        vector = np.zeros(vector_length, dtype=np.int64)
        if len(indices) > vector_length:
            vector[:] = indices[:vector_length]
        else:
            vector[: len(indices)] = indices
            vector[len(indices) :] = padding_index

        return vector

    def _get_indices(self, sentence: list[str]) -> list[int]:
        """Return the vectorized sentence

        Args:
            sentence (list[str]): list of tokens
        Returns:
            indices (list[int]): list of integers representing the sentence
        """
        return [self.vocab[token] for token in sentence]

    def vectorize(
        self, sentence: list[str], use_dataset_max_length: bool = True
    ) -> np.ndarray:
        """
        Return the vectorized sequence

        Args:
            sentence (list[str]): raw sentence from the dataset
            use_dataset_max_length (bool): whether to use the global max vector length
        Returns:
            the vectorized sequence with padding
        """
        vector_length = -1
        if use_dataset_max_length:
            vector_length = self.max_len

        indices = self._get_indices(sentence)
        vector = self._vectorize(
            indices, vector_length=vector_length, padding_index=self.vocab.pad_index
        )

        return vector

    @classmethod
    def from_serializable(cls, contents: dict) -> "TMVectorizer":
        """Instantiates the TMVectorizer from a serialized dictionary

        Args:
            contents (dict): a dictionary generated by `to_serializable`

        Returns:
            TMVectorizer:
        """
        vocab = Vocabulary.from_serializable(contents["vocab"])
        max_len = contents["max_len"]
        return cls(vocab=vocab, max_len=max_len)

    def to_serializable(self) -> dict:
        """Returns a dictionary that can be serialized

        Returns:
            dict: a dict contains Vocabulary instance and max_len attribute
        """
        return {"vocab": self.vocab.to_serializable(), "max_len": self.max_len}

    def save_vectorizer(self, filepath: str) -> None:
        """Dump this TMVectorizer instance to file

        Args:
            filepath (str): the path to store the file
        """
        with open(filepath, "w") as f:
            json.dump(self.to_serializable(), f)

    @classmethod
    def load_vectorizer(cls, filepath: str) -> "TMVectorizer":
        """Load TMVectorizer from a file

        Args:
            filepath (str): the path stored the file

        Returns:
            TMVectorizer:
        """
        with open(filepath) as f:
            return TMVectorizer.from_serializable(json.load(f))


class TMDataset(Dataset):
    """Dataset for text matching"""

    def __init__(self, text_df: pd.DataFrame, vectorizer: TMVectorizer) -> None:
        """

        Args:
            text_df (pd.DataFrame): a DataFrame which contains the processed data examples
            vectorizer (TMVectorizer): a TMVectorizer instance
        """

        self.text_df = text_df
        self._vectorizer = vectorizer

    def __getitem__(self, index: int) -> Tuple[np.ndarray, np.ndarray, int]:
        row = self.text_df.iloc[index]
        return (
            self._vectorizer.vectorize(row.sentence1),
            self._vectorizer.vectorize(row.sentence2),
            row.label,
        )

    def get_vectorizer(self) -> TMVectorizer:
        return self._vectorizer

    def __len__(self) -> int:
        return len(self.text_df)

模型训练

定义辅助函数和指标：

def make_dirs(dirpath):
    if not os.path.exists(dirpath):
        os.makedirs(dirpath)


def tokenize(sentence: str):
    return list(jieba.cut(sentence))


def build_dataframe_from_csv(dataset_csv: str) -> pd.DataFrame:
    df = pd.read_csv(
        dataset_csv,
        sep="\t",
        header=None,
        names=["sentence1", "sentence2", "label"],
    )

    df.sentence1 = df.sentence1.apply(tokenize)
    df.sentence2 = df.sentence2.apply(tokenize)

    return df


def metrics(y: torch.Tensor, y_pred: torch.Tensor) -> Tuple[float, float, float, float]:
    TP = ((y_pred == 1) & (y == 1)).sum().float()  # True Positive
    TN = ((y_pred == 0) & (y == 0)).sum().float()  # True Negative
    FN = ((y_pred == 0) & (y == 1)).sum().float()  # False Negatvie
    FP = ((y_pred == 1) & (y == 0)).sum().float()  # False Positive
    p = TP / (TP + FP).clamp(min=1e-8)  # Precision
    r = TP / (TP + FN).clamp(min=1e-8)  # Recall
    F1 = 2 * r * p / (r + p).clamp(min=1e-8)  # F1 score
    acc = (TP + TN) / (TP + TN + FP + FN).clamp(min=1e-8)  # Accurary
    return acc, p, r, F1

定义评估函数和训练函数：

def evaluate(
    data_iter: DataLoader, model: nn.Module
) -> Tuple[float, float, float, float]:
    y_list, y_pred_list = [], []
    model.eval()
    for x1, x2, y in tqdm(data_iter):
        x1 = x1.to(device).long()
        x2 = x2.to(device).long()
        y = torch.LongTensor(y).to(device)

        output = model(x1, x2)

        pred = torch.argmax(output, dim=1).long()

        y_pred_list.append(pred)
        y_list.append(y)

    y_pred = torch.cat(y_pred_list, 0)
    y = torch.cat(y_list, 0)
    acc, p, r, f1 = metrics(y, y_pred)
    return acc, p, r, f1


def train(
    data_iter: DataLoader,
    model: nn.Module,
    criterion: nn.CrossEntropyLoss,
    optimizer: torch.optim.Optimizer,
    print_every: int = 500,
    verbose=True,
) -> None:
    model.train()

    for step, (x1, x2, y) in enumerate(tqdm(data_iter)):
        x1 = x1.to(device).long()
        x2 = x2.to(device).long()
        y = torch.LongTensor(y).to(device)

        output = model(x1, x2)

        loss = criterion(output, y)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if verbose and (step + 1) % print_every == 0:
            pred = torch.argmax(output, dim=1).long()
            acc, p, r, f1 = metrics(y, pred)

            print(
                f" TRAIN iter={step+1} loss={loss.item():.6f} accuracy={acc:.3f} precision={p:.3f} recal={r:.3f} f1 score={f1:.4f}"
            )

参数定义：

 args = Namespace(
        dataset_csv="text_matching/data/lcqmc/{}.txt",
        vectorizer_file="vectorizer.json",
        model_state_file="model.pth",
        save_dir=f"{os.path.dirname(__file__)}/model_storage",
        reload_model=False,
        cuda=True,
        learning_rate=4e-4,
        batch_size=128,
        num_epochs=10,
        max_len=50,
        embedding_dim=300,
        hidden_size=300,
        num_classes=2,
        lstm_dropout=0.8,
        dropout=0.5,
        min_freq=2,
        print_every=500,
        verbose=True,
    )

这个模型非常简单，但效果是非常不错的，可以作为一个很好的baseline。在训练过程中发现对训练集的准确率达到了100%，有点过拟合了，因此最后把lstm的dropout加大到0.8，最后看一下训练效果如何：

  make_dirs(args.save_dir)

    if args.cuda:
        device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    else:
        device = torch.device("cpu")

    print(f"Using device: {device}.")

    vectorizer_path = os.path.join(args.save_dir, args.vectorizer_file)

    train_df = build_dataframe_from_csv(args.dataset_csv.format("train"))
    test_df = build_dataframe_from_csv(args.dataset_csv.format("test"))
    dev_df = build_dataframe_from_csv(args.dataset_csv.format("dev"))

    if os.path.exists(vectorizer_path):
        print("Loading vectorizer file.")
        vectorizer = TMVectorizer.load_vectorizer(vectorizer_path)
        args.vocab_size = len(vectorizer.vocab)
    else:
        print("Creating a new Vectorizer.")

        train_sentences = train_df.sentence1.to_list() + train_df.sentence2.to_list()

        vocab = Vocabulary.build(train_sentences, args.min_freq)

        args.vocab_size = len(vocab)

        print(f"Builds vocabulary : {vocab}")

        vectorizer = TMVectorizer(vocab, args.max_len)

        vectorizer.save_vectorizer(vectorizer_path)

    train_dataset = TMDataset(train_df, vectorizer)
    test_dataset = TMDataset(test_df, vectorizer)
    dev_dataset = TMDataset(dev_df, vectorizer)

    train_data_loader = DataLoader(
        train_dataset, batch_size=args.batch_size, shuffle=True
    )
    dev_data_loader = DataLoader(dev_dataset, batch_size=args.batch_size)
    test_data_loader = DataLoader(test_dataset, batch_size=args.batch_size)

    print(f"Arguments : {args}")
    model = ESIM(
        args.vocab_size,
        args.embedding_dim,
        args.hidden_size,
        args.num_classes,
        args.lstm_dropout,
        args.dropout,
    )

    print(f"Model: {model}")

    model_saved_path = os.path.join(args.save_dir, args.model_state_file)
    if args.reload_model and os.path.exists(model_saved_path):
        model.load_state_dict(torch.load(args.model_saved_path))
        print("Reloaded model")
    else:
        print("New model")

    model = model.to(device)

    optimizer = torch.optim.Adam(model.parameters(), lr=args.learning_rate)
    criterion = nn.CrossEntropyLoss()

    for epoch in range(args.num_epochs):
        train(
            train_data_loader,
            model,
            criterion,
            optimizer,
            print_every=args.print_every,
            verbose=args.verbose,
        )
        print("Begin evalute on dev set.")
        with torch.no_grad():
            acc, p, r, f1 = evaluate(dev_data_loader, model)

            print(
                f"EVALUATE [{epoch+1}/{args.num_epochs}]  accuracy={acc:.3f} precision={p:.3f} recal={r:.3f} f1 score={f1:.4f}"
            )

    model.eval()

    acc, p, r, f1 = evaluate(test_data_loader, model)
    print(f"TEST accuracy={acc:.3f} precision={p:.3f} recal={r:.3f} f1 score={f1:.4f}")

python .\text_matching\esim\train.py
Using device: cuda:0.
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
Loading model cost 0.563 seconds.
Prefix dict has been built successfully.
Loading vectorizer file.
Arguments : Namespace(dataset_csv='text_matching/data/lcqmc/{}.txt', vectorizer_file='vectorizer.json', model_state_file='model.pth', save_dir='D:\\workspace\\nlp-in-action\\text_matching\\esim/model_storage', reload_model=False, cuda=True, learning_rate=0.0004, batch_size=128, num_epochs=10, max_len=50, embedding_dim=300, hidden_size=300, num_classes=2, lstm_dropout=0.8, dropout=0.5, min_freq=2, print_every=500, verbose=True, vocab_size=35925)      
D:\workspace\nlp-in-action\.venv\lib\site-packages\torch\nn\modules\rnn.py:67: UserWarning: dropout option adds dropout after all but last recurrent layer, so non-zero dropout expects num_layers greater than 1, but got dropout=0.8 and num_layers=1
  warnings.warn("dropout option adds dropout after all but last "
Model: ESIM(
  (embedding): Embedding(35925, 300)
  (lstm_a): LSTM(300, 300, batch_first=True, dropout=0.8, bidirectional=True)
  (lstm_b): LSTM(300, 300, batch_first=True, dropout=0.8, bidirectional=True)
  (lstm_v_a): LSTM(2400, 300, batch_first=True, dropout=0.8, bidirectional=True)
  (lstm_v_b): LSTM(2400, 300, batch_first=True, dropout=0.8, bidirectional=True)
  (predict): Sequential(
    (0): Linear(in_features=2400, out_features=600, bias=True)
    (1): ReLU()
    (2): Dropout(p=0.5, inplace=False)
    (3): Linear(in_features=600, out_features=300, bias=True)
    (4): ReLU()
    (5): Dropout(p=0.5, inplace=False)
    (6): Linear(in_features=300, out_features=2, bias=True)
  )
)
New model
 27%|█████████████████████████████████████████████████▋                                                                                                                                        | 499/1866 [01:33<04:13,  5.40it/s] 
TRAIN iter=500 loss=0.500601 accuracy=0.750 precision=0.714 recal=0.846 f1 score=0.7746
 54%|███████████████████████████████████████████████████████████████████████████████████████████████████▌                                                                                      | 999/1866 [03:04<02:40,  5.41it/s] 
TRAIN iter=1000 loss=0.250350 accuracy=0.883 precision=0.907 recal=0.895 f1 score=0.9007
 80%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌                                    | 1499/1866 [04:35<01:07,  5.43it/s] 
TRAIN iter=1500 loss=0.311494 accuracy=0.844 precision=0.868 recal=0.868 f1 score=0.8684
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1866/1866 [05:42<00:00,  5.45it/s] 
Begin evalute on dev set.
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 69/69 [00:04<00:00, 17.10it/s] 
EVALUATE [1/10]  accuracy=0.771 precision=0.788 recal=0.741 f1 score=0.7637
...
TRAIN iter=500 loss=0.005086 accuracy=1.000 precision=1.000 recal=1.000 f1 score=1.0000
...
EVALUATE [10/10]  accuracy=0.815 precision=0.807 recal=0.829 f1 score=0.8178
100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 98/98 [00:05<00:00, 17.38it/s] 
TEST accuracy=0.817 precision=0.771 recal=0.903 f1 score=0.8318

可以看到，训练集上的损失第一次降到了0.005级别，准确率甚至达到了100%，但最终在测试集上的准确率相比训练集还是逊色了一些，只有81.7%，不过相比前面几个模型已经很不错了。