assignmentutor™您的专属作业导师

assignmentutor-lab™ 为您的留学生涯保驾护航 在代写自然语言处理NLP方面已经树立了自己的口碑, 保证靠谱, 高质且原创的统计Statistics代写服务。我们的专家在代写自然语言处理NLP代写方面经验极为丰富，各种代写自然语言处理NLP相关的作业也就用不着说。

• Statistical Inference 统计推断
• Statistical Computing 统计计算
• (Generalized) Linear Models 广义线性模型
• Statistical Machine Learning 统计机器学习
• Longitudinal Data Analysis 纵向数据分析
• Foundations of Data Science 数据科学基础

## 机器学习代写|自然语言处理代写NLP代考|Fine-Tuning BERT Models

In Chapter 1, Getting Started with the Model Architecture of the Transformer, we defined the building blocks of the architecture of the original Transformer. Think of the contains bricks such as encoders, decoders, embedding layers, positional encoding methods, multi-head attention layers, masked multi-head attention layers, post-layer normalization, feed-forward sub-layers, and linear output layers. The bricks come in various sizes and forms. You can spend hours building all sorts of models using the same building kit! Some constructions will only require some of the bricks. Other constructions will add a new piece, just like when we obtain additional bricks for a model built using $\mathrm{LEGO}^{\infty}$ components.
BERT added a new piece to the Transformer building kit: a bidirectional multihead attention sub-layer. When we humans are having problems understanding a sentence, we do not just look at the past words. BERT, like us, looks at all the words in the same sentence at the same time.

In this chapter, we will first explore the architecture of Bidirectional Encoder Representations from Transformers (BERT). BERT only uses the blocks of the encoders of the Transformer in a novel way and does not use the decoder stack.
Then we will fine-tune a pretrained BERT model. The BERT model we will fine-tune was trained by a third party and uploaded to Hugging Face. Transformers can be pretrained. Then, a pretrained BERT, for example, can be fine-tuned on several NLP tasks. We will go through this fascinating experience of downstream Transformer usage using Hugging Face modules.
This chapter covers the following topics:

• Bidirectional Encoder Representations from Transformers (BERT)
• The architecture of BERT
• The two-step BERT framework
• Preparing the pretraining environment
• Defining pretraining encoder layers
• Defining fine-tuning
• Building a fine-tuning BERT model
• BERT model configuration
• Measuring the performance of the fine-tuned model
Our first step will be to explore the background of the Transformer.

## 机器学习代写|自然语言处理代写NLP代考|The encoder stack

The first building block we will take from the original Transformer model is an encoder layer. The encoder layer as described in Chapter 1, Getting Started with the Model Architecture of the Transformer, is shown in Figure 2.1:

The BERT model does not use decoder layers. A BERT model has an encoder stack but no decoder stacks. The masked tokens (hiding the tokens to predict) are in the attention layers of the encoder, as we will see when we zoom into a BERT encoder layer in the following sections.

The original Transformer contains a stack of $N=6$ layers. The number of dimensions of the original Transformer is $d_{\text {mudd }}=512$. The number of attention heads of the original Transformer is $A=8$. The dimensions of a head of the original Transformer is:
$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{512}{8}=64$$
BERT encoder layers are larger than the original Transformer model.
Two BERT models can be built with the encoder layers: also be expressed as $H=768$, as in the BERT paper. A multi-head attention sub-layer contains $A=12$ heads. The dimensions of each head $z_{A}$ remains 64 as in the original Transformer model:
$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{768}{12}=64$$

The output of each multi-head attention sub-layer before concatenation will be the output of the 12 heads:
output_multi-head_attention $=\left{z_{0}, z_{1}, z_{2}, \ldots, z_{11}\right}$ multi-head attention sub-layer contains $A=16$ heads. The dimensions of each head $z_{A}$ also remains 64 as in the original Transformer model:
$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{1024}{16}=64$$
The output of each multi-head attention sub-layer before concatenation will be the output of the 16 heads:
$$\text { output_multi-head_attention }=\left{z_{0}, z_{1}, z_{2}, \ldots, z_{15}\right}$$

## 机器学习代写|自然语言处理代写NLP代考|Fine-Tuning BERT Models

BERT 在 Transformer 构建工具包中添加了一个新部分：双向多头注意力子层。当我们人类在理解句子时遇到问题时，我们不会只看过去的单词。BERT 和我们一样，会同时查看同一个句子中的所有单词。

• 来自 Transformers (BERT) 的双向编码器表示
• BERT的架构
• 两步 BERT 框架
• 准备预训练环境
• 定义预训练编码器层
• 定义微调
• 下游多任务处理
• 构建微调的 BERT 模型
• 加载可访问性判断数据集
• 创建注意力面具
• BERT模型配置
• 测量微调模型的性能
我们的第一步将是探索 Transformer 的背景。

## 机器学习代写|自然语言处理代写NLP代考|The encoder stack

BERT 模型不使用解码器层。BERT 模型有一个编码器堆栈，但没有解码器堆栈。掩码标记（隐藏要预测的标记) 位于编码器的注意力层 中，正如我们将在以下部分中放大 BERT 编码器层时看到的那样。

$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{512}{8}=64$$
BERT 编码器层大于原始的 Transformer 模型。

$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{768}{12}=64$$

Transformer 模型一样，也保持 64：
$$d_{k}=\frac{d_{\text {model }}}{A}=\frac{1024}{16}=64$$

$\backslash$ left 的分隔符缺失或无法识别

## 有限元方法代写

assignmentutor™作为专业的留学生服务机构，多年来已为美国、英国、加拿大、澳洲等留学热门地的学生提供专业的学术服务，包括但不限于Essay代写，Assignment代写，Dissertation代写，Report代写，小组作业代写，Proposal代写，Paper代写，Presentation代写，计算机作业代写，论文修改和润色，网课代做，exam代考等等。写作范围涵盖高中，本科，研究生等海外留学全阶段，辐射金融，经济学，会计学，审计学，管理学等全球99%专业科目。写作团队既有专业英语母语作者，也有海外名校硕博留学生，每位写作老师都拥有过硬的语言能力，专业的学科背景和学术写作经验。我们承诺100%原创，100%专业，100%准时，100%满意。

## MATLAB代写

MATLAB 是一种用于技术计算的高性能语言。它将计算、可视化和编程集成在一个易于使用的环境中，其中问题和解决方案以熟悉的数学符号表示。典型用途包括：数学和计算算法开发建模、仿真和原型制作数据分析、探索和可视化科学和工程图形应用程序开发，包括图形用户界面构建MATLAB 是一个交互式系统，其基本数据元素是一个不需要维度的数组。这使您可以解决许多技术计算问题，尤其是那些具有矩阵和向量公式的问题，而只需用 C 或 Fortran 等标量非交互式语言编写程序所需的时间的一小部分。MATLAB 名称代表矩阵实验室。MATLAB 最初的编写目的是提供对由 LINPACK 和 EISPACK 项目开发的矩阵软件的轻松访问，这两个项目共同代表了矩阵计算软件的最新技术。MATLAB 经过多年的发展，得到了许多用户的投入。在大学环境中，它是数学、工程和科学入门和高级课程的标准教学工具。在工业领域，MATLAB 是高效研究、开发和分析的首选工具。MATLAB 具有一系列称为工具箱的特定于应用程序的解决方案。对于大多数 MATLAB 用户来说非常重要，工具箱允许您学习应用专业技术。工具箱是 MATLAB 函数（M 文件）的综合集合，可扩展 MATLAB 环境以解决特定类别的问题。可用工具箱的领域包括信号处理、控制系统、神经网络、模糊逻辑、小波、仿真等。

assignmentutor™您的专属作业导师
assignmentutor™您的专属作业导师