6. 预训练与加载模型

Reading time: 29 minutes

文本生成

为了训练一个模型，我们需要该模型能够生成新的标记。然后，我们将生成的标记与预期的标记进行比较，以便训练模型学习它需要生成的标记。

如前面的例子中，我们已经预测了一些标记，可以重用该功能来实现这个目的。

文本评估

为了进行正确的训练，需要测量检查获得的预测与预期标记的匹配情况。训练的目标是最大化正确标记的可能性，这涉及到相对于其他标记增加其概率。

为了最大化正确标记的概率，必须修改模型的权重，以使该概率最大化。权重的更新是通过反向传播完成的。这需要一个要最大化的损失函数。在这种情况下，函数将是执行的预测与期望预测之间的差异。

然而，它将使用以n为底的对数，而不是处理原始预测。因此，如果当前对预期标记的预测是7.4541e-05，则7.4541e-05的自然对数（以e为底）大约是**-9.5042**。
然后，对于每个具有5个标记上下文长度的条目，例如，模型需要预测5个标记，前4个标记是输入的最后一个，第五个是预测的标记。因此，在这种情况下，对于每个条目，我们将有5个预测（即使前4个在输入中，模型并不知道这一点），因此有5个预期标记，因此有5个概率需要最大化。

因此，在对每个预测执行自然对数后，计算平均值，去掉负号（这称为_交叉熵损失_），这是需要尽可能接近0的数字，因为1的自然对数是0：

衡量模型好坏的另一种方法称为困惑度。困惑度是用于评估概率模型预测样本的好坏的指标。在语言建模中，它表示模型在预测序列中的下一个标记时的不确定性。
例如，困惑度值为48725，意味着在需要预测一个标记时，它对词汇表中48,725个标记中的哪个是正确的感到不确定。

预训练示例

这是在https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/01_main-chapter-code/ch05.ipynb中提出的初始代码，有时会稍作修改。

"""
This is code explained before so it won't be exaplained
"""

import tiktoken
import torch
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader


class GPTDatasetV1(Dataset):
def __init__(self, txt, tokenizer, max_length, stride):
self.input_ids = []
self.target_ids = []

# Tokenize the entire text
token_ids = tokenizer.encode(txt, allowed_special={"<|endoftext|>"})

# Use a sliding window to chunk the book into overlapping sequences of max_length
for i in range(0, len(token_ids) - max_length, stride):
input_chunk = token_ids[i:i + max_length]
target_chunk = token_ids[i + 1: i + max_length + 1]
self.input_ids.append(torch.tensor(input_chunk))
self.target_ids.append(torch.tensor(target_chunk))

def __len__(self):
return len(self.input_ids)

def __getitem__(self, idx):
return self.input_ids[idx], self.target_ids[idx]


def create_dataloader_v1(txt, batch_size=4, max_length=256,
stride=128, shuffle=True, drop_last=True, num_workers=0):
# Initialize the tokenizer
tokenizer = tiktoken.get_encoding("gpt2")

# Create dataset
dataset = GPTDatasetV1(txt, tokenizer, max_length, stride)

# Create dataloader
dataloader = DataLoader(
dataset, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, num_workers=num_workers)

return dataloader


class MultiHeadAttention(nn.Module):
def __init__(self, d_in, d_out, context_length, dropout, num_heads, qkv_bias=False):
super().__init__()
assert d_out % num_heads == 0, "d_out must be divisible by n_heads"

self.d_out = d_out
self.num_heads = num_heads
self.head_dim = d_out // num_heads  # Reduce the projection dim to match desired output dim

self.W_query = nn.Linear(d_in, d_out, bias=qkv_bias)
self.W_key = nn.Linear(d_in, d_out, bias=qkv_bias)
self.W_value = nn.Linear(d_in, d_out, bias=qkv_bias)
self.out_proj = nn.Linear(d_out, d_out)  # Linear layer to combine head outputs
self.dropout = nn.Dropout(dropout)
self.register_buffer('mask', torch.triu(torch.ones(context_length, context_length), diagonal=1))

def forward(self, x):
b, num_tokens, d_in = x.shape

keys = self.W_key(x)  # Shape: (b, num_tokens, d_out)
queries = self.W_query(x)
values = self.W_value(x)

# We implicitly split the matrix by adding a `num_heads` dimension
# Unroll last dim: (b, num_tokens, d_out) -> (b, num_tokens, num_heads, head_dim)
keys = keys.view(b, num_tokens, self.num_heads, self.head_dim)
values = values.view(b, num_tokens, self.num_heads, self.head_dim)
queries = queries.view(b, num_tokens, self.num_heads, self.head_dim)

# Transpose: (b, num_tokens, num_heads, head_dim) -> (b, num_heads, num_tokens, head_dim)
keys = keys.transpose(1, 2)
queries = queries.transpose(1, 2)
values = values.transpose(1, 2)

# Compute scaled dot-product attention (aka self-attention) with a causal mask
attn_scores = queries @ keys.transpose(2, 3)  # Dot product for each head

# Original mask truncated to the number of tokens and converted to boolean
mask_bool = self.mask.bool()[:num_tokens, :num_tokens]

# Use the mask to fill attention scores
attn_scores.masked_fill_(mask_bool, -torch.inf)

attn_weights = torch.softmax(attn_scores / keys.shape[-1]**0.5, dim=-1)
attn_weights = self.dropout(attn_weights)

# Shape: (b, num_tokens, num_heads, head_dim)
context_vec = (attn_weights @ values).transpose(1, 2)

# Combine heads, where self.d_out = self.num_heads * self.head_dim
context_vec = context_vec.reshape(b, num_tokens, self.d_out)
context_vec = self.out_proj(context_vec)  # optional projection

return context_vec


class LayerNorm(nn.Module):
def __init__(self, emb_dim):
super().__init__()
self.eps = 1e-5
self.scale = nn.Parameter(torch.ones(emb_dim))
self.shift = nn.Parameter(torch.zeros(emb_dim))

def forward(self, x):
mean = x.mean(dim=-1, keepdim=True)
var = x.var(dim=-1, keepdim=True, unbiased=False)
norm_x = (x - mean) / torch.sqrt(var + self.eps)
return self.scale * norm_x + self.shift


class GELU(nn.Module):
def __init__(self):
super().__init__()

def forward(self, x):
return 0.5 * x * (1 + torch.tanh(
torch.sqrt(torch.tensor(2.0 / torch.pi)) *
(x + 0.044715 * torch.pow(x, 3))
))


class FeedForward(nn.Module):
def __init__(self, cfg):
super().__init__()
self.layers = nn.Sequential(
nn.Linear(cfg["emb_dim"], 4 * cfg["emb_dim"]),
GELU(),
nn.Linear(4 * cfg["emb_dim"], cfg["emb_dim"]),
)

def forward(self, x):
return self.layers(x)


class TransformerBlock(nn.Module):
def __init__(self, cfg):
super().__init__()
self.att = MultiHeadAttention(
d_in=cfg["emb_dim"],
d_out=cfg["emb_dim"],
context_length=cfg["context_length"],
num_heads=cfg["n_heads"],
dropout=cfg["drop_rate"],
qkv_bias=cfg["qkv_bias"])
self.ff = FeedForward(cfg)
self.norm1 = LayerNorm(cfg["emb_dim"])
self.norm2 = LayerNorm(cfg["emb_dim"])
self.drop_shortcut = nn.Dropout(cfg["drop_rate"])

def forward(self, x):
# Shortcut connection for attention block
shortcut = x
x = self.norm1(x)
x = self.att(x)   # Shape [batch_size, num_tokens, emb_size]
x = self.drop_shortcut(x)
x = x + shortcut  # Add the original input back

# Shortcut connection for feed-forward block
shortcut = x
x = self.norm2(x)
x = self.ff(x)
x = self.drop_shortcut(x)
x = x + shortcut  # Add the original input back

return x


class GPTModel(nn.Module):
def __init__(self, cfg):
super().__init__()
self.tok_emb = nn.Embedding(cfg["vocab_size"], cfg["emb_dim"])
self.pos_emb = nn.Embedding(cfg["context_length"], cfg["emb_dim"])
self.drop_emb = nn.Dropout(cfg["drop_rate"])

self.trf_blocks = nn.Sequential(
*[TransformerBlock(cfg) for _ in range(cfg["n_layers"])])

self.final_norm = LayerNorm(cfg["emb_dim"])
self.out_head = nn.Linear(cfg["emb_dim"], cfg["vocab_size"], bias=False)

def forward(self, in_idx):
batch_size, seq_len = in_idx.shape
tok_embeds = self.tok_emb(in_idx)
pos_embeds = self.pos_emb(torch.arange(seq_len, device=in_idx.device))
x = tok_embeds + pos_embeds  # Shape [batch_size, num_tokens, emb_size]
x = self.drop_emb(x)
x = self.trf_blocks(x)
x = self.final_norm(x)
logits = self.out_head(x)
return logits

# Download contents to train the data with
import os
import urllib.request

file_path = "the-verdict.txt"
url = "https://raw.githubusercontent.com/rasbt/LLMs-from-scratch/main/ch02/01_main-chapter-code/the-verdict.txt"

if not os.path.exists(file_path):
with urllib.request.urlopen(url) as response:
text_data = response.read().decode('utf-8')
with open(file_path, "w", encoding="utf-8") as file:
file.write(text_data)
else:
with open(file_path, "r", encoding="utf-8") as file:
text_data = file.read()

total_characters = len(text_data)
tokenizer = tiktoken.get_encoding("gpt2")
total_tokens = len(tokenizer.encode(text_data))

print("Data downloaded")
print("Characters:", total_characters)
print("Tokens:", total_tokens)

# Model initialization
GPT_CONFIG_124M = {
"vocab_size": 50257,   # Vocabulary size
"context_length": 256, # Shortened context length (orig: 1024)
"emb_dim": 768,        # Embedding dimension
"n_heads": 12,         # Number of attention heads
"n_layers": 12,        # Number of layers
"drop_rate": 0.1,      # Dropout rate
"qkv_bias": False      # Query-key-value bias
}

torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.eval()
print ("Model initialized")


# Functions to transform from tokens to ids and from to ids to tokens
def text_to_token_ids(text, tokenizer):
encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})
encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension
return encoded_tensor

def token_ids_to_text(token_ids, tokenizer):
flat = token_ids.squeeze(0) # remove batch dimension
return tokenizer.decode(flat.tolist())



# Define loss functions
def calc_loss_batch(input_batch, target_batch, model, device):
input_batch, target_batch = input_batch.to(device), target_batch.to(device)
logits = model(input_batch)
loss = torch.nn.functional.cross_entropy(logits.flatten(0, 1), target_batch.flatten())
return loss


def calc_loss_loader(data_loader, model, device, num_batches=None):
total_loss = 0.
if len(data_loader) == 0:
return float("nan")
elif num_batches is None:
num_batches = len(data_loader)
else:
# Reduce the number of batches to match the total number of batches in the data loader
# if num_batches exceeds the number of batches in the data loader
num_batches = min(num_batches, len(data_loader))
for i, (input_batch, target_batch) in enumerate(data_loader):
if i < num_batches:
loss = calc_loss_batch(input_batch, target_batch, model, device)
total_loss += loss.item()
else:
break
return total_loss / num_batches


# Apply Train/validation ratio and create dataloaders
train_ratio = 0.90
split_idx = int(train_ratio * len(text_data))
train_data = text_data[:split_idx]
val_data = text_data[split_idx:]

torch.manual_seed(123)

train_loader = create_dataloader_v1(
train_data,
batch_size=2,
max_length=GPT_CONFIG_124M["context_length"],
stride=GPT_CONFIG_124M["context_length"],
drop_last=True,
shuffle=True,
num_workers=0
)

val_loader = create_dataloader_v1(
val_data,
batch_size=2,
max_length=GPT_CONFIG_124M["context_length"],
stride=GPT_CONFIG_124M["context_length"],
drop_last=False,
shuffle=False,
num_workers=0
)


# Sanity checks
if total_tokens * (train_ratio) < GPT_CONFIG_124M["context_length"]:
print("Not enough tokens for the training loader. "
"Try to lower the `GPT_CONFIG_124M['context_length']` or "
"increase the `training_ratio`")

if total_tokens * (1-train_ratio) < GPT_CONFIG_124M["context_length"]:
print("Not enough tokens for the validation loader. "
"Try to lower the `GPT_CONFIG_124M['context_length']` or "
"decrease the `training_ratio`")

print("Train loader:")
for x, y in train_loader:
print(x.shape, y.shape)

print("\nValidation loader:")
for x, y in val_loader:
print(x.shape, y.shape)

train_tokens = 0
for input_batch, target_batch in train_loader:
train_tokens += input_batch.numel()

val_tokens = 0
for input_batch, target_batch in val_loader:
val_tokens += input_batch.numel()

print("Training tokens:", train_tokens)
print("Validation tokens:", val_tokens)
print("All tokens:", train_tokens + val_tokens)


# Indicate the device to use
if torch.cuda.is_available():
device = torch.device("cuda")
elif torch.backends.mps.is_available():
device = torch.device("mps")
else:
device = torch.device("cpu")

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

model.to(device) # no assignment model = model.to(device) necessary for nn.Module classes



# Pre-calculate losses without starting yet
torch.manual_seed(123) # For reproducibility due to the shuffling in the data loader

with torch.no_grad(): # Disable gradient tracking for efficiency because we are not training, yet
train_loss = calc_loss_loader(train_loader, model, device)
val_loss = calc_loss_loader(val_loader, model, device)

print("Training loss:", train_loss)
print("Validation loss:", val_loss)


# Functions to train the data
def train_model_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
eval_freq, eval_iter, start_context, tokenizer):
# Initialize lists to track losses and tokens seen
train_losses, val_losses, track_tokens_seen = [], [], []
tokens_seen, global_step = 0, -1

# Main training loop
for epoch in range(num_epochs):
model.train()  # Set model to training mode

for input_batch, target_batch in train_loader:
optimizer.zero_grad() # Reset loss gradients from previous batch iteration
loss = calc_loss_batch(input_batch, target_batch, model, device)
loss.backward() # Calculate loss gradients
optimizer.step() # Update model weights using loss gradients
tokens_seen += input_batch.numel()
global_step += 1

# Optional evaluation step
if global_step % eval_freq == 0:
train_loss, val_loss = evaluate_model(
model, train_loader, val_loader, device, eval_iter)
train_losses.append(train_loss)
val_losses.append(val_loss)
track_tokens_seen.append(tokens_seen)
print(f"Ep {epoch+1} (Step {global_step:06d}): "
f"Train loss {train_loss:.3f}, Val loss {val_loss:.3f}")

# Print a sample text after each epoch
generate_and_print_sample(
model, tokenizer, device, start_context
)

return train_losses, val_losses, track_tokens_seen


def evaluate_model(model, train_loader, val_loader, device, eval_iter):
model.eval()
with torch.no_grad():
train_loss = calc_loss_loader(train_loader, model, device, num_batches=eval_iter)
val_loss = calc_loss_loader(val_loader, model, device, num_batches=eval_iter)
model.train()
return train_loss, val_loss


def generate_and_print_sample(model, tokenizer, device, start_context):
model.eval()
context_size = model.pos_emb.weight.shape[0]
encoded = text_to_token_ids(start_context, tokenizer).to(device)
with torch.no_grad():
token_ids = generate_text(
model=model, idx=encoded,
max_new_tokens=50, context_size=context_size
)
decoded_text = token_ids_to_text(token_ids, tokenizer)
print(decoded_text.replace("\n", " "))  # Compact print format
model.train()


# Start training!
import time
start_time = time.time()

torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=0.0004, weight_decay=0.1)

num_epochs = 10
train_losses, val_losses, tokens_seen = train_model_simple(
model, train_loader, val_loader, optimizer, device,
num_epochs=num_epochs, eval_freq=5, eval_iter=5,
start_context="Every effort moves you", tokenizer=tokenizer
)

end_time = time.time()
execution_time_minutes = (end_time - start_time) / 60
print(f"Training completed in {execution_time_minutes:.2f} minutes.")



# Show graphics with the training process
import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
import math
def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
fig, ax1 = plt.subplots(figsize=(5, 3))
ax1.plot(epochs_seen, train_losses, label="Training loss")
ax1.plot(
epochs_seen, val_losses, linestyle="-.", label="Validation loss"
)
ax1.set_xlabel("Epochs")
ax1.set_ylabel("Loss")
ax1.legend(loc="upper right")
ax1.xaxis.set_major_locator(MaxNLocator(integer=True))
ax2 = ax1.twiny()
ax2.plot(tokens_seen, train_losses, alpha=0)
ax2.set_xlabel("Tokens seen")
fig.tight_layout()
plt.show()

# Compute perplexity from the loss values
train_ppls = [math.exp(loss) for loss in train_losses]
val_ppls = [math.exp(loss) for loss in val_losses]
# Plot perplexity over tokens seen
plt.figure()
plt.plot(tokens_seen, train_ppls, label='Training Perplexity')
plt.plot(tokens_seen, val_ppls, label='Validation Perplexity')
plt.xlabel('Tokens Seen')
plt.ylabel('Perplexity')
plt.title('Perplexity over Training')
plt.legend()
plt.show()

epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
plot_losses(epochs_tensor, tokens_seen, train_losses, val_losses)


torch.save({
"model_state_dict": model.state_dict(),
"optimizer_state_dict": optimizer.state_dict(),
},
"/tmp/model_and_optimizer.pth"
)

让我们逐步解释

文本 <--> ids 转换的函数

这些是一些简单的函数，可以用于将词汇中的文本转换为 ids 及其反向转换。这在文本处理的开始和预测的结束时是必要的：

# Functions to transform from tokens to ids and from to ids to tokens
def text_to_token_ids(text, tokenizer):
encoded = tokenizer.encode(text, allowed_special={'<|endoftext|>'})
encoded_tensor = torch.tensor(encoded).unsqueeze(0) # add batch dimension
return encoded_tensor

def token_ids_to_text(token_ids, tokenizer):
flat = token_ids.squeeze(0) # remove batch dimension
return tokenizer.decode(flat.tolist())

生成文本函数

在前面的部分中，一个函数仅在获取 logits 后获取 最可能的标记。然而，这意味着对于每个输入，总是会生成相同的输出，这使得它非常确定性。

以下的 generate_text 函数将应用 top-k、temperature 和 multinomial 概念。

• top-k 意味着我们将开始将所有标记的概率减少到 -inf，除了前 k 个标记。因此，如果 k=3，在做出决策之前，只有 3 个最可能的标记的概率将与 -inf 不同。
• temperature 意味着每个概率将被温度值除以。值为 0.1 将提高最高概率与最低概率的比较，而温度为 5 的情况下，例如将使其更加平坦。这有助于提高我们希望 LLM 具有的响应变化。
• 在应用温度后，再次应用 softmax 函数，使所有剩余标记的总概率为 1。
• 最后，函数不再选择概率最大的标记，而是应用 multinomial 来 根据最终概率预测下一个标记。因此，如果标记 1 的概率为 70%，标记 2 的概率为 20%，标记 3 的概率为 10%，那么 70% 的时间将选择标记 1，20% 的时间将选择标记 2，10% 的时间将选择标记 3。

# Generate text function
def generate_text(model, idx, max_new_tokens, context_size, temperature=0.0, top_k=None, eos_id=None):

# For-loop is the same as before: Get logits, and only focus on last time step
for _ in range(max_new_tokens):
idx_cond = idx[:, -context_size:]
with torch.no_grad():
logits = model(idx_cond)
logits = logits[:, -1, :]

# New: Filter logits with top_k sampling
if top_k is not None:
# Keep only top_k values
top_logits, _ = torch.topk(logits, top_k)
min_val = top_logits[:, -1]
logits = torch.where(logits < min_val, torch.tensor(float("-inf")).to(logits.device), logits)

# New: Apply temperature scaling
if temperature > 0.0:
logits = logits / temperature

# Apply softmax to get probabilities
probs = torch.softmax(logits, dim=-1)  # (batch_size, context_len)

# Sample from the distribution
idx_next = torch.multinomial(probs, num_samples=1)  # (batch_size, 1)

# Otherwise same as before: get idx of the vocab entry with the highest logits value
else:
idx_next = torch.argmax(logits, dim=-1, keepdim=True)  # (batch_size, 1)

if idx_next == eos_id:  # Stop generating early if end-of-sequence token is encountered and eos_id is specified
break

# Same as before: append sampled index to the running sequence
idx = torch.cat((idx, idx_next), dim=1)  # (batch_size, num_tokens+1)

return idx

Loss functions

calc_loss_batch 函数计算单个批次预测的交叉熵。
calc_loss_loader 获取所有批次的交叉熵并计算 平均交叉熵。

# Define loss functions
def calc_loss_batch(input_batch, target_batch, model, device):
input_batch, target_batch = input_batch.to(device), target_batch.to(device)
logits = model(input_batch)
loss = torch.nn.functional.cross_entropy(logits.flatten(0, 1), target_batch.flatten())
return loss

def calc_loss_loader(data_loader, model, device, num_batches=None):
total_loss = 0.
if len(data_loader) == 0:
return float("nan")
elif num_batches is None:
num_batches = len(data_loader)
else:
# Reduce the number of batches to match the total number of batches in the data loader
# if num_batches exceeds the number of batches in the data loader
num_batches = min(num_batches, len(data_loader))
for i, (input_batch, target_batch) in enumerate(data_loader):
if i < num_batches:
loss = calc_loss_batch(input_batch, target_batch, model, device)
total_loss += loss.item()
else:
break
return total_loss / num_batches

加载数据

函数create_dataloader_v1和create_dataloader_v1在前面的部分已经讨论过。

从这里可以注意到，定义了90%的文本将用于训练，而10%将用于验证，两个数据集存储在两个不同的数据加载器中。
请注意，有时数据集的一部分也会留作测试集，以更好地评估模型的性能。

两个数据加载器使用相同的批量大小、最大长度、步幅和工作线程数（在这种情况下为0）。
主要的区别在于每个加载器使用的数据，以及验证器不会丢弃最后一部分数据，也不会打乱数据，因为这对验证目的并不需要。

此外，步幅与上下文长度一样大，意味着用于训练数据的上下文之间不会重叠（减少过拟合，但也减少训练数据集）。

此外，请注意，在这种情况下，批量大小为2，以将数据分为2个批次，主要目的是允许并行处理并减少每个批次的消耗。

train_ratio = 0.90
split_idx = int(train_ratio * len(text_data))
train_data = text_data[:split_idx]
val_data = text_data[split_idx:]

torch.manual_seed(123)

train_loader = create_dataloader_v1(
train_data,
batch_size=2,
max_length=GPT_CONFIG_124M["context_length"],
stride=GPT_CONFIG_124M["context_length"],
drop_last=True,
shuffle=True,
num_workers=0
)

val_loader = create_dataloader_v1(
val_data,
batch_size=2,
max_length=GPT_CONFIG_124M["context_length"],
stride=GPT_CONFIG_124M["context_length"],
drop_last=False,
shuffle=False,
num_workers=0
)

Sanity Checks

目标是检查是否有足够的用于训练的 tokens，形状是否符合预期，并获取有关用于训练和验证的 tokens 数量的一些信息：

# Sanity checks
if total_tokens * (train_ratio) < GPT_CONFIG_124M["context_length"]:
print("Not enough tokens for the training loader. "
"Try to lower the `GPT_CONFIG_124M['context_length']` or "
"increase the `training_ratio`")

if total_tokens * (1-train_ratio) < GPT_CONFIG_124M["context_length"]:
print("Not enough tokens for the validation loader. "
"Try to lower the `GPT_CONFIG_124M['context_length']` or "
"decrease the `training_ratio`")

print("Train loader:")
for x, y in train_loader:
print(x.shape, y.shape)

print("\nValidation loader:")
for x, y in val_loader:
print(x.shape, y.shape)

train_tokens = 0
for input_batch, target_batch in train_loader:
train_tokens += input_batch.numel()

val_tokens = 0
for input_batch, target_batch in val_loader:
val_tokens += input_batch.numel()

print("Training tokens:", train_tokens)
print("Validation tokens:", val_tokens)
print("All tokens:", train_tokens + val_tokens)

选择用于训练和预计算的设备

以下代码仅选择要使用的设备，并计算训练损失和验证损失（在尚未进行任何训练的情况下）作为起点。

# Indicate the device to use

if torch.cuda.is_available():
device = torch.device("cuda")
elif torch.backends.mps.is_available():
device = torch.device("mps")
else:
device = torch.device("cpu")

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

model.to(device) # no assignment model = model.to(device) necessary for nn.Module classes

# Pre-calculate losses without starting yet
torch.manual_seed(123) # For reproducibility due to the shuffling in the data loader

with torch.no_grad(): # Disable gradient tracking for efficiency because we are not training, yet
train_loss = calc_loss_loader(train_loader, model, device)
val_loss = calc_loss_loader(val_loader, model, device)

print("Training loss:", train_loss)
print("Validation loss:", val_loss)

训练函数

函数 generate_and_print_sample 将获取一个上下文并生成一些标记，以便了解模型在该时刻的表现。这由 train_model_simple 在每一步调用。

函数 evaluate_model 会根据训练函数的指示频繁调用，用于测量模型训练时的训练损失和验证损失。

然后，主要的函数 train_model_simple 实际上是训练模型的函数。它期望：

• 训练数据加载器（数据已分离并准备好进行训练）
• 验证器加载器
• 训练期间使用的 优化器：这是将使用梯度并更新参数以减少损失的函数。在这种情况下，如你所见，使用的是 AdamW，但还有许多其他选择。
• 调用 optimizer.zero_grad() 以在每轮重置梯度，防止它们累积。
• lr 参数是 学习率，决定在优化过程中更新模型参数时采取的 步长大小。较 小 的学习率意味着优化器对权重进行 较小的更新，这可能导致更 精确 的收敛，但可能会 减慢 训练。较 大 的学习率可以加快训练，但 有可能超出 损失函数的最小值（跳过 损失函数最小化的点）。
• 权重衰减 通过添加一个额外的项来修改 损失计算 步骤，以惩罚大权重。这鼓励优化器找到具有较小权重的解决方案，在良好拟合数据和保持模型简单之间取得平衡，防止机器学习模型过拟合，避免模型对任何单一特征赋予过多重要性。
• 传统优化器如带有 L2 正则化的 SGD 将权重衰减与损失函数的梯度结合。然而，AdamW（Adam 优化器的一个变体）将权重衰减与梯度更新解耦，从而实现更有效的正则化。
• 用于训练的设备
• 训练轮数：遍历训练数据的次数
• 评估频率：调用 evaluate_model 的频率
• 评估迭代：在调用 generate_and_print_sample 时评估模型当前状态时使用的批次数
• 开始上下文：调用 generate_and_print_sample 时使用的起始句子
• 分词器

# Functions to train the data
def train_model_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
eval_freq, eval_iter, start_context, tokenizer):
# Initialize lists to track losses and tokens seen
train_losses, val_losses, track_tokens_seen = [], [], []
tokens_seen, global_step = 0, -1

# Main training loop
for epoch in range(num_epochs):
model.train()  # Set model to training mode

for input_batch, target_batch in train_loader:
optimizer.zero_grad() # Reset loss gradients from previous batch iteration
loss = calc_loss_batch(input_batch, target_batch, model, device)
loss.backward() # Calculate loss gradients
optimizer.step() # Update model weights using loss gradients
tokens_seen += input_batch.numel()
global_step += 1

# Optional evaluation step
if global_step % eval_freq == 0:
train_loss, val_loss = evaluate_model(
model, train_loader, val_loader, device, eval_iter)
train_losses.append(train_loss)
val_losses.append(val_loss)
track_tokens_seen.append(tokens_seen)
print(f"Ep {epoch+1} (Step {global_step:06d}): "
f"Train loss {train_loss:.3f}, Val loss {val_loss:.3f}")

# Print a sample text after each epoch
generate_and_print_sample(
model, tokenizer, device, start_context
)

return train_losses, val_losses, track_tokens_seen


def evaluate_model(model, train_loader, val_loader, device, eval_iter):
model.eval() # Set in eval mode to avoid dropout
with torch.no_grad():
train_loss = calc_loss_loader(train_loader, model, device, num_batches=eval_iter)
val_loss = calc_loss_loader(val_loader, model, device, num_batches=eval_iter)
model.train() # Back to training model applying all the configurations
return train_loss, val_loss


def generate_and_print_sample(model, tokenizer, device, start_context):
model.eval() # Set in eval mode to avoid dropout
context_size = model.pos_emb.weight.shape[0]
encoded = text_to_token_ids(start_context, tokenizer).to(device)
with torch.no_grad():
token_ids = generate_text(
model=model, idx=encoded,
max_new_tokens=50, context_size=context_size
)
decoded_text = token_ids_to_text(token_ids, tokenizer)
print(decoded_text.replace("\n", " "))  # Compact print format
model.train() # Back to training model applying all the configurations

Start training

import time
start_time = time.time()

torch.manual_seed(123)
model = GPTModel(GPT_CONFIG_124M)
model.to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=0.0004, weight_decay=0.1)

num_epochs = 10
train_losses, val_losses, tokens_seen = train_model_simple(
model, train_loader, val_loader, optimizer, device,
num_epochs=num_epochs, eval_freq=5, eval_iter=5,
start_context="Every effort moves you", tokenizer=tokenizer
)

end_time = time.time()
execution_time_minutes = (end_time - start_time) / 60
print(f"Training completed in {execution_time_minutes:.2f} minutes.")

打印训练演变

使用以下函数，可以打印模型在训练过程中的演变。

import matplotlib.pyplot as plt
from matplotlib.ticker import MaxNLocator
import math
def plot_losses(epochs_seen, tokens_seen, train_losses, val_losses):
fig, ax1 = plt.subplots(figsize=(5, 3))
ax1.plot(epochs_seen, train_losses, label="Training loss")
ax1.plot(
epochs_seen, val_losses, linestyle="-.", label="Validation loss"
)
ax1.set_xlabel("Epochs")
ax1.set_ylabel("Loss")
ax1.legend(loc="upper right")
ax1.xaxis.set_major_locator(MaxNLocator(integer=True))
ax2 = ax1.twiny()
ax2.plot(tokens_seen, train_losses, alpha=0)
ax2.set_xlabel("Tokens seen")
fig.tight_layout()
plt.show()

# Compute perplexity from the loss values
train_ppls = [math.exp(loss) for loss in train_losses]
val_ppls = [math.exp(loss) for loss in val_losses]
# Plot perplexity over tokens seen
plt.figure()
plt.plot(tokens_seen, train_ppls, label='Training Perplexity')
plt.plot(tokens_seen, val_ppls, label='Validation Perplexity')
plt.xlabel('Tokens Seen')
plt.ylabel('Perplexity')
plt.title('Perplexity over Training')
plt.legend()
plt.show()

epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
plot_losses(epochs_tensor, tokens_seen, train_losses, val_losses)

保存模型

如果您想稍后继续训练，可以保存模型和优化器：

# Save the model and the optimizer for later training
torch.save({
"model_state_dict": model.state_dict(),
"optimizer_state_dict": optimizer.state_dict(),
},
"/tmp/model_and_optimizer.pth"
)
# Note that this model with the optimizer occupied close to 2GB

# Restore model and optimizer for training
checkpoint = torch.load("/tmp/model_and_optimizer.pth", map_location=device)

model = GPTModel(GPT_CONFIG_124M)
model.load_state_dict(checkpoint["model_state_dict"])
optimizer = torch.optim.AdamW(model.parameters(), lr=5e-4, weight_decay=0.1)
optimizer.load_state_dict(checkpoint["optimizer_state_dict"])
model.train(); # Put in training mode

或者仅仅是模型，如果您只打算使用它：

# Save the model
torch.save(model.state_dict(), "model.pth")

# Load it
model = GPTModel(GPT_CONFIG_124M)

model.load_state_dict(torch.load("model.pth", map_location=device))

model.eval() # Put in eval mode

加载 GPT2 权重

有两个快速脚本可以在本地加载 GPT2 权重。对于这两个脚本，您可以在本地克隆仓库 https://github.com/rasbt/LLMs-from-scratch，然后：

• 脚本 https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/01_main-chapter-code/gpt_generate.py 将下载所有权重并将格式从 OpenAI 转换为我们 LLM 所期望的格式。该脚本还准备了所需的配置和提示：“每一次努力都在推动你”
• 脚本 https://github.com/rasbt/LLMs-from-scratch/blob/main/ch05/02_alternative_weight_loading/weight-loading-hf-transformers.ipynb 允许您在本地加载任何 GPT2 权重（只需更改 CHOOSE_MODEL 变量）并从一些提示中预测文本。

参考文献

• https://www.manning.com/books/build-a-large-language-model-from-scratch