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
#Downloading and unzipping the dataset
import urllib.request
import zipfile
import os
from pathlib import Path

url = "https://archive.ics.uci.edu/static/public/228/sms+spam+collection.zip"
zip_path = "sms_spam_collection.zip"
extracted_path = "sms_spam_collection"
data_file_path = Path(extracted_path) / "SMSSpamCollection.tsv"

def download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path):
    if data_file_path.exists():
        print(f"{data_file_path} already exists. Skipping download and extraction.")
        return

    # Downloading the file
    with urllib.request.urlopen(url) as response:
        with open(zip_path, "wb") as out_file:
            out_file.write(response.read())

    # Unzipping the file
    with zipfile.ZipFile(zip_path, "r") as zip_ref:
        zip_ref.extractall(extracted_path)

    # Add .tsv file extension
    original_file_path = Path(extracted_path) / "SMSSpamCollection"
    os.rename(original_file_path, data_file_path)
    print(f"File downloaded and saved as {data_file_path}")

download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)

import pandas as pd

df = pd.read_csv(data_file_path, sep="\t", header=None, names=["Label", "Text"])
df

1
print(df["Label"].value_counts())

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
#Creating a balanced dataset
def create_balanced_dataset(df):
    
    # Count the instances of "spam"
    num_spam = df[df["Label"] == "spam"].shape[0]
    
    # Randomly sample "ham" instances to match the number of "spam" instances
    ham_subset = df[df["Label"] == "ham"].sample(num_spam, random_state=123)
    
    # Combine ham "subset" with "spam"
    balanced_df = pd.concat([ham_subset, df[df["Label"] == "spam"]])

    return balanced_df


balanced_df = create_balanced_dataset(df)
print(balanced_df["Label"].value_counts())

1
2
balanced_df["Label"] = balanced_df["Label"].map({"ham": 0, "spam": 1})    
balanced_df

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#Splitting the dataset
def random_split(df, train_frac, validation_frac):
    # Shuffle the entire DataFrame
    df = df.sample(frac=1, random_state=123).reset_index(drop=True)

    # Calculate split indices
    train_end = int(len(df) * train_frac)
    validation_end = train_end + int(len(df) * validation_frac)

    # Split the DataFrame
    train_df = df[:train_end]
    validation_df = df[train_end:validation_end]
    test_df = df[validation_end:]

    return train_df, validation_df, test_df

train_df, validation_df, test_df = random_split(balanced_df, 0.7, 0.1)
# Test size is implied to be 0.2 as the remainder

train_df.to_csv("train.csv", index=None)
validation_df.to_csv("validation.csv", index=None)
test_df.to_csv("test.csv", index=None)

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
#Setting up a Pytorch Dataset class
import torch
from torch.utils.data import Dataset


class SpamDataset(Dataset):
    def __init__(self, csv_file, tokenizer, max_length=None, pad_token_id=50256):
        self.data = pd.read_csv(csv_file)

        # Pre-tokenize texts
        self.encoded_texts = [
            tokenizer.encode(text) for text in self.data["Text"]
        ]

        if max_length is None:
            self.max_length = self._longest_encoded_length()
        else:
            self.max_length = max_length
            # Truncate sequences if they are longer than max_length
            self.encoded_texts = [
                encoded_text[:self.max_length]
                for encoded_text in self.encoded_texts
            ]

        # Pad sequences to the longest sequence
        self.encoded_texts = [
            encoded_text + [pad_token_id] * (self.max_length - len(encoded_text))
            for encoded_text in self.encoded_texts
        ]

    def __getitem__(self, index):
        encoded = self.encoded_texts[index]
        label = self.data.iloc[index]["Label"]
        return (
            torch.tensor(encoded, dtype=torch.long),
            torch.tensor(label, dtype=torch.long)
        )

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

    def _longest_encoded_length(self):
        max_length = 0
        for encoded_text in self.encoded_texts:
            encoded_length = len(encoded_text)
            if encoded_length > max_length:
                max_length = encoded_length
        return max_length
        # Note: A more pythonic version to implement this method
        # is the following, which is also used in the next chapter:
        # return max(len(encoded_text) for encoded_text in self.encoded_texts)

train_dataset = SpamDataset(
    csv_file="train.csv",
    max_length=None,
    tokenizer=tokenizer
)

print(train_dataset.max_length) #120

1
2
3
4
5
6
7
8
9
10
val_dataset = SpamDataset(
    csv_file="validation.csv",
    max_length=train_dataset.max_length, #保持和训练集一样的max_length
    tokenizer=tokenizer
)
test_dataset = SpamDataset(
    csv_file="test.csv",
    max_length=train_dataset.max_length, #保持和训练集一样的max_length
    tokenizer=tokenizer
)

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
#Creating PyTorch data loaders
from torch.utils.data import DataLoader

num_workers = 0 #This setting ensures compatibility with most computers.
batch_size = 8

torch.manual_seed(123)

train_loader = DataLoader(
    dataset=train_dataset,
    batch_size=batch_size,
    shuffle=True,
    num_workers=num_workers,
    drop_last=True,
)

val_loader = DataLoader(
    dataset=val_dataset,
    batch_size=batch_size,
    num_workers=num_workers,
    drop_last=False,
)

test_loader = DataLoader(
    dataset=test_dataset,
    batch_size=batch_size,
    num_workers=num_workers,
    drop_last=False,
)

print("Train loader:")
for input_batch, target_batch in train_loader:
    pass

#打印最后一个batch的张量维度
print("Input batch dimensions:", input_batch.shape)
print("Label batch dimensions", target_batch.shape)

1
2
3
print(f"{len(train_loader)} training batches") #130 training batches
print(f"{len(val_loader)} validation batches") #19 validation batches
print(f"{len(test_loader)} test batches") #38 test batches

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
CHOOSE_MODEL = "gpt2-small (124M)"
INPUT_PROMPT = "Every effort moves"

BASE_CONFIG = {
    "vocab_size": 50257,     # Vocabulary size
    "context_length": 1024,  # Context length
    "drop_rate": 0.0,        # Dropout rate
    "qkv_bias": True         # Query-key-value bias
}

model_configs = {
    "gpt2-small (124M)": {"emb_dim": 768, "n_layers": 12, "n_heads": 12},
    "gpt2-medium (355M)": {"emb_dim": 1024, "n_layers": 24, "n_heads": 16},
    "gpt2-large (774M)": {"emb_dim": 1280, "n_layers": 36, "n_heads": 20},
    "gpt2-xl (1558M)": {"emb_dim": 1600, "n_layers": 48, "n_heads": 25},
}

BASE_CONFIG.update(model_configs[CHOOSE_MODEL])

assert train_dataset.max_length <= BASE_CONFIG["context_length"], (
    f"Dataset length {train_dataset.max_length} exceeds model's context "
    f"length {BASE_CONFIG['context_length']}. Reinitialize data sets with "
    f"`max_length={BASE_CONFIG['context_length']}`"
)

1
2
3
4
5
6
7
8
9
10
#Loading a pretrained GPT model
from gpt_download import download_and_load_gpt2
from previous_chapters import GPTModel, load_weights_into_gpt

model_size = CHOOSE_MODEL.split(" ")[-1].lstrip("(").rstrip(")")
settings, params = download_and_load_gpt2(model_size=model_size, models_dir="gpt2")

model = GPTModel(BASE_CONFIG)
load_weights_into_gpt(model, params)
model.eval();

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
from previous_chapters import (
    generate_text_simple,
    text_to_token_ids,
    token_ids_to_text
)


text_1 = "Every effort moves you"

token_ids = generate_text_simple(
    model=model,
    idx=text_to_token_ids(text_1, tokenizer),
    max_new_tokens=15,
    context_size=BASE_CONFIG["context_length"]
)

print(token_ids_to_text(token_ids, tokenizer))

1
2
3
4
5
6
7
8
9
10
11
12
13
14
text_2 = (
    "Is the following text 'spam'? Answer with 'yes' or 'no':"
    " 'You are a winner you have been specially"
    " selected to receive $1000 cash or a $2000 award.'"
)

token_ids = generate_text_simple(
    model=model,
    idx=text_to_token_ids(text_2, tokenizer),
    max_new_tokens=23,
    context_size=BASE_CONFIG["context_length"]
)

print(token_ids_to_text(token_ids, tokenizer))

1
2
for param in model.parameters():
    param.requires_grad = False

1
2
3
4
5
#Adding a classification layer
torch.manual_seed(123)

num_classes = 2
model.out_head = torch.nn.Linear(in_features=BASE_CONFIG["emb_dim"], out_features=num_classes)

1
2
3
4
5
for param in model.trf_blocks[-1].parameters():
    param.requires_grad = True

for param in model.final_norm.parameters():
    param.requires_grad = True

1
2
3
4
5
6
7
8
9
10
inputs = tokenizer.encode("Do you have time")
inputs = torch.tensor(inputs).unsqueeze(0)
print("Inputs:", inputs)
print("Inputs dimensions:", inputs.shape) # shape: (batch_size, num_tokens)

with torch.no_grad():
    outputs = model(inputs)

print("Outputs:\n", outputs)
print("Outputs dimensions:", outputs.shape) # shape: (batch_size, num_tokens, num_classes)

1
print("Last output token:", outputs[:, -1, :]) #Last output token: tensor([[-3.5983,  3.9902]])

1
2
3
4
print("Last output token:", outputs[:, -1, :]) #Last output token: tensor([[-3.5983,  3.9902]])
probas = torch.softmax(outputs[:, -1, :], dim=-1) #可省略
label = torch.argmax(probas)
print("Class label:", label.item()) #Class label: 1

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#Calculating the classification accuracy
def calc_accuracy_loader(data_loader, model, device, num_batches=None):
    model.eval()
    correct_predictions, num_examples = 0, 0

    if num_batches is None:
        num_batches = len(data_loader)
    else:
        num_batches = min(num_batches, len(data_loader))
    for i, (input_batch, target_batch) in enumerate(data_loader):
        if i < num_batches:
            input_batch, target_batch = input_batch.to(device), target_batch.to(device)

            with torch.no_grad():
                logits = model(input_batch)[:, -1, :]  # Logits of last output token
            predicted_labels = torch.argmax(logits, dim=-1)

            num_examples += predicted_labels.shape[0]
            correct_predictions += (predicted_labels == target_batch).sum().item()
        else:
            break
    return correct_predictions / num_examples

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

# Note:
# Uncommenting the following lines will allow the code to run on Apple Silicon chips, if applicable,
# which is approximately 2x faster than on an Apple CPU (as measured on an M3 MacBook Air).
# As of this writing, in PyTorch 2.4, the results obtained via CPU and MPS were identical.
# However, in earlier versions of PyTorch, you may observe different results when using MPS.

#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"Running on {device} device.")

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

torch.manual_seed(123) # For reproducibility due to the shuffling in the training data loader

train_accuracy = calc_accuracy_loader(train_loader, model, device, num_batches=10)
val_accuracy = calc_accuracy_loader(val_loader, model, device, num_batches=10)
test_accuracy = calc_accuracy_loader(test_loader, model, device, num_batches=10)

print(f"Training accuracy: {train_accuracy*100:.2f}%") #Training accuracy: 46.25%
print(f"Validation accuracy: {val_accuracy*100:.2f}%") #Validation accuracy: 45.00%
print(f"Test accuracy: {test_accuracy*100:.2f}%") #Test accuracy: 48.75%

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
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)[:, -1, :]  # Logits of last output token
    loss = torch.nn.functional.cross_entropy(logits, target_batch)
    return loss

#Calculating the classification loss
# Same as in chapter 5
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

1
2
3
4
5
6
7
8
with torch.no_grad(): # Disable gradient tracking for efficiency because we are not training, yet
    train_loss = calc_loss_loader(train_loader, model, device, num_batches=5)
    val_loss = calc_loss_loader(val_loader, model, device, num_batches=5)
    test_loss = calc_loss_loader(test_loader, model, device, num_batches=5)

print(f"Training loss: {train_loss:.3f}") #Training loss: 2.453
print(f"Validation loss: {val_loss:.3f}") #Validation loss: 2.583
print(f"Test loss: {test_loss:.3f}") #Test loss: 2.322

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
# Overall the same as `train_model_simple` in chapter 5
def train_classifier_simple(model, train_loader, val_loader, optimizer, device, num_epochs,
                            eval_freq, eval_iter):
    # Initialize lists to track losses and examples seen
    train_losses, val_losses, train_accs, val_accs = [], [], [], []
    examples_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
            examples_seen += input_batch.shape[0] # New: track examples instead of tokens
            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)
                print(f"Ep {epoch+1} (Step {global_step:06d}): "
                      f"Train loss {train_loss:.3f}, Val loss {val_loss:.3f}")

        # Calculate accuracy after each epoch
        train_accuracy = calc_accuracy_loader(train_loader, model, device, num_batches=eval_iter)
        val_accuracy = calc_accuracy_loader(val_loader, model, device, num_batches=eval_iter)
        print(f"Training accuracy: {train_accuracy*100:.2f}% | ", end="")
        print(f"Validation accuracy: {val_accuracy*100:.2f}%")
        train_accs.append(train_accuracy)
        val_accs.append(val_accuracy)

    return train_losses, val_losses, train_accs, val_accs, examples_seen

1
2
3
4
5
6
7
8
# Same as chapter 5
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

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
import time

start_time = time.time()

torch.manual_seed(123)

optimizer = torch.optim.AdamW(model.parameters(), lr=5e-5, weight_decay=0.1)

num_epochs = 5
train_losses, val_losses, train_accs, val_accs, examples_seen = train_classifier_simple(
    model, train_loader, val_loader, optimizer, device,
    num_epochs=num_epochs, eval_freq=50, eval_iter=5,
)

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

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
#Plotting the classification loss
import matplotlib.pyplot as plt

def plot_values(epochs_seen, examples_seen, train_values, val_values, label="loss"):
    fig, ax1 = plt.subplots(figsize=(5, 3))

    # Plot training and validation loss against epochs
    ax1.plot(epochs_seen, train_values, label=f"Training {label}")
    ax1.plot(epochs_seen, val_values, linestyle="-.", label=f"Validation {label}")
    ax1.set_xlabel("Epochs")
    ax1.set_ylabel(label.capitalize())
    ax1.legend()

    # Create a second x-axis for examples seen
    ax2 = ax1.twiny()  # Create a second x-axis that shares the same y-axis
    ax2.plot(examples_seen, train_values, alpha=0)  # Invisible plot for aligning ticks
    ax2.set_xlabel("Examples seen")

    fig.tight_layout()  # Adjust layout to make room
    plt.savefig(f"{label}-plot.pdf")
    plt.show()

epochs_tensor = torch.linspace(0, num_epochs, len(train_losses))
examples_seen_tensor = torch.linspace(0, examples_seen, len(train_losses))

plot_values(epochs_tensor, examples_seen_tensor, train_losses, val_losses)

1
2
3
4
epochs_tensor = torch.linspace(0, num_epochs, len(train_accs))
examples_seen_tensor = torch.linspace(0, examples_seen, len(train_accs))

plot_values(epochs_tensor, examples_seen_tensor, train_accs, val_accs, label="accuracy")

1
2
3
4
5
6
7
train_accuracy = calc_accuracy_loader(train_loader, model, device)
val_accuracy = calc_accuracy_loader(val_loader, model, device)
test_accuracy = calc_accuracy_loader(test_loader, model, device)

print(f"Training accuracy: {train_accuracy*100:.2f}%") #Training accuracy: 97.21%
print(f"Validation accuracy: {val_accuracy*100:.2f}%") #Validation accuracy: 97.32%
print(f"Test accuracy: {test_accuracy*100:.2f}%") #Test accuracy: 95.67%

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
#Using the model to classify new texts
def classify_review(text, model, tokenizer, device, max_length=None, pad_token_id=50256):
    model.eval()

    # Prepare inputs to the model
    input_ids = tokenizer.encode(text)
    supported_context_length = model.pos_emb.weight.shape[0]
    # Note: In the book, this was originally written as pos_emb.weight.shape[1] by mistake
    # It didn't break the code but would have caused unnecessary truncation (to 768 instead of 1024)

    # Truncate sequences if they too long
    input_ids = input_ids[:min(max_length, supported_context_length)]

    # Pad sequences to the longest sequence
    input_ids += [pad_token_id] * (max_length - len(input_ids))
    input_tensor = torch.tensor(input_ids, device=device).unsqueeze(0) # add batch dimension

    # Model inference
    with torch.no_grad():
        logits = model(input_tensor)[:, -1, :]  # Logits of the last output token
    predicted_label = torch.argmax(logits, dim=-1).item()

    # Return the classified result
    return "spam" if predicted_label == 1 else "not spam"

text_1 = (
    "You are a winner you have been specially"
    " selected to receive $1000 cash or a $2000 award."
)

print(classify_review(
    text_1, model, tokenizer, device, max_length=train_dataset.max_length
)) #spam

text_2 = (
    "Hey, just wanted to check if we're still on"
    " for dinner tonight? Let me know!"
)

print(classify_review(
    text_2, model, tokenizer, device, max_length=train_dataset.max_length
)) #not spam

1
torch.save(model.state_dict(), "review_classifier.pth")

1
2
model_state_dict = torch.load("review_classifier.pth", map_location=device, weights_only=True)
model.load_state_dict(model_state_dict)