Fine Tuning for Classification

import requests
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
    response = requests.get(url, stream=True, timeout=60)
    response.raise_for_status()
    with open(zip_path, "wb") as out_file:
        for chunk in response.iter_content(chunk_size=8192):
            if chunk:
                out_file.write(chunk)

    # 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}")


try:
    download_and_unzip_spam_data(url, zip_path, extracted_path, data_file_path)
except (requests.exceptions.RequestException, TimeoutError) as e:
    print(f"Primary URL failed: {e}. Trying backup URL...")
    url = "https://f001.backblazeb2.com/file/LLMs-from-scratch/sms%2Bspam%2Bcollection.zip"
    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

df["Label"].value_counts()

Label
ham     4825
spam     747
Name: count, dtype: int64

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)
balanced_df["Label"].value_counts()

Label
ham     747
spam    747
Name: count, dtype: int64

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

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)

import tiktoken
tokenizer = tiktoken.get_encoding("gpt2")
print(tokenizer.encode("<|endoftext|>", allowed_special={"<|endoftext|>"}))

[50256]

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
)

train_dataset.max_length

120

val_dataset = SpamDataset(
    csv_file="validation.csv",
    max_length=train_dataset.max_length,
    tokenizer=tokenizer
)
test_dataset = SpamDataset(
    csv_file="test.csv",
    max_length=train_dataset.max_length,
    tokenizer=tokenizer
)

from torch.utils.data import DataLoader

num_workers = 0
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
)

for input_batch, target_batch in train_loader:
    pass
print("Input batch dimensions:", input_batch.shape)
print("Label batch dimensions", target_batch.shape)

Input batch dimensions: torch.Size([8, 120])
Label batch dimensions torch.Size([8])

print(f"{len(train_loader)} training batches")
print(f"{len(val_loader)} validation batches")
print(f"{len(test_loader)} test batches")

130 training batches
19 validation batches
38 test batches

CHOOSE_MODEL = "gpt2-small (124M)"
INPUT_PROMPT = "Every effort moves"
BASE_CONFIG = {
 "vocab_size": 50257,
 "context_length": 1024,
 "drop_rate": 0.0,
 "qkv_bias": True
}
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])

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()

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"]
)
token_ids_to_text(token_ids, tokenizer)

'Every effort moves you forward.\n\nThe first step is to understand the importance of your work'

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))

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.'

The following text 'spam'? Answer with 'yes' or 'no': 'You are a winner

model

GPTModel(
  (tok_emb): Embedding(50257, 768)
  (pos_emb): Embedding(1024, 768)
  (drop_emb): Dropout(p=0.0, inplace=False)
  (trf_blocks): Sequential(
    (0): TransformerBlock(
      (att): MultiHeadAttention(
        (W_q): Linear(in_features=768, out_features=768, bias=True)
        (W_k): Linear(in_features=768, out_features=768, bias=True)
        (W_v): Linear(in_features=768, out_features=768, bias=True)
        (out_proj): Linear(in_features=768, out_features=768, bias=True)
        (dropout): Dropout(p=0.0, inplace=False)
      )
      (ff): FeedForward(
        (layers): Sequential(
          (0): Linear(in_features=768, out_features=3072, bias=True)
          (1): GELU()
          (2): Linear(in_features=3072, out_features=768, bias=True)
        )
      )
      (norm1): LayerNorm()
      (norm2): LayerNorm()
      (drop_shortcut): Dropout(p=0.0, inplace=False)
    )
    (1): TransformerBlock(
...
    )
  )
  (final_norm): LayerNorm()
  (out_head): Linear(in_features=768, out_features=50257, bias=False)
)
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

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

torch.manual_seed(123)
num_classes = 2
model.out_head = torch.nn.Linear(
    in_features=BASE_CONFIG["emb_dim"],
    out_features=num_classes
)

for param in model.trf_blocks[-1].parameters():
    param.requires_grad = True
for param in model.final_norm.parameters():
    param.requires_grad = True

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 = input_batch.to(device)
            target_batch = target_batch.to(device)

            with torch.no_grad():
                logits = model(input_batch)[:, -1, :]
            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

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
torch.manual_seed(123)
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}%")
print(f"Validation accuracy: {val_accuracy*100:.2f}%")
print(f"Test accuracy: {test_accuracy*100:.2f}%")
device

Training accuracy: 46.25%
Validation accuracy: 45.00%
Test accuracy: 48.75%

def calc_loss_batch(input_batch, target_batch, model, device):
    input_batch = input_batch.to(device)
    target_batch = target_batch.to(device)
    logits = model(input_batch)[:, -1, :]
    loss = torch.nn.functional.cross_entropy(logits, target_batch)
    return 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

# 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


# 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

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.")

Ep 1 (Step 000000): Train loss 2.153, Val loss 2.392
Ep 1 (Step 000050): Train loss 0.617, Val loss 0.637
Ep 1 (Step 000100): Train loss 0.523, Val loss 0.557
Training accuracy: 70.00% | Validation accuracy: 72.50%
Ep 2 (Step 000150): Train loss 0.561, Val loss 0.489
Ep 2 (Step 000200): Train loss 0.419, Val loss 0.397
Ep 2 (Step 000250): Train loss 0.409, Val loss 0.353
Training accuracy: 82.50% | Validation accuracy: 85.00%
Ep 3 (Step 000300): Train loss 0.333, Val loss 0.320
Ep 3 (Step 000350): Train loss 0.340, Val loss 0.306
Training accuracy: 90.00% | Validation accuracy: 90.00%
Ep 4 (Step 000400): Train loss 0.136, Val loss 0.200
Ep 4 (Step 000450): Train loss 0.153, Val loss 0.132
Ep 4 (Step 000500): Train loss 0.222, Val loss 0.137
Training accuracy: 100.00% | Validation accuracy: 97.50%
Ep 5 (Step 000550): Train loss 0.207, Val loss 0.143
Ep 5 (Step 000600): Train loss 0.083, Val loss 0.074
Training accuracy: 100.00% | Validation accuracy: 97.50%
Training completed in 1.23 minutes.

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)

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"
)

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}%")
print(f"Validation accuracy: {val_accuracy*100:.2f}%")
print(f"Test accuracy: {test_accuracy*100:.2f}%")

def classify_review(text, model, tokenizer, device, max_length=None, pad_token_id=50256):
    model.eval()
    
    input_ids = tokenizer.encode(text)
    supported_context_length = model.pos_emb.weight.shape[1]
    
    input_ids = input_ids[:min(
        max_length, supported_context_length
    )]
    input_ids += [pad_token_id] * (max_length - len(input_ids))

    input_tensor = torch.tensor(
        input_ids, device=device
    ).unsqueeze(0)

    with torch.no_grad():
        logits = model(input_tensor)[:, -1, :]
    predicted_label = torch.argmax(logits, dim=-1).item()
    
    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

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

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