app.py

# %%writefile app.py

import streamlit as st
import matplotlib.pyplot as plt
import torch
from transformers import AutoTokenizer, DataCollatorWithPadding, AutoModelForSequenceClassification, AdamW
from datasets import load_dataset
from evaluate import load as load_metric
from torch.utils.data import DataLoader
import random

DEVICE = torch.device("cpu")
NUM_ROUNDS = 3



########################TinyLLM####################################

import torch
import torch.nn as nn
from torch.nn import functional as F

# hyperparameters
batch_size = 64 # how many independent sequences will we process in parallel?
block_size = 256 # what is the maximum context length for predictions?
max_iters = 5000
eval_interval = 500
learning_rate = 3e-4
device = 'cuda' if torch.cuda.is_available() else 'cpu'
eval_iters = 200
n_embd = 384
n_head = 6
n_layer = 6
dropout = 0.2
# ------------

torch.manual_seed(1337)

# wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
with open('input.txt', 'r', encoding='utf-8') as f:
    text = f.read()

# here are all the unique characters that occur in this text
chars = sorted(list(set(text)))
vocab_size = len(chars)
# create a mapping from characters to integers
stoi = { ch:i for i,ch in enumerate(chars) }
itos = { i:ch for i,ch in enumerate(chars) }
encode = lambda s: [stoi[c] for c in s] # encoder: take a string, output a list of integers
decode = lambda l: ''.join([itos[i] for i in l]) # decoder: take a list of integers, output a string

# Train and test splits
data = torch.tensor(encode(text), dtype=torch.long)
n = int(0.9*len(data)) # first 90% will be train, rest val
train_data = data[:n]
val_data = data[n:]

# data loading
def get_batch(split):
    # generate a small batch of data of inputs x and targets y
    data = train_data if split == 'train' else val_data
    ix = torch.randint(len(data) - block_size, (batch_size,))
    x = torch.stack([data[i:i+block_size] for i in ix])
    y = torch.stack([data[i+1:i+block_size+1] for i in ix])
    x, y = x.to(device), y.to(device)
    return x, y

@torch.no_grad()
def estimate_loss():
    out = {}
    model.eval()
    for split in ['train', 'val']:
        losses = torch.zeros(eval_iters)
        for k in range(eval_iters):
            X, Y = get_batch(split)
            logits, loss = model(X, Y)
            losses[k] = loss.item()
        out[split] = losses.mean()
    model.train()
    return out

class Head(nn.Module):
    """ one head of self-attention """

    def __init__(self, head_size):
        super().__init__()
        self.key = nn.Linear(n_embd, head_size, bias=False)
        self.query = nn.Linear(n_embd, head_size, bias=False)
        self.value = nn.Linear(n_embd, head_size, bias=False)
        self.register_buffer('tril', torch.tril(torch.ones(block_size, block_size)))

        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        # input of size (batch, time-step, channels)
        # output of size (batch, time-step, head size)
        B,T,C = x.shape
        k = self.key(x)   # (B,T,hs)
        q = self.query(x) # (B,T,hs)
        # compute attention scores ("affinities")
        wei = q @ k.transpose(-2,-1) * k.shape[-1]**-0.5 # (B, T, hs) @ (B, hs, T) -> (B, T, T)
        wei = wei.masked_fill(self.tril[:T, :T] == 0, float('-inf')) # (B, T, T)
        wei = F.softmax(wei, dim=-1) # (B, T, T)
        wei = self.dropout(wei)
        # perform the weighted aggregation of the values
        v = self.value(x) # (B,T,hs)
        out = wei @ v # (B, T, T) @ (B, T, hs) -> (B, T, hs)
        return out

class MultiHeadAttention(nn.Module):
    """ multiple heads of self-attention in parallel """

    def __init__(self, num_heads, head_size):
        super().__init__()
        self.heads = nn.ModuleList([Head(head_size) for _ in range(num_heads)])
        self.proj = nn.Linear(head_size * num_heads, n_embd)
        self.dropout = nn.Dropout(dropout)

    def forward(self, x):
        out = torch.cat([h(x) for h in self.heads], dim=-1)
        out = self.dropout(self.proj(out))
        return out

class FeedFoward(nn.Module):
    """ a simple linear layer followed by a non-linearity """

    def __init__(self, n_embd):
        super().__init__()
        self.net = nn.Sequential(
            nn.Linear(n_embd, 4 * n_embd),
            nn.ReLU(),
            nn.Linear(4 * n_embd, n_embd),
            nn.Dropout(dropout),
        )

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

class Block(nn.Module):
    """ Transformer block: communication followed by computation """

    def __init__(self, n_embd, n_head):
        # n_embd: embedding dimension, n_head: the number of heads we'd like
        super().__init__()
        head_size = n_embd // n_head
        self.sa = MultiHeadAttention(n_head, head_size)
        self.ffwd = FeedFoward(n_embd)
        self.ln1 = nn.LayerNorm(n_embd)
        self.ln2 = nn.LayerNorm(n_embd)

    def forward(self, x):
        x = x + self.sa(self.ln1(x))
        x = x + self.ffwd(self.ln2(x))
        return x

class GPTLanguageModel(nn.Module):

    def __init__(self):
        super().__init__()
        # each token directly reads off the logits for the next token from a lookup table
        self.token_embedding_table = nn.Embedding(vocab_size, n_embd)
        self.position_embedding_table = nn.Embedding(block_size, n_embd)
        self.blocks = nn.Sequential(*[Block(n_embd, n_head=n_head) for _ in range(n_layer)])
        self.ln_f = nn.LayerNorm(n_embd) # final layer norm
        self.lm_head = nn.Linear(n_embd, vocab_size)

        # better init, not covered in the original GPT video, but important, will cover in followup video
        self.apply(self._init_weights)

    def _init_weights(self, module):
        if isinstance(module, nn.Linear):
            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)
            if module.bias is not None:
                torch.nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            torch.nn.init.normal_(module.weight, mean=0.0, std=0.02)

    def forward(self, idx, targets=None):
        B, T = idx.shape

        # idx and targets are both (B,T) tensor of integers
        tok_emb = self.token_embedding_table(idx) # (B,T,C)
        pos_emb = self.position_embedding_table(torch.arange(T, device=device)) # (T,C)
        x = tok_emb + pos_emb # (B,T,C)
        x = self.blocks(x) # (B,T,C)
        x = self.ln_f(x) # (B,T,C)
        logits = self.lm_head(x) # (B,T,vocab_size)

        if targets is None:
            loss = None
        else:
            B, T, C = logits.shape
            logits = logits.view(B*T, C)
            targets = targets.view(B*T)
            loss = F.cross_entropy(logits, targets)

        return logits, loss

    def generate(self, idx, max_new_tokens):
        # idx is (B, T) array of indices in the current context
        for _ in range(max_new_tokens):
            # crop idx to the last block_size tokens
            idx_cond = idx[:, -block_size:]
            # get the predictions
            logits, loss = self(idx_cond)
            # focus only on the last time step
            logits = logits[:, -1, :] # becomes (B, C)
            # apply softmax to get probabilities
            probs = F.softmax(logits, dim=-1) # (B, C)
            # sample from the distribution
            idx_next = torch.multinomial(probs, num_samples=1) # (B, 1)
            # append sampled index to the running sequence
            idx = torch.cat((idx, idx_next), dim=1) # (B, T+1)
        return idx

model = GPTLanguageModel()
m = model.to(device)
# print the number of parameters in the model
print(sum(p.numel() for p in m.parameters())/1e6, 'M parameters')

# create a PyTorch optimizer
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)

for iter in range(max_iters):

    # every once in a while evaluate the loss on train and val sets
    if iter % eval_interval == 0 or iter == max_iters - 1:
        losses = estimate_loss()
        print(f"step {iter}: train loss {losses['train']:.4f}, val loss {losses['val']:.4f}")

    # sample a batch of data
    xb, yb = get_batch('train')

    # evaluate the loss
    logits, loss = model(xb, yb)
    optimizer.zero_grad(set_to_none=True)
    loss.backward()
    optimizer.step()

# generate from the model
context = torch.zeros((1, 1), dtype=torch.long, device=device)
print(decode(m.generate(context, max_new_tokens=500)[0].tolist()))
#open('more.txt', 'w').write(decode(m.generate(context, max_new_tokens=10000)[0].tolist()))











########################TinyLLM##################################

def load_data(dataset_name):
    raw_datasets = load_dataset(dataset_name)
    raw_datasets = raw_datasets.shuffle(seed=42)
    del raw_datasets["unsupervised"]

    tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")

    def tokenize_function(examples):
        return tokenizer(examples["text"], truncation=True)

    train_population = random.sample(range(len(raw_datasets["train"])), 20)
    test_population = random.sample(range(len(raw_datasets["test"])), 20)

    tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
    tokenized_datasets["train"] = tokenized_datasets["train"].select(train_population)
    tokenized_datasets["test"] = tokenized_datasets["test"].select(test_population)

    tokenized_datasets = tokenized_datasets.remove_columns("text")
    tokenized_datasets = tokenized_datasets.rename_column("label", "labels")

    data_collator = DataCollatorWithPadding(tokenizer=tokenizer)
    trainloader = DataLoader(tokenized_datasets["train"], shuffle=True, batch_size=32, collate_fn=data_collator)
    testloader = DataLoader(tokenized_datasets["test"], batch_size=32, collate_fn=data_collator)

    return trainloader, testloader

def train(net, trainloader, epochs):
    optimizer = AdamW(net.parameters(), lr=5e-5)
    net.train()
    for _ in range(epochs):
        for batch in trainloader:
            batch = {k: v.to(DEVICE) for k, v in batch.items()}
            outputs = net(**batch)
            loss = outputs.loss
            loss.backward()
            optimizer.step()
            optimizer.zero_grad()

def test(net, testloader):
    metric = load_metric("accuracy")
    loss = 0
    net.eval()
    for batch in testloader:
        batch = {k: v.to(DEVICE) for k, v in batch.items()}
        with torch.no_grad():
            outputs = net(**batch)
        logits = outputs.logits
        loss += outputs.loss.item()
        predictions = torch.argmax(logits, dim=-1)
        metric.add_batch(predictions=predictions, references=batch["labels"])
    loss /= len(testloader.dataset)
    accuracy = metric.compute()["accuracy"]
    return loss, accuracy

net = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased", num_labels=2).to(DEVICE)

def main():
    st.write("## Federated Learning with dynamic models and datasets for mobile devices")
    dataset_name = st.selectbox("Dataset", ["imdb", "amazon_polarity", "ag_news"])
    model_name = st.selectbox("Model", ["bert-base-uncased", "distilbert-base-uncased"])
    NUM_CLIENTS = st.slider("Number of Clients", min_value=1, max_value=10, value=2)
    NUM_ROUNDS = st.slider("Number of Rounds", min_value=1, max_value=10, value=3)

    trainloader, testloader = load_data(dataset_name)

    if st.button("Start Training"):
        round_losses = []
        round_accuracies = []  # Store accuracy values for each round
        for round_num in range(1, NUM_ROUNDS + 1):
            st.write(f"## Round {round_num}")

            st.write("### Training Metrics for Each Client")
            for client in range(1, NUM_CLIENTS + 1):
                client_loss, client_accuracy = test(net, testloader)  # Placeholder for actual client metrics
                st.write(f"Client {client}: Loss: {client_loss}, Accuracy: {client_accuracy}")

            st.write("### Accuracy Over Rounds")
            round_accuracies.append(client_accuracy)  # Append the accuracy for this round
            plt.plot(range(1, round_num + 1), round_accuracies, marker='o')  # Plot accuracy over rounds
            plt.xlabel("Round")
            plt.ylabel("Accuracy")
            plt.title("Accuracy Over Rounds")
            st.pyplot()

            st.write("### Loss Over Rounds")
            loss_value = random.random()  # Placeholder for loss values
            round_losses.append(loss_value)
            rounds = list(range(1, round_num + 1))
            plt.plot(rounds, round_losses)
            plt.xlabel("Round")
            plt.ylabel("Loss")
            plt.title("Loss Over Rounds")
            st.pyplot()

            st.success(f"Round {round_num} completed successfully!")

    else:
        st.write("Click the 'Start Training' button to start the training process.")

if __name__ == "__main__":
    main()