nanoGPT
nanoGPT copied to clipboard
try to add more context to learn
Hi. I tried to add more information to the context than just the average of the previous tokens. I added a table that calculates the distance between tokens and adds to wei at the end. But I don't know if that makes sense. I made a global train_mode variable and during training it is set to True but when generating it is changed to False.
this is outputs after 3 times x 5000 iterations. I take 3 training shots. This is result after third training loop on google colab. Because my laptop is 2-3 x times slower than their machines. :)
step 4999: train loss 1.6128, val loss 1.7871
I'm a rookie on this field. Does it improve anything in the model at all?
For example, we have
xs = tensor([18., 47., 56., 57., 58., 1., 15., 47.])
cm = torch.zeros((8))
cm[0] = xs[0]-xs[1]
cm[1] = xs[1]-xs[2]
cm[2] = xs[2]-xs[3]
cm[3] = xs[3]-xs[4]
cm[4] = xs[4]-xs[5]
cm[5] = xs[5]-xs[6]
cm[6] = xs[6]-xs[7]
cm # tensor([-29., -9., -1., -1., 57., -14., -32., 0.])
#cm[torch.arange(7)] = xs[torch.arange(0,7)] - xs[torch.arange(1,8)]
#tensor([-29., -9., -1., -1., 57., -14., -32., 0.])
cm
Nor is defentain by his fouwl and speeceef:
What madam; light I come yours crother,
But acctey's sheath with is see;
Ask his tend, here such my brother menest as actiness, my nugleds, destired, as us as mind.
The flesse; and grace. or meheigness, apppecity-mean's young
contens youtful, patient, you are but,
His duke of bety that dead.
Lad, you lipp's sue, best feast man's break of the feel;
And here seet he is dost not minder hereignes?
BBATH:
Till behear, sit from teaths: I may were thee rude now.
PARILINA:
Luce than he
voicess more conduce fiten:
Thy ham swoon. You from are what heart raim'n.
Low, War, as drengentaged, time fatrom what fight them griet remed justices.
CORIOLANUS:
I say, behow, so much down's gently as virtue,
Wlike deempade your penger, thy swoundship, war, face, what,
Wordespers a much'd of from
thee things then at mure pattal her,
As you set greaties, adoug-mue face I
Hom not bed mistrol!
First Servingman:
As was me noble, my answere reoten,
And moutster mockh'd nor agar
Do heaven, pomplarigeus again!
I robes, O, if sweet the hall hast
hatan's haste full sing then hasts. They capfite, noble eye
Ast can drawleign reessirtate, the reportation,
Whiced sea
Eving inteed to much liest as bear bands! I would, what coburpety than thou's merty thee hath;
Juliet's sepeak these love's hotnow,
I please the sain'st may see is ciest. I'll his husband smeen thee;
He last been it, that it then ure!
HAMINNNUS:
Show not thing's dryy:.
Inreal, when then I torchisoon the friends thet to can?
HARD IIV:
I, what Coast him think the ceque in prinhes,
Truth as plase,
That whit as where these that nappite the greation.
PAHN:
I'll womerch's like, noble,
As night my conscien'st; play speed the horn'd;
And know for your fucel'sim: as he do yes.
Now might now, by her kisnow be this lets; there are her;
Or or grast thou met's deed-indreat be his unbdound,
speak him do slaint, give lettain.
HENRY BOLINNGBROKE:
I wear the Mearage, and sheat, whipt the cucord.
GLOUCESTE
This is the modification
if train_mode == True:
cm = torch.zeros((block_size, block_size))
cm = cm - wei[:, :, torch.arange(0,cm.shape[0])]
rol = cm[:, :, torch.arange(0,cm.shape[0])].roll(-1)
rol[:,:,cm.shape[0]-1] = float("-inf")
rol[:,:,cm.shape[0]-1].exp()
wei = wei + cm
Here's the code
import torch
import torch.nn as nn
from torch.nn import functional as F
# hyperparameters
batch_size = 16 # how many independent sequences will we process in parallel?
block_size = 32 # what is the maximum context length for predictions?
max_iters = 5000
eval_interval = 100
learning_rate = 1e-2
device = 'cuda' if torch.cuda.is_available() else 'cpu'
eval_iters = 200
n_embd = 64
n_head = 4
n_layer = 4
dropout = 0.0
# ------------
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:]
train_mode = True
# 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):
B,T,C = x.shape
k = self.key(x) # (B,T,C)
q = self.query(x) # (B,T,C)
# compute attention scores ("affinities")
wei = q @ k.transpose(-2,-1) * C**-0.5 # (B, T, C) @ (B, C, 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,C)
#####
global train_mode
if train_mode == True:
cm = torch.zeros((block_size, block_size))
#print(wei.shape)
#print(C)
#print(torch.arange(0,cm.shape[0]))
cm = cm - wei[:, :, torch.arange(0,cm.shape[0])]
#print(cm.shape, wei.shape)
# roll
rol = cm[:, :, torch.arange(0,cm.shape[0])].roll(-1)
# change last column
rol[:,:,cm.shape[0]-1] = float("-inf")
# and move to 0 by exp
rol[:,:,cm.shape[0]-1].exp()
#print(cm.shape, wei.shape)
wei = wei + cm
#print(" afeter ", cm.shape, wei.shape)
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)
out = wei @ v # (B, T, T) @ (B, T, C) -> (B, T, C)
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(n_embd, 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
# super simple bigram model
class BigramLanguageModel(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)
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):
global train_mode
train_mode = False
# 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
#print(idx)
idx_cond = idx[:, -block_size:]
# get the predictions
logits, loss = self(idx_cond)
#print(logits, loss)
# 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 = BigramLanguageModel()
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)
Training loop
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()
Example
train_mode = False
context = torch.zeros((1, 1), dtype=torch.long, device=device)
print(decode(m.generate(context, max_new_tokens=2000)[0].tolist()))