-
Notifications
You must be signed in to change notification settings - Fork 0
/
bigram_v1.py
126 lines (104 loc) · 3.94 KB
/
bigram_v1.py
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
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
# Simple bigram model without any attention mechanism
import torch
import torch.nn as nn
from torch.nn import functional as F
# hyperparameters
batch_size = 4 # how many independet sequences we will process in parallel
block_size = 8 # what is the maximum context length of the predictions?
max_iters = 3000
eval_interval = 300
learning_rate = 1e-2
device = "cuda" if torch.cuda.is_available() else "cpu"
eval_iters = 200
torch.manual_seed(1337)
with open("input.txt", "r", encoding="utf-8") as f:
text = f.read()
# unique characters that occur in the dataset
chars = sorted(list(set(text)))
vocab_size = len(chars)
# creating 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: takes a string, output a list of integers
decode = lambda l: "".join(
[itos[i] for i in l]
) # decoder: takes a list of integers, outputs 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
# super simple bigram model
class BigramLanguageModel(nn.Module):
def __init__(self, vocab_size):
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, vocab_size)
def forward(self, idx, targets=None):
# idx and targets are both (B, T) tensors of integers
logits = self.token_embedding_table(idx) # B,T,C
if targets is None:
loss = None
else:
B, T, C = logits.shape
targets = targets.view(B * T)
loss = F.cross_entropy(logits.view(B * T, C), 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):
# get the predictions
logits, loss = self(idx)
# focus only on 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(vocab_size)
m = model.to(device)
optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
for iter in range(max_iters):
# every once in while evaluate loss on train and val sets
if iter % eval_interval == 0:
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 = m(xb, yb)
optimizer.zero_grad(set_to_none=True)
loss.backward()
optimizer.step()
# generate from model
context = torch.zeros((1, 1), dtype=torch.long)
print(decode(m.generate(context, max_new_tokens=500)[0].tolist()))