【Colossal-AI】LLMが自分のPCで安く簡単に、高速で利用できるツール

!pip install colossalai%cd ColossalAI!pip install -r requirements/requirements.txt!CUDA_EXT=1 pip install .%cd examples/images/resnet!pip install -r requirements.txt

!colossalai run --nproc_per_node 1 train.py -c ./ckpt-fp32

--nproc_per_node

!python eval.py -c ./ckpt-fp32 -e 80

import time

start_time = time.time()

!colossalai run --nproc_per_node 1 train.py -c ./ckpt-fp32

end_time = time.time()

elapsed_time = end_time - start_time
print(f"ColossalAI Training took {elapsed_time:.2f} seconds.")

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import torchvision.models as models

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=2)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=2)

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
net = models.resnet18(pretrained=False)
net = net.to(device)

criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

import time

start_time = time.time()

for epoch in range(80):  # 80エポックで学習
    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        inputs, labels = data[0].to(device), data[1].to(device)

        optimizer.zero_grad()

        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 2000 == 1999:  # 2000ミニバッチごとに表示
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

end_time = time.time()

elapsed_time = end_time - start_time
print(f"PyTorch Training took {elapsed_time:.2f} seconds.")

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data[0].to(device), data[1].to(device)
        outputs = net(images)
        _, predicted = outputs.max(1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))