import os
import platform
import argparse
import time
import math
import warnings
import torch
import pandas as pd
import torch.nn.functional as F
from contextlib import nullcontext
from torch import optim
from transformers import AutoTokenizer
from transformers import AutoModelForCausalLM
from peft import get_peft_model, LoraConfig, TaskType
from torch.utils.data import DataLoader
from model.LMConfig import LMConfig
from model.dataset import SFTDataset
warnings.filterwarnings('ignore')
def Logger(content):
print(content)
def get_lr(it, all):
warmup_iters = args.warmup_iters
lr_decay_iters = all
min_lr = args.learning_rate / 10
if it < warmup_iters:
return args.learning_rate * it / warmup_iters
if it > lr_decay_iters:
return min_lr
decay_ratio = (it - warmup_iters) / (lr_decay_iters - warmup_iters)
assert 0 <= decay_ratio <= 1
coeff = 0.5 * (1.0 + math.cos(math.pi * decay_ratio))
return min_lr + coeff * (args.learning_rate - min_lr)
def train_epoch(epoch, wandb):
start_time = time.time()
for step, (X, Y, loss_mask) in enumerate(train_loader):
X = X.to(args.device)
Y = Y.to(args.device)
loss_mask = loss_mask.to(args.device)
lr = get_lr(epoch * iter_per_epoch + step, args.epochs * iter_per_epoch)
for param_group in optimizer.param_groups:
param_group['lr'] = lr
with ctx:
logits = model(X, Y).logits
loss = F.cross_entropy(logits.view(-1, logits.size(-1)), Y.view(-1), ignore_index=0, reduction='none')
loss_mask = loss_mask.view(-1)
loss = torch.sum(loss * loss_mask) / loss_mask.sum()
loss = loss / args.accumulation_steps
scaler.scale(loss).backward()
if (step + 1) % args.accumulation_steps == 0:
scaler.unscale_(optimizer)
torch.nn.utils.clip_grad_norm_(model.parameters(), args.grad_clip)
scaler.step(optimizer)
scaler.update()
optimizer.zero_grad(set_to_none=True)
if step % args.log_interval == 0:
spend_time = time.time() - start_time
Logger(
'Epoch:[{}/{}]({}/{}) loss:{:.3f} lr:{:.7f} epoch_Time:{}min:'.format(
epoch,
args.epochs,
step,
iter_per_epoch,
loss.item() * args.accumulation_steps,
optimizer.param_groups[-1]['lr'],
spend_time / (step + 1) * iter_per_epoch // 60 - spend_time // 60))
if wandb is not None:
wandb.log({"loss": loss.item() * args.accumulation_steps,
"lr": optimizer.param_groups[-1]['lr'],
"epoch_Time": spend_time / (step + 1) * iter_per_epoch // 60 - spend_time // 60})
if (step + 1) % args.save_interval == 0:
model.save_pretrained(args.save_dir)
def find_all_linear_names(model):
cls = torch.nn.Linear
lora_module_names = set()
for name, module in model.named_modules():
if isinstance(module, cls):
names = name.split('.')
lora_module_names.add(names[0] if len(names) == 1 else names[-1])
if 'lm_head' in lora_module_names:
lora_module_names.remove('lm_head')
return list(lora_module_names)
def init_model():
model_name_or_path = "./minimind-v1-small"
tokenizer_name_or_path = "./minimind-v1-small"
tokenizer = AutoTokenizer.from_pretrained(tokenizer_name_or_path, trust_remote_code=True, use_fast=False)
model = AutoModelForCausalLM.from_pretrained(model_name_or_path, trust_remote_code=True).to(args.device)
target_modules = find_all_linear_names(model)
peft_config = LoraConfig(
task_type=TaskType.CAUSAL_LM,
r=8,
lora_alpha=16,
lora_dropout=0.1,
inference_mode=False,
target_modules=target_modules
)
model = get_peft_model(model, peft_config)
model.print_trainable_parameters()
model = model.to(args.device)
return model, tokenizer
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="MiniMind LoRA Fine-tuning")
parser.add_argument("--out_dir", type=str, default="out", help="Output directory")
parser.add_argument("--epochs", type=int, default=20, help="Number of epochs")
parser.add_argument("--batch_size", type=int, default=16, help="Batch size")
parser.add_argument("--learning_rate", type=float, default=1e-4, help="Learning rate")
parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu", help="Device to use")
parser.add_argument("--dtype", type=str, default="bfloat16", help="Data type")
parser.add_argument("--use_wandb", action="store_true", help="Use Weights & Biases")
parser.add_argument("--wandb_project", type=str, default="MiniMind-LoRA", help="Weights & Biases project name")
parser.add_argument("--num_workers", type=int, default=0, help="Number of workers for data loading")
parser.add_argument("--accumulation_steps", type=int, default=1, help="Gradient accumulation steps")
parser.add_argument("--grad_clip", type=float, default=1.0, help="Gradient clipping threshold")
parser.add_argument("--warmup_iters", type=int, default=1000, help="Number of warmup iterations")
parser.add_argument("--log_interval", type=int, default=100, help="Logging interval")
parser.add_argument("--save_interval", type=int, default=1000, help="Model saving interval")
args = parser.parse_args()
lm_config = LMConfig()
max_seq_len = lm_config.max_seq_len
args.save_dir = os.path.join(args.out_dir)
os.makedirs(args.save_dir, exist_ok=True)
os.makedirs(args.out_dir, exist_ok=True)
tokens_per_iter = args.batch_size * max_seq_len
torch.manual_seed(1337)
device_type = "cuda" if "cuda" in args.device else "cpu"
args.wandb_run_name = f"MiniMind-LoRA-Epoch-{args.epochs}-BatchSize-{args.batch_size}-LearningRate-{args.learning_rate}"
ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast()
if args.use_wandb:
import wandb
wandb.init(project=args.wandb_project, name=args.wandb_run_name)
else:
wandb = None
model, tokenizer = init_model()
df = pd.read_csv('./dataset/sft_data.csv')
df = df.sample(frac=1.0)
train_ds = SFTDataset(df, tokenizer, max_length=max_seq_len)
train_loader = DataLoader(
train_ds,
batch_size=args.batch_size,
pin_memory=True,
drop_last=False,
shuffle=False,
num_workers=args.num_workers,
)
scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype in ['float16', 'bfloat16']))
optimizer = optim.Adam(model.parameters(), lr=args.learning_rate)
if False and platform.system() != 'Windows' and float(torch.__version__.split('.')[0]) >= 2:
Logger("compiling the model... (takes a ~minute)")
unoptimized_model = model
model = torch.compile(model)
iter_per_epoch = len(train_loader)
for epoch in range(args.epochs):
train_epoch(epoch, wandb)