209 lines
8.1 KiB
Python
209 lines
8.1 KiB
Python
import os
|
||
import platform
|
||
import argparse
|
||
import time
|
||
import math
|
||
import warnings
|
||
|
||
import pandas as pd
|
||
import torch
|
||
import torch.nn.functional as F
|
||
import torch.distributed as dist
|
||
from contextlib import nullcontext
|
||
|
||
from torch import optim, nn
|
||
from torch.nn.parallel import DistributedDataParallel
|
||
from torch.utils.data import DataLoader, DistributedSampler
|
||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
from model.model import MiniMindLM
|
||
from model.LMConfig import LMConfig
|
||
from model.dataset import SFTDataset
|
||
|
||
warnings.filterwarnings('ignore')
|
||
|
||
|
||
def Logger(content):
|
||
if not ddp or dist.get_rank() == 0:
|
||
print(content)
|
||
|
||
|
||
def get_lr(current_step, total_steps, lr):
|
||
return lr / 10 + 0.5 * lr * (1 + math.cos(math.pi * current_step / total_steps))
|
||
|
||
|
||
def train_epoch(epoch, wandb):
|
||
# 思考标签占位符
|
||
start_of_think_ids = tokenizer('<think>').input_ids
|
||
end_of_think_ids = tokenizer('</think>').input_ids
|
||
start_of_answer_ids = tokenizer('</answer>').input_ids
|
||
end_of_answer_ids = tokenizer('</answer>').input_ids
|
||
loss_fct = nn.CrossEntropyLoss(reduction='none')
|
||
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, args.learning_rate)
|
||
for param_group in optimizer.param_groups:
|
||
param_group['lr'] = lr
|
||
|
||
with ctx:
|
||
res = model(X)
|
||
loss = loss_fct(
|
||
res.logits.view(-1, res.logits.size(-1)),
|
||
Y.view(-1)
|
||
).view(Y.size())
|
||
sp_ids = torch.isin(Y.view(-1),
|
||
torch.tensor(start_of_think_ids + end_of_think_ids
|
||
+ start_of_answer_ids + end_of_answer_ids
|
||
).to(args.device))
|
||
# 在 sp_ids 对应的位置增加额外的惩罚
|
||
loss_mask = loss_mask.view(-1)
|
||
loss_mask_sum = loss_mask.sum()
|
||
loss_mask[sp_ids] = 10
|
||
loss_mask = loss_mask.view(Y.size())
|
||
loss = (loss * loss_mask).sum() / loss_mask_sum
|
||
loss += res.aux_loss
|
||
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:{:.12f} epoch_Time:{}min:'.format(
|
||
epoch + 1,
|
||
args.epochs,
|
||
step,
|
||
iter_per_epoch,
|
||
loss.item(),
|
||
optimizer.param_groups[-1]['lr'],
|
||
spend_time / (step + 1) * iter_per_epoch // 60 - spend_time // 60))
|
||
|
||
if (wandb is not None) and (not ddp or dist.get_rank() == 0):
|
||
wandb.log({"loss": loss,
|
||
"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 and (not ddp or dist.get_rank() == 0):
|
||
model.eval()
|
||
moe_path = '_moe' if lm_config.use_moe else ''
|
||
ckp = f'{args.save_dir}/reason_{lm_config.dim}{moe_path}.pth'
|
||
|
||
if isinstance(model, torch.nn.parallel.DistributedDataParallel):
|
||
state_dict = model.module.state_dict()
|
||
else:
|
||
state_dict = model.state_dict()
|
||
|
||
torch.save(state_dict, ckp)
|
||
model.train()
|
||
|
||
|
||
def init_model(lm_config):
|
||
tokenizer = AutoTokenizer.from_pretrained('./model/minimind_tokenizer')
|
||
model = MiniMindLM(lm_config)
|
||
moe_path = '_moe' if lm_config.use_moe else ''
|
||
ckp = f'./out/rlhf_{lm_config.dim}{moe_path}.pth'
|
||
state_dict = torch.load(ckp, map_location=args.device)
|
||
model.load_state_dict(state_dict, strict=False)
|
||
Logger(f'LLM总参数量：{sum(p.numel() for p in model.parameters() if p.requires_grad) / 1e6:.3f} 百万')
|
||
model = model.to(args.device)
|
||
return model, tokenizer
|
||
|
||
|
||
def init_distributed_mode():
|
||
if not ddp: return
|
||
global ddp_local_rank, DEVICE
|
||
|
||
dist.init_process_group(backend="nccl")
|
||
ddp_rank = int(os.environ["RANK"])
|
||
ddp_local_rank = int(os.environ["LOCAL_RANK"])
|
||
ddp_world_size = int(os.environ["WORLD_SIZE"])
|
||
DEVICE = f"cuda:{ddp_local_rank}"
|
||
torch.cuda.set_device(DEVICE)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
parser = argparse.ArgumentParser(description="MiniMind Distill Reasoning")
|
||
parser.add_argument("--out_dir", type=str, default="out")
|
||
parser.add_argument("--epochs", type=int, default=1)
|
||
parser.add_argument("--batch_size", type=int, default=8)
|
||
parser.add_argument("--learning_rate", type=float, default=1e-6)
|
||
parser.add_argument("--device", type=str, default="cuda:0" if torch.cuda.is_available() else "cpu")
|
||
parser.add_argument("--dtype", type=str, default="bfloat16")
|
||
parser.add_argument("--use_wandb", action="store_true")
|
||
parser.add_argument("--wandb_project", type=str, default="MiniMind-Full-SFT")
|
||
parser.add_argument("--num_workers", type=int, default=1)
|
||
parser.add_argument("--ddp", action="store_true")
|
||
parser.add_argument("--accumulation_steps", type=int, default=1)
|
||
parser.add_argument("--grad_clip", type=float, default=1.0)
|
||
parser.add_argument("--warmup_iters", type=int, default=0)
|
||
parser.add_argument("--log_interval", type=int, default=1)
|
||
parser.add_argument("--save_interval", type=int, default=50)
|
||
parser.add_argument('--local_rank', type=int, default=-1)
|
||
parser.add_argument('--dim', default=512, type=int)
|
||
parser.add_argument('--n_layers', default=8, type=int)
|
||
parser.add_argument('--max_seq_len', default=1024, type=int)
|
||
parser.add_argument('--use_moe', default=False, type=bool)
|
||
parser.add_argument("--data_path", type=str, default="./dataset/r1_mix_1024.jsonl")
|
||
|
||
args = parser.parse_args()
|
||
|
||
lm_config = LMConfig(dim=args.dim, n_layers=args.n_layers, max_seq_len=args.max_seq_len, use_moe=args.use_moe)
|
||
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 * lm_config.max_seq_len
|
||
torch.manual_seed(1337)
|
||
device_type = "cuda" if "cuda" in args.device else "cpu"
|
||
|
||
args.wandb_run_name = f"MiniMind-Distill-Reasoning-Epoch-{args.epochs}-BatchSize-{args.batch_size}-LearningRate-{args.learning_rate}"
|
||
|
||
ctx = nullcontext() if device_type == "cpu" else torch.cuda.amp.autocast()
|
||
ddp = int(os.environ.get("RANK", -1)) != -1 # is this a ddp run?
|
||
ddp_local_rank, DEVICE = 0, "cuda:0"
|
||
if ddp:
|
||
init_distributed_mode()
|
||
args.device = torch.device(DEVICE)
|
||
|
||
if args.use_wandb and (not ddp or ddp_local_rank == 0):
|
||
import wandb
|
||
|
||
wandb.init(project=args.wandb_project, name=args.wandb_run_name)
|
||
else:
|
||
wandb = None
|
||
|
||
model, tokenizer = init_model(lm_config)
|
||
|
||
train_ds = SFTDataset(args.data_path, tokenizer, max_length=lm_config.max_seq_len)
|
||
train_sampler = DistributedSampler(train_ds) if ddp else None
|
||
train_loader = DataLoader(
|
||
train_ds,
|
||
batch_size=args.batch_size,
|
||
pin_memory=True,
|
||
drop_last=False,
|
||
shuffle=False,
|
||
num_workers=args.num_workers,
|
||
sampler=train_sampler
|
||
)
|
||
|
||
scaler = torch.cuda.amp.GradScaler(enabled=(args.dtype in ['float16', 'bfloat16']))
|
||
optimizer = optim.AdamW(model.parameters(), lr=args.learning_rate)
|
||
|
||
if ddp:
|
||
model._ddp_params_and_buffers_to_ignore = {"pos_cis"}
|
||
model = DistributedDataParallel(model, device_ids=[ddp_local_rank])
|
||
|
||
iter_per_epoch = len(train_loader)
|
||
for epoch in range(args.epochs):
|
||
train_epoch(epoch, wandb)
|