scripts/train.py

from pathlib import Path
import sys,os,numpy as np,torch;import torch.distributed as dist
from torch.nn.parallel import DistributedDataParallel as DDP
R=Path(__file__).resolve().parents[1];sys.path.insert(0,str(R));from model.weatherbench2 import *
c=cfg(R);rank=int(os.getenv('RANK',0));world=int(os.getenv('WORLD_SIZE',1));ddp=world>1
if ddp:dist.init_process_group('gloo')
d=np.load(R/c['data']['path']);base=WB2Baseline(**c['model']);m=DDP(base) if ddp else base;opt=torch.optim.Adam(m.parameters(),lr=c['train']['lr']);ids=np.arange(rank,len(d['input']),world);loss=((m(torch.tensor(d['input'][ids]))-torch.tensor(d['target'][ids]))**2).mean();opt.zero_grad();loss.backward();opt.step();v=loss.detach().double()
if ddp:dist.all_reduce(v);v/=world
p=R/c['paths']['checkpoint']
if rank==0:p.parent.mkdir(parents=True,exist_ok=True);torch.save({'model':base.state_dict(),'model_config':c['model']},p);write(R/c['paths']['training_metrics'],{'mse':float(v),'world_size':world});print(p)
if ddp:dist.destroy_process_group()