| import os,subprocess,json,time,sys |
| from pathlib import Path |
| root=Path('/data/nyako-training-150'); art=root/'artifacts' |
| env=os.environ.copy();env['PYTHONUNBUFFERED']='1';env['TOKENIZERS_PARALLELISM']='false';env['OMP_NUM_THREADS']='8' |
| cmd=[str(root/'venv/bin/python'),'scripts/dev/anima_train_network.py','--config_file',str(art/'config/train.toml')] |
| (art/'config/launch.json').write_text(json.dumps({'command':cmd,'cwd':str(root/'lora-scripts-next')},indent=2)) |
| (art/'config/trainer_commit.txt').write_bytes(subprocess.check_output(['git','rev-parse','HEAD'],cwd=root/'lora-scripts-next')) |
| with (art/'config/packages.txt').open('w') as f:subprocess.run([str(root/'venv/bin/pip'),'freeze'],stdout=f) |
| (root/'status.json').write_text(json.dumps({'stage':'training','started':time.time()})) |
| with (art/'logs/train.log').open('w') as f: |
| result=subprocess.run(cmd,cwd=root/'lora-scripts-next',env=env,stdout=f,stderr=subprocess.STDOUT) |
| (root/'status.json').write_text(json.dumps({'stage':'training_finished' if result.returncode==0 else 'training_failed','returncode':result.returncode,'time':time.time()})) |
| if result.returncode: sys.exit(result.returncode) |
| subprocess.run([str(root/'venv/bin/python'),str(root/'scripts/upload.py')],check=True,env=env) |
|
|
