b3a61e8ce2
* use tensorboard to see if resume from checkpoint works * make sure e2e test is either fp16 or bf16 * set max_steps and save limit so we have the checkpoint when testing resuming * fix test parameters
34 lines
797 B
Python
34 lines
797 B
Python
"""
|
|
helper utils for tests
|
|
"""
|
|
import os
|
|
import shutil
|
|
import tempfile
|
|
from functools import wraps
|
|
from pathlib import Path
|
|
|
|
|
|
def with_temp_dir(test_func):
|
|
@wraps(test_func)
|
|
def wrapper(*args, **kwargs):
|
|
# Create a temporary directory
|
|
temp_dir = tempfile.mkdtemp()
|
|
try:
|
|
# Pass the temporary directory to the test function
|
|
test_func(*args, temp_dir=temp_dir, **kwargs)
|
|
finally:
|
|
# Clean up the directory after the test
|
|
shutil.rmtree(temp_dir)
|
|
|
|
return wrapper
|
|
|
|
|
|
def most_recent_subdir(path):
|
|
base_path = Path(path)
|
|
subdirectories = [d for d in base_path.iterdir() if d.is_dir()]
|
|
if not subdirectories:
|
|
return None
|
|
subdir = max(subdirectories, key=os.path.getctime)
|
|
|
|
return subdir
|