mirror of
https://github.com/deepspeedai/DeepSpeed.git
synced 2025-10-20 15:33:51 +08:00
fix typo s/1014 /1024 (#7528)
fix typo s/1014 /1024 s/was_interruptted /was_interrupted detail info modified: deepspeed/autotuning/scheduler.py modified: deepspeed/autotuning/utils.py Co-authored-by: Olatunji Ruwase <tunji.ruwase@snowflake.com>
This commit is contained in:
@ -18,7 +18,7 @@ from tqdm import tqdm
|
|||||||
|
|
||||||
from ..utils import logger
|
from ..utils import logger
|
||||||
from .constants import AUTOTUNING, AUTOTUNING_METRIC_PATH, BUFSIZE
|
from .constants import AUTOTUNING, AUTOTUNING_METRIC_PATH, BUFSIZE
|
||||||
from .utils import get_val_by_key, search_error, was_interruptted
|
from .utils import get_val_by_key, search_error, was_interrupted
|
||||||
"""
|
"""
|
||||||
thread-0: loop over experiment queue dispatching experiments if they become available
|
thread-0: loop over experiment queue dispatching experiments if they become available
|
||||||
thread-N: start each experiment in its own thread
|
thread-N: start each experiment in its own thread
|
||||||
@ -76,7 +76,7 @@ class ResourceManager:
|
|||||||
|
|
||||||
# skip existing experiments (except for the ones that were interrupted)
|
# skip existing experiments (except for the ones that were interrupted)
|
||||||
if os.path.exists(result_dir) and os.path.exists(stderr_file):
|
if os.path.exists(result_dir) and os.path.exists(stderr_file):
|
||||||
if not was_interruptted(stderr_file):
|
if not was_interrupted(stderr_file):
|
||||||
err = search_error(stderr_file)
|
err = search_error(stderr_file)
|
||||||
exp_id = exp["exp_id"]
|
exp_id = exp["exp_id"]
|
||||||
self.finished_experiments[exp_id] = (exp, err)
|
self.finished_experiments[exp_id] = (exp, err)
|
||||||
|
@ -26,7 +26,7 @@ def search_error(filename):
|
|||||||
return None
|
return None
|
||||||
|
|
||||||
|
|
||||||
def was_interruptted(filename):
|
def was_interrupted(filename):
|
||||||
if not os.path.exists(filename):
|
if not os.path.exists(filename):
|
||||||
return "stderr.log does not exist"
|
return "stderr.log does not exist"
|
||||||
with open(filename) as f:
|
with open(filename) as f:
|
||||||
@ -422,7 +422,7 @@ def memory_to_string(n, postfix="", units=None, precision=2):
|
|||||||
elif n // 10**6 > 0:
|
elif n // 10**6 > 0:
|
||||||
return str(round(n / 1024**2, precision)) + " M" + postfix
|
return str(round(n / 1024**2, precision)) + " M" + postfix
|
||||||
elif n // 10**3 > 0:
|
elif n // 10**3 > 0:
|
||||||
return str(round(n / 1014, precision)) + " K" + postfix
|
return str(round(n / 1024, precision)) + " K" + postfix
|
||||||
else:
|
else:
|
||||||
return str(n) + " "
|
return str(n) + " "
|
||||||
else:
|
else:
|
||||||
|
Reference in New Issue
Block a user