Some checks failed
Self-hosted runner (nightly-past-ci-caller) / Get number (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.11 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.10 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.9 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.8 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.7 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.6 (push) Has been cancelled
Self-hosted runner (nightly-past-ci-caller) / TensorFlow 2.5 (push) Has been cancelled
Self-hosted runner (benchmark) / Benchmark (aws-g5-4xlarge-cache) (push) Has been cancelled
Build documentation / build (push) Has been cancelled
Build documentation / build_other_lang (push) Has been cancelled
CodeQL Security Analysis / CodeQL Analysis (push) Has been cancelled
New model PR merged notification / Notify new model (push) Has been cancelled
PR CI / pr-ci (push) Has been cancelled
Slow tests on important models (on Push - A10) / Get all modified files (push) Has been cancelled
Secret Leaks / trufflehog (push) Has been cancelled
Update Transformers metadata / build_and_package (push) Has been cancelled
Slow tests on important models (on Push - A10) / Model CI (push) Has been cancelled
Check Tiny Models / Check tiny models (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Model CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Pipeline CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Example CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / DeepSpeed CI (push) Has been cancelled
Self-hosted runner (Intel Gaudi3 scheduled CI caller) / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI - Flash Attn / Setup (push) Has been cancelled
Nvidia CI - Flash Attn / Model CI (push) Has been cancelled
Nvidia CI / Setup (push) Has been cancelled
Nvidia CI / Model CI (push) Has been cancelled
Nvidia CI / Torch pipeline CI (push) Has been cancelled
Nvidia CI / Example CI (push) Has been cancelled
Nvidia CI / Trainer/FSDP CI (push) Has been cancelled
Nvidia CI / DeepSpeed CI (push) Has been cancelled
Nvidia CI / Quantization CI (push) Has been cancelled
Nvidia CI / Kernels CI (push) Has been cancelled
Doctests / Setup (push) Has been cancelled
Doctests / Call doctest jobs (push) Has been cancelled
Doctests / Send results to webhook (push) Has been cancelled
Extras Smoke Test / Get supported Python versions (push) Has been cancelled
Extras Smoke Test / Test extras on Python ${{ matrix.python-version }} (push) Has been cancelled
Extras Smoke Test / Check Slack token availability (push) Has been cancelled
Extras Smoke Test / Notify failures to Slack (push) Has been cancelled
Self-hosted runner (AMD scheduled CI caller) / Trigger Scheduled AMD CI (push) Has been cancelled
Stale Bot / Close Stale Issues (push) Has been cancelled
53 lines
1.4 KiB
Python
53 lines
1.4 KiB
Python
import json
|
|
import logging
|
|
import os
|
|
import subprocess
|
|
from argparse import ArgumentParser
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def parse_args():
|
|
parser = ArgumentParser()
|
|
parsed, unknown = parser.parse_known_args()
|
|
for arg in unknown:
|
|
if arg.startswith(("-", "--")):
|
|
parser.add_argument(arg.split("=")[0])
|
|
|
|
return parser.parse_args()
|
|
|
|
|
|
def main():
|
|
args = parse_args()
|
|
port = 8888
|
|
num_gpus = int(os.environ["SM_NUM_GPUS"])
|
|
hosts = json.loads(os.environ["SM_HOSTS"])
|
|
num_nodes = len(hosts)
|
|
current_host = os.environ["SM_CURRENT_HOST"]
|
|
rank = hosts.index(current_host)
|
|
os.environ["NCCL_DEBUG"] = "INFO"
|
|
|
|
if num_nodes > 1:
|
|
cmd = f"""python -m torch.distributed.launch \
|
|
--nnodes={num_nodes} \
|
|
--node_rank={rank} \
|
|
--nproc_per_node={num_gpus} \
|
|
--master_addr={hosts[0]} \
|
|
--master_port={port} \
|
|
./run_glue.py \
|
|
{"".join([f" --{parameter} {value}" for parameter, value in args.__dict__.items()])}"""
|
|
else:
|
|
cmd = f"""python -m torch.distributed.launch \
|
|
--nproc_per_node={num_gpus} \
|
|
./run_glue.py \
|
|
{"".join([f" --{parameter} {value}" for parameter, value in args.__dict__.items()])}"""
|
|
try:
|
|
subprocess.run(cmd, shell=True)
|
|
except Exception as e:
|
|
logger.info(e)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|