ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2026-04-20 14:37:40 +00:00
commit 1a6c5886fb
1 changed files with 8 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

14
scripts/benchmarks/compare_grpo_runs.py
View file

@ -39,8 +39,9 @@ def _diff(a, b):
if not a or not b:
return None
n = min(len(a), len(b))
diffs = [abs(a[i] - b[i]) for i in range(n)
if a[i] is not None and b[i] is not None]
diffs = [
abs(a[i] - b[i]) for i in range(n) if a[i] is not None and b[i] is not None
]
if not diffs:
return None
return {
@ -52,12 +53,13 @@ def _diff(a, b):
def main():
p = argparse.ArgumentParser()
p.add_argument("--ref", required=True)
p.add_argument("--candidate", required=True)
p.add_argument("--ref", required = True)
p.add_argument("--candidate", required = True)
args = p.parse_args()
from torch_debugging_utils import compare_training_runs
base = compare_training_runs(args.ref, args.candidate, loss_tol=1e-3, grad_tol=1e-3)
base = compare_training_runs(args.ref, args.candidate, loss_tol = 1e-3, grad_tol = 1e-3)
ref_a = _arrays(args.ref)
cand_a = _arrays(args.candidate)
@ -71,7 +73,7 @@ def main():
"kl_diff": extras["kl"],
"time_diff_ms": extras["time_ms"],
}
print(json.dumps(out, indent=2))
print(json.dumps(out, indent = 2))
if __name__ == "__main__":