swe_bench_verified end-to-end verified (oracle patch -> official sweb image -> resolved); image naming mapped to local swebench/ set; ladder2 complete 28/28
This commit is contained in:
parent
3d16e9647a
commit
0e1e31ba10
@ -19,10 +19,17 @@ from ..spec import DatasetSpec
|
|||||||
def swe_bench_verified():
|
def swe_bench_verified():
|
||||||
def to_sample(record: dict) -> Sample:
|
def to_sample(record: dict) -> Sample:
|
||||||
instance_id = record['instance_id']
|
instance_id = record['instance_id']
|
||||||
|
# image naming: local swebench/ set uses {repo}_1776_{repo}-{num}; the
|
||||||
|
# newer official layout is sweb.eval.x86_64.{repo}__{repo}-{num}
|
||||||
|
img = f'sweb.eval.x86_64.{instance_id}'
|
||||||
|
if '__' in instance_id:
|
||||||
|
repo, num = instance_id.rsplit('-', 1)
|
||||||
|
r = repo.split('__')[0]
|
||||||
|
img = f'swebench/sweb.eval.x86_64.{r}_1776_{r.split("__")[-1]}-{num}'
|
||||||
return Sample(
|
return Sample(
|
||||||
input=record['problem_statement'],
|
input=record['problem_statement'],
|
||||||
target=record['patch'], # gold patch (for oracle/oracle-check only)
|
target=record['patch'], # gold patch (for oracle/oracle-check only)
|
||||||
sandbox=SandboxSpec(image=f'sweb.eval.x86_64.{instance_id}'), # official image naming
|
sandbox=SandboxSpec(image=img),
|
||||||
metadata={
|
metadata={
|
||||||
'instance_id': instance_id,
|
'instance_id': instance_id,
|
||||||
'repo': record['repo'],
|
'repo': record['repo'],
|
||||||
|
|||||||
Loading…
x
Reference in New Issue
Block a user