archive historical results and add token budget logs

This commit is contained in:
pj committed 2026-09-25 22:07:26 +05:30
1 parent 638e978227
commit e94b75c6f5
813 files changed
+12631 -410710

No files matched your search

@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.astropy_1776_astropy-7336:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-11066:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-11163:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-11206:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-13512:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-13794:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-14140:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-14534:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-15268:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-15525:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.django_1776_django-15973:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.matplotlib_1776_matplotlib-26291:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.pydata_1776_xarray-6721:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.pytest-dev_1776_pytest-5631:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.scikit-learn_1776_scikit-learn-13779:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-11445:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.sphinx-doc_1776_sphinx-8269:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.sympy_1776_sympy-16450:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.sympy_1776_sympy-19783:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none
@@ -0,0 +1,7 @@
services:
default:
image: swebench/sweb.eval.x86_64.sympy_1776_sympy-21379:latest
command: sleep infinity
working_dir: /testbed
mem_limit: 8g
network_mode: none