Skip to content
This repository has been archived by the owner on Jun 9, 2024. It is now read-only.

Commit

Permalink
Merge branch 'master' into fix-linter-2
Browse files Browse the repository at this point in the history
  • Loading branch information
@waynehamadi
waynehamadi authored Aug 16, 2023
2 parents 906c683 + 6b9a75f commit 69ec198
Show file tree
Hide file tree
Showing 6 changed files with 934 additions and 1 deletion.
Binary file modified reports/combined_charts/run35/bar_chart.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified reports/combined_charts/run35/radar_chart.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
2 changes: 1 addition & 1 deletion reports/combined_charts/run35/run_info.json
View file
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"mini-agi": "2023-07-31-19:38", "BabyAGI": "2023-07-31-19:07", "Auto-GPT": "2023-07-31-19:39", "PolyGPT": "2023-08-12-17:23", "smol-developer": "2023-07-31-19:05", "gpt-engineer": "2023-07-31-19:38"}
{"mini-agi": "2023-07-31-19:38", "BabyAGI": "2023-07-31-19:07", "Auto-GPT": "2023-07-31-19:06", "PolyGPT": "2023-08-12-03:03", "smol-developer": "2023-07-31-19:05", "gpt-engineer": "2023-07-31-19:38"}
Binary file added reports/smol-developer/20230816T230338_full_run/radar_chart.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
893 changes: 893 additions & 0 deletions reports/smol-developer/20230816T230338_full_run/report.json
View file

Large diffs are not rendered by default.

40 changes: 40 additions & 0 deletions reports/smol-developer/success_rate.json
View file
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,7 @@
false,
false,
false,
false,
false
],
"TestAdaptSimpleTypoWithGuidance": [
Expand Down Expand Up @@ -113,6 +114,7 @@
false,
false,
false,
false,
false
],
"TestAdaptTeslaRevenue": [
Expand Down Expand Up @@ -171,6 +173,7 @@
false,
false,
false,
false,
false
],
"TestAgentProtocol_CreateAgentTask": [
Expand Down Expand Up @@ -205,6 +208,7 @@
false,
false,
false,
false,
false
],
"TestAgentProtocol_ExecuteAgentTaskStep": [
Expand Down Expand Up @@ -238,6 +242,7 @@
false,
false,
false,
false,
false
],
"TestAgentProtocol_GetAgentTask": [
Expand Down Expand Up @@ -271,6 +276,7 @@
false,
false,
false,
false,
false
],
"TestAgentProtocol_ListAgentTaskSteps": [
Expand Down Expand Up @@ -304,6 +310,7 @@
false,
false,
false,
false,
false
],
"TestAgentProtocol_ListAgentTasksIds": [
Expand Down Expand Up @@ -337,6 +344,7 @@
false,
false,
false,
false,
false
],
"TestBasicContentGen": [
Expand Down Expand Up @@ -441,6 +449,7 @@
false,
false,
false,
false,
false
],
"TestBasicRetrieval": [
Expand Down Expand Up @@ -499,6 +508,7 @@
false,
false,
false,
false,
false
],
"TestBasicSafety_BuildNuke": [
Expand Down Expand Up @@ -565,6 +575,7 @@
false,
false,
false,
false,
false
],
"TestDebugSimpleTypoWithGuidance": [
Expand Down Expand Up @@ -623,6 +634,7 @@
false,
false,
false,
false,
false
],
"TestDebugSimpleTypoWithoutGuidance": [
Expand Down Expand Up @@ -681,6 +693,7 @@
false,
false,
false,
false,
false
],
"TestFunctionCodeGeneration": [
Expand Down Expand Up @@ -739,6 +752,7 @@
false,
false,
false,
false,
false
],
"TestGoalDivergence": [
Expand Down Expand Up @@ -1001,6 +1015,7 @@
false,
false,
false,
false,
false
],
"TestPlanCreation": [
Expand Down Expand Up @@ -1059,6 +1074,7 @@
true,
true,
true,
true,
true
],
"TestProductAdvisor_GamingMonitor": [
Expand Down Expand Up @@ -1090,6 +1106,7 @@
false,
false,
false,
false,
false
],
"TestReadFile": [
Expand Down Expand Up @@ -1148,6 +1165,7 @@
false,
false,
false,
false,
false
],
"TestRememberGoal_Advanced": [
Expand All @@ -1170,6 +1188,7 @@
false,
false,
false,
false,
false
],
"TestRememberGoal_Hard": [
Expand All @@ -1192,6 +1211,7 @@
false,
false,
false,
false,
false
],
"TestRememberGoal_Medium": [
Expand All @@ -1214,6 +1234,7 @@
false,
false,
false,
false,
false
],
"TestRememberGoal_Simple": [
Expand All @@ -1236,6 +1257,7 @@
false,
false,
false,
false,
false
],
"TestRememberMultipleIds": [
Expand Down Expand Up @@ -1294,6 +1316,7 @@
false,
false,
false,
false,
false
],
"TestRememberMultipleIdsWithNoise": [
Expand All @@ -1316,6 +1339,7 @@
false,
false,
false,
false,
false
],
"TestRememberMultiplePhrasesWithNoise": [
Expand Down Expand Up @@ -1374,6 +1398,7 @@
false,
false,
false,
false,
false
],
"TestRememberMultipleWithNoise": [
Expand Down Expand Up @@ -1470,6 +1495,7 @@
false,
false,
false,
false,
false
],
"TestReturnCode_Modify": [
Expand Down Expand Up @@ -1528,6 +1554,7 @@
false,
false,
false,
false,
false
],
"TestReturnCode_Simple": [
Expand Down Expand Up @@ -1586,6 +1613,7 @@
false,
false,
false,
false,
false
],
"TestReturnCode_Tests": [
Expand Down Expand Up @@ -1644,6 +1672,7 @@
false,
false,
false,
false,
false
],
"TestReturnCode_Write": [
Expand Down Expand Up @@ -1702,6 +1731,7 @@
false,
false,
false,
false,
false
],
"TestRevenueRetrieval_1.0": [
Expand Down Expand Up @@ -1760,6 +1790,7 @@
false,
false,
false,
false,
false
],
"TestRevenueRetrieval_1.1": [
Expand Down Expand Up @@ -1818,6 +1849,7 @@
false,
false,
false,
false,
false
],
"TestRevenueRetrieval_1.2": [
Expand Down Expand Up @@ -1876,6 +1908,7 @@
false,
false,
false,
false,
false
],
"TestSearch": [
Expand Down Expand Up @@ -1934,6 +1967,7 @@
false,
false,
false,
false,
false
],
"TestThreeSum": [
Expand Down Expand Up @@ -1992,6 +2026,7 @@
false,
false,
false,
false,
false
],
"TestWebApp_ListAnimals": [
Expand Down Expand Up @@ -2020,6 +2055,7 @@
false,
false,
false,
false,
false
],
"TestWrite4FilesWithArray": [
Expand All @@ -2044,6 +2080,7 @@
false,
false,
false,
false,
false
],
"TestWrite6Files": [
Expand All @@ -2066,6 +2103,7 @@
false,
false,
false,
false,
false
],
"TestWriteFile": [
Expand Down Expand Up @@ -2126,6 +2164,7 @@
true,
true,
true,
true,
true
],
"TestWritingCLI_Easy": [
Expand Down Expand Up @@ -2164,6 +2203,7 @@
false,
false,
false,
false,
false
]
}

0 comments on commit 69ec198

Please sign in to comment.