From 8e63522012d2b7f8b226aa2cecfbe0477d88eac4 Mon Sep 17 00:00:00 2001 From: Ayush Maniar Date: Sat, 8 Mar 2025 15:55:01 -0800 Subject: [PATCH] Stop tracking results files --- .gitignore | 3 ++- .../results.txt | 25 ------------------- ..._craft_better_tasks_03-02_07-15results.txt | 21 ---------------- results/clauderesults.txt | 21 ---------------- 4 files changed, 2 insertions(+), 68 deletions(-) delete mode 100644 results/4o_craft_better_tasks_03-02_07-15/results.txt delete mode 100644 results/4o_craft_better_tasks_03-02_07-15results.txt delete mode 100644 results/clauderesults.txt diff --git a/.gitignore b/.gitignore index 94e3d0b..dc9fb86 100644 --- a/.gitignore +++ b/.gitignore @@ -19,4 +19,5 @@ experiments/ andy_*.json jill_*.json src/models/logs/* -server_data* \ No newline at end of file +server_data* +results/* \ No newline at end of file diff --git a/results/4o_craft_better_tasks_03-02_07-15/results.txt b/results/4o_craft_better_tasks_03-02_07-15/results.txt deleted file mode 100644 index 894ac0b..0000000 --- a/results/4o_craft_better_tasks_03-02_07-15/results.txt +++ /dev/null @@ -1,25 +0,0 @@ -Results -total: 823 -successful: 196 -success_rate: 0.23815309842041313 -base_total: 69 -base_successful: 20 -base_success_rate: 0.2898550724637681 -base_no_plan_total: 27 -base_no_plan_successful: 10 -base_no_plan_success_rate: 0.37037037037037035 -missing_total: 375 -missing_successful: 72 -missing_success_rate: 0.192 -full_plan_total: 196 -full_plan_successful: 39 -full_plan_success_rate: 0.1989795918367347 -partial_plan_total: 282 -partial_plan_successful: 62 -partial_plan_success_rate: 0.2198581560283688 -no_plan_total: 276 -no_plan_successful: 75 -no_plan_success_rate: 0.2717391304347826 -high_depth_total: 505 -high_depth_successful: 90 -high_depth_success_rate: 0.1782178217821782 diff --git a/results/4o_craft_better_tasks_03-02_07-15results.txt b/results/4o_craft_better_tasks_03-02_07-15results.txt deleted file mode 100644 index 8740300..0000000 --- a/results/4o_craft_better_tasks_03-02_07-15results.txt +++ /dev/null @@ -1,21 +0,0 @@ -Folder: total -> 304 -Folder: successful -> 77 -Folder: success_rate -> 0.2532894736842105 -Folder: base_total -> 39 -Folder: base_successful -> 12 -Folder: base_success_rate -> 0.3076923076923077 -Folder: missing_total -> 102 -Folder: missing_successful -> 19 -Folder: missing_success_rate -> 0.18627450980392157 -Folder: full_plan_total -> 57 -Folder: full_plan_successful -> 9 -Folder: full_plan_success_rate -> 0.15789473684210525 -Folder: partial_plan_total -> 108 -Folder: partial_plan_successful -> 26 -Folder: partial_plan_success_rate -> 0.24074074074074073 -Folder: no_plan_total -> 99 -Folder: no_plan_successful -> 30 -Folder: no_plan_success_rate -> 0.30303030303030304 -Folder: high_depth_total -> 165 -Folder: high_depth_successful -> 29 -Folder: high_depth_success_rate -> 0.17575757575757575 diff --git a/results/clauderesults.txt b/results/clauderesults.txt deleted file mode 100644 index 3cc50c1..0000000 --- a/results/clauderesults.txt +++ /dev/null @@ -1,21 +0,0 @@ -Folder: total -> 601 -Folder: successful -> 210 -Folder: success_rate -> 0.34941763727121466 -Folder: base_total -> 69 -Folder: base_successful -> 31 -Folder: base_success_rate -> 0.4492753623188406 -Folder: missing_total -> 232 -Folder: missing_successful -> 87 -Folder: missing_success_rate -> 0.375 -Folder: full_plan_total -> 126 -Folder: full_plan_successful -> 47 -Folder: full_plan_success_rate -> 0.373015873015873 -Folder: partial_plan_total -> 201 -Folder: partial_plan_successful -> 62 -Folder: partial_plan_success_rate -> 0.30845771144278605 -Folder: no_plan_total -> 205 -Folder: no_plan_successful -> 70 -Folder: no_plan_success_rate -> 0.34146341463414637 -Folder: high_depth_total -> 292 -Folder: high_depth_successful -> 55 -Folder: high_depth_success_rate -> 0.18835616438356165