Checkpoint experiments through SWE pilot v2

This commit is contained in:
pj committed 2026-09-15 15:46:10 +05:30
1 parent abacd5c5e1
commit 72d77018d8
845 files changed
+431756 -41

No files matched your search

@@ -0,0 +1,5 @@
episode_id,run_id,condition,cohort,split,task_id,model,log_path,sample_uuid,report_directory,score,limit,error,total_tokens,input_tokens,cache_read_tokens,cache_write_tokens,output_tokens,reasoning_tokens,model_calls,messages,submit_tool_calls,score_events,working_seconds,scratch_files,published_post_ids,peer_post_exposure_ids
worker-1cfa9f8aebb6,b792b18e01be4d5f9e3c501d4b5f2fe7,board,1,original,lcbhard_0,openrouter/z-ai/glm-5.3-flash,/Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p1_MXeGhVFnNd6cknbzk8pCBo.eval,huWE6DJyKwTBCyGAJQ2xJy,episode-001,C,,,13171,3962,7616,,1593,371,4,10,1,2,50.294,[],[],[]
worker-53b41e4a73e1,b792b18e01be4d5f9e3c501d4b5f2fe7,board,1,conflicting,lcbhard_1,openrouter/z-ai/glm-5.3-flash,/Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p2_HWqPfyg8RWqT2M4Dtwe8Xa.eval,9BhsBaJP5bHayKHQpHgJ2q,episode-002,C,,,185878,28354,143872,,13652,8355,15,32,1,2,380.245,[],[],[]
worker-4b6fc9699479,b792b18e01be4d5f9e3c501d4b5f2fe7,board,1,conflicting,lcbhard_2,openrouter/z-ai/glm-5.3-flash,/Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p3_QAU44iehguAMqgTH7xkNu5.eval,nLZx4PK6MDb3WkuigLoRMY,episode-003,C,,,102164,17371,78272,,6521,2548,14,31,2,3,206.566,[],"[1, 2]",[]
worker-78c73023435d,2c8915e4364f4533a00907d465013a6e,private,1,original,lcbhard_0,openrouter/z-ai/glm-5.3-flash,/Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-08-21-00-00_board-pilot-private-c1-p1_EakSh9iqXg4KnaKMkWP5YY.eval,4VG3PgLotmjmfBozmKYrx9,episode-004,C,,,11036,3781,5888,,1367,148,4,10,1,2,40.126,[],[],[]
1 episode_id run_id condition cohort split task_id model log_path sample_uuid report_directory score limit error total_tokens input_tokens cache_read_tokens cache_write_tokens output_tokens reasoning_tokens model_calls messages submit_tool_calls score_events working_seconds scratch_files published_post_ids peer_post_exposure_ids
2 worker-1cfa9f8aebb6 b792b18e01be4d5f9e3c501d4b5f2fe7 board 1 original lcbhard_0 openrouter/z-ai/glm-5.3-flash /Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p1_MXeGhVFnNd6cknbzk8pCBo.eval huWE6DJyKwTBCyGAJQ2xJy episode-001 C 13171 3962 7616 1593 371 4 10 1 2 50.294 [] [] []
3 worker-53b41e4a73e1 b792b18e01be4d5f9e3c501d4b5f2fe7 board 1 conflicting lcbhard_1 openrouter/z-ai/glm-5.3-flash /Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p2_HWqPfyg8RWqT2M4Dtwe8Xa.eval 9BhsBaJP5bHayKHQpHgJ2q episode-002 C 185878 28354 143872 13652 8355 15 32 1 2 380.245 [] [] []
4 worker-4b6fc9699479 b792b18e01be4d5f9e3c501d4b5f2fe7 board 1 conflicting lcbhard_2 openrouter/z-ai/glm-5.3-flash /Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-01-58-00-00_board-pilot-board-c1-p3_QAU44iehguAMqgTH7xkNu5.eval nLZx4PK6MDb3WkuigLoRMY episode-003 C 102164 17371 78272 6521 2548 14 31 2 3 206.566 [] [1, 2] []
5 worker-78c73023435d 2c8915e4364f4533a00907d465013a6e private 1 original lcbhard_0 openrouter/z-ai/glm-5.3-flash /Users/pj/Workspace/projects/python/research/messageboardbench/logs/board-pilot-glm-sept8/evals/2026-09-07T19-08-21-00-00_board-pilot-private-c1-p1_EakSh9iqXg4KnaKMkWP5YY.eval 4VG3PgLotmjmfBozmKYrx9 episode-004 C 11036 3781 5888 1367 148 4 10 1 2 40.126 [] [] []