├── .gitignore ├── LICENSE ├── README.md ├── details ├── 2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv ├── 2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv ├── 2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv ├── 2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv ├── 2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv ├── 2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv ├── 2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv ├── 2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv ├── 2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv ├── 2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv ├── 2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv ├── 2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv ├── 2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv ├── 2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv ├── 2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv ├── 2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv ├── 2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv ├── 2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv ├── 2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv ├── 2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv ├── 2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv ├── 2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv ├── 2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv ├── 2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv ├── 2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv ├── 2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv ├── 2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv ├── 2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv ├── 2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv ├── 2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv ├── 2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv ├── 2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv ├── 2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv ├── 2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv ├── 2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv ├── 2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv ├── 2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv ├── 2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv ├── 2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv ├── 2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv ├── 2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv ├── 2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv ├── 2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv ├── 2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv ├── 2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv ├── 2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv ├── 2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv ├── 2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv ├── 2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv ├── 2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv ├── 2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv ├── 2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv ├── 2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv ├── 2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv ├── 2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv ├── 2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv ├── 2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv ├── 2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv ├── 2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv ├── 2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv ├── 2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv ├── 2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv ├── 2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv ├── 2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv ├── 2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv ├── 2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv ├── 2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv ├── 2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv ├── 2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv ├── 2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv ├── 2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv ├── 2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv ├── 2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv ├── 2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv ├── 2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv ├── 2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv ├── 2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv ├── 2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv ├── 2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv ├── 2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv ├── 2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv ├── 2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv ├── 2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv ├── 2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv ├── 2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv ├── 2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv ├── 2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv └── all-details.csv ├── exams ├── agi-eval │ ├── aqua-rat-10.jsonl │ ├── aqua-rat-100.jsonl │ ├── aqua-rat-254.jsonl │ ├── logiqa-en-10.jsonl │ ├── logiqa-en-100.jsonl │ ├── logiqa-en-651.jsonl │ ├── lsat-ar-10.jsonl │ ├── lsat-ar-100.jsonl │ ├── lsat-ar-230.jsonl │ ├── lsat-lr-10.jsonl │ ├── lsat-lr-100.jsonl │ ├── lsat-lr-510.jsonl │ ├── lsat-rc-10.jsonl │ ├── lsat-rc-100.jsonl │ ├── lsat-rc-269.jsonl │ ├── sat-en-10.jsonl │ ├── sat-en-100.jsonl │ ├── sat-en-206.jsonl │ ├── sat-math-10.jsonl │ ├── sat-math-100.jsonl │ └── sat-math-220.jsonl ├── arc │ ├── arc-challenge-test-10.jsonl │ ├── arc-challenge-test-100.jsonl │ ├── arc-challenge-test-1000.jsonl │ ├── arc-challenge-test-1172.jsonl │ ├── arc-easy-test-10.jsonl │ ├── arc-easy-test-100.jsonl │ ├── arc-easy-test-1000.jsonl │ └── arc-easy-test-2376.jsonl ├── comprehensive │ └── comprehensive-100.jsonl ├── hellaswag │ ├── hellaswag_val-10.jsonl │ ├── hellaswag_val-100.jsonl │ ├── hellaswag_val-1000.jsonl │ └── hellaswag_val-10000.jsonl └── medmcqa │ ├── medmcqa-dev-10.jsonl │ ├── medmcqa-dev-100.jsonl │ ├── medmcqa-dev-1000.jsonl │ └── medmcqa-dev-2816.jsonl ├── logs ├── 2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.txt ├── 2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.txt ├── 2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.txt ├── 2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.txt ├── 2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.txt ├── 2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.txt ├── 2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.txt ├── 2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.txt ├── 2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.txt ├── 2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.txt ├── 2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.txt ├── 2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.txt ├── 2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.txt ├── 2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.txt ├── 2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.txt ├── 2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.txt ├── 2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.txt ├── 2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.txt ├── 2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.txt ├── 2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.txt ├── 2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.txt ├── 2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.txt ├── 2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.txt ├── 2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.txt ├── 2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.txt ├── 2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.txt ├── 2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.txt ├── 2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.txt ├── 2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.txt ├── 2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.txt ├── 2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.txt ├── 2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.txt ├── 2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.txt ├── 2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.txt ├── 2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.txt ├── 2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.txt ├── 2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.txt ├── 2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.txt ├── 2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.txt ├── 2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.txt ├── 2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.txt ├── 2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.txt ├── 2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.txt ├── 2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.txt ├── 2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.txt ├── 2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.txt ├── 2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.txt ├── 2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.txt ├── 2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.txt ├── 2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.txt ├── 2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.txt ├── 2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.txt ├── 2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.txt ├── 2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.txt ├── 2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.txt ├── 2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.txt ├── 2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.txt ├── 2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.txt ├── 2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.txt ├── 2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.txt ├── 2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.txt ├── 2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.txt ├── 2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.txt ├── 2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.txt ├── 2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.txt ├── 2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.txt ├── 2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.txt ├── 2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.txt ├── 2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.txt ├── 2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.txt ├── 2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.txt ├── 2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.txt ├── 2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.txt ├── 2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.txt ├── 2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.txt ├── 2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.txt ├── 2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.txt ├── 2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.txt ├── 2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.txt ├── 2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.txt ├── 2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.txt ├── 2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.txt ├── 2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.txt ├── 2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.txt ├── 2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.txt ├── 2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.txt └── 2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.txt ├── plots ├── accuracy-by-exam.png ├── accuracy-by-prompt-and-exam.png ├── accuracy-by-prompt-for-gpt-3.5.png ├── accuracy-by-prompt-for-gpt-4.png ├── accuracy-by-prompt.png ├── accuracy-by-temperature-and-prompt.png ├── distribution-of-accuracy-for-gpt-3.5-with-ccot.png ├── distribution-of-accuracy-for-gpt-3.5-with-vcot.png ├── distribution-of-accuracy-for-gpt-4-with-ccot.png ├── distribution-of-accuracy-for-gpt-4-with-vcot.png ├── distribution-of-response-length-for-ccot.png ├── distribution-of-response-length-for-cot.png ├── distribution-of-response-length-for-gpt-3.5-with-ccot.png ├── distribution-of-response-length-for-gpt-3.5-with-vcot.png ├── distribution-of-response-length-for-gpt-4-with-ccot.png ├── distribution-of-response-length-for-gpt-4-with-vcot.png ├── response-length-by-prompt-and-exam-for-gpt-3.5.png ├── response-length-by-prompt-and-exam-for-gpt-4.png ├── response-length-by-prompt-for-gpt-3.5.png ├── response-length-by-prompt-for-gpt-4.png ├── token-length-by-prompt-and-exam.png ├── tokens-by-prompt-and-exam-for-gpt-3.5.png ├── tokens-by-prompt-and-exam-for-gpt-4.png ├── tokens-by-prompt-and-exam.png ├── tokens-by-prompt-for-gpt-3.5.png ├── tokens-by-prompt-for-gpt-4.png ├── tokens-by-prompt.png ├── tokenss-by-prompt.png ├── total-cost-by-prompt-for-gpt-3.5.png ├── total-cost-by-prompt-for-gpt-4.png └── violin-accuracy-by-prompt-for-gpt-4.png ├── results ├── 2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv ├── 2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv ├── 2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv ├── 2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv ├── 2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv ├── 2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv ├── 2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv ├── 2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv ├── 2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv ├── 2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv ├── 2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv ├── 2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv ├── 2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv ├── 2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv ├── 2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv ├── 2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv ├── 2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv ├── 2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv ├── 2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv ├── 2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv ├── 2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv ├── 2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv ├── 2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv ├── 2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv ├── 2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv ├── 2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv ├── 2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv ├── 2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv ├── 2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv ├── 2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv ├── 2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv ├── 2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv ├── 2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv ├── 2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv ├── 2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv ├── 2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv ├── 2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv ├── 2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv ├── 2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv ├── 2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv ├── 2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv ├── 2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv ├── 2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv ├── 2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv ├── 2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv ├── 2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv ├── 2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv ├── 2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv ├── 2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv ├── 2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv ├── 2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv ├── 2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv ├── 2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv ├── 2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv ├── 2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv ├── 2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv ├── 2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv ├── 2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv ├── 2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv ├── 2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv ├── 2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv ├── 2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv ├── 2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv ├── 2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv ├── 2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv ├── 2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv ├── 2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv ├── 2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv ├── 2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv ├── 2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv ├── 2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv ├── 2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv ├── 2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv ├── 2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv ├── 2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv ├── 2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv ├── 2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv ├── 2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv ├── 2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv ├── 2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv ├── 2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv ├── 2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv ├── 2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv ├── 2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv ├── 2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv ├── 2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv └── 2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv ├── source ├── .idea │ ├── .gitignore │ ├── .name │ ├── conciseness.iml │ ├── inspectionProfiles │ │ ├── Project_Default.xml │ │ └── profiles_settings.xml │ ├── jupyter-settings.xml │ ├── misc.xml │ └── modules.xml ├── actions.py ├── agents │ ├── __init__.py │ ├── agent.py │ ├── agent_factory.py │ ├── baseline_agent.py │ ├── chain_of_thought_agent.py │ ├── composite_agent.py │ └── concise_agent.py ├── analyze │ ├── analyze_cost.py │ ├── plot_by_exam.py │ ├── plot_by_prompt.py │ ├── plot_by_prompt_and_exam.py │ ├── plot_response_length_by_prompt.py │ ├── plot_response_length_by_prompt_and_exam.py │ ├── test_performance.py │ ├── test_performance_on_math.py │ └── test_response_length.py ├── details.py ├── dialogs.py ├── exams.py ├── experiments.py ├── logs.py ├── main.py ├── models │ ├── __init__.py │ ├── gpt.py │ ├── llama.py │ └── response.py ├── process │ └── process_details.py └── results.py └── technical-appendix.pdf /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/README.md -------------------------------------------------------------------------------- /details/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv -------------------------------------------------------------------------------- /details/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /details/all-details.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/details/all-details.csv -------------------------------------------------------------------------------- /exams/agi-eval/aqua-rat-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/aqua-rat-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/aqua-rat-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/aqua-rat-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/aqua-rat-254.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/aqua-rat-254.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/logiqa-en-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/logiqa-en-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/logiqa-en-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/logiqa-en-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/logiqa-en-651.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/logiqa-en-651.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-ar-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-ar-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-ar-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-ar-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-ar-230.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-ar-230.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-lr-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-lr-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-lr-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-lr-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-lr-510.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-lr-510.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-rc-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-rc-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-rc-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-rc-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/lsat-rc-269.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/lsat-rc-269.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-en-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-en-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-en-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-en-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-en-206.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-en-206.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-math-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-math-10.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-math-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-math-100.jsonl -------------------------------------------------------------------------------- /exams/agi-eval/sat-math-220.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/agi-eval/sat-math-220.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-challenge-test-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-challenge-test-10.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-challenge-test-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-challenge-test-100.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-challenge-test-1000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-challenge-test-1000.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-challenge-test-1172.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-challenge-test-1172.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-easy-test-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-easy-test-10.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-easy-test-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-easy-test-100.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-easy-test-1000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-easy-test-1000.jsonl -------------------------------------------------------------------------------- /exams/arc/arc-easy-test-2376.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/arc/arc-easy-test-2376.jsonl -------------------------------------------------------------------------------- /exams/comprehensive/comprehensive-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/comprehensive/comprehensive-100.jsonl -------------------------------------------------------------------------------- /exams/hellaswag/hellaswag_val-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/hellaswag/hellaswag_val-10.jsonl -------------------------------------------------------------------------------- /exams/hellaswag/hellaswag_val-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/hellaswag/hellaswag_val-100.jsonl -------------------------------------------------------------------------------- /exams/hellaswag/hellaswag_val-1000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/hellaswag/hellaswag_val-1000.jsonl -------------------------------------------------------------------------------- /exams/hellaswag/hellaswag_val-10000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/hellaswag/hellaswag_val-10000.jsonl -------------------------------------------------------------------------------- /exams/medmcqa/medmcqa-dev-10.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/medmcqa/medmcqa-dev-10.jsonl -------------------------------------------------------------------------------- /exams/medmcqa/medmcqa-dev-100.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/medmcqa/medmcqa-dev-100.jsonl -------------------------------------------------------------------------------- /exams/medmcqa/medmcqa-dev-1000.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/medmcqa/medmcqa-dev-1000.jsonl -------------------------------------------------------------------------------- /exams/medmcqa/medmcqa-dev-2816.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/exams/medmcqa/medmcqa-dev-2816.jsonl -------------------------------------------------------------------------------- /logs/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /logs/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.txt -------------------------------------------------------------------------------- /logs/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/logs/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.txt -------------------------------------------------------------------------------- /plots/accuracy-by-exam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-exam.png -------------------------------------------------------------------------------- /plots/accuracy-by-prompt-and-exam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-prompt-and-exam.png -------------------------------------------------------------------------------- /plots/accuracy-by-prompt-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-prompt-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/accuracy-by-prompt-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-prompt-for-gpt-4.png -------------------------------------------------------------------------------- /plots/accuracy-by-prompt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-prompt.png -------------------------------------------------------------------------------- /plots/accuracy-by-temperature-and-prompt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/accuracy-by-temperature-and-prompt.png -------------------------------------------------------------------------------- /plots/distribution-of-accuracy-for-gpt-3.5-with-ccot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-accuracy-for-gpt-3.5-with-ccot.png -------------------------------------------------------------------------------- /plots/distribution-of-accuracy-for-gpt-3.5-with-vcot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-accuracy-for-gpt-3.5-with-vcot.png -------------------------------------------------------------------------------- /plots/distribution-of-accuracy-for-gpt-4-with-ccot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-accuracy-for-gpt-4-with-ccot.png -------------------------------------------------------------------------------- /plots/distribution-of-accuracy-for-gpt-4-with-vcot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-accuracy-for-gpt-4-with-vcot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-ccot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-ccot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-cot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-cot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-gpt-3.5-with-ccot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-gpt-3.5-with-ccot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-gpt-3.5-with-vcot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-gpt-3.5-with-vcot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-gpt-4-with-ccot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-gpt-4-with-ccot.png -------------------------------------------------------------------------------- /plots/distribution-of-response-length-for-gpt-4-with-vcot.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/distribution-of-response-length-for-gpt-4-with-vcot.png -------------------------------------------------------------------------------- /plots/response-length-by-prompt-and-exam-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/response-length-by-prompt-and-exam-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/response-length-by-prompt-and-exam-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/response-length-by-prompt-and-exam-for-gpt-4.png -------------------------------------------------------------------------------- /plots/response-length-by-prompt-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/response-length-by-prompt-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/response-length-by-prompt-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/response-length-by-prompt-for-gpt-4.png -------------------------------------------------------------------------------- /plots/token-length-by-prompt-and-exam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/token-length-by-prompt-and-exam.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt-and-exam-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt-and-exam-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt-and-exam-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt-and-exam-for-gpt-4.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt-and-exam.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt-and-exam.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt-for-gpt-4.png -------------------------------------------------------------------------------- /plots/tokens-by-prompt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokens-by-prompt.png -------------------------------------------------------------------------------- /plots/tokenss-by-prompt.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/tokenss-by-prompt.png -------------------------------------------------------------------------------- /plots/total-cost-by-prompt-for-gpt-3.5.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/total-cost-by-prompt-for-gpt-3.5.png -------------------------------------------------------------------------------- /plots/total-cost-by-prompt-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/total-cost-by-prompt-for-gpt-4.png -------------------------------------------------------------------------------- /plots/violin-accuracy-by-prompt-for-gpt-4.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/plots/violin-accuracy-by-prompt-for-gpt-4.png -------------------------------------------------------------------------------- /results/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 15-24-38 - gpt-35-turbo - baseline - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 15-25-25 - gpt-35-turbo - chain_of_thought - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 15-32-02 - gpt-35-turbo - composite - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 15-43-28 - gpt-4 - baseline - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 15-47-26 - gpt-4 - chain_of_thought - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 16-16-14 - gpt-4 - composite - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 18-59-17 - gpt-35-turbo - baseline - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-00-46 - gpt-35-turbo - baseline - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-01-28 - gpt-35-turbo - baseline - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-02-11 - gpt-35-turbo - baseline - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-02-50 - gpt-35-turbo - baseline - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-03-31 - gpt-35-turbo - baseline - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-04-16 - gpt-35-turbo - baseline - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-06-24 - gpt-35-turbo - baseline - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-07-01 - gpt-35-turbo - baseline - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-07-36 - gpt-35-turbo - baseline - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-08-11 - gpt-35-turbo - chain_of_thought - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-16-42 - gpt-35-turbo - chain_of_thought - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-23-35 - gpt-35-turbo - chain_of_thought - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-35-25 - gpt-35-turbo - chain_of_thought - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-42-05 - gpt-35-turbo - chain_of_thought - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 19-58-05 - gpt-35-turbo - chain_of_thought - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-03-29 - gpt-35-turbo - chain_of_thought - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-10-33 - gpt-35-turbo - chain_of_thought - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-14-41 - gpt-35-turbo - chain_of_thought - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-20-06 - gpt-35-turbo - chain_of_thought - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-24-50 - gpt-35-turbo - composite - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-35-16 - gpt-35-turbo - composite - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-45-28 - gpt-35-turbo - composite - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 20-59-33 - gpt-35-turbo - composite - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-09-43 - gpt-35-turbo - composite - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-19-32 - gpt-35-turbo - composite - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-28-57 - gpt-35-turbo - composite - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-38-11 - gpt-35-turbo - composite - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-46-23 - gpt-35-turbo - composite - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 21-54-59 - gpt-35-turbo - composite - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-20-40 - gpt-4 - baseline - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-27-36 - gpt-4 - baseline - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-30-49 - gpt-4 - baseline - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-34-11 - gpt-4 - baseline - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-37-25 - gpt-4 - baseline - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-40-46 - gpt-4 - baseline - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-44-17 - gpt-4 - baseline - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-49-39 - gpt-4 - baseline - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-52-44 - gpt-4 - baseline - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-56-06 - gpt-4 - baseline - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 22-59-16 - gpt-4 - chain_of_thought - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-11-30 23-40-46 - gpt-4 - chain_of_thought - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 00-15-25 - gpt-4 - chain_of_thought - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 01-38-56 - gpt-4 - chain_of_thought - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 02-08-47 - gpt-4 - chain_of_thought - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 02-34-32 - gpt-4 - chain_of_thought - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 08-01-13 - gpt-4 - chain_of_thought - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 08-47-01 - gpt-4 - chain_of_thought - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 09-06-29 - gpt-4 - chain_of_thought - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 09-30-07 - gpt-4 - chain_of_thought - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 10-36-11 - gpt-4 - composite - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 11-47-09 - gpt-4 - composite - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 12-39-07 - gpt-4 - composite - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 13-47-31 - gpt-4 - composite - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 14-38-55 - gpt-4 - composite - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 15-25-19 - gpt-4 - composite - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 16-04-52 - gpt-4 - composite - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 16-51-35 - gpt-4 - composite - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 17-26-42 - gpt-4 - composite - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-01 18-03-43 - gpt-4 - composite - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 11-09-36 - gpt-35-turbo - concise - comprehensive-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 11-29-13 - gpt-35-turbo - concise - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 11-34-53 - gpt-35-turbo - concise - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 12-17-31 - gpt-4 - concise - aqua-rat-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 12-43-56 - gpt-4 - concise - sat-math-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-19-57 - gpt-35-turbo - concise - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-23-52 - gpt-35-turbo - concise - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-30-05 - gpt-35-turbo - concise - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-33-15 - gpt-35-turbo - concise - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-36-19 - gpt-35-turbo - concise - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-39-27 - gpt-35-turbo - concise - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-41-52 - gpt-35-turbo - concise - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-44-32 - gpt-35-turbo - concise - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /results/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-02 23-47-10 - gpt-4 - concise - logiqa-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 00-03-46 - gpt-4 - concise - lsat-ar-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 00-46-03 - gpt-4 - concise - lsat-lr-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 00-57-46 - gpt-4 - concise - lsat-rc-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 01-07-10 - gpt-4 - concise - sat-en-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 01-19-16 - gpt-4 - concise - arc-challenge-test-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 01-30-11 - gpt-4 - concise - hellaswag_val-100.csv -------------------------------------------------------------------------------- /results/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/results/2023-12-03 01-35-59 - gpt-4 - concise - medmcqa-dev-100.csv -------------------------------------------------------------------------------- /source/.idea/.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/.gitignore -------------------------------------------------------------------------------- /source/.idea/.name: -------------------------------------------------------------------------------- 1 | conciseness -------------------------------------------------------------------------------- /source/.idea/conciseness.iml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/conciseness.iml -------------------------------------------------------------------------------- /source/.idea/inspectionProfiles/Project_Default.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/inspectionProfiles/Project_Default.xml -------------------------------------------------------------------------------- /source/.idea/inspectionProfiles/profiles_settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/inspectionProfiles/profiles_settings.xml -------------------------------------------------------------------------------- /source/.idea/jupyter-settings.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/jupyter-settings.xml -------------------------------------------------------------------------------- /source/.idea/misc.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/misc.xml -------------------------------------------------------------------------------- /source/.idea/modules.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/.idea/modules.xml -------------------------------------------------------------------------------- /source/actions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/actions.py -------------------------------------------------------------------------------- /source/agents/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/__init__.py -------------------------------------------------------------------------------- /source/agents/agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/agent.py -------------------------------------------------------------------------------- /source/agents/agent_factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/agent_factory.py -------------------------------------------------------------------------------- /source/agents/baseline_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/baseline_agent.py -------------------------------------------------------------------------------- /source/agents/chain_of_thought_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/chain_of_thought_agent.py -------------------------------------------------------------------------------- /source/agents/composite_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/composite_agent.py -------------------------------------------------------------------------------- /source/agents/concise_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/agents/concise_agent.py -------------------------------------------------------------------------------- /source/analyze/analyze_cost.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/analyze_cost.py -------------------------------------------------------------------------------- /source/analyze/plot_by_exam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/plot_by_exam.py -------------------------------------------------------------------------------- /source/analyze/plot_by_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/plot_by_prompt.py -------------------------------------------------------------------------------- /source/analyze/plot_by_prompt_and_exam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/plot_by_prompt_and_exam.py -------------------------------------------------------------------------------- /source/analyze/plot_response_length_by_prompt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/plot_response_length_by_prompt.py -------------------------------------------------------------------------------- /source/analyze/plot_response_length_by_prompt_and_exam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/plot_response_length_by_prompt_and_exam.py -------------------------------------------------------------------------------- /source/analyze/test_performance.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/test_performance.py -------------------------------------------------------------------------------- /source/analyze/test_performance_on_math.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/test_performance_on_math.py -------------------------------------------------------------------------------- /source/analyze/test_response_length.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/analyze/test_response_length.py -------------------------------------------------------------------------------- /source/details.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/details.py -------------------------------------------------------------------------------- /source/dialogs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/dialogs.py -------------------------------------------------------------------------------- /source/exams.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/exams.py -------------------------------------------------------------------------------- /source/experiments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/experiments.py -------------------------------------------------------------------------------- /source/logs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/logs.py -------------------------------------------------------------------------------- /source/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/main.py -------------------------------------------------------------------------------- /source/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/models/__init__.py -------------------------------------------------------------------------------- /source/models/gpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/models/gpt.py -------------------------------------------------------------------------------- /source/models/llama.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/models/llama.py -------------------------------------------------------------------------------- /source/models/response.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/models/response.py -------------------------------------------------------------------------------- /source/process/process_details.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/process/process_details.py -------------------------------------------------------------------------------- /source/results.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/source/results.py -------------------------------------------------------------------------------- /technical-appendix.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/matthewrenze/jhu-concise-cot/HEAD/technical-appendix.pdf --------------------------------------------------------------------------------