0000000000000000000000000000000000000000 2a187daf512e2ea2614661cbc444dec5bb716a2f Luca Benedetto <luca.benedetto93@gmail.com> 1698835054 +0000	clone: from github.com:lucabenedetto/roleplaying-qa-llms.git
2a187daf512e2ea2614661cbc444dec5bb716a2f f75b41d10326c658987bfe7826becfd84eff42af Luca Benedetto <luca.benedetto93@gmail.com> 1698835390 +0000	commit: add first version of the .py files
f75b41d10326c658987bfe7826becfd84eff42af 8bf0fa882c41409ab393c445cc496cd46cda8e67 Luca Benedetto <luca.benedetto93@gmail.com> 1698835430 +0000	commit: add gitignore
8bf0fa882c41409ab393c445cc496cd46cda8e67 118ce88d60837aa79e03a8b4fbbbaf78f934620f Luca Benedetto <luca.benedetto93@gmail.com> 1698835555 +0000	commit: add first version of requirements file
118ce88d60837aa79e03a8b4fbbbaf78f934620f 0f6be2c0d6dacdf05b858fea840d17e4eb0606fd Luca Benedetto <luca.benedetto93@gmail.com> 1698850112 +0000	commit: add levels and system message for prompt id 46
0f6be2c0d6dacdf05b858fea840d17e4eb0606fd 4689f029b31bc2f9da95bd7c74135c518b18ee77 Luca Benedetto <luca.benedetto93@gmail.com> 1698853438 +0000	commit: added "best" prompts for reading comprehensino questions
4689f029b31bc2f9da95bd7c74135c518b18ee77 e889776516199a6a9db5c7079956461b043c2531 Luca Benedetto <luca.benedetto93@gmail.com> 1698857689 +0000	commit: rename file
e889776516199a6a9db5c7079956461b043c2531 71266ed22496e2d692067b71972385184eadc324 Luca Benedetto <luca.benedetto93@gmail.com> 1698859438 +0000	commit: add requirements
71266ed22496e2d692067b71972385184eadc324 539c17ab291484aa9280de2b09ac0ae12578f065 Luca Benedetto <luca.benedetto93@gmail.com> 1698859450 +0000	commit: add first version to test inference with llama
539c17ab291484aa9280de2b09ac0ae12578f065 3b426220b1e43005324ae960b23451af61e48f84 Luca Benedetto <luca.benedetto93@gmail.com> 1698943210 +0000	commit: add accelerate. Had an error with llama (ImportError: Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`)
3b426220b1e43005324ae960b23451af61e48f84 8e8d58cf469666537935113b14b86fdff530c0c6 Luca Benedetto <luca.benedetto93@gmail.com> 1698944542 +0000	commit: first test with arc data
8e8d58cf469666537935113b14b86fdff530c0c6 acffed1e798efe738ffe7af8941b3159dc74b4f1 Luca Benedetto <luca.benedetto93@gmail.com> 1698945016 +0000	commit: add first test of prompt from ARC for llama2
acffed1e798efe738ffe7af8941b3159dc74b4f1 f75438d706e1ea4f8c79cea7ae16cde2e17af2d1 Luca Benedetto <luca.benedetto93@gmail.com> 1698945387 +0000	commit: new tests on max_length
f75438d706e1ea4f8c79cea7ae16cde2e17af2d1 8b1c19a0e036db76790d14ad45c12d7242c820e8 Luca Benedetto <luca.benedetto93@gmail.com> 1698945787 +0000	commit: new tests on max_length
8b1c19a0e036db76790d14ad45c12d7242c820e8 a5aaf034ac63e3731b5609ad87a33732d3e2b74d Luca Benedetto <luca.benedetto93@gmail.com> 1698946290 +0000	commit: new tests on max_length
a5aaf034ac63e3731b5609ad87a33732d3e2b74d 4eb285ad9a10b6f5317a0065eb675e0aa3966412 Luca Benedetto <luca.benedetto93@gmail.com> 1699006767 +0000	commit: add venv to gitignore
4eb285ad9a10b6f5317a0065eb675e0aa3966412 001a4ba1d2fa1bc2154a6edd2e36b5375b7c949a Luca Benedetto <luca.benedetto93@gmail.com> 1699026962 +0000	pull: Fast-forward
001a4ba1d2fa1bc2154a6edd2e36b5375b7c949a e47794ff2186da2a91eef4c4754ade04855f4035 Luca Benedetto <luca.benedetto93@gmail.com> 1699275516 +0000	pull: Fast-forward
e47794ff2186da2a91eef4c4754ade04855f4035 2d738079de79229c01a23864c50d41d6475d89ed Luca Benedetto <luca.benedetto93@gmail.com> 1699276891 +0000	pull: Fast-forward
2d738079de79229c01a23864c50d41d6475d89ed aada3d79cbac58b560067ed50d40d5c1aa1422b9 Luca Benedetto <luca.benedetto93@gmail.com> 1699277167 +0000	commit: fix definition of five_levels_int
aada3d79cbac58b560067ed50d40d5c1aa1422b9 f491aed7f228d7b7101f77069470d9047eddc66a Luca Benedetto <luca.benedetto93@gmail.com> 1699457620 +0000	pull: Fast-forward
f491aed7f228d7b7101f77069470d9047eddc66a 3a2f4c89324af53a7d6e4309ed32374110d21adb Luca Benedetto <luca.benedetto93@gmail.com> 1699531998 +0000	pull: Fast-forward
3a2f4c89324af53a7d6e4309ed32374110d21adb aa2defde5093a48903476a8b37b5aaff3d2c5e16 Luca Benedetto <luca.benedetto93@gmail.com> 1699542407 +0000	pull: Fast-forward
aa2defde5093a48903476a8b37b5aaff3d2c5e16 70b8fb683c3aaeee8f6338562b9e7fc14f6f009a Luca Benedetto <luca.benedetto93@gmail.com> 1699543765 +0000	pull: Fast-forward
70b8fb683c3aaeee8f6338562b9e7fc14f6f009a 38943636cce53f41693cca2b58fb05f291ed8e32 Luca Benedetto <luca.benedetto93@gmail.com> 1699554187 +0000	pull: Fast-forward
38943636cce53f41693cca2b58fb05f291ed8e32 d0f559c95d0b5581c0bca35446948a8ed5ab38f9 Luca Benedetto <luca.benedetto93@gmail.com> 1699611369 +0000	commit: remove print
d0f559c95d0b5581c0bca35446948a8ed5ab38f9 2afc06c6841051d0626abf713480ebf13eaf6abe Luca Benedetto <luca.benedetto93@gmail.com> 1699617869 +0000	pull: Fast-forward
2afc06c6841051d0626abf713480ebf13eaf6abe f25c6f631fb6a852db0e8fd1ebfac99a5abcdcc6 Luca Benedetto <luca.benedetto93@gmail.com> 1699879420 +0000	pull: Fast-forward
f25c6f631fb6a852db0e8fd1ebfac99a5abcdcc6 73cf0f4b4901376ebe41d79452b4a41b72847a2c Luca Benedetto <luca.benedetto93@gmail.com> 1699978880 +0000	pull: Fast-forward
73cf0f4b4901376ebe41d79452b4a41b72847a2c dd95ff2faa76e85f3da5ddd223bccfac7acee6a5 Luca Benedetto <luca.benedetto93@gmail.com> 1699979203 +0000	commit: add param for llama 70b
dd95ff2faa76e85f3da5ddd223bccfac7acee6a5 3184ff13e2f562eb87de1971420a082488f3dbc0 Luca Benedetto <luca.benedetto93@gmail.com> 1699980940 +0000	commit: test with 4bit
3184ff13e2f562eb87de1971420a082488f3dbc0 c5233b757b21e3a2a0b30bf6e0cf71261d483e37 Luca Benedetto <luca.benedetto93@gmail.com> 1700133256 +0000	commit: fix gpt version
c5233b757b21e3a2a0b30bf6e0cf71261d483e37 b61a09a47648475039dac33f81aba8a686ce2a65 Luca Benedetto <luca.benedetto93@gmail.com> 1700215362 +0000	pull: Fast-forward
b61a09a47648475039dac33f81aba8a686ce2a65 03a4d12453f58c7ea974bb2ac7c4e7bd54a4100d Luca Benedetto <luca.benedetto93@gmail.com> 1700906545 +0000	pull: Fast-forward
03a4d12453f58c7ea974bb2ac7c4e7bd54a4100d 2954289392c2b9988553a13534b606fcc4d1e077 Luca Benedetto <luca.benedetto93@gmail.com> 1701082357 +0000	pull: Fast-forward
2954289392c2b9988553a13534b606fcc4d1e077 f213911f3642cfd08600ac1c972fc2d93d10a3f7 Luca Benedetto <luca.benedetto93@gmail.com> 1701261973 +0000	pull: Fast-forward
f213911f3642cfd08600ac1c972fc2d93d10a3f7 f1dafebc42953bd931636682ad5885d12f684e04 Luca Benedetto <luca.benedetto93@gmail.com> 1701446813 +0000	pull: Fast-forward
f1dafebc42953bd931636682ad5885d12f684e04 de36b70316ba32d83c029c0cc57b5d85795978a0 Luca Benedetto <luca.benedetto93@gmail.com> 1701684184 +0000	pull: Fast-forward
de36b70316ba32d83c029c0cc57b5d85795978a0 12418be34d8c72c72a272ae0f6b42dbc018c4310 Luca Benedetto <luca.benedetto93@gmail.com> 1701793869 +0000	pull: Fast-forward
12418be34d8c72c72a272ae0f6b42dbc018c4310 8e389dbf1d07b72a5f734a2fda1bf772f0f2279b Luca Benedetto <luca.benedetto93@gmail.com> 1702292851 +0000	pull: Fast-forward
8e389dbf1d07b72a5f734a2fda1bf772f0f2279b a6deb22561f75ead6a2410ac9f39d884ecdc3239 Luca Benedetto <luca.benedetto93@gmail.com> 1702293171 +0000	commit: fix typo
a6deb22561f75ead6a2410ac9f39d884ecdc3239 eaf974a615da16a97a53e7efe6f1058aa5bbbcae Luca Benedetto <luca.benedetto93@gmail.com> 1702294349 +0000	pull: Fast-forward
eaf974a615da16a97a53e7efe6f1058aa5bbbcae 9c8b06e6a32280907b89c1da66953d44613b88f6 Luca Benedetto <luca.benedetto93@gmail.com> 1702294916 +0000	pull: Fast-forward
9c8b06e6a32280907b89c1da66953d44613b88f6 4406abbdb3087250b632276e0261e4f727f63c99 Luca Benedetto <luca.benedetto93@gmail.com> 1702570915 +0000	pull: Fast-forward
4406abbdb3087250b632276e0261e4f727f63c99 a571fecf7f76e650f0470c366a2ad0e94bf0b8fb Luca Benedetto <luca.benedetto93@gmail.com> 1702571246 +0000	commit: fix folder path
a571fecf7f76e650f0470c366a2ad0e94bf0b8fb 88c681514f316645dd7bfbbb6f320f58d13c22ec Luca Benedetto <luca.benedetto93@gmail.com> 1702571261 +0000	commit: fix param
88c681514f316645dd7bfbbb6f320f58d13c22ec 208e2aa5706c52543c3468c48a6d0627541d76cc Luca Benedetto <luca.benedetto93@gmail.com> 1702573368 +0000	pull: Fast-forward
208e2aa5706c52543c3468c48a6d0627541d76cc ed4144cb97cace05bb83f05b3d0401165f2b121a Luca Benedetto <luca.benedetto93@gmail.com> 1702573475 +0000	pull: Fast-forward
ed4144cb97cace05bb83f05b3d0401165f2b121a faeaa3c29c80a986f8d1bdb12ac5c31dd73f6b3f Luca Benedetto <luca.benedetto93@gmail.com> 1702653185 +0000	pull: Fast-forward
faeaa3c29c80a986f8d1bdb12ac5c31dd73f6b3f 38b932534bf9a4acaeecff857991bded082909e6 Luca Benedetto <luca.benedetto93@gmail.com> 1702656683 +0000	pull: Fast-forward
38b932534bf9a4acaeecff857991bded082909e6 5567110d237beea9e9a0c14de6cfdc9a04a15e6b Luca Benedetto <luca.benedetto93@gmail.com> 1713299567 +0100	commit: add plot for analysis generalisation on the three dataset
5567110d237beea9e9a0c14de6cfdc9a04a15e6b 4793794e5d6aa6892420c18b3d0c3de937168d49 Luca Benedetto <luca.benedetto93@gmail.com> 1713299584 +0100	commit: remove comment
4793794e5d6aa6892420c18b3d0c3de937168d49 992eb6186db3f5c9f450b358ef8534963bb45d5a Luca Benedetto <luca.benedetto93@gmail.com> 1713300056 +0100	commit: update plot gpt4 vs. gpt3.5 to improve readability
992eb6186db3f5c9f450b358ef8534963bb45d5a 2671928e22121a685d4f68ebb913b54eab3fa75d Luca Benedetto <luca.benedetto93@gmail.com> 1715675317 +0100	commit: update figure for analysis generalisation to new datasets
2671928e22121a685d4f68ebb913b54eab3fa75d fbcd71b04417432e462d2487686d5ea1d2b0429a Luca Benedetto <luca.benedetto93@gmail.com> 1715675642 +0100	commit: update plot comparison with reference prompt
fbcd71b04417432e462d2487686d5ea1d2b0429a ea82df35b4c947f46339288851b1b7b04aa4cfa1 Luca Benedetto <luca.benedetto93@gmail.com> 1715675662 +0100	commit: fix commented line
ea82df35b4c947f46339288851b1b7b04aa4cfa1 d88e15f33b6b6c7eddb8e5bf322c9ff2b2eb0953 Luca Benedetto <luca.benedetto93@gmail.com> 1715690832 +0100	commit: add plot CUPA MCQA accuracy per difficulty level
d88e15f33b6b6c7eddb8e5bf322c9ff2b2eb0953 1cf2385522053468f8e68433227b9f98b32cf10d Luca Benedetto <luca.benedetto93@gmail.com> 1715691014 +0100	commit: update size of plots MCQA accuracy per difficulty level
1cf2385522053468f8e68433227b9f98b32cf10d 72c99e251bc6f1ce3696d2c2b3ccb9c8b9d7b7c4 Luca Benedetto <luca.benedetto93@gmail.com> 1715693565 +0100	commit: add new version of plots for comparison different llms
72c99e251bc6f1ce3696d2c2b3ccb9c8b9d7b7c4 0a9d4bfcda5769043581b875ac0edc3268e36b7c Luca Benedetto <luca.benedetto93@gmail.com> 1715701333 +0100	commit: add plt.tight_layout()
0a9d4bfcda5769043581b875ac0edc3268e36b7c b09e1da8fce07290c78b5211b3f7f3fe6866de7a Luca Benedetto <luca.benedetto93@gmail.com> 1715701375 +0100	commit: add plt.tight_layout()
b09e1da8fce07290c78b5211b3f7f3fe6866de7a 2267f12a2cf52fd7fcf2dea755e9a125518315f8 Luca Benedetto <luca.benedetto93@gmail.com> 1715766912 +0100	pull: Fast-forward
2267f12a2cf52fd7fcf2dea755e9a125518315f8 5428276f19fee1a7f6130caa95b33e33e9a95756 Luca Benedetto <luca.benedetto93@gmail.com> 1715777839 +0100	pull: Fast-forward
5428276f19fee1a7f6130caa95b33e33e9a95756 56647a8af75ca6607f36621d5b8c80c9a130a2e3 Luca Benedetto <luca.benedetto93@gmail.com> 1716993413 +0100	pull: Fast-forward
56647a8af75ca6607f36621d5b8c80c9a130a2e3 8d1f48e55c89ed8344f879eb63873d9d12655291 Luca Benedetto <luca.benedetto93@gmail.com> 1717747023 +0100	commit: refactor eval metric monotonicity
8d1f48e55c89ed8344f879eb63873d9d12655291 043b6179e05403061d7f06399ec99085084d581f Luca Benedetto <luca.benedetto93@gmail.com> 1717747071 +0100	commit: add plot_metrics_difficulty_analysis
043b6179e05403061d7f06399ec99085084d581f 104a17f183bb5565063822e6d8e5440cfe2bd07e Luca Benedetto <luca.benedetto93@gmail.com> 1717749059 +0100	commit: add script for plotting the confusion matrices of the explanation analysis, the values are taken from another script
