-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
3 changed files
with
74 additions
and
0 deletions.
There are no files selected for viewing
35 changes: 35 additions & 0 deletions
35
automation-api/yival_experiments/output/report_tables/1_number_of_average_answers.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
model_configuration_id,prompt_variation_id,number_of_answers,model_name | ||
mc019,prompt3,1.5,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc024,prompt2,1.0607142857142857,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" | ||
mc021,prompt1,1.167857142857143,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc023,prompt2,1.6535714285714285,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc015,prompt2,1.0613026819923372,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc019,prompt2,1.0,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc018,prompt1,1.7633587786259541,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc016,prompt2,1.0190839694656488,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc015,prompt1,1.0766283524904214,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc021,prompt3,1.042857142857143,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc024,prompt1,1.0571428571428572,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" | ||
mc023,prompt3,1.4392857142857143,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc015,prompt3,1.0,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc020,prompt1,1.0214285714285714,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc018,prompt2,1.6641221374045803,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc014,prompt2,1.0240384615384615,"Alibaba Qianwen Plus {""top_p"": 0.1, ""top_k"": 100}" | ||
mc014,prompt1,1.0096153846153846,"Alibaba Qianwen Plus {""top_p"": 0.1, ""top_k"": 100}" | ||
mc021,prompt2,1.1,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc009,prompt2,1.7644787644787645,"Google PaLM (Text Bison) {""temperature"": 0.01}" | ||
mc022,prompt3,1.1321428571428571,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" | ||
mc016,prompt3,1.0,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc009,prompt1,1.9034749034749034,"Google PaLM (Text Bison) {""temperature"": 0.01}" | ||
mc023,prompt1,1.4214285714285715,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc024,prompt3,1.05,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" | ||
mc017,prompt1,1.1603053435114503,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc020,prompt3,1.0178571428571428,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc020,prompt2,1.0,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc019,prompt1,1.0,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc017,prompt2,1.1488549618320612,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc016,prompt1,1.0458015267175573,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc018,prompt3,1.5,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc017,prompt3,1.0,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc022,prompt1,1.0857142857142856,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" | ||
mc022,prompt2,1.1178571428571429,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" |
35 changes: 35 additions & 0 deletions
35
automation-api/yival_experiments/output/report_tables/2_average_rates.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,35 @@ | ||
model_configuration_id,prompt_variation_id,total_questions_asked,Correct Rate %,Wrong Rate %,Very Wrong Rate %,Indecisive Rate %,model_name | ||
mc019,prompt1,2,50.0,0.0,50.0,0.0,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc021,prompt2,280,82.5,12.5,2.5,2.5,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc022,prompt2,280,65.0,25.0,8.928571428571429,1.0714285714285714,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" | ||
mc024,prompt1,280,79.64285714285714,16.785714285714285,3.571428571428571,0.0,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" | ||
mc015,prompt2,261,50.191570881226056,36.7816091954023,9.961685823754788,3.065134099616858,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc019,prompt3,2,50.0,50.0,0.0,0.0,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc020,prompt2,280,63.92857142857142,26.071428571428573,9.642857142857144,0.35714285714285715,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc023,prompt1,280,64.64285714285715,15.714285714285714,8.928571428571429,10.714285714285714,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc024,prompt3,280,74.28571428571429,23.57142857142857,2.142857142857143,0.0,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" | ||
mc014,prompt1,208,36.53846153846153,32.21153846153847,12.01923076923077,19.230769230769234,"Alibaba Qianwen Plus {""top_p"": 0.1, ""top_k"": 100}" | ||
mc023,prompt3,280,62.142857142857146,21.428571428571427,8.928571428571429,7.5,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc016,prompt2,262,67.93893129770993,14.50381679389313,11.068702290076336,6.488549618320611,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc016,prompt1,262,38.93129770992366,45.80152671755725,15.267175572519085,0.0,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc017,prompt1,262,59.16030534351145,27.099236641221374,2.2900763358778624,11.450381679389313,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc018,prompt2,262,61.06870229007634,13.740458015267176,9.923664122137405,15.267175572519085,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc018,prompt1,262,34.73282442748092,41.603053435114504,17.17557251908397,6.488549618320611,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc016,prompt3,2,50.0,50.0,0.0,0.0,"OpenAI GPT3.5 June 2023 {""temperature"": 0.01}" | ||
mc017,prompt2,262,63.358778625954194,15.267175572519085,0.7633587786259541,20.610687022900763,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc017,prompt3,2,50.0,0.0,0.0,50.0,"OpenAI GPT4 June 2023 {""temperature"": 0.01}" | ||
mc018,prompt3,2,0.0,100.0,0.0,0.0,"OpenAI GPT3.5 June 2023 {""temperature"": 1}" | ||
mc014,prompt2,208,40.38461538461539,21.153846153846153,13.461538461538462,25.0,"Alibaba Qianwen Plus {""top_p"": 0.1, ""top_k"": 100}" | ||
mc020,prompt1,280,53.57142857142857,37.857142857142854,8.571428571428571,0.0,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc023,prompt2,280,65.0,17.857142857142858,3.571428571428571,13.571428571428571,"Alibaba Qianwen Max {""temperature"": 0.01}" | ||
mc015,prompt1,261,31.800766283524908,50.191570881226056,16.091954022988507,1.9157088122605364,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc019,prompt2,2,100.0,0.0,0.0,0.0,"Google PaLM (Chat Bison) {""temperature"": 0.01}" | ||
mc020,prompt3,280,50.357142857142854,39.64285714285714,10.0,0.0,"Google Gemini Pro {""temperature"": 0.01}" | ||
mc021,prompt1,280,78.57142857142857,18.21428571428571,2.5,0.7142857142857143,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc022,prompt1,280,37.142857142857146,48.214285714285715,14.285714285714285,0.35714285714285715,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" | ||
mc009,prompt1,259,38.996138996138995,27.7992277992278,22.393822393822393,10.81081081081081,"Google PaLM (Text Bison) {""temperature"": 0.01}" | ||
mc009,prompt2,259,36.293436293436294,42.084942084942085,14.671814671814673,6.94980694980695,"Google PaLM (Text Bison) {""temperature"": 0.01}" | ||
mc015,prompt3,2,50.0,50.0,0.0,0.0,"Meta llama2 (hosted on replicate) {""temperature"": 0.01}" | ||
mc021,prompt3,280,76.42857142857142,21.071428571428573,2.5,0.0,"OpenAI GPT4 Turbo Nov 2023 {""temperature"": 0.01}" | ||
mc022,prompt3,280,35.0,50.0,15.0,0.0,"OpenAI GPT3.5 Nov 2023' {""temperature"": 0.01}" | ||
mc024,prompt2,280,84.28571428571429,13.214285714285715,2.142857142857143,0.35714285714285715,"OpenAI GPT4 Turbo Jan 2024 {""temperature"": 0.01}" |
4 changes: 4 additions & 0 deletions
4
automation-api/yival_experiments/output/report_tables/3_correct_rate_by_prompt.csv
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,4 @@ | ||
prompt_variation_id,total_questions_asked,Correct Rate %,Wrong Rate %,Very Wrong Rate %,Indecisive Rate % | ||
prompt1,1410,62.5531914893617,27.4468085106383,7.588652482269503,2.4113475177304964 | ||
prompt2,1410,72.12765957446808,18.79432624113475,5.319148936170213,3.7588652482269502 | ||
prompt3,1410,59.50354609929078,31.27659574468085,7.659574468085106,1.5602836879432624 |