yhyu13 commited on
Commit
97d7a28
1 Parent(s): b07ed04

Add chatgpt alpacaeval result

Browse files
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4/alpaca_eval_log.txt ADDED
The diff for this file is too large to render. See raw diff
 
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4/annotation_chatgpt_fn.json ADDED
The diff for this file is too large to render. See raw diff
 
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4/leaderboard.csv ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ,win_rate,standard_error,n_wins,n_wins_base,n_draws,n_total,mode,avg_length
2
+ gpt4,73.7888198757764,1.5359801545073597,588,205,12,805,minimal,1365
3
+ claude,70.37267080745342,1.599519507147828,562,234,9,805,minimal,1082
4
+ chatgpt,66.08695652173913,1.6626479994330317,529,270,6,805,minimal,811
5
+ wizardlm-13b,65.15527950310559,1.670034107787565,520,276,9,805,minimal,985
6
+ vicuna-13b,64.09937888198758,1.6895185863153146,515,288,2,805,minimal,1037
7
+ guanaco-65b,62.36024844720497,1.7086348811605765,502,303,0,805,minimal,1249
8
+ oasst-rlhf-llama-33b,62.0496894409938,1.7080028976103514,498,304,3,805,minimal,1079
9
+ alpaca-farm-ppo-human,60.24844720496895,1.7169496733548772,481,316,8,805,minimal,803
10
+ falcon-40b-instruct,56.52173913043478,1.7438750520312944,453,348,4,805,minimal,662
11
+ phi-2-alpaca-gpt4,54.22885572139303,1.7537289814567856,434,366,4,804,community,1138
12
+ text_davinci_003,50.0,0.0,0,0,805,805,minimal,307
13
+ alpaca-7b,45.21739130434783,1.7375846781579476,356,433,16,805,minimal,396
14
+ phi-2,43.7888198757764,1.7441776958694664,350,450,5,805,community,924
15
+ text_davinci_001,28.07453416149068,1.5602183426587484,216,569,20,805,minimal,296
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4/model_outputs.json ADDED
The diff for this file is too large to render. See raw diff
 
alpaca_eval/chatgpt_fn_--phi-2-alpaca-gpt4/reference_outputs.json ADDED
The diff for this file is too large to render. See raw diff