Jimin Huang commited on
Commit
43322c4
1 Parent(s): 3e16491

feature: add auto evaluation tab

Browse files
Files changed (3) hide show
  1. leaderboard.csv +0 -3
  2. leaderboard.csv.bak +11 -0
  3. leaderboard_auto.csv +4 -1
leaderboard.csv CHANGED
@@ -1,6 +1,3 @@
1
- GPT-NeoX,,0.45,0.51,0.73,0.61,,0.28,,,,,,
2
- OPT-66B,,0.49,0.52,0.79,0.57,,0.30,,,,,,
3
- BLOOM,,0.50,0.53,0.77,0.56,,0.36,,,,,,
4
  ChatGPT,0.78,0.78,,0.77,0.77,0.58,0.60,0.53,-0.025,0.50,0.005,0.55,0.01
5
  GPT-4,0.76,0.78,,0.86,0.83,0.63,0.76,0.54,0.03,0.52,0.02,0.57,0.01
6
  BloombergGPT,,0.51,0.75,0.82,0.61,,0.43,,,,,,
 
 
 
 
1
  ChatGPT,0.78,0.78,,0.77,0.77,0.58,0.60,0.53,-0.025,0.50,0.005,0.55,0.01
2
  GPT-4,0.76,0.78,,0.86,0.83,0.63,0.76,0.54,0.03,0.52,0.02,0.57,0.01
3
  BloombergGPT,,0.51,0.75,0.82,0.61,,0.43,,,,,,
leaderboard.csv.bak ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ GPT-NeoX,,0.45,0.51,0.73,0.61,,0.28,,,,,,
2
+ OPT-66B,,0.49,0.52,0.79,0.57,,0.30,,,,,,
3
+ BLOOM,,0.50,0.53,0.77,0.56,,0.36,,,,,,
4
+ ChatGPT,0.78,0.78,,0.77,0.77,0.58,0.60,0.53,-0.025,0.50,0.005,0.55,0.01
5
+ GPT-4,0.76,0.78,,0.86,0.83,0.63,0.76,0.54,0.03,0.52,0.02,0.57,0.01
6
+ BloombergGPT,,0.51,0.75,0.82,0.61,,0.43,,,,,,
7
+ FinMA-7B,0.86,0.86,0.84,0.98,0.75,0.06,0.25,0.48,0.04,0.50,0.00,0.56,-0.02
8
+ FinMA-30B,0.87,0.88,0.87,0.97,0.62,0.11,0.40,0.47,0.04,0.49,0.00,0.43,-0.05
9
+ FinMA-7B-full,0.88,0.88,0.83,0.97,0.67,0.06,0.32,0.51,0.06,0.52,0.03,0.52,0.04
10
+ FinCON-7B-full,0.86,0.86,0.87,0.97,0.59,0.01,0.12,0.51,0.05,0.5,0.0,0.53,0.06
11
+
leaderboard_auto.csv CHANGED
@@ -1,3 +1,6 @@
1
  llama-7b,0.02,0.08,0.95,0.31,0.02,0.76,0.05,0,0,0,1,0.02,0,0.96,0.08,0,0.84,0.01,0.02,0.99,0,0,0,0,1,0,0,1
2
  bloomz-7b,0.36,0.52,0.03,0.79,0.0,0.61,0.0,0.01,0.54,0.01,0.02,0.48,-0.02,0.06,0.51,-0.03,0.10,0.18,0.31,0.49,0,0,0,0,1,0.57,0.72,0
3
- chatgpt,0.78,0.78,0.0,,,0.77,0.56,0.58,0.53,-0.025,0,0.5,0.005,0,0.55,0.01,0,,,,,,,,,,,
 
 
 
 
1
  llama-7b,0.02,0.08,0.95,0.31,0.02,0.76,0.05,0,0,0,1,0.02,0,0.96,0.08,0,0.84,0.01,0.02,0.99,0,0,0,0,1,0,0,1
2
  bloomz-7b,0.36,0.52,0.03,0.79,0.0,0.61,0.0,0.01,0.54,0.01,0.02,0.48,-0.02,0.06,0.51,-0.03,0.10,0.18,0.31,0.49,0,0,0,0,1,0.57,0.72,0
3
+ chatgpt,0.78,0.78,0.0,,,0.77,0.77,0.58,0.53,-0.025,0,0.5,0.005,0,0.55,0.01,0,,,,,,,,,,,
4
+ GPT-4,0.76,0.78,0.0,,,0.86,0.83,0.63,0.54,0.03,0,0.52,0.02,0,0.57,0.01,0,,,,,,,,,,,
5
+ FinMA-7B,0.86,0.86,0.0,0.84,0.0,0.98,0.75,0.06,0.48,0.04,0.0,0.5,0.0,0,0.56,-0.02,0.0,,,,,,,,,,,
6
+ FinMA-7B-full,0.88,0.88,0.0,0.83,0,0.97,0.67,0.06,0.51,0.06,0.0,0.52,0.03,0.0,0.52,0.04,0.0,,,,,,,,,,,