bergum autoevaluator HF staff commited on
Commit
0a67a88
1 Parent(s): c37fe26

Add evaluation results on the default config of emotion (#2)

Browse files

- Add evaluation results on the default config of emotion (966a6723c009147bcb240e7df1acc70b8dc132ef)


Co-authored-by: Evaluation Bot <autoevaluator@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -20,6 +20,59 @@ model-index:
20
  - name: Accuracy
21
  type: accuracy
22
  value: 0.9265
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  ---
24
 
25
  # xtremedistil-emotion
 
20
  - name: Accuracy
21
  type: accuracy
22
  value: 0.9265
23
+ - task:
24
+ type: text-classification
25
+ name: Text Classification
26
+ dataset:
27
+ name: emotion
28
+ type: emotion
29
+ config: default
30
+ split: test
31
+ metrics:
32
+ - name: Accuracy
33
+ type: accuracy
34
+ value: 0.926
35
+ verified: true
36
+ - name: Precision Macro
37
+ type: precision
38
+ value: 0.8855308537052737
39
+ verified: true
40
+ - name: Precision Micro
41
+ type: precision
42
+ value: 0.926
43
+ verified: true
44
+ - name: Precision Weighted
45
+ type: precision
46
+ value: 0.9281282413639949
47
+ verified: true
48
+ - name: Recall Macro
49
+ type: recall
50
+ value: 0.8969894921856228
51
+ verified: true
52
+ - name: Recall Micro
53
+ type: recall
54
+ value: 0.926
55
+ verified: true
56
+ - name: Recall Weighted
57
+ type: recall
58
+ value: 0.926
59
+ verified: true
60
+ - name: F1 Macro
61
+ type: f1
62
+ value: 0.8903400738742536
63
+ verified: true
64
+ - name: F1 Micro
65
+ type: f1
66
+ value: 0.926
67
+ verified: true
68
+ - name: F1 Weighted
69
+ type: f1
70
+ value: 0.9265018282649476
71
+ verified: true
72
+ - name: loss
73
+ type: loss
74
+ value: 0.2258329838514328
75
+ verified: true
76
  ---
77
 
78
  # xtremedistil-emotion