JeremiahZ autoevaluator HF staff commited on
Commit
aec7163
1 Parent(s): 5791004

Add evaluation results on the cola config and validation split of glue (#1)

Browse files

- Add evaluation results on the cola config and validation split of glue (2bab33629149fe2619223d8f0e8eeda0a870dedc)


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

Files changed (1) hide show
  1. README.md +53 -0
README.md CHANGED
@@ -22,6 +22,59 @@ model-index:
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
  value: 0.5880094937717885
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
22
  - name: Matthews Correlation
23
  type: matthews_correlation
24
  value: 0.5880094937717885
25
+ - task:
26
+ type: text-classification
27
+ name: Text Classification
28
+ dataset:
29
+ name: glue
30
+ type: glue
31
+ config: cola
32
+ split: validation
33
+ metrics:
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.8322147651006712
37
+ verified: true
38
+ - name: Precision Macro
39
+ type: precision
40
+ value: 0.830203748981255
41
+ verified: true
42
+ - name: Precision Micro
43
+ type: precision
44
+ value: 0.8322147651006712
45
+ verified: true
46
+ - name: Precision Weighted
47
+ type: precision
48
+ value: 0.8315568610076411
49
+ verified: true
50
+ - name: Recall Macro
51
+ type: recall
52
+ value: 0.7617741060121812
53
+ verified: true
54
+ - name: Recall Micro
55
+ type: recall
56
+ value: 0.8322147651006712
57
+ verified: true
58
+ - name: Recall Weighted
59
+ type: recall
60
+ value: 0.8322147651006712
61
+ verified: true
62
+ - name: F1 Macro
63
+ type: f1
64
+ value: 0.7831814623565482
65
+ verified: true
66
+ - name: F1 Micro
67
+ type: f1
68
+ value: 0.8322147651006712
69
+ verified: true
70
+ - name: F1 Weighted
71
+ type: f1
72
+ value: 0.8226255909753084
73
+ verified: true
74
+ - name: loss
75
+ type: loss
76
+ value: 0.5406177043914795
77
+ verified: true
78
  ---
79
 
80
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You