Add evaluation results on trec dataset

#1
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +59 -3
README.md CHANGED
@@ -1,13 +1,69 @@
1
  ---
2
- language:
3
  - en
4
- thumbnail:
5
  tags:
6
  - text-classification
7
  license: mit
8
  datasets:
9
  - trec
10
- metrics:
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  # bert-base-cased trained on TREC 6-class task
 
1
  ---
2
+ language:
3
  - en
4
+ thumbnail: null
5
  tags:
6
  - text-classification
7
  license: mit
8
  datasets:
9
  - trec
10
+ metrics: null
11
+ model-index:
12
+ - name: aychang/bert-base-cased-trec-coarse
13
+ results:
14
+ - task:
15
+ type: text-classification
16
+ name: Text Classification
17
+ dataset:
18
+ name: trec
19
+ type: trec
20
+ config: default
21
+ split: test
22
+ metrics:
23
+ - name: Accuracy
24
+ type: accuracy
25
+ value: 0.974
26
+ verified: true
27
+ - name: Precision Macro
28
+ type: precision
29
+ value: 0.9793164100816639
30
+ verified: true
31
+ - name: Precision Micro
32
+ type: precision
33
+ value: 0.974
34
+ verified: true
35
+ - name: Precision Weighted
36
+ type: precision
37
+ value: 0.9746805065928548
38
+ verified: true
39
+ - name: Recall Macro
40
+ type: recall
41
+ value: 0.9783617516169679
42
+ verified: true
43
+ - name: Recall Micro
44
+ type: recall
45
+ value: 0.974
46
+ verified: true
47
+ - name: Recall Weighted
48
+ type: recall
49
+ value: 0.974
50
+ verified: true
51
+ - name: F1 Macro
52
+ type: f1
53
+ value: 0.9783635353409951
54
+ verified: true
55
+ - name: F1 Micro
56
+ type: f1
57
+ value: 0.974
58
+ verified: true
59
+ - name: F1 Weighted
60
+ type: f1
61
+ value: 0.97377371266232
62
+ verified: true
63
+ - name: loss
64
+ type: loss
65
+ value: 0.13812002539634705
66
+ verified: true
67
  ---
68
 
69
  # bert-base-cased trained on TREC 6-class task