Add evaluation results on masakhaner dataset

#1
by autoevaluator HF staff - opened
Files changed (1) hide show
  1. README.md +39 -3
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- language:
3
- - am
4
  tags:
5
  - NER
6
  - token-classification
@@ -11,7 +11,43 @@ metrics:
11
  - precision
12
  - recall
13
  widget:
14
- - text: "ቀዳሚው የሶማሌ ክልል በአወዳይ ከተማ ለተገደሉ የክልሉ ተወላጆች ያከናወነው የቀብር ስነ ስርዓትን የተመለከተ ዘገባ ነው ፡፡"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  ---
16
 
17
 
 
1
  ---
2
+ language:
3
+ - am
4
  tags:
5
  - NER
6
  - token-classification
 
11
  - precision
12
  - recall
13
  widget:
14
+ - text: "\u1240\u12F3\u121A\u12CD \u12E8\u1236\u121B\u120C \u12AD\u120D\u120D \u1260\
15
+ \u12A0\u12C8\u12F3\u12ED \u12A8\u1270\u121B \u1208\u1270\u1308\u12F0\u1209 \u12E8\
16
+ \u12AD\u120D\u1209 \u1270\u12C8\u120B\u1306\u127D \u12EB\u12A8\u1293\u12C8\u1290\
17
+ \u12CD \u12E8\u1240\u1265\u122D \u1235\u1290 \u1235\u122D\u12D3\u1275\u1295 \u12E8\
18
+ \u1270\u1218\u1208\u12A8\u1270 \u12D8\u1308\u1263 \u1290\u12CD \u1361\u1361"
19
+ model-index:
20
+ - name: mbeukman/xlm-roberta-base-finetuned-ner-amharic
21
+ results:
22
+ - task:
23
+ type: token-classification
24
+ name: Token Classification
25
+ dataset:
26
+ name: masakhaner
27
+ type: masakhaner
28
+ config: amh
29
+ split: test
30
+ metrics:
31
+ - name: Accuracy
32
+ type: accuracy
33
+ value: 0.9112588436203952
34
+ verified: true
35
+ - name: Precision
36
+ type: precision
37
+ value: 0.9385994025887819
38
+ verified: true
39
+ - name: Recall
40
+ type: recall
41
+ value: 0.9238810846128717
42
+ verified: true
43
+ - name: F1
44
+ type: f1
45
+ value: 0.931182087586434
46
+ verified: true
47
+ - name: loss
48
+ type: loss
49
+ value: 0.6867610216140747
50
+ verified: true
51
  ---
52
 
53