lewtun HF staff commited on
Commit
d91a486
1 Parent(s): 38e2c17

Add evaluation results on masakhaner dataset

Browse files

Beep boop, I am a bot from Hugging Face's automatic model evaluator 👋!\
Your model has been evaluated on the [masakhaner](https://huggingface.co/datasets/masakhaner) dataset by

@lewtun

, using the predictions stored [here](https://huggingface.co/datasets/autoevaluate/autoeval-staging-eval-project-ab647f27-7704971).\
Accept this pull request to see the results displayed on the [Hub leaderboard](https://huggingface.co/spaces/autoevaluate/leaderboards?dataset=masakhaner).\
Evaluate your model on more datasets [here](https://huggingface.co/spaces/autoevaluate/model-evaluator?dataset=masakhaner).

Files changed (1) hide show
  1. README.md +36 -3
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- language:
3
- - yo
4
  tags:
5
  - NER
6
  datasets:
@@ -10,7 +10,40 @@ metrics:
10
  - precision
11
  - recall
12
  widget:
13
- - text: " ẹ̀rí ó fi ẹsẹ̀ rinlẹ̀ ."
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
 
 
1
  ---
2
+ language:
3
+ - yo
4
  tags:
5
  - NER
6
  datasets:
 
10
  - precision
11
  - recall
12
  widget:
13
+ - text: "K\xF2 s\xED \u1EB9\u0300r\xED t\xED \xF3 fi \u1EB9s\u1EB9\u0300 rinl\u1EB9\
14
+ \u0300 ."
15
+ model-index:
16
+ - name: mbeukman/xlm-roberta-base-finetuned-swahili-finetuned-ner-yoruba
17
+ results:
18
+ - task:
19
+ type: token-classification
20
+ name: Token Classification
21
+ dataset:
22
+ name: masakhaner
23
+ type: masakhaner
24
+ config: yor
25
+ split: test
26
+ metrics:
27
+ - name: Accuracy
28
+ type: accuracy
29
+ value: 0.9407527591063883
30
+ verified: true
31
+ - name: Precision
32
+ type: precision
33
+ value: 0.944257816826018
34
+ verified: true
35
+ - name: Recall
36
+ type: recall
37
+ value: 0.9620505491199037
38
+ verified: true
39
+ - name: F1
40
+ type: f1
41
+ value: 0.9530711477914191
42
+ verified: true
43
+ - name: loss
44
+ type: loss
45
+ value: 0.49712973833084106
46
+ verified: true
47
  ---
48
 
49