Hugging Face's logo

Conrad747
/
luganda-ner-v1

Token Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
2
Conrad747 commited on
Commit
41e7f24
·
1 Parent(s): b7b3494

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -19
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.7958904109589041
28
  - name: Recall
29
  type: recall
30
- value: 0.7803895231699127
31
  - name: F1
32
  type: f1
33
- value: 0.7880637504238724
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9450776825903877
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the lg-ner dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.2863
47
- - Precision: 0.7959
48
- - Recall: 0.7804
49
- - F1: 0.7881
50
- - Accuracy: 0.9451
51
 
52
  ## Model description
53
 
@@ -78,16 +78,16 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
- | No log | 1.0 | 261 | 0.5454 | 0.4946 | 0.2471 | 0.3296 | 0.8597 |
82
- | 0.6168 | 2.0 | 522 | 0.3598 | 0.6993 | 0.5608 | 0.6224 | 0.9078 |
83
- | 0.6168 | 3.0 | 783 | 0.3842 | 0.6326 | 0.6696 | 0.6506 | 0.8941 |
84
- | 0.2599 | 4.0 | 1044 | 0.2755 | 0.7857 | 0.6870 | 0.7331 | 0.9333 |
85
- | 0.2599 | 5.0 | 1305 | 0.2642 | 0.8019 | 0.7206 | 0.7591 | 0.9351 |
86
- | 0.1498 | 6.0 | 1566 | 0.2755 | 0.7886 | 0.7589 | 0.7734 | 0.9385 |
87
- | 0.1498 | 7.0 | 1827 | 0.2601 | 0.7945 | 0.7609 | 0.7774 | 0.9458 |
88
- | 0.1023 | 8.0 | 2088 | 0.2889 | 0.7875 | 0.7717 | 0.7795 | 0.9409 |
89
- | 0.1023 | 9.0 | 2349 | 0.2819 | 0.8082 | 0.7670 | 0.7870 | 0.9460 |
90
- | 0.0716 | 10.0 | 2610 | 0.2863 | 0.7959 | 0.7804 | 0.7881 | 0.9451 |
91
 
92
 
93
  ### Framework versions
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.7987967914438503
28
  - name: Recall
29
  type: recall
30
+ value: 0.8025520483546004
31
  - name: F1
32
  type: f1
33
+ value: 0.8006700167504188
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9451502831421519
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the lg-ner dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.3188
47
+ - Precision: 0.7988
48
+ - Recall: 0.8026
49
+ - F1: 0.8007
50
+ - Accuracy: 0.9452
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 1.0 | 261 | 0.2915 | 0.7456 | 0.6891 | 0.7162 | 0.9240 |
82
+ | 0.2284 | 2.0 | 522 | 0.2965 | 0.7393 | 0.7314 | 0.7353 | 0.9294 |
83
+ | 0.2284 | 3.0 | 783 | 0.2830 | 0.7426 | 0.7576 | 0.7500 | 0.9271 |
84
+ | 0.1426 | 4.0 | 1044 | 0.2710 | 0.7935 | 0.7690 | 0.7810 | 0.9387 |
85
+ | 0.1426 | 5.0 | 1305 | 0.2805 | 0.8087 | 0.7636 | 0.7855 | 0.9389 |
86
+ | 0.0881 | 6.0 | 1566 | 0.2992 | 0.7734 | 0.7884 | 0.7808 | 0.9404 |
87
+ | 0.0881 | 7.0 | 1827 | 0.2746 | 0.8109 | 0.7864 | 0.7985 | 0.9457 |
88
+ | 0.0582 | 8.0 | 2088 | 0.3149 | 0.7753 | 0.7925 | 0.7838 | 0.9400 |
89
+ | 0.0582 | 9.0 | 2349 | 0.3179 | 0.7940 | 0.7945 | 0.7942 | 0.9440 |
90
+ | 0.0403 | 10.0 | 2610 | 0.3188 | 0.7988 | 0.8026 | 0.8007 | 0.9452 |
91
 
92
 
93
  ### Framework versions