Hugging Face's logo

Conrad747
/
luganda-ner-v4

Token Classification
Transformers
PyTorch
deberta-v2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
1
Conrad747 commited on
Commit
e829989
•
1 Parent(s): 6dd20ae

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.7849185946872322
28
  - name: Recall
29
  type: recall
30
- value: 0.7862660944206008
31
  - name: F1
32
  type: f1
33
- value: 0.7855917667238421
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9542220362038296
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 [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the lg-ner dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.2222
47
- - Precision: 0.7849
48
- - Recall: 0.7863
49
- - F1: 0.7856
50
- - Accuracy: 0.9542
51
 
52
  ## Model description
53
 
@@ -78,21 +78,21 @@ 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 | 0.3533 | 0.6141 | 0.4644 | 0.5288 | 0.9208 |
82
- | 0.5126 | 2.0 | 522 | 0.2765 | 0.6658 | 0.6567 | 0.6612 | 0.9326 |
83
- | 0.5126 | 3.0 | 783 | 0.2336 | 0.6834 | 0.7133 | 0.6980 | 0.9433 |
84
- | 0.2374 | 4.0 | 1044 | 0.2207 | 0.7358 | 0.7433 | 0.7395 | 0.9489 |
85
- | 0.2374 | 5.0 | 1305 | 0.2134 | 0.7796 | 0.7528 | 0.7659 | 0.9525 |
86
- | 0.1646 | 6.0 | 1566 | 0.2359 | 0.7423 | 0.7665 | 0.7542 | 0.9484 |
87
- | 0.1646 | 7.0 | 1827 | 0.2223 | 0.7807 | 0.7854 | 0.7831 | 0.9541 |
88
- | 0.1219 | 8.0 | 2088 | 0.2300 | 0.8140 | 0.7665 | 0.7896 | 0.9557 |
89
- | 0.1219 | 9.0 | 2349 | 0.2223 | 0.7733 | 0.7966 | 0.7848 | 0.9547 |
90
- | 0.1016 | 10.0 | 2610 | 0.2222 | 0.7849 | 0.7863 | 0.7856 | 0.9542 |
91
 
92
 
93
  ### Framework versions
94
 
95
- - Transformers 4.26.1
96
  - Pytorch 1.13.1+cu116
97
- - Datasets 2.10.1
98
  - Tokenizers 0.13.2
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.7540871934604905
28
  - name: Recall
29
  type: recall
30
+ value: 0.7454545454545455
31
  - name: F1
32
  type: f1
33
+ value: 0.7497460209955976
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9360226606759132
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 [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the lg-ner dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.3024
47
+ - Precision: 0.7541
48
+ - Recall: 0.7455
49
+ - F1: 0.7497
50
+ - Accuracy: 0.9360
51
 
52
  ## Model description
53
 
 
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | No log | 1.0 | 261 | 0.4811 | 0.5366 | 0.2768 | 0.3652 | 0.8752 |
82
+ | 0.5133 | 2.0 | 522 | 0.3632 | 0.6560 | 0.5380 | 0.5912 | 0.9021 |
83
+ | 0.5133 | 3.0 | 783 | 0.3104 | 0.7069 | 0.5993 | 0.6487 | 0.9207 |
84
+ | 0.2592 | 4.0 | 1044 | 0.3339 | 0.7494 | 0.6303 | 0.6847 | 0.9269 |
85
+ | 0.2592 | 5.0 | 1305 | 0.3153 | 0.7513 | 0.6593 | 0.7023 | 0.9318 |
86
+ | 0.167 | 6.0 | 1566 | 0.3071 | 0.7190 | 0.7219 | 0.7204 | 0.9291 |
87
+ | 0.167 | 7.0 | 1827 | 0.3072 | 0.7955 | 0.7071 | 0.7487 | 0.9360 |
88
+ | 0.1191 | 8.0 | 2088 | 0.3133 | 0.7505 | 0.7455 | 0.7480 | 0.9339 |
89
+ | 0.1191 | 9.0 | 2349 | 0.3132 | 0.7510 | 0.7394 | 0.7452 | 0.9349 |
90
+ | 0.092 | 10.0 | 2610 | 0.3024 | 0.7541 | 0.7455 | 0.7497 | 0.9360 |
91
 
92
 
93
  ### Framework versions
94
 
95
+ - Transformers 4.27.4
96
  - Pytorch 1.13.1+cu116
97
+ - Datasets 2.11.0
98
  - Tokenizers 0.13.2