Hugging Face's logo

LucasMagnana
/
bert-finetuned-ner

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
LucasMagnana commited on
Commit
f6a23eb
·
verified ·
1 Parent(s): 37bbeeb

Training complete

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -20,21 +20,21 @@ model-index:
20
  name: conll2003
21
  type: conll2003
22
  config: conll2003
23
- split: validation
24
  args: conll2003
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9348150605407198
29
  - name: Recall
30
  type: recall
31
- value: 0.9485021878155503
32
  - name: F1
33
  type: f1
34
- value: 0.9416088881463537
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9860040030611644
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0650
48
- - Precision: 0.9348
49
- - Recall: 0.9485
50
- - F1: 0.9416
51
- - Accuracy: 0.9860
52
 
53
  ## Model description
54
 
@@ -79,9 +79,9 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.0743 | 1.0 | 1756 | 0.0605 | 0.9008 | 0.9367 | 0.9184 | 0.9829 |
83
- | 0.0364 | 2.0 | 3512 | 0.0664 | 0.9300 | 0.9473 | 0.9386 | 0.9850 |
84
- | 0.0232 | 3.0 | 5268 | 0.0650 | 0.9348 | 0.9485 | 0.9416 | 0.9860 |
85
 
86
 
87
  ### Framework versions
 
20
  name: conll2003
21
  type: conll2003
22
  config: conll2003
23
+ split: None
24
  args: conll2003
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9341604631927213
29
  - name: Recall
30
  type: recall
31
+ value: 0.9503534163581285
32
  - name: F1
33
  type: f1
34
+ value: 0.9421873696504547
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9865191028433508
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the conll2003 dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.0615
48
+ - Precision: 0.9342
49
+ - Recall: 0.9504
50
+ - F1: 0.9422
51
+ - Accuracy: 0.9865
52
 
53
  ## Model description
54
 
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.0765 | 1.0 | 1756 | 0.0651 | 0.9007 | 0.9329 | 0.9165 | 0.9810 |
83
+ | 0.0373 | 2.0 | 3512 | 0.0626 | 0.9324 | 0.9451 | 0.9387 | 0.9853 |
84
+ | 0.0228 | 3.0 | 5268 | 0.0615 | 0.9342 | 0.9504 | 0.9422 | 0.9865 |
85
 
86
 
87
  ### Framework versions