Hugging Face's logo

Fiddi
/
distilbert-base-uncased-finetuned-ner

Token Classification
Transformers
PyTorch
TensorBoard
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
2
Fiddi commited on
Commit
23036ee
•
1 Parent(s): a841c28

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -13
README.md CHANGED
@@ -22,16 +22,16 @@ model-index:
22
  metrics:
23
  - name: Precision
24
  type: precision
25
- value: 0.9278761061946903
26
  - name: Recall
27
  type: recall
28
- value: 0.9383599955252265
29
  - name: F1
30
  type: f1
31
- value: 0.9330886033705991
32
  - name: Accuracy
33
  type: accuracy
34
- value: 0.9839865283492462
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -41,10 +41,10 @@ should probably proofread and complete it, then remove this comment. -->
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
- - Loss: 0.0612
45
- - Precision: 0.9279
46
- - Recall: 0.9384
47
- - F1: 0.9331
48
  - Accuracy: 0.9840
49
 
50
  ## Model description
@@ -76,14 +76,14 @@ The following hyperparameters were used during training:
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
- | 0.2483 | 1.0 | 878 | 0.0697 | 0.9078 | 0.9217 | 0.9147 | 0.9807 |
80
- | 0.0529 | 2.0 | 1756 | 0.0609 | 0.9213 | 0.9349 | 0.9280 | 0.9831 |
81
- | 0.0316 | 3.0 | 2634 | 0.0612 | 0.9279 | 0.9384 | 0.9331 | 0.9840 |
82
 
83
 
84
  ### Framework versions
85
 
86
- - Transformers 4.11.2
87
- - Pytorch 1.9.0+cu102
88
  - Datasets 1.12.1
89
  - Tokenizers 0.10.3
 
22
  metrics:
23
  - name: Precision
24
  type: precision
25
+ value: 0.9278202147680726
26
  - name: Recall
27
  type: recall
28
+ value: 0.9375769101689228
29
  - name: F1
30
  type: f1
31
+ value: 0.9326730469619409
32
  - name: Accuracy
33
  type: accuracy
34
+ value: 0.9839706419686403
35
  ---
36
 
37
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
41
 
42
  This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the conll2003 dataset.
43
  It achieves the following results on the evaluation set:
44
+ - Loss: 0.0595
45
+ - Precision: 0.9278
46
+ - Recall: 0.9376
47
+ - F1: 0.9327
48
  - Accuracy: 0.9840
49
 
50
  ## Model description
 
76
 
77
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
78
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
79
+ | 0.2414 | 1.0 | 878 | 0.0702 | 0.9143 | 0.9223 | 0.9182 | 0.9808 |
80
+ | 0.0503 | 2.0 | 1756 | 0.0603 | 0.9186 | 0.9337 | 0.9260 | 0.9831 |
81
+ | 0.0306 | 3.0 | 2634 | 0.0595 | 0.9278 | 0.9376 | 0.9327 | 0.9840 |
82
 
83
 
84
  ### Framework versions
85
 
86
+ - Transformers 4.11.3
87
+ - Pytorch 1.9.0+cu111
88
  - Datasets 1.12.1
89
  - Tokenizers 0.10.3