Hugging Face's logo

Kriyans
/
Bert-NER

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
28
Kriyans commited on
Commit
3e7d79e
·
1 Parent(s): ec8cf71

End of training

Browse files
Files changed (1) hide show
  1. README.md +15 -13
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9960679780215291
29
  - name: Recall
30
  type: recall
31
- value: 0.9775873302260312
32
  - name: F1
33
  type: f1
34
- value: 0.9867411308232034
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9929220376370028
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0221
48
- - Precision: 0.9961
49
- - Recall: 0.9776
50
- - F1: 0.9867
51
- - Accuracy: 0.9929
52
 
53
  ## Model description
54
 
@@ -73,15 +73,17 @@ The following hyperparameters were used during training:
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 3
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 469 | 0.0397 | 0.9929 | 0.9595 | 0.9759 | 0.9873 |
83
- | 0.0422 | 2.0 | 938 | 0.0296 | 0.9892 | 0.9739 | 0.9815 | 0.9901 |
84
- | 0.0343 | 3.0 | 1407 | 0.0221 | 0.9961 | 0.9776 | 0.9867 | 0.9929 |
 
 
85
 
86
 
87
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9835852784414629
29
  - name: Recall
30
  type: recall
31
+ value: 0.9699698679172614
32
  - name: F1
33
  type: f1
34
+ value: 0.9767301265014201
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9882015601687542
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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the ner dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.0334
48
+ - Precision: 0.9836
49
+ - Recall: 0.9700
50
+ - F1: 0.9767
51
+ - Accuracy: 0.9882
52
 
53
  ## Model description
54
 
 
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 5
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 1.0 | 486 | 0.0584 | 0.9738 | 0.9574 | 0.9655 | 0.9821 |
83
+ | 0.116 | 2.0 | 972 | 0.0459 | 0.9751 | 0.9646 | 0.9698 | 0.9849 |
84
+ | 0.0561 | 3.0 | 1458 | 0.0395 | 0.9803 | 0.9668 | 0.9735 | 0.9867 |
85
+ | 0.0446 | 4.0 | 1944 | 0.0353 | 0.9819 | 0.9686 | 0.9752 | 0.9875 |
86
+ | 0.0409 | 5.0 | 2430 | 0.0334 | 0.9836 | 0.9700 | 0.9767 | 0.9882 |
87
 
88
 
89
  ### Framework versions