Hugging Face's logo

Kriyans
/
Bert-NER

Token Classification
Transformers
PyTorch
TensorBoard
Safetensors
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
28
Kriyans commited on
Commit
775c3c5
•
1 Parent(s): e370f47

End of training

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9896954662296407
29
  - name: Recall
30
  type: recall
31
- value: 0.9704150478224023
32
  - name: F1
33
  type: f1
34
- value: 0.9799604321344418
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9894401834309103
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: 0.0320
48
- - Precision: 0.9897
49
- - Recall: 0.9704
50
- - F1: 0.9800
51
- - Accuracy: 0.9894
52
 
53
  ## Model description
54
 
@@ -67,7 +67,7 @@ More information needed
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
- - learning_rate: 0.0001
71
  - train_batch_size: 16
72
  - eval_batch_size: 16
73
  - seed: 42
@@ -79,16 +79,16 @@ The following hyperparameters were used during training:
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.0503 | 0.58 | 500 | 0.0506 | 0.9744 | 0.9656 | 0.9700 | 0.9846 |
83
- | 0.0461 | 1.17 | 1000 | 0.0450 | 0.9781 | 0.9657 | 0.9719 | 0.9856 |
84
- | 0.0428 | 1.75 | 1500 | 0.0424 | 0.9804 | 0.9677 | 0.9740 | 0.9864 |
85
- | 0.0379 | 2.33 | 2000 | 0.0375 | 0.9839 | 0.9704 | 0.9771 | 0.9880 |
86
- | 0.0352 | 2.91 | 2500 | 0.0320 | 0.9897 | 0.9704 | 0.9800 | 0.9894 |
87
 
88
 
89
  ### Framework versions
90
 
91
- - Transformers 4.34.0
92
- - Pytorch 2.0.1+cu118
93
- - Datasets 2.14.5
94
  - Tokenizers 0.14.1
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9790805727433154
29
  - name: Recall
30
  type: recall
31
+ value: 0.9648238440626479
32
  - name: F1
33
  type: f1
34
+ value: 0.9718999284886718
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.985535111315454
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: 0.0457
48
+ - Precision: 0.9791
49
+ - Recall: 0.9648
50
+ - F1: 0.9719
51
+ - Accuracy: 0.9855
52
 
53
  ## Model description
54
 
 
67
  ### Training hyperparameters
68
 
69
  The following hyperparameters were used during training:
70
+ - learning_rate: 2e-05
71
  - train_batch_size: 16
72
  - eval_batch_size: 16
73
  - seed: 42
 
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.1213 | 0.58 | 500 | 0.0608 | 0.9658 | 0.9626 | 0.9642 | 0.9815 |
83
+ | 0.0562 | 1.17 | 1000 | 0.0513 | 0.9746 | 0.9638 | 0.9692 | 0.9841 |
84
+ | 0.0514 | 1.75 | 1500 | 0.0484 | 0.9778 | 0.9643 | 0.9710 | 0.9851 |
85
+ | 0.0468 | 2.33 | 2000 | 0.0471 | 0.9776 | 0.9653 | 0.9715 | 0.9853 |
86
+ | 0.0461 | 2.91 | 2500 | 0.0457 | 0.9791 | 0.9648 | 0.9719 | 0.9855 |
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.34.1
92
+ - Pytorch 2.1.0+cu118
93
+ - Datasets 2.14.6
94
  - Tokenizers 0.14.1