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
b79ea2c
•
1 Parent(s): c5ce7a9

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -19
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 1.0
29
  - name: Recall
30
  type: recall
31
- value: 0.999957470335559
32
  - name: F1
33
  type: f1
34
- value: 0.9999787347155767
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9999890011988694
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,9 +44,9 @@ 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: 0.0000
48
- - Precision: 1.0
49
- - Recall: 1.0000
50
  - F1: 1.0000
51
  - Accuracy: 1.0000
52
 
@@ -73,27 +73,22 @@ 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: 10
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.0127 | 1.0 | 626 | 0.0069 | 0.9955 | 0.9957 | 0.9956 | 0.9986 |
83
- | 0.01 | 2.0 | 1252 | 0.0068 | 0.9972 | 0.9971 | 0.9972 | 0.9991 |
84
- | 0.0075 | 3.0 | 1878 | 0.0029 | 0.9987 | 0.9982 | 0.9984 | 0.9995 |
85
- | 0.006 | 4.0 | 2504 | 0.0010 | 0.9994 | 0.9994 | 0.9994 | 0.9998 |
86
- | 0.0052 | 5.0 | 3130 | 0.0007 | 0.9997 | 0.9997 | 0.9997 | 0.9999 |
87
- | 0.0032 | 6.0 | 3756 | 0.0003 | 0.9999 | 0.9998 | 0.9999 | 1.0000 |
88
- | 0.003 | 7.0 | 4382 | 0.0001 | 1.0000 | 1.0000 | 1.0000 | 1.0000 |
89
- | 0.0013 | 8.0 | 5008 | 0.0000 | 1.0 | 1.0 | 1.0 | 1.0 |
90
- | 0.0013 | 9.0 | 5634 | 0.0001 | 1.0000 | 0.9999 | 0.9999 | 1.0000 |
91
- | 0.0011 | 10.0 | 6260 | 0.0000 | 1.0 | 1.0000 | 1.0000 | 1.0000 |
92
 
93
 
94
  ### Framework versions
95
 
96
- - Transformers 4.33.1
97
  - Pytorch 2.0.1+cu118
98
  - Datasets 2.14.5
99
  - Tokenizers 0.13.3
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9999768614928964
29
  - name: Recall
30
  type: recall
31
+ value: 0.9999305876908838
32
  - name: F1
33
  type: f1
34
+ value: 0.9999537240565493
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9999695484028137
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: 0.0001
48
+ - Precision: 1.0000
49
+ - Recall: 0.9999
50
  - F1: 1.0000
51
  - Accuracy: 1.0000
52
 
 
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
+ | 0.0405 | 1.0 | 688 | 0.0024 | 0.9962 | 0.9969 | 0.9965 | 0.9980 |
83
+ | 0.0078 | 2.0 | 1376 | 0.0017 | 0.9972 | 0.9989 | 0.9981 | 0.9990 |
84
+ | 0.0024 | 3.0 | 2064 | 0.0004 | 0.9995 | 0.9998 | 0.9997 | 0.9998 |
85
+ | 0.0008 | 4.0 | 2752 | 0.0002 | 0.9999 | 0.9999 | 0.9999 | 0.9999 |
86
+ | 0.001 | 5.0 | 3440 | 0.0001 | 1.0000 | 0.9999 | 1.0000 | 1.0000 |
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
90
 
91
+ - Transformers 4.33.2
92
  - Pytorch 2.0.1+cu118
93
  - Datasets 2.14.5
94
  - Tokenizers 0.13.3