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
92c050f
•
1 Parent(s): 177df62

End of training

Browse files
Files changed (1) hide show
  1. README.md +27 -17
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.9805194805194806
29
  - name: Recall
30
  type: recall
31
- value: 0.984171322160149
32
  - name: F1
33
  type: f1
34
- value: 0.9823420074349444
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9989348679713209
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 indian_names dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.0053
48
- - Precision: 0.9805
49
- - Recall: 0.9842
50
- - F1: 0.9823
51
- - Accuracy: 0.9989
52
 
53
  ## Model description
54
 
@@ -73,22 +73,32 @@ 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: 5
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | No log | 1.0 | 213 | 0.0572 | 0.6793 | 0.7356 | 0.7063 | 0.9820 |
83
- | No log | 2.0 | 426 | 0.0248 | 0.8912 | 0.8887 | 0.8900 | 0.9936 |
84
- | 0.0713 | 3.0 | 639 | 0.0118 | 0.9570 | 0.9534 | 0.9552 | 0.9973 |
85
- | 0.0713 | 4.0 | 852 | 0.0067 | 0.9777 | 0.9800 | 0.9788 | 0.9987 |
86
- | 0.0164 | 5.0 | 1065 | 0.0053 | 0.9805 | 0.9842 | 0.9823 | 0.9989 |
 
 
 
 
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
90
 
91
- - Transformers 4.33.0
92
  - Pytorch 2.0.1+cu118
93
- - Datasets 2.14.4
94
  - Tokenizers 0.13.3
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.9941348973607038
29
  - name: Recall
30
  type: recall
31
+ value: 0.9921951219512195
32
  - name: F1
33
  type: f1
34
+ value: 0.9931640625
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9998052125131481
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 indian_names dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.0012
48
+ - Precision: 0.9941
49
+ - Recall: 0.9922
50
+ - F1: 0.9932
51
+ - Accuracy: 0.9998
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: 15
77
 
78
  ### Training results
79
 
80
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | No log | 1.0 | 63 | 0.1413 | 0.0 | 0.0 | 0.0 | 0.9745 |
83
+ | No log | 2.0 | 126 | 0.1211 | 0.0 | 0.0 | 0.0 | 0.9745 |
84
+ | No log | 3.0 | 189 | 0.0656 | 0.6231 | 0.2790 | 0.3854 | 0.9811 |
85
+ | No log | 4.0 | 252 | 0.0380 | 0.7297 | 0.6059 | 0.6620 | 0.9894 |
86
+ | No log | 5.0 | 315 | 0.0259 | 0.8341 | 0.7259 | 0.7762 | 0.9931 |
87
+ | No log | 6.0 | 378 | 0.0136 | 0.8842 | 0.8712 | 0.8776 | 0.9963 |
88
+ | No log | 7.0 | 441 | 0.0076 | 0.9286 | 0.9268 | 0.9277 | 0.9981 |
89
+ | 0.0748 | 8.0 | 504 | 0.0054 | 0.9409 | 0.9473 | 0.9441 | 0.9985 |
90
+ | 0.0748 | 9.0 | 567 | 0.0042 | 0.9520 | 0.9678 | 0.9598 | 0.9991 |
91
+ | 0.0748 | 10.0 | 630 | 0.0025 | 0.9738 | 0.9795 | 0.9767 | 0.9995 |
92
+ | 0.0748 | 11.0 | 693 | 0.0019 | 0.9863 | 0.9863 | 0.9863 | 0.9997 |
93
+ | 0.0748 | 12.0 | 756 | 0.0015 | 0.9961 | 0.9912 | 0.9936 | 0.9998 |
94
+ | 0.0748 | 13.0 | 819 | 0.0014 | 0.9912 | 0.9912 | 0.9912 | 0.9998 |
95
+ | 0.0748 | 14.0 | 882 | 0.0013 | 0.9912 | 0.9912 | 0.9912 | 0.9998 |
96
+ | 0.0748 | 15.0 | 945 | 0.0012 | 0.9941 | 0.9922 | 0.9932 | 0.9998 |
97
 
98
 
99
  ### Framework versions
100
 
101
+ - Transformers 4.33.1
102
  - Pytorch 2.0.1+cu118
103
+ - Datasets 2.14.5
104
  - Tokenizers 0.13.3