Hugging Face's logo

alvarobartt
/
distilbert-base-cased-ner

Token Classification
Transformers
PyTorch
distilbert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
4
Alvaro Bartolome commited on
Commit
9367b3d
•
1 Parent(s): 5455d5e

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +24 -19
README.md CHANGED
@@ -24,16 +24,16 @@ model-index:
24
  metrics:
25
  - name: Precision
26
  type: precision
27
- value: 0.9254922831293241
28
  - name: Recall
29
  type: recall
30
- value: 0.9361205813744842
31
  - name: F1
32
  type: f1
33
- value: 0.9307760927743086
34
  - name: Accuracy
35
  type: accuracy
36
- value: 0.9831488785541885
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -43,11 +43,11 @@ should probably proofread and complete it, then remove this comment. -->
43
 
44
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the conll2003 dataset.
45
  It achieves the following results on the evaluation set:
46
- - Loss: 0.0966
47
- - Precision: 0.9255
48
- - Recall: 0.9361
49
- - F1: 0.9308
50
- - Accuracy: 0.9831
51
 
52
  ## Model description
53
 
@@ -66,29 +66,34 @@ More information needed
66
  ### Training hyperparameters
67
 
68
  The following hyperparameters were used during training:
69
- - learning_rate: 5e-05
70
  - train_batch_size: 8
71
  - eval_batch_size: 8
72
  - seed: 2147483647
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
- - num_epochs: 5
76
  - mixed_precision_training: Native AMP
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.1045 | 1.0 | 1756 | 0.0891 | 0.8908 | 0.9032 | 0.8970 | 0.9747 |
83
- | 0.044 | 2.0 | 3512 | 0.0809 | 0.9209 | 0.9175 | 0.9192 | 0.9793 |
84
- | 0.0253 | 3.0 | 5268 | 0.0806 | 0.9268 | 0.9280 | 0.9274 | 0.9821 |
85
- | 0.0129 | 4.0 | 7024 | 0.0909 | 0.9301 | 0.9341 | 0.9321 | 0.9829 |
86
- | 0.0042 | 5.0 | 8780 | 0.0966 | 0.9255 | 0.9361 | 0.9308 | 0.9831 |
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
90
 
91
- - Transformers 4.28.0.dev0
92
  - Pytorch 2.0.0+cu118
93
  - Datasets 2.11.0
94
  - Tokenizers 0.13.3
 
24
  metrics:
25
  - name: Precision
26
  type: precision
27
+ value: 0.9306692773228907
28
  - name: Recall
29
  type: recall
30
+ value: 0.9381841019199713
31
  - name: F1
32
  type: f1
33
+ value: 0.9344115807345187
34
  - name: Accuracy
35
  type: accuracy
36
+ value: 0.9832666156472597
37
  ---
38
 
39
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
43
 
44
  This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the conll2003 dataset.
45
  It achieves the following results on the evaluation set:
46
+ - Loss: 0.1183
47
+ - Precision: 0.9307
48
+ - Recall: 0.9382
49
+ - F1: 0.9344
50
+ - Accuracy: 0.9833
51
 
52
  ## Model description
53
 
 
66
  ### Training hyperparameters
67
 
68
  The following hyperparameters were used during training:
69
+ - learning_rate: 2e-05
70
  - train_batch_size: 8
71
  - eval_batch_size: 8
72
  - seed: 2147483647
73
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
  - lr_scheduler_type: linear
75
+ - num_epochs: 10
76
  - mixed_precision_training: Native AMP
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.1081 | 1.0 | 1756 | 0.0963 | 0.8947 | 0.8982 | 0.8964 | 0.9742 |
83
+ | 0.0518 | 2.0 | 3512 | 0.0780 | 0.9219 | 0.9182 | 0.9200 | 0.9803 |
84
+ | 0.0348 | 3.0 | 5268 | 0.0833 | 0.9258 | 0.9271 | 0.9264 | 0.9819 |
85
+ | 0.0268 | 4.0 | 7024 | 0.0900 | 0.9152 | 0.9241 | 0.9196 | 0.9805 |
86
+ | 0.0167 | 5.0 | 8780 | 0.0929 | 0.9225 | 0.9320 | 0.9272 | 0.9822 |
87
+ | 0.0071 | 6.0 | 10536 | 0.1119 | 0.9229 | 0.9270 | 0.9249 | 0.9816 |
88
+ | 0.0056 | 7.0 | 12292 | 0.1073 | 0.9286 | 0.9366 | 0.9326 | 0.9832 |
89
+ | 0.0021 | 8.0 | 14048 | 0.1194 | 0.9285 | 0.9350 | 0.9318 | 0.9829 |
90
+ | 0.0019 | 9.0 | 15804 | 0.1156 | 0.9318 | 0.9376 | 0.9347 | 0.9833 |
91
+ | 0.0011 | 10.0 | 17560 | 0.1183 | 0.9307 | 0.9382 | 0.9344 | 0.9833 |
92
 
93
 
94
  ### Framework versions
95
 
96
+ - Transformers 4.27.4
97
  - Pytorch 2.0.0+cu118
98
  - Datasets 2.11.0
99
  - Tokenizers 0.13.3