1 ---
2 tags:
3 - generated_from_trainer
4 datasets:
5 - conll2003
6 metrics:
7 - precision
8 - recall
9 - f1
10 - accuracy
11 model-index:
12 - name: bert-tiny-finetuned-ner
13 results:
14 - task:
15 name: Token Classification
16 type: token-classification
17 dataset:
18 name: conll2003
19 type: conll2003
20 args: conll2003
21 metrics:
22 - name: Precision
23 type: precision
24 value: 0.8083060109289617
25 - name: Recall
26 type: recall
27 value: 0.8273856136033113
28 - name: F1
29 type: f1
30 value: 0.8177345348001547
31 - name: Accuracy
32 type: accuracy
33 value: 0.9597597979252387
34 ---
35
36 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
37 should probably proofread and complete it, then remove this comment. -->
38
39 # bert-tiny-finetuned-ner
40
41 This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on the conll2003 dataset.
42 It achieves the following results on the evaluation set:
43 - Loss: 0.1689
44 - Precision: 0.8083
45 - Recall: 0.8274
46 - F1: 0.8177
47 - Accuracy: 0.9598
48
49 ## Model description
50
51 More information needed
52
53 ## Intended uses & limitations
54
55 More information needed
56
57 ## Training and evaluation data
58
59 More information needed
60
61 ## Training procedure
62
63 ### Training hyperparameters
64
65 The following hyperparameters were used during training:
66 - learning_rate: 2e-05
67 - train_batch_size: 16
68 - eval_batch_size: 16
69 - seed: 42
70 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
71 - lr_scheduler_type: linear
72 - num_epochs: 5
73
74 ### Training results
75
76 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
77 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
78 | 0.0355 | 1.0 | 878 | 0.1692 | 0.8072 | 0.8248 | 0.8159 | 0.9594 |
79 | 0.0411 | 2.0 | 1756 | 0.1678 | 0.8101 | 0.8277 | 0.8188 | 0.9600 |
80 | 0.0386 | 3.0 | 2634 | 0.1697 | 0.8103 | 0.8269 | 0.8186 | 0.9599 |
81 | 0.0373 | 4.0 | 3512 | 0.1694 | 0.8106 | 0.8263 | 0.8183 | 0.9600 |
82 | 0.0383 | 5.0 | 4390 | 0.1689 | 0.8083 | 0.8274 | 0.8177 | 0.9598 |
83
84
85 ### Framework versions
86
87 - Transformers 4.10.0
88 - Pytorch 1.9.0+cu102
89 - Datasets 1.11.0
90 - Tokenizers 0.10.3
91