siddharthtumre commited on
Commit
112da14
1 Parent(s): a6343e4

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +93 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - jnlpba
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: pubmedbert-finetuned-ner
14
+ results:
15
+ - task:
16
+ name: Token Classification
17
+ type: token-classification
18
+ dataset:
19
+ name: jnlpba
20
+ type: jnlpba
21
+ config: jnlpba
22
+ split: train
23
+ args: jnlpba
24
+ metrics:
25
+ - name: Precision
26
+ type: precision
27
+ value: 0.6877153861747415
28
+ - name: Recall
29
+ type: recall
30
+ value: 0.7833063957515586
31
+ - name: F1
32
+ type: f1
33
+ value: 0.7324050086355786
34
+ - name: Accuracy
35
+ type: accuracy
36
+ value: 0.926729986431479
37
+ ---
38
+
39
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
40
+ should probably proofread and complete it, then remove this comment. -->
41
+
42
+ # pubmedbert-finetuned-ner
43
+
44
+ This model is a fine-tuned version of [microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) on the jnlpba dataset.
45
+ It achieves the following results on the evaluation set:
46
+ - Loss: 0.3766
47
+ - Precision: 0.6877
48
+ - Recall: 0.7833
49
+ - F1: 0.7324
50
+ - Accuracy: 0.9267
51
+
52
+ ## Model description
53
+
54
+ More information needed
55
+
56
+ ## Intended uses & limitations
57
+
58
+ More information needed
59
+
60
+ ## Training and evaluation data
61
+
62
+ More information needed
63
+
64
+ ## Training procedure
65
+
66
+ ### Training hyperparameters
67
+
68
+ The following hyperparameters were used during training:
69
+ - learning_rate: 2e-05
70
+ - train_batch_size: 16
71
+ - eval_batch_size: 16
72
+ - seed: 42
73
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
74
+ - lr_scheduler_type: linear
75
+ - num_epochs: 5
76
+
77
+ ### Training results
78
+
79
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
80
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
81
+ | 0.1607 | 1.0 | 2319 | 0.2241 | 0.6853 | 0.7835 | 0.7311 | 0.9302 |
82
+ | 0.112 | 2.0 | 4638 | 0.2620 | 0.6753 | 0.7929 | 0.7294 | 0.9276 |
83
+ | 0.0785 | 3.0 | 6957 | 0.3014 | 0.6948 | 0.7731 | 0.7319 | 0.9268 |
84
+ | 0.055 | 4.0 | 9276 | 0.3526 | 0.6898 | 0.7801 | 0.7322 | 0.9268 |
85
+ | 0.0418 | 5.0 | 11595 | 0.3766 | 0.6877 | 0.7833 | 0.7324 | 0.9267 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.21.1
91
+ - Pytorch 1.12.1+cu113
92
+ - Datasets 2.4.0
93
+ - Tokenizers 0.12.1