jambo commited on
Commit
16ef812
1 Parent(s): b497d43

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +91 -0
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - marker-associations-snp-binary-base
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: marker-associations-snp-binary-base
14
+ results:
15
+ - task:
16
+ name: Text Classification
17
+ type: text-classification
18
+ dataset:
19
+ name: marker-associations-snp-binary-base
20
+ type: marker-associations-snp-binary-base
21
+ metrics:
22
+ - name: Precision
23
+ type: precision
24
+ value: 0.9384057971014492
25
+ - name: Recall
26
+ type: recall
27
+ value: 0.9055944055944056
28
+ - name: F1
29
+ type: f1
30
+ value: 0.9217081850533808
31
+ - name: Accuracy
32
+ type: accuracy
33
+ value: 0.9107505070993914
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
+ # marker-associations-snp-binary-base
40
+
41
+ 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 marker-associations-snp-binary-base dataset.
42
+ It achieves the following results on the evaluation set:
43
+ - Loss: 0.4027
44
+ - Precision: 0.9384
45
+ - Recall: 0.9056
46
+ - F1: 0.9217
47
+ - Accuracy: 0.9108
48
+ - Auc: 0.9578
49
+
50
+ ## Model description
51
+
52
+ More information needed
53
+
54
+ ## Intended uses & limitations
55
+
56
+ More information needed
57
+
58
+ ## Training and evaluation data
59
+
60
+ More information needed
61
+
62
+ ## Training procedure
63
+
64
+ ### Training hyperparameters
65
+
66
+ The following hyperparameters were used during training:
67
+ - learning_rate: 5e-05
68
+ - train_batch_size: 16
69
+ - eval_batch_size: 16
70
+ - seed: 1
71
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
72
+ - lr_scheduler_type: linear
73
+ - num_epochs: 15
74
+
75
+ ### Training results
76
+
77
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | Auc |
78
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|:------:|
79
+ | No log | 1.0 | 153 | 0.2776 | 0.9 | 0.9441 | 0.9215 | 0.9067 | 0.9613 |
80
+ | No log | 2.0 | 306 | 0.4380 | 0.9126 | 0.9126 | 0.9126 | 0.8986 | 0.9510 |
81
+ | No log | 3.0 | 459 | 0.4027 | 0.9384 | 0.9056 | 0.9217 | 0.9108 | 0.9578 |
82
+ | 0.2215 | 4.0 | 612 | 0.3547 | 0.9449 | 0.8986 | 0.9211 | 0.9108 | 0.9642 |
83
+ | 0.2215 | 5.0 | 765 | 0.4465 | 0.9107 | 0.9266 | 0.9185 | 0.9047 | 0.9636 |
84
+ | 0.2215 | 6.0 | 918 | 0.5770 | 0.8970 | 0.9441 | 0.9199 | 0.9047 | 0.9666 |
85
+
86
+
87
+ ### Framework versions
88
+
89
+ - Transformers 4.11.3
90
+ - Pytorch 1.9.0+cu111
91
+ - Tokenizers 0.10.3