Commit
·
d17321e
1
Parent(s):
719947f
End of training
Browse files
README.md
ADDED
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: dmis-lab/biobert-v1.1
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: BioNLP13CG_bioBERT_NER
|
7 |
+
results: []
|
8 |
+
---
|
9 |
+
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
# BioNLP13CG_bioBERT_NER
|
14 |
+
|
15 |
+
This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 0.1928
|
18 |
+
- Seqeval classification report: precision recall f1-score support
|
19 |
+
|
20 |
+
Amino_acid 0.89 0.88 0.88 576
|
21 |
+
Anatomical_system 0.96 0.82 0.89 317
|
22 |
+
Cancer 0.92 0.91 0.91 1649
|
23 |
+
Cell 0.00 0.00 0.00 25
|
24 |
+
Cellular_component 0.00 0.00 0.00 12
|
25 |
+
Developing_anatomical_structure 0.75 0.85 0.80 438
|
26 |
+
Gene_or_gene_product 0.87 0.18 0.29 74
|
27 |
+
Immaterial_anatomical_entity 0.84 0.84 0.84 4142
|
28 |
+
Multi-tissue_structure 0.85 0.84 0.84 451
|
29 |
+
Organ 0.51 0.23 0.31 80
|
30 |
+
Organism 0.52 0.66 0.58 182
|
31 |
+
Organism_subdivision 0.81 0.80 0.81 314
|
32 |
+
Organism_substance 0.73 0.66 0.69 96
|
33 |
+
Pathological_formation 0.75 0.68 0.71 262
|
34 |
+
Simple_chemical 0.55 0.44 0.49 112
|
35 |
+
Tissue 0.82 0.91 0.87 300
|
36 |
+
|
37 |
+
micro avg 0.84 0.82 0.83 9030
|
38 |
+
macro avg 0.67 0.60 0.62 9030
|
39 |
+
weighted avg 0.84 0.82 0.83 9030
|
40 |
+
|
41 |
+
|
42 |
+
## Model description
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Intended uses & limitations
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training and evaluation data
|
51 |
+
|
52 |
+
More information needed
|
53 |
+
|
54 |
+
## Training procedure
|
55 |
+
|
56 |
+
### Training hyperparameters
|
57 |
+
|
58 |
+
The following hyperparameters were used during training:
|
59 |
+
- learning_rate: 2e-05
|
60 |
+
- train_batch_size: 16
|
61 |
+
- eval_batch_size: 16
|
62 |
+
- seed: 42
|
63 |
+
- gradient_accumulation_steps: 2
|
64 |
+
- total_train_batch_size: 32
|
65 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
66 |
+
- lr_scheduler_type: linear
|
67 |
+
- num_epochs: 3
|
68 |
+
|
69 |
+
### Training results
|
70 |
+
|
71 |
+
| Training Loss | Epoch | Step | Validation Loss | Seqeval classification report |
|
72 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
|
73 |
+
| No log | 0.99 | 95 | 0.2929 | precision recall f1-score support
|
74 |
+
|
75 |
+
Amino_acid 0.68 0.81 0.73 576
|
76 |
+
Anatomical_system 0.93 0.74 0.82 317
|
77 |
+
Cancer 0.89 0.89 0.89 1649
|
78 |
+
Cell 0.00 0.00 0.00 25
|
79 |
+
Cellular_component 0.00 0.00 0.00 12
|
80 |
+
Developing_anatomical_structure 0.56 0.79 0.65 438
|
81 |
+
Gene_or_gene_product 0.00 0.00 0.00 74
|
82 |
+
Immaterial_anatomical_entity 0.79 0.76 0.77 4142
|
83 |
+
Multi-tissue_structure 0.84 0.75 0.79 451
|
84 |
+
Organ 0.00 0.00 0.00 80
|
85 |
+
Organism 0.62 0.08 0.15 182
|
86 |
+
Organism_subdivision 0.64 0.78 0.70 314
|
87 |
+
Organism_substance 0.00 0.00 0.00 96
|
88 |
+
Pathological_formation 0.63 0.44 0.52 262
|
89 |
+
Simple_chemical 0.79 0.13 0.23 112
|
90 |
+
Tissue 0.82 0.45 0.58 300
|
91 |
+
|
92 |
+
micro avg 0.78 0.72 0.75 9030
|
93 |
+
macro avg 0.51 0.41 0.43 9030
|
94 |
+
weighted avg 0.76 0.72 0.73 9030
|
95 |
+
|
|
96 |
+
| No log | 2.0 | 191 | 0.2053 | precision recall f1-score support
|
97 |
+
|
98 |
+
Amino_acid 0.87 0.87 0.87 576
|
99 |
+
Anatomical_system 0.98 0.80 0.88 317
|
100 |
+
Cancer 0.89 0.92 0.91 1649
|
101 |
+
Cell 0.00 0.00 0.00 25
|
102 |
+
Cellular_component 0.00 0.00 0.00 12
|
103 |
+
Developing_anatomical_structure 0.74 0.84 0.79 438
|
104 |
+
Gene_or_gene_product 1.00 0.05 0.10 74
|
105 |
+
Immaterial_anatomical_entity 0.83 0.83 0.83 4142
|
106 |
+
Multi-tissue_structure 0.85 0.82 0.83 451
|
107 |
+
Organ 0.48 0.15 0.23 80
|
108 |
+
Organism 0.49 0.66 0.56 182
|
109 |
+
Organism_subdivision 0.79 0.80 0.80 314
|
110 |
+
Organism_substance 0.75 0.58 0.65 96
|
111 |
+
Pathological_formation 0.76 0.66 0.71 262
|
112 |
+
Simple_chemical 0.48 0.42 0.45 112
|
113 |
+
Tissue 0.80 0.90 0.85 300
|
114 |
+
|
115 |
+
micro avg 0.82 0.82 0.82 9030
|
116 |
+
macro avg 0.67 0.58 0.59 9030
|
117 |
+
weighted avg 0.82 0.82 0.81 9030
|
118 |
+
|
|
119 |
+
| No log | 2.98 | 285 | 0.1928 | precision recall f1-score support
|
120 |
+
|
121 |
+
Amino_acid 0.89 0.88 0.88 576
|
122 |
+
Anatomical_system 0.96 0.82 0.89 317
|
123 |
+
Cancer 0.92 0.91 0.91 1649
|
124 |
+
Cell 0.00 0.00 0.00 25
|
125 |
+
Cellular_component 0.00 0.00 0.00 12
|
126 |
+
Developing_anatomical_structure 0.75 0.85 0.80 438
|
127 |
+
Gene_or_gene_product 0.87 0.18 0.29 74
|
128 |
+
Immaterial_anatomical_entity 0.84 0.84 0.84 4142
|
129 |
+
Multi-tissue_structure 0.85 0.84 0.84 451
|
130 |
+
Organ 0.51 0.23 0.31 80
|
131 |
+
Organism 0.52 0.66 0.58 182
|
132 |
+
Organism_subdivision 0.81 0.80 0.81 314
|
133 |
+
Organism_substance 0.73 0.66 0.69 96
|
134 |
+
Pathological_formation 0.75 0.68 0.71 262
|
135 |
+
Simple_chemical 0.55 0.44 0.49 112
|
136 |
+
Tissue 0.82 0.91 0.87 300
|
137 |
+
|
138 |
+
micro avg 0.84 0.82 0.83 9030
|
139 |
+
macro avg 0.67 0.60 0.62 9030
|
140 |
+
weighted avg 0.84 0.82 0.83 9030
|
141 |
+
|
|
142 |
+
|
143 |
+
|
144 |
+
### Framework versions
|
145 |
+
|
146 |
+
- Transformers 4.35.2
|
147 |
+
- Pytorch 2.1.0+cu121
|
148 |
+
- Datasets 2.15.0
|
149 |
+
- Tokenizers 0.15.0
|