Hugging Face's logo

judithrosell
/
BioNLP13CG_PubMedBERT_NER

Token Classification
Transformers
TensorBoard
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
judithrosell commited on
Commit
e424294
•
1 Parent(s): da1b788

End of training

Browse files
Files changed (1) hide show
  1. README.md +150 -0
README.md ADDED
@@ -0,0 +1,150 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: BioNLP13CG_PubMedBERT_NER
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # BioNLP13CG_PubMedBERT_NER
15
+
16
+ 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 None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.2066
19
+ - Seqeval classification report: precision recall f1-score support
20
+
21
+ Amino_acid 0.78 0.81 0.79 301
22
+ Anatomical_system 0.00 0.00 0.00 3
23
+ Cancer 0.00 0.00 0.00 37
24
+ Cell 0.79 0.85 0.82 446
25
+ Cellular_component 0.00 0.00 0.00 19
26
+ Developing_anatomical_structure 0.55 0.78 0.65 399
27
+ Gene_or_gene_product 0.68 0.41 0.51 128
28
+ Immaterial_anatomical_entity 0.00 0.00 0.00 45
29
+ Multi-tissue_structure 0.25 0.02 0.04 98
30
+ Organ 0.00 0.00 0.00 19
31
+ Organism 0.90 0.93 0.92 1108
32
+ Organism_subdivision 0.71 0.12 0.21 120
33
+ Organism_substance 0.62 0.59 0.60 128
34
+ Pathological_formation 0.00 0.00 0.00 41
35
+ Simple_chemical 0.87 0.86 0.86 4397
36
+ Tissue 0.90 0.93 0.91 1790
37
+
38
+ micro avg 0.84 0.83 0.84 9079
39
+ macro avg 0.44 0.39 0.39 9079
40
+ weighted avg 0.83 0.83 0.82 9079
41
+
42
+
43
+ ## Model description
44
+
45
+ More information needed
46
+
47
+ ## Intended uses & limitations
48
+
49
+ More information needed
50
+
51
+ ## Training and evaluation data
52
+
53
+ More information needed
54
+
55
+ ## Training procedure
56
+
57
+ ### Training hyperparameters
58
+
59
+ The following hyperparameters were used during training:
60
+ - learning_rate: 2e-05
61
+ - train_batch_size: 16
62
+ - eval_batch_size: 16
63
+ - seed: 42
64
+ - gradient_accumulation_steps: 2
65
+ - total_train_batch_size: 32
66
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
67
+ - lr_scheduler_type: linear
68
+ - num_epochs: 3
69
+
70
+ ### Training results
71
+
72
+ | Training Loss | Epoch | Step | Validation Loss | Seqeval classification report |
73
+ |:-------------:|:-----:|:----:|:---------------:|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
74
+ | No log | 0.99 | 95 | 0.3390 | precision recall f1-score support
75
+
76
+ Amino_acid 0.81 0.10 0.18 301
77
+ Anatomical_system 0.00 0.00 0.00 3
78
+ Cancer 0.00 0.00 0.00 37
79
+ Cell 0.82 0.76 0.79 446
80
+ Cellular_component 0.00 0.00 0.00 19
81
+ Developing_anatomical_structure 0.90 0.07 0.13 399
82
+ Gene_or_gene_product 0.00 0.00 0.00 128
83
+ Immaterial_anatomical_entity 0.00 0.00 0.00 45
84
+ Multi-tissue_structure 0.00 0.00 0.00 98
85
+ Organ 0.00 0.00 0.00 19
86
+ Organism 0.64 0.86 0.73 1108
87
+ Organism_subdivision 0.00 0.00 0.00 120
88
+ Organism_substance 0.00 0.00 0.00 128
89
+ Pathological_formation 0.00 0.00 0.00 41
90
+ Simple_chemical 0.83 0.79 0.81 4397
91
+ Tissue 0.74 0.91 0.82 1790
92
+
93
+ micro avg 0.77 0.71 0.74 9079
94
+ macro avg 0.30 0.22 0.22 9079
95
+ weighted avg 0.73 0.71 0.69 9079
96
+ |
97
+ | No log | 2.0 | 191 | 0.2209 | precision recall f1-score support
98
+
99
+ Amino_acid 0.76 0.75 0.76 301
100
+ Anatomical_system 0.00 0.00 0.00 3
101
+ Cancer 0.00 0.00 0.00 37
102
+ Cell 0.78 0.87 0.82 446
103
+ Cellular_component 0.00 0.00 0.00 19
104
+ Developing_anatomical_structure 0.52 0.75 0.61 399
105
+ Gene_or_gene_product 0.65 0.24 0.35 128
106
+ Immaterial_anatomical_entity 0.00 0.00 0.00 45
107
+ Multi-tissue_structure 0.00 0.00 0.00 98
108
+ Organ 0.00 0.00 0.00 19
109
+ Organism 0.89 0.92 0.91 1108
110
+ Organism_subdivision 0.50 0.05 0.09 120
111
+ Organism_substance 0.61 0.52 0.56 128
112
+ Pathological_formation 0.00 0.00 0.00 41
113
+ Simple_chemical 0.86 0.86 0.86 4397
114
+ Tissue 0.87 0.93 0.90 1790
115
+
116
+ micro avg 0.83 0.82 0.83 9079
117
+ macro avg 0.40 0.37 0.37 9079
118
+ weighted avg 0.81 0.82 0.81 9079
119
+ |
120
+ | No log | 2.98 | 285 | 0.2066 | precision recall f1-score support
121
+
122
+ Amino_acid 0.78 0.81 0.79 301
123
+ Anatomical_system 0.00 0.00 0.00 3
124
+ Cancer 0.00 0.00 0.00 37
125
+ Cell 0.79 0.85 0.82 446
126
+ Cellular_component 0.00 0.00 0.00 19
127
+ Developing_anatomical_structure 0.55 0.78 0.65 399
128
+ Gene_or_gene_product 0.68 0.41 0.51 128
129
+ Immaterial_anatomical_entity 0.00 0.00 0.00 45
130
+ Multi-tissue_structure 0.25 0.02 0.04 98
131
+ Organ 0.00 0.00 0.00 19
132
+ Organism 0.90 0.93 0.92 1108
133
+ Organism_subdivision 0.71 0.12 0.21 120
134
+ Organism_substance 0.62 0.59 0.60 128
135
+ Pathological_formation 0.00 0.00 0.00 41
136
+ Simple_chemical 0.87 0.86 0.86 4397
137
+ Tissue 0.90 0.93 0.91 1790
138
+
139
+ micro avg 0.84 0.83 0.84 9079
140
+ macro avg 0.44 0.39 0.39 9079
141
+ weighted avg 0.83 0.83 0.82 9079
142
+ |
143
+
144
+
145
+ ### Framework versions
146
+
147
+ - Transformers 4.35.2
148
+ - Pytorch 2.1.0+cu118
149
+ - Datasets 2.15.0
150
+ - Tokenizers 0.15.0