Hugging Face's logo

judithrosell
/
BioNLP13CG_ClinicalBERT_NER

Token Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
judithrosell commited on
Commit
675a392
•
1 Parent(s): 5f7b979

End of training

Browse files
Files changed (1) hide show
  1. README.md +149 -0
README.md ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: medicalai/ClinicalBERT
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: BioNLP13CG_ClinicalBERT_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_ClinicalBERT_NER
14
+
15
+ This model is a fine-tuned version of [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.3339
18
+ - Seqeval classification report: precision recall f1-score support
19
+
20
+ Amino_acid 0.81 0.59 0.68 297
21
+ Anatomical_system 0.70 0.78 0.74 297
22
+ Cancer 0.74 0.73 0.73 3490
23
+ Cell 0.72 0.87 0.79 1360
24
+ Cellular_component 0.00 0.00 0.00 99
25
+ Developing_anatomical_structure 0.00 0.00 0.00 11
26
+ Gene_or_gene_product 0.67 0.25 0.37 174
27
+ Immaterial_anatomical_entity 0.52 0.76 0.62 432
28
+ Multi-tissue_structure 0.83 0.59 0.69 317
29
+ Organ 0.00 0.00 0.00 49
30
+ Organism 0.71 0.48 0.57 464
31
+ Organism_subdivision 0.70 0.72 0.71 678
32
+ Organism_substance 0.00 0.00 0.00 128
33
+ Pathological_formation 0.62 0.05 0.09 108
34
+ Simple_chemical 0.00 0.00 0.00 56
35
+ Tissue 0.80 0.85 0.82 1566
36
+
37
+ micro avg 0.73 0.71 0.72 9526
38
+ macro avg 0.49 0.42 0.43 9526
39
+ weighted avg 0.71 0.71 0.70 9526
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 | 0.4681 | precision recall f1-score support
74
+
75
+ Amino_acid 1.00 0.02 0.04 297
76
+ Anatomical_system 0.44 0.68 0.54 297
77
+ Cancer 0.68 0.63 0.65 3490
78
+ Cell 0.59 0.85 0.70 1360
79
+ Cellular_component 0.00 0.00 0.00 99
80
+ Developing_anatomical_structure 0.00 0.00 0.00 11
81
+ Gene_or_gene_product 0.00 0.00 0.00 174
82
+ Immaterial_anatomical_entity 0.40 0.60 0.48 432
83
+ Multi-tissue_structure 0.86 0.06 0.11 317
84
+ Organ 0.00 0.00 0.00 49
85
+ Organism 0.88 0.02 0.03 464
86
+ Organism_subdivision 0.62 0.54 0.58 678
87
+ Organism_substance 0.00 0.00 0.00 128
88
+ Pathological_formation 0.00 0.00 0.00 108
89
+ Simple_chemical 0.00 0.00 0.00 56
90
+ Tissue 0.70 0.84 0.76 1566
91
+
92
+ micro avg 0.63 0.58 0.60 9526
93
+ macro avg 0.39 0.27 0.24 9526
94
+ weighted avg 0.63 0.58 0.55 9526
95
+ |
96
+ | No log | 2.0 | 191 | 0.3526 | precision recall f1-score support
97
+
98
+ Amino_acid 0.81 0.52 0.63 297
99
+ Anatomical_system 0.66 0.77 0.71 297
100
+ Cancer 0.74 0.73 0.73 3490
101
+ Cell 0.71 0.87 0.78 1360
102
+ Cellular_component 0.00 0.00 0.00 99
103
+ Developing_anatomical_structure 0.00 0.00 0.00 11
104
+ Gene_or_gene_product 0.76 0.20 0.32 174
105
+ Immaterial_anatomical_entity 0.46 0.76 0.57 432
106
+ Multi-tissue_structure 0.83 0.57 0.68 317
107
+ Organ 0.00 0.00 0.00 49
108
+ Organism 0.68 0.44 0.54 464
109
+ Organism_subdivision 0.71 0.67 0.69 678
110
+ Organism_substance 0.00 0.00 0.00 128
111
+ Pathological_formation 1.00 0.01 0.02 108
112
+ Simple_chemical 0.00 0.00 0.00 56
113
+ Tissue 0.78 0.85 0.81 1566
114
+
115
+ micro avg 0.72 0.70 0.71 9526
116
+ macro avg 0.51 0.40 0.41 9526
117
+ weighted avg 0.70 0.70 0.68 9526
118
+ |
119
+ | No log | 2.98 | 285 | 0.3339 | precision recall f1-score support
120
+
121
+ Amino_acid 0.81 0.59 0.68 297
122
+ Anatomical_system 0.70 0.78 0.74 297
123
+ Cancer 0.74 0.73 0.73 3490
124
+ Cell 0.72 0.87 0.79 1360
125
+ Cellular_component 0.00 0.00 0.00 99
126
+ Developing_anatomical_structure 0.00 0.00 0.00 11
127
+ Gene_or_gene_product 0.67 0.25 0.37 174
128
+ Immaterial_anatomical_entity 0.52 0.76 0.62 432
129
+ Multi-tissue_structure 0.83 0.59 0.69 317
130
+ Organ 0.00 0.00 0.00 49
131
+ Organism 0.71 0.48 0.57 464
132
+ Organism_subdivision 0.70 0.72 0.71 678
133
+ Organism_substance 0.00 0.00 0.00 128
134
+ Pathological_formation 0.62 0.05 0.09 108
135
+ Simple_chemical 0.00 0.00 0.00 56
136
+ Tissue 0.80 0.85 0.82 1566
137
+
138
+ micro avg 0.73 0.71 0.72 9526
139
+ macro avg 0.49 0.42 0.43 9526
140
+ weighted avg 0.71 0.71 0.70 9526
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