Hugging Face's logo

sciarrilli
/
biobert-base-cased-v1.2-finetuned-ner

Token Classification
Transformers
PyTorch
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
4
sciarrilli commited on
Commit
57d16e5
•
1 Parent(s): be91527

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +15 -15
README.md CHANGED
@@ -21,16 +21,16 @@ model-index:
21
  metrics:
22
  - name: Precision
23
  type: precision
24
- value: 0.8948080842655547
25
  - name: Recall
26
  type: recall
27
- value: 0.9282417121275703
28
  - name: F1
29
  type: f1
30
- value: 0.9112183219652858
31
  - name: Accuracy
32
  type: accuracy
33
- value: 0.9601644367242017
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -40,15 +40,15 @@ should probably proofread and complete it, then remove this comment. -->
40
 
41
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the jnlpba dataset.
42
  It achieves the following results on the evaluation set:
43
- - Loss: 0.1265
44
- - Precision: 0.8948
45
- - Recall: 0.9282
46
- - F1: 0.9112
47
- - Accuracy: 0.9602
48
 
49
  ## Model description
50
 
51
- BioBERT fine-tuned on JNLPBA dataset for NER in Biomedical.
52
 
53
  ## Intended uses & limitations
54
 
@@ -75,14 +75,14 @@ The following hyperparameters were used during training:
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
77
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
78
- | 0.2278 | 1.0 | 1858 | 0.1826 | 0.8415 | 0.8815 | 0.8610 | 0.9384 |
79
- | 0.151 | 2.0 | 3716 | 0.1443 | 0.8756 | 0.9162 | 0.8955 | 0.9530 |
80
- | 0.1157 | 3.0 | 5574 | 0.1265 | 0.8948 | 0.9282 | 0.9112 | 0.9602 |
81
 
82
 
83
  ### Framework versions
84
 
85
- - Transformers 4.12.0.dev0
86
  - Pytorch 1.9.1+cu102
87
- - Datasets 1.12.1
88
  - Tokenizers 0.10.3
 
21
  metrics:
22
  - name: Precision
23
  type: precision
24
+ value: 0.7191307944386116
25
  - name: Recall
26
  type: recall
27
+ value: 0.82492700729927
28
  - name: F1
29
  type: f1
30
+ value: 0.7684044126395947
31
  - name: Accuracy
32
  type: accuracy
33
+ value: 0.9044411982318681
34
  ---
35
 
36
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
40
 
41
  This model is a fine-tuned version of [dmis-lab/biobert-base-cased-v1.2](https://huggingface.co/dmis-lab/biobert-base-cased-v1.2) on the jnlpba dataset.
42
  It achieves the following results on the evaluation set:
43
+ - Loss: 0.3965
44
+ - Precision: 0.7191
45
+ - Recall: 0.8249
46
+ - F1: 0.7684
47
+ - Accuracy: 0.9044
48
 
49
  ## Model description
50
 
51
+ More information needed
52
 
53
  ## Intended uses & limitations
54
 
 
75
 
76
  | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
77
  |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
78
+ | 0.2038 | 1.0 | 2319 | 0.3123 | 0.7116 | 0.8319 | 0.7670 | 0.9043 |
79
+ | 0.1334 | 2.0 | 4638 | 0.3466 | 0.7148 | 0.8259 | 0.7663 | 0.9039 |
80
+ | 0.095 | 3.0 | 6957 | 0.3965 | 0.7191 | 0.8249 | 0.7684 | 0.9044 |
81
 
82
 
83
  ### Framework versions
84
 
85
+ - Transformers 4.11.3
86
  - Pytorch 1.9.1+cu102
87
+ - Datasets 1.13.2
88
  - Tokenizers 0.10.3