Commit
•
b727701
1
Parent(s):
939dd8f
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- bc4chemd_ner
|
7 |
+
metrics:
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
- f1
|
11 |
+
- accuracy
|
12 |
+
model-index:
|
13 |
+
- name: bc4chemd_ner-Bio_ClinicalBERT-finetuned-ner
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Token Classification
|
17 |
+
type: token-classification
|
18 |
+
dataset:
|
19 |
+
name: bc4chemd_ner
|
20 |
+
type: bc4chemd_ner
|
21 |
+
args: bc4chemd
|
22 |
+
metrics:
|
23 |
+
- name: Precision
|
24 |
+
type: precision
|
25 |
+
value: 0.8911526429774604
|
26 |
+
- name: Recall
|
27 |
+
type: recall
|
28 |
+
value: 0.8766669296930482
|
29 |
+
- name: F1
|
30 |
+
type: f1
|
31 |
+
value: 0.8838504375497215
|
32 |
+
- name: Accuracy
|
33 |
+
type: accuracy
|
34 |
+
value: 0.9906009271141061
|
35 |
+
---
|
36 |
+
|
37 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
38 |
+
should probably proofread and complete it, then remove this comment. -->
|
39 |
+
|
40 |
+
# bc4chemd_ner-Bio_ClinicalBERT-finetuned-ner
|
41 |
+
|
42 |
+
This model is a fine-tuned version of [emilyalsentzer/Bio_ClinicalBERT](https://huggingface.co/emilyalsentzer/Bio_ClinicalBERT) on the bc4chemd_ner dataset.
|
43 |
+
It achieves the following results on the evaluation set:
|
44 |
+
- Loss: 0.0648
|
45 |
+
- Precision: 0.8912
|
46 |
+
- Recall: 0.8767
|
47 |
+
- F1: 0.8839
|
48 |
+
- Accuracy: 0.9906
|
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: 2e-05
|
68 |
+
- train_batch_size: 16
|
69 |
+
- eval_batch_size: 16
|
70 |
+
- seed: 42
|
71 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
72 |
+
- lr_scheduler_type: linear
|
73 |
+
- num_epochs: 10
|
74 |
+
|
75 |
+
### Training results
|
76 |
+
|
77 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
78 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
79 |
+
| 0.0088 | 1.0 | 1918 | 0.0322 | 0.8763 | 0.8506 | 0.8633 | 0.9894 |
|
80 |
+
| 0.0079 | 2.0 | 3836 | 0.0375 | 0.8820 | 0.8571 | 0.8694 | 0.9896 |
|
81 |
+
| 0.0085 | 3.0 | 5754 | 0.0382 | 0.8671 | 0.8820 | 0.8744 | 0.9900 |
|
82 |
+
| 0.0011 | 4.0 | 7672 | 0.0513 | 0.8895 | 0.8520 | 0.8704 | 0.9896 |
|
83 |
+
| 0.0016 | 5.0 | 9590 | 0.0489 | 0.8871 | 0.8721 | 0.8795 | 0.9903 |
|
84 |
+
| 0.0002 | 6.0 | 11508 | 0.0541 | 0.8906 | 0.8751 | 0.8828 | 0.9904 |
|
85 |
+
| 0.0001 | 7.0 | 13426 | 0.0541 | 0.8794 | 0.8828 | 0.8811 | 0.9904 |
|
86 |
+
| 0.0001 | 8.0 | 15344 | 0.0590 | 0.8771 | 0.8881 | 0.8825 | 0.9905 |
|
87 |
+
| 0.0 | 9.0 | 17262 | 0.0622 | 0.8901 | 0.8797 | 0.8849 | 0.9906 |
|
88 |
+
| 0.0058 | 10.0 | 19180 | 0.0648 | 0.8912 | 0.8767 | 0.8839 | 0.9906 |
|
89 |
+
|
90 |
+
|
91 |
+
### Framework versions
|
92 |
+
|
93 |
+
- Transformers 4.20.1
|
94 |
+
- Pytorch 1.12.0+cu113
|
95 |
+
- Datasets 2.3.2
|
96 |
+
- Tokenizers 0.12.1
|