update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-sa-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- f1
|
9 |
+
model-index:
|
10 |
+
- name: legal-base-bert-NER
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# legal-base-bert-NER
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [nlpaueb/legal-bert-base-uncased](https://huggingface.co/nlpaueb/legal-bert-base-uncased) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0195
|
22 |
+
- Precision: 0.9678
|
23 |
+
- Recall: 0.9748
|
24 |
+
- F1: 0.9712
|
25 |
+
- Classification Report: precision recall f1-score support
|
26 |
+
|
27 |
+
LOC 0.98 0.99 0.98 1837
|
28 |
+
MISC 0.92 0.93 0.93 922
|
29 |
+
ORG 0.96 0.97 0.96 1341
|
30 |
+
PER 0.99 0.99 0.99 1842
|
31 |
+
|
32 |
+
micro avg 0.97 0.97 0.97 5942
|
33 |
+
macro avg 0.96 0.97 0.97 5942
|
34 |
+
weighted avg 0.97 0.97 0.97 5942
|
35 |
+
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 5e-05
|
55 |
+
- train_batch_size: 16
|
56 |
+
- eval_batch_size: 16
|
57 |
+
- seed: 42
|
58 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
59 |
+
- lr_scheduler_type: linear
|
60 |
+
- num_epochs: 3
|
61 |
+
|
62 |
+
### Training results
|
63 |
+
|
64 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Classification Report |
|
65 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
|
66 |
+
| 0.0423 | 2.3 | 500 | 0.0195 | 0.9678 | 0.9748 | 0.9712 | precision recall f1-score support
|
67 |
+
|
68 |
+
LOC 0.98 0.99 0.98 1837
|
69 |
+
MISC 0.92 0.93 0.93 922
|
70 |
+
ORG 0.96 0.97 0.96 1341
|
71 |
+
PER 0.99 0.99 0.99 1842
|
72 |
+
|
73 |
+
micro avg 0.97 0.97 0.97 5942
|
74 |
+
macro avg 0.96 0.97 0.97 5942
|
75 |
+
weighted avg 0.97 0.97 0.97 5942
|
76 |
+
|
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.30.2
|
82 |
+
- Pytorch 2.0.0
|
83 |
+
- Datasets 2.1.0
|
84 |
+
- Tokenizers 0.13.3
|