finiteautomata
commited on
Commit
•
bc1198f
1
Parent(s):
12eecb5
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- precision
|
7 |
+
- recall
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: distilbert-legal-definitions
|
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 |
+
# distilbert-legal-definitions
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0034
|
22 |
+
- Precision: 0.9668
|
23 |
+
- Recall: 0.9707
|
24 |
+
- Macro F1: 0.9688
|
25 |
+
- Micro F1: 0.9688
|
26 |
+
- Accuracy: 0.9994
|
27 |
+
- Term F1: 0.9688
|
28 |
+
- Term Precision: 0.9668
|
29 |
+
- Term Recall: 0.9707
|
30 |
+
|
31 |
+
## Model description
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Intended uses & limitations
|
36 |
+
|
37 |
+
More information needed
|
38 |
+
|
39 |
+
## Training and evaluation data
|
40 |
+
|
41 |
+
More information needed
|
42 |
+
|
43 |
+
## Training procedure
|
44 |
+
|
45 |
+
### Training hyperparameters
|
46 |
+
|
47 |
+
The following hyperparameters were used during training:
|
48 |
+
- learning_rate: 5e-05
|
49 |
+
- train_batch_size: 32
|
50 |
+
- eval_batch_size: 32
|
51 |
+
- seed: 42
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- lr_scheduler_warmup_ratio: 0.1
|
55 |
+
- num_epochs: 4
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Macro F1 | Micro F1 | Accuracy | Term F1 | Term Precision | Term Recall |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|:--------:|:-------:|:--------------:|:-----------:|
|
61 |
+
| 0.0049 | 1.0 | 2325 | 0.0034 | 0.9790 | 0.9580 | 0.9684 | 0.9684 | 0.9993 | 0.9684 | 0.9790 | 0.9580 |
|
62 |
+
| 0.0023 | 2.0 | 4650 | 0.0032 | 0.9669 | 0.9786 | 0.9727 | 0.9727 | 0.9994 | 0.9727 | 0.9669 | 0.9786 |
|
63 |
+
| 0.0013 | 3.0 | 6975 | 0.0018 | 0.9836 | 0.9794 | 0.9815 | 0.9815 | 0.9997 | 0.9815 | 0.9836 | 0.9794 |
|
64 |
+
| 0.0006 | 4.0 | 9300 | 0.0016 | 0.9879 | 0.9828 | 0.9854 | 0.9854 | 0.9997 | 0.9854 | 0.9879 | 0.9828 |
|
65 |
+
|
66 |
+
|
67 |
+
### Framework versions
|
68 |
+
|
69 |
+
- Transformers 4.21.3
|
70 |
+
- Pytorch 1.12.1+cu113
|
71 |
+
- Datasets 2.4.0
|
72 |
+
- Tokenizers 0.12.1
|