update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: cc-by-nc-sa-4.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
metrics:
|
6 |
+
- accuracy
|
7 |
+
- precision
|
8 |
+
- recall
|
9 |
+
- f1
|
10 |
+
model-index:
|
11 |
+
- name: legal_long_legal_ver2_test_sm
|
12 |
+
results: []
|
13 |
+
---
|
14 |
+
|
15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
+
should probably proofread and complete it, then remove this comment. -->
|
17 |
+
|
18 |
+
# legal_long_legal_ver2_test_sm
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [kiddothe2b/legal-longformer-base](https://huggingface.co/kiddothe2b/legal-longformer-base) on the None dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 2.7379
|
23 |
+
- Accuracy: 0.5519
|
24 |
+
- Precision: 0.5139
|
25 |
+
- Recall: 0.5663
|
26 |
+
- F1: 0.5388
|
27 |
+
- D-index: 1.2690
|
28 |
+
|
29 |
+
## Model description
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Intended uses & limitations
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training and evaluation data
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Training procedure
|
42 |
+
|
43 |
+
### Training hyperparameters
|
44 |
+
|
45 |
+
The following hyperparameters were used during training:
|
46 |
+
- learning_rate: 5e-05
|
47 |
+
- train_batch_size: 8
|
48 |
+
- eval_batch_size: 16
|
49 |
+
- seed: 42
|
50 |
+
- gradient_accumulation_steps: 8
|
51 |
+
- total_train_batch_size: 64
|
52 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
53 |
+
- lr_scheduler_type: linear
|
54 |
+
- lr_scheduler_warmup_steps: 200
|
55 |
+
- num_epochs: 20
|
56 |
+
|
57 |
+
### Training results
|
58 |
+
|
59 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | D-index |
|
60 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:-------:|
|
61 |
+
| No log | 0.98 | 26 | 0.6957 | 0.4599 | 0.44 | 0.6173 | 0.5138 | 1.1026 |
|
62 |
+
| No log | 2.0 | 53 | 0.6960 | 0.4528 | 0.4262 | 0.5306 | 0.4727 | 1.0831 |
|
63 |
+
| No log | 2.98 | 79 | 0.6978 | 0.4481 | 0.4312 | 0.6071 | 0.5042 | 1.0794 |
|
64 |
+
| No log | 4.0 | 106 | 0.7232 | 0.4788 | 0.4622 | 0.7806 | 0.5806 | 1.1493 |
|
65 |
+
| No log | 4.98 | 132 | 0.7340 | 0.5189 | 0.4828 | 0.5714 | 0.5234 | 1.2095 |
|
66 |
+
| No log | 6.0 | 159 | 0.8623 | 0.5425 | 0.5049 | 0.5255 | 0.515 | 1.2493 |
|
67 |
+
| No log | 6.98 | 185 | 1.2325 | 0.5448 | 0.5116 | 0.3367 | 0.4062 | 1.2412 |
|
68 |
+
| No log | 8.0 | 212 | 1.4773 | 0.5165 | 0.4717 | 0.3827 | 0.4225 | 1.1925 |
|
69 |
+
| No log | 8.98 | 238 | 1.6199 | 0.5330 | 0.4941 | 0.4286 | 0.4590 | 1.2258 |
|
70 |
+
| No log | 10.0 | 265 | 1.8976 | 0.5259 | 0.4900 | 0.6276 | 0.5503 | 1.2261 |
|
71 |
+
| No log | 10.98 | 291 | 2.1687 | 0.4953 | 0.4622 | 0.5612 | 0.5069 | 1.1653 |
|
72 |
+
| No log | 12.0 | 318 | 2.3087 | 0.4882 | 0.4578 | 0.5816 | 0.5124 | 1.1535 |
|
73 |
+
| No log | 12.98 | 344 | 2.5168 | 0.4953 | 0.4667 | 0.6429 | 0.5408 | 1.1708 |
|
74 |
+
| No log | 14.0 | 371 | 2.5389 | 0.5142 | 0.4788 | 0.5765 | 0.5231 | 1.2012 |
|
75 |
+
| No log | 14.98 | 397 | 2.4224 | 0.5330 | 0.4957 | 0.5918 | 0.5395 | 1.2366 |
|
76 |
+
| No log | 16.0 | 424 | 2.6391 | 0.5212 | 0.4852 | 0.5867 | 0.5312 | 1.2148 |
|
77 |
+
| No log | 16.98 | 450 | 2.7235 | 0.5307 | 0.4932 | 0.5510 | 0.5205 | 1.2297 |
|
78 |
+
| No log | 18.0 | 477 | 2.7272 | 0.5425 | 0.5045 | 0.5765 | 0.5381 | 1.2527 |
|
79 |
+
| 0.2333 | 18.98 | 503 | 2.7222 | 0.5495 | 0.5117 | 0.5561 | 0.5330 | 1.2641 |
|
80 |
+
| 0.2333 | 19.62 | 520 | 2.7379 | 0.5519 | 0.5139 | 0.5663 | 0.5388 | 1.2690 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.27.4
|
86 |
+
- Pytorch 1.13.1+cu116
|
87 |
+
- Datasets 2.11.0
|
88 |
+
- Tokenizers 0.13.2
|