End of training
Browse files
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: law-ai/InLegalBERT
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
- precision
|
9 |
+
- recall
|
10 |
+
model-index:
|
11 |
+
- name: IndianLegalBERT
|
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 |
+
# IndianLegalBERT
|
19 |
+
|
20 |
+
This model is a fine-tuned version of [law-ai/InLegalBERT](https://huggingface.co/law-ai/InLegalBERT) on an unknown dataset.
|
21 |
+
It achieves the following results on the evaluation set:
|
22 |
+
- Loss: 1.2872
|
23 |
+
- Accuracy: 0.8218
|
24 |
+
- Precision: 0.8227
|
25 |
+
- Recall: 0.8218
|
26 |
+
- Precision Macro: 0.7823
|
27 |
+
- Recall Macro: 0.7855
|
28 |
+
- Macro Fpr: 0.0158
|
29 |
+
- Weighted Fpr: 0.0152
|
30 |
+
- Weighted Specificity: 0.9773
|
31 |
+
- Macro Specificity: 0.9866
|
32 |
+
- Weighted Sensitivity: 0.8218
|
33 |
+
- Macro Sensitivity: 0.7855
|
34 |
+
- F1 Micro: 0.8218
|
35 |
+
- F1 Macro: 0.7809
|
36 |
+
- F1 Weighted: 0.8211
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 5e-05
|
56 |
+
- train_batch_size: 8
|
57 |
+
- eval_batch_size: 8
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 10
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | Precision Macro | Recall Macro | Macro Fpr | Weighted Fpr | Weighted Specificity | Macro Specificity | Weighted Sensitivity | Macro Sensitivity | F1 Micro | F1 Macro | F1 Weighted |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:---------------:|:------------:|:---------:|:------------:|:--------------------:|:-----------------:|:--------------------:|:-----------------:|:--------:|:--------:|:-----------:|
|
68 |
+
| 1.1031 | 1.0 | 643 | 0.6873 | 0.7854 | 0.7628 | 0.7854 | 0.5923 | 0.6107 | 0.0201 | 0.0191 | 0.9691 | 0.9836 | 0.7854 | 0.6107 | 0.7854 | 0.5863 | 0.7674 |
|
69 |
+
| 0.5953 | 2.0 | 1286 | 0.6741 | 0.8195 | 0.8135 | 0.8195 | 0.7481 | 0.7363 | 0.0162 | 0.0155 | 0.9753 | 0.9863 | 0.8195 | 0.7363 | 0.8195 | 0.7377 | 0.8153 |
|
70 |
+
| 0.4673 | 3.0 | 1929 | 0.7955 | 0.8242 | 0.8206 | 0.8242 | 0.7588 | 0.7421 | 0.0157 | 0.0150 | 0.9749 | 0.9866 | 0.8242 | 0.7421 | 0.8242 | 0.7433 | 0.8204 |
|
71 |
+
| 0.2292 | 4.0 | 2572 | 0.8666 | 0.8280 | 0.8297 | 0.8280 | 0.7945 | 0.7864 | 0.0151 | 0.0146 | 0.9786 | 0.9871 | 0.8280 | 0.7864 | 0.8280 | 0.7840 | 0.8270 |
|
72 |
+
| 0.1583 | 5.0 | 3215 | 0.9898 | 0.8335 | 0.8348 | 0.8335 | 0.8115 | 0.7893 | 0.0147 | 0.0141 | 0.9778 | 0.9874 | 0.8335 | 0.7893 | 0.8335 | 0.7926 | 0.8308 |
|
73 |
+
| 0.0975 | 6.0 | 3858 | 1.1179 | 0.8218 | 0.8260 | 0.8218 | 0.8185 | 0.7573 | 0.0158 | 0.0152 | 0.9781 | 0.9867 | 0.8218 | 0.7573 | 0.8218 | 0.7656 | 0.8203 |
|
74 |
+
| 0.0529 | 7.0 | 4501 | 1.1545 | 0.8211 | 0.8205 | 0.8211 | 0.7916 | 0.7691 | 0.0160 | 0.0153 | 0.9758 | 0.9865 | 0.8211 | 0.7691 | 0.8211 | 0.7773 | 0.8203 |
|
75 |
+
| 0.0184 | 8.0 | 5144 | 1.2160 | 0.8234 | 0.8248 | 0.8234 | 0.7770 | 0.7829 | 0.0157 | 0.0151 | 0.9774 | 0.9867 | 0.8234 | 0.7829 | 0.8234 | 0.7771 | 0.8229 |
|
76 |
+
| 0.0186 | 9.0 | 5787 | 1.2777 | 0.8226 | 0.8244 | 0.8226 | 0.7882 | 0.7851 | 0.0157 | 0.0152 | 0.9774 | 0.9867 | 0.8226 | 0.7851 | 0.8226 | 0.7827 | 0.8223 |
|
77 |
+
| 0.007 | 10.0 | 6430 | 1.2872 | 0.8218 | 0.8227 | 0.8218 | 0.7823 | 0.7855 | 0.0158 | 0.0152 | 0.9773 | 0.9866 | 0.8218 | 0.7855 | 0.8218 | 0.7809 | 0.8211 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.38.2
|
83 |
+
- Pytorch 2.1.2
|
84 |
+
- Datasets 2.1.0
|
85 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 437998636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9f18bb44944b7c56f72b081936ad17152713249f0d59bf8013cb9ccf6507767
|
3 |
size 437998636
|
runs/Apr12_20-55-42_f580b627d25e/events.out.tfevents.1712955386.f580b627d25e.34.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c06a585d63333a2ee13722994219756120ac5a6fe2fedc89f56aa41bca7144ee
|
3 |
+
size 18866
|