Hugging Face's logo

MHGanainy
/
roberta-base-legal-multi-downstream-indian-ner

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
MHGanainy commited on
Commit
eb12075
·
verified ·
1 Parent(s): fdab5c9

Model save

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model: MHGanainy/roberta-base-legal-multi
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: roberta-base-legal-multi-downstream-indian-ner
13
+ results: []
14
+ ---
15
+
16
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
+ should probably proofread and complete it, then remove this comment. -->
18
+
19
+ # roberta-base-legal-multi-downstream-indian-ner
20
+
21
+ This model is a fine-tuned version of [MHGanainy/roberta-base-legal-multi](https://huggingface.co/MHGanainy/roberta-base-legal-multi) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.2526
24
+ - Precision: 0.6406
25
+ - Recall: 0.8244
26
+ - F1: 0.7210
27
+ - Accuracy: 0.9663
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: 3e-05
47
+ - train_batch_size: 64
48
+ - eval_batch_size: 64
49
+ - seed: 1
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 20.0
53
+ - mixed_precision_training: Native AMP
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | No log | 1.0 | 172 | 0.2310 | 0.1233 | 0.4904 | 0.1971 | 0.8307 |
60
+ | No log | 2.0 | 344 | 0.1929 | 0.1983 | 0.5393 | 0.2900 | 0.8765 |
61
+ | 0.4324 | 3.0 | 516 | 0.1667 | 0.1773 | 0.4897 | 0.2604 | 0.8738 |
62
+ | 0.4324 | 4.0 | 688 | 0.1836 | 0.2957 | 0.6059 | 0.3975 | 0.9081 |
63
+ | 0.4324 | 5.0 | 860 | 0.2005 | 0.2855 | 0.5623 | 0.3787 | 0.9137 |
64
+ | 0.1106 | 6.0 | 1032 | 0.2003 | 0.3858 | 0.6974 | 0.4968 | 0.9323 |
65
+ | 0.1106 | 7.0 | 1204 | 0.2224 | 0.4182 | 0.6719 | 0.5155 | 0.9428 |
66
+ | 0.1106 | 8.0 | 1376 | 0.2221 | 0.3347 | 0.6147 | 0.4334 | 0.9312 |
67
+ | 0.0589 | 9.0 | 1548 | 0.1960 | 0.4067 | 0.7026 | 0.5152 | 0.9404 |
68
+ | 0.0589 | 10.0 | 1720 | 0.1904 | 0.5049 | 0.7410 | 0.6006 | 0.9524 |
69
+ | 0.0589 | 11.0 | 1892 | 0.2274 | 0.5337 | 0.7707 | 0.6307 | 0.9565 |
70
+ | 0.0359 | 12.0 | 2064 | 0.2471 | 0.5525 | 0.7696 | 0.6432 | 0.9575 |
71
+ | 0.0359 | 13.0 | 2236 | 0.2352 | 0.5649 | 0.7675 | 0.6508 | 0.9591 |
72
+ | 0.0359 | 14.0 | 2408 | 0.2297 | 0.5530 | 0.7661 | 0.6424 | 0.9586 |
73
+ | 0.0224 | 15.0 | 2580 | 0.2349 | 0.5702 | 0.7923 | 0.6632 | 0.9597 |
74
+ | 0.0224 | 16.0 | 2752 | 0.2465 | 0.6033 | 0.8052 | 0.6898 | 0.9624 |
75
+ | 0.0224 | 17.0 | 2924 | 0.2428 | 0.6100 | 0.8098 | 0.6959 | 0.9647 |
76
+ | 0.0143 | 18.0 | 3096 | 0.2543 | 0.6238 | 0.8154 | 0.7068 | 0.9646 |
77
+ | 0.0143 | 19.0 | 3268 | 0.2526 | 0.6305 | 0.8161 | 0.7114 | 0.9651 |
78
+ | 0.0143 | 20.0 | 3440 | 0.2526 | 0.6406 | 0.8244 | 0.7210 | 0.9663 |
79
+
80
+
81
+ ### Framework versions
82
+
83
+ - Transformers 4.44.2
84
+ - Pytorch 2.4.0+cu121
85
+ - Datasets 2.21.0
86
+ - Tokenizers 0.19.1