Hugging Face's logo

apwic
/
nerugm-base-2

Token Classification
Transformers
TensorBoard
Safetensors
Indonesian
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
apwic commited on
Commit
3b239b4
•
1 Parent(s): 32d259c

Model save

Browse files
Files changed (1) hide show
  1. README.md +85 -0
README.md ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: indolem/indobert-base-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - precision
8
+ - recall
9
+ - f1
10
+ - accuracy
11
+ model-index:
12
+ - name: nerugm-base-2
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
+ # nerugm-base-2
20
+
21
+ This model is a fine-tuned version of [indolem/indobert-base-uncased](https://huggingface.co/indolem/indobert-base-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.3243
24
+ - Precision: 0.7942
25
+ - Recall: 0.8879
26
+ - F1: 0.8384
27
+ - Accuracy: 0.9605
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: 16
48
+ - eval_batch_size: 64
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 20.0
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
57
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
58
+ | 0.3438 | 1.0 | 106 | 0.1653 | 0.7345 | 0.8407 | 0.7840 | 0.9492 |
59
+ | 0.1133 | 2.0 | 212 | 0.1340 | 0.7677 | 0.8968 | 0.8272 | 0.9570 |
60
+ | 0.0736 | 3.0 | 318 | 0.1448 | 0.7769 | 0.8732 | 0.8222 | 0.9590 |
61
+ | 0.0473 | 4.0 | 424 | 0.1585 | 0.7888 | 0.8702 | 0.8275 | 0.9612 |
62
+ | 0.0311 | 5.0 | 530 | 0.1845 | 0.7895 | 0.8850 | 0.8345 | 0.9605 |
63
+ | 0.0179 | 6.0 | 636 | 0.2145 | 0.7867 | 0.8702 | 0.8263 | 0.9602 |
64
+ | 0.0126 | 7.0 | 742 | 0.2225 | 0.7789 | 0.8732 | 0.8234 | 0.9567 |
65
+ | 0.0091 | 8.0 | 848 | 0.2556 | 0.7839 | 0.8879 | 0.8326 | 0.9582 |
66
+ | 0.0041 | 9.0 | 954 | 0.2574 | 0.7973 | 0.8702 | 0.8322 | 0.9610 |
67
+ | 0.0036 | 10.0 | 1060 | 0.3124 | 0.7702 | 0.8702 | 0.8172 | 0.9555 |
68
+ | 0.0038 | 11.0 | 1166 | 0.2837 | 0.7905 | 0.8791 | 0.8324 | 0.9607 |
69
+ | 0.0017 | 12.0 | 1272 | 0.3035 | 0.7795 | 0.8761 | 0.825 | 0.9575 |
70
+ | 0.0015 | 13.0 | 1378 | 0.3068 | 0.7874 | 0.8850 | 0.8333 | 0.9605 |
71
+ | 0.0012 | 14.0 | 1484 | 0.3286 | 0.7839 | 0.8879 | 0.8326 | 0.9577 |
72
+ | 0.0006 | 15.0 | 1590 | 0.3137 | 0.7984 | 0.8879 | 0.8408 | 0.9607 |
73
+ | 0.0008 | 16.0 | 1696 | 0.3065 | 0.8011 | 0.8791 | 0.8383 | 0.9617 |
74
+ | 0.0014 | 17.0 | 1802 | 0.3305 | 0.7885 | 0.8909 | 0.8366 | 0.9590 |
75
+ | 0.0005 | 18.0 | 1908 | 0.3245 | 0.7895 | 0.8850 | 0.8345 | 0.9597 |
76
+ | 0.0004 | 19.0 | 2014 | 0.3248 | 0.7921 | 0.8879 | 0.8373 | 0.9602 |
77
+ | 0.0003 | 20.0 | 2120 | 0.3243 | 0.7942 | 0.8879 | 0.8384 | 0.9605 |
78
+
79
+
80
+ ### Framework versions
81
+
82
+ - Transformers 4.39.3
83
+ - Pytorch 2.3.0+cu121
84
+ - Datasets 2.19.1
85
+ - Tokenizers 0.15.2