Tommert25 commited on
Commit
c37073d
·
1 Parent(s): cec5723

End of training

Browse files
Files changed (1) hide show
  1. README.md +77 -0
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: bert-base-multilingual-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - recall
8
+ - accuracy
9
+ model-index:
10
+ - name: multibert_dataaugmentation
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
+ # multibert_dataaugmentation
18
+
19
+ This model is a fine-tuned version of [bert-base-multilingual-uncased](https://huggingface.co/bert-base-multilingual-uncased) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.5981
22
+ - Precisions: 0.8870
23
+ - Recall: 0.8815
24
+ - F-measure: 0.8825
25
+ - Accuracy: 0.9265
26
+
27
+ ## Model description
28
+
29
+ More information needed
30
+
31
+ ## Intended uses & limitations
32
+
33
+ More information needed
34
+
35
+ ## Training and evaluation data
36
+
37
+ More information needed
38
+
39
+ ## Training procedure
40
+
41
+ ### Training hyperparameters
42
+
43
+ The following hyperparameters were used during training:
44
+ - learning_rate: 7.5e-05
45
+ - train_batch_size: 16
46
+ - eval_batch_size: 16
47
+ - seed: 42
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 14
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
55
+ |:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:|
56
+ | 0.5651 | 1.0 | 284 | 0.4671 | 0.8381 | 0.7291 | 0.7488 | 0.8699 |
57
+ | 0.2863 | 2.0 | 568 | 0.4120 | 0.8143 | 0.8209 | 0.8151 | 0.8946 |
58
+ | 0.1717 | 3.0 | 852 | 0.3688 | 0.8778 | 0.8430 | 0.8579 | 0.9065 |
59
+ | 0.1085 | 4.0 | 1136 | 0.4175 | 0.8609 | 0.8656 | 0.8624 | 0.9097 |
60
+ | 0.0677 | 5.0 | 1420 | 0.4885 | 0.8728 | 0.8483 | 0.8588 | 0.9142 |
61
+ | 0.0526 | 6.0 | 1704 | 0.5384 | 0.8672 | 0.8786 | 0.8672 | 0.9152 |
62
+ | 0.0372 | 7.0 | 1988 | 0.4872 | 0.8766 | 0.8770 | 0.8759 | 0.9161 |
63
+ | 0.0239 | 8.0 | 2272 | 0.5377 | 0.9011 | 0.8665 | 0.8799 | 0.9227 |
64
+ | 0.0181 | 9.0 | 2556 | 0.5604 | 0.8846 | 0.8796 | 0.8813 | 0.9236 |
65
+ | 0.0117 | 10.0 | 2840 | 0.5815 | 0.8695 | 0.8786 | 0.8700 | 0.9229 |
66
+ | 0.008 | 11.0 | 3124 | 0.6035 | 0.8842 | 0.8701 | 0.8744 | 0.9206 |
67
+ | 0.0047 | 12.0 | 3408 | 0.5789 | 0.8644 | 0.8815 | 0.8662 | 0.9232 |
68
+ | 0.0037 | 13.0 | 3692 | 0.5891 | 0.8763 | 0.8782 | 0.8740 | 0.9259 |
69
+ | 0.0026 | 14.0 | 3976 | 0.5981 | 0.8870 | 0.8815 | 0.8825 | 0.9265 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.34.0
75
+ - Pytorch 2.0.1+cu118
76
+ - Datasets 2.14.5
77
+ - Tokenizers 0.14.1