Erdenebold commited on
Commit
4b4d9b2
·
1 Parent(s): a5e7b34

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +76 -0
README.md ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - mn
4
+ license: apache-2.0
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - precision
9
+ - recall
10
+ - f1
11
+ - accuracy
12
+ model-index:
13
+ - name: test-distilbert-base-multilingual-cased
14
+ results: []
15
+ ---
16
+
17
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
18
+ should probably proofread and complete it, then remove this comment. -->
19
+
20
+ # test-distilbert-base-multilingual-cased
21
+
22
+ This model is a fine-tuned version of [distilbert-base-multilingual-cased](https://huggingface.co/distilbert-base-multilingual-cased) on the None dataset.
23
+ It achieves the following results on the evaluation set:
24
+ - Loss: 0.1533
25
+ - Precision: 0.8783
26
+ - Recall: 0.9010
27
+ - F1: 0.8895
28
+ - Accuracy: 0.9721
29
+
30
+ ## Model description
31
+
32
+ More information needed
33
+
34
+ ## Intended uses & limitations
35
+
36
+ More information needed
37
+
38
+ ## Training and evaluation data
39
+
40
+ More information needed
41
+
42
+ ## Training procedure
43
+
44
+ ### Training hyperparameters
45
+
46
+ The following hyperparameters were used during training:
47
+ - learning_rate: 2e-05
48
+ - train_batch_size: 16
49
+ - eval_batch_size: 32
50
+ - seed: 42
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - num_epochs: 10
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
58
+ |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
59
+ | 0.2124 | 1.0 | 477 | 0.1286 | 0.8065 | 0.8469 | 0.8262 | 0.9586 |
60
+ | 0.103 | 2.0 | 954 | 0.1113 | 0.8374 | 0.8772 | 0.8568 | 0.9663 |
61
+ | 0.0673 | 3.0 | 1431 | 0.1124 | 0.8480 | 0.8810 | 0.8641 | 0.9668 |
62
+ | 0.0474 | 4.0 | 1908 | 0.1165 | 0.8658 | 0.8922 | 0.8788 | 0.9710 |
63
+ | 0.0338 | 5.0 | 2385 | 0.1254 | 0.8664 | 0.8909 | 0.8785 | 0.9692 |
64
+ | 0.0236 | 6.0 | 2862 | 0.1349 | 0.8686 | 0.8954 | 0.8818 | 0.9707 |
65
+ | 0.018 | 7.0 | 3339 | 0.1428 | 0.8772 | 0.8991 | 0.8880 | 0.9715 |
66
+ | 0.0133 | 8.0 | 3816 | 0.1505 | 0.8739 | 0.8961 | 0.8849 | 0.9712 |
67
+ | 0.0106 | 9.0 | 4293 | 0.1529 | 0.8812 | 0.9012 | 0.8911 | 0.9720 |
68
+ | 0.0082 | 10.0 | 4770 | 0.1533 | 0.8783 | 0.9010 | 0.8895 | 0.9721 |
69
+
70
+
71
+ ### Framework versions
72
+
73
+ - Transformers 4.28.0
74
+ - Pytorch 2.0.1+cu118
75
+ - Datasets 2.12.0
76
+ - Tokenizers 0.13.3