Hugging Face's logo

Etelis
/
TUF_BERT_5E

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
text-embeddings-inference
Model card Files
xet
 Community
2
Etelis commited on
Commit
a8ab473
·
1 Parent(s): b0e3625

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +108 -0
README.md ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - accuracy
7
+ model-index:
8
+ - name: TUF_BERT_5E
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # TUF_BERT_5E
16
+
17
+ This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.3251
20
+ - Accuracy: 0.9467
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 2e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
50
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
51
+ | 0.4078 | 0.1 | 50 | 0.2430 | 0.92 |
52
+ | 0.2488 | 0.2 | 100 | 0.1465 | 0.94 |
53
+ | 0.1966 | 0.3 | 150 | 0.1284 | 0.96 |
54
+ | 0.2096 | 0.4 | 200 | 0.2879 | 0.9067 |
55
+ | 0.2015 | 0.5 | 250 | 0.1629 | 0.9467 |
56
+ | 0.1692 | 0.59 | 300 | 0.2165 | 0.9133 |
57
+ | 0.1794 | 0.69 | 350 | 0.1535 | 0.9533 |
58
+ | 0.1975 | 0.79 | 400 | 0.1429 | 0.9333 |
59
+ | 0.1394 | 0.89 | 450 | 0.2384 | 0.92 |
60
+ | 0.191 | 0.99 | 500 | 0.2198 | 0.94 |
61
+ | 0.0907 | 1.09 | 550 | 0.1270 | 0.9467 |
62
+ | 0.073 | 1.19 | 600 | 0.2016 | 0.94 |
63
+ | 0.1594 | 1.29 | 650 | 0.2078 | 0.9267 |
64
+ | 0.087 | 1.39 | 700 | 0.3312 | 0.9333 |
65
+ | 0.0961 | 1.49 | 750 | 0.3704 | 0.92 |
66
+ | 0.1225 | 1.58 | 800 | 0.1686 | 0.9467 |
67
+ | 0.0969 | 1.68 | 850 | 0.1525 | 0.9333 |
68
+ | 0.0942 | 1.78 | 900 | 0.1924 | 0.94 |
69
+ | 0.0681 | 1.88 | 950 | 0.1825 | 0.9467 |
70
+ | 0.1295 | 1.98 | 1000 | 0.1360 | 0.9333 |
71
+ | 0.0626 | 2.08 | 1050 | 0.2014 | 0.94 |
72
+ | 0.0372 | 2.18 | 1100 | 0.2030 | 0.9467 |
73
+ | 0.0077 | 2.28 | 1150 | 0.2615 | 0.9467 |
74
+ | 0.0393 | 2.38 | 1200 | 0.4256 | 0.9267 |
75
+ | 0.0492 | 2.48 | 1250 | 0.3057 | 0.94 |
76
+ | 0.0184 | 2.57 | 1300 | 0.1308 | 0.9733 |
77
+ | 0.0209 | 2.67 | 1350 | 0.2848 | 0.9467 |
78
+ | 0.0328 | 2.77 | 1400 | 0.1862 | 0.96 |
79
+ | 0.0333 | 2.87 | 1450 | 0.2347 | 0.96 |
80
+ | 0.0527 | 2.97 | 1500 | 0.3855 | 0.9333 |
81
+ | 0.0685 | 3.07 | 1550 | 0.3174 | 0.94 |
82
+ | 0.0217 | 3.17 | 1600 | 0.2320 | 0.9533 |
83
+ | 0.0036 | 3.27 | 1650 | 0.3219 | 0.9333 |
84
+ | 0.0015 | 3.37 | 1700 | 0.1649 | 0.9733 |
85
+ | 0.0177 | 3.47 | 1750 | 0.3785 | 0.94 |
86
+ | 0.0142 | 3.56 | 1800 | 0.1420 | 0.9733 |
87
+ | 0.0319 | 3.66 | 1850 | 0.4057 | 0.9333 |
88
+ | 0.0254 | 3.76 | 1900 | 0.1824 | 0.96 |
89
+ | 0.0092 | 3.86 | 1950 | 0.2400 | 0.9533 |
90
+ | 0.0306 | 3.96 | 2000 | 0.2238 | 0.96 |
91
+ | 0.0118 | 4.06 | 2050 | 0.2623 | 0.9533 |
92
+ | 0.0097 | 4.16 | 2100 | 0.3642 | 0.9467 |
93
+ | 0.0132 | 4.26 | 2150 | 0.3235 | 0.9467 |
94
+ | 0.0155 | 4.36 | 2200 | 0.3535 | 0.9467 |
95
+ | 0.0043 | 4.46 | 2250 | 0.3236 | 0.9467 |
96
+ | 0.0004 | 4.55 | 2300 | 0.2984 | 0.9467 |
97
+ | 0.009 | 4.65 | 2350 | 0.2941 | 0.9467 |
98
+ | 0.0068 | 4.75 | 2400 | 0.2936 | 0.9467 |
99
+ | 0.0102 | 4.85 | 2450 | 0.3138 | 0.9467 |
100
+ | 0.0015 | 4.95 | 2500 | 0.3251 | 0.9467 |
101
+
102
+
103
+ ### Framework versions
104
+
105
+ - Transformers 4.24.0
106
+ - Pytorch 1.13.0
107
+ - Datasets 2.7.1
108
+ - Tokenizers 0.13.2