Hugging Face's logo

cm-mueller
/
BACnet-Klassifizierung-Raumlufttechnik

Text Classification
Transformers
PyTorch
TensorBoard
German
bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
cm-mueller commited on
Commit
795a08c
•
1 Parent(s): b59380d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +103 -0
README.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - f1
7
+ model-index:
8
+ - name: BACnet-Klassifizierung-Raumlufttechnik-bert-base-german-cased
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
+ # BACnet-Klassifizierung-Raumlufttechnik-bert-base-german-cased
16
+
17
+ This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.0597
20
+ - F1: [0.98461538 0.66666667 1. 1. 1. 1.
21
+ 0.94736842 1. 1. 1. 1. 0.99115044
22
+ 0.85714286 1. 1. 1. 1. 0.
23
+ 1. ]
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 8
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 16
47
+ - total_train_batch_size: 128
48
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
+ - lr_scheduler_type: linear
50
+ - num_epochs: 10.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss | F1 |
55
+ |:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
56
+ | 2.1097 | 0.99 | 18 | 1.1253 | [0.77966102 0. 0.7037037 0. 0.875 0.57142857
57
+ 0. 0.94736842 0. 0.92857143 0. 0.85496183
58
+ 0. 1. 0.69230769 0. 0.79569892 0.
59
+ 0.53333333] |
60
+ | 0.8677 | 1.99 | 36 | 0.4032 | [0.98461538 0. 0.91666667 0.90909091 1. 1.
61
+ 0.8 1. 0.33333333 0.96551724 0. 0.96551724
62
+ 0.4 1. 0.71428571 1. 0.97297297 0.
63
+ 0.9 ] |
64
+ | 0.3622 | 2.99 | 54 | 0.1977 | [0.98461538 0.66666667 0.97777778 0.90909091 1. 1.
65
+ 0.94736842 1. 0.90909091 0.96551724 0.5 0.98245614
66
+ 0.85714286 1. 0.90909091 1. 1. 0.
67
+ 1. ] |
68
+ | 0.1729 | 3.99 | 72 | 0.1447 | [0.98461538 0.66666667 0.97777778 0.90909091 1. 1.
69
+ 0.94736842 1. 1. 0.96551724 0.8 0.97391304
70
+ 0.85714286 1. 0.95238095 1. 1. 0.
71
+ 1. ] |
72
+ | 0.0995 | 4.99 | 90 | 0.0972 | [0.98461538 0.66666667 0.97777778 0.95652174 1. 1.
73
+ 0.94736842 1. 1. 0.96551724 1. 0.98245614
74
+ 0.85714286 1. 1. 1. 1. 0.
75
+ 1. ] |
76
+ | 0.0682 | 5.99 | 108 | 0.0814 | [0.98461538 0.66666667 1. 0.95652174 1. 1.
77
+ 0.94736842 1. 1. 0.96551724 1. 0.97391304
78
+ 0.66666667 1. 1. 1. 1. 0.
79
+ 0.95652174] |
80
+ | 0.0575 | 6.99 | 126 | 0.0701 | [0.98461538 0.66666667 1. 1. 1. 1.
81
+ 0.94736842 1. 1. 1. 1. 0.99115044
82
+ 0.85714286 1. 1. 1. 1. 0.
83
+ 1. ] |
84
+ | 0.0406 | 7.99 | 144 | 0.0576 | [0.98461538 0.66666667 1. 1. 1. 1.
85
+ 0.94736842 1. 1. 1. 1. 0.99115044
86
+ 0.85714286 1. 1. 1. 1. 0.
87
+ 1. ] |
88
+ | 0.0392 | 8.99 | 162 | 0.0625 | [0.98461538 0.66666667 1. 1. 1. 1.
89
+ 0.94736842 1. 1. 1. 1. 0.99115044
90
+ 0.85714286 1. 1. 1. 1. 0.
91
+ 1. ] |
92
+ | 0.0337 | 9.99 | 180 | 0.0597 | [0.98461538 0.66666667 1. 1. 1. 1.
93
+ 0.94736842 1. 1. 1. 1. 0.99115044
94
+ 0.85714286 1. 1. 1. 1. 0.
95
+ 1. ] |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.21.1
101
+ - Pytorch 1.12.0+cu113
102
+ - Datasets 2.4.0
103
+ - Tokenizers 0.12.1