sianbru commited on
Commit
1c95522
1 Parent(s): 91020a8

Model save

Browse files
Files changed (1) hide show
  1. README.md +68 -0
README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: bert-base-german-dbmdz-uncased
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ - f1
9
+ - precision
10
+ - recall
11
+ model-index:
12
+ - name: product_classifier_split_url_nodigit_all
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
+ # product_classifier_split_url_nodigit_all
20
+
21
+ This model is a fine-tuned version of [bert-base-german-dbmdz-uncased](https://huggingface.co/bert-base-german-dbmdz-uncased) on an unknown dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.1833
24
+ - Accuracy: 0.9734
25
+ - F1: 0.9732
26
+ - Precision: 0.9731
27
+ - Recall: 0.9734
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: 2e-05
47
+ - train_batch_size: 32
48
+ - eval_batch_size: 32
49
+ - seed: 42
50
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
51
+ - lr_scheduler_type: linear
52
+ - num_epochs: 3
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
57
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
58
+ | 0.0385 | 1.0 | 1300 | 0.1880 | 0.9666 | 0.9663 | 0.9665 | 0.9666 |
59
+ | 0.0198 | 2.0 | 2600 | 0.1707 | 0.9718 | 0.9718 | 0.9719 | 0.9718 |
60
+ | 0.0083 | 3.0 | 3900 | 0.1833 | 0.9734 | 0.9732 | 0.9731 | 0.9734 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - Transformers 4.32.0
66
+ - Pytorch 2.0.1+cu117
67
+ - Datasets 2.14.4
68
+ - Tokenizers 0.13.3