Hugging Face's logo

OpenAlex
/
bert-base-multilingual-cased-finetuned-openalex-topic-classification-title-abstract

Text Classification
Transformers
TensorFlow
Safetensors
bert
Inference Endpoints
Model card Files Community
justin13barrett commited on
Commit
983f956
•
1 Parent(s): 0811c81

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -17
README.md CHANGED
@@ -16,14 +16,8 @@ probably proofread and complete it, then remove this comment. -->
16
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
  - Train Loss: 2.4942
19
- - Train Categorical Accuracy: 0.0002
20
- - Train Top 2 Categorical Accuracy: 0.0005
21
- - Train Top 10 Categorical Accuracy: 0.0024
22
  - Validation Loss: 3.0737
23
- - Validation Categorical Accuracy: 0.0003
24
- - Validation Top 2 Categorical Accuracy: 0.0006
25
- - Validation Top 10 Categorical Accuracy: 0.0028
26
- - Train Accuracy: 0.4846
27
  - Epoch: 7
28
 
29
  ## Model description
@@ -48,16 +42,16 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Train Loss | Train Categorical Accuracy | Train Top 2 Categorical Accuracy | Train Top 10 Categorical Accuracy | Validation Loss | Validation Categorical Accuracy | Validation Top 2 Categorical Accuracy | Validation Top 10 Categorical Accuracy | Train Accuracy | Epoch |
52
- |:----------:|:--------------------------:|:--------------------------------:|:---------------------------------:|:---------------:|:-------------------------------:|:-------------------------------------:|:--------------------------------------:|:--------------:|:-----:|
53
- | 4.8075 | 0.0001 | 0.0002 | 0.0020 | 3.6686 | 0.0000 | 0.0001 | 0.0017 | 0.3839 | 0 |
54
- | 3.4867 | 0.0002 | 0.0004 | 0.0028 | 3.3360 | 0.0001 | 0.0002 | 0.0014 | 0.4337 | 1 |
55
- | 3.1865 | 0.0002 | 0.0004 | 0.0027 | 3.2005 | 0.0002 | 0.0005 | 0.0033 | 0.4556 | 2 |
56
- | 2.9969 | 0.0002 | 0.0005 | 0.0027 | 3.1379 | 0.0001 | 0.0002 | 0.0014 | 0.4675 | 3 |
57
- | 2.8489 | 0.0002 | 0.0004 | 0.0025 | 3.0900 | 0.0002 | 0.0005 | 0.0031 | 0.4746 | 4 |
58
- | 2.7212 | 0.0002 | 0.0005 | 0.0025 | 3.0744 | 0.0002 | 0.0003 | 0.0021 | 0.4799 | 5 |
59
- | 2.6035 | 0.0002 | 0.0004 | 0.0025 | 3.0660 | 0.0002 | 0.0004 | 0.0023 | 0.4831 | 6 |
60
- | 2.4942 | 0.0002 | 0.0005 | 0.0024 | 3.0737 | 0.0003 | 0.0006 | 0.0028 | 0.4846 | 7 |
61
 
62
 
63
  ### Framework versions
 
16
  This model is a fine-tuned version of [bert-base-multilingual-cased](https://huggingface.co/bert-base-multilingual-cased) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
  - Train Loss: 2.4942
 
 
 
19
  - Validation Loss: 3.0737
20
+ - Validation Accuracy: 0.4846
 
 
 
21
  - Epoch: 7
22
 
23
  ## Model description
 
42
 
43
  ### Training results
44
 
45
+ | Train Loss | Validation Loss | Train Accuracy | Epoch |
46
+ |:----------:|:---------------:|:--------------:|:-----:|
47
+ | 4.8075 | 3.6686 | 0.3839 | 0 |
48
+ | 3.4867 | 3.3360 | 0.4337 | 1 |
49
+ | 3.1865 | 3.2005 | 0.4556 | 2 |
50
+ | 2.9969 | 3.1379 | 0.4675 | 3 |
51
+ | 2.8489 | 3.0900 | 0.4746 | 4 |
52
+ | 2.7212 | 3.0744 | 0.4799 | 5 |
53
+ | 2.6035 | 3.0660 | 0.4831 | 6 |
54
+ | 2.4942 | 3.0737 | 0.4846 | 7 |
55
 
56
 
57
  ### Framework versions