Hugging Face's logo

Noodle-bg
/
BERT_Text_classification_clean

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files
xet
Community
Noodle-bg commited on
Commit
c0d69da
·
verified ·
1 Parent(s): 31220c9

Model save

Browse files
Files changed (1) hide show
  1. README.md +17 -17
README.md CHANGED
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.5765
24
- - Accuracy: 0.8916
25
- - F1: 0.8819
26
- - Precision: 0.8861
27
- - Recall: 0.8814
28
 
29
  ## Model description
30
 
@@ -56,18 +56,18 @@ The following hyperparameters were used during training:
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
- | 1.7091 | 0.24 | 50 | 1.3063 | 0.7223 | 0.6464 | 0.6264 | 0.6964 |
60
- | 0.7451 | 0.48 | 100 | 0.4844 | 0.8477 | 0.8309 | 0.8442 | 0.8343 |
61
- | 0.3087 | 0.71 | 150 | 0.4129 | 0.8603 | 0.8527 | 0.8555 | 0.8518 |
62
- | 0.2333 | 0.95 | 200 | 0.3832 | 0.8858 | 0.8749 | 0.8772 | 0.8753 |
63
- | 0.1012 | 1.19 | 250 | 0.5194 | 0.8836 | 0.8736 | 0.8772 | 0.8733 |
64
- | 0.1 | 1.43 | 300 | 0.5694 | 0.8688 | 0.8581 | 0.8636 | 0.8578 |
65
- | 0.1025 | 1.67 | 350 | 0.5772 | 0.8849 | 0.8751 | 0.8794 | 0.8748 |
66
- | 0.0592 | 1.9 | 400 | 0.6057 | 0.8849 | 0.8741 | 0.8797 | 0.8742 |
67
- | 0.0425 | 2.14 | 450 | 0.5783 | 0.8921 | 0.8811 | 0.8852 | 0.8812 |
68
- | 0.0337 | 2.38 | 500 | 0.5376 | 0.8925 | 0.8815 | 0.8852 | 0.8816 |
69
- | 0.031 | 2.62 | 550 | 0.5806 | 0.8912 | 0.8804 | 0.8841 | 0.8805 |
70
- | 0.009 | 2.86 | 600 | 0.5765 | 0.8916 | 0.8819 | 0.8861 | 0.8814 |
71
 
72
 
73
  ### Framework versions
 
20
 
21
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.5208
24
+ - Accuracy: 0.9028
25
+ - F1: 0.8924
26
+ - Precision: 0.8990
27
+ - Recall: 0.8925
28
 
29
  ## Model description
30
 
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
58
  |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
59
+ | 1.6803 | 0.24 | 50 | 1.2419 | 0.7613 | 0.7374 | 0.7493 | 0.7460 |
60
+ | 0.6367 | 0.48 | 100 | 0.4523 | 0.8437 | 0.8358 | 0.8377 | 0.8357 |
61
+ | 0.2756 | 0.71 | 150 | 0.4543 | 0.8625 | 0.8550 | 0.8576 | 0.8544 |
62
+ | 0.2569 | 0.95 | 200 | 0.4377 | 0.8845 | 0.8715 | 0.8791 | 0.8727 |
63
+ | 0.1044 | 1.19 | 250 | 0.5032 | 0.8903 | 0.8793 | 0.8828 | 0.8795 |
64
+ | 0.0745 | 1.43 | 300 | 0.5342 | 0.8912 | 0.8791 | 0.8881 | 0.8798 |
65
+ | 0.0906 | 1.67 | 350 | 0.5484 | 0.8992 | 0.8880 | 0.8956 | 0.8886 |
66
+ | 0.0839 | 1.9 | 400 | 0.5337 | 0.8939 | 0.8827 | 0.8858 | 0.8830 |
67
+ | 0.0474 | 2.14 | 450 | 0.5237 | 0.8983 | 0.8876 | 0.8938 | 0.8879 |
68
+ | 0.0346 | 2.38 | 500 | 0.4822 | 0.9037 | 0.8939 | 0.9005 | 0.8939 |
69
+ | 0.0243 | 2.62 | 550 | 0.5014 | 0.9019 | 0.8916 | 0.8964 | 0.8917 |
70
+ | 0.0181 | 2.86 | 600 | 0.5208 | 0.9028 | 0.8924 | 0.8990 | 0.8925 |
71
 
72
 
73
  ### Framework versions