Hugging Face's logo

osei1819
/
phishing_detection_fine_tuned_bert

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Model card Files Community
osei1819 commited on
Commit
561d5ea
·
verified ·
1 Parent(s): 9bb21d7

End of training

Browse files
Files changed (1) hide show
  1. README.md +18 -9
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.2946
25
- - Accuracy: 0.8809
26
- - F1: 0.8809
27
- - Precision: 0.8808
28
- - Recall: 0.8809
29
 
30
  ## Model description
31
 
@@ -51,13 +51,22 @@ The following hyperparameters were used during training:
51
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 500
54
- - num_epochs: 1
55
 
56
  ### Training results
57
 
58
- | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
- |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
- | 0.2703 | 1.0 | 3622 | 0.2946 | 0.8809 | 0.8809 | 0.8808 | 0.8809 |
 
 
 
 
 
 
 
 
 
61
 
62
 
63
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 0.3343
25
+ - Accuracy: 0.8565
26
+ - F1: 0.8573
27
+ - Precision: 0.8596
28
+ - Recall: 0.8565
29
 
30
  ## Model description
31
 
 
51
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
  - lr_scheduler_warmup_steps: 500
54
+ - num_epochs: 10
55
 
56
  ### Training results
57
 
58
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
59
+ |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
60
+ | 0.411 | 1.0 | 3622 | 0.3300 | 0.8222 | 0.8242 | 0.8509 | 0.8222 |
61
+ | 0.4471 | 2.0 | 7244 | 0.6779 | 0.8154 | 0.8067 | 0.8274 | 0.8154 |
62
+ | 0.6583 | 3.0 | 10866 | 0.6717 | 0.6079 | 0.4597 | 0.3695 | 0.6079 |
63
+ | 0.6286 | 4.0 | 14488 | 0.6698 | 0.6079 | 0.4597 | 0.3695 | 0.6079 |
64
+ | 0.6527 | 5.0 | 18110 | 0.6697 | 0.6079 | 0.4597 | 0.3695 | 0.6079 |
65
+ | 0.336 | 6.0 | 21732 | 0.4681 | 0.7707 | 0.7719 | 0.8293 | 0.7707 |
66
+ | 0.5686 | 7.0 | 25354 | 0.6242 | 0.5740 | 0.5518 | 0.7128 | 0.5740 |
67
+ | 0.334 | 8.0 | 28976 | 0.3666 | 0.8279 | 0.8298 | 0.8433 | 0.8279 |
68
+ | 0.4017 | 9.0 | 32598 | 0.3711 | 0.8571 | 0.8561 | 0.8564 | 0.8571 |
69
+ | 0.2285 | 10.0 | 36220 | 0.3343 | 0.8565 | 0.8573 | 0.8596 | 0.8565 |
70
 
71
 
72
  ### Framework versions