ab-ai commited on
Commit
33768a4
1 Parent(s): 2626ebd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -11
README.md CHANGED
@@ -24,10 +24,10 @@ The model is intended to be used for automatically identifying and extracting PI
24
 
25
  The model's performance was evaluated on a held-out validation set using the following metrics:
26
 
27
- - Precision: 0.93
28
- - Recall: 0.94
29
- - F1 Score: 0.94
30
- - Accuracy: 0.97
31
 
32
  ## Limitations and bias
33
 
@@ -41,16 +41,16 @@ The model's performance was evaluated on a held-out validation set using the fol
41
  - Data used to train and evaluate the model should be handled with caution to avoid the risk of exposing PII.
42
  - Regular monitoring and auditing of the model's predictions may be necessary to identify and mitigate any potential biases or errors.
43
 
44
- ## Training results
45
 
46
  | Epoch | Training Loss | Validation Loss | Precision | Recall | F1 Score | Accuracy |
47
  |-------|---------------|-----------------|-----------|--------|----------|----------|
48
- | 1 | 0.093200 | 0.071345 | 0.905912 | 0.933906 | 0.919696 | 0.968861 |
49
- | 2 | 0.067100 | 0.069066 | 0.912207 | 0.936481 | 0.924185 | 0.969175 |
50
- | 3 | 0.060000 | 0.063845 | 0.930860 | 0.947639 | 0.939175 | 0.970566 |
51
- | 4 | 0.043600 | 0.086811 | 0.925738 | 0.941631 | 0.933617 | 0.965496 |
52
- | 5 | 0.025400 | 0.118688 | 0.931181 | 0.940773 | 0.935952 | 0.965092 |
53
- | 6 | 0.012400 | 0.154431 | 0.931181 | 0.940773 | 0.935952 | 0.971463 |
54
 
55
  ## Authors
56
 
 
24
 
25
  The model's performance was evaluated on a held-out validation set using the following metrics:
26
 
27
+ - Precision: 94%
28
+ - Recall: 96%
29
+ - F1 Score: 95%
30
+ - Accuracy: 99%
31
 
32
  ## Limitations and bias
33
 
 
41
  - Data used to train and evaluate the model should be handled with caution to avoid the risk of exposing PII.
42
  - Regular monitoring and auditing of the model's predictions may be necessary to identify and mitigate any potential biases or errors.
43
 
44
+ ## Model Training and Evaluation Results
45
 
46
  | Epoch | Training Loss | Validation Loss | Precision | Recall | F1 Score | Accuracy |
47
  |-------|---------------|-----------------|-----------|--------|----------|----------|
48
+ | 1 | 0.047 | 0.051537 | 91.35% | 95.23% | 93.25% | 98.56% |
49
+ | 2 | 0.0307 | 0.043873 | 93.27% | 96.10% | 94.66% | 98.75% |
50
+ | 3 | 0.0208 | 0.04702 | 91.83% | 95.49% | 93.62% | 98.54% |
51
+ | 4 | 0.0147 | 0.046979 | 93.27% | 94.97% | 94.11% | 98.77% |
52
+ | 5 | 0.0094 | 0.057863 | 93.41% | 95.92% | 94.65% | 98.70% |
53
+
54
 
55
  ## Authors
56