Update README.md
Browse files
README.md
CHANGED
@@ -13,9 +13,12 @@ I used this password list as a dataset + random password generation using the `r
|
|
13 |
The model was trained on 4,2MiB of .csv data for 2 epochs on Adam with learning rate 0.00001, batch size 4 and mse loss.
|
14 |
The model embeds every input character with the ord() builtin python function. The model has `128 128` dense layer parameters.
|
15 |
## Evaluation
|
|
|
|
|
|
|
16 |
The evaluation of the model on a test dataset shows:
|
17 |
-
**loss** -
|
18 |
-
**accuracy** -
|
19 |
## Model usage
|
20 |
The `start.py` file has a `clf` function that inputs a string of a password and responds with a 0-1 float value. 1 means secure and 0 insecure.
|
21 |
To train the model, create a `dataset.csv` file. Here's an example:
|
|
|
13 |
The model was trained on 4,2MiB of .csv data for 2 epochs on Adam with learning rate 0.00001, batch size 4 and mse loss.
|
14 |
The model embeds every input character with the ord() builtin python function. The model has `128 128` dense layer parameters.
|
15 |
## Evaluation
|
16 |
+
On training the model had
|
17 |
+
**loss** - 0.0025
|
18 |
+
**accuracy** - 0.9972
|
19 |
The evaluation of the model on a test dataset shows:
|
20 |
+
**loss** - 0.0023
|
21 |
+
**accuracy** - 0.9972
|
22 |
## Model usage
|
23 |
The `start.py` file has a `clf` function that inputs a string of a password and responds with a 0-1 float value. 1 means secure and 0 insecure.
|
24 |
To train the model, create a `dataset.csv` file. Here's an example:
|