adding the notebook to train
Browse files
README.md
CHANGED
|
@@ -21,6 +21,7 @@ tags:
|
|
| 21 |
## Model
|
| 22 |
1. Multi-head neural network. One head is used for each feature (description, requirements, and benefits of the job).
|
| 23 |
2. Best metrics achieved (over validation data-split): Precision: 0.83, Recall: 0.65, F1-score: 0.71
|
|
|
|
| 24 |
|
| 25 |
### Components:
|
| 26 |
Text Encoder: distilbert-base-uncased is used to encode the textual input into a dense vector.
|
|
|
|
| 21 |
## Model
|
| 22 |
1. Multi-head neural network. One head is used for each feature (description, requirements, and benefits of the job).
|
| 23 |
2. Best metrics achieved (over validation data-split): Precision: 0.83, Recall: 0.65, F1-score: 0.71
|
| 24 |
+
3. Code used for training comes from this GitHub repo: https://github.com/sebassaras02/AdvancedDLCourse/blob/master/02_transformers_nlp/bert.ipynb
|
| 25 |
|
| 26 |
### Components:
|
| 27 |
Text Encoder: distilbert-base-uncased is used to encode the textual input into a dense vector.
|