Commit ·
7284817
1
Parent(s): d08d694
updating the testing and validation doc
Browse files
docs/testing_and_validation.md
CHANGED
|
@@ -22,9 +22,6 @@ Behavioral testing evaluates the model's capabilities and robustness beyond simp
|
|
| 22 |
| **Directional Tests** | 10 | **Passed** | Verify that specific changes to the input cause expected changes in the output (e.g., adding specific keywords should increase probability of related skills). |
|
| 23 |
| **Minimum Functionality Tests** | 17 | **Passed** | Check basic capabilities and sanity checks (e.g., simple inputs produce valid outputs). |
|
| 24 |
|
| 25 |
-
### Technical Notes
|
| 26 |
-
- **Training Tests Excluded:** `test_model_training.py` was excluded from the run due to a missing PyTorch dependency in the environment, but the inference tests cover the model's behavior fully.
|
| 27 |
-
- **Robustness:** The model demonstrates excellent consistency across all 36 behavioral scenarios.
|
| 28 |
|
| 29 |
### How to Regenerate
|
| 30 |
To run the behavioral tests and generate the JSON report:
|
|
|
|
| 22 |
| **Directional Tests** | 10 | **Passed** | Verify that specific changes to the input cause expected changes in the output (e.g., adding specific keywords should increase probability of related skills). |
|
| 23 |
| **Minimum Functionality Tests** | 17 | **Passed** | Check basic capabilities and sanity checks (e.g., simple inputs produce valid outputs). |
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
### How to Regenerate
|
| 27 |
To run the behavioral tests and generate the JSON report:
|