Update README.md
Browse files
README.md
CHANGED
|
@@ -19,23 +19,6 @@ This model is a fine-tuned version of [neuralmind/bert-base-portuguese-cased](ht
|
|
| 19 |
More information needed
|
| 20 |
|
| 21 |
|
| 22 |
-
## Evaluation
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
- 'exact': 75.76715597879051
|
| 26 |
-
- 'f1': 86.10779795627346
|
| 27 |
-
- 'total': 130319
|
| 28 |
-
- 'HasAns_exact': 66.280047453957
|
| 29 |
-
- 'HasAns_f1': 81.80143193308851
|
| 30 |
-
- 'HasAns_total': 86821
|
| 31 |
-
- 'NoAns_exact': 94.70320474504575
|
| 32 |
-
- 'NoAns_f1': 94.70320474504575
|
| 33 |
-
- 'NoAns_total': 43498
|
| 34 |
-
- 'best_exact': 75.77176006568497
|
| 35 |
-
- 'best_exact_thresh': 0.0
|
| 36 |
-
- 'best_f1': 86.11240204317286
|
| 37 |
-
- 'best_f1_thresh': 0.0
|
| 38 |
-
|
| 39 |
|
| 40 |
### Training hyperparameters
|
| 41 |
|
|
|
|
| 19 |
More information needed
|
| 20 |
|
| 21 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
### Training hyperparameters
|
| 24 |
|