Update README.md
Browse files
README.md
CHANGED
|
@@ -46,15 +46,15 @@ The following hyperparameters were used during training:
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
-
|
| 51 |
-
| 15.6719 | 0.99 | 22 | 5.3660 |
|
| 52 |
-
| 4.3293 | 1.98 | 44 | 4.4748 |
|
| 53 |
-
| 3.882 | 2.97 | 66 | 4.2731 |
|
| 54 |
-
| 3.7072 | 3.96 | 88 | 4.1473 |
|
| 55 |
-
| 3.6499 | 4.94 | 110 | 4.1219 |
|
| 56 |
-
| 3.5604 | 5.93 | 132 | 4.0896 |
|
| 57 |
-
| 3.5268 | 6.92 | 154 | 4.0700 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:----------:|
|
| 51 |
+
| 15.6719 | 0.99 | 22 | 5.3660 | 214.0051 |
|
| 52 |
+
| 4.3293 | 1.98 | 44 | 4.4748 | 87.7770 |
|
| 53 |
+
| 3.882 | 2.97 | 66 | 4.2731 | 71.7437 |
|
| 54 |
+
| 3.7072 | 3.96 | 88 | 4.1473 | 63.2630 |
|
| 55 |
+
| 3.6499 | 4.94 | 110 | 4.1219 | 61.6763 |
|
| 56 |
+
| 3.5604 | 5.93 | 132 | 4.0896 | 59.7160 |
|
| 57 |
+
| 3.5268 | 6.92 | 154 | 4.0700 | 58.5570 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|