Update README.md
Browse files
README.md
CHANGED
|
@@ -21,18 +21,6 @@ It achieves the following results on the evaluation set:
|
|
| 21 |
- Loss: 1.4442
|
| 22 |
- Perplexity: 4.2384
|
| 23 |
|
| 24 |
-
## Model description
|
| 25 |
-
|
| 26 |
-
More information needed
|
| 27 |
-
|
| 28 |
-
## Intended uses & limitations
|
| 29 |
-
|
| 30 |
-
More information needed
|
| 31 |
-
|
| 32 |
-
## Training and evaluation data
|
| 33 |
-
|
| 34 |
-
More information needed
|
| 35 |
-
|
| 36 |
## Training procedure
|
| 37 |
|
| 38 |
### Training hyperparameters
|
|
@@ -55,6 +43,7 @@ The following hyperparameters were used during training:
|
|
| 55 |
| 1.6345 | 1.2022 | 666 | 1.5242 | 4.5915 |
|
| 56 |
| 1.6345 | 1.8032 | 999 | 1.4899 | 4.4364 |
|
| 57 |
| 1.4894 | 2.4043 | 1332 | 1.4634 | 4.3205 |
|
|
|
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 21 |
- Loss: 1.4442
|
| 22 |
- Perplexity: 4.2384
|
| 23 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
## Training procedure
|
| 25 |
|
| 26 |
### Training hyperparameters
|
|
|
|
| 43 |
| 1.6345 | 1.2022 | 666 | 1.5242 | 4.5915 |
|
| 44 |
| 1.6345 | 1.8032 | 999 | 1.4899 | 4.4364 |
|
| 45 |
| 1.4894 | 2.4043 | 1332 | 1.4634 | 4.3205 |
|
| 46 |
+
| 1.4894 | 3 | 1664 | 1.4442 | 4.2384 |
|
| 47 |
|
| 48 |
|
| 49 |
### Framework versions
|