Commit
•
f2c62d6
1
Parent(s):
c0f12d0
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,10 +30,12 @@ More information needed
|
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
-
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
|
|
|
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
|
|
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
+
The training and evaluation data come straight from the `train` and `validation` splits in the clinc_oos dataset, respectively; and tokenized using the `distilbert-base-uncased` tokenization.
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
|
| 37 |
+
Please see page 224 in Chapter 8: Making Transformers Efficient in Production, Natural Language Processing with Transformers, May 2022.
|
| 38 |
+
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|