Commit
•
36e22a9
1
Parent(s):
749bba9
Update README.md
Browse files
README.md
CHANGED
|
@@ -55,11 +55,12 @@ training_args = TrainingArguments(
|
|
| 55 |
)
|
| 56 |
```
|
| 57 |
### Eval results
|
| 58 |
-
The model was evaluated using the binary test sets for MultiNLI and ANLI and the dev set for Fever-NLI. The metric used is accuracy.
|
| 59 |
|
| 60 |
mnli-m | mnli-mm | fever-nli | anli-all | anli-r3
|
| 61 |
---------|----------|---------|----------|----------
|
| 62 |
-
|
|
|
|
| 63 |
|
| 64 |
## Limitations and bias
|
| 65 |
Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.
|
|
|
|
| 55 |
)
|
| 56 |
```
|
| 57 |
### Eval results
|
| 58 |
+
The model was evaluated using the binary test sets for MultiNLI and ANLI and the binary dev set for Fever-NLI. The metric used is accuracy.
|
| 59 |
|
| 60 |
mnli-m | mnli-mm | fever-nli | anli-all | anli-r3
|
| 61 |
---------|----------|---------|----------|----------
|
| 62 |
+
0.927 | 0.921 | 0.892 | 0.684 | 0.673
|
| 63 |
+
|
| 64 |
|
| 65 |
## Limitations and bias
|
| 66 |
Please consult the original DeBERTa paper and literature on different NLI datasets for potential biases.
|