Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
datasets:
|
| 3 |
+
- benayas/snips
|
| 4 |
+
language:
|
| 5 |
+
- en
|
| 6 |
+
base_model:
|
| 7 |
+
- microsoft/deberta-v3-small
|
| 8 |
+
pipeline_tag: text-classification
|
| 9 |
+
---
|
| 10 |
+
DeBERTaV3 (small) finetuned on the SNIPS dataset for intent classification with 5 epochs:
|
| 11 |
+
|
| 12 |
+
```json
|
| 13 |
+
{
|
| 14 |
+
"epoch": 5.0,
|
| 15 |
+
"eval_accuracy": 0.9299145299145299,
|
| 16 |
+
"eval_f1": 0.9300746034490112,
|
| 17 |
+
"eval_loss": 0.3602432310581207,
|
| 18 |
+
"eval_runtime": 41.4693,
|
| 19 |
+
"eval_samples_per_second": 14.107,
|
| 20 |
+
"eval_steps_per_second": 3.545,
|
| 21 |
+
"step": 430
|
| 22 |
+
}
|
| 23 |
+
```
|