Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
datasets:
|
| 4 |
+
- nyu-mll/glue
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
+
library_name: transformers
|
| 10 |
+
pipeline_tag: text-classification
|
| 11 |
+
---
|
| 12 |
+
# Model
|
| 13 |
+
|
| 14 |
+
`bert-base-cased` fine-tuned on QNLI.
|
| 15 |
+
|
| 16 |
+
Eval results:
|
| 17 |
+
|
| 18 |
+
```json
|
| 19 |
+
{
|
| 20 |
+
"epoch": 3.0,
|
| 21 |
+
"eval_accuracy": 0.90591250228812,
|
| 22 |
+
"eval_loss": 0.32652467489242554,
|
| 23 |
+
"eval_runtime": 10.899,
|
| 24 |
+
"eval_samples": 5463,
|
| 25 |
+
"eval_samples_per_second": 501.238,
|
| 26 |
+
"eval_steps_per_second": 62.666
|
| 27 |
+
}
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
Train results
|
| 31 |
+
|
| 32 |
+
```json
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.0,
|
| 35 |
+
"train_loss": 0.21169122040720828,
|
| 36 |
+
"train_runtime": 1639.2307,
|
| 37 |
+
"train_samples": 104743,
|
| 38 |
+
"train_samples_per_second": 191.693,
|
| 39 |
+
"train_steps_per_second": 5.992
|
| 40 |
+
}
|
| 41 |
+
```
|