Update README.md
Browse files
README.md
CHANGED
|
@@ -36,13 +36,15 @@ This work investigates two subtasks in temporal reasoning: 1. Date Arithmetic (d
|
|
| 36 |
|
| 37 |
40,000 synthetic samples
|
| 38 |
|
| 39 |
-
[More Information Needed]
|
| 40 |
-
|
| 41 |
### Training Procedure
|
| 42 |
|
| 43 |
#### Training Hyperparameters
|
| 44 |
|
| 45 |
-
- **
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
|
| 47 |
## Evaluation
|
| 48 |
|
|
|
|
| 36 |
|
| 37 |
40,000 synthetic samples
|
| 38 |
|
|
|
|
|
|
|
| 39 |
### Training Procedure
|
| 40 |
|
| 41 |
#### Training Hyperparameters
|
| 42 |
|
| 43 |
+
- **Precision:** BF16
|
| 44 |
+
- **Learning rate:** 5.0e-5
|
| 45 |
+
- **Batch size per device:** 16
|
| 46 |
+
- **Epoch:** 5
|
| 47 |
+
- **Cutoff length:** 2048
|
| 48 |
|
| 49 |
## Evaluation
|
| 50 |
|