Update README.md
Browse files
README.md
CHANGED
|
@@ -27,8 +27,13 @@ Hyperparameters
|
|
| 27 |
Some of the key hyperparameters used for fine-tuning:
|
| 28 |
|
| 29 |
Batch Size: 3
|
|
|
|
| 30 |
Gradient Accumulation Steps: 12
|
|
|
|
| 31 |
Optimizer: AdamW
|
|
|
|
| 32 |
Learning Rate: 1e-4
|
|
|
|
| 33 |
Epochs: 5
|
|
|
|
| 34 |
Max Sequence Length: 512
|
|
|
|
| 27 |
Some of the key hyperparameters used for fine-tuning:
|
| 28 |
|
| 29 |
Batch Size: 3
|
| 30 |
+
|
| 31 |
Gradient Accumulation Steps: 12
|
| 32 |
+
|
| 33 |
Optimizer: AdamW
|
| 34 |
+
|
| 35 |
Learning Rate: 1e-4
|
| 36 |
+
|
| 37 |
Epochs: 5
|
| 38 |
+
|
| 39 |
Max Sequence Length: 512
|