Update README.md
Browse files
README.md
CHANGED
@@ -116,14 +116,14 @@ Each hypothesis was constructed using the following candidate labels:
|
|
116 |
|
117 |
### Training Hyperparameters
|
118 |
|
119 |
-
-Batch Size: 128
|
120 |
-
-Learning Rate: 2e-5
|
121 |
-
-Epochs: 3
|
122 |
-
-Label Smoothing Factor: 0.1
|
123 |
-
-Optimizer: AdamW
|
124 |
-
-Scheduler: Linear with warmup
|
125 |
-
-Loss Function: Weighted cross-entropy to address class imbalance.
|
126 |
-
|
127 |
|
128 |
## Evaluation
|
129 |
|
|
|
116 |
|
117 |
### Training Hyperparameters
|
118 |
|
119 |
+
- Batch Size: 128
|
120 |
+
- Learning Rate: 2e-5
|
121 |
+
- Epochs: 3
|
122 |
+
- Label Smoothing Factor: 0.1
|
123 |
+
- Optimizer: AdamW
|
124 |
+
- Scheduler: Linear with warmup
|
125 |
+
- Loss Function: Weighted cross-entropy to address class imbalance.
|
126 |
+
- ...
|
127 |
|
128 |
## Evaluation
|
129 |
|