Commit
·
311a6a1
1
Parent(s):
332e209
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,26 +35,7 @@ More information needed
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
| 38 |
-
### Training hyperparameters
|
| 39 |
|
| 40 |
-
The following hyperparameters were used during training:
|
| 41 |
-
- learning_rate: 2e-05
|
| 42 |
-
- train_batch_size: 5
|
| 43 |
-
- eval_batch_size: 5
|
| 44 |
-
- seed: 42
|
| 45 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
-
- lr_scheduler_type: linear
|
| 47 |
-
- num_epochs: 5
|
| 48 |
-
|
| 49 |
-
### Training results
|
| 50 |
-
|
| 51 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|
| 52 |
-
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
|
| 53 |
-
| 0.56 | 1.0 | 24 | 0.4072 | 0.8214 | 0.8248 |
|
| 54 |
-
| 0.3144 | 2.0 | 48 | 0.2016 | 0.9286 | 0.9275 |
|
| 55 |
-
| 0.1469 | 3.0 | 72 | 0.1103 | 0.9643 | 0.9643 |
|
| 56 |
-
| 0.0986 | 4.0 | 96 | 0.0963 | 0.9821 | 0.9822 |
|
| 57 |
-
| 0.0768 | 5.0 | 120 | 0.0735 | 0.9643 | 0.9643 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 35 |
|
| 36 |
## Training procedure
|
| 37 |
|
|
|
|
| 38 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
|
| 40 |
|
| 41 |
### Framework versions
|