Update README.md
Browse files
README.md
CHANGED
|
@@ -56,9 +56,6 @@ num_epochs: 40
|
|
| 56 |
|
| 57 |
Accuracy (Eval dataset and predict) for a sample of 2000: 80.70%
|
| 58 |
|
| 59 |
-
num_epochs: 100
|
| 60 |
-
|
| 61 |
-
Accuracy (Eval dataset and predict) for a sample of 2000: 80%
|
| 62 |
|
| 63 |
## Training procedure
|
| 64 |
|
|
@@ -74,7 +71,7 @@ The following hyperparameters were used during training:
|
|
| 74 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 75 |
- lr_scheduler_type: constant
|
| 76 |
- lr_scheduler_warmup_ratio: 0.03
|
| 77 |
-
- num_epochs:
|
| 78 |
|
| 79 |
### Training results
|
| 80 |
|
|
|
|
| 56 |
|
| 57 |
Accuracy (Eval dataset and predict) for a sample of 2000: 80.70%
|
| 58 |
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
## Training procedure
|
| 61 |
|
|
|
|
| 71 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 72 |
- lr_scheduler_type: constant
|
| 73 |
- lr_scheduler_warmup_ratio: 0.03
|
| 74 |
+
- num_epochs: 40
|
| 75 |
|
| 76 |
### Training results
|
| 77 |
|