End of training
Browse files
README.md
CHANGED
@@ -58,7 +58,7 @@ The following hyperparameters were used during training:
|
|
58 |
- total_train_batch_size: 32
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: cosine
|
61 |
-
- training_steps:
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
|
|
58 |
- total_train_batch_size: 32
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: cosine
|
61 |
+
- training_steps: 1000
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|