Update README.md
Browse files
README.md
CHANGED
@@ -65,7 +65,7 @@ The following hyperparameters were used during training:
|
|
65 |
- train_batch_size: 32
|
66 |
- eval_batch_size: 64
|
67 |
- seed: 1270
|
68 |
-
- optimizer:
|
69 |
- lr_scheduler_type: linear
|
70 |
- lr_scheduler_warmup_steps: 150
|
71 |
- num_epochs: 1
|
|
|
65 |
- train_batch_size: 32
|
66 |
- eval_batch_size: 64
|
67 |
- seed: 1270
|
68 |
+
- optimizer: AdamW with betas=(0.9,0.999) and epsilon=1e-08
|
69 |
- lr_scheduler_type: linear
|
70 |
- lr_scheduler_warmup_steps: 150
|
71 |
- num_epochs: 1
|