reinforcementlucia
commited on
Commit
•
92ca566
1
Parent(s):
8f72ee3
Update README.md
Browse files
README.md
CHANGED
@@ -35,15 +35,13 @@ Trained on 9k rows of data.
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
-
- train_batch_size:
|
39 |
-
- eval_batch_size: 8
|
40 |
- seed: 42
|
41 |
-
- gradient_accumulation_steps:
|
42 |
-
- total_train_batch_size: 16
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
- lr_scheduler_warmup_steps: 0.1
|
46 |
-
- num_epochs:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 2e-05
|
38 |
+
- train_batch_size: 1
|
|
|
39 |
- seed: 42
|
40 |
+
- gradient_accumulation_steps: 2
|
|
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
- lr_scheduler_warmup_steps: 0.1
|
44 |
+
- num_epochs: 4
|
45 |
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|