update model card README.md
Browse files
README.md
CHANGED
@@ -31,11 +31,11 @@ More information needed
|
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
- learning_rate: 5e-05
|
34 |
-
- train_batch_size:
|
35 |
-
- eval_batch_size:
|
36 |
- seed: 42
|
37 |
- gradient_accumulation_steps: 16
|
38 |
-
- total_train_batch_size:
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
- lr_scheduler_warmup_steps: 500
|
@@ -48,6 +48,6 @@ The following hyperparameters were used during training:
|
|
48 |
### Framework versions
|
49 |
|
50 |
- Transformers 4.20.1
|
51 |
-
- Pytorch 1.
|
52 |
- Datasets 2.4.0
|
53 |
- Tokenizers 0.12.1
|
|
|
31 |
|
32 |
The following hyperparameters were used during training:
|
33 |
- learning_rate: 5e-05
|
34 |
+
- train_batch_size: 3
|
35 |
+
- eval_batch_size: 3
|
36 |
- seed: 42
|
37 |
- gradient_accumulation_steps: 16
|
38 |
+
- total_train_batch_size: 48
|
39 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
40 |
- lr_scheduler_type: linear
|
41 |
- lr_scheduler_warmup_steps: 500
|
|
|
48 |
### Framework versions
|
49 |
|
50 |
- Transformers 4.20.1
|
51 |
+
- Pytorch 1.12.1+cu116
|
52 |
- Datasets 2.4.0
|
53 |
- Tokenizers 0.12.1
|