End of training
Browse files
README.md
CHANGED
|
@@ -33,16 +33,17 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
-
- train_batch_size:
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
-
- gradient_accumulation_steps:
|
| 41 |
- total_train_batch_size: 32
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
-
-
|
| 45 |
-
-
|
|
|
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
|
@@ -52,6 +53,6 @@ The following hyperparameters were used during training:
|
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- Transformers 4.51.3
|
| 55 |
-
- Pytorch 2.7.
|
| 56 |
-
- Datasets
|
| 57 |
-
- Tokenizers 0.21.
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 4
|
| 41 |
- total_train_batch_size: 32
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
+
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 60
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
|
|
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.51.3
|
| 56 |
+
- Pytorch 2.7.1+cu118
|
| 57 |
+
- Datasets 4.0.0
|
| 58 |
+
- Tokenizers 0.21.2
|