Commit
•
d2e406b
1
Parent(s):
49f47d3
End of training
Browse files
README.md
CHANGED
|
@@ -36,13 +36,14 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0002
|
| 39 |
-
- train_batch_size:
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
-
- training_steps:
|
|
|
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
@@ -52,6 +53,6 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
- PEFT 0.9.0
|
| 54 |
- Transformers 4.38.2
|
| 55 |
-
- Pytorch 2.1
|
| 56 |
- Datasets 2.18.0
|
| 57 |
- Tokenizers 0.15.2
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.0002
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
- eval_batch_size: 8
|
| 41 |
- seed: 42
|
| 42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_ratio: 0.03
|
| 45 |
+
- training_steps: 100
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
|
|
|
| 53 |
|
| 54 |
- PEFT 0.9.0
|
| 55 |
- Transformers 4.38.2
|
| 56 |
+
- Pytorch 2.2.1+cu121
|
| 57 |
- Datasets 2.18.0
|
| 58 |
- Tokenizers 0.15.2
|