Update README.md
Browse files
README.md
CHANGED
|
@@ -82,7 +82,7 @@ The following hyperparameters were used during training:
|
|
| 82 |
- trainable params: 25,165,824 || all params: 326,801,408 || trainable%: 7.700647360735974
|
| 83 |
> The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
|
| 84 |
|
| 85 |
-
- Num examples =
|
| 86 |
- Num Epochs = 5
|
| 87 |
- Instantaneous batch size per device = 6
|
| 88 |
- Total train batch size (w. parallel, distributed & accumulation) = 144
|
|
@@ -93,7 +93,6 @@ The following hyperparameters were used during training:
|
|
| 93 |
### Framework versions
|
| 94 |
|
| 95 |
- PEFT 0.4.0
|
| 96 |
-
- PEFT 0.14.0
|
| 97 |
- Transformers 4.47.0
|
| 98 |
- Pytorch 2.5.1+cu121
|
| 99 |
- Datasets 3.3.1
|
|
|
|
| 82 |
- trainable params: 25,165,824 || all params: 326,801,408 || trainable%: 7.700647360735974
|
| 83 |
> The model is loaded in 8-bit precision. To train this model you need to add additional modules inside the model such as adapters using `peft` library and freeze the model weights. Please check the examples in https://github.com/huggingface/peft for more details.
|
| 84 |
|
| 85 |
+
- Num examples = 1_000_000
|
| 86 |
- Num Epochs = 5
|
| 87 |
- Instantaneous batch size per device = 6
|
| 88 |
- Total train batch size (w. parallel, distributed & accumulation) = 144
|
|
|
|
| 93 |
### Framework versions
|
| 94 |
|
| 95 |
- PEFT 0.4.0
|
|
|
|
| 96 |
- Transformers 4.47.0
|
| 97 |
- Pytorch 2.5.1+cu121
|
| 98 |
- Datasets 3.3.1
|