Update README.md
Browse filescorrected Axolotl Version
README.md
CHANGED
|
@@ -30,7 +30,6 @@ The 25% layer selection ensures minimal computational overhead for fine-tuning.
|
|
| 30 |
|
| 31 |
## Training:
|
| 32 |
- Trained on **2x A40s (48GB VRAM each)** for over 1 hour using the **Axolotl**.
|
| 33 |
-
- Fine-tuning aimed to optimize the balance between model performance and resource efficiency, demonstrating how targeted spectrum fine-tuning can deliver substantial improvements without the need for full-scale model adjustments.
|
| 34 |
|
| 35 |
|
| 36 |
### Training hyperparameters
|
|
@@ -58,7 +57,7 @@ The following hyperparameters were used during training:
|
|
| 58 |
|
| 59 |
### Framework versions
|
| 60 |
|
| 61 |
-
- Axolotl 0.4.
|
| 62 |
- Transformers 4.44.2
|
| 63 |
- Pytorch 2.4.0+cu121
|
| 64 |
- Datasets 2.20.0
|
|
|
|
| 30 |
|
| 31 |
## Training:
|
| 32 |
- Trained on **2x A40s (48GB VRAM each)** for over 1 hour using the **Axolotl**.
|
|
|
|
| 33 |
|
| 34 |
|
| 35 |
### Training hyperparameters
|
|
|
|
| 57 |
|
| 58 |
### Framework versions
|
| 59 |
|
| 60 |
+
- Axolotl 0.4.1
|
| 61 |
- Transformers 4.44.2
|
| 62 |
- Pytorch 2.4.0+cu121
|
| 63 |
- Datasets 2.20.0
|