Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,7 @@ General Fine-tuning informations:
|
|
| 26 |
- Quantization type: normal float 4-bit
|
| 27 |
- QLoRA compute type: brain float 16-bit
|
| 28 |
- Total time: 1 hour 23 minutes
|
|
|
|
| 29 |
|
| 30 |
Some of the Hyperparameters were determined using Hyperparameter optimization with Ray Tune. The corresponding result for the best trial were:
|
| 31 |
|
|
|
|
| 26 |
- Quantization type: normal float 4-bit
|
| 27 |
- QLoRA compute type: brain float 16-bit
|
| 28 |
- Total time: 1 hour 23 minutes
|
| 29 |
+
- Accelerator: Nvidia L4 Tensor Core GPU
|
| 30 |
|
| 31 |
Some of the Hyperparameters were determined using Hyperparameter optimization with Ray Tune. The corresponding result for the best trial were:
|
| 32 |
|