Update README.md
Browse files
README.md
CHANGED
|
@@ -97,7 +97,7 @@ Trained on [GUIrilla-Task](https://huggingface.co/datasets/GUIrilla/GUIrilla-Tas
|
|
| 97 |
## Training Procedure
|
| 98 |
|
| 99 |
* 2 epochs LoRA fine-tuning on 2 × H100 80 GB.
|
| 100 |
-
* Optimiser – AdamW (β₁ = 0.9, β₂ = 0.95), LR = 2 e-5 with cosine decay and 0.05 warm up
|
| 101 |
|
| 102 |
---
|
| 103 |
|
|
|
|
| 97 |
## Training Procedure
|
| 98 |
|
| 99 |
* 2 epochs LoRA fine-tuning on 2 × H100 80 GB.
|
| 100 |
+
* Optimiser – AdamW (β₁ = 0.9, β₂ = 0.95), LR = 2 e-5 with cosine decay and 0.05 warm up ratio.
|
| 101 |
|
| 102 |
---
|
| 103 |
|