Update README.md
Browse files
README.md
CHANGED
|
@@ -36,7 +36,8 @@ This model is a fine-tuned version of **Qwen 2.5-14B**, trained on QwQ 32B Previ
|
|
| 36 |
- Gradient Accumulation Steps: 2 (Effective Batch Size: 16)
|
| 37 |
- Warm-Up Steps: 5
|
| 38 |
- Weight Decay: 0.01
|
| 39 |
-
- **Training Steps**: 500 steps
|
|
|
|
| 40 |
|
| 41 |
---
|
| 42 |
|
|
|
|
| 36 |
- Gradient Accumulation Steps: 2 (Effective Batch Size: 16)
|
| 37 |
- Warm-Up Steps: 5
|
| 38 |
- Weight Decay: 0.01
|
| 39 |
+
- **Training Steps**: 500 steps
|
| 40 |
+
- **Hardware Information**: A100-80GB
|
| 41 |
|
| 42 |
---
|
| 43 |
|