Update README.md
Browse files
README.md
CHANGED
|
@@ -1,4 +1,3 @@
|
|
| 1 |
-
|
| 2 |
---
|
| 3 |
language: en
|
| 4 |
license: mit
|
|
@@ -7,6 +6,9 @@ tags:
|
|
| 7 |
- gpt2
|
| 8 |
- math
|
| 9 |
- fine-tuned
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
# GPT-2.5-Math
|
|
@@ -26,4 +28,4 @@ The model is trained for mathematical reasoning. While it is a 0.2B parameter mo
|
|
| 26 |
- **Optimizer:** AdamW
|
| 27 |
- **Precision:** Mixed Precision (torch.amp)
|
| 28 |
- **Epochs:** 3
|
| 29 |
-
- **Learning Rate:** 5e-5
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
language: en
|
| 3 |
license: mit
|
|
|
|
| 6 |
- gpt2
|
| 7 |
- math
|
| 8 |
- fine-tuned
|
| 9 |
+
- Pro
|
| 10 |
+
- Math
|
| 11 |
+
pipeline_tag: text-generation
|
| 12 |
---
|
| 13 |
|
| 14 |
# GPT-2.5-Math
|
|
|
|
| 28 |
- **Optimizer:** AdamW
|
| 29 |
- **Precision:** Mixed Precision (torch.amp)
|
| 30 |
- **Epochs:** 3
|
| 31 |
+
- **Learning Rate:** 5e-5
|