Commit
·
c05b8fe
1
Parent(s):
7b2a769
Update README.md
Browse files
README.md
CHANGED
|
@@ -40,6 +40,7 @@ The dataset used to train this model combines two main sources of data: the [`sy
|
|
| 40 |
|
| 41 |
- **Size:** 124,441,344 total parameters
|
| 42 |
- **Dataset:** [Instruct-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/fine-tuning-instruct-aira)
|
|
|
|
| 43 |
- **Number of Epochs:** 5
|
| 44 |
- **Batch size:** 32
|
| 45 |
- **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
|
|
|
|
| 40 |
|
| 41 |
- **Size:** 124,441,344 total parameters
|
| 42 |
- **Dataset:** [Instruct-Aira Dataset](https://huggingface.co/datasets/nicholasKluge/fine-tuning-instruct-aira)
|
| 43 |
+
- **Language:** English
|
| 44 |
- **Number of Epochs:** 5
|
| 45 |
- **Batch size:** 32
|
| 46 |
- **Optimizer:** `torch.optim.AdamW` (warmup_steps = 1e2, learning_rate = 5e-4, epsilon = 1e-8)
|